Re: [RFC PATCH v1 1/2] selftest/mm: test HWPoison hugetlb truncation behavior

[Pedro Falcato <pedro.falcato@gmail.com>]

On Sun, Jan 19, 2025 at 6:06 PM Jiaqi Yan <jiaqiyan@google.com> wrote:
>
> Test based on my understanding of the memory failure recovery behavior
> for HugeTLB file system, especially after file is truncated/closed.
>
> Signed-off-by: Jiaqi Yan <jiaqiyan@google.com>
> ---
>  tools/testing/selftests/mm/Makefile           |   1 +
>  tools/testing/selftests/mm/hugetlb-mfr-base.c | 240 ++++++++++++++++++
>  2 files changed, 241 insertions(+)
>  create mode 100644 tools/testing/selftests/mm/hugetlb-mfr-base.c
>
> diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
> index 63ce39d024bb5..576626c93ccab 100644
> --- a/tools/testing/selftests/mm/Makefile
> +++ b/tools/testing/selftests/mm/Makefile
> @@ -62,6 +62,7 @@ TEST_GEN_FILES += hmm-tests
>  TEST_GEN_FILES += hugetlb-madvise
>  TEST_GEN_FILES += hugetlb-read-hwpoison
>  TEST_GEN_FILES += hugetlb-soft-offline
> +TEST_GEN_FILES += hugetlb-mfr-base
>  TEST_GEN_FILES += hugepage-mmap
>  TEST_GEN_FILES += hugepage-mremap
>  TEST_GEN_FILES += hugepage-shm
> diff --git a/tools/testing/selftests/mm/hugetlb-mfr-base.c b/tools/testing/selftests/mm/hugetlb-mfr-base.c
> new file mode 100644
> index 0000000000000..b8eee071babe6
> --- /dev/null
> +++ b/tools/testing/selftests/mm/hugetlb-mfr-base.c
> @@ -0,0 +1,240 @@
> +// SPDX-License-Identifier: GPL-2.0
> +
> +#define _GNU_SOURCE
> +#include <errno.h>
> +#include <pthread.h>
> +#include <signal.h>
> +#include <stdbool.h>
> +#include <stdlib.h>
> +#include <stdio.h>
> +#include <string.h>
> +#include <unistd.h>
> +
> +#include <linux/magic.h>
> +#include <linux/memfd.h>
> +#include <sys/mman.h>
> +#include <sys/prctl.h>
> +#include <sys/statfs.h>
> +#include <sys/types.h>
> +
> +#include "../kselftest.h"
> +#include "vm_util.h"
> +
> +#define EPREFIX                        " !!! "
> +#define BYTE_LENTH_IN_1G       0x40000000

LENGTH, but the macro name itself is also a little weird-sounding

> +#define HUGETLB_FILL           0xab
> +
> +static void *sigbus_addr;
> +static int sigbus_addr_lsb;
> +static bool expecting_sigbus;
> +static bool got_sigbus;
> +static bool was_mceerr;
> +
> +static int create_hugetlbfs_file(struct statfs *file_stat)
> +{
> +       int fd;
> +       int flags = MFD_HUGETLB | MFD_HUGE_1GB;
> +
> +       fd = memfd_create("hugetlb_tmp", flags);
> +       if (fd < 0)
> +               ksft_exit_fail_perror("Failed to memfd_create");
> +
> +       memset(file_stat, 0, sizeof(*file_stat));
> +       if (fstatfs(fd, file_stat)) {
> +               close(fd);
> +               ksft_exit_fail_perror("Failed to fstatfs");
> +       }
> +       if (file_stat->f_type != HUGETLBFS_MAGIC) {
> +               close(fd);
> +               ksft_exit_fail_msg("Not hugetlbfs file");
> +       }
> +
> +       ksft_print_msg("Created hugetlb_tmp file\n");
> +       ksft_print_msg("hugepagesize=%#lx\n", file_stat->f_bsize);
> +       if (file_stat->f_bsize != BYTE_LENTH_IN_1G)
> +               ksft_exit_fail_msg("Hugepage size is not 1G");
> +
> +       return fd;
> +}
> +
> +/*
> + * SIGBUS handler for "do_hwpoison" thread that mapped and MADV_HWPOISON
> + */
> +static void sigbus_handler(int signo, siginfo_t *info, void *context)
> +{
> +       if (!expecting_sigbus)
> +               ksft_exit_fail_msg("unexpected sigbus with addr=%p",
> +                                  info->si_addr);
> +
> +       got_sigbus = true;
> +       was_mceerr = (info->si_code == BUS_MCEERR_AO ||
> +                     info->si_code == BUS_MCEERR_AR);
> +       sigbus_addr = info->si_addr;
> +       sigbus_addr_lsb = info->si_addr_lsb;
> +}
> +
> +static void *do_hwpoison(void *hwpoison_addr)
> +{
> +       int hwpoison_size = getpagesize();
> +
> +       ksft_print_msg("MADV_HWPOISON hwpoison_addr=%p, len=%d\n",
> +                      hwpoison_addr, hwpoison_size);
> +       if (madvise(hwpoison_addr, hwpoison_size, MADV_HWPOISON) < 0)
> +               ksft_exit_fail_perror("Failed to MADV_HWPOISON");
> +
> +       pthread_exit(NULL);
> +}
> +
> +static void test_hwpoison_multiple_pages(unsigned char *start_addr)
> +{
> +       pthread_t pthread;
> +       int ret;
> +       unsigned char *hwpoison_addr;
> +       unsigned long offsets[] = {0x200000};
> +
> +       for (size_t i = 0; i < ARRAY_SIZE(offsets); ++i) {
> +               sigbus_addr = (void *)0xBADBADBAD;
> +               sigbus_addr_lsb = 0;
> +               was_mceerr = false;
> +               got_sigbus = false;
> +               expecting_sigbus = true;
> +               hwpoison_addr = start_addr + offsets[i];
> +
> +               ret = pthread_create(&pthread, NULL, &do_hwpoison, hwpoison_addr);
> +               if (ret)
> +                       ksft_exit_fail_perror("Failed to create hwpoison thread");
> +
> +               ksft_print_msg("Created thread to hwpoison and access hwpoison_addr=%p\n",
> +                              hwpoison_addr);
> +
> +               pthread_join(pthread, NULL);
> +
> +               if (!got_sigbus)
> +                       ksft_test_result_fail("Didn't get a SIGBUS\n");
> +               if (!was_mceerr)
> +                       ksft_test_result_fail("Didn't get a BUS_MCEERR_A(R|O)\n");
> +               if (sigbus_addr != hwpoison_addr)
> +                       ksft_test_result_fail("Incorrect address: got=%p, expected=%p\n",
> +                                             sigbus_addr, hwpoison_addr);
> +               if (sigbus_addr_lsb != 30)
> +                       ksft_test_result_fail("Incorrect address LSB: got=%d, expected=%d\n",
> +                                             sigbus_addr_lsb, pshift());
> +
> +               ksft_print_msg("Received expected and correct SIGBUS\n");
> +       }
> +}
> +
> +static int read_nr_hugepages(unsigned long hugepage_size,
> +                            unsigned long *nr_hugepages)
> +{
> +       char buffer[256] = {0};
> +       char cmd[256] = {0};
> +
> +       sprintf(cmd, "cat /sys/kernel/mm/hugepages/hugepages-%ldkB/nr_hugepages",
> +               hugepage_size);

You'll notice this is just reading a file through an external command

> +       FILE *cmdfile = popen(cmd, "r");
> +
> +       if (cmdfile == NULL) {
> +               ksft_perror(EPREFIX "failed to popen nr_hugepages");
> +               return -1;
> +       }
> +
> +       if (!fgets(buffer, sizeof(buffer), cmdfile)) {
> +               ksft_perror(EPREFIX "failed to read nr_hugepages");
> +               pclose(cmdfile);
> +               return -1;
> +       }

and this is just reading a "file" (pipe) directly, soo....

static int read_nr_hugepages(...)
{
    char path[256];
    snprintf(path, 256,
/sys/kernel/mm/hugepages/hugepages-%ldkB/nr_hugepages",
hugepage_size);
    FILE *file = fopen(path, "r");
    fscanf(file, "%lu", nr_hugepages);
}

(error handling omitted)

-- 
Pedro