diff options
Diffstat (limited to 'tools/testing')
32 files changed, 493 insertions, 112 deletions
diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c index 124bc883365e..cdd7a45c045d 100644 --- a/tools/testing/selftests/arm64/fp/fp-ptrace.c +++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c @@ -1187,7 +1187,7 @@ static void sve_write_sve(pid_t child, struct test_config *config) if (!vl) return; - iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_SVE); iov.iov_base = malloc(iov.iov_len); if (!iov.iov_base) { ksft_print_msg("Failed allocating %lu byte SVE write buffer\n", @@ -1234,8 +1234,7 @@ static void sve_write_fpsimd(pid_t child, struct test_config *config) if (!vl) return; - iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, - SVE_PT_REGS_FPSIMD); + iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_FPSIMD); iov.iov_base = malloc(iov.iov_len); if (!iov.iov_base) { ksft_print_msg("Failed allocating %lu byte SVE write buffer\n", diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py index cd23af875317..3e3a89a34afe 100755 --- a/tools/testing/selftests/drivers/net/hw/csum.py +++ b/tools/testing/selftests/drivers/net/hw/csum.py @@ -17,7 +17,7 @@ def test_receive(cfg, ipver="6", extra_args=None): ip_args = f"-{ipver} -S {cfg.remote_addr_v[ipver]} -D {cfg.addr_v[ipver]}" rx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -n 100 {ip_args} -r 1 -R {extra_args}" - tx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -n 100 {ip_args} -r 1 -T {extra_args}" + tx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -n 100 {ip_args} -r 1 -T {extra_args}" with bkg(rx_cmd, exit_wait=True): wait_port_listen(34000, proto="udp") @@ -37,7 +37,7 @@ def test_transmit(cfg, ipver="6", extra_args=None): if extra_args != "-U -Z": extra_args += " -r 1" - rx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -L 1 -n 100 {ip_args} -R {extra_args}" + rx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -L 1 -n 100 {ip_args} -R {extra_args}" tx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -L 1 -n 100 {ip_args} -T {extra_args}" with bkg(rx_cmd, host=cfg.remote, exit_wait=True): diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 2925e47db995..8516e8434bc4 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -751,7 +751,7 @@ for (; _metadata->trigger; _metadata->trigger = \ __bail(_assert, _metadata)) -#define is_signed_type(var) (!!(((__typeof__(var))(-1)) < (__typeof__(var))1)) +#define is_signed_var(var) (!!(((__typeof__(var))(-1)) < (__typeof__(var))1)) #define __EXPECT(_expected, _expected_str, _seen, _seen_str, _t, _assert) do { \ /* Avoid multiple evaluation of the cases */ \ @@ -759,7 +759,7 @@ __typeof__(_seen) __seen = (_seen); \ if (!(__exp _t __seen)) { \ /* Report with actual signedness to avoid weird output. */ \ - switch (is_signed_type(__exp) * 2 + is_signed_type(__seen)) { \ + switch (is_signed_var(__exp) * 2 + is_signed_var(__seen)) { \ case 0: { \ uintmax_t __exp_print = (uintmax_t)__exp; \ uintmax_t __seen_print = (uintmax_t)__seen; \ diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index f6fe7a07a0a2..41b40c676d7f 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -169,6 +169,7 @@ TEST_GEN_PROGS_arm64 += arm64/vgic_irq TEST_GEN_PROGS_arm64 += arm64/vgic_lpi_stress TEST_GEN_PROGS_arm64 += arm64/vpmu_counter_access TEST_GEN_PROGS_arm64 += arm64/no-vgic-v3 +TEST_GEN_PROGS_arm64 += arm64/kvm-uuid TEST_GEN_PROGS_arm64 += access_tracking_perf_test TEST_GEN_PROGS_arm64 += arch_timer TEST_GEN_PROGS_arm64 += coalesced_io_test diff --git a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c index cef8f7323ceb..713005b6f508 100644 --- a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c @@ -146,7 +146,7 @@ static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu) val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); - el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val); + el0 = FIELD_GET(ID_AA64PFR0_EL1_EL0, val); return el0 == ID_AA64PFR0_EL1_EL0_IMP; } diff --git a/tools/testing/selftests/kvm/arm64/debug-exceptions.c b/tools/testing/selftests/kvm/arm64/debug-exceptions.c index e34963956fbc..1d431de8729c 100644 --- a/tools/testing/selftests/kvm/arm64/debug-exceptions.c +++ b/tools/testing/selftests/kvm/arm64/debug-exceptions.c @@ -116,12 +116,12 @@ static void reset_debug_state(void) /* Reset all bcr/bvr/wcr/wvr registers */ dfr0 = read_sysreg(id_aa64dfr0_el1); - brps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_BRPs), dfr0); + brps = FIELD_GET(ID_AA64DFR0_EL1_BRPs, dfr0); for (i = 0; i <= brps; i++) { write_dbgbcr(i, 0); write_dbgbvr(i, 0); } - wrps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_WRPs), dfr0); + wrps = FIELD_GET(ID_AA64DFR0_EL1_WRPs, dfr0); for (i = 0; i <= wrps; i++) { write_dbgwcr(i, 0); write_dbgwvr(i, 0); @@ -418,7 +418,7 @@ static void guest_code_ss(int test_cnt) static int debug_version(uint64_t id_aa64dfr0) { - return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer), id_aa64dfr0); + return FIELD_GET(ID_AA64DFR0_EL1_DebugVer, id_aa64dfr0); } static void test_guest_debug_exceptions(uint8_t bpn, uint8_t wpn, uint8_t ctx_bpn) @@ -539,14 +539,14 @@ void test_guest_debug_exceptions_all(uint64_t aa64dfr0) int b, w, c; /* Number of breakpoints */ - brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_BRPs), aa64dfr0) + 1; + brp_num = FIELD_GET(ID_AA64DFR0_EL1_BRPs, aa64dfr0) + 1; __TEST_REQUIRE(brp_num >= 2, "At least two breakpoints are required"); /* Number of watchpoints */ - wrp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_WRPs), aa64dfr0) + 1; + wrp_num = FIELD_GET(ID_AA64DFR0_EL1_WRPs, aa64dfr0) + 1; /* Number of context aware breakpoints */ - ctx_brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_CTX_CMPs), aa64dfr0) + 1; + ctx_brp_num = FIELD_GET(ID_AA64DFR0_EL1_CTX_CMPs, aa64dfr0) + 1; pr_debug("%s brp_num:%d, wrp_num:%d, ctx_brp_num:%d\n", __func__, brp_num, wrp_num, ctx_brp_num); diff --git a/tools/testing/selftests/kvm/arm64/kvm-uuid.c b/tools/testing/selftests/kvm/arm64/kvm-uuid.c new file mode 100644 index 000000000000..af9581b860f1 --- /dev/null +++ b/tools/testing/selftests/kvm/arm64/kvm-uuid.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Check that nobody has tampered with KVM's UID + +#include <errno.h> +#include <linux/arm-smccc.h> +#include <asm/kvm.h> +#include <kvm_util.h> + +#include "processor.h" + +/* + * Do NOT redefine these constants, or try to replace them with some + * "common" version. They are hardcoded here to detect any potential + * breakage happening in the rest of the kernel. + * + * KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74 + */ +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 0xb66fb428U +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 0xe911c52eU +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2 0x564bcaa9U +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3 0x743a004dU + +static void guest_code(void) +{ + struct arm_smccc_res res = {}; + + smccc_hvc(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID, 0, 0, 0, 0, 0, 0, 0, &res); + + __GUEST_ASSERT(res.a0 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 && + res.a1 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 && + res.a2 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2 && + res.a3 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3, + "Unexpected KVM-specific UID %lx %lx %lx %lx\n", res.a0, res.a1, res.a2, res.a3); + GUEST_DONE(); +} + +int main (int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + bool guest_done = false; + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + while (!guest_done) { + vcpu_run(vcpu); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + break; + case UCALL_DONE: + guest_done = true; + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + case UCALL_PRINTF: + printf("%s", uc.buffer); + break; + default: + TEST_FAIL("Unexpected guest exit"); + } + } + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c index ebd70430c89d..f222538e6084 100644 --- a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c +++ b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c @@ -54,7 +54,7 @@ static void guest_code(void) * Check that we advertise that ID_AA64PFR0_EL1.GIC == 0, having * hidden the feature at runtime without any other userspace action. */ - __GUEST_ASSERT(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC), + __GUEST_ASSERT(FIELD_GET(ID_AA64PFR0_EL1_GIC, read_sysreg(id_aa64pfr0_el1)) == 0, "GICv3 wrongly advertised"); @@ -165,7 +165,7 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, NULL); pfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); - __TEST_REQUIRE(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC), pfr0), + __TEST_REQUIRE(FIELD_GET(ID_AA64PFR0_EL1_GIC, pfr0), "GICv3 not supported."); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/arm64/page_fault_test.c b/tools/testing/selftests/kvm/arm64/page_fault_test.c index dc6559dad9d8..4ccbd389d133 100644 --- a/tools/testing/selftests/kvm/arm64/page_fault_test.c +++ b/tools/testing/selftests/kvm/arm64/page_fault_test.c @@ -95,14 +95,14 @@ static bool guest_check_lse(void) uint64_t isar0 = read_sysreg(id_aa64isar0_el1); uint64_t atomic; - atomic = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_ATOMIC), isar0); + atomic = FIELD_GET(ID_AA64ISAR0_EL1_ATOMIC, isar0); return atomic >= 2; } static bool guest_check_dc_zva(void) { uint64_t dczid = read_sysreg(dczid_el0); - uint64_t dzp = FIELD_GET(ARM64_FEATURE_MASK(DCZID_EL0_DZP), dczid); + uint64_t dzp = FIELD_GET(DCZID_EL0_DZP, dczid); return dzp == 0; } @@ -195,7 +195,7 @@ static bool guest_set_ha(void) uint64_t hadbs, tcr; /* Skip if HA is not supported. */ - hadbs = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HAFDBS), mmfr1); + hadbs = FIELD_GET(ID_AA64MMFR1_EL1_HAFDBS, mmfr1); if (hadbs == 0) return false; diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c index d3bf9204409c..189321e96925 100644 --- a/tools/testing/selftests/kvm/arm64/set_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c @@ -243,6 +243,7 @@ static void guest_code(void) GUEST_REG_SYNC(SYS_ID_AA64MMFR0_EL1); GUEST_REG_SYNC(SYS_ID_AA64MMFR1_EL1); GUEST_REG_SYNC(SYS_ID_AA64MMFR2_EL1); + GUEST_REG_SYNC(SYS_ID_AA64MMFR3_EL1); GUEST_REG_SYNC(SYS_ID_AA64ZFR0_EL1); GUEST_REG_SYNC(SYS_CTR_EL0); GUEST_REG_SYNC(SYS_MIDR_EL1); @@ -594,8 +595,8 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu) */ val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1)); - mte = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE), val); - mte_frac = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac), val); + mte = FIELD_GET(ID_AA64PFR1_EL1_MTE, val); + mte_frac = FIELD_GET(ID_AA64PFR1_EL1_MTE_frac, val); if (mte != ID_AA64PFR1_EL1_MTE_MTE2 || mte_frac != ID_AA64PFR1_EL1_MTE_frac_NI) { ksft_test_result_skip("MTE_ASYNC or MTE_ASYMM are supported, nothing to test\n"); @@ -612,7 +613,7 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu) } val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1)); - mte_frac = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac), val); + mte_frac = FIELD_GET(ID_AA64PFR1_EL1_MTE_frac, val); if (mte_frac == ID_AA64PFR1_EL1_MTE_frac_NI) ksft_test_result_pass("ID_AA64PFR1_EL1.MTE_frac=0 accepted and still 0xF\n"); else @@ -774,7 +775,7 @@ int main(void) /* Check for AARCH64 only system */ val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); - el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val); + el0 = FIELD_GET(ID_AA64PFR0_EL1_EL0, val); aarch64_only = (el0 == ID_AA64PFR0_EL1_EL0_IMP); ksft_print_header(); diff --git a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c index f16b3b27e32e..a0c4ab839155 100644 --- a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c +++ b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c @@ -441,7 +441,7 @@ static void create_vpmu_vm(void *guest_code) /* Make sure that PMUv3 support is indicated in the ID register */ dfr0 = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1)); - pmuver = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), dfr0); + pmuver = FIELD_GET(ID_AA64DFR0_EL1_PMUVer, dfr0); TEST_ASSERT(pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF && pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP, "Unexpected PMUVER (0x%x) on the vCPU with PMUv3", pmuver); diff --git a/tools/testing/selftests/kvm/lib/arm64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c index 9d69904cb608..eb115123d741 100644 --- a/tools/testing/selftests/kvm/lib/arm64/processor.c +++ b/tools/testing/selftests/kvm/lib/arm64/processor.c @@ -573,15 +573,15 @@ void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k, err = ioctl(vcpu_fd, KVM_GET_ONE_REG, ®); TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd)); - gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val); + gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN4, val); *ipa4k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN4_NI, ID_AA64MMFR0_EL1_TGRAN4_52_BIT); - gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val); + gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN64, val); *ipa64k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN64_NI, ID_AA64MMFR0_EL1_TGRAN64_IMP); - gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val); + gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN16, val); *ipa16k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN16_NI, ID_AA64MMFR0_EL1_TGRAN16_52_BIT); 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 05de1fc0005b..44a3f8a58806 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -439,8 +439,11 @@ 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; diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b31a71f2b372..c7e03e1d6f63 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -99,6 +99,7 @@ TEST_GEN_PROGS += bind_wildcard TEST_GEN_PROGS += bind_timewait TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh +TEST_PROGS += test_vxlan_nh.sh TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh TEST_PROGS += test_neigh.sh diff --git a/tools/testing/selftests/net/bind_bhash.c b/tools/testing/selftests/net/bind_bhash.c index 57ff67a3751e..da04b0b19b73 100644 --- a/tools/testing/selftests/net/bind_bhash.c +++ b/tools/testing/selftests/net/bind_bhash.c @@ -75,7 +75,7 @@ static void *setup(void *arg) int *array = (int *)arg; for (i = 0; i < MAX_CONNECTIONS; i++) { - sock_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr); + sock_fd = bind_socket(SO_REUSEPORT, setup_addr); if (sock_fd < 0) { ret = sock_fd; pthread_exit(&ret); @@ -103,7 +103,7 @@ int main(int argc, const char *argv[]) setup_addr = use_v6 ? setup_addr_v6 : setup_addr_v4; - listener_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr); + listener_fd = bind_socket(SO_REUSEPORT, setup_addr); if (listen(listener_fd, 100) < 0) { perror("listen failed"); return -1; diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh index 606a43a60f73..7fc6c5dbd551 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_clash.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh @@ -99,7 +99,7 @@ run_one_clash_test() local entries local cre - if ! ip netns exec "$ns" ./udpclash $daddr $dport;then + if ! ip netns exec "$ns" timeout 30 ./udpclash $daddr $dport;then echo "INFO: did not receive expected number of replies for $daddr:$dport" ip netns exec "$ctns" conntrack -S # don't fail: check if clash resolution triggered after all. diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh index 788cd56ea4a0..615fe3c6f405 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_resize.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh @@ -187,7 +187,7 @@ ct_udpclash() [ -x udpclash ] || return while [ $now -lt $end ]; do - ip netns exec "$ns" ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1 + ip netns exec "$ns" timeout 30 ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1 now=$(date +%s) done @@ -277,6 +277,7 @@ check_taint() insert_flood() { local n="$1" + local timeout="$2" local r=0 r=$((RANDOM%$insert_count)) @@ -302,7 +303,7 @@ test_floodresize_all() read tainted_then < /proc/sys/kernel/tainted for n in "$nsclient1" "$nsclient2";do - insert_flood "$n" & + insert_flood "$n" "$timeout" & done # resize table constantly while flood/insert/dump/flushs diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh index a4ee5496f2a1..45832df98295 100755 --- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh @@ -20,6 +20,7 @@ ret=0 SOCAT_TIMEOUT=60 nsin="" +nsin_small="" ns1out="" ns2out="" @@ -36,7 +37,7 @@ cleanup() { cleanup_all_ns - rm -f "$nsin" "$ns1out" "$ns2out" + rm -f "$nsin" "$nsin_small" "$ns1out" "$ns2out" [ "$log_netns" -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns="$log_netns" } @@ -72,6 +73,7 @@ lmtu=1500 rmtu=2000 filesize=$((2 * 1024 * 1024)) +filesize_small=$((filesize / 16)) usage(){ echo "nft_flowtable.sh [OPTIONS]" @@ -89,7 +91,10 @@ do o) omtu=$OPTARG;; l) lmtu=$OPTARG;; r) rmtu=$OPTARG;; - s) filesize=$OPTARG;; + s) + filesize=$OPTARG + filesize_small=$((OPTARG / 16)) + ;; *) usage;; esac done @@ -215,6 +220,7 @@ if ! ip netns exec "$ns2" ping -c 1 -q 10.0.1.99 > /dev/null; then fi nsin=$(mktemp) +nsin_small=$(mktemp) ns1out=$(mktemp) ns2out=$(mktemp) @@ -265,6 +271,7 @@ check_counters() check_dscp() { local what=$1 + local pmtud="$2" local ok=1 local counter @@ -277,37 +284,39 @@ check_dscp() local pc4z=${counter%*bytes*} local pc4z=${pc4z#*packets} + local failmsg="FAIL: pmtu $pmtu: $what counters do not match, expected" + case "$what" in "dscp_none") if [ "$pc4" -gt 0 ] || [ "$pc4z" -eq 0 ]; then - echo "FAIL: dscp counters do not match, expected dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2 + echo "$failmsg dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2 ret=1 ok=0 fi ;; "dscp_fwd") if [ "$pc4" -eq 0 ] || [ "$pc4z" -eq 0 ]; then - echo "FAIL: dscp counters do not match, expected dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2 + echo "$failmsg dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2 ret=1 ok=0 fi ;; "dscp_ingress") if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then - echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 + echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 ret=1 ok=0 fi ;; "dscp_egress") if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then - echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 + echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 ret=1 ok=0 fi ;; *) - echo "FAIL: Unknown DSCP check" 1>&2 + echo "$failmsg: Unknown DSCP check" 1>&2 ret=1 ok=0 esac @@ -319,9 +328,9 @@ check_dscp() check_transfer() { - in=$1 - out=$2 - what=$3 + local in=$1 + local out=$2 + local what=$3 if ! cmp "$in" "$out" > /dev/null 2>&1; then echo "FAIL: file mismatch for $what" 1>&2 @@ -342,25 +351,39 @@ test_tcp_forwarding_ip() { local nsa=$1 local nsb=$2 - local dstip=$3 - local dstport=$4 + local pmtu=$3 + local dstip=$4 + local dstport=$5 local lret=0 + local socatc + local socatl + local infile="$nsin" + + if [ $pmtu -eq 0 ]; then + infile="$nsin_small" + fi - timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$nsin" > "$ns2out" & + timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$infile" > "$ns2out" & lpid=$! busywait 1000 listener_ready - timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$nsin" > "$ns1out" + timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$infile" > "$ns1out" + socatc=$? wait $lpid + socatl=$? - if ! check_transfer "$nsin" "$ns2out" "ns1 -> ns2"; then + if [ $socatl -ne 0 ] || [ $socatc -ne 0 ];then + rc=1 + fi + + if ! check_transfer "$infile" "$ns2out" "ns1 -> ns2"; then lret=1 ret=1 fi - if ! check_transfer "$nsin" "$ns1out" "ns1 <- ns2"; then + if ! check_transfer "$infile" "$ns1out" "ns1 <- ns2"; then lret=1 ret=1 fi @@ -370,14 +393,16 @@ test_tcp_forwarding_ip() test_tcp_forwarding() { - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 + local pmtu="$3" + + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 return $? } test_tcp_forwarding_set_dscp() { - check_dscp "dscp_none" + local pmtu="$3" ip netns exec "$nsr1" nft -f - <<EOF table netdev dscpmangle { @@ -388,8 +413,8 @@ table netdev dscpmangle { } EOF if [ $? -eq 0 ]; then - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 - check_dscp "dscp_ingress" + test_tcp_forwarding_ip "$1" "$2" "$3" 10.0.2.99 12345 + check_dscp "dscp_ingress" "$pmtu" ip netns exec "$nsr1" nft delete table netdev dscpmangle else @@ -405,10 +430,10 @@ table netdev dscpmangle { } EOF if [ $? -eq 0 ]; then - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 - check_dscp "dscp_egress" + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 + check_dscp "dscp_egress" "$pmtu" - ip netns exec "$nsr1" nft flush table netdev dscpmangle + ip netns exec "$nsr1" nft delete table netdev dscpmangle else echo "SKIP: Could not load netdev:egress for veth1" fi @@ -416,48 +441,53 @@ fi # partial. If flowtable really works, then both dscp-is-0 and dscp-is-cs3 # counters should have seen packets (before and after ft offload kicks in). ip netns exec "$nsr1" nft -a insert rule inet filter forward ip dscp set cs3 - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 - check_dscp "dscp_fwd" + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 + check_dscp "dscp_fwd" "$pmtu" } test_tcp_forwarding_nat() { + local nsa="$1" + local nsb="$2" + local pmtu="$3" + local what="$4" local lret - local pmtu - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 - lret=$? + [ "$pmtu" -eq 0 ] && what="$what (pmtu disabled)" - pmtu=$3 - what=$4 + test_tcp_forwarding_ip "$nsa" "$nsb" "$pmtu" 10.0.2.99 12345 + lret=$? if [ "$lret" -eq 0 ] ; then if [ "$pmtu" -eq 1 ] ;then - check_counters "flow offload for ns1/ns2 with masquerade and pmtu discovery $what" + check_counters "flow offload for ns1/ns2 with masquerade $what" else echo "PASS: flow offload for ns1/ns2 with masquerade $what" fi - test_tcp_forwarding_ip "$1" "$2" 10.6.6.6 1666 + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.6.6.6 1666 lret=$? if [ "$pmtu" -eq 1 ] ;then - check_counters "flow offload for ns1/ns2 with dnat and pmtu discovery $what" + check_counters "flow offload for ns1/ns2 with dnat $what" elif [ "$lret" -eq 0 ] ; then echo "PASS: flow offload for ns1/ns2 with dnat $what" fi + else + echo "FAIL: flow offload for ns1/ns2 with dnat $what" fi return $lret } make_file "$nsin" "$filesize" +make_file "$nsin_small" "$filesize_small" # First test: # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed. # Due to MTU mismatch in both directions, all packets (except small packets like pure # acks) have to be handled by normal forwarding path. Therefore, packet counters # are not checked. -if test_tcp_forwarding "$ns1" "$ns2"; then +if test_tcp_forwarding "$ns1" "$ns2" 0; then echo "PASS: flow offloaded for ns1/ns2" else echo "FAIL: flow offload for ns1/ns2:" 1>&2 @@ -489,8 +519,9 @@ table ip nat { } EOF +check_dscp "dscp_none" "0" if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 0 ""; then - echo "FAIL: flow offload for ns1/ns2 with dscp update" 1>&2 + echo "FAIL: flow offload for ns1/ns2 with dscp update and no pmtu discovery" 1>&2 exit 0 fi @@ -513,6 +544,14 @@ ip netns exec "$ns2" sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null # For earlier tests (large mtus), packets cannot be handled via flowtable # (except pure acks and other small packets). ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null +ip netns exec "$ns2" nft reset counters table inet filter >/dev/null + +if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 1 ""; then + echo "FAIL: flow offload for ns1/ns2 with dscp update and pmtu discovery" 1>&2 + exit 0 +fi + +ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 ""; then echo "FAIL: flow offload for ns1/ns2 with NAT and pmtu discovery" 1>&2 @@ -644,7 +683,7 @@ ip -net "$ns2" route del 192.168.10.1 via 10.0.2.1 ip -net "$ns2" route add default via 10.0.2.1 ip -net "$ns2" route add default via dead:2::1 -if test_tcp_forwarding "$ns1" "$ns2"; then +if test_tcp_forwarding "$ns1" "$ns2" 1; then check_counters "ipsec tunnel mode for ns1/ns2" else echo "FAIL: ipsec tunnel mode for ns1/ns2" @@ -668,7 +707,7 @@ if [ "$1" = "" ]; then fi echo "re-run with random mtus and file size: -o $o -l $l -r $r -s $filesize" - $0 -o "$o" -l "$l" -r "$r" -s "$filesize" + $0 -o "$o" -l "$l" -r "$r" -s "$filesize" || ret=1 fi exit $ret diff --git a/tools/testing/selftests/net/netfilter/udpclash.c b/tools/testing/selftests/net/netfilter/udpclash.c index 85c7b906ad08..79de163d61ab 100644 --- a/tools/testing/selftests/net/netfilter/udpclash.c +++ b/tools/testing/selftests/net/netfilter/udpclash.c @@ -29,7 +29,7 @@ struct thread_args { int sockfd; }; -static int wait = 1; +static volatile int wait = 1; static void *thread_main(void *varg) { diff --git a/tools/testing/selftests/net/test_vxlan_nh.sh b/tools/testing/selftests/net/test_vxlan_nh.sh new file mode 100755 index 000000000000..20f3369f776b --- /dev/null +++ b/tools/testing/selftests/net/test_vxlan_nh.sh @@ -0,0 +1,223 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh +TESTS=" + basic_tx_ipv4 + basic_tx_ipv6 + learning + proxy_ipv4 + proxy_ipv6 +" +VERBOSE=0 + +################################################################################ +# Utilities + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + echo "COMMAND: $cmd" + stderr= + fi + + out=$(eval "$cmd" "$stderr") + rc=$? + if [ "$VERBOSE" -eq 1 ] && [ -n "$out" ]; then + echo " $out" + fi + + return $rc +} + +################################################################################ +# Cleanup + +exit_cleanup_all() +{ + cleanup_all_ns + exit "${EXIT_STATUS}" +} + +################################################################################ +# Tests + +nh_stats_get() +{ + ip -n "$ns1" -s -j nexthop show id 10 | jq ".[][\"group_stats\"][][\"packets\"]" +} + +tc_stats_get() +{ + tc_rule_handle_stats_get "dev dummy1 egress" 101 ".packets" "-n $ns1" +} + +basic_tx_common() +{ + local af_str=$1; shift + local proto=$1; shift + local local_addr=$1; shift + local plen=$1; shift + local remote_addr=$1; shift + + RET=0 + + # Test basic Tx functionality. Check that stats are incremented on + # both the FDB nexthop group and the egress device. + + run_cmd "ip -n $ns1 link add name dummy1 up type dummy" + run_cmd "ip -n $ns1 route add $remote_addr/$plen dev dummy1" + run_cmd "tc -n $ns1 qdisc add dev dummy1 clsact" + run_cmd "tc -n $ns1 filter add dev dummy1 egress proto $proto pref 1 handle 101 flower ip_proto udp dst_ip $remote_addr dst_port 4789 action pass" + + run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo" + + run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb" + run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb" + + run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789" + run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10" + + run_cmd "ip netns exec $ns1 mausezahn vx0 -a own -b 00:11:22:33:44:55 -c 1 -q" + + busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" nh_stats_get > /dev/null + check_err $? "FDB nexthop group stats did not increase" + + busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" tc_stats_get > /dev/null + check_err $? "tc filter stats did not increase" + + log_test "VXLAN FDB nexthop: $af_str basic Tx" +} + +basic_tx_ipv4() +{ + basic_tx_common "IPv4" ipv4 192.0.2.1 32 192.0.2.2 +} + +basic_tx_ipv6() +{ + basic_tx_common "IPv6" ipv6 2001:db8:1::1 128 2001:db8:1::2 +} + +learning() +{ + RET=0 + + # When learning is enabled on the VXLAN device, an incoming packet + # might try to refresh an FDB entry that points to an FDB nexthop group + # instead of an ordinary remote destination. Check that the kernel does + # not crash in this situation. + + run_cmd "ip -n $ns1 address add 192.0.2.1/32 dev lo" + run_cmd "ip -n $ns1 address add 192.0.2.2/32 dev lo" + + run_cmd "ip -n $ns1 nexthop add id 1 via 192.0.2.3 fdb" + run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb" + + run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local 192.0.2.1 dstport 12345 localbypass" + run_cmd "ip -n $ns1 link add name vx1 up type vxlan id 10020 local 192.0.2.2 dstport 54321 learning" + + run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static dst 192.0.2.2 port 54321 vni 10020" + run_cmd "bridge -n $ns1 fdb add 00:aa:bb:cc:dd:ee dev vx1 self static nhid 10" + + run_cmd "ip netns exec $ns1 mausezahn vx0 -a 00:aa:bb:cc:dd:ee -b 00:11:22:33:44:55 -c 1 -q" + + log_test "VXLAN FDB nexthop: learning" +} + +proxy_common() +{ + local af_str=$1; shift + local local_addr=$1; shift + local plen=$1; shift + local remote_addr=$1; shift + local neigh_addr=$1; shift + local ping_cmd=$1; shift + + RET=0 + + # When the "proxy" option is enabled on the VXLAN device, the device + # will suppress ARP requests and IPv6 Neighbor Solicitation messages if + # it is able to reply on behalf of the remote host. That is, if a + # matching and valid neighbor entry is configured on the VXLAN device + # whose MAC address is not behind the "any" remote (0.0.0.0 / ::). The + # FDB entry for the neighbor's MAC address might point to an FDB + # nexthop group instead of an ordinary remote destination. Check that + # the kernel does not crash in this situation. + + run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo" + + run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb" + run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb" + + run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789 proxy" + + run_cmd "ip -n $ns1 neigh add $neigh_addr lladdr 00:11:22:33:44:55 nud perm dev vx0" + + run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10" + + run_cmd "ip netns exec $ns1 $ping_cmd" + + log_test "VXLAN FDB nexthop: $af_str proxy" +} + +proxy_ipv4() +{ + proxy_common "IPv4" 192.0.2.1 32 192.0.2.2 192.0.2.3 \ + "arping -b -c 1 -s 192.0.2.1 -I vx0 192.0.2.3" +} + +proxy_ipv6() +{ + proxy_common "IPv6" 2001:db8:1::1 128 2001:db8:1::2 2001:db8:1::3 \ + "ndisc6 -r 1 -s 2001:db8:1::1 -w 1 2001:db8:1::3 vx0" +} + +################################################################################ +# Usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -v Verbose mode (show commands and output) +EOF +} + +################################################################################ +# Main + +while getopts ":t:pvh" opt; do + case $opt in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=$((VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +require_command mausezahn +require_command arping +require_command ndisc6 +require_command jq + +if ! ip nexthop help 2>&1 | grep -q "stats"; then + echo "SKIP: iproute2 ip too old, missing nexthop stats support" + exit "$ksft_skip" +fi + +trap exit_cleanup_all EXIT + +for t in $TESTS +do + setup_ns ns1; $t; cleanup_all_ns; +done diff --git a/tools/testing/selftests/ublk/file_backed.c b/tools/testing/selftests/ublk/file_backed.c index 2d93ac860bd5..cd9fe69ecce2 100644 --- a/tools/testing/selftests/ublk/file_backed.c +++ b/tools/testing/selftests/ublk/file_backed.c @@ -20,7 +20,7 @@ static int loop_queue_flush_io(struct ublk_thread *t, struct ublk_queue *q, struct io_uring_sqe *sqe[1]; ublk_io_alloc_sqes(t, sqe, 1); - io_uring_prep_fsync(sqe[0], 1 /*fds[1]*/, IORING_FSYNC_DATASYNC); + io_uring_prep_fsync(sqe[0], ublk_get_registered_fd(q, 1) /*fds[1]*/, IORING_FSYNC_DATASYNC); io_uring_sqe_set_flags(sqe[0], IOSQE_FIXED_FILE); /* bit63 marks us as tgt io */ sqe[0]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1); @@ -42,7 +42,7 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, if (!sqe[0]) return -ENOMEM; - io_uring_prep_rw(op, sqe[0], 1 /*fds[1]*/, + io_uring_prep_rw(op, sqe[0], ublk_get_registered_fd(q, 1) /*fds[1]*/, addr, iod->nr_sectors << 9, iod->start_sector << 9); @@ -56,19 +56,19 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, ublk_io_alloc_sqes(t, sqe, 3); - io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index); + io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index); sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK; sqe[0]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1); - io_uring_prep_rw(op, sqe[1], 1 /*fds[1]*/, 0, + io_uring_prep_rw(op, sqe[1], ublk_get_registered_fd(q, 1) /*fds[1]*/, 0, iod->nr_sectors << 9, iod->start_sector << 9); sqe[1]->buf_index = tag; sqe[1]->flags |= IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK; sqe[1]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1); - io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index); + io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index); sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1); return 2; diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index 6512dfbdbce3..b71faba86c3b 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -432,7 +432,7 @@ static void ublk_thread_deinit(struct ublk_thread *t) } } -static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags) +static int ublk_queue_init(struct ublk_queue *q, unsigned long long extra_flags) { struct ublk_dev *dev = q->dev; int depth = dev->dev_info.queue_depth; @@ -446,6 +446,9 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags) q->flags = dev->dev_info.flags; q->flags |= extra_flags; + /* Cache fd in queue for fast path access */ + q->ublk_fd = dev->fds[0]; + cmd_buf_size = ublk_queue_cmd_buf_sz(q); off = UBLKSRV_CMD_BUF_OFFSET + q->q_id * ublk_queue_max_cmd_buf_sz(); q->io_cmd_buf = mmap(0, cmd_buf_size, PROT_READ, @@ -481,9 +484,10 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags) return -ENOMEM; } -static int ublk_thread_init(struct ublk_thread *t) +static int ublk_thread_init(struct ublk_thread *t, unsigned long long extra_flags) { struct ublk_dev *dev = t->dev; + unsigned long long flags = dev->dev_info.flags | extra_flags; int ring_depth = dev->tgt.sq_depth, cq_depth = dev->tgt.cq_depth; int ret; @@ -512,7 +516,17 @@ static int ublk_thread_init(struct ublk_thread *t) io_uring_register_ring_fd(&t->ring); - ret = io_uring_register_files(&t->ring, dev->fds, dev->nr_fds); + if (flags & UBLKS_Q_NO_UBLK_FIXED_FD) { + /* Register only backing files starting from index 1, exclude ublk control device */ + if (dev->nr_fds > 1) { + ret = io_uring_register_files(&t->ring, &dev->fds[1], dev->nr_fds - 1); + } else { + /* No backing files to register, skip file registration */ + ret = 0; + } + } else { + ret = io_uring_register_files(&t->ring, dev->fds, dev->nr_fds); + } if (ret) { ublk_err("ublk dev %d thread %d register files failed %d\n", t->dev->dev_info.dev_id, t->idx, ret); @@ -626,9 +640,12 @@ int ublk_queue_io_cmd(struct ublk_thread *t, struct ublk_io *io) /* These fields should be written once, never change */ ublk_set_sqe_cmd_op(sqe[0], cmd_op); - sqe[0]->fd = 0; /* dev->fds[0] */ + sqe[0]->fd = ublk_get_registered_fd(q, 0); /* dev->fds[0] */ sqe[0]->opcode = IORING_OP_URING_CMD; - sqe[0]->flags = IOSQE_FIXED_FILE; + if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD) + sqe[0]->flags = 0; /* Use raw FD, not fixed file */ + else + sqe[0]->flags = IOSQE_FIXED_FILE; sqe[0]->rw_flags = 0; cmd->tag = io->tag; cmd->q_id = q->q_id; @@ -832,6 +849,7 @@ struct ublk_thread_info { unsigned idx; sem_t *ready; cpu_set_t *affinity; + unsigned long long extra_flags; }; static void *ublk_io_handler_fn(void *data) @@ -844,7 +862,7 @@ static void *ublk_io_handler_fn(void *data) t->dev = info->dev; t->idx = info->idx; - ret = ublk_thread_init(t); + ret = ublk_thread_init(t, info->extra_flags); if (ret) { ublk_err("ublk dev %d thread %u init failed\n", dev_id, t->idx); @@ -934,6 +952,8 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) if (ctx->auto_zc_fallback) extra_flags = UBLKS_Q_AUTO_BUF_REG_FALLBACK; + if (ctx->no_ublk_fixed_fd) + extra_flags |= UBLKS_Q_NO_UBLK_FIXED_FD; for (i = 0; i < dinfo->nr_hw_queues; i++) { dev->q[i].dev = dev; @@ -951,6 +971,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) tinfo[i].dev = dev; tinfo[i].idx = i; tinfo[i].ready = &ready; + tinfo[i].extra_flags = extra_flags; /* * If threads are not tied 1:1 to queues, setting thread @@ -1471,7 +1492,7 @@ static void __cmd_create_help(char *exe, bool recovery) printf("%s %s -t [null|loop|stripe|fault_inject] [-q nr_queues] [-d depth] [-n dev_id]\n", exe, recovery ? "recover" : "add"); printf("\t[--foreground] [--quiet] [-z] [--auto_zc] [--auto_zc_fallback] [--debug_mask mask] [-r 0|1 ] [-g]\n"); - printf("\t[-e 0|1 ] [-i 0|1]\n"); + printf("\t[-e 0|1 ] [-i 0|1] [--no_ublk_fixed_fd]\n"); printf("\t[--nthreads threads] [--per_io_tasks]\n"); printf("\t[target options] [backfile1] [backfile2] ...\n"); printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n"); @@ -1534,6 +1555,7 @@ int main(int argc, char *argv[]) { "size", 1, NULL, 's'}, { "nthreads", 1, NULL, 0 }, { "per_io_tasks", 0, NULL, 0 }, + { "no_ublk_fixed_fd", 0, NULL, 0 }, { 0, 0, 0, 0 } }; const struct ublk_tgt_ops *ops = NULL; @@ -1613,6 +1635,8 @@ int main(int argc, char *argv[]) ctx.nthreads = strtol(optarg, NULL, 10); if (!strcmp(longopts[option_idx].name, "per_io_tasks")) ctx.per_io_tasks = 1; + if (!strcmp(longopts[option_idx].name, "no_ublk_fixed_fd")) + ctx.no_ublk_fixed_fd = 1; break; case '?': /* diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h index 219233f8a053..5e55484fb0aa 100644 --- a/tools/testing/selftests/ublk/kublk.h +++ b/tools/testing/selftests/ublk/kublk.h @@ -77,6 +77,7 @@ struct dev_ctx { unsigned int recovery:1; unsigned int auto_zc_fallback:1; unsigned int per_io_tasks:1; + unsigned int no_ublk_fixed_fd:1; int _evtfd; int _shmid; @@ -166,7 +167,9 @@ struct ublk_queue { /* borrow one bit of ublk uapi flags, which may never be used */ #define UBLKS_Q_AUTO_BUF_REG_FALLBACK (1ULL << 63) +#define UBLKS_Q_NO_UBLK_FIXED_FD (1ULL << 62) __u64 flags; + int ublk_fd; /* cached ublk char device fd */ struct ublk_io ios[UBLK_QUEUE_DEPTH]; }; @@ -273,34 +276,48 @@ static inline int ublk_io_alloc_sqes(struct ublk_thread *t, return nr_sqes; } -static inline void io_uring_prep_buf_register(struct io_uring_sqe *sqe, - int dev_fd, int tag, int q_id, __u64 index) +static inline int ublk_get_registered_fd(struct ublk_queue *q, int fd_index) +{ + if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD) { + if (fd_index == 0) + /* Return the raw ublk FD for index 0 */ + return q->ublk_fd; + /* Adjust index for backing files (index 1 becomes 0, etc.) */ + return fd_index - 1; + } + return fd_index; +} + +static inline void __io_uring_prep_buf_reg_unreg(struct io_uring_sqe *sqe, + struct ublk_queue *q, int tag, int q_id, __u64 index) { struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd; + int dev_fd = ublk_get_registered_fd(q, 0); io_uring_prep_read(sqe, dev_fd, 0, 0, 0); sqe->opcode = IORING_OP_URING_CMD; - sqe->flags |= IOSQE_FIXED_FILE; - sqe->cmd_op = UBLK_U_IO_REGISTER_IO_BUF; + if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD) + sqe->flags &= ~IOSQE_FIXED_FILE; + else + sqe->flags |= IOSQE_FIXED_FILE; cmd->tag = tag; cmd->addr = index; cmd->q_id = q_id; } -static inline void io_uring_prep_buf_unregister(struct io_uring_sqe *sqe, - int dev_fd, int tag, int q_id, __u64 index) +static inline void io_uring_prep_buf_register(struct io_uring_sqe *sqe, + struct ublk_queue *q, int tag, int q_id, __u64 index) { - struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd; + __io_uring_prep_buf_reg_unreg(sqe, q, tag, q_id, index); + sqe->cmd_op = UBLK_U_IO_REGISTER_IO_BUF; +} - io_uring_prep_read(sqe, dev_fd, 0, 0, 0); - sqe->opcode = IORING_OP_URING_CMD; - sqe->flags |= IOSQE_FIXED_FILE; +static inline void io_uring_prep_buf_unregister(struct io_uring_sqe *sqe, + struct ublk_queue *q, int tag, int q_id, __u64 index) +{ + __io_uring_prep_buf_reg_unreg(sqe, q, tag, q_id, index); sqe->cmd_op = UBLK_U_IO_UNREGISTER_IO_BUF; - - cmd->tag = tag; - cmd->addr = index; - cmd->q_id = q_id; } static inline void *ublk_get_sqe_cmd(const struct io_uring_sqe *sqe) diff --git a/tools/testing/selftests/ublk/null.c b/tools/testing/selftests/ublk/null.c index f0e0003a4860..280043f6b689 100644 --- a/tools/testing/selftests/ublk/null.c +++ b/tools/testing/selftests/ublk/null.c @@ -63,7 +63,7 @@ static int null_queue_zc_io(struct ublk_thread *t, struct ublk_queue *q, ublk_io_alloc_sqes(t, sqe, 3); - io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index); + io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index); sqe[0]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1); sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK; @@ -71,7 +71,7 @@ static int null_queue_zc_io(struct ublk_thread *t, struct ublk_queue *q, __setup_nop_io(tag, iod, sqe[1], q->q_id); sqe[1]->flags |= IOSQE_IO_HARDLINK; - io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index); + io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index); sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1); // buf register is marked as IOSQE_CQE_SKIP_SUCCESS diff --git a/tools/testing/selftests/ublk/stripe.c b/tools/testing/selftests/ublk/stripe.c index 1fb9b7cc281b..791fa8dc1651 100644 --- a/tools/testing/selftests/ublk/stripe.c +++ b/tools/testing/selftests/ublk/stripe.c @@ -142,7 +142,7 @@ static int stripe_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, ublk_io_alloc_sqes(t, sqe, s->nr + extra); if (zc) { - io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, io->buf_index); + io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, io->buf_index); sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK; sqe[0]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1); @@ -168,7 +168,7 @@ static int stripe_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, if (zc) { struct io_uring_sqe *unreg = sqe[s->nr + 1]; - io_uring_prep_buf_unregister(unreg, 0, tag, q->q_id, io->buf_index); + io_uring_prep_buf_unregister(unreg, q, tag, q->q_id, io->buf_index); unreg->user_data = build_user_data( tag, ublk_cmd_op_nr(unreg->cmd_op), 0, q->q_id, 1); } diff --git a/tools/testing/selftests/ublk/test_stress_04.sh b/tools/testing/selftests/ublk/test_stress_04.sh index 40d1437ca298..3f901db4d09d 100755 --- a/tools/testing/selftests/ublk/test_stress_04.sh +++ b/tools/testing/selftests/ublk/test_stress_04.sh @@ -28,14 +28,14 @@ _create_backfile 0 256M _create_backfile 1 128M _create_backfile 2 128M -ublk_io_and_kill_daemon 8G -t null -q 4 -z & -ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" & +ublk_io_and_kill_daemon 8G -t null -q 4 -z --no_ublk_fixed_fd & +ublk_io_and_kill_daemon 256M -t loop -q 4 -z --no_ublk_fixed_fd "${UBLK_BACKFILES[0]}" & ublk_io_and_kill_daemon 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & if _have_feature "AUTO_BUF_REG"; then ublk_io_and_kill_daemon 8G -t null -q 4 --auto_zc & ublk_io_and_kill_daemon 256M -t loop -q 4 --auto_zc "${UBLK_BACKFILES[0]}" & - ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & + ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc --no_ublk_fixed_fd "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & ublk_io_and_kill_daemon 8G -t null -q 4 -z --auto_zc --auto_zc_fallback & fi |