March 2021 - Linux-kselftest-mirror

[PATCH] selftests/sgx: fix EINIT failure dueto SGX_INVALID_SIGNATURE

by Tianjia Zhang

q2 is not always 384-byte length. Sometimes it only has 383-byte. In this case, the valid portion of q2 is reordered reversely for little endian order, and the remaining portion is filled with zero. Signed-off-by: Tianjia Zhang <tianjia.zhang(a)linux.alibaba.com> --- tools/testing/selftests/sgx/sigstruct.c | 41 +++++++++++++------------ 1 file changed, 21 insertions(+), 20 deletions(-) diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c index dee7a3d6c5a5..92bbc5a15c39 100644 --- a/tools/testing/selftests/sgx/sigstruct.c +++ b/tools/testing/selftests/sgx/sigstruct.c @@ -55,10 +55,27 @@ static bool alloc_q1q2_ctx(const uint8_t *s, const uint8_t *m, return true; } +static void reverse_bytes(void *data, int length) +{ + int i = 0; + int j = length - 1; + uint8_t temp; + uint8_t *ptr = data; + + while (i < j) { + temp = ptr[i]; + ptr[i] = ptr[j]; + ptr[j] = temp; + i++; + j--; + } +} + static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1, uint8_t *q2) { struct q1q2_ctx ctx; + int len; if (!alloc_q1q2_ctx(s, m, &ctx)) { fprintf(stderr, "Not enough memory for Q1Q2 calculation\n"); @@ -89,8 +106,10 @@ static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1, goto out; } - BN_bn2bin(ctx.q1, q1); - BN_bn2bin(ctx.q2, q2); + len = BN_bn2bin(ctx.q1, q1); + reverse_bytes(q1, len); + len = BN_bn2bin(ctx.q2, q2); + reverse_bytes(q2, len); free_q1q2_ctx(&ctx); return true; @@ -152,22 +171,6 @@ static RSA *gen_sign_key(void) return key; } -static void reverse_bytes(void *data, int length) -{ - int i = 0; - int j = length - 1; - uint8_t temp; - uint8_t *ptr = data; - - while (i < j) { - temp = ptr[i]; - ptr[i] = ptr[j]; - ptr[j] = temp; - i++; - j--; - } -} - enum mrtags { MRECREATE = 0x0045544145524345, MREADD = 0x0000000044444145, @@ -367,8 +370,6 @@ bool encl_measure(struct encl *encl) /* BE -> LE */ reverse_bytes(sigstruct->signature, SGX_MODULUS_SIZE); reverse_bytes(sigstruct->modulus, SGX_MODULUS_SIZE); - reverse_bytes(sigstruct->q1, SGX_MODULUS_SIZE); - reverse_bytes(sigstruct->q2, SGX_MODULUS_SIZE); EVP_MD_CTX_destroy(ctx); RSA_free(key); -- 2.19.1.3.ge56e4f7

3 years, 1 month

4
14
0 0

[PATCH v2] mm: huge_memory: a new debugfs interface for splitting THP tests.

by Zi Yan

From: Zi Yan <ziy(a)nvidia.com> We do not have a direct user interface of splitting the compound page backing a THP and there is no need unless we want to expose the THP implementation details to users. Adding an interface for debugging. By writing "<pid>,<vaddr_start>,<vaddr_end>" to <debugfs>/split_huge_pages_in_range_pid, THPs within the given virtual address range from the process with the given pid are split. It is used to test split_huge_page function. In addition, a selftest program is added to tools/testing/selftests/vm to utilize the interface by splitting PMD THPs and PTE-mapped THPs. Changelog: >From v1: 1. Removed unnecessary calling to vma_migratable, spotted by kernel test robot <lkp(a)intel.com>. 2. Dropped the use of find_mm_struct and code it directly, since there is no need for the permission check in that function and the function is only available when migration is on. 3. Added some comments in the selftest program to clarify how PTE-mapped THPs are formed. Signed-off-by: Zi Yan <ziy(a)nvidia.com> --- mm/huge_memory.c | 112 ++++++ tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 1 + .../selftests/vm/split_huge_page_test.c | 320 ++++++++++++++++++ 4 files changed, 434 insertions(+) create mode 100644 tools/testing/selftests/vm/split_huge_page_test.c diff --git a/mm/huge_memory.c b/mm/huge_memory.c index bff92dea5ab3..7797e8b2aba0 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -7,6 +7,7 @@ #include <linux/mm.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/highmem.h> @@ -2965,10 +2966,121 @@ static int split_huge_pages_set(void *data, u64 val) DEFINE_DEBUGFS_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set, "%llu\n"); +static ssize_t split_huge_pages_in_range_pid_write(struct file *file, + const char __user *buf, size_t count, loff_t *ppops) +{ + static DEFINE_MUTEX(mutex); + ssize_t ret; + char input_buf[80]; /* hold pid, start_vaddr, end_vaddr */ + int pid; + unsigned long vaddr_start, vaddr_end, addr; + struct task_struct *task; + struct mm_struct *mm; + unsigned long total = 0, split = 0; + + ret = mutex_lock_interruptible(&mutex); + if (ret) + return ret; + + ret = -EFAULT; + + memset(input_buf, 0, 80); + if (copy_from_user(input_buf, buf, min_t(size_t, count, 80))) + goto out; + + input_buf[79] = '\0'; + ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end); + if (ret != 3) { + ret = -EINVAL; + goto out; + } + vaddr_start &= PAGE_MASK; + vaddr_end &= PAGE_MASK; + + ret = strlen(input_buf); + pr_debug("split huge pages in pid: %d, vaddr: [%lx - %lx]\n", + pid, vaddr_start, vaddr_end); + + /* Find the task_struct from pid */ + rcu_read_lock(); + task = find_task_by_vpid(pid); + if (!task) { + rcu_read_unlock(); + ret = -ESRCH; + goto out; + } + get_task_struct(task); + rcu_read_unlock(); + + /* Find the mm_struct */ + mm = get_task_mm(task); + put_task_struct(task); + + if (!mm) { + ret = -EINVAL; + goto out; + } + + mmap_read_lock(mm); + /* + * always increase addr by PAGE_SIZE, since we could have a PTE page + * table filled with PTE-mapped THPs, each of which is distinct. + */ + for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) { + struct vm_area_struct *vma = find_vma(mm, addr); + unsigned int follflags; + struct page *page; + + if (!vma || addr < vma->vm_start) + break; + + /* FOLL_DUMP to ignore special (like zero) pages */ + follflags = FOLL_GET | FOLL_DUMP; + page = follow_page(vma, addr, follflags); + + if (IS_ERR(page)) + break; + if (!page) + break; + + if (!is_transparent_hugepage(page)) + continue; + + total++; + if (!can_split_huge_page(compound_head(page), NULL)) + continue; + + if (!trylock_page(page)) + continue; + + if (!split_huge_page(page)) + split++; + + unlock_page(page); + put_page(page); + } + mmap_read_unlock(mm); + mmput(mm); + + pr_debug("%lu of %lu THP split\n", split, total); +out: + mutex_unlock(&mutex); + return ret; + +} + +static const struct file_operations split_huge_pages_in_range_pid_fops = { + .owner = THIS_MODULE, + .write = split_huge_pages_in_range_pid_write, + .llseek = no_llseek, +}; + static int __init split_huge_pages_debugfs(void) { debugfs_create_file("split_huge_pages", 0200, NULL, NULL, &split_huge_pages_fops); + debugfs_create_file("split_huge_pages_in_range_pid", 0200, NULL, NULL, + &split_huge_pages_in_range_pid_fops); return 0; } late_initcall(split_huge_pages_debugfs); diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 9a35c3f6a557..1f651e85ed60 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -22,3 +22,4 @@ map_fixed_noreplace write_to_hugetlbfs hmm-tests local_config.* +split_huge_page_test diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index d42115e4284d..4cbc91d6869f 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -42,6 +42,7 @@ TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd +TEST_GEN_FILES += split_huge_page_test ifeq ($(MACHINE),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32) diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c new file mode 100644 index 000000000000..0c6532dfdd96 --- /dev/null +++ b/tools/testing/selftests/vm/split_huge_page_test.c @@ -0,0 +1,320 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A test of splitting PMD THPs and PTE-mapped THPs from a specified virtual + * address range in a process via <debugfs>/split_huge_pages_in_range_pid + * interface. + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include "numa.h" +#include <unistd.h> +#include <errno.h> +#include <inttypes.h> +#include <string.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <sys/mman.h> +#include <sys/time.h> +#include <sys/wait.h> +#include <malloc.h> +#include <stdbool.h> + +uint64_t pagesize; +unsigned int pageshift; +uint64_t pmd_pagesize; + +#define PMD_SIZE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size" +#define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages_in_range_pid" +#define SMAP_PATH "/proc/self/smaps" +#define INPUT_MAX 80 + +#define PFN_MASK ((1UL<<55)-1) +#define KPF_THP (1UL<<22) + +int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file) +{ + uint64_t paddr; + uint64_t page_flags; + + if (pagemap_file) { + pread(pagemap_file, &paddr, sizeof(paddr), + ((long)vaddr >> pageshift) * sizeof(paddr)); + + if (kpageflags_file) { + pread(kpageflags_file, &page_flags, sizeof(page_flags), + (paddr & PFN_MASK) * sizeof(page_flags)); + + return !!(page_flags & KPF_THP); + } + } + return 0; +} + + +static uint64_t read_pmd_pagesize(void) +{ + int fd; + char buf[20]; + ssize_t num_read; + + fd = open(PMD_SIZE_PATH, O_RDONLY); + if (fd == -1) { + perror("Open hpage_pmd_size failed"); + exit(EXIT_FAILURE); + } + num_read = read(fd, buf, 19); + if (num_read < 1) { + close(fd); + perror("Read hpage_pmd_size failed"); + exit(EXIT_FAILURE); + } + buf[num_read] = '\0'; + close(fd); + + return strtoul(buf, NULL, 10); +} + +static int write_file(const char *path, const char *buf, size_t buflen) +{ + int fd; + ssize_t numwritten; + + fd = open(path, O_WRONLY); + if (fd == -1) + return 0; + + numwritten = write(fd, buf, buflen - 1); + close(fd); + if (numwritten < 1) + return 0; + + return (unsigned int) numwritten; +} + +static void write_debugfs(int pid, uint64_t vaddr_start, uint64_t vaddr_end) +{ + char input[INPUT_MAX]; + int ret; + + ret = snprintf(input, INPUT_MAX, "%d,0x%lx,0x%lx", pid, vaddr_start, + vaddr_end); + if (ret >= INPUT_MAX) { + printf("%s: Debugfs input is too long\n", __func__); + exit(EXIT_FAILURE); + } + + if (!write_file(SPLIT_DEBUGFS, input, ret + 1)) { + perror(SPLIT_DEBUGFS); + exit(EXIT_FAILURE); + } +} + +#define MAX_LINE_LENGTH 500 + +static bool check_for_pattern(FILE *fp, const char *pattern, char *buf) +{ + while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) { + if (!strncmp(buf, pattern, strlen(pattern))) + return true; + } + return false; +} + +static uint64_t check_huge(void *addr) +{ + uint64_t thp = 0; + int ret; + FILE *fp; + char buffer[MAX_LINE_LENGTH]; + char addr_pattern[MAX_LINE_LENGTH]; + + ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", + (unsigned long) addr); + if (ret >= MAX_LINE_LENGTH) { + printf("%s: Pattern is too long\n", __func__); + exit(EXIT_FAILURE); + } + + + fp = fopen(SMAP_PATH, "r"); + if (!fp) { + printf("%s: Failed to open file %s\n", __func__, SMAP_PATH); + exit(EXIT_FAILURE); + } + if (!check_for_pattern(fp, addr_pattern, buffer)) + goto err_out; + + /* + * Fetch the AnonHugePages: in the same block and check the number of + * hugepages. + */ + if (!check_for_pattern(fp, "AnonHugePages:", buffer)) + goto err_out; + + if (sscanf(buffer, "AnonHugePages:%10ld kB", &thp) != 1) { + printf("Reading smap error\n"); + exit(EXIT_FAILURE); + } + +err_out: + fclose(fp); + return thp; +} + +void split_pmd_thp(void) +{ + char *one_page; + size_t len = 4 * pmd_pagesize; + uint64_t thp_size; + size_t i; + + one_page = memalign(pmd_pagesize, len); + + madvise(one_page, len, MADV_HUGEPAGE); + + for (i = 0; i < len; i++) + one_page[i] = (char)i; + + thp_size = check_huge(one_page); + if (!thp_size) { + printf("No THP is allocatd"); + exit(EXIT_FAILURE); + } + + /* split all THPs */ + write_debugfs(getpid(), (uint64_t)one_page, (uint64_t)one_page + len); + + for (i = 0; i < len; i++) + if (one_page[i] != (char)i) { + printf("%ld byte corrupted\n", i); + exit(EXIT_FAILURE); + } + + + thp_size = check_huge(one_page); + if (thp_size) { + printf("Still %ld kB AnonHugePages not split\n", thp_size); + exit(EXIT_FAILURE); + } + + printf("Split huge pages successful\n"); + free(one_page); +} + +void split_pte_mapped_thp(void) +{ + char *one_page, *pte_mapped, *pte_mapped2; + size_t len = 4 * pmd_pagesize; + uint64_t thp_size; + size_t i; + const char *pagemap_template = "/proc/%d/pagemap"; + const char *kpageflags_proc = "/proc/kpageflags"; + char pagemap_proc[255]; + int pagemap_fd; + int kpageflags_fd; + + if (snprintf(pagemap_proc, 255, pagemap_template, getpid()) < 0) { + perror("get pagemap proc error"); + exit(EXIT_FAILURE); + } + pagemap_fd = open(pagemap_proc, O_RDONLY); + + if (pagemap_fd == -1) { + perror("read pagemap:"); + exit(EXIT_FAILURE); + } + + kpageflags_fd = open(kpageflags_proc, O_RDONLY); + + if (kpageflags_fd == -1) { + perror("read kpageflags:"); + exit(EXIT_FAILURE); + } + + one_page = mmap((void *)(1UL << 30), len, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + + madvise(one_page, len, MADV_HUGEPAGE); + + for (i = 0; i < len; i++) + one_page[i] = (char)i; + + thp_size = check_huge(one_page); + if (!thp_size) { + printf("No THP is allocatd"); + exit(EXIT_FAILURE); + } + + /* remap the first pagesize of first THP */ + pte_mapped = mremap(one_page, pagesize, pagesize, MREMAP_MAYMOVE); + + /* remap the Nth pagesize of Nth THP */ + for (i = 1; i < 4; i++) { + pte_mapped2 = mremap(one_page + pmd_pagesize * i + pagesize * i, + pagesize, pagesize, + MREMAP_MAYMOVE|MREMAP_FIXED, + pte_mapped + pagesize * i); + if (pte_mapped2 == (char *)-1) { + perror("mremap failed"); + exit(EXIT_FAILURE); + } + } + + /* smap does not show THPs after mremap, use kpageflags instead */ + thp_size = 0; + for (i = 0; i < pagesize * 4; i++) + if (i % pagesize == 0 && + is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) + thp_size++; + + if (thp_size != 4) { + printf("Some THPs are missing during mremap\n"); + exit(EXIT_FAILURE); + } + + /* split all remapped THPs */ + write_debugfs(getpid(), (uint64_t)pte_mapped, + (uint64_t)pte_mapped + pagesize * 4); + + /* smap does not show THPs after mremap, use kpageflags instead */ + thp_size = 0; + for (i = 0; i < pagesize * 4; i++) { + if (pte_mapped[i] != (char)i) { + printf("%ld byte corrupted\n", i); + exit(EXIT_FAILURE); + } + if (i % pagesize == 0 && + is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) + thp_size++; + } + + if (thp_size) { + printf("Still %ld THPs not split\n", thp_size); + exit(EXIT_FAILURE); + } + + printf("Split PTE-mapped huge pages successful\n"); + munmap(one_page, len); + close(pagemap_fd); + close(kpageflags_fd); +} + +int main(int argc, char **argv) +{ + if (geteuid() != 0) { + printf("Please run the benchmark as root\n"); + exit(EXIT_FAILURE); + } + + pagesize = getpagesize(); + pageshift = ffs(pagesize) - 1; + pmd_pagesize = read_pmd_pagesize(); + + split_pmd_thp(); + split_pte_mapped_thp(); + + return 0; +} -- 2.30.1

3 years, 1 month

3
3
0 0

[PATCH] selftests/bpf: fix warning comparing pointer to 0

by Jiapeng Chong

Fix the following coccicheck warning: ./tools/testing/selftests/bpf/progs/test_global_func10.c:17:12-13: WARNING comparing pointer to 0. Reported-by: Abaci Robot <abaci(a)linux.alibaba.com> Signed-off-by: Jiapeng Chong <jiapeng.chong(a)linux.alibaba.com> --- tools/testing/selftests/bpf/progs/test_global_func10.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/progs/test_global_func10.c b/tools/testing/selftests/bpf/progs/test_global_func10.c index 61c2ae9..97b7031 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func10.c +++ b/tools/testing/selftests/bpf/progs/test_global_func10.c @@ -14,7 +14,7 @@ struct Big { __noinline int foo(const struct Big *big) { - if (big == 0) + if (!big) return 0; return bpf_get_prandom_u32() < big->y; -- 1.8.3.1

3 years, 1 month

3
2
0 0

[PATCH] bpf: fix warning comparing pointer to 0

by Jiapeng Chong

Fix the following coccicheck warning: ./tools/testing/selftests/bpf/progs/fentry_test.c:67:12-13: WARNING comparing pointer to 0. Reported-by: Abaci Robot <abaci(a)linux.alibaba.com> Signed-off-by: Jiapeng Chong <jiapeng.chong(a)linux.alibaba.com> --- tools/testing/selftests/bpf/progs/fentry_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c index 5f645fd..52a550d 100644 --- a/tools/testing/selftests/bpf/progs/fentry_test.c +++ b/tools/testing/selftests/bpf/progs/fentry_test.c @@ -64,7 +64,7 @@ struct bpf_fentry_test_t { SEC("fentry/bpf_fentry_test7") int BPF_PROG(test7, struct bpf_fentry_test_t *arg) { - if (arg == 0) + if (!arg) test7_result = 1; return 0; } -- 1.8.3.1

3 years, 1 month

2
1
0 0

[PATCH v2] kunit: fix checkpatch warning

by Lucas Stankus

Tidy up code by fixing the following checkpatch warnings: CHECK: Alignment should match open parenthesis CHECK: Lines should not end with a '(' Signed-off-by: Lucas Stankus <lucas.p.stankus(a)gmail.com> --- Change log v1 -> v2 fixed signed-off-by tag lib/kunit/assert.c | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-) diff --git a/lib/kunit/assert.c b/lib/kunit/assert.c index e0ec7d6fed6f..acfbf86bddd6 100644 --- a/lib/kunit/assert.c +++ b/lib/kunit/assert.c @@ -25,7 +25,7 @@ void kunit_base_assert_format(const struct kunit_assert *assert, } string_stream_add(stream, "%s FAILED at %s:%d\n", - expect_or_assert, assert->file, assert->line); + expect_or_assert, assert->file, assert->line); } EXPORT_SYMBOL_GPL(kunit_base_assert_format); @@ -48,8 +48,9 @@ EXPORT_SYMBOL_GPL(kunit_fail_assert_format); void kunit_unary_assert_format(const struct kunit_assert *assert, struct string_stream *stream) { - struct kunit_unary_assert *unary_assert = container_of( - assert, struct kunit_unary_assert, assert); + struct kunit_unary_assert *unary_assert; + + unary_assert = container_of(assert, struct kunit_unary_assert, assert); kunit_base_assert_format(assert, stream); if (unary_assert->expected_true) @@ -67,8 +68,10 @@ EXPORT_SYMBOL_GPL(kunit_unary_assert_format); void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, struct string_stream *stream) { - struct kunit_ptr_not_err_assert *ptr_assert = container_of( - assert, struct kunit_ptr_not_err_assert, assert); + struct kunit_ptr_not_err_assert *ptr_assert; + + ptr_assert = container_of(assert, struct kunit_ptr_not_err_assert, + assert); kunit_base_assert_format(assert, stream); if (!ptr_assert->value) { @@ -111,8 +114,10 @@ static bool is_literal(struct kunit *test, const char *text, long long value, void kunit_binary_assert_format(const struct kunit_assert *assert, struct string_stream *stream) { - struct kunit_binary_assert *binary_assert = container_of( - assert, struct kunit_binary_assert, assert); + struct kunit_binary_assert *binary_assert; + + binary_assert = container_of(assert, struct kunit_binary_assert, + assert); kunit_base_assert_format(assert, stream); string_stream_add(stream, @@ -137,8 +142,10 @@ EXPORT_SYMBOL_GPL(kunit_binary_assert_format); void kunit_binary_ptr_assert_format(const struct kunit_assert *assert, struct string_stream *stream) { - struct kunit_binary_ptr_assert *binary_assert = container_of( - assert, struct kunit_binary_ptr_assert, assert); + struct kunit_binary_ptr_assert *binary_assert; + + binary_assert = container_of(assert, struct kunit_binary_ptr_assert, + assert); kunit_base_assert_format(assert, stream); string_stream_add(stream, @@ -159,8 +166,10 @@ EXPORT_SYMBOL_GPL(kunit_binary_ptr_assert_format); void kunit_binary_str_assert_format(const struct kunit_assert *assert, struct string_stream *stream) { - struct kunit_binary_str_assert *binary_assert = container_of( - assert, struct kunit_binary_str_assert, assert); + struct kunit_binary_str_assert *binary_assert; + + binary_assert = container_of(assert, struct kunit_binary_str_assert, + assert); kunit_base_assert_format(assert, stream); string_stream_add(stream, -- 2.30.1

3 years, 1 month

3
4
0 0

[PATCH] kselftest: arm64: Fix exit code of sve-ptrace

by Mark Brown

We track if sve-ptrace encountered a failure in a variable but don't actually use that value when we exit the program, do so. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/arm64/fp/sve-ptrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c index b2282be6f938..612d3899614a 100644 --- a/tools/testing/selftests/arm64/fp/sve-ptrace.c +++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c @@ -332,5 +332,5 @@ int main(void) ksft_print_cnts(); - return 0; + return ret; } -- 2.20.1

3 years, 1 month

2
1
0 0

[PATCH v2 0/5] userfaultfd: support minor fault handling for shmem

by Axel Rasmussen

Base ==== This series is based on top of my series which adds minor fault handling for hugetlbfs [1]. (And, therefore, it is based on 5.12-rc1 and Peter Xu's series for disabling huge pmd sharing as well.) [1] https://lore.kernel.org/linux-fsdevel/20210301222728.176417-1-axelrasmussen… Changelog ========= v1->v2: - For UFFDIO_CONTINUE, don't mess with page flags. Just use find_lock_page to get a locked page from the page cache, instead of doing __SetPageLocked. This fixes a VM_BUG_ON v1 hit when handling minor faults for THP-backed shmem (a tmpfs mounted with huge=always). Overview ======== See my original series linked above for a detailed overview of minor fault handling in general. The feature in this series works exactly like the hugetblfs version (from userspace's perspective). I'm sending this as a separate series because: - The original minor fault handling series has a full set of R-Bs, and seems close to being merged. So, it seems reasonable to start looking at this next step, which extends the basic functionality. - shmem is different enough that this series may require some additional work before it's ready, and I don't want to delay the original series unnecessarily by bundling them together. Use Case ======== In some cases it is useful to have VM memory backed by tmpfs instead of hugetlbfs. So, this feature will be used to support the same VM live migration use case described in my original series. Additionally, Android folks (Lokesh Gidra <lokeshgidra(a)google.com>) hope to optimize the Android Runtime garbage collector using this feature: "The plan is to use userfaultfd for concurrently compacting the heap. With this feature, the heap can be shared-mapped at another location where the GC-thread(s) could continue the compaction operation without the need to invoke userfault ioctl(UFFDIO_COPY) each time. OTOH, if and when Java threads get faults on the heap, UFFDIO_CONTINUE can be used to resume execution. Furthermore, this feature enables updating references in the 'non-moving' portion of the heap efficiently. Without this feature, uneccessary page copying (ioctl(UFFDIO_COPY)) would be required." Axel Rasmussen (5): userfaultfd: support minor fault handling for shmem userfaultfd/selftests: use memfd_create for shmem test type userfaultfd/selftests: create alias mappings in the shmem test userfaultfd/selftests: reinitialize test context in each test userfaultfd/selftests: exercise minor fault handling shmem support fs/userfaultfd.c | 6 +- include/linux/shmem_fs.h | 26 +- include/uapi/linux/userfaultfd.h | 4 +- mm/memory.c | 8 +- mm/shmem.c | 92 +++---- mm/userfaultfd.c | 27 +- tools/testing/selftests/vm/userfaultfd.c | 322 +++++++++++++++-------- 7 files changed, 295 insertions(+), 190 deletions(-) -- 2.30.1.766.gb4fecdf3b7-goog

3 years, 1 month

2
9
0 0

[PATCH] mm: huge_memory: a new debugfs interface for splitting THP tests.

by Zi Yan

From: Zi Yan <ziy(a)nvidia.com> By writing "<pid>,<vaddr_start>,<vaddr_end>" to <debugfs>/split_huge_pages_in_range_pid, THPs in the process with the given pid and virtual address range are split. It is used to test split_huge_page function. In addition, a selftest program is added to tools/testing/selftests/vm to utilize the interface by splitting PMD THPs and PTE-mapped THPs. Signed-off-by: Zi Yan <ziy(a)nvidia.com> --- mm/huge_memory.c | 98 ++++++ mm/internal.h | 1 + mm/migrate.c | 2 +- tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 1 + .../selftests/vm/split_huge_page_test.c | 318 ++++++++++++++++++ 6 files changed, 420 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/vm/split_huge_page_test.c diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 395c75111d33..818172f887bf 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -7,6 +7,7 @@ #include <linux/mm.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/highmem.h> @@ -2971,10 +2972,107 @@ static int split_huge_pages_set(void *data, u64 val) DEFINE_DEBUGFS_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set, "%llu\n"); +static ssize_t split_huge_pages_in_range_pid_write(struct file *file, + const char __user *buf, size_t count, loff_t *ppops) +{ + static DEFINE_MUTEX(mutex); + ssize_t ret; + char input_buf[80]; /* hold pid, start_vaddr, end_vaddr */ + int pid; + unsigned long vaddr_start, vaddr_end, addr; + nodemask_t task_nodes; + struct mm_struct *mm; + unsigned long total = 0, split = 0; + + ret = mutex_lock_interruptible(&mutex); + if (ret) + return ret; + + ret = -EFAULT; + + memset(input_buf, 0, 80); + if (copy_from_user(input_buf, buf, min_t(size_t, count, 80))) + goto out; + + input_buf[79] = '\0'; + ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end); + if (ret != 3) { + ret = -EINVAL; + goto out; + } + vaddr_start &= PAGE_MASK; + vaddr_end &= PAGE_MASK; + + ret = strlen(input_buf); + pr_debug("split huge pages in pid: %d, vaddr: [%lx - %lx]\n", + pid, vaddr_start, vaddr_end); + + mm = find_mm_struct(pid, &task_nodes); + if (IS_ERR(mm)) { + ret = -EINVAL; + goto out; + } + + mmap_read_lock(mm); + /* + * always increase addr by PAGE_SIZE, since we could have a PTE page + * table filled with PTE-mapped THPs, each of which is distinct. + */ + for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) { + struct vm_area_struct *vma = find_vma(mm, addr); + unsigned int follflags; + struct page *page; + + if (!vma || addr < vma->vm_start || !vma_migratable(vma)) + break; + + /* FOLL_DUMP to ignore special (like zero) pages */ + follflags = FOLL_GET | FOLL_DUMP; + page = follow_page(vma, addr, follflags); + + if (IS_ERR(page)) + break; + if (!page) + break; + + if (!is_transparent_hugepage(page)) + continue; + + total++; + if (!can_split_huge_page(compound_head(page), NULL)) + continue; + + if (!trylock_page(page)) + continue; + + if (!split_huge_page(page)) + split++; + + unlock_page(page); + put_page(page); + } + mmap_read_unlock(mm); + mmput(mm); + + pr_debug("%lu of %lu THP split\n", split, total); +out: + mutex_unlock(&mutex); + return ret; + +} + +static const struct file_operations split_huge_pages_in_range_pid_fops = { + .owner = THIS_MODULE, + .write = split_huge_pages_in_range_pid_write, + .llseek = no_llseek, +}; + static int __init split_huge_pages_debugfs(void) { debugfs_create_file("split_huge_pages", 0200, NULL, NULL, &split_huge_pages_fops); + debugfs_create_file("split_huge_pages_in_range_pid", 0200, NULL, NULL, + &split_huge_pages_in_range_pid_fops); return 0; } late_initcall(split_huge_pages_debugfs); diff --git a/mm/internal.h b/mm/internal.h index 9902648f2206..1659d00100ef 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -623,4 +623,5 @@ struct migration_target_control { gfp_t gfp_mask; }; +struct mm_struct *find_mm_struct(pid_t pid, nodemask_t *mem_nodes); #endif /* __MM_INTERNAL_H */ diff --git a/mm/migrate.c b/mm/migrate.c index 62b81d5257aa..ce5f213debb2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1913,7 +1913,7 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, return nr_pages ? -EFAULT : 0; } -static struct mm_struct *find_mm_struct(pid_t pid, nodemask_t *mem_nodes) +struct mm_struct *find_mm_struct(pid_t pid, nodemask_t *mem_nodes) { struct task_struct *task; struct mm_struct *mm; diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 9a35c3f6a557..1f651e85ed60 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -22,3 +22,4 @@ map_fixed_noreplace write_to_hugetlbfs hmm-tests local_config.* +split_huge_page_test diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index d42115e4284d..4cbc91d6869f 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -42,6 +42,7 @@ TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd +TEST_GEN_FILES += split_huge_page_test ifeq ($(MACHINE),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32) diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c new file mode 100644 index 000000000000..8ea8000fda62 --- /dev/null +++ b/tools/testing/selftests/vm/split_huge_page_test.c @@ -0,0 +1,318 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A test of splitting PMD THPs and PTE-mapped THPs from a specified virtual + * address range in a process via <debugfs>/split_huge_pages_in_range_pid + * interface. + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include "numa.h" +#include <unistd.h> +#include <errno.h> +#include <inttypes.h> +#include <string.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <sys/mman.h> +#include <sys/time.h> +#include <sys/wait.h> +#include <malloc.h> +#include <stdbool.h> + +uint64_t pagesize; +unsigned int pageshift; +uint64_t pmd_pagesize; + +#define PMD_SIZE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size" +#define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages_in_range_pid" +#define SMAP_PATH "/proc/self/smaps" +#define INPUT_MAX 80 + +#define PFN_MASK ((1UL<<55)-1) +#define KPF_THP (1UL<<22) + +int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file) +{ + uint64_t paddr; + uint64_t page_flags; + + if (pagemap_file) { + pread(pagemap_file, &paddr, sizeof(paddr), + ((long)vaddr >> pageshift) * sizeof(paddr)); + + if (kpageflags_file) { + pread(kpageflags_file, &page_flags, sizeof(page_flags), + (paddr & PFN_MASK) * sizeof(page_flags)); + + return !!(page_flags & KPF_THP); + } + } + return 0; +} + + +static uint64_t read_pmd_pagesize(void) +{ + int fd; + char buf[20]; + ssize_t num_read; + + fd = open(PMD_SIZE_PATH, O_RDONLY); + if (fd == -1) { + perror("Open hpage_pmd_size failed"); + exit(EXIT_FAILURE); + } + num_read = read(fd, buf, 19); + if (num_read < 1) { + close(fd); + perror("Read hpage_pmd_size failed"); + exit(EXIT_FAILURE); + } + buf[num_read] = '\0'; + close(fd); + + return strtoul(buf, NULL, 10); +} + +static int write_file(const char *path, const char *buf, size_t buflen) +{ + int fd; + ssize_t numwritten; + + fd = open(path, O_WRONLY); + if (fd == -1) + return 0; + + numwritten = write(fd, buf, buflen - 1); + close(fd); + if (numwritten < 1) + return 0; + + return (unsigned int) numwritten; +} + +static void write_debugfs(int pid, uint64_t vaddr_start, uint64_t vaddr_end) +{ + char input[INPUT_MAX]; + int ret; + + ret = snprintf(input, INPUT_MAX, "%d,0x%lx,0x%lx", pid, vaddr_start, + vaddr_end); + if (ret >= INPUT_MAX) { + printf("%s: Debugfs input is too long\n", __func__); + exit(EXIT_FAILURE); + } + + if (!write_file(SPLIT_DEBUGFS, input, ret + 1)) { + perror(SPLIT_DEBUGFS); + exit(EXIT_FAILURE); + } +} + +#define MAX_LINE_LENGTH 500 + +static bool check_for_pattern(FILE *fp, const char *pattern, char *buf) +{ + while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) { + if (!strncmp(buf, pattern, strlen(pattern))) + return true; + } + return false; +} + +static uint64_t check_huge(void *addr) +{ + uint64_t thp = 0; + int ret; + FILE *fp; + char buffer[MAX_LINE_LENGTH]; + char addr_pattern[MAX_LINE_LENGTH]; + + ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", + (unsigned long) addr); + if (ret >= MAX_LINE_LENGTH) { + printf("%s: Pattern is too long\n", __func__); + exit(EXIT_FAILURE); + } + + + fp = fopen(SMAP_PATH, "r"); + if (!fp) { + printf("%s: Failed to open file %s\n", __func__, SMAP_PATH); + exit(EXIT_FAILURE); + } + if (!check_for_pattern(fp, addr_pattern, buffer)) + goto err_out; + + /* + * Fetch the AnonHugePages: in the same block and check the number of + * hugepages. + */ + if (!check_for_pattern(fp, "AnonHugePages:", buffer)) + goto err_out; + + if (sscanf(buffer, "AnonHugePages:%10ld kB", &thp) != 1) { + printf("Reading smap error\n"); + exit(EXIT_FAILURE); + } + +err_out: + fclose(fp); + return thp; +} + +void split_pmd_thp(void) +{ + char *one_page; + size_t len = 4 * pmd_pagesize; + uint64_t thp_size; + size_t i; + + one_page = memalign(pmd_pagesize, len); + + madvise(one_page, len, MADV_HUGEPAGE); + + for (i = 0; i < len; i++) + one_page[i] = (char)i; + + thp_size = check_huge(one_page); + if (!thp_size) { + printf("No THP is allocatd"); + exit(EXIT_FAILURE); + } + + /* split all possible huge pages */ + write_debugfs(getpid(), (uint64_t)one_page, (uint64_t)one_page + len); + + for (i = 0; i < len; i++) + if (one_page[i] != (char)i) { + printf("%ld byte corrupted\n", i); + exit(EXIT_FAILURE); + } + + + thp_size = check_huge(one_page); + if (thp_size) { + printf("Still %ld kB AnonHugePages not split\n", thp_size); + exit(EXIT_FAILURE); + } + + printf("Split huge pages successful\n"); + free(one_page); +} + +void split_pte_mapped_thp(void) +{ + char *one_page, *pte_mapped, *pte_mapped2; + size_t len = 4 * pmd_pagesize; + uint64_t thp_size; + size_t i; + const char *pagemap_template = "/proc/%d/pagemap"; + const char *kpageflags_proc = "/proc/kpageflags"; + char pagemap_proc[255]; + int pagemap_fd; + int kpageflags_fd; + + if (snprintf(pagemap_proc, 255, pagemap_template, getpid()) < 0) { + perror("get pagemap proc error"); + exit(EXIT_FAILURE); + } + pagemap_fd = open(pagemap_proc, O_RDONLY); + + if (pagemap_fd == -1) { + perror("read pagemap:"); + exit(EXIT_FAILURE); + } + + kpageflags_fd = open(kpageflags_proc, O_RDONLY); + + if (kpageflags_fd == -1) { + perror("read kpageflags:"); + exit(EXIT_FAILURE); + } + + one_page = mmap((void *)(1UL << 30), len, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + + madvise(one_page, len, MADV_HUGEPAGE); + + for (i = 0; i < len; i++) + one_page[i] = (char)i; + + thp_size = check_huge(one_page); + if (!thp_size) { + printf("No THP is allocatd"); + exit(EXIT_FAILURE); + } + + pte_mapped = mremap(one_page, pagesize, pagesize, MREMAP_MAYMOVE); + + for (i = 1; i < 4; i++) { + pte_mapped2 = mremap(one_page + pmd_pagesize * i + pagesize * i, + pagesize, pagesize, + MREMAP_MAYMOVE|MREMAP_FIXED, + pte_mapped + pagesize * i); + if (pte_mapped2 == (char *)-1) { + perror("mremap failed"); + exit(EXIT_FAILURE); + } + } + + /* smap does not show THPs after mremap, use kpageflags instead */ + thp_size = 0; + for (i = 0; i < pagesize * 4; i++) + if (i % pagesize == 0 && + is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) + thp_size++; + + if (thp_size != 4) { + printf("Some THPs are missing during mremap\n"); + exit(EXIT_FAILURE); + } + + /* split all possible huge pages */ + write_debugfs(getpid(), (uint64_t)pte_mapped, + (uint64_t)pte_mapped + pagesize * 4); + + /* smap does not show THPs after mremap, use kpageflags instead */ + thp_size = 0; + for (i = 0; i < pagesize * 4; i++) { + if (pte_mapped[i] != (char)i) { + printf("%ld byte corrupted\n", i); + exit(EXIT_FAILURE); + } + if (i % pagesize == 0 && + is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) + thp_size++; + } + + if (thp_size) { + printf("Still %ld THPs not split\n", thp_size); + exit(EXIT_FAILURE); + } + + printf("Split PTE-mapped huge pages successful\n"); + munmap(one_page, len); + close(pagemap_fd); + close(kpageflags_fd); +} + +int main(int argc, char **argv) +{ + if (geteuid() != 0) { + printf("Please run the benchmark as root\n"); + exit(EXIT_FAILURE); + } + + pagesize = getpagesize(); + pageshift = ffs(pagesize) - 1; + pmd_pagesize = read_pmd_pagesize(); + + split_pmd_thp(); + split_pte_mapped_thp(); + + return 0; +} -- 2.30.1

3 years, 1 month

5
13
0 0

[PATCH bpf-next] selftests/bpf: Fix typo in Makefile

by Jean-Philippe Brucker

The selftest build fails when trying to install the scripts: rsync: [sender] link_stat "tools/testing/selftests/bpf/test_docs_build.sh" failed: No such file or directory (2) Fix the filename. Fixes: a01d935b2e09 ("tools/bpf: Remove bpf-helpers from bpftool docs") Signed-off-by: Jean-Philippe Brucker <jean-philippe(a)linaro.org> --- tools/testing/selftests/bpf/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index b5827464c6b5..c3999587bc23 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -68,7 +68,7 @@ TEST_PROGS := test_kmod.sh \ test_bpftool_build.sh \ test_bpftool.sh \ test_bpftool_metadata.sh \ - test_docs_build.sh \ + test_doc_build.sh \ test_xsk.sh TEST_PROGS_EXTENDED := with_addr.sh \ -- 2.30.1

3 years, 1 month

3
2
0 0

Re: [PATCH] mm: huge_memory: a new debugfs interface for splitting THP tests.

by Zi Yan

+ the rest of cc back and move your reply inline. On 8 Mar 2021, at 12:47, Mika Penttilä wrote: >> >> >> On 8.3.2021 17.22, Zi Yan wrote: >>> From: Zi Yan <ziy(a)nvidia.com> >>> >>> By writing "<pid>,<vaddr_start>,<vaddr_end>" to >>> <debugfs>/split_huge_pages_in_range_pid, THPs in the process with the >>> given pid and virtual address range are split. It is used to test >>> split_huge_page function. In addition, a selftest program is added to >>> tools/testing/selftests/vm to utilize the interface by splitting >>> PMD THPs and PTE-mapped THPs. >>> >>> Signed-off-by: Zi Yan <ziy(a)nvidia.com> >> >> Hi! >> >> I think your test program is not correct. The mremaps shrink to one page, after the first mremap the pointers are bogus. >> Also, mremap splits pmds with split_huge_pmd().. And those you can't split with split_huge_page because it is a normal pmd. >> Maybe you didn't indent to shrink to page size? >> >> >> --Mika > Hi, > > Sorry, wrote too fast.. the splits are okay of course from pte mapped thp to plain pages (mremap -> split pmd -> debugfs write ->split pages). > But the remap offsets are I think maybe not you wanted. You mean I mremap the first PAGESIZE from first THP, second PAGESIZE from second THP and so on to create PTE-mapped THPs? I did it on purpose so split_huge_page can work on different part of THPs. >> >> >>> --- >>> mm/huge_memory.c | 98 ++++++ >>> mm/internal.h | 1 + >>> mm/migrate.c | 2 +- >>> tools/testing/selftests/vm/.gitignore | 1 + >>> tools/testing/selftests/vm/Makefile | 1 + >>> .../selftests/vm/split_huge_page_test.c | 318 ++++++++++++++++++ >>> 6 files changed, 420 insertions(+), 1 deletion(-) >>> create mode 100644 tools/testing/selftests/vm/split_huge_page_test.c >>> >>> diff --git a/mm/huge_memory.c b/mm/huge_memory.c >>> index 395c75111d33..818172f887bf 100644 >>> --- a/mm/huge_memory.c >>> +++ b/mm/huge_memory.c >>> @@ -7,6 +7,7 @@ >>> #include <linux/mm.h> >>> #include <linux/sched.h> >>> +#include <linux/sched/mm.h> >>> #include <linux/sched/coredump.h> >>> #include <linux/sched/numa_balancing.h> >>> #include <linux/highmem.h> >>> @@ -2971,10 +2972,107 @@ static int split_huge_pages_set(void *data, u64 val) >>> DEFINE_DEBUGFS_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set, >>> "%llu\n"); >>> +static ssize_t split_huge_pages_in_range_pid_write(struct file *file, >>> + const char __user *buf, size_t count, loff_t *ppops) >>> +{ >>> + static DEFINE_MUTEX(mutex); >>> + ssize_t ret; >>> + char input_buf[80]; /* hold pid, start_vaddr, end_vaddr */ >>> + int pid; >>> + unsigned long vaddr_start, vaddr_end, addr; >>> + nodemask_t task_nodes; >>> + struct mm_struct *mm; >>> + unsigned long total = 0, split = 0; >>> + >>> + ret = mutex_lock_interruptible(&mutex); >>> + if (ret) >>> + return ret; >>> + >>> + ret = -EFAULT; >>> + >>> + memset(input_buf, 0, 80); >>> + if (copy_from_user(input_buf, buf, min_t(size_t, count, 80))) >>> + goto out; >>> + >>> + input_buf[79] = '\0'; >>> + ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end); >>> + if (ret != 3) { >>> + ret = -EINVAL; >>> + goto out; >>> + } >>> + vaddr_start &= PAGE_MASK; >>> + vaddr_end &= PAGE_MASK; >>> + >>> + ret = strlen(input_buf); >>> + pr_debug("split huge pages in pid: %d, vaddr: [%lx - %lx]\n", >>> + pid, vaddr_start, vaddr_end); >>> + >>> + mm = find_mm_struct(pid, &task_nodes); >>> + if (IS_ERR(mm)) { >>> + ret = -EINVAL; >>> + goto out; >>> + } >>> + >>> + mmap_read_lock(mm); >>> + /* >>> + * always increase addr by PAGE_SIZE, since we could have a PTE page >>> + * table filled with PTE-mapped THPs, each of which is distinct. >>> + */ >>> + for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) { >>> + struct vm_area_struct *vma = find_vma(mm, addr); >>> + unsigned int follflags; >>> + struct page *page; >>> + >>> + if (!vma || addr < vma->vm_start || !vma_migratable(vma)) >>> + break; >>> + >>> + /* FOLL_DUMP to ignore special (like zero) pages */ >>> + follflags = FOLL_GET | FOLL_DUMP; >>> + page = follow_page(vma, addr, follflags); >>> + >>> + if (IS_ERR(page)) >>> + break; >>> + if (!page) >>> + break; >>> + >>> + if (!is_transparent_hugepage(page)) >>> + continue; >>> + >>> + total++; >>> + if (!can_split_huge_page(compound_head(page), NULL)) >>> + continue; >>> + >>> + if (!trylock_page(page)) >>> + continue; >>> + >>> + if (!split_huge_page(page)) >>> + split++; >>> + >>> + unlock_page(page); >>> + put_page(page); >>> + } >>> + mmap_read_unlock(mm); >>> + mmput(mm); >>> + >>> + pr_debug("%lu of %lu THP split\n", split, total); >>> +out: >>> + mutex_unlock(&mutex); >>> + return ret; >>> + >>> +} >>> + >>> +static const struct file_operations split_huge_pages_in_range_pid_fops = { >>> + .owner = THIS_MODULE, >>> + .write = split_huge_pages_in_range_pid_write, >>> + .llseek = no_llseek, >>> +}; >>> + >>> static int __init split_huge_pages_debugfs(void) >>> { >>> debugfs_create_file("split_huge_pages", 0200, NULL, NULL, >>> &split_huge_pages_fops); >>> + debugfs_create_file("split_huge_pages_in_range_pid", 0200, NULL, NULL, >>> + &split_huge_pages_in_range_pid_fops); >>> return 0; >>> } >>> late_initcall(split_huge_pages_debugfs); >>> diff --git a/mm/internal.h b/mm/internal.h >>> index 9902648f2206..1659d00100ef 100644 >>> --- a/mm/internal.h >>> +++ b/mm/internal.h >>> @@ -623,4 +623,5 @@ struct migration_target_control { >>> gfp_t gfp_mask; >>> }; >>> +struct mm_struct *find_mm_struct(pid_t pid, nodemask_t *mem_nodes); >>> #endif /* __MM_INTERNAL_H */ >>> diff --git a/mm/migrate.c b/mm/migrate.c >>> index 62b81d5257aa..ce5f213debb2 100644 >>> --- a/mm/migrate.c >>> +++ b/mm/migrate.c >>> @@ -1913,7 +1913,7 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, >>> return nr_pages ? -EFAULT : 0; >>> } >>> -static struct mm_struct *find_mm_struct(pid_t pid, nodemask_t *mem_nodes) >>> +struct mm_struct *find_mm_struct(pid_t pid, nodemask_t *mem_nodes) >>> { >>> struct task_struct *task; >>> struct mm_struct *mm; >>> diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore >>> index 9a35c3f6a557..1f651e85ed60 100644 >>> --- a/tools/testing/selftests/vm/.gitignore >>> +++ b/tools/testing/selftests/vm/.gitignore >>> @@ -22,3 +22,4 @@ map_fixed_noreplace >>> write_to_hugetlbfs >>> hmm-tests >>> local_config.* >>> +split_huge_page_test >>> diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile >>> index d42115e4284d..4cbc91d6869f 100644 >>> --- a/tools/testing/selftests/vm/Makefile >>> +++ b/tools/testing/selftests/vm/Makefile >>> @@ -42,6 +42,7 @@ TEST_GEN_FILES += on-fault-limit >>> TEST_GEN_FILES += thuge-gen >>> TEST_GEN_FILES += transhuge-stress >>> TEST_GEN_FILES += userfaultfd >>> +TEST_GEN_FILES += split_huge_page_test >>> ifeq ($(MACHINE),x86_64) >>> CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32) >>> diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c >>> new file mode 100644 >>> index 000000000000..8ea8000fda62 >>> --- /dev/null >>> +++ b/tools/testing/selftests/vm/split_huge_page_test.c >>> @@ -0,0 +1,318 @@ >>> +// SPDX-License-Identifier: GPL-2.0 >>> +/* >>> + * A test of splitting PMD THPs and PTE-mapped THPs from a specified virtual >>> + * address range in a process via <debugfs>/split_huge_pages_in_range_pid >>> + * interface. >>> + */ >>> + >>> +#define _GNU_SOURCE >>> +#include <stdio.h> >>> +#include <stdlib.h> >>> +#include "numa.h" >>> +#include <unistd.h> >>> +#include <errno.h> >>> +#include <inttypes.h> >>> +#include <string.h> >>> +#include <sys/types.h> >>> +#include <sys/stat.h> >>> +#include <fcntl.h> >>> +#include <sys/mman.h> >>> +#include <sys/time.h> >>> +#include <sys/wait.h> >>> +#include <malloc.h> >>> +#include <stdbool.h> >>> + >>> +uint64_t pagesize; >>> +unsigned int pageshift; >>> +uint64_t pmd_pagesize; >>> + >>> +#define PMD_SIZE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size" >>> +#define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages_in_range_pid" >>> +#define SMAP_PATH "/proc/self/smaps" >>> +#define INPUT_MAX 80 >>> + >>> +#define PFN_MASK ((1UL<<55)-1) >>> +#define KPF_THP (1UL<<22) >>> + >>> +int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file) >>> +{ >>> + uint64_t paddr; >>> + uint64_t page_flags; >>> + >>> + if (pagemap_file) { >>> + pread(pagemap_file, &paddr, sizeof(paddr), >>> + ((long)vaddr >> pageshift) * sizeof(paddr)); >>> + >>> + if (kpageflags_file) { >>> + pread(kpageflags_file, &page_flags, sizeof(page_flags), >>> + (paddr & PFN_MASK) * sizeof(page_flags)); >>> + >>> + return !!(page_flags & KPF_THP); >>> + } >>> + } >>> + return 0; >>> +} >>> + >>> + >>> +static uint64_t read_pmd_pagesize(void) >>> +{ >>> + int fd; >>> + char buf[20]; >>> + ssize_t num_read; >>> + >>> + fd = open(PMD_SIZE_PATH, O_RDONLY); >>> + if (fd == -1) { >>> + perror("Open hpage_pmd_size failed"); >>> + exit(EXIT_FAILURE); >>> + } >>> + num_read = read(fd, buf, 19); >>> + if (num_read < 1) { >>> + close(fd); >>> + perror("Read hpage_pmd_size failed"); >>> + exit(EXIT_FAILURE); >>> + } >>> + buf[num_read] = '\0'; >>> + close(fd); >>> + >>> + return strtoul(buf, NULL, 10); >>> +} >>> + >>> +static int write_file(const char *path, const char *buf, size_t buflen) >>> +{ >>> + int fd; >>> + ssize_t numwritten; >>> + >>> + fd = open(path, O_WRONLY); >>> + if (fd == -1) >>> + return 0; >>> + >>> + numwritten = write(fd, buf, buflen - 1); >>> + close(fd); >>> + if (numwritten < 1) >>> + return 0; >>> + >>> + return (unsigned int) numwritten; >>> +} >>> + >>> +static void write_debugfs(int pid, uint64_t vaddr_start, uint64_t vaddr_end) >>> +{ >>> + char input[INPUT_MAX]; >>> + int ret; >>> + >>> + ret = snprintf(input, INPUT_MAX, "%d,0x%lx,0x%lx", pid, vaddr_start, >>> + vaddr_end); >>> + if (ret >= INPUT_MAX) { >>> + printf("%s: Debugfs input is too long\n", __func__); >>> + exit(EXIT_FAILURE); >>> + } >>> + >>> + if (!write_file(SPLIT_DEBUGFS, input, ret + 1)) { >>> + perror(SPLIT_DEBUGFS); >>> + exit(EXIT_FAILURE); >>> + } >>> +} >>> + >>> +#define MAX_LINE_LENGTH 500 >>> + >>> +static bool check_for_pattern(FILE *fp, const char *pattern, char *buf) >>> +{ >>> + while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) { >>> + if (!strncmp(buf, pattern, strlen(pattern))) >>> + return true; >>> + } >>> + return false; >>> +} >>> + >>> +static uint64_t check_huge(void *addr) >>> +{ >>> + uint64_t thp = 0; >>> + int ret; >>> + FILE *fp; >>> + char buffer[MAX_LINE_LENGTH]; >>> + char addr_pattern[MAX_LINE_LENGTH]; >>> + >>> + ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", >>> + (unsigned long) addr); >>> + if (ret >= MAX_LINE_LENGTH) { >>> + printf("%s: Pattern is too long\n", __func__); >>> + exit(EXIT_FAILURE); >>> + } >>> + >>> + >>> + fp = fopen(SMAP_PATH, "r"); >>> + if (!fp) { >>> + printf("%s: Failed to open file %s\n", __func__, SMAP_PATH); >>> + exit(EXIT_FAILURE); >>> + } >>> + if (!check_for_pattern(fp, addr_pattern, buffer)) >>> + goto err_out; >>> + >>> + /* >>> + * Fetch the AnonHugePages: in the same block and check the number of >>> + * hugepages. >>> + */ >>> + if (!check_for_pattern(fp, "AnonHugePages:", buffer)) >>> + goto err_out; >>> + >>> + if (sscanf(buffer, "AnonHugePages:%10ld kB", &thp) != 1) { >>> + printf("Reading smap error\n"); >>> + exit(EXIT_FAILURE); >>> + } >>> + >>> +err_out: >>> + fclose(fp); >>> + return thp; >>> +} >>> + >>> +void split_pmd_thp(void) >>> +{ >>> + char *one_page; >>> + size_t len = 4 * pmd_pagesize; >>> + uint64_t thp_size; >>> + size_t i; >>> + >>> + one_page = memalign(pmd_pagesize, len); >>> + >>> + madvise(one_page, len, MADV_HUGEPAGE); >>> + >>> + for (i = 0; i < len; i++) >>> + one_page[i] = (char)i; >>> + >>> + thp_size = check_huge(one_page); >>> + if (!thp_size) { >>> + printf("No THP is allocatd"); >>> + exit(EXIT_FAILURE); >>> + } >>> + >>> + /* split all possible huge pages */ >>> + write_debugfs(getpid(), (uint64_t)one_page, (uint64_t)one_page + len); >>> + >>> + for (i = 0; i < len; i++) >>> + if (one_page[i] != (char)i) { >>> + printf("%ld byte corrupted\n", i); >>> + exit(EXIT_FAILURE); >>> + } >>> + >>> + >>> + thp_size = check_huge(one_page); >>> + if (thp_size) { >>> + printf("Still %ld kB AnonHugePages not split\n", thp_size); >>> + exit(EXIT_FAILURE); >>> + } >>> + >>> + printf("Split huge pages successful\n"); >>> + free(one_page); >>> +} >>> + >>> +void split_pte_mapped_thp(void) >>> +{ >>> + char *one_page, *pte_mapped, *pte_mapped2; >>> + size_t len = 4 * pmd_pagesize; >>> + uint64_t thp_size; >>> + size_t i; >>> + const char *pagemap_template = "/proc/%d/pagemap"; >>> + const char *kpageflags_proc = "/proc/kpageflags"; >>> + char pagemap_proc[255]; >>> + int pagemap_fd; >>> + int kpageflags_fd; >>> + >>> + if (snprintf(pagemap_proc, 255, pagemap_template, getpid()) < 0) { >>> + perror("get pagemap proc error"); >>> + exit(EXIT_FAILURE); >>> + } >>> + pagemap_fd = open(pagemap_proc, O_RDONLY); >>> + >>> + if (pagemap_fd == -1) { >>> + perror("read pagemap:"); >>> + exit(EXIT_FAILURE); >>> + } >>> + >>> + kpageflags_fd = open(kpageflags_proc, O_RDONLY); >>> + >>> + if (kpageflags_fd == -1) { >>> + perror("read kpageflags:"); >>> + exit(EXIT_FAILURE); >>> + } >>> + >>> + one_page = mmap((void *)(1UL << 30), len, PROT_READ | PROT_WRITE, >>> + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); >>> + >>> + madvise(one_page, len, MADV_HUGEPAGE); >>> + >>> + for (i = 0; i < len; i++) >>> + one_page[i] = (char)i; >>> + >>> + thp_size = check_huge(one_page); >>> + if (!thp_size) { >>> + printf("No THP is allocatd"); >>> + exit(EXIT_FAILURE); >>> + } >>> + >>> + pte_mapped = mremap(one_page, pagesize, pagesize, MREMAP_MAYMOVE); >>> + >>> + for (i = 1; i < 4; i++) { >>> + pte_mapped2 = mremap(one_page + pmd_pagesize * i + pagesize * i, >>> + pagesize, pagesize, >>> + MREMAP_MAYMOVE|MREMAP_FIXED, >>> + pte_mapped + pagesize * i); >>> + if (pte_mapped2 == (char *)-1) { >>> + perror("mremap failed"); >>> + exit(EXIT_FAILURE); >>> + } >>> + } >>> + >>> + /* smap does not show THPs after mremap, use kpageflags instead */ >>> + thp_size = 0; >>> + for (i = 0; i < pagesize * 4; i++) >>> + if (i % pagesize == 0 && >>> + is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) >>> + thp_size++; >>> + >>> + if (thp_size != 4) { >>> + printf("Some THPs are missing during mremap\n"); >>> + exit(EXIT_FAILURE); >>> + } >>> + >>> + /* split all possible huge pages */ >>> + write_debugfs(getpid(), (uint64_t)pte_mapped, >>> + (uint64_t)pte_mapped + pagesize * 4); >>> + >>> + /* smap does not show THPs after mremap, use kpageflags instead */ >>> + thp_size = 0; >>> + for (i = 0; i < pagesize * 4; i++) { >>> + if (pte_mapped[i] != (char)i) { >>> + printf("%ld byte corrupted\n", i); >>> + exit(EXIT_FAILURE); >>> + } >>> + if (i % pagesize == 0 && >>> + is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) >>> + thp_size++; >>> + } >>> + >>> + if (thp_size) { >>> + printf("Still %ld THPs not split\n", thp_size); >>> + exit(EXIT_FAILURE); >>> + } >>> + >>> + printf("Split PTE-mapped huge pages successful\n"); >>> + munmap(one_page, len); >>> + close(pagemap_fd); >>> + close(kpageflags_fd); >>> +} >>> + >>> +int main(int argc, char **argv) >>> +{ >>> + if (geteuid() != 0) { >>> + printf("Please run the benchmark as root\n"); >>> + exit(EXIT_FAILURE); >>> + } >>> + >>> + pagesize = getpagesize(); >>> + pageshift = ffs(pagesize) - 1; >>> + pmd_pagesize = read_pmd_pagesize(); >>> + >>> + split_pmd_thp(); >>> + split_pte_mapped_thp(); >>> + >>> + return 0; >>> +} >> — Best Regards, Yan Zi

3 years, 1 month

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror March 2021