> On Wed, Sep 02, 2026 at 06:56:11PM +0100, Yeoreum Yun wrote: > > HPAGE_SIZE and HPAGE_SHIFT macro is written based on the 4KB PAGE_SIZE. > > When this macro is used in some test, test result would be strange in > > the system where PAGE_SIZE is more than 4KB. > > > > Here is example with transhuge-stress test with 16KB PAGE_SIZE: > > > > transhuge-stress: allocate 61073 transhuge pages, using 122146 MiB > > virtual memory and 1908 MiB of ram > > 3.292 s/loop, 0.054 ms/page, 37106.002 MiB/s 2566 succeed, 58507 > > failed, 2566 different pages > > 0.591 s/loop, 0.010 ms/page, 206850.792 MiB/s 0 succeed, 61073 > > failed, 0 different pages > > 0.527 s/loop, 0.009 ms/page, 231895.107 MiB/s 0 succeed, 61073 > > failed, 0 different pages > > 0.527 s/loop, 0.009 ms/page, 231839.704 MiB/s 0 succeed, 61073 > > failed, 0 different pages > > 0.528 s/loop, 0.009 ms/page, 231544.782 MiB/s 0 succeed, 61073 > > failed, 0 different pages > > 0.528 s/loop, 0.009 ms/page, 231462.074 MiB/s 0 succeed, 61073 > > failed, 0 different pages > > 0.527 s/loop, 0.009 ms/page, 231770.300 MiB/s 0 succeed, 61073 > > failed, 0 different pages > > ... > > ok 1 Completed > > > > Remove the HPAGE_SIZE and HPAGE_SHIFT macro. and introduce hpshift() > > helper to get the HPAGE_SHIFT properly. For HPAGE_SIZE, use pre-exist > > helper, read_pmd_pagesize(). > > > > Also, do KSM_MERGE_TIME_HUGE_PAGES test with size of 512 MiB which > > is the LCD pmd_size among 4KB, 16KB and 64KB page_size. > > Probably worth spelling out Least Common Denominator for those who might > mistaken this for a kind of display panel :P
Bad typo :( LCM (least common multiple) :( > > I also wonder if it's worth pulling that out as a separate patch in a series > for > better bisectability? Okay. I'll separate it. > > > > > After this patch, output of transhuge-stress: > > > > transhuge-stress: allocate 3817 transhuge pages, using 122146 MiB virtual > > memory and 119 MiB of ram > > 2.558 s/loop, 0.670 ms/page, 47755.759 MiB/s 2585 succeed, 1232 > > failed, 2585 different pages > > 2.640 s/loop, 0.692 ms/page, 46268.432 MiB/s 2585 succeed, 1232 > > failed, 2585 different pages > > 2.635 s/loop, 0.690 ms/page, 46360.298 MiB/s 2585 succeed, 1232 > > failed, 2585 different pages > > 2.782 s/loop, 0.729 ms/page, 43899.795 MiB/s 2616 succeed, 1201 > > failed, 2616 different pages > > 2.692 s/loop, 0.705 ms/page, 45380.876 MiB/s 2627 succeed, 1190 > > failed, 2627 different pages > > 2.612 s/loop, 0.684 ms/page, 46765.812 MiB/s 2628 succeed, 1189 > > failed, 2628 different pages > > 2.683 s/loop, 0.703 ms/page, 45520.990 MiB/s 2630 succeed, 1187 > > failed, 2630 different pages > > 2.727 s/loop, 0.714 ms/page, 44789.321 MiB/s 2631 succeed, 1186 > > failed, 2631 different pages > > ... > > ok 1 Completed > > > > Suggested-by: Lorenzo Stoakes (ARM) <[email protected]> > > Signed-off-by: Yeoreum Yun <[email protected]> > > Firstly THANK YOU for doing this :) hugely appreciated. > > Also thank you again for the birthday cakes ;) > > And apologies for the nitpicks :P No worries! Thanks for your comment ;) > > > --- > > tools/testing/selftests/mm/guard-regions.c | 12 +++++-- > > tools/testing/selftests/mm/ksm_tests.c | 17 ++++++---- > > tools/testing/selftests/mm/run_vmtests.sh | 4 +-- > > tools/testing/selftests/mm/transhuge-stress.c | 22 +++++++------ > > tools/testing/selftests/mm/vm_util.c | 32 ++++++++++++++++--- > > tools/testing/selftests/mm/vm_util.h | 9 ++---- > > 6 files changed, 66 insertions(+), 30 deletions(-) > > > > diff --git a/tools/testing/selftests/mm/guard-regions.c > > b/tools/testing/selftests/mm/guard-regions.c > > index 5c8ec3ca75d7..d370592b291f 100644 > > --- a/tools/testing/selftests/mm/guard-regions.c > > +++ b/tools/testing/selftests/mm/guard-regions.c > > @@ -2195,14 +2195,22 @@ TEST_F(guard_regions, pagemap_scan) > > TEST_F(guard_regions, collapse) > > { > > const unsigned long page_size = self->page_size; > > - const unsigned long size = 2 * HPAGE_SIZE; > > - const unsigned long num_pages = size / page_size; > > + uint64_t hpage_size; > > + unsigned long size; > > + unsigned long num_pages; > > char *ptr; > > int i; > > > > if (!thp_available()) > > SKIP(return, "Transparent Hugepages not available\n"); > > > > + hpage_size = read_pmd_pagesize(); > > + if (!hpage_size) > > + ksft_exit_fail_msg("reading hpage_size failed\n"); > > + > > + size = 2 * hpage_size; > > + num_pages = size / page_size; > > + > > /* Need file to be correct size for tests for non-anon. */ > > if (variant->backing != ANON_BACKED) > > ASSERT_EQ(ftruncate(self->fd, size), 0); > > diff --git a/tools/testing/selftests/mm/ksm_tests.c > > b/tools/testing/selftests/mm/ksm_tests.c > > index 5fd7792a0d47..278e77055007 100644 > > --- a/tools/testing/selftests/mm/ksm_tests.c > > +++ b/tools/testing/selftests/mm/ksm_tests.c > > @@ -521,6 +521,11 @@ static int ksm_merge_hugepages_time(int merge_type, > > int mapping, int prot, > > struct timespec start_time, end_time; > > unsigned long scan_time_ns; > > int pagemap_fd, n_normal_pages, n_huge_pages; > > + uint64_t hpage_size = read_pmd_pagesize(); > > NIT: can this be const? Acked. > > > + > > + if (!hpage_size) { > > + ksft_exit_fail_msg("reading hpage_size failed\n"); > > + } > > NIT: can drop the {} Acked. > > > > > if (!thp_is_enabled()) { > > ksft_print_msg("Transparent Hugepages not available\n"); > > @@ -530,10 +535,10 @@ static int ksm_merge_hugepages_time(int merge_type, > > int mapping, int prot, > > map_size *= MB; > > size_t len = map_size; > > > > - len -= len % HPAGE_SIZE; > > - map_ptr_orig = mmap(NULL, len + HPAGE_SIZE, PROT_READ | PROT_WRITE, > > + len -= len % hpage_size; > > + map_ptr_orig = mmap(NULL, len + hpage_size, PROT_READ | PROT_WRITE, > > MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0); > > - map_ptr = map_ptr_orig + HPAGE_SIZE - (uintptr_t)map_ptr_orig % > > HPAGE_SIZE; > > + map_ptr = map_ptr_orig + hpage_size - (uintptr_t)map_ptr_orig % > > hpage_size; > > > > if (map_ptr_orig == MAP_FAILED) > > err(2, "initial mmap"); > > @@ -547,7 +552,7 @@ static int ksm_merge_hugepages_time(int merge_type, int > > mapping, int prot, > > > > n_normal_pages = 0; > > n_huge_pages = 0; > > - for (void *p = map_ptr; p < map_ptr + len; p += HPAGE_SIZE) { > > + for (void *p = map_ptr; p < map_ptr + len; p += hpage_size) { > > if (allocate_transhuge(p, pagemap_fd) < 0) > > n_normal_pages++; > > else > > @@ -578,11 +583,11 @@ static int ksm_merge_hugepages_time(int merge_type, > > int mapping, int prot, > > ksft_print_msg("Average speed: %.3f MiB/s\n", (map_size / MB) / > > ((double)scan_time_ns / > > NSEC_PER_SEC)); > > > > - munmap(map_ptr_orig, len + HPAGE_SIZE); > > + munmap(map_ptr_orig, len + hpage_size); > > return KSFT_PASS; > > > > err_out: > > - munmap(map_ptr_orig, len + HPAGE_SIZE); > > + munmap(map_ptr_orig, len + hpage_size); > > return KSFT_FAIL; > > } > > > > diff --git a/tools/testing/selftests/mm/run_vmtests.sh > > b/tools/testing/selftests/mm/run_vmtests.sh > > index d09f9f6a384e..24aa1de27c25 100755 > > --- a/tools/testing/selftests/mm/run_vmtests.sh > > +++ b/tools/testing/selftests/mm/run_vmtests.sh > > @@ -360,8 +360,8 @@ fi > > CATEGORY="memfd_secret" run_test ./memfd_secret > > fi > > > > -# KSM KSM_MERGE_TIME_HUGE_PAGES test with size of 100 > > -CATEGORY="ksm" run_test ./ksm_tests -H -s 100 > > +# KSM KSM_MERGE_TIME_HUGE_PAGES test with size of 512 > > +CATEGORY="ksm" run_test ./ksm_tests -H -s 512 > > See above re: splitting out. Okay. I'll split! > > > # KSM KSM_MERGE_TIME test with size of 100 > > CATEGORY="ksm" run_test ./ksm_tests -P -s 100 > > # KSM MADV_MERGEABLE test with 10 identical pages > > diff --git a/tools/testing/selftests/mm/transhuge-stress.c > > b/tools/testing/selftests/mm/transhuge-stress.c > > index 8eb0c5630e7e..66ae94afaf8d 100644 > > --- a/tools/testing/selftests/mm/transhuge-stress.c > > +++ b/tools/testing/selftests/mm/transhuge-stress.c > > @@ -35,6 +35,8 @@ int main(int argc, char **argv) > > size_t map_len; > > int pagemap_fd; > > int duration = 0; > > + uint64_t hpage_size = read_pmd_pagesize(); > > + uint64_t hpage_shift = hpshift(); > > NIT: could be consts? Okay. > > > > > ksft_print_header(); > > > > @@ -70,23 +72,23 @@ int main(int argc, char **argv) > > } > > > > warnx("allocate %zd transhuge pages, using %zd MiB virtual memory" > > - " and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20, > > - ram >> (20 + HPAGE_SHIFT - pshift() - 1)); > > + " and %zd MiB of ram", len >> hpage_shift, len >> 20, > > + ram >> (20 + hpage_shift - pshift() - 1)); > > > > pagemap_fd = open("/proc/self/pagemap", O_RDONLY); > > if (pagemap_fd < 0) > > ksft_exit_fail_msg("open pagemap\n"); > > > > - len -= len % HPAGE_SIZE; > > - ptr = mmap(NULL, len + HPAGE_SIZE, PROT_RW, mmap_flags, backing_fd, 0); > > + len -= len % hpage_size; > > + ptr = mmap(NULL, len + hpage_size, PROT_RW, mmap_flags, backing_fd, 0); > > if (ptr == MAP_FAILED) > > ksft_exit_fail_msg("initial mmap"); > > - ptr += HPAGE_SIZE - (uintptr_t)ptr % HPAGE_SIZE; > > + ptr += hpage_size - (uintptr_t)ptr % hpage_size; > > > > if (madvise(ptr, len, MADV_HUGEPAGE)) > > ksft_exit_fail_msg("MADV_HUGEPAGE"); > > > > - map_len = ram >> (HPAGE_SHIFT - 1); > > + map_len = ram >> (hpage_shift - 1); > > map = malloc(map_len); > > if (!map) > > ksft_exit_fail_msg("map malloc\n"); > > @@ -99,7 +101,7 @@ int main(int argc, char **argv) > > memset(map, 0, map_len); > > > > clock_gettime(CLOCK_MONOTONIC, &a); > > - for (p = ptr; p < ptr + len; p += HPAGE_SIZE) { > > + for (p = ptr; p < ptr + len; p += hpage_size) { > > int64_t pfn; > > > > pfn = allocate_transhuge(p, pagemap_fd); > > @@ -107,7 +109,7 @@ int main(int argc, char **argv) > > if (pfn < 0) { > > nr_failed++; > > } else { > > - size_t idx = pfn >> (HPAGE_SHIFT - pshift()); > > + size_t idx = pfn >> (hpage_shift - pshift()); > > > > nr_succeed++; > > if (idx >= map_len) { > > @@ -123,7 +125,7 @@ int main(int argc, char **argv) > > } > > > > /* split transhuge page, keep last page */ > > - if (madvise(p, HPAGE_SIZE - psize(), MADV_DONTNEED)) > > + if (madvise(p, hpage_size - psize(), MADV_DONTNEED)) > > ksft_exit_fail_msg("MADV_DONTNEED"); > > } > > clock_gettime(CLOCK_MONOTONIC, &b); > > @@ -131,7 +133,7 @@ int main(int argc, char **argv) > > > > ksft_print_msg("%.3f s/loop, %.3f ms/page, %10.3f MiB/s\t" > > "%4d succeed, %4d failed, %4d different pages\n", > > - s, s * 1000 / (len >> HPAGE_SHIFT), len / s / (1 > > << 20), > > + s, s * 1000 / (len >> hpage_shift), len / s / (1 > > << 20), > > nr_succeed, nr_failed, nr_pages); > > > > if (duration > 0 && b.tv_sec - start.tv_sec >= duration) { > > diff --git a/tools/testing/selftests/mm/vm_util.c > > b/tools/testing/selftests/mm/vm_util.c > > index 4821a3563036..4332f8fb2104 100644 > > --- a/tools/testing/selftests/mm/vm_util.c > > +++ b/tools/testing/selftests/mm/vm_util.c > > @@ -21,6 +21,8 @@ > > > > unsigned int __page_size; > > unsigned int __page_shift; > > +uint64_t __hpage_size; > > +uint64_t __hpage_shift; > > > > uint64_t pagemap_get_entry(int fd, char *start) > > { > > @@ -161,6 +163,9 @@ uint64_t read_pmd_pagesize(void) > > char buf[20]; > > ssize_t num_read; > > > > + if (__hpage_size) > > + return __hpage_size; > > + > > fd = open(PMD_SIZE_FILE_PATH, O_RDONLY); > > if (fd == -1) > > return 0; > > @@ -173,7 +178,24 @@ uint64_t read_pmd_pagesize(void) > > buf[num_read] = '\0'; > > close(fd); > > > > - return strtoul(buf, NULL, 10); > > + __hpage_size = strtoul(buf, NULL, 10); > > + > > + return __hpage_size; > > +} > > + > > +uint64_t hpshift(void) > > +{ > > + if (!__hpage_shift) { > > + if (!__hpage_size) { > > + __hpage_size = read_pmd_pagesize(); > > + if (!__hpage_size) > > + ksft_exit_fail_msg("reading __hpage_size > > failed\n"); > > + } > > This nesting is a bit horrifying :P > > Maybe: > > if (__hpage_shift && __hpage_size) > return; > > if (!__hpage_size) { > ... > } > > if (!__hpage_shift) { > ... > } > > ? I see. I'll untie the nesting. > > > + > > + __hpage_shift = (ffsl(__hpage_size) - 1); > > + } > > + > > + return __hpage_shift; > > } > > > > unsigned long rss_anon(void) > > @@ -452,14 +474,16 @@ bool check_huge_shmem(void *addr, size_t len, int > > nr_hpages, uint64_t hpage_size > > int64_t allocate_transhuge(void *ptr, int pagemap_fd) > > { > > uint64_t ent[2]; > > + uint64_t hpage_size = read_pmd_pagesize(); > > + uint64_t hpage_shift = hpshift(); > > NIT: could be const? Okay ;) > > > > > /* drop pmd */ > > - if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, > > + if (mmap(ptr, hpage_size, PROT_READ | PROT_WRITE, > > MAP_FIXED | MAP_ANONYMOUS | > > MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) > > ksft_exit_fail_msg("mmap transhuge\n"); > > > > - if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) > > + if (madvise(ptr, hpage_size, MADV_HUGEPAGE)) > > ksft_exit_fail_msg("MADV_HUGEPAGE\n"); > > > > /* allocate transparent huge page */ > > @@ -471,7 +495,7 @@ int64_t allocate_transhuge(void *ptr, int pagemap_fd) > > > > if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && > > PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && > > - !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - pshift())) - 1))) > > + !(PAGEMAP_PFN(ent[0]) & ((1 << (hpage_shift - pshift())) - 1))) > > return PAGEMAP_PFN(ent[0]); > > > > return -1; > > diff --git a/tools/testing/selftests/mm/vm_util.h > > b/tools/testing/selftests/mm/vm_util.h > > index 9a49af88702e..20a6334605c7 100644 > > --- a/tools/testing/selftests/mm/vm_util.h > > +++ b/tools/testing/selftests/mm/vm_util.h > > @@ -31,6 +31,8 @@ > > > > extern unsigned int __page_size; > > extern unsigned int __page_shift; > > +extern uint64_t __hpage_size; > > +extern uint64_t __hpage_shift; > > > > /* > > * Represents an open fd and PROCMAP_QUERY state for binary (via ioctl) > > @@ -89,6 +91,7 @@ unsigned long pagemap_get_pfn(int fd, char *start); > > void clear_softdirty(void); > > bool check_for_pattern(FILE *fp, const char *pattern, char *buf, size_t > > len); > > uint64_t read_pmd_pagesize(void); > > +uint64_t hpshift(void); > > unsigned long rss_anon(void); > > bool check_huge_anon(void *addr, size_t len, int nr_hpages, uint64_t > > hpage_size); > > bool check_huge_file(void *addr, size_t len, int nr_hpages, uint64_t > > hpage_size); > > @@ -157,12 +160,6 @@ int ksm_stop(void); > > int get_hardware_corrupted_size(unsigned long *val); > > int unpoison_memory(unsigned long pfn); > > > > -/* > > - * On ppc64 this will only work with radix 2M hugepage size > > - */ > > -#define HPAGE_SHIFT 21 > > -#define HPAGE_SIZE (1 << HPAGE_SHIFT) > > - > > Worth calling this change out in commit msg also? It was spelled out as They're removed ;). > > > #define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) > > #define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) > > > > -- > > LEVI:{C3F47F37-75D8-414A-A8BA-3980EC8A46D7} > > > > -- Thanks! -- Sincerely, Yeoreum Yun
