May 2021 - Linux-kselftest-mirror

[PATCH RESEND v2 1/2] KVM: selftests: Keep track of memslots more efficiently

by Maciej S. Szmigiero

From: "Maciej S. Szmigiero" <maciej.szmigiero(a)oracle.com> The KVM selftest framework was using a simple list for keeping track of the memslots currently in use. This resulted in lookups and adding a single memslot being O(n), the later due to linear scanning of the existing memslot set to check for the presence of any conflicting entries. Before this change, benchmarking high count of memslots was more or less impossible as pretty much all the benchmark time was spent in the selftest framework code. We can simply use a rbtree for keeping track of both of gfn and hva. We don't need an interval tree for hva here as we can't have overlapping memslots because we allocate a completely new memory chunk for each new memslot. Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero(a)oracle.com> Reviewed-by: Andrew Jones <drjones(a)redhat.com> --- This is just a resend of this patch without any changes. tools/testing/selftests/kvm/Makefile | 2 +- tools/testing/selftests/kvm/lib/kvm_util.c | 141 ++++++++++++++---- .../selftests/kvm/lib/kvm_util_internal.h | 15 +- tools/testing/selftests/kvm/lib/rbtree.c | 1 + 4 files changed, 124 insertions(+), 35 deletions(-) create mode 100644 tools/testing/selftests/kvm/lib/rbtree.c diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index e439d027939d..a8c30f888d40 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -33,7 +33,7 @@ ifeq ($(ARCH),s390) UNAME_M := s390x endif -LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c +LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index fc83f6c5902d..646e94cc101b 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -203,7 +203,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) TEST_ASSERT(vm != NULL, "Insufficient Memory"); INIT_LIST_HEAD(&vm->vcpus); - INIT_LIST_HEAD(&vm->userspace_mem_regions); + vm->regions.gpa_tree = RB_ROOT; + vm->regions.hva_tree = RB_ROOT; + hash_init(vm->regions.slot_hash); vm->mode = mode; vm->type = 0; @@ -355,13 +357,14 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, */ void kvm_vm_restart(struct kvm_vm *vmp, int perm) { + int ctr; struct userspace_mem_region *region; vm_open(vmp, perm); if (vmp->has_irqchip) vm_create_irqchip(vmp); - list_for_each_entry(region, &vmp->userspace_mem_regions, list) { + hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) { int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, &region->region); TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" " rc: %i errno: %i\n" @@ -424,14 +427,21 @@ uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) static struct userspace_mem_region * userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end) { - struct userspace_mem_region *region; + struct rb_node *node; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + for (node = vm->regions.gpa_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, gpa_node); uint64_t existing_start = region->region.guest_phys_addr; uint64_t existing_end = region->region.guest_phys_addr + region->region.memory_size - 1; if (start <= existing_end && end >= existing_start) return region; + + if (start < existing_start) + node = node->rb_left; + else + node = node->rb_right; } return NULL; @@ -546,11 +556,16 @@ void kvm_vm_release(struct kvm_vm *vmp) } static void __vm_mem_region_delete(struct kvm_vm *vm, - struct userspace_mem_region *region) + struct userspace_mem_region *region, + bool unlink) { int ret; - list_del(&region->list); + if (unlink) { + rb_erase(&region->gpa_node, &vm->regions.gpa_tree); + rb_erase(&region->hva_node, &vm->regions.hva_tree); + hash_del(&region->slot_node); + } region->region.memory_size = 0; ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region->region); @@ -569,14 +584,16 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, */ void kvm_vm_free(struct kvm_vm *vmp) { - struct userspace_mem_region *region, *tmp; + int ctr; + struct hlist_node *node; + struct userspace_mem_region *region; if (vmp == NULL) return; /* Free userspace_mem_regions. */ - list_for_each_entry_safe(region, tmp, &vmp->userspace_mem_regions, list) - __vm_mem_region_delete(vmp, region); + hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node) + __vm_mem_region_delete(vmp, region, false); /* Free sparsebit arrays. */ sparsebit_free(&vmp->vpages_valid); @@ -658,6 +675,57 @@ int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len) return 0; } +static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &gpa_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), gpa_node); + parent = *cur; + if (region->region.guest_phys_addr < + cregion->region.guest_phys_addr) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->region.guest_phys_addr != + cregion->region.guest_phys_addr, + "Duplicate GPA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(&region->gpa_node, parent, cur); + rb_insert_color(&region->gpa_node, gpa_tree); +} + +static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &hva_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), hva_node); + parent = *cur; + if (region->host_mem < cregion->host_mem) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->host_mem != + cregion->host_mem, + "Duplicate HVA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(&region->hva_node, parent, cur); + rb_insert_color(&region->hva_node, hva_tree); +} + /* * VM Userspace Memory Region Add * @@ -722,7 +790,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, (uint64_t) region->region.memory_size); /* Confirm no region with the requested slot already exists. */ - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + slot) { if (region->region.slot != slot) continue; @@ -793,8 +862,10 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, ret, errno, slot, flags, guest_paddr, (uint64_t) region->region.memory_size); - /* Add to linked-list of memory regions. */ - list_add(&region->list, &vm->userspace_mem_regions); + /* Add to quick lookup data structures */ + vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region); + vm_userspace_mem_region_hva_insert(&vm->regions.hva_tree, region); + hash_add(vm->regions.slot_hash, &region->slot_node, slot); } /* @@ -817,10 +888,10 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + memslot) if (region->region.slot == memslot) return region; - } fprintf(stderr, "No mem region with the requested slot found,\n" " requested slot: %u\n", memslot); @@ -905,7 +976,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) */ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) { - __vm_mem_region_delete(vm, memslot2region(vm, slot)); + __vm_mem_region_delete(vm, memslot2region(vm, slot), true); } /* @@ -1177,16 +1248,14 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((gpa >= region->region.guest_phys_addr) - && (gpa <= (region->region.guest_phys_addr - + region->region.memory_size - 1))) - return (void *) ((uintptr_t) region->host_mem - + (gpa - region->region.guest_phys_addr)); + region = userspace_mem_region_find(vm, gpa, gpa); + if (!region) { + TEST_FAIL("No vm physical memory at 0x%lx", gpa); + return NULL; } - TEST_FAIL("No vm physical memory at 0x%lx", gpa); - return NULL; + return (void *)((uintptr_t)region->host_mem + + (gpa - region->region.guest_phys_addr)); } /* @@ -1208,15 +1277,22 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) */ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) { - struct userspace_mem_region *region; + struct rb_node *node; + + for (node = vm->regions.hva_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, hva_node); + + if (hva >= region->host_mem) { + if (hva <= (region->host_mem + + region->region.memory_size - 1)) + return (vm_paddr_t)((uintptr_t) + region->region.guest_phys_addr + + (hva - (uintptr_t)region->host_mem)); - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((hva >= region->host_mem) - && (hva <= (region->host_mem - + region->region.memory_size - 1))) - return (vm_paddr_t) ((uintptr_t) - region->region.guest_phys_addr - + (hva - (uintptr_t) region->host_mem)); + node = node->rb_right; + } else + node = node->rb_left; } TEST_FAIL("No mapping to a guest physical address, hva: %p", hva); @@ -1822,6 +1898,7 @@ int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, */ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { + int ctr; struct userspace_mem_region *region; struct vcpu *vcpu; @@ -1829,7 +1906,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd); fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size); fprintf(stream, "%*sMem Regions:\n", indent, ""); - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) { fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx " "host_virt: %p\n", indent + 2, "", (uint64_t) region->region.guest_phys_addr, diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 91ce1b5d480b..b30e8c7b119b 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -8,6 +8,9 @@ #ifndef SELFTEST_KVM_UTIL_INTERNAL_H #define SELFTEST_KVM_UTIL_INTERNAL_H +#include "linux/hashtable.h" +#include "linux/rbtree.h" + #include "sparsebit.h" struct userspace_mem_region { @@ -18,7 +21,9 @@ struct userspace_mem_region { void *host_mem; void *mmap_start; size_t mmap_size; - struct list_head list; + struct rb_node gpa_node; + struct rb_node hva_node; + struct hlist_node slot_node; }; struct vcpu { @@ -31,6 +36,12 @@ struct vcpu { uint32_t dirty_gfns_count; }; +struct userspace_mem_regions { + struct rb_root gpa_tree; + struct rb_root hva_tree; + DECLARE_HASHTABLE(slot_hash, 9); +}; + struct kvm_vm { int mode; unsigned long type; @@ -43,7 +54,7 @@ struct kvm_vm { unsigned int va_bits; uint64_t max_gfn; struct list_head vcpus; - struct list_head userspace_mem_regions; + struct userspace_mem_regions regions; struct sparsebit *vpages_valid; struct sparsebit *vpages_mapped; bool has_irqchip; diff --git a/tools/testing/selftests/kvm/lib/rbtree.c b/tools/testing/selftests/kvm/lib/rbtree.c new file mode 100644 index 000000000000..a703f0194ea3 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/rbtree.c @@ -0,0 +1 @@ +#include "../../../../lib/rbtree.c"

2 years, 11 months

1
1
0 0

[RFC PATCH v2 07/11] selftests/x86: Test Key Locker internal key maintenance

by Chang S. Bae

The test validates the internal key to be the same in all CPUs. It performs the validation again with the Suspend-To-RAM (ACPI S3) state. Signed-off-by: Chang S. Bae <chang.seok.bae(a)intel.com> Cc: linux-kernel(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org --- Changes from RFC v1: * Commented the binutils version number for ENCODEKEY128 (Peter Zijlstra) --- tools/testing/selftests/x86/Makefile | 2 +- tools/testing/selftests/x86/keylocker.c | 177 ++++++++++++++++++++++++ 2 files changed, 178 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/x86/keylocker.c diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 333980375bc7..09237cc84108 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -13,7 +13,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie) TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ check_initial_reg_state sigreturn iopl ioperm \ test_vsyscall mov_ss_trap \ - syscall_arg_fault fsgsbase_restore + syscall_arg_fault fsgsbase_restore keylocker TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer diff --git a/tools/testing/selftests/x86/keylocker.c b/tools/testing/selftests/x86/keylocker.c new file mode 100644 index 000000000000..78bbb7939b1a --- /dev/null +++ b/tools/testing/selftests/x86/keylocker.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * keylocker.c, validate the internal key management. + */ +#undef _GNU_SOURCE +#define _GNU_SOURCE 1 + +#include <stdio.h> +#include <stdbool.h> +#include <string.h> +#include <fcntl.h> +#include <err.h> +#include <sched.h> +#include <setjmp.h> +#include <signal.h> +#include <unistd.h> + +#define HANDLE_SIZE 48 + +static bool keylocker_disabled; + +/* Encode a 128-bit key to a 384-bit handle */ +static inline void __encode_key(char *handle) +{ + static const unsigned char aeskey[] = { 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, + 0x71, 0x77, 0x74, 0x69, 0x6f, 0x6b, 0x6c, 0x78 }; + + asm volatile ("movdqu %0, %%xmm0" : : "m" (*aeskey) :); + + /* Set no restriction to the handle */ + asm volatile ("mov $0, %%eax" :); + + /* ENCODEKEY128 %EAX (supported by binutils >= 2.36) */ + asm volatile (".byte 0xf3, 0xf, 0x38, 0xfa, 0xc0"); + + asm volatile ("movdqu %%xmm0, %0; movdqu %%xmm1, %1; movdqu %%xmm2, %2;" + : "=m" (handle[0]), "=m" (handle[0x10]), "=m" (handle[0x20])); +} + +static jmp_buf jmpbuf; + +static void handle_sigill(int sig, siginfo_t *si, void *ctx_void) +{ + keylocker_disabled = true; + siglongjmp(jmpbuf, 1); +} + +static bool encode_key(char *handle) +{ + bool success = true; + struct sigaction sa; + int ret; + + memset(&sa, 0, sizeof(sa)); + + /* Set signal handler */ + sa.sa_flags = SA_SIGINFO; + sa.sa_sigaction = handle_sigill; + sigemptyset(&sa.sa_mask); + ret = sigaction(SIGILL, &sa, 0); + if (ret) + err(1, "sigaction"); + + if (sigsetjmp(jmpbuf, 1)) + success = false; + else + __encode_key(handle); + + /* Clear signal handler */ + sa.sa_flags = 0; + sa.sa_sigaction = NULL; + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + ret = sigaction(SIGILL, &sa, 0); + if (ret) + err(1, "sigaction"); + + return success; +} + +/* + * Test if the internal key is the same in all the CPUs: + * + * Since the value is not readable, compare the encoded output of a AES key + * between CPUs. + */ + +static int nerrs; + +static unsigned char cpu0_handle[HANDLE_SIZE] = { 0 }; + +static void test_internal_key(bool slept, long cpus) +{ + int cpu, errs; + + printf("Test the internal key consistency between CPUs\n"); + + for (cpu = 0, errs = 0; cpu < cpus; cpu++) { + char handle[HANDLE_SIZE] = { 0 }; + cpu_set_t mask; + bool success; + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + sched_setaffinity(0, sizeof(cpu_set_t), &mask); + + success = encode_key(handle); + if (!success) { + /* The encode should success after the S3 sleep */ + if (slept) + errs++; + printf("[%s]\tKey Locker disabled at CPU%d\n", + slept ? "FAIL" : "NOTE", cpu); + continue; + } + + if (cpu == 0 && !slept) { + /* Record the first handle value as reference */ + memcpy(cpu0_handle, handle, HANDLE_SIZE); + } else if (memcmp(cpu0_handle, handle, HANDLE_SIZE)) { + printf("[FAIL]\tMismatched internal key at CPU%d\n", + cpu); + errs++; + } + } + + if (errs == 0 && !keylocker_disabled) + printf("[OK]\tAll the internal keys are the same\n"); + else + nerrs += errs; +} + +static void switch_to_sleep(bool *slept) +{ + ssize_t bytes; + int fd; + + printf("Transition to Suspend-To-RAM state\n"); + + fd = open("/sys/power/mem_sleep", O_RDWR); + if (fd < 0) + err(1, "Open /sys/power/mem_sleep"); + + bytes = write(fd, "deep", strlen("deep")); + if (bytes != strlen("deep")) + err(1, "Write /sys/power/mem_sleep"); + close(fd); + + fd = open("/sys/power/state", O_RDWR); + if (fd < 0) + err(1, "Open /sys/power/state"); + + bytes = write(fd, "mem", strlen("mem")); + if (bytes != strlen("mem")) + err(1, "Write /sys/power/state"); + close(fd); + + printf("Wake up from Suspend-To-RAM state\n"); + *slept = true; +} + +int main(void) +{ + bool slept = false; + long cpus; + + cpus = sysconf(_SC_NPROCESSORS_ONLN); + printf("%ld CPUs in the system\n", cpus); + + test_internal_key(slept, cpus); + if (keylocker_disabled) + return nerrs ? 1 : 0; + + switch_to_sleep(&slept); + test_internal_key(slept, cpus); + return nerrs ? 1 : 0; +} -- 2.17.1

2 years, 11 months

1
0
0 0

[PATCH] selftests/bpf: only munmap the mmaped ringbuf pages

by Thadeu Lima de Souza Cascardo

One the mmap tests will map a single page, then try to extend the mapping by use of mremap, which should fail. Right after that, it unmaps the extended area, which may end up unmapping other valid mapped areas, this causing a segfault. Only unmap the area that is expected to be mapped. Fixes: b2fb299c9aa4 ("selftests/bpf: test ringbuf mmap read-only and read-write restrictions") Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo(a)canonical.com> --- tools/testing/selftests/bpf/prog_tests/ringbuf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index 197e30b83298..f9a8ae331963 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -146,7 +146,7 @@ void test_ringbuf(void) ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_WRITE), "write_protect"); ASSERT_ERR(mprotect(mmap_ptr, page_size, PROT_EXEC), "exec_protect"); ASSERT_ERR_PTR(mremap(mmap_ptr, 0, 3 * page_size, MREMAP_MAYMOVE), "ro_remap"); - ASSERT_OK(munmap(mmap_ptr, 3 * page_size), "unmap_ro"); + ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_ro"); /* only trigger BPF program for current process */ skel->bss->pid = getpid(); -- 2.30.2

2 years, 11 months

2
1
0 0

[PATCH -next] tools/testing/selftests/exec: fix link error

by Yang Yingliang

Fix the link error by adding '-static': gcc -Wall -Wl,-z,max-page-size=0x1000 -pie load_address.c -o /home/yang/linux/tools/testing/selftests/exec/load_address_4096 /usr/bin/ld: /tmp/ccopEGun.o: relocation R_AARCH64_ADR_PREL_PG_HI21 against symbol `stderr@@GLIBC_2.17' which may bind externally can not be used when making a shared object; recompile with -fPIC /usr/bin/ld: /tmp/ccopEGun.o(.text+0x158): unresolvable R_AARCH64_ADR_PREL_PG_HI21 relocation against symbol `stderr@@GLIBC_2.17' /usr/bin/ld: final link failed: bad value collect2: error: ld returned 1 exit status make: *** [Makefile:25: tools/testing/selftests/exec/load_address_4096] Error 1 Fixes: 206e22f01941 ("tools/testing/selftests: add self-test for verifying load alignment") Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- tools/testing/selftests/exec/Makefile | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index cf69b2fcce59..dd61118df66e 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -28,8 +28,8 @@ $(OUTPUT)/execveat.denatured: $(OUTPUT)/execveat cp $< $@ chmod -x $@ $(OUTPUT)/load_address_4096: load_address.c - $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000 -pie $< -o $@ + $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000 -pie -static $< -o $@ $(OUTPUT)/load_address_2097152: load_address.c - $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x200000 -pie $< -o $@ + $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x200000 -pie -static $< -o $@ $(OUTPUT)/load_address_16777216: load_address.c - $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000000 -pie $< -o $@ + $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000000 -pie -static $< -o $@ -- 2.25.1

2 years, 11 months

1
0
0 0

[PATCH][next] kselftest: Fix spelling mistake "hiearchy" -> "hierarchy"

by Colin King

From: Colin Ian King <colin.king(a)canonical.com> There is a spelling mistake in a message. Fix it. Signed-off-by: Colin Ian King <colin.king(a)canonical.com> --- tools/testing/selftests/sched/cs_prctl_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c index 63fe6521c56d..cf9ca10b876c 100644 --- a/tools/testing/selftests/sched/cs_prctl_test.c +++ b/tools/testing/selftests/sched/cs_prctl_test.c @@ -262,7 +262,7 @@ int main(int argc, char *argv[]) if (setpgid(0, 0) != 0) handle_error("process group"); - printf("\n## Create a thread/process/process group hiearchy\n"); + printf("\n## Create a thread/process/process group hierarchy\n"); create_processes(num_processes, num_threads, procs); disp_processes(num_processes, procs); validate(get_cs_cookie(0) == 0); -- 2.30.2

2 years, 11 months

1
0
0 0

[PATCH v3 0/4] KVM statistics data fd-based binary interface

by Jing Zhang

This patchset provides a file descriptor for every VM and VCPU to read KVM statistics data in binary format. It is meant to provide a lightweight, flexible, scalable and efficient lock-free solution for user space telemetry applications to pull the statistics data periodically for large scale systems. The pulling frequency could be as high as a few times per second. In this patchset, every statistics data are treated to have some attributes as below: * architecture dependent or common * VM statistics data or VCPU statistics data * type: cumulative, instantaneous, * unit: none for simple counter, nanosecond, microsecond, millisecond, second, Byte, KiByte, MiByte, GiByte. Clock Cycles Since no lock/synchronization is used, the consistency between all the statistics data is not guaranteed. That means not all statistics data are read out at the exact same time, since the statistics date are still being updated by KVM subsystems while they are read out. --- * v2 -> v3 - Rebase to kvm/queue, commit edf408f5257b ("KVM: avoid "deadlock" between install_new_memslots and MMU notifier") - Resolve some nitpicks about format * v1 -> v2 - Use ARRAY_SIZE to count the number of stats descriptors - Fix missing `size` field initialization in macro STATS_DESC [1] https://lore.kernel.org/kvm/20210402224359.2297157-1-jingzhangos@google.com [2] https://lore.kernel.org/kvm/20210415151741.1607806-1-jingzhangos@google.com --- Jing Zhang (4): KVM: stats: Separate common stats from architecture specific ones KVM: stats: Add fd-based API to read binary stats data KVM: stats: Add documentation for statistics data binary interface KVM: selftests: Add selftest for KVM statistics data binary interface Documentation/virt/kvm/api.rst | 171 ++++++++ arch/arm64/include/asm/kvm_host.h | 9 +- arch/arm64/kvm/guest.c | 42 +- arch/mips/include/asm/kvm_host.h | 9 +- arch/mips/kvm/mips.c | 67 +++- arch/powerpc/include/asm/kvm_host.h | 9 +- arch/powerpc/kvm/book3s.c | 68 +++- arch/powerpc/kvm/book3s_hv.c | 12 +- arch/powerpc/kvm/book3s_pr.c | 2 +- arch/powerpc/kvm/book3s_pr_papr.c | 2 +- arch/powerpc/kvm/booke.c | 63 ++- arch/s390/include/asm/kvm_host.h | 9 +- arch/s390/kvm/kvm-s390.c | 133 ++++++- arch/x86/include/asm/kvm_host.h | 9 +- arch/x86/kvm/x86.c | 71 +++- include/linux/kvm_host.h | 132 ++++++- include/linux/kvm_types.h | 12 + include/uapi/linux/kvm.h | 50 +++ tools/testing/selftests/kvm/.gitignore | 1 + tools/testing/selftests/kvm/Makefile | 3 + .../testing/selftests/kvm/include/kvm_util.h | 3 + .../selftests/kvm/kvm_bin_form_stats.c | 370 ++++++++++++++++++ tools/testing/selftests/kvm/lib/kvm_util.c | 11 + virt/kvm/kvm_main.c | 237 ++++++++++- 24 files changed, 1405 insertions(+), 90 deletions(-) create mode 100644 tools/testing/selftests/kvm/kvm_bin_form_stats.c base-commit: edf408f5257ba39e63781b820528e1ce1ec0f543 -- 2.31.1.498.g6c1eba8ee3d-goog

2 years, 11 months

1
8
0 0

[PATCH v5 1/3] kunit: make test->lock irq safe

by glittao＠gmail.com

From: Vlastimil Babka <vbabka(a)suse.cz> The upcoming SLUB kunit test will be calling kunit_find_named_resource() from a context with disabled interrupts. That means kunit's test->lock needs to be IRQ safe to avoid potential deadlocks and lockdep splats. This patch therefore changes the test->lock usage to spin_lock_irqsave() and spin_unlock_irqrestore(). Signed-off-by: Vlastimil Babka <vbabka(a)suse.cz> Signed-off-by: Oliver Glitta <glittao(a)gmail.com> --- Changes since v4 Rebased whole series on 5.13-rc1 include/kunit/test.h | 5 +++-- lib/kunit/test.c | 18 +++++++++++------- 2 files changed, 14 insertions(+), 9 deletions(-) diff --git a/include/kunit/test.h b/include/kunit/test.h index 49601c4b98b8..524d4789af22 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -515,8 +515,9 @@ kunit_find_resource(struct kunit *test, void *match_data) { struct kunit_resource *res, *found = NULL; + unsigned long flags; - spin_lock(&test->lock); + spin_lock_irqsave(&test->lock, flags); list_for_each_entry_reverse(res, &test->resources, node) { if (match(test, res, (void *)match_data)) { @@ -526,7 +527,7 @@ kunit_find_resource(struct kunit *test, } } - spin_unlock(&test->lock); + spin_unlock_irqrestore(&test->lock, flags); return found; } diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 2f6cc0123232..45f068864d76 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -475,6 +475,7 @@ int kunit_add_resource(struct kunit *test, void *data) { int ret = 0; + unsigned long flags; res->free = free; kref_init(&res->refcount); @@ -487,10 +488,10 @@ int kunit_add_resource(struct kunit *test, res->data = data; } - spin_lock(&test->lock); + spin_lock_irqsave(&test->lock, flags); list_add_tail(&res->node, &test->resources); /* refcount for list is established by kref_init() */ - spin_unlock(&test->lock); + spin_unlock_irqrestore(&test->lock, flags); return ret; } @@ -548,9 +549,11 @@ EXPORT_SYMBOL_GPL(kunit_alloc_and_get_resource); void kunit_remove_resource(struct kunit *test, struct kunit_resource *res) { - spin_lock(&test->lock); + unsigned long flags; + + spin_lock_irqsave(&test->lock, flags); list_del(&res->node); - spin_unlock(&test->lock); + spin_unlock_irqrestore(&test->lock, flags); kunit_put_resource(res); } EXPORT_SYMBOL_GPL(kunit_remove_resource); @@ -630,6 +633,7 @@ EXPORT_SYMBOL_GPL(kunit_kfree); void kunit_cleanup(struct kunit *test) { struct kunit_resource *res; + unsigned long flags; /* * test->resources is a stack - each allocation must be freed in the @@ -641,9 +645,9 @@ void kunit_cleanup(struct kunit *test) * protect against the current node being deleted, not the next. */ while (true) { - spin_lock(&test->lock); + spin_lock_irqsave(&test->lock, flags); if (list_empty(&test->resources)) { - spin_unlock(&test->lock); + spin_unlock_irqrestore(&test->lock, flags); break; } res = list_last_entry(&test->resources, @@ -654,7 +658,7 @@ void kunit_cleanup(struct kunit *test) * resource, and this can't happen if the test->lock * is held. */ - spin_unlock(&test->lock); + spin_unlock_irqrestore(&test->lock, flags); kunit_remove_resource(test, res); } current->kunit_test = NULL; -- 2.31.1.272.g89b43f80a5

2 years, 11 months

5
9
0 0

[PATCH v5 0/2] CPU-Idle latency selftest framework

by Pratik R. Sampat

Changelog RFC v4 --> PATCH v5: 1. Added a CPU online check prior to parsing the CPU topology to avoid parsing topologies for CPUs unavailable for the latency test 2. Added comment describing the selftest in cpuidle.sh As I have made changes to cpuidle.sh's working, hence dropping "Reviewed-by" from Doug Smythies for the second patch, while retaining it for the first patch. RFC v4: https://lkml.org/lkml/2021/4/12/99 --- A kernel module + userspace driver to estimate the wakeup latency caused by going into stop states. The motivation behind this program is to find significant deviations behind advertised latency and residency values. The patchset measures latencies for two kinds of events. IPIs and Timers As this is a software-only mechanism, there will additional latencies of the kernel-firmware-hardware interactions. To account for that, the program also measures a baseline latency on a 100 percent loaded CPU and the latencies achieved must be in view relative to that. To achieve this, we introduce a kernel module and expose its control knobs through the debugfs interface that the selftests can engage with. The kernel module provides the following interfaces within /sys/kernel/debug/latency_test/ for, IPI test: ipi_cpu_dest = Destination CPU for the IPI ipi_cpu_src = Origin of the IPI ipi_latency_ns = Measured latency time in ns Timeout test: timeout_cpu_src = CPU on which the timer to be queued timeout_expected_ns = Timer duration timeout_diff_ns = Difference of actual duration vs expected timer Sample output on a POWER9 system is as follows: # --IPI Latency Test--- # Baseline Average IPI latency(ns): 3114 # Observed Average IPI latency(ns) - State0: 3265 # Observed Average IPI latency(ns) - State1: 3507 # Observed Average IPI latency(ns) - State2: 3739 # Observed Average IPI latency(ns) - State3: 3807 # Observed Average IPI latency(ns) - State4: 17070 # Observed Average IPI latency(ns) - State5: 1038174 # Observed Average IPI latency(ns) - State6: 1068784 # # --Timeout Latency Test-- # Baseline Average timeout diff(ns): 1420 # Observed Average timeout diff(ns) - State0: 1640 # Observed Average timeout diff(ns) - State1: 1764 # Observed Average timeout diff(ns) - State2: 1715 # Observed Average timeout diff(ns) - State3: 1845 # Observed Average timeout diff(ns) - State4: 16581 # Observed Average timeout diff(ns) - State5: 939977 # Observed Average timeout diff(ns) - State6: 1073024 Things to keep in mind: 1. This kernel module + bash driver does not guarantee idleness on a core when the IPI and the Timer is armed. It only invokes sleep and hopes that the core is idle once the IPI/Timer is invoked onto it. Hence this program must be run on a completely idle system for best results 2. Even on a completely idle system, there maybe book-keeping tasks or jitter tasks that can run on the core we want idle. This can create outliers in the latency measurement. Thankfully, these outliers should be large enough to easily weed them out. 3. A userspace only selftest variant was also sent out as RFC based on suggestions over the previous patchset to simply the kernel complexeity. However, a userspace only approach had more noise in the latency measurement due to userspace-kernel interactions which led to run to run variance and a lesser accurate test. Another downside of the nature of a userspace program is that it takes orders of magnitude longer to complete a full system test compared to the kernel framework. RFC patch: https://lkml.org/lkml/2020/9/2/356 4. For Intel Systems, the Timer based latencies don't exactly give out the measure of idle latencies. This is because of a hardware optimization mechanism that pre-arms a CPU when a timer is set to wakeup. That doesn't make this metric useless for Intel systems, it just means that is measuring IPI/Timer responding latency rather than idle wakeup latencies. (Source: https://lkml.org/lkml/2020/9/2/610) For solution to this problem, a hardware based latency analyzer is devised by Artem Bityutskiy from Intel. https://youtu.be/Opk92aQyvt0?t=8266 https://intel.github.io/wult/ Pratik R. Sampat (2): cpuidle: Extract IPI based and timer based wakeup latency from idle states selftest/cpuidle: Add support for cpuidle latency measurement drivers/cpuidle/Makefile | 1 + drivers/cpuidle/test-cpuidle_latency.c | 157 ++++++++ lib/Kconfig.debug | 10 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/cpuidle/Makefile | 6 + tools/testing/selftests/cpuidle/cpuidle.sh | 414 +++++++++++++++++++++ tools/testing/selftests/cpuidle/settings | 2 + 7 files changed, 591 insertions(+) create mode 100644 drivers/cpuidle/test-cpuidle_latency.c create mode 100644 tools/testing/selftests/cpuidle/Makefile create mode 100755 tools/testing/selftests/cpuidle/cpuidle.sh create mode 100644 tools/testing/selftests/cpuidle/settings -- 2.17.1

2 years, 11 months

2
3
0 0

[PATCH v4 1/2] selftests/sgx: Rename 'eenter' and 'sgx_call_vdso'

by Jarkko Sakkinen

Rename symbols for better clarity: * 'eenter' -> 'vdso_sgx_enter_enclave' * 'sgx_call_vdso' -> 'sgx_enter_enclave' Signed-off-by: Jarkko Sakkinen <jarkko(a)kernel.org> --- v2: Refined thh renames just a bit. tools/testing/selftests/sgx/call.S | 6 +++--- tools/testing/selftests/sgx/main.c | 25 +++++++++++++------------ tools/testing/selftests/sgx/main.h | 4 ++-- 3 files changed, 18 insertions(+), 17 deletions(-) diff --git a/tools/testing/selftests/sgx/call.S b/tools/testing/selftests/sgx/call.S index 4ecadc7490f4..b09a25890f3b 100644 --- a/tools/testing/selftests/sgx/call.S +++ b/tools/testing/selftests/sgx/call.S @@ -5,8 +5,8 @@ .text - .global sgx_call_vdso -sgx_call_vdso: + .global sgx_enter_enclave +sgx_enter_enclave: .cfi_startproc push %r15 .cfi_adjust_cfa_offset 8 @@ -27,7 +27,7 @@ sgx_call_vdso: .cfi_adjust_cfa_offset 8 push 0x38(%rsp) .cfi_adjust_cfa_offset 8 - call *eenter(%rip) + call *vdso_sgx_enter_enclave(%rip) add $0x10, %rsp .cfi_adjust_cfa_offset -0x10 pop %rbx diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c index d304a4044eb9..43da68388e25 100644 --- a/tools/testing/selftests/sgx/main.c +++ b/tools/testing/selftests/sgx/main.c @@ -21,7 +21,7 @@ #include "../kselftest.h" static const uint64_t MAGIC = 0x1122334455667788ULL; -vdso_sgx_enter_enclave_t eenter; +vdso_sgx_enter_enclave_t vdso_sgx_enter_enclave; struct vdso_symtab { Elf64_Sym *elf_symtab; @@ -149,7 +149,7 @@ int main(int argc, char *argv[]) { struct sgx_enclave_run run; struct vdso_symtab symtab; - Elf64_Sym *eenter_sym; + Elf64_Sym *sgx_enter_enclave_sym; uint64_t result = 0; struct encl encl; unsigned int i; @@ -194,29 +194,30 @@ int main(int argc, char *argv[]) if (!vdso_get_symtab(addr, &symtab)) goto err; - eenter_sym = vdso_symtab_get(&symtab, "__vdso_sgx_enter_enclave"); - if (!eenter_sym) + sgx_enter_enclave_sym = vdso_symtab_get(&symtab, "__vdso_sgx_enter_enclave"); + if (!sgx_enter_enclave_sym) goto err; - eenter = addr + eenter_sym->st_value; + vdso_sgx_enter_enclave = addr + sgx_enter_enclave_sym->st_value; - ret = sgx_call_vdso((void *)&MAGIC, &result, 0, EENTER, NULL, NULL, &run); - if (!report_results(&run, ret, result, "sgx_call_vdso")) + ret = sgx_enter_enclave((void *)&MAGIC, &result, 0, EENTER, + NULL, NULL, &run); + if (!report_results(&run, ret, result, "sgx_enter_enclave_unclobbered")) goto err; /* Invoke the vDSO directly. */ result = 0; - ret = eenter((unsigned long)&MAGIC, (unsigned long)&result, 0, EENTER, - 0, 0, &run); - if (!report_results(&run, ret, result, "eenter")) + ret = vdso_sgx_enter_enclave((unsigned long)&MAGIC, (unsigned long)&result, + 0, EENTER, 0, 0, &run); + if (!report_results(&run, ret, result, "sgx_enter_enclave")) goto err; /* And with an exit handler. */ run.user_handler = (__u64)user_handler; run.user_data = 0xdeadbeef; - ret = eenter((unsigned long)&MAGIC, (unsigned long)&result, 0, EENTER, - 0, 0, &run); + ret = vdso_sgx_enter_enclave((unsigned long)&MAGIC, (unsigned long)&result, + 0, EENTER, 0, 0, &run); if (!report_results(&run, ret, result, "user_handler")) goto err; diff --git a/tools/testing/selftests/sgx/main.h b/tools/testing/selftests/sgx/main.h index 67211a708f04..68672fd86cf9 100644 --- a/tools/testing/selftests/sgx/main.h +++ b/tools/testing/selftests/sgx/main.h @@ -35,7 +35,7 @@ bool encl_load(const char *path, struct encl *encl); bool encl_measure(struct encl *encl); bool encl_build(struct encl *encl); -int sgx_call_vdso(void *rdi, void *rsi, long rdx, u32 function, void *r8, void *r9, - struct sgx_enclave_run *run); +int sgx_enter_enclave(void *rdi, void *rsi, long rdx, u32 function, void *r8, void *r9, + struct sgx_enclave_run *run); #endif /* MAIN_H */ -- 2.31.1

2 years, 11 months

3
7
0 0

[PATCHv2] selftests: xfrm: put cleanup code into an exit trap

by Po-Hsu Lin

If the xfrm_policy.sh script gets terminated by any reason, the netns namespace files created by the test will be left alone. In this case a second attempt to run this test will fail with: # Cannot create namespace file "/run/netns/ns1": File exists Move the netns cleanup code into an exit trap so that we can ensure these files will be removed in the end. Changes in V2: - Update commit message and patch title. Signed-off-by: Po-Hsu Lin <po-hsu.lin(a)canonical.com> --- tools/testing/selftests/net/xfrm_policy.sh | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh index bdf450e..bb4632b 100755 --- a/tools/testing/selftests/net/xfrm_policy.sh +++ b/tools/testing/selftests/net/xfrm_policy.sh @@ -28,6 +28,11 @@ KEY_AES=0x0123456789abcdef0123456789012345 SPI1=0x1 SPI2=0x2 +cleanup() { + for i in 1 2 3 4;do ip netns del ns$i 2>/dev/null ;done +} +trap cleanup EXIT + do_esp_policy() { local ns=$1 local me=$2 @@ -481,6 +486,4 @@ check_hthresh_repeat "policies with repeated htresh change" check_random_order ns3 "policies inserted in random order" -for i in 1 2 3 4;do ip netns del ns$i;done - exit $ret -- 2.7.4

2 years, 11 months

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror May 2021