- Linux-kselftest-mirror - lists.linaro.org

[PATCH] selftests: timers: remove unneeded semicolon

by Jiapeng Chong

Fix the following coccicheck warnings: ./tools/testing/selftests/timers/inconsistency-check.c:75:2-3: Unneeded semicolon. Reported-by: Abaci Robot <abaci(a)linux.alibaba.com> Signed-off-by: Jiapeng Chong <jiapeng.chong(a)linux.alibaba.com> --- tools/testing/selftests/timers/inconsistency-check.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/timers/inconsistency-check.c b/tools/testing/selftests/timers/inconsistency-check.c index 022d3ff..e6756d9 100644 --- a/tools/testing/selftests/timers/inconsistency-check.c +++ b/tools/testing/selftests/timers/inconsistency-check.c @@ -72,7 +72,7 @@ char *clockstring(int clockid) return "CLOCK_BOOTTIME_ALARM"; case CLOCK_TAI: return "CLOCK_TAI"; - }; + } return "UNKNOWN_CLOCKID"; } -- 1.8.3.1

4 years, 3 months

2
1
0 0

[PATCH] selftests/vm: fix out-of-tree build

by Rong Chen

When building out-of-tree, attempting to make target from $(OUTPUT) directory: make[1]: *** No rule to make target '$(OUTPUT)/protection_keys.c', needed by '$(OUTPUT)/protection_keys_32'. Reported-by: kernel test robot <lkp(a)intel.com> Signed-off-by: Rong Chen <rong.a.chen(a)intel.com> --- tools/testing/selftests/vm/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 4cbc91d6869f..73e1cc96d7c2 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -102,7 +102,7 @@ endef ifeq ($(CAN_BUILD_I386),1) $(BINARIES_32): CFLAGS += -m32 $(BINARIES_32): LDLIBS += -lrt -ldl -lm -$(BINARIES_32): %_32: %.c +$(BINARIES_32): $(OUTPUT)/%_32: %.c $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@ $(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t)))) endif @@ -110,7 +110,7 @@ endif ifeq ($(CAN_BUILD_X86_64),1) $(BINARIES_64): CFLAGS += -m64 $(BINARIES_64): LDLIBS += -lrt -ldl -$(BINARIES_64): %_64: %.c +$(BINARIES_64): $(OUTPUT)/%_64: %.c $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@ $(foreach t,$(TARGETS),$(eval $(call gen-target-rule-64,$(t)))) endif -- 2.20.1

4 years, 3 months

1
0
0 0

[PATCH] tools/testing/selftests/vm/: fix warning comparing pointer to 0

by Jiapeng Chong

Fix the following coccicheck warning: ./tools/testing/selftests/vm/map_populate.c:82:16-17: 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/vm/map_populate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/vm/map_populate.c b/tools/testing/selftests/vm/map_populate.c index 6b8aeaa..fb11b9e 100644 --- a/tools/testing/selftests/vm/map_populate.c +++ b/tools/testing/selftests/vm/map_populate.c @@ -79,7 +79,7 @@ int main(int argc, char **argv) unsigned long *smap; ftmp = tmpfile(); - BUG_ON(ftmp == 0, "tmpfile()"); + BUG_ON(!ftmp, "tmpfile()"); ret = ftruncate(fileno(ftmp), MMAP_SZ); BUG_ON(ret, "ftruncate()"); -- 1.8.3.1

4 years, 3 months

1
0
0 0

[PATCH v3] kunit: Match parenthesis alignment to improve code readability

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> Reviewed-by: Brendan Higgins <brendanhiggins(a)google.com> --- Changelog v2 -> v3: Reword subject line 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, -- 2.30.2

4 years, 3 months

1
0
0 0

[PATCH v5 0/8] Fork brute force attack mitigation

by John Wood

Attacks against vulnerable userspace applications with the purpose to break ASLR or bypass canaries traditionally use some level of brute force with the help of the fork system call. This is possible since when creating a new process using fork its memory contents are the same as those of the parent process (the process that called the fork system call). So, the attacker can test the memory infinite times to find the correct memory values or the correct memory addresses without worrying about crashing the application. Based on the above scenario it would be nice to have this detected and mitigated, and this is the goal of this patch serie. Specifically the following attacks are expected to be detected: 1.- Launching (fork()/exec()) a setuid/setgid process repeatedly until a desirable memory layout is got (e.g. Stack Clash). 2.- Connecting to an exec()ing network daemon (e.g. xinetd) repeatedly until a desirable memory layout is got (e.g. what CTFs do for simple network service). 3.- Launching processes without exec() (e.g. Android Zygote) and exposing state to attack a sibling. 4.- Connecting to a fork()ing network daemon (e.g. apache) repeatedly until the previously shared memory layout of all the other children is exposed (e.g. kind of related to HeartBleed). In each case, a privilege boundary has been crossed: Case 1: setuid/setgid process Case 2: network to local Case 3: privilege changes Case 4: network to local So, what will really be detected are fork/exec brute force attacks that cross any of the commented bounds. The implementation details and comparison against other existing implementations can be found in the "Documentation" patch. This v5 version has changed a lot from the v2. Basically the application crash period is now compute on an on-going basis using an exponential moving average (EMA), a detection of a brute force attack through the "execve" system call has been added and the crossing of the commented privilege bounds are taken into account. Also, the fine tune has also been removed and now, all this kind of attacks are detected without administrator intervention. In the v2 version Kees Cook suggested to study if the statistical data shared by all the fork hierarchy processes can be tracked in some other way. Specifically the question was if this info can be hold by the family hierarchy of the mm struct. After studying this hierarchy I think it is not suitable for the Brute LSM since they are totally copied on fork() and in this case we want that they are shared. So I leave this road. So, knowing all this information I will explain now the different patches: The 1/8 patch defines a new LSM hook to get the fatal signal of a task. This will be useful during the attack detection phase. The 2/8 patch defines a new LSM and manages the statistical data shared by all the fork hierarchy processes. The 3/8 patch detects a fork/exec brute force attack. The 4/8 patch narrows the detection taken into account the privilege boundary crossing. The 5/8 patch mitigates a brute force attack. The 6/8 patch adds self-tests to validate the Brute LSM expectations. The 7/8 patch adds the documentation to explain this implementation. The 8/8 patch updates the maintainers file. This patch serie is a task of the KSPP [1] and can also be accessed from my github tree [2] in the "brute_v4" branch. [1] https://github.com/KSPP/linux/issues/39 [2] https://github.com/johwood/linux/ The previous versions can be found in: RFC https://lore.kernel.org/kernel-hardening/20200910202107.3799376-1-keescook@… Version 2 https://lore.kernel.org/kernel-hardening/20201025134540.3770-1-john.wood@gm… Version 3 https://lore.kernel.org/lkml/20210221154919.68050-1-john.wood@gmx.com/ Version 4 https://lore.kernel.org/lkml/20210227150956.6022-1-john.wood@gmx.com/ Changelog RFC -> v2 ------------------- - Rename this feature with a more suitable name (Jann Horn, Kees Cook). - Convert the code to an LSM (Kees Cook). - Add locking to avoid data races (Jann Horn). - Add a new LSM hook to get the fatal signal of a task (Jann Horn, Kees Cook). - Add the last crashes timestamps list to avoid false positives in the attack detection (Jann Horn). - Use "period" instead of "rate" (Jann Horn). - Other minor changes suggested (Jann Horn, Kees Cook). Changelog v2 -> v3 ------------------ - Compute the application crash period on an on-going basis (Kees Cook). - Detect a brute force attack through the execve system call (Kees Cook). - Detect an slow brute force attack (Randy Dunlap). - Fine tuning the detection taken into account privilege boundary crossing (Kees Cook). - Taken into account only fatal signals delivered by the kernel (Kees Cook). - Remove the sysctl attributes to fine tuning the detection (Kees Cook). - Remove the prctls to allow per process enabling/disabling (Kees Cook). - Improve the documentation (Kees Cook). - Fix some typos in the documentation (Randy Dunlap). - Add self-test to validate the expectations (Kees Cook). Changelog v3 -> v4 ------------------ - Fix all the warnings shown by the tool "scripts/kernel-doc" (Randy Dunlap). Changelog v4 -> v5 ------------------ - Fix some typos (Randy Dunlap). Any constructive comments are welcome. Thanks. John Wood (8): security: Add LSM hook at the point where a task gets a fatal signal security/brute: Define a LSM and manage statistical data securtiy/brute: Detect a brute force attack security/brute: Fine tuning the attack detection security/brute: Mitigate a brute force attack selftests/brute: Add tests for the Brute LSM Documentation: Add documentation for the Brute LSM MAINTAINERS: Add a new entry for the Brute LSM Documentation/admin-guide/LSM/Brute.rst | 224 +++++ Documentation/admin-guide/LSM/index.rst | 1 + MAINTAINERS | 7 + include/linux/lsm_hook_defs.h | 1 + include/linux/lsm_hooks.h | 4 + include/linux/security.h | 4 + kernel/signal.c | 1 + security/Kconfig | 11 +- security/Makefile | 4 + security/brute/Kconfig | 13 + security/brute/Makefile | 2 + security/brute/brute.c | 1102 ++++++++++++++++++++++ security/security.c | 5 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/brute/.gitignore | 2 + tools/testing/selftests/brute/Makefile | 5 + tools/testing/selftests/brute/config | 1 + tools/testing/selftests/brute/exec.c | 44 + tools/testing/selftests/brute/test.c | 507 ++++++++++ tools/testing/selftests/brute/test.sh | 226 +++++ 20 files changed, 2160 insertions(+), 5 deletions(-) create mode 100644 Documentation/admin-guide/LSM/Brute.rst create mode 100644 security/brute/Kconfig create mode 100644 security/brute/Makefile create mode 100644 security/brute/brute.c create mode 100644 tools/testing/selftests/brute/.gitignore create mode 100644 tools/testing/selftests/brute/Makefile create mode 100644 tools/testing/selftests/brute/config create mode 100644 tools/testing/selftests/brute/exec.c create mode 100644 tools/testing/selftests/brute/test.c create mode 100755 tools/testing/selftests/brute/test.sh -- 2.25.1

4 years, 3 months

3
24
0 0

[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

4 years, 3 months

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

4 years, 3 months

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

4 years, 4 months

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

4 years, 4 months

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

4 years, 4 months

3
4
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror