From 61c2c6764e6fcc95507dcf672d15f33b0af300f2 Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Wed, 6 Jul 2022 16:59:32 -0700 Subject: selftests/vm: modularize collapse selftests Modularize the collapse action of khugepaged collapse selftests by introducing a struct collapse_context which specifies how to collapse a given memory range and the expected semantics of the collapse. This can be reused later to test other collapse contexts. Additionally, all tests have logic that checks if a collapse occurred via reading /proc/self/smaps, and report if this is different than expected. Move this logic into the per-context ->collapse() hook instead of repeating it in every test. Link: https://lkml.kernel.org/r/20220706235936.2197195-15-zokeefe@google.com Signed-off-by: Zach O'Keefe Cc: Alex Shi Cc: Andrea Arcangeli Cc: Arnd Bergmann Cc: Axel Rasmussen Cc: Chris Kennelly Cc: Chris Zankel Cc: David Hildenbrand Cc: David Rientjes Cc: Helge Deller Cc: Hugh Dickins Cc: Ivan Kokshaysky Cc: James Bottomley Cc: Jens Axboe Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Miaohe Lin Cc: Michal Hocko Cc: Minchan Kim Cc: Pasha Tatashin Cc: Pavel Begunkov Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Thomas Bogendoerfer Cc: Vlastimil Babka Cc: Yang Shi Cc: Zi Yan Cc: Dan Carpenter Cc: "Souptick Joarder (HPE)" Signed-off-by: Andrew Morton --- tools/testing/selftests/vm/khugepaged.c | 251 ++++++++++++++------------------ 1 file changed, 110 insertions(+), 141 deletions(-) (limited to 'tools/testing/selftests/vm/khugepaged.c') diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index 155120b67a16..0f1bee0eff24 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -23,6 +23,11 @@ static int hpage_pmd_nr; #define THP_SYSFS "/sys/kernel/mm/transparent_hugepage/" #define PID_SMAPS "/proc/self/smaps" +struct collapse_context { + void (*collapse)(const char *msg, char *p, bool expect); + bool enforce_pte_scan_limits; +}; + enum thp_enabled { THP_ALWAYS, THP_MADVISE, @@ -501,6 +506,21 @@ static bool wait_for_scan(const char *msg, char *p) return timeout == -1; } +static void khugepaged_collapse(const char *msg, char *p, bool expect) +{ + if (wait_for_scan(msg, p)) { + if (expect) + fail("Timeout"); + else + success("OK"); + return; + } else if (check_huge(p) == expect) { + success("OK"); + } else { + fail("Fail"); + } +} + static void alloc_at_fault(void) { struct settings settings = default_settings; @@ -528,53 +548,39 @@ static void alloc_at_fault(void) munmap(p, hpage_pmd_size); } -static void collapse_full(void) +static void collapse_full(struct collapse_context *c) { void *p; p = alloc_mapping(); fill_memory(p, 0, hpage_pmd_size); - if (wait_for_scan("Collapse fully populated PTE table", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Collapse fully populated PTE table", p, true); validate_memory(p, 0, hpage_pmd_size); munmap(p, hpage_pmd_size); } -static void collapse_empty(void) +static void collapse_empty(struct collapse_context *c) { void *p; p = alloc_mapping(); - if (wait_for_scan("Do not collapse empty PTE table", p)) - fail("Timeout"); - else if (check_huge(p)) - fail("Fail"); - else - success("OK"); + c->collapse("Do not collapse empty PTE table", p, false); munmap(p, hpage_pmd_size); } -static void collapse_single_pte_entry(void) +static void collapse_single_pte_entry(struct collapse_context *c) { void *p; p = alloc_mapping(); fill_memory(p, 0, page_size); - if (wait_for_scan("Collapse PTE table with single PTE entry present", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Collapse PTE table with single PTE entry present", p, + true); validate_memory(p, 0, page_size); munmap(p, hpage_pmd_size); } -static void collapse_max_ptes_none(void) +static void collapse_max_ptes_none(struct collapse_context *c) { int max_ptes_none = hpage_pmd_nr / 2; struct settings settings = default_settings; @@ -586,28 +592,22 @@ static void collapse_max_ptes_none(void) p = alloc_mapping(); fill_memory(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size); - if (wait_for_scan("Do not collapse with max_ptes_none exceeded", p)) - fail("Timeout"); - else if (check_huge(p)) - fail("Fail"); - else - success("OK"); + c->collapse("Maybe collapse with max_ptes_none exceeded", p, + !c->enforce_pte_scan_limits); validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size); - fill_memory(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size); - if (wait_for_scan("Collapse with max_ptes_none PTEs empty", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); - validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size); + if (c->enforce_pte_scan_limits) { + fill_memory(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size); + c->collapse("Collapse with max_ptes_none PTEs empty", p, true); + validate_memory(p, 0, + (hpage_pmd_nr - max_ptes_none) * page_size); + } munmap(p, hpage_pmd_size); write_settings(&default_settings); } -static void collapse_swapin_single_pte(void) +static void collapse_swapin_single_pte(struct collapse_context *c) { void *p; p = alloc_mapping(); @@ -625,18 +625,13 @@ static void collapse_swapin_single_pte(void) goto out; } - if (wait_for_scan("Collapse with swapping in single PTE entry", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Collapse with swapping in single PTE entry", p, true); validate_memory(p, 0, hpage_pmd_size); out: munmap(p, hpage_pmd_size); } -static void collapse_max_ptes_swap(void) +static void collapse_max_ptes_swap(struct collapse_context *c) { int max_ptes_swap = read_num("khugepaged/max_ptes_swap"); void *p; @@ -656,39 +651,34 @@ static void collapse_max_ptes_swap(void) goto out; } - if (wait_for_scan("Do not collapse with max_ptes_swap exceeded", p)) - fail("Timeout"); - else if (check_huge(p)) - fail("Fail"); - else - success("OK"); + c->collapse("Maybe collapse with max_ptes_swap exceeded", p, + !c->enforce_pte_scan_limits); validate_memory(p, 0, hpage_pmd_size); - fill_memory(p, 0, hpage_pmd_size); - printf("Swapout %d of %d pages...", max_ptes_swap, hpage_pmd_nr); - if (madvise(p, max_ptes_swap * page_size, MADV_PAGEOUT)) { - perror("madvise(MADV_PAGEOUT)"); - exit(EXIT_FAILURE); - } - if (check_swap(p, max_ptes_swap * page_size)) { - success("OK"); - } else { - fail("Fail"); - goto out; - } + if (c->enforce_pte_scan_limits) { + fill_memory(p, 0, hpage_pmd_size); + printf("Swapout %d of %d pages...", max_ptes_swap, + hpage_pmd_nr); + if (madvise(p, max_ptes_swap * page_size, MADV_PAGEOUT)) { + perror("madvise(MADV_PAGEOUT)"); + exit(EXIT_FAILURE); + } + if (check_swap(p, max_ptes_swap * page_size)) { + success("OK"); + } else { + fail("Fail"); + goto out; + } - if (wait_for_scan("Collapse with max_ptes_swap pages swapped out", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); - validate_memory(p, 0, hpage_pmd_size); + c->collapse("Collapse with max_ptes_swap pages swapped out", p, + true); + validate_memory(p, 0, hpage_pmd_size); + } out: munmap(p, hpage_pmd_size); } -static void collapse_single_pte_entry_compound(void) +static void collapse_single_pte_entry_compound(struct collapse_context *c) { void *p; @@ -710,17 +700,13 @@ static void collapse_single_pte_entry_compound(void) else fail("Fail"); - if (wait_for_scan("Collapse PTE table with single PTE mapping compound page", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Collapse PTE table with single PTE mapping compound page", + p, true); validate_memory(p, 0, page_size); munmap(p, hpage_pmd_size); } -static void collapse_full_of_compound(void) +static void collapse_full_of_compound(struct collapse_context *c) { void *p; @@ -742,17 +728,12 @@ static void collapse_full_of_compound(void) else fail("Fail"); - if (wait_for_scan("Collapse PTE table full of compound pages", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Collapse PTE table full of compound pages", p, true); validate_memory(p, 0, hpage_pmd_size); munmap(p, hpage_pmd_size); } -static void collapse_compound_extreme(void) +static void collapse_compound_extreme(struct collapse_context *c) { void *p; int i; @@ -798,18 +779,14 @@ static void collapse_compound_extreme(void) else fail("Fail"); - if (wait_for_scan("Collapse PTE table full of different compound pages", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Collapse PTE table full of different compound pages", p, + true); validate_memory(p, 0, hpage_pmd_size); munmap(p, hpage_pmd_size); } -static void collapse_fork(void) +static void collapse_fork(struct collapse_context *c) { int wstatus; void *p; @@ -835,13 +812,8 @@ static void collapse_fork(void) fail("Fail"); fill_memory(p, page_size, 2 * page_size); - - if (wait_for_scan("Collapse PTE table with single page shared with parent process", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Collapse PTE table with single page shared with parent process", + p, true); validate_memory(p, 0, page_size); munmap(p, hpage_pmd_size); @@ -860,7 +832,7 @@ static void collapse_fork(void) munmap(p, hpage_pmd_size); } -static void collapse_fork_compound(void) +static void collapse_fork_compound(struct collapse_context *c) { int wstatus; void *p; @@ -896,14 +868,10 @@ static void collapse_fork_compound(void) fill_memory(p, 0, page_size); write_num("khugepaged/max_ptes_shared", hpage_pmd_nr - 1); - if (wait_for_scan("Collapse PTE table full of compound pages in child", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Collapse PTE table full of compound pages in child", + p, true); write_num("khugepaged/max_ptes_shared", - default_settings.khugepaged.max_ptes_shared); + default_settings.khugepaged.max_ptes_shared); validate_memory(p, 0, hpage_pmd_size); munmap(p, hpage_pmd_size); @@ -922,7 +890,7 @@ static void collapse_fork_compound(void) munmap(p, hpage_pmd_size); } -static void collapse_max_ptes_shared() +static void collapse_max_ptes_shared(struct collapse_context *c) { int max_ptes_shared = read_num("khugepaged/max_ptes_shared"); int wstatus; @@ -957,28 +925,22 @@ static void collapse_max_ptes_shared() else fail("Fail"); - if (wait_for_scan("Do not collapse with max_ptes_shared exceeded", p)) - fail("Timeout"); - else if (!check_huge(p)) - success("OK"); - else - fail("Fail"); - - printf("Trigger CoW on page %d of %d...", - hpage_pmd_nr - max_ptes_shared, hpage_pmd_nr); - fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared) * page_size); - if (!check_huge(p)) - success("OK"); - else - fail("Fail"); - - - if (wait_for_scan("Collapse with max_ptes_shared PTEs shared", p)) - fail("Timeout"); - else if (check_huge(p)) - success("OK"); - else - fail("Fail"); + c->collapse("Maybe collapse with max_ptes_shared exceeded", p, + !c->enforce_pte_scan_limits); + + if (c->enforce_pte_scan_limits) { + printf("Trigger CoW on page %d of %d...", + hpage_pmd_nr - max_ptes_shared, hpage_pmd_nr); + fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared) * + page_size); + if (!check_huge(p)) + success("OK"); + else + fail("Fail"); + + c->collapse("Collapse with max_ptes_shared PTEs shared", + p, true); + } validate_memory(p, 0, hpage_pmd_size); munmap(p, hpage_pmd_size); @@ -999,6 +961,8 @@ static void collapse_max_ptes_shared() int main(void) { + struct collapse_context c; + setbuf(stdout, NULL); page_size = getpagesize(); @@ -1014,18 +978,23 @@ int main(void) adjust_settings(); alloc_at_fault(); - collapse_full(); - collapse_empty(); - collapse_single_pte_entry(); - collapse_max_ptes_none(); - collapse_swapin_single_pte(); - collapse_max_ptes_swap(); - collapse_single_pte_entry_compound(); - collapse_full_of_compound(); - collapse_compound_extreme(); - collapse_fork(); - collapse_fork_compound(); - collapse_max_ptes_shared(); + + printf("\n*** Testing context: khugepaged ***\n"); + c.collapse = &khugepaged_collapse; + c.enforce_pte_scan_limits = true; + + collapse_full(&c); + collapse_empty(&c); + collapse_single_pte_entry(&c); + collapse_max_ptes_none(&c); + collapse_swapin_single_pte(&c); + collapse_max_ptes_swap(&c); + collapse_single_pte_entry_compound(&c); + collapse_full_of_compound(&c); + collapse_compound_extreme(&c); + collapse_fork(&c); + collapse_fork_compound(&c); + collapse_max_ptes_shared(&c); restore_settings(0); } -- cgit From be6667b0db97e10b2a6d57a906c2c8fd2b985e5e Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Wed, 6 Jul 2022 16:59:33 -0700 Subject: selftests/vm: dedup hugepage allocation logic The code p = alloc_mapping(); printf("Allocate huge page..."); madvise(p, hpage_pmd_size, MADV_HUGEPAGE); fill_memory(p, 0, hpage_pmd_size); if (check_huge(p)) success("OK"); else fail("Fail"); Is repeated many times in different tests. Add a helper, alloc_hpage() to handle this. Link: https://lkml.kernel.org/r/20220706235936.2197195-16-zokeefe@google.com Signed-off-by: Zach O'Keefe Cc: Alex Shi Cc: Andrea Arcangeli Cc: Arnd Bergmann Cc: Axel Rasmussen Cc: Chris Kennelly Cc: Chris Zankel Cc: David Hildenbrand Cc: David Rientjes Cc: Helge Deller Cc: Hugh Dickins Cc: Ivan Kokshaysky Cc: James Bottomley Cc: Jens Axboe Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Miaohe Lin Cc: Michal Hocko Cc: Minchan Kim Cc: Pasha Tatashin Cc: Pavel Begunkov Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Thomas Bogendoerfer Cc: Vlastimil Babka Cc: Yang Shi Cc: Zi Yan Cc: Dan Carpenter Cc: "Souptick Joarder (HPE)" Signed-off-by: Andrew Morton --- tools/testing/selftests/vm/khugepaged.c | 62 ++++++++++++--------------------- 1 file changed, 23 insertions(+), 39 deletions(-) (limited to 'tools/testing/selftests/vm/khugepaged.c') diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index 0f1bee0eff24..eb6f5bbacff1 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -461,6 +461,25 @@ static void fill_memory(int *p, unsigned long start, unsigned long end) p[i * page_size / sizeof(*p)] = i + 0xdead0000; } +/* + * Returns pmd-mapped hugepage in VMA marked VM_HUGEPAGE, filled with + * validate_memory()'able contents. + */ +static void *alloc_hpage(void) +{ + void *p; + + p = alloc_mapping(); + printf("Allocate huge page..."); + madvise(p, hpage_pmd_size, MADV_HUGEPAGE); + fill_memory(p, 0, hpage_pmd_size); + if (check_huge(p)) + success("OK"); + else + fail("Fail"); + return p; +} + static void validate_memory(int *p, unsigned long start, unsigned long end) { int i; @@ -682,15 +701,7 @@ static void collapse_single_pte_entry_compound(struct collapse_context *c) { void *p; - p = alloc_mapping(); - - printf("Allocate huge page..."); - madvise(p, hpage_pmd_size, MADV_HUGEPAGE); - fill_memory(p, 0, hpage_pmd_size); - if (check_huge(p)) - success("OK"); - else - fail("Fail"); + p = alloc_hpage(); madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); printf("Split huge page leaving single PTE mapping compound page..."); @@ -710,16 +721,7 @@ static void collapse_full_of_compound(struct collapse_context *c) { void *p; - p = alloc_mapping(); - - printf("Allocate huge page..."); - madvise(p, hpage_pmd_size, MADV_HUGEPAGE); - fill_memory(p, 0, hpage_pmd_size); - if (check_huge(p)) - success("OK"); - else - fail("Fail"); - + p = alloc_hpage(); printf("Split huge page leaving single PTE page table full of compound pages..."); madvise(p, page_size, MADV_NOHUGEPAGE); madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); @@ -837,16 +839,7 @@ static void collapse_fork_compound(struct collapse_context *c) int wstatus; void *p; - p = alloc_mapping(); - - printf("Allocate huge page..."); - madvise(p, hpage_pmd_size, MADV_HUGEPAGE); - fill_memory(p, 0, hpage_pmd_size); - if (check_huge(p)) - success("OK"); - else - fail("Fail"); - + p = alloc_hpage(); printf("Share huge page over fork()..."); if (!fork()) { /* Do not touch settings on child exit */ @@ -896,16 +889,7 @@ static void collapse_max_ptes_shared(struct collapse_context *c) int wstatus; void *p; - p = alloc_mapping(); - - printf("Allocate huge page..."); - madvise(p, hpage_pmd_size, MADV_HUGEPAGE); - fill_memory(p, 0, hpage_pmd_size); - if (check_huge(p)) - success("OK"); - else - fail("Fail"); - + p = alloc_hpage(); printf("Share huge page over fork()..."); if (!fork()) { /* Do not touch settings on child exit */ -- cgit From 9330694de59f17e110a58be486a2c64d32bab42f Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Wed, 6 Jul 2022 16:59:34 -0700 Subject: selftests/vm: add MADV_COLLAPSE collapse context to selftests Add madvise collapse context to hugepage collapse selftests. This context is tested with /sys/kernel/mm/transparent_hugepage/enabled set to "never" in order to avoid unwanted interaction with khugepaged during testing. Also, refactor updates to sysfs THP settings using a stack so that the THP settings from nested callers can be restored. Link: https://lkml.kernel.org/r/20220706235936.2197195-17-zokeefe@google.com Signed-off-by: Zach O'Keefe Cc: Alex Shi Cc: Andrea Arcangeli Cc: Arnd Bergmann Cc: Axel Rasmussen Cc: Chris Kennelly Cc: Chris Zankel Cc: David Hildenbrand Cc: David Rientjes Cc: Helge Deller Cc: Hugh Dickins Cc: Ivan Kokshaysky Cc: James Bottomley Cc: Jens Axboe Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Miaohe Lin Cc: Michal Hocko Cc: Minchan Kim Cc: Pasha Tatashin Cc: Pavel Begunkov Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Thomas Bogendoerfer Cc: Vlastimil Babka Cc: Yang Shi Cc: Zi Yan Cc: Dan Carpenter Cc: "Souptick Joarder (HPE)" Signed-off-by: Andrew Morton --- tools/testing/selftests/vm/khugepaged.c | 171 +++++++++++++++++++++++--------- 1 file changed, 125 insertions(+), 46 deletions(-) (limited to 'tools/testing/selftests/vm/khugepaged.c') diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index eb6f5bbacff1..780f04440e15 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -14,6 +14,9 @@ #ifndef MADV_PAGEOUT #define MADV_PAGEOUT 21 #endif +#ifndef MADV_COLLAPSE +#define MADV_COLLAPSE 25 +#endif #define BASE_ADDR ((void *)(1UL << 30)) static unsigned long hpage_pmd_size; @@ -95,18 +98,6 @@ struct settings { struct khugepaged_settings khugepaged; }; -static struct settings default_settings = { - .thp_enabled = THP_MADVISE, - .thp_defrag = THP_DEFRAG_ALWAYS, - .shmem_enabled = SHMEM_NEVER, - .use_zero_page = 0, - .khugepaged = { - .defrag = 1, - .alloc_sleep_millisecs = 10, - .scan_sleep_millisecs = 10, - }, -}; - static struct settings saved_settings; static bool skip_settings_restore; @@ -284,6 +275,39 @@ static void write_settings(struct settings *settings) write_num("khugepaged/pages_to_scan", khugepaged->pages_to_scan); } +#define MAX_SETTINGS_DEPTH 4 +static struct settings settings_stack[MAX_SETTINGS_DEPTH]; +static int settings_index; + +static struct settings *current_settings(void) +{ + if (!settings_index) { + printf("Fail: No settings set"); + exit(EXIT_FAILURE); + } + return settings_stack + settings_index - 1; +} + +static void push_settings(struct settings *settings) +{ + if (settings_index >= MAX_SETTINGS_DEPTH) { + printf("Fail: Settings stack exceeded"); + exit(EXIT_FAILURE); + } + settings_stack[settings_index++] = *settings; + write_settings(current_settings()); +} + +static void pop_settings(void) +{ + if (settings_index <= 0) { + printf("Fail: Settings stack empty"); + exit(EXIT_FAILURE); + } + --settings_index; + write_settings(current_settings()); +} + static void restore_settings(int sig) { if (skip_settings_restore) @@ -327,14 +351,6 @@ static void save_settings(void) signal(SIGQUIT, restore_settings); } -static void adjust_settings(void) -{ - - printf("Adjust settings..."); - write_settings(&default_settings); - success("OK"); -} - #define MAX_LINE_LENGTH 500 static bool check_for_pattern(FILE *fp, char *pattern, char *buf) @@ -493,6 +509,38 @@ static void validate_memory(int *p, unsigned long start, unsigned long end) } } +static void madvise_collapse(const char *msg, char *p, bool expect) +{ + int ret; + struct settings settings = *current_settings(); + + printf("%s...", msg); + /* Sanity check */ + if (check_huge(p)) { + printf("Unexpected huge page\n"); + exit(EXIT_FAILURE); + } + + /* + * Prevent khugepaged interference and tests that MADV_COLLAPSE + * ignores /sys/kernel/mm/transparent_hugepage/enabled + */ + settings.thp_enabled = THP_NEVER; + push_settings(&settings); + + /* Clear VM_NOHUGEPAGE */ + madvise(p, hpage_pmd_size, MADV_HUGEPAGE); + ret = madvise(p, hpage_pmd_size, MADV_COLLAPSE); + if (((bool)ret) == expect) + fail("Fail: Bad return value"); + else if (check_huge(p) != expect) + fail("Fail: check_huge()"); + else + success("OK"); + + pop_settings(); +} + #define TICK 500000 static bool wait_for_scan(const char *msg, char *p) { @@ -542,11 +590,11 @@ static void khugepaged_collapse(const char *msg, char *p, bool expect) static void alloc_at_fault(void) { - struct settings settings = default_settings; + struct settings settings = *current_settings(); char *p; settings.thp_enabled = THP_ALWAYS; - write_settings(&settings); + push_settings(&settings); p = alloc_mapping(); *p = 1; @@ -556,7 +604,7 @@ static void alloc_at_fault(void) else fail("Fail"); - write_settings(&default_settings); + pop_settings(); madvise(p, page_size, MADV_DONTNEED); printf("Split huge PMD on MADV_DONTNEED..."); @@ -602,11 +650,11 @@ static void collapse_single_pte_entry(struct collapse_context *c) static void collapse_max_ptes_none(struct collapse_context *c) { int max_ptes_none = hpage_pmd_nr / 2; - struct settings settings = default_settings; + struct settings settings = *current_settings(); void *p; settings.khugepaged.max_ptes_none = max_ptes_none; - write_settings(&settings); + push_settings(&settings); p = alloc_mapping(); @@ -623,7 +671,7 @@ static void collapse_max_ptes_none(struct collapse_context *c) } munmap(p, hpage_pmd_size); - write_settings(&default_settings); + pop_settings(); } static void collapse_swapin_single_pte(struct collapse_context *c) @@ -703,7 +751,6 @@ static void collapse_single_pte_entry_compound(struct collapse_context *c) p = alloc_hpage(); madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); - printf("Split huge page leaving single PTE mapping compound page..."); madvise(p + page_size, hpage_pmd_size - page_size, MADV_DONTNEED); if (!check_huge(p)) @@ -864,7 +911,7 @@ static void collapse_fork_compound(struct collapse_context *c) c->collapse("Collapse PTE table full of compound pages in child", p, true); write_num("khugepaged/max_ptes_shared", - default_settings.khugepaged.max_ptes_shared); + current_settings()->khugepaged.max_ptes_shared); validate_memory(p, 0, hpage_pmd_size); munmap(p, hpage_pmd_size); @@ -943,9 +990,21 @@ static void collapse_max_ptes_shared(struct collapse_context *c) munmap(p, hpage_pmd_size); } -int main(void) +int main(int argc, const char **argv) { struct collapse_context c; + struct settings default_settings = { + .thp_enabled = THP_MADVISE, + .thp_defrag = THP_DEFRAG_ALWAYS, + .shmem_enabled = SHMEM_NEVER, + .use_zero_page = 0, + .khugepaged = { + .defrag = 1, + .alloc_sleep_millisecs = 10, + .scan_sleep_millisecs = 10, + }, + }; + const char *tests = argc == 1 ? "all" : argv[1]; setbuf(stdout, NULL); @@ -959,26 +1018,46 @@ int main(void) default_settings.khugepaged.pages_to_scan = hpage_pmd_nr * 8; save_settings(); - adjust_settings(); + push_settings(&default_settings); alloc_at_fault(); - printf("\n*** Testing context: khugepaged ***\n"); - c.collapse = &khugepaged_collapse; - c.enforce_pte_scan_limits = true; - - collapse_full(&c); - collapse_empty(&c); - collapse_single_pte_entry(&c); - collapse_max_ptes_none(&c); - collapse_swapin_single_pte(&c); - collapse_max_ptes_swap(&c); - collapse_single_pte_entry_compound(&c); - collapse_full_of_compound(&c); - collapse_compound_extreme(&c); - collapse_fork(&c); - collapse_fork_compound(&c); - collapse_max_ptes_shared(&c); + if (!strcmp(tests, "khugepaged") || !strcmp(tests, "all")) { + printf("\n*** Testing context: khugepaged ***\n"); + c.collapse = &khugepaged_collapse; + c.enforce_pte_scan_limits = true; + + collapse_full(&c); + collapse_empty(&c); + collapse_single_pte_entry(&c); + collapse_max_ptes_none(&c); + collapse_swapin_single_pte(&c); + collapse_max_ptes_swap(&c); + collapse_single_pte_entry_compound(&c); + collapse_full_of_compound(&c); + collapse_compound_extreme(&c); + collapse_fork(&c); + collapse_fork_compound(&c); + collapse_max_ptes_shared(&c); + } + if (!strcmp(tests, "madvise") || !strcmp(tests, "all")) { + printf("\n*** Testing context: madvise ***\n"); + c.collapse = &madvise_collapse; + c.enforce_pte_scan_limits = false; + + collapse_full(&c); + collapse_empty(&c); + collapse_single_pte_entry(&c); + collapse_max_ptes_none(&c); + collapse_swapin_single_pte(&c); + collapse_max_ptes_swap(&c); + collapse_single_pte_entry_compound(&c); + collapse_full_of_compound(&c); + collapse_compound_extreme(&c); + collapse_fork(&c); + collapse_fork_compound(&c); + collapse_max_ptes_shared(&c); + } restore_settings(0); } -- cgit From 1370a21fe4708b3bfa748d355146e4fbadf52f90 Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Wed, 6 Jul 2022 16:59:35 -0700 Subject: selftests/vm: add selftest to verify recollapse of THPs Add selftest specific to madvise collapse context that tests MADV_COLLAPSE is "successful" if a hugepage-aligned/sized region is already pmd-mapped. This test also verifies that MADV_COLLAPSE can collapse memory into THPs even in "madvise" THP mode and the memory isn't marked VM_HUGEPAGE. Link: https://lkml.kernel.org/r/20220706235936.2197195-18-zokeefe@google.com Signed-off-by: Zach O'Keefe Cc: Alex Shi Cc: Andrea Arcangeli Cc: Arnd Bergmann Cc: Axel Rasmussen Cc: Chris Kennelly Cc: Chris Zankel Cc: David Hildenbrand Cc: David Rientjes Cc: Helge Deller Cc: Hugh Dickins Cc: Ivan Kokshaysky Cc: James Bottomley Cc: Jens Axboe Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Miaohe Lin Cc: Michal Hocko Cc: Minchan Kim Cc: Pasha Tatashin Cc: Pavel Begunkov Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Thomas Bogendoerfer Cc: Vlastimil Babka Cc: Yang Shi Cc: Zi Yan Cc: Dan Carpenter Cc: "Souptick Joarder (HPE)" Signed-off-by: Andrew Morton --- tools/testing/selftests/vm/khugepaged.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'tools/testing/selftests/vm/khugepaged.c') diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index 780f04440e15..87cd0b99477f 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -990,6 +990,36 @@ static void collapse_max_ptes_shared(struct collapse_context *c) munmap(p, hpage_pmd_size); } +static void madvise_collapse_existing_thps(void) +{ + void *p; + int err; + + p = alloc_mapping(); + fill_memory(p, 0, hpage_pmd_size); + + printf("Collapse fully populated PTE table..."); + /* + * Note that we don't set MADV_HUGEPAGE here, which + * also tests that VM_HUGEPAGE isn't required for + * MADV_COLLAPSE in "madvise" mode. + */ + err = madvise(p, hpage_pmd_size, MADV_COLLAPSE); + if (err == 0 && check_huge(p)) { + success("OK"); + printf("Re-collapse PMD-mapped hugepage"); + err = madvise(p, hpage_pmd_size, MADV_COLLAPSE); + if (err == 0 && check_huge(p)) + success("OK"); + else + fail("Fail"); + } else { + fail("Fail"); + } + validate_memory(p, 0, hpage_pmd_size); + munmap(p, hpage_pmd_size); +} + int main(int argc, const char **argv) { struct collapse_context c; @@ -1057,6 +1087,7 @@ int main(int argc, const char **argv) collapse_fork(&c); collapse_fork_compound(&c); collapse_max_ptes_shared(&c); + madvise_collapse_existing_thps(); } restore_settings(0); -- cgit From 9d0d946840075e0268f4f77fe39ba0f53e84c7c4 Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Wed, 6 Jul 2022 16:59:36 -0700 Subject: selftests/vm: add selftest to verify multi THP collapse Add support to allocate and verify collapse of multiple hugepage-sized regions into multiple THPs. Add "nr" argument to check_huge() that instructs check_huge() to check for exactly "nr_hpages" THPs. This has the added benefit of now being able to check for exactly 0 THPs, and so callsites that previously checked the negation of exactly 1 THP are now more correct. ->collapse struct collapse_context hook has been expanded with a "nr_hpages" argument to collapse "nr_hpages" hugepages. The collapse_full() test has been repurposed to collapse 4 THPs at once. It is expected more tests will want to test multi THP collapse (e.g. file/shmem). This is of particular benefit to madvise collapse context given that it may do many THP collapses during a single syscall. Link: https://lkml.kernel.org/r/20220706235936.2197195-19-zokeefe@google.com Signed-off-by: Zach O'Keefe Cc: Alex Shi Cc: Andrea Arcangeli Cc: Arnd Bergmann Cc: Axel Rasmussen Cc: Chris Kennelly Cc: Chris Zankel Cc: David Hildenbrand Cc: David Rientjes Cc: Helge Deller Cc: Hugh Dickins Cc: Ivan Kokshaysky Cc: James Bottomley Cc: Jens Axboe Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Miaohe Lin Cc: Michal Hocko Cc: Minchan Kim Cc: Pasha Tatashin Cc: Pavel Begunkov Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Thomas Bogendoerfer Cc: Vlastimil Babka Cc: Yang Shi Cc: Zi Yan Cc: Dan Carpenter Cc: "Souptick Joarder (HPE)" Signed-off-by: Andrew Morton --- tools/testing/selftests/vm/khugepaged.c | 140 +++++++++++++++++--------------- 1 file changed, 73 insertions(+), 67 deletions(-) (limited to 'tools/testing/selftests/vm/khugepaged.c') diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index 87cd0b99477f..b77b1e28cdb3 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -27,7 +27,7 @@ static int hpage_pmd_nr; #define PID_SMAPS "/proc/self/smaps" struct collapse_context { - void (*collapse)(const char *msg, char *p, bool expect); + void (*collapse)(const char *msg, char *p, int nr_hpages, bool expect); bool enforce_pte_scan_limits; }; @@ -362,7 +362,7 @@ static bool check_for_pattern(FILE *fp, char *pattern, char *buf) return false; } -static bool check_huge(void *addr) +static bool check_huge(void *addr, int nr_hpages) { bool thp = false; int ret; @@ -387,7 +387,7 @@ static bool check_huge(void *addr) goto err_out; ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "AnonHugePages:%10ld kB", - hpage_pmd_size >> 10); + nr_hpages * (hpage_pmd_size >> 10)); if (ret >= MAX_LINE_LENGTH) { printf("%s: Pattern is too long\n", __func__); exit(EXIT_FAILURE); @@ -455,12 +455,12 @@ err_out: return swap; } -static void *alloc_mapping(void) +static void *alloc_mapping(int nr) { void *p; - p = mmap(BASE_ADDR, hpage_pmd_size, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + p = mmap(BASE_ADDR, nr * hpage_pmd_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (p != BASE_ADDR) { printf("Failed to allocate VMA at %p\n", BASE_ADDR); exit(EXIT_FAILURE); @@ -485,11 +485,11 @@ static void *alloc_hpage(void) { void *p; - p = alloc_mapping(); + p = alloc_mapping(1); printf("Allocate huge page..."); madvise(p, hpage_pmd_size, MADV_HUGEPAGE); fill_memory(p, 0, hpage_pmd_size); - if (check_huge(p)) + if (check_huge(p, 1)) success("OK"); else fail("Fail"); @@ -509,14 +509,15 @@ static void validate_memory(int *p, unsigned long start, unsigned long end) } } -static void madvise_collapse(const char *msg, char *p, bool expect) +static void madvise_collapse(const char *msg, char *p, int nr_hpages, + bool expect) { int ret; struct settings settings = *current_settings(); printf("%s...", msg); /* Sanity check */ - if (check_huge(p)) { + if (!check_huge(p, 0)) { printf("Unexpected huge page\n"); exit(EXIT_FAILURE); } @@ -529,11 +530,11 @@ static void madvise_collapse(const char *msg, char *p, bool expect) push_settings(&settings); /* Clear VM_NOHUGEPAGE */ - madvise(p, hpage_pmd_size, MADV_HUGEPAGE); - ret = madvise(p, hpage_pmd_size, MADV_COLLAPSE); + madvise(p, nr_hpages * hpage_pmd_size, MADV_HUGEPAGE); + ret = madvise(p, nr_hpages * hpage_pmd_size, MADV_COLLAPSE); if (((bool)ret) == expect) fail("Fail: Bad return value"); - else if (check_huge(p) != expect) + else if (check_huge(p, nr_hpages) != expect) fail("Fail: check_huge()"); else success("OK"); @@ -542,25 +543,25 @@ static void madvise_collapse(const char *msg, char *p, bool expect) } #define TICK 500000 -static bool wait_for_scan(const char *msg, char *p) +static bool wait_for_scan(const char *msg, char *p, int nr_hpages) { int full_scans; int timeout = 6; /* 3 seconds */ /* Sanity check */ - if (check_huge(p)) { + if (!check_huge(p, 0)) { printf("Unexpected huge page\n"); exit(EXIT_FAILURE); } - madvise(p, hpage_pmd_size, MADV_HUGEPAGE); + madvise(p, nr_hpages * hpage_pmd_size, MADV_HUGEPAGE); /* Wait until the second full_scan completed */ full_scans = read_num("khugepaged/full_scans") + 2; printf("%s...", msg); while (timeout--) { - if (check_huge(p)) + if (check_huge(p, nr_hpages)) break; if (read_num("khugepaged/full_scans") >= full_scans) break; @@ -568,20 +569,21 @@ static bool wait_for_scan(const char *msg, char *p) usleep(TICK); } - madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); + madvise(p, nr_hpages * hpage_pmd_size, MADV_NOHUGEPAGE); return timeout == -1; } -static void khugepaged_collapse(const char *msg, char *p, bool expect) +static void khugepaged_collapse(const char *msg, char *p, int nr_hpages, + bool expect) { - if (wait_for_scan(msg, p)) { + if (wait_for_scan(msg, p, nr_hpages)) { if (expect) fail("Timeout"); else success("OK"); return; - } else if (check_huge(p) == expect) { + } else if (check_huge(p, nr_hpages) == expect) { success("OK"); } else { fail("Fail"); @@ -596,10 +598,10 @@ static void alloc_at_fault(void) settings.thp_enabled = THP_ALWAYS; push_settings(&settings); - p = alloc_mapping(); + p = alloc_mapping(1); *p = 1; printf("Allocate huge page on fault..."); - if (check_huge(p)) + if (check_huge(p, 1)) success("OK"); else fail("Fail"); @@ -608,7 +610,7 @@ static void alloc_at_fault(void) madvise(p, page_size, MADV_DONTNEED); printf("Split huge PMD on MADV_DONTNEED..."); - if (!check_huge(p)) + if (check_huge(p, 0)) success("OK"); else fail("Fail"); @@ -618,20 +620,23 @@ static void alloc_at_fault(void) static void collapse_full(struct collapse_context *c) { void *p; + int nr_hpages = 4; + unsigned long size = nr_hpages * hpage_pmd_size; - p = alloc_mapping(); - fill_memory(p, 0, hpage_pmd_size); - c->collapse("Collapse fully populated PTE table", p, true); - validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + p = alloc_mapping(nr_hpages); + fill_memory(p, 0, size); + c->collapse("Collapse multiple fully populated PTE table", p, nr_hpages, + true); + validate_memory(p, 0, size); + munmap(p, size); } static void collapse_empty(struct collapse_context *c) { void *p; - p = alloc_mapping(); - c->collapse("Do not collapse empty PTE table", p, false); + p = alloc_mapping(1); + c->collapse("Do not collapse empty PTE table", p, 1, false); munmap(p, hpage_pmd_size); } @@ -639,10 +644,10 @@ static void collapse_single_pte_entry(struct collapse_context *c) { void *p; - p = alloc_mapping(); + p = alloc_mapping(1); fill_memory(p, 0, page_size); c->collapse("Collapse PTE table with single PTE entry present", p, - true); + 1, true); validate_memory(p, 0, page_size); munmap(p, hpage_pmd_size); } @@ -656,16 +661,17 @@ static void collapse_max_ptes_none(struct collapse_context *c) settings.khugepaged.max_ptes_none = max_ptes_none; push_settings(&settings); - p = alloc_mapping(); + p = alloc_mapping(1); fill_memory(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size); - c->collapse("Maybe collapse with max_ptes_none exceeded", p, + c->collapse("Maybe collapse with max_ptes_none exceeded", p, 1, !c->enforce_pte_scan_limits); validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size); if (c->enforce_pte_scan_limits) { fill_memory(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size); - c->collapse("Collapse with max_ptes_none PTEs empty", p, true); + c->collapse("Collapse with max_ptes_none PTEs empty", p, 1, + true); validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size); } @@ -677,7 +683,7 @@ static void collapse_max_ptes_none(struct collapse_context *c) static void collapse_swapin_single_pte(struct collapse_context *c) { void *p; - p = alloc_mapping(); + p = alloc_mapping(1); fill_memory(p, 0, hpage_pmd_size); printf("Swapout one page..."); @@ -692,7 +698,7 @@ static void collapse_swapin_single_pte(struct collapse_context *c) goto out; } - c->collapse("Collapse with swapping in single PTE entry", p, true); + c->collapse("Collapse with swapping in single PTE entry", p, 1, true); validate_memory(p, 0, hpage_pmd_size); out: munmap(p, hpage_pmd_size); @@ -703,7 +709,7 @@ static void collapse_max_ptes_swap(struct collapse_context *c) int max_ptes_swap = read_num("khugepaged/max_ptes_swap"); void *p; - p = alloc_mapping(); + p = alloc_mapping(1); fill_memory(p, 0, hpage_pmd_size); printf("Swapout %d of %d pages...", max_ptes_swap + 1, hpage_pmd_nr); @@ -718,7 +724,7 @@ static void collapse_max_ptes_swap(struct collapse_context *c) goto out; } - c->collapse("Maybe collapse with max_ptes_swap exceeded", p, + c->collapse("Maybe collapse with max_ptes_swap exceeded", p, 1, !c->enforce_pte_scan_limits); validate_memory(p, 0, hpage_pmd_size); @@ -738,7 +744,7 @@ static void collapse_max_ptes_swap(struct collapse_context *c) } c->collapse("Collapse with max_ptes_swap pages swapped out", p, - true); + 1, true); validate_memory(p, 0, hpage_pmd_size); } out: @@ -753,13 +759,13 @@ static void collapse_single_pte_entry_compound(struct collapse_context *c) madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); printf("Split huge page leaving single PTE mapping compound page..."); madvise(p + page_size, hpage_pmd_size - page_size, MADV_DONTNEED); - if (!check_huge(p)) + if (check_huge(p, 0)) success("OK"); else fail("Fail"); c->collapse("Collapse PTE table with single PTE mapping compound page", - p, true); + p, 1, true); validate_memory(p, 0, page_size); munmap(p, hpage_pmd_size); } @@ -772,12 +778,12 @@ static void collapse_full_of_compound(struct collapse_context *c) printf("Split huge page leaving single PTE page table full of compound pages..."); madvise(p, page_size, MADV_NOHUGEPAGE); madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); - if (!check_huge(p)) + if (check_huge(p, 0)) success("OK"); else fail("Fail"); - c->collapse("Collapse PTE table full of compound pages", p, true); + c->collapse("Collapse PTE table full of compound pages", p, 1, true); validate_memory(p, 0, hpage_pmd_size); munmap(p, hpage_pmd_size); } @@ -787,14 +793,14 @@ static void collapse_compound_extreme(struct collapse_context *c) void *p; int i; - p = alloc_mapping(); + p = alloc_mapping(1); for (i = 0; i < hpage_pmd_nr; i++) { printf("\rConstruct PTE page table full of different PTE-mapped compound pages %3d/%d...", i + 1, hpage_pmd_nr); madvise(BASE_ADDR, hpage_pmd_size, MADV_HUGEPAGE); fill_memory(BASE_ADDR, 0, hpage_pmd_size); - if (!check_huge(BASE_ADDR)) { + if (!check_huge(BASE_ADDR, 1)) { printf("Failed to allocate huge page\n"); exit(EXIT_FAILURE); } @@ -823,12 +829,12 @@ static void collapse_compound_extreme(struct collapse_context *c) munmap(BASE_ADDR, hpage_pmd_size); fill_memory(p, 0, hpage_pmd_size); - if (!check_huge(p)) + if (check_huge(p, 0)) success("OK"); else fail("Fail"); - c->collapse("Collapse PTE table full of different compound pages", p, + c->collapse("Collapse PTE table full of different compound pages", p, 1, true); validate_memory(p, 0, hpage_pmd_size); @@ -840,11 +846,11 @@ static void collapse_fork(struct collapse_context *c) int wstatus; void *p; - p = alloc_mapping(); + p = alloc_mapping(1); printf("Allocate small page..."); fill_memory(p, 0, page_size); - if (!check_huge(p)) + if (check_huge(p, 0)) success("OK"); else fail("Fail"); @@ -855,14 +861,14 @@ static void collapse_fork(struct collapse_context *c) skip_settings_restore = true; exit_status = 0; - if (!check_huge(p)) + if (check_huge(p, 0)) success("OK"); else fail("Fail"); fill_memory(p, page_size, 2 * page_size); c->collapse("Collapse PTE table with single page shared with parent process", - p, true); + p, 1, true); validate_memory(p, 0, page_size); munmap(p, hpage_pmd_size); @@ -873,7 +879,7 @@ static void collapse_fork(struct collapse_context *c) exit_status += WEXITSTATUS(wstatus); printf("Check if parent still has small page..."); - if (!check_huge(p)) + if (check_huge(p, 0)) success("OK"); else fail("Fail"); @@ -893,7 +899,7 @@ static void collapse_fork_compound(struct collapse_context *c) skip_settings_restore = true; exit_status = 0; - if (check_huge(p)) + if (check_huge(p, 1)) success("OK"); else fail("Fail"); @@ -901,7 +907,7 @@ static void collapse_fork_compound(struct collapse_context *c) printf("Split huge page PMD in child process..."); madvise(p, page_size, MADV_NOHUGEPAGE); madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); - if (!check_huge(p)) + if (check_huge(p, 0)) success("OK"); else fail("Fail"); @@ -909,7 +915,7 @@ static void collapse_fork_compound(struct collapse_context *c) write_num("khugepaged/max_ptes_shared", hpage_pmd_nr - 1); c->collapse("Collapse PTE table full of compound pages in child", - p, true); + p, 1, true); write_num("khugepaged/max_ptes_shared", current_settings()->khugepaged.max_ptes_shared); @@ -922,7 +928,7 @@ static void collapse_fork_compound(struct collapse_context *c) exit_status += WEXITSTATUS(wstatus); printf("Check if parent still has huge page..."); - if (check_huge(p)) + if (check_huge(p, 1)) success("OK"); else fail("Fail"); @@ -943,7 +949,7 @@ static void collapse_max_ptes_shared(struct collapse_context *c) skip_settings_restore = true; exit_status = 0; - if (check_huge(p)) + if (check_huge(p, 1)) success("OK"); else fail("Fail"); @@ -951,26 +957,26 @@ static void collapse_max_ptes_shared(struct collapse_context *c) printf("Trigger CoW on page %d of %d...", hpage_pmd_nr - max_ptes_shared - 1, hpage_pmd_nr); fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared - 1) * page_size); - if (!check_huge(p)) + if (check_huge(p, 0)) success("OK"); else fail("Fail"); c->collapse("Maybe collapse with max_ptes_shared exceeded", p, - !c->enforce_pte_scan_limits); + 1, !c->enforce_pte_scan_limits); if (c->enforce_pte_scan_limits) { printf("Trigger CoW on page %d of %d...", hpage_pmd_nr - max_ptes_shared, hpage_pmd_nr); fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared) * page_size); - if (!check_huge(p)) + if (check_huge(p, 0)) success("OK"); else fail("Fail"); c->collapse("Collapse with max_ptes_shared PTEs shared", - p, true); + p, 1, true); } validate_memory(p, 0, hpage_pmd_size); @@ -982,7 +988,7 @@ static void collapse_max_ptes_shared(struct collapse_context *c) exit_status += WEXITSTATUS(wstatus); printf("Check if parent still has huge page..."); - if (check_huge(p)) + if (check_huge(p, 1)) success("OK"); else fail("Fail"); @@ -995,7 +1001,7 @@ static void madvise_collapse_existing_thps(void) void *p; int err; - p = alloc_mapping(); + p = alloc_mapping(1); fill_memory(p, 0, hpage_pmd_size); printf("Collapse fully populated PTE table..."); @@ -1005,11 +1011,11 @@ static void madvise_collapse_existing_thps(void) * MADV_COLLAPSE in "madvise" mode. */ err = madvise(p, hpage_pmd_size, MADV_COLLAPSE); - if (err == 0 && check_huge(p)) { + if (err == 0 && check_huge(p, 1)) { success("OK"); printf("Re-collapse PMD-mapped hugepage"); err = madvise(p, hpage_pmd_size, MADV_COLLAPSE); - if (err == 0 && check_huge(p)) + if (err == 0 && check_huge(p, 1)) success("OK"); else fail("Fail"); -- cgit From 3505c8e62acfb62908ffd7d2d6c5971657596d1d Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Thu, 22 Sep 2022 11:46:51 -0700 Subject: selftests/vm: retry on EAGAIN for MADV_COLLAPSE selftest MADV_COLLAPSE is a best-effort request that will set errno to an actionable value if the request cannot be performed. For example, if pages are not found on the LRU, or if they are currently locked by something else, MADV_COLLAPSE will fail and set errno to EAGAIN to inform callers that they may try again. Since the khugepaged selftest is the first public use of MADV_COLLAPSE, set a best practice of checking errno and retrying on EAGAIN. Link: https://lkml.kernel.org/r/20220922184651.1016461-2-zokeefe@google.com Fixes: 9330694de59f ("selftests/vm: add MADV_COLLAPSE collapse context to selftests") Signed-off-by: Zach O'Keefe Cc: Axel Rasmussen Cc: Chris Kennelly Cc: David Hildenbrand Cc: David Rientjes Cc: Hugh Dickins Cc: James Houghton Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Minchan Kim Cc: Pasha Tatashin Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Vlastimil Babka Cc: Yang Shi Signed-off-by: Andrew Morton --- tools/testing/selftests/vm/khugepaged.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'tools/testing/selftests/vm/khugepaged.c') diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index b77b1e28cdb3..b55dc331af13 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -1,4 +1,5 @@ #define _GNU_SOURCE +#include #include #include #include @@ -477,6 +478,26 @@ static void fill_memory(int *p, unsigned long start, unsigned long end) p[i * page_size / sizeof(*p)] = i + 0xdead0000; } +/* + * MADV_COLLAPSE is a best-effort request and may fail if an internal + * resource is temporarily unavailable, in which case it will set errno to + * EAGAIN. In such a case, immediately reattempt the operation one more + * time. + */ +static int madvise_collapse_retry(void *p, unsigned long size) +{ + bool retry = true; + int ret; + +retry: + ret = madvise(p, size, MADV_COLLAPSE); + if (ret && errno == EAGAIN && retry) { + retry = false; + goto retry; + } + return ret; +} + /* * Returns pmd-mapped hugepage in VMA marked VM_HUGEPAGE, filled with * validate_memory()'able contents. @@ -531,7 +552,7 @@ static void madvise_collapse(const char *msg, char *p, int nr_hpages, /* Clear VM_NOHUGEPAGE */ madvise(p, nr_hpages * hpage_pmd_size, MADV_HUGEPAGE); - ret = madvise(p, nr_hpages * hpage_pmd_size, MADV_COLLAPSE); + ret = madvise_collapse_retry(p, nr_hpages * hpage_pmd_size); if (((bool)ret) == expect) fail("Fail: Bad return value"); else if (check_huge(p, nr_hpages) != expect) -- cgit From c07c343cda8ef02985ac6583a2e5af892726f734 Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Thu, 22 Sep 2022 15:40:41 -0700 Subject: selftests/vm: dedup THP helpers These files: tools/testing/selftests/vm/vm_util.c tools/testing/selftests/vm/khugepaged.c Both contain logic to: 1) Determine hugepage size on current system 2) Read /proc/self/smaps to determine number of THPs at an address Refactor selftests/vm/khugepaged.c to use the vm_util common helpers and add it as a build dependency. Since selftests/vm/khugepaged.c is the largest user of check_huge(), change the signature of check_huge() to match selftests/vm/khugepaged.c's useage: take an expected number of hugepages, and return a bool indicating if the correct number of hugepages were found. Add a wrapper, check_huge_anon(), in anticipation of checking smaps for file and shmem hugepages. Update existing callsites to use the new pattern / function. Likewise, check_for_pattern() was duplicated, and it's a general enough helper to include in vm_util helpers as well. Link: https://lkml.kernel.org/r/20220907144521.3115321-6-zokeefe@google.com Link: https://lkml.kernel.org/r/20220922224046.1143204-6-zokeefe@google.com Signed-off-by: Zach O'Keefe Reviewed-by: Zi Yan Cc: Axel Rasmussen Cc: Chris Kennelly Cc: David Hildenbrand Cc: David Rientjes Cc: Hugh Dickins Cc: James Houghton Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Minchan Kim Cc: Pasha Tatashin Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Vlastimil Babka Cc: Yang Shi Signed-off-by: Andrew Morton --- tools/testing/selftests/vm/khugepaged.c | 64 ++++----------------------------- 1 file changed, 7 insertions(+), 57 deletions(-) (limited to 'tools/testing/selftests/vm/khugepaged.c') diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index b55dc331af13..235a64b4458c 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -12,6 +12,8 @@ #include #include +#include "vm_util.h" + #ifndef MADV_PAGEOUT #define MADV_PAGEOUT 21 #endif @@ -352,64 +354,12 @@ static void save_settings(void) signal(SIGQUIT, restore_settings); } -#define MAX_LINE_LENGTH 500 - -static bool check_for_pattern(FILE *fp, char *pattern, char *buf) -{ - while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) { - if (!strncmp(buf, pattern, strlen(pattern))) - return true; - } - return false; -} - static bool check_huge(void *addr, int nr_hpages) { - bool thp = false; - 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(PID_SMAPS, "r"); - if (!fp) { - printf("%s: Failed to open file %s\n", __func__, PID_SMAPS); - exit(EXIT_FAILURE); - } - if (!check_for_pattern(fp, addr_pattern, buffer)) - goto err_out; - - ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "AnonHugePages:%10ld kB", - nr_hpages * (hpage_pmd_size >> 10)); - if (ret >= MAX_LINE_LENGTH) { - printf("%s: Pattern is too long\n", __func__); - exit(EXIT_FAILURE); - } - /* - * Fetch the AnonHugePages: in the same block and check whether it got - * the expected number of hugeepages next. - */ - if (!check_for_pattern(fp, "AnonHugePages:", buffer)) - goto err_out; - - if (strncmp(buffer, addr_pattern, strlen(addr_pattern))) - goto err_out; - - thp = true; -err_out: - fclose(fp); - return thp; + return check_huge_anon(addr, nr_hpages, hpage_pmd_size); } - +#define MAX_LINE_LENGTH 500 static bool check_swap(void *addr, unsigned long size) { bool swap = false; @@ -431,7 +381,7 @@ static bool check_swap(void *addr, unsigned long size) printf("%s: Failed to open file %s\n", __func__, PID_SMAPS); exit(EXIT_FAILURE); } - if (!check_for_pattern(fp, addr_pattern, buffer)) + if (!check_for_pattern(fp, addr_pattern, buffer, sizeof(buffer))) goto err_out; ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "Swap:%19ld kB", @@ -444,7 +394,7 @@ static bool check_swap(void *addr, unsigned long size) * Fetch the Swap: in the same block and check whether it got * the expected number of hugeepages next. */ - if (!check_for_pattern(fp, "Swap:", buffer)) + if (!check_for_pattern(fp, "Swap:", buffer, sizeof(buffer))) goto err_out; if (strncmp(buffer, addr_pattern, strlen(addr_pattern))) @@ -1066,7 +1016,7 @@ int main(int argc, const char **argv) setbuf(stdout, NULL); page_size = getpagesize(); - hpage_pmd_size = read_num("hpage_pmd_size"); + hpage_pmd_size = read_pmd_pagesize(); hpage_pmd_nr = hpage_pmd_size / page_size; default_settings.khugepaged.max_ptes_none = hpage_pmd_nr - 1; -- cgit From 8e638707a3f1a82dccbdc9285980329644946d4f Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Thu, 22 Sep 2022 15:40:42 -0700 Subject: selftests/vm: modularize thp collapse memory operations Modularize operations to setup, cleanup, fault, and check for huge pages, for a given memory type. This allows reusing existing tests with additional memory types by defining new memory operations. Following patches will add file and shmem memory types. Link: https://lkml.kernel.org/r/20220907144521.3115321-7-zokeefe@google.com Link: https://lkml.kernel.org/r/20220922224046.1143204-7-zokeefe@google.com Signed-off-by: Zach O'Keefe Cc: Axel Rasmussen Cc: Chris Kennelly Cc: David Hildenbrand Cc: David Rientjes Cc: Hugh Dickins Cc: James Houghton Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Minchan Kim Cc: Pasha Tatashin Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Vlastimil Babka Cc: Yang Shi Signed-off-by: Andrew Morton --- tools/testing/selftests/vm/khugepaged.c | 373 ++++++++++++++++++-------------- 1 file changed, 207 insertions(+), 166 deletions(-) (limited to 'tools/testing/selftests/vm/khugepaged.c') diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index 235a64b4458c..06ea6f18980e 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -29,8 +29,16 @@ static int hpage_pmd_nr; #define THP_SYSFS "/sys/kernel/mm/transparent_hugepage/" #define PID_SMAPS "/proc/self/smaps" +struct mem_ops { + void *(*setup_area)(int nr_hpages); + void (*cleanup_area)(void *p, unsigned long size); + void (*fault)(void *p, unsigned long start, unsigned long end); + bool (*check_huge)(void *addr, int nr_hpages); +}; + struct collapse_context { - void (*collapse)(const char *msg, char *p, int nr_hpages, bool expect); + void (*collapse)(const char *msg, char *p, int nr_hpages, + struct mem_ops *ops, bool expect); bool enforce_pte_scan_limits; }; @@ -354,11 +362,6 @@ static void save_settings(void) signal(SIGQUIT, restore_settings); } -static bool check_huge(void *addr, int nr_hpages) -{ - return check_huge_anon(addr, nr_hpages, hpage_pmd_size); -} - #define MAX_LINE_LENGTH 500 static bool check_swap(void *addr, unsigned long size) { @@ -452,18 +455,33 @@ retry: * Returns pmd-mapped hugepage in VMA marked VM_HUGEPAGE, filled with * validate_memory()'able contents. */ -static void *alloc_hpage(void) +static void *alloc_hpage(struct mem_ops *ops) { - void *p; + void *p = ops->setup_area(1); - p = alloc_mapping(1); + ops->fault(p, 0, hpage_pmd_size); + + /* + * VMA should be neither VM_HUGEPAGE nor VM_NOHUGEPAGE. + * The latter is ineligible for collapse by MADV_COLLAPSE + * while the former might cause MADV_COLLAPSE to race with + * khugepaged on low-load system (like a test machine), which + * would cause MADV_COLLAPSE to fail with EAGAIN. + */ printf("Allocate huge page..."); - madvise(p, hpage_pmd_size, MADV_HUGEPAGE); - fill_memory(p, 0, hpage_pmd_size); - if (check_huge(p, 1)) - success("OK"); - else - fail("Fail"); + if (madvise_collapse_retry(p, hpage_pmd_size)) { + perror("madvise(MADV_COLLAPSE)"); + exit(EXIT_FAILURE); + } + if (!ops->check_huge(p, 1)) { + perror("madvise(MADV_COLLAPSE)"); + exit(EXIT_FAILURE); + } + if (madvise(p, hpage_pmd_size, MADV_HUGEPAGE)) { + perror("madvise(MADV_HUGEPAGE)"); + exit(EXIT_FAILURE); + } + success("OK"); return p; } @@ -480,18 +498,40 @@ static void validate_memory(int *p, unsigned long start, unsigned long end) } } -static void madvise_collapse(const char *msg, char *p, int nr_hpages, - bool expect) +static void *anon_setup_area(int nr_hpages) +{ + return alloc_mapping(nr_hpages); +} + +static void anon_cleanup_area(void *p, unsigned long size) +{ + munmap(p, size); +} + +static void anon_fault(void *p, unsigned long start, unsigned long end) +{ + fill_memory(p, start, end); +} + +static bool anon_check_huge(void *addr, int nr_hpages) +{ + return check_huge_anon(addr, nr_hpages, hpage_pmd_size); +} + +static struct mem_ops anon_ops = { + .setup_area = &anon_setup_area, + .cleanup_area = &anon_cleanup_area, + .fault = &anon_fault, + .check_huge = &anon_check_huge, +}; + +static void __madvise_collapse(const char *msg, char *p, int nr_hpages, + struct mem_ops *ops, bool expect) { int ret; struct settings settings = *current_settings(); printf("%s...", msg); - /* Sanity check */ - if (!check_huge(p, 0)) { - printf("Unexpected huge page\n"); - exit(EXIT_FAILURE); - } /* * Prevent khugepaged interference and tests that MADV_COLLAPSE @@ -505,7 +545,7 @@ static void madvise_collapse(const char *msg, char *p, int nr_hpages, ret = madvise_collapse_retry(p, nr_hpages * hpage_pmd_size); if (((bool)ret) == expect) fail("Fail: Bad return value"); - else if (check_huge(p, nr_hpages) != expect) + else if (!ops->check_huge(p, expect ? nr_hpages : 0)) fail("Fail: check_huge()"); else success("OK"); @@ -513,14 +553,26 @@ static void madvise_collapse(const char *msg, char *p, int nr_hpages, pop_settings(); } +static void madvise_collapse(const char *msg, char *p, int nr_hpages, + struct mem_ops *ops, bool expect) +{ + /* Sanity check */ + if (!ops->check_huge(p, 0)) { + printf("Unexpected huge page\n"); + exit(EXIT_FAILURE); + } + __madvise_collapse(msg, p, nr_hpages, ops, expect); +} + #define TICK 500000 -static bool wait_for_scan(const char *msg, char *p, int nr_hpages) +static bool wait_for_scan(const char *msg, char *p, int nr_hpages, + struct mem_ops *ops) { int full_scans; int timeout = 6; /* 3 seconds */ /* Sanity check */ - if (!check_huge(p, 0)) { + if (!ops->check_huge(p, 0)) { printf("Unexpected huge page\n"); exit(EXIT_FAILURE); } @@ -532,7 +584,7 @@ static bool wait_for_scan(const char *msg, char *p, int nr_hpages) printf("%s...", msg); while (timeout--) { - if (check_huge(p, nr_hpages)) + if (ops->check_huge(p, nr_hpages)) break; if (read_num("khugepaged/full_scans") >= full_scans) break; @@ -546,19 +598,20 @@ static bool wait_for_scan(const char *msg, char *p, int nr_hpages) } static void khugepaged_collapse(const char *msg, char *p, int nr_hpages, - bool expect) + struct mem_ops *ops, bool expect) { - if (wait_for_scan(msg, p, nr_hpages)) { + if (wait_for_scan(msg, p, nr_hpages, ops)) { if (expect) fail("Timeout"); else success("OK"); return; - } else if (check_huge(p, nr_hpages) == expect) { + } + + if (ops->check_huge(p, expect ? nr_hpages : 0)) success("OK"); - } else { + else fail("Fail"); - } } static void alloc_at_fault(void) @@ -572,7 +625,7 @@ static void alloc_at_fault(void) p = alloc_mapping(1); *p = 1; printf("Allocate huge page on fault..."); - if (check_huge(p, 1)) + if (check_huge_anon(p, 1, hpage_pmd_size)) success("OK"); else fail("Fail"); @@ -581,49 +634,48 @@ static void alloc_at_fault(void) madvise(p, page_size, MADV_DONTNEED); printf("Split huge PMD on MADV_DONTNEED..."); - if (check_huge(p, 0)) + if (check_huge_anon(p, 0, hpage_pmd_size)) success("OK"); else fail("Fail"); munmap(p, hpage_pmd_size); } -static void collapse_full(struct collapse_context *c) +static void collapse_full(struct collapse_context *c, struct mem_ops *ops) { void *p; int nr_hpages = 4; unsigned long size = nr_hpages * hpage_pmd_size; - p = alloc_mapping(nr_hpages); - fill_memory(p, 0, size); + p = ops->setup_area(nr_hpages); + ops->fault(p, 0, size); c->collapse("Collapse multiple fully populated PTE table", p, nr_hpages, - true); + ops, true); validate_memory(p, 0, size); - munmap(p, size); + ops->cleanup_area(p, size); } -static void collapse_empty(struct collapse_context *c) +static void collapse_empty(struct collapse_context *c, struct mem_ops *ops) { void *p; - p = alloc_mapping(1); - c->collapse("Do not collapse empty PTE table", p, 1, false); - munmap(p, hpage_pmd_size); + p = ops->setup_area(1); + c->collapse("Do not collapse empty PTE table", p, 1, ops, false); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_single_pte_entry(struct collapse_context *c) +static void collapse_single_pte_entry(struct collapse_context *c, struct mem_ops *ops) { void *p; - p = alloc_mapping(1); - fill_memory(p, 0, page_size); + p = ops->setup_area(1); + ops->fault(p, 0, page_size); c->collapse("Collapse PTE table with single PTE entry present", p, - 1, true); - validate_memory(p, 0, page_size); - munmap(p, hpage_pmd_size); + 1, ops, true); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_max_ptes_none(struct collapse_context *c) +static void collapse_max_ptes_none(struct collapse_context *c, struct mem_ops *ops) { int max_ptes_none = hpage_pmd_nr / 2; struct settings settings = *current_settings(); @@ -632,30 +684,30 @@ static void collapse_max_ptes_none(struct collapse_context *c) settings.khugepaged.max_ptes_none = max_ptes_none; push_settings(&settings); - p = alloc_mapping(1); + p = ops->setup_area(1); - fill_memory(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size); + ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size); c->collapse("Maybe collapse with max_ptes_none exceeded", p, 1, - !c->enforce_pte_scan_limits); + ops, !c->enforce_pte_scan_limits); validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size); if (c->enforce_pte_scan_limits) { - fill_memory(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size); - c->collapse("Collapse with max_ptes_none PTEs empty", p, 1, + ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size); + c->collapse("Collapse with max_ptes_none PTEs empty", p, 1, ops, true); validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size); } - - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); pop_settings(); } -static void collapse_swapin_single_pte(struct collapse_context *c) +static void collapse_swapin_single_pte(struct collapse_context *c, struct mem_ops *ops) { void *p; - p = alloc_mapping(1); - fill_memory(p, 0, hpage_pmd_size); + + p = ops->setup_area(1); + ops->fault(p, 0, hpage_pmd_size); printf("Swapout one page..."); if (madvise(p, page_size, MADV_PAGEOUT)) { @@ -669,20 +721,21 @@ static void collapse_swapin_single_pte(struct collapse_context *c) goto out; } - c->collapse("Collapse with swapping in single PTE entry", p, 1, true); + c->collapse("Collapse with swapping in single PTE entry", p, 1, ops, + true); validate_memory(p, 0, hpage_pmd_size); out: - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_max_ptes_swap(struct collapse_context *c) +static void collapse_max_ptes_swap(struct collapse_context *c, struct mem_ops *ops) { int max_ptes_swap = read_num("khugepaged/max_ptes_swap"); void *p; - p = alloc_mapping(1); + p = ops->setup_area(1); + ops->fault(p, 0, hpage_pmd_size); - fill_memory(p, 0, hpage_pmd_size); printf("Swapout %d of %d pages...", max_ptes_swap + 1, hpage_pmd_nr); if (madvise(p, (max_ptes_swap + 1) * page_size, MADV_PAGEOUT)) { perror("madvise(MADV_PAGEOUT)"); @@ -695,12 +748,12 @@ static void collapse_max_ptes_swap(struct collapse_context *c) goto out; } - c->collapse("Maybe collapse with max_ptes_swap exceeded", p, 1, + c->collapse("Maybe collapse with max_ptes_swap exceeded", p, 1, ops, !c->enforce_pte_scan_limits); validate_memory(p, 0, hpage_pmd_size); if (c->enforce_pte_scan_limits) { - fill_memory(p, 0, hpage_pmd_size); + ops->fault(p, 0, hpage_pmd_size); printf("Swapout %d of %d pages...", max_ptes_swap, hpage_pmd_nr); if (madvise(p, max_ptes_swap * page_size, MADV_PAGEOUT)) { @@ -715,63 +768,65 @@ static void collapse_max_ptes_swap(struct collapse_context *c) } c->collapse("Collapse with max_ptes_swap pages swapped out", p, - 1, true); + 1, ops, true); validate_memory(p, 0, hpage_pmd_size); } out: - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_single_pte_entry_compound(struct collapse_context *c) +static void collapse_single_pte_entry_compound(struct collapse_context *c, struct mem_ops *ops) { void *p; - p = alloc_hpage(); + p = alloc_hpage(ops); + madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); printf("Split huge page leaving single PTE mapping compound page..."); madvise(p + page_size, hpage_pmd_size - page_size, MADV_DONTNEED); - if (check_huge(p, 0)) + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); c->collapse("Collapse PTE table with single PTE mapping compound page", - p, 1, true); + p, 1, ops, true); validate_memory(p, 0, page_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_full_of_compound(struct collapse_context *c) +static void collapse_full_of_compound(struct collapse_context *c, struct mem_ops *ops) { void *p; - p = alloc_hpage(); + p = alloc_hpage(ops); printf("Split huge page leaving single PTE page table full of compound pages..."); madvise(p, page_size, MADV_NOHUGEPAGE); madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); - if (check_huge(p, 0)) + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); - c->collapse("Collapse PTE table full of compound pages", p, 1, true); + c->collapse("Collapse PTE table full of compound pages", p, 1, ops, + true); validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_compound_extreme(struct collapse_context *c) +static void collapse_compound_extreme(struct collapse_context *c, struct mem_ops *ops) { void *p; int i; - p = alloc_mapping(1); + p = ops->setup_area(1); for (i = 0; i < hpage_pmd_nr; i++) { printf("\rConstruct PTE page table full of different PTE-mapped compound pages %3d/%d...", i + 1, hpage_pmd_nr); madvise(BASE_ADDR, hpage_pmd_size, MADV_HUGEPAGE); - fill_memory(BASE_ADDR, 0, hpage_pmd_size); - if (!check_huge(BASE_ADDR, 1)) { + ops->fault(BASE_ADDR, 0, hpage_pmd_size); + if (!ops->check_huge(BASE_ADDR, 1)) { printf("Failed to allocate huge page\n"); exit(EXIT_FAILURE); } @@ -798,30 +853,30 @@ static void collapse_compound_extreme(struct collapse_context *c) } } - munmap(BASE_ADDR, hpage_pmd_size); - fill_memory(p, 0, hpage_pmd_size); - if (check_huge(p, 0)) + ops->cleanup_area(BASE_ADDR, hpage_pmd_size); + ops->fault(p, 0, hpage_pmd_size); + if (!ops->check_huge(p, 1)) success("OK"); else fail("Fail"); c->collapse("Collapse PTE table full of different compound pages", p, 1, - true); + ops, true); validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_fork(struct collapse_context *c) +static void collapse_fork(struct collapse_context *c, struct mem_ops *ops) { int wstatus; void *p; - p = alloc_mapping(1); + p = ops->setup_area(1); printf("Allocate small page..."); - fill_memory(p, 0, page_size); - if (check_huge(p, 0)) + ops->fault(p, 0, page_size); + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); @@ -832,17 +887,17 @@ static void collapse_fork(struct collapse_context *c) skip_settings_restore = true; exit_status = 0; - if (check_huge(p, 0)) + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); - fill_memory(p, page_size, 2 * page_size); + ops->fault(p, page_size, 2 * page_size); c->collapse("Collapse PTE table with single page shared with parent process", - p, 1, true); + p, 1, ops, true); validate_memory(p, 0, page_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); exit(exit_status); } @@ -850,27 +905,27 @@ static void collapse_fork(struct collapse_context *c) exit_status += WEXITSTATUS(wstatus); printf("Check if parent still has small page..."); - if (check_huge(p, 0)) + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); validate_memory(p, 0, page_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_fork_compound(struct collapse_context *c) +static void collapse_fork_compound(struct collapse_context *c, struct mem_ops *ops) { int wstatus; void *p; - p = alloc_hpage(); + p = alloc_hpage(ops); printf("Share huge page over fork()..."); if (!fork()) { /* Do not touch settings on child exit */ skip_settings_restore = true; exit_status = 0; - if (check_huge(p, 1)) + if (ops->check_huge(p, 1)) success("OK"); else fail("Fail"); @@ -878,20 +933,20 @@ static void collapse_fork_compound(struct collapse_context *c) printf("Split huge page PMD in child process..."); madvise(p, page_size, MADV_NOHUGEPAGE); madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); - if (check_huge(p, 0)) + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); - fill_memory(p, 0, page_size); + ops->fault(p, 0, page_size); write_num("khugepaged/max_ptes_shared", hpage_pmd_nr - 1); c->collapse("Collapse PTE table full of compound pages in child", - p, 1, true); + p, 1, ops, true); write_num("khugepaged/max_ptes_shared", current_settings()->khugepaged.max_ptes_shared); validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); exit(exit_status); } @@ -899,59 +954,59 @@ static void collapse_fork_compound(struct collapse_context *c) exit_status += WEXITSTATUS(wstatus); printf("Check if parent still has huge page..."); - if (check_huge(p, 1)) + if (ops->check_huge(p, 1)) success("OK"); else fail("Fail"); validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void collapse_max_ptes_shared(struct collapse_context *c) +static void collapse_max_ptes_shared(struct collapse_context *c, struct mem_ops *ops) { int max_ptes_shared = read_num("khugepaged/max_ptes_shared"); int wstatus; void *p; - p = alloc_hpage(); + p = alloc_hpage(ops); printf("Share huge page over fork()..."); if (!fork()) { /* Do not touch settings on child exit */ skip_settings_restore = true; exit_status = 0; - if (check_huge(p, 1)) + if (ops->check_huge(p, 1)) success("OK"); else fail("Fail"); printf("Trigger CoW on page %d of %d...", hpage_pmd_nr - max_ptes_shared - 1, hpage_pmd_nr); - fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared - 1) * page_size); - if (check_huge(p, 0)) + ops->fault(p, 0, (hpage_pmd_nr - max_ptes_shared - 1) * page_size); + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); c->collapse("Maybe collapse with max_ptes_shared exceeded", p, - 1, !c->enforce_pte_scan_limits); + 1, ops, !c->enforce_pte_scan_limits); if (c->enforce_pte_scan_limits) { printf("Trigger CoW on page %d of %d...", hpage_pmd_nr - max_ptes_shared, hpage_pmd_nr); - fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared) * + ops->fault(p, 0, (hpage_pmd_nr - max_ptes_shared) * page_size); - if (check_huge(p, 0)) + if (ops->check_huge(p, 0)) success("OK"); else fail("Fail"); c->collapse("Collapse with max_ptes_shared PTEs shared", - p, 1, true); + p, 1, ops, true); } validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); exit(exit_status); } @@ -959,42 +1014,28 @@ static void collapse_max_ptes_shared(struct collapse_context *c) exit_status += WEXITSTATUS(wstatus); printf("Check if parent still has huge page..."); - if (check_huge(p, 1)) + if (ops->check_huge(p, 1)) success("OK"); else fail("Fail"); validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } -static void madvise_collapse_existing_thps(void) +static void madvise_collapse_existing_thps(struct collapse_context *c, + struct mem_ops *ops) { void *p; - int err; - p = alloc_mapping(1); - fill_memory(p, 0, hpage_pmd_size); + p = ops->setup_area(1); + ops->fault(p, 0, hpage_pmd_size); + c->collapse("Collapse fully populated PTE table...", p, 1, ops, true); + validate_memory(p, 0, hpage_pmd_size); - printf("Collapse fully populated PTE table..."); - /* - * Note that we don't set MADV_HUGEPAGE here, which - * also tests that VM_HUGEPAGE isn't required for - * MADV_COLLAPSE in "madvise" mode. - */ - err = madvise(p, hpage_pmd_size, MADV_COLLAPSE); - if (err == 0 && check_huge(p, 1)) { - success("OK"); - printf("Re-collapse PMD-mapped hugepage"); - err = madvise(p, hpage_pmd_size, MADV_COLLAPSE); - if (err == 0 && check_huge(p, 1)) - success("OK"); - else - fail("Fail"); - } else { - fail("Fail"); - } + /* c->collapse() will find a hugepage and complain - call directly. */ + __madvise_collapse("Re-collapse PMD-mapped hugepage", p, 1, ops, true); validate_memory(p, 0, hpage_pmd_size); - munmap(p, hpage_pmd_size); + ops->cleanup_area(p, hpage_pmd_size); } int main(int argc, const char **argv) @@ -1034,37 +1075,37 @@ int main(int argc, const char **argv) c.collapse = &khugepaged_collapse; c.enforce_pte_scan_limits = true; - collapse_full(&c); - collapse_empty(&c); - collapse_single_pte_entry(&c); - collapse_max_ptes_none(&c); - collapse_swapin_single_pte(&c); - collapse_max_ptes_swap(&c); - collapse_single_pte_entry_compound(&c); - collapse_full_of_compound(&c); - collapse_compound_extreme(&c); - collapse_fork(&c); - collapse_fork_compound(&c); - collapse_max_ptes_shared(&c); + collapse_full(&c, &anon_ops); + collapse_empty(&c, &anon_ops); + collapse_single_pte_entry(&c, &anon_ops); + collapse_max_ptes_none(&c, &anon_ops); + collapse_swapin_single_pte(&c, &anon_ops); + collapse_max_ptes_swap(&c, &anon_ops); + collapse_single_pte_entry_compound(&c, &anon_ops); + collapse_full_of_compound(&c, &anon_ops); + collapse_compound_extreme(&c, &anon_ops); + collapse_fork(&c, &anon_ops); + collapse_fork_compound(&c, &anon_ops); + collapse_max_ptes_shared(&c, &anon_ops); } if (!strcmp(tests, "madvise") || !strcmp(tests, "all")) { printf("\n*** Testing context: madvise ***\n"); c.collapse = &madvise_collapse; c.enforce_pte_scan_limits = false; - collapse_full(&c); - collapse_empty(&c); - collapse_single_pte_entry(&c); - collapse_max_ptes_none(&c); - collapse_swapin_single_pte(&c); - collapse_max_ptes_swap(&c); - collapse_single_pte_entry_compound(&c); - collapse_full_of_compound(&c); - collapse_compound_extreme(&c); - collapse_fork(&c); - collapse_fork_compound(&c); - collapse_max_ptes_shared(&c); - madvise_collapse_existing_thps(); + collapse_full(&c, &anon_ops); + collapse_empty(&c, &anon_ops); + collapse_single_pte_entry(&c, &anon_ops); + collapse_max_ptes_none(&c, &anon_ops); + collapse_swapin_single_pte(&c, &anon_ops); + collapse_max_ptes_swap(&c, &anon_ops); + collapse_single_pte_entry_compound(&c, &anon_ops); + collapse_full_of_compound(&c, &anon_ops); + collapse_compound_extreme(&c, &anon_ops); + collapse_fork(&c, &anon_ops); + collapse_fork_compound(&c, &anon_ops); + collapse_max_ptes_shared(&c, &anon_ops); + madvise_collapse_existing_thps(&c, &anon_ops); } restore_settings(0); -- cgit From 1b03d0d558a281f12f68e5917dfa781c3b94e074 Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Thu, 22 Sep 2022 15:40:43 -0700 Subject: selftests/vm: add thp collapse file and tmpfs testing Add memory operations for file-backed and tmpfs memory. Call existing tests with these new memory operations to test collapse functionality of khugepaged and MADV_COLLAPSE on file-backed and tmpfs memory. Not all tests are reusable; for example, collapse_swapin_single_pte() which checks swap usage. Refactor test arguments. Usage is now: Usage: ./khugepaged [dir] : : : [all|khugepaged|madvise] : [all|anon|file] "file,all" mem_type requires [dir] argument "file,all" mem_type requires kernel built with CONFIG_READ_ONLY_THP_FOR_FS=y if [dir] is a (sub)directory of a tmpfs mount, tmpfs must be mounted with huge=madvise option for khugepaged tests to work Refactor calling tests to make it clear what collapse context / memory operations they support, but only invoke tests requested by user. Also log what test is being ran, and with what context / memory, to make test logs more human readable. A new test file is created and deleted for every test to ensure no pages remain in the page cache between tests (tests also may attempt to collapse different amount of memory). For file-backed memory where the file is stored on a block device, disable /sys/block//queue/read_ahead_kb so that pages don't find their way into the page cache without the tests faulting them in. Add file and shmem wrappers to vm_utils check for file and shmem hugepages in smaps. [zokeefe@google.com: fix "add thp collapse file and tmpfs testing" for tmpfs] Link: https://lkml.kernel.org/r/20220913212517.3163701-1-zokeefe@google.com Link: https://lkml.kernel.org/r/20220907144521.3115321-8-zokeefe@google.com Link: https://lkml.kernel.org/r/20220922224046.1143204-8-zokeefe@google.com Signed-off-by: Zach O'Keefe Cc: Axel Rasmussen Cc: Chris Kennelly Cc: David Hildenbrand Cc: David Rientjes Cc: Hugh Dickins Cc: James Houghton Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Minchan Kim Cc: Pasha Tatashin Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Vlastimil Babka Cc: Yang Shi Signed-off-by: Andrew Morton --- tools/testing/selftests/vm/khugepaged.c | 475 ++++++++++++++++++++++++++++---- 1 file changed, 419 insertions(+), 56 deletions(-) (limited to 'tools/testing/selftests/vm/khugepaged.c') diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index 06ea6f18980e..08de6141c2af 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -1,7 +1,9 @@ #define _GNU_SOURCE +#include #include #include #include +#include #include #include #include @@ -11,12 +13,21 @@ #include #include +#include +#include +#include +#include + +#include "linux/magic.h" #include "vm_util.h" #ifndef MADV_PAGEOUT #define MADV_PAGEOUT 21 #endif +#ifndef MADV_POPULATE_READ +#define MADV_POPULATE_READ 22 +#endif #ifndef MADV_COLLAPSE #define MADV_COLLAPSE 25 #endif @@ -28,20 +39,47 @@ static int hpage_pmd_nr; #define THP_SYSFS "/sys/kernel/mm/transparent_hugepage/" #define PID_SMAPS "/proc/self/smaps" +#define TEST_FILE "collapse_test_file" + +#define MAX_LINE_LENGTH 500 + +enum vma_type { + VMA_ANON, + VMA_FILE, + VMA_SHMEM, +}; struct mem_ops { void *(*setup_area)(int nr_hpages); void (*cleanup_area)(void *p, unsigned long size); void (*fault)(void *p, unsigned long start, unsigned long end); bool (*check_huge)(void *addr, int nr_hpages); + const char *name; }; +static struct mem_ops *file_ops; +static struct mem_ops *anon_ops; + struct collapse_context { void (*collapse)(const char *msg, char *p, int nr_hpages, struct mem_ops *ops, bool expect); bool enforce_pte_scan_limits; + const char *name; +}; + +static struct collapse_context *khugepaged_context; +static struct collapse_context *madvise_context; + +struct file_info { + const char *dir; + char path[PATH_MAX]; + enum vma_type type; + int fd; + char dev_queue_read_ahead_path[PATH_MAX]; }; +static struct file_info finfo; + enum thp_enabled { THP_ALWAYS, THP_MADVISE, @@ -107,6 +145,7 @@ struct settings { enum shmem_enabled shmem_enabled; bool use_zero_page; struct khugepaged_settings khugepaged; + unsigned long read_ahead_kb; }; static struct settings saved_settings; @@ -125,6 +164,11 @@ static void fail(const char *msg) exit_status++; } +static void skip(const char *msg) +{ + printf(" \e[33m%s\e[0m\n", msg); +} + static int read_file(const char *path, char *buf, size_t buflen) { int fd; @@ -152,13 +196,19 @@ static int write_file(const char *path, const char *buf, size_t buflen) ssize_t numwritten; fd = open(path, O_WRONLY); - if (fd == -1) + if (fd == -1) { + printf("open(%s)\n", path); + exit(EXIT_FAILURE); return 0; + } numwritten = write(fd, buf, buflen - 1); close(fd); - if (numwritten < 1) + if (numwritten < 1) { + printf("write(%s)\n", buf); + exit(EXIT_FAILURE); return 0; + } return (unsigned int) numwritten; } @@ -225,20 +275,11 @@ static void write_string(const char *name, const char *val) } } -static const unsigned long read_num(const char *name) +static const unsigned long _read_num(const char *path) { - char path[PATH_MAX]; char buf[21]; - int ret; - ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name); - if (ret >= PATH_MAX) { - printf("%s: Pathname is too long\n", __func__); - exit(EXIT_FAILURE); - } - - ret = read_file(path, buf, sizeof(buf)); - if (ret < 0) { + if (read_file(path, buf, sizeof(buf)) < 0) { perror("read_file(read_num)"); exit(EXIT_FAILURE); } @@ -246,10 +287,9 @@ static const unsigned long read_num(const char *name) return strtoul(buf, NULL, 10); } -static void write_num(const char *name, unsigned long num) +static const unsigned long read_num(const char *name) { char path[PATH_MAX]; - char buf[21]; int ret; ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name); @@ -257,6 +297,12 @@ static void write_num(const char *name, unsigned long num) printf("%s: Pathname is too long\n", __func__); exit(EXIT_FAILURE); } + return _read_num(path); +} + +static void _write_num(const char *path, unsigned long num) +{ + char buf[21]; sprintf(buf, "%ld", num); if (!write_file(path, buf, strlen(buf) + 1)) { @@ -265,6 +311,19 @@ static void write_num(const char *name, unsigned long num) } } +static void write_num(const char *name, unsigned long num) +{ + char path[PATH_MAX]; + int ret; + + ret = snprintf(path, PATH_MAX, THP_SYSFS "%s", name); + if (ret >= PATH_MAX) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + _write_num(path, num); +} + static void write_settings(struct settings *settings) { struct khugepaged_settings *khugepaged = &settings->khugepaged; @@ -284,6 +343,10 @@ static void write_settings(struct settings *settings) write_num("khugepaged/max_ptes_swap", khugepaged->max_ptes_swap); write_num("khugepaged/max_ptes_shared", khugepaged->max_ptes_shared); write_num("khugepaged/pages_to_scan", khugepaged->pages_to_scan); + + if (file_ops && finfo.type == VMA_FILE) + _write_num(finfo.dev_queue_read_ahead_path, + settings->read_ahead_kb); } #define MAX_SETTINGS_DEPTH 4 @@ -354,6 +417,10 @@ static void save_settings(void) .max_ptes_shared = read_num("khugepaged/max_ptes_shared"), .pages_to_scan = read_num("khugepaged/pages_to_scan"), }; + if (file_ops && finfo.type == VMA_FILE) + saved_settings.read_ahead_kb = + _read_num(finfo.dev_queue_read_ahead_path); + success("OK"); signal(SIGTERM, restore_settings); @@ -362,7 +429,90 @@ static void save_settings(void) signal(SIGQUIT, restore_settings); } -#define MAX_LINE_LENGTH 500 +static void get_finfo(const char *dir) +{ + struct stat path_stat; + struct statfs fs; + char buf[1 << 10]; + char path[PATH_MAX]; + char *str, *end; + + finfo.dir = dir; + stat(finfo.dir, &path_stat); + if (!S_ISDIR(path_stat.st_mode)) { + printf("%s: Not a directory (%s)\n", __func__, finfo.dir); + exit(EXIT_FAILURE); + } + if (snprintf(finfo.path, sizeof(finfo.path), "%s/" TEST_FILE, + finfo.dir) >= sizeof(finfo.path)) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + if (statfs(finfo.dir, &fs)) { + perror("statfs()"); + exit(EXIT_FAILURE); + } + finfo.type = fs.f_type == TMPFS_MAGIC ? VMA_SHMEM : VMA_FILE; + if (finfo.type == VMA_SHMEM) + return; + + /* Find owning device's queue/read_ahead_kb control */ + if (snprintf(path, sizeof(path), "/sys/dev/block/%d:%d/uevent", + major(path_stat.st_dev), minor(path_stat.st_dev)) + >= sizeof(path)) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + if (read_file(path, buf, sizeof(buf)) < 0) { + perror("read_file(read_num)"); + exit(EXIT_FAILURE); + } + if (strstr(buf, "DEVTYPE=disk")) { + /* Found it */ + if (snprintf(finfo.dev_queue_read_ahead_path, + sizeof(finfo.dev_queue_read_ahead_path), + "/sys/dev/block/%d:%d/queue/read_ahead_kb", + major(path_stat.st_dev), minor(path_stat.st_dev)) + >= sizeof(finfo.dev_queue_read_ahead_path)) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + return; + } + if (!strstr(buf, "DEVTYPE=partition")) { + printf("%s: Unknown device type: %s\n", __func__, path); + exit(EXIT_FAILURE); + } + /* + * Partition of block device - need to find actual device. + * Using naming convention that devnameN is partition of + * device devname. + */ + str = strstr(buf, "DEVNAME="); + if (!str) { + printf("%s: Could not read: %s", __func__, path); + exit(EXIT_FAILURE); + } + str += 8; + end = str; + while (*end) { + if (isdigit(*end)) { + *end = '\0'; + if (snprintf(finfo.dev_queue_read_ahead_path, + sizeof(finfo.dev_queue_read_ahead_path), + "/sys/block/%s/queue/read_ahead_kb", + str) >= sizeof(finfo.dev_queue_read_ahead_path)) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + return; + } + ++end; + } + printf("%s: Could not read: %s\n", __func__, path); + exit(EXIT_FAILURE); +} + static bool check_swap(void *addr, unsigned long size) { bool swap = false; @@ -518,11 +668,91 @@ static bool anon_check_huge(void *addr, int nr_hpages) return check_huge_anon(addr, nr_hpages, hpage_pmd_size); } -static struct mem_ops anon_ops = { +static void *file_setup_area(int nr_hpages) +{ + int fd; + void *p; + unsigned long size; + + unlink(finfo.path); /* Cleanup from previous failed tests */ + printf("Creating %s for collapse%s...", finfo.path, + finfo.type == VMA_SHMEM ? " (tmpfs)" : ""); + fd = open(finfo.path, O_DSYNC | O_CREAT | O_RDWR | O_TRUNC | O_EXCL, + 777); + if (fd < 0) { + perror("open()"); + exit(EXIT_FAILURE); + } + + size = nr_hpages * hpage_pmd_size; + p = alloc_mapping(nr_hpages); + fill_memory(p, 0, size); + write(fd, p, size); + close(fd); + munmap(p, size); + success("OK"); + + printf("Opening %s read only for collapse...", finfo.path); + finfo.fd = open(finfo.path, O_RDONLY, 777); + if (finfo.fd < 0) { + perror("open()"); + exit(EXIT_FAILURE); + } + p = mmap(BASE_ADDR, size, PROT_READ | PROT_EXEC, + MAP_PRIVATE, finfo.fd, 0); + if (p == MAP_FAILED || p != BASE_ADDR) { + perror("mmap()"); + exit(EXIT_FAILURE); + } + + /* Drop page cache */ + write_file("/proc/sys/vm/drop_caches", "3", 2); + success("OK"); + return p; +} + +static void file_cleanup_area(void *p, unsigned long size) +{ + munmap(p, size); + close(finfo.fd); + unlink(finfo.path); +} + +static void file_fault(void *p, unsigned long start, unsigned long end) +{ + if (madvise(((char *)p) + start, end - start, MADV_POPULATE_READ)) { + perror("madvise(MADV_POPULATE_READ"); + exit(EXIT_FAILURE); + } +} + +static bool file_check_huge(void *addr, int nr_hpages) +{ + switch (finfo.type) { + case VMA_FILE: + return check_huge_file(addr, nr_hpages, hpage_pmd_size); + case VMA_SHMEM: + return check_huge_shmem(addr, nr_hpages, hpage_pmd_size); + default: + exit(EXIT_FAILURE); + return false; + } +} + +static struct mem_ops __anon_ops = { .setup_area = &anon_setup_area, .cleanup_area = &anon_cleanup_area, .fault = &anon_fault, .check_huge = &anon_check_huge, + .name = "anon", +}; + +static struct mem_ops __file_ops = { + .setup_area = &file_setup_area, + .cleanup_area = &file_cleanup_area, + .fault = &file_fault, + .check_huge = &file_check_huge, + .name = "file", }; static void __madvise_collapse(const char *msg, char *p, int nr_hpages, @@ -538,6 +768,7 @@ static void __madvise_collapse(const char *msg, char *p, int nr_hpages, * ignores /sys/kernel/mm/transparent_hugepage/enabled */ settings.thp_enabled = THP_NEVER; + settings.shmem_enabled = SHMEM_NEVER; push_settings(&settings); /* Clear VM_NOHUGEPAGE */ @@ -608,12 +839,37 @@ static void khugepaged_collapse(const char *msg, char *p, int nr_hpages, return; } + /* + * For file and shmem memory, khugepaged only retracts pte entries after + * putting the new hugepage in the page cache. The hugepage must be + * subsequently refaulted to install the pmd mapping for the mm. + */ + if (ops != &__anon_ops) + ops->fault(p, 0, nr_hpages * hpage_pmd_size); + if (ops->check_huge(p, expect ? nr_hpages : 0)) success("OK"); else fail("Fail"); } +static struct collapse_context __khugepaged_context = { + .collapse = &khugepaged_collapse, + .enforce_pte_scan_limits = true, + .name = "khugepaged", +}; + +static struct collapse_context __madvise_context = { + .collapse = &madvise_collapse, + .enforce_pte_scan_limits = false, + .name = "madvise", +}; + +static bool is_tmpfs(struct mem_ops *ops) +{ + return ops == &__file_ops && finfo.type == VMA_SHMEM; +} + static void alloc_at_fault(void) { struct settings settings = *current_settings(); @@ -686,6 +942,13 @@ static void collapse_max_ptes_none(struct collapse_context *c, struct mem_ops *o p = ops->setup_area(1); + if (is_tmpfs(ops)) { + /* shmem pages always in the page cache */ + printf("tmpfs..."); + skip("Skip"); + goto skip; + } + ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size); c->collapse("Maybe collapse with max_ptes_none exceeded", p, 1, ops, !c->enforce_pte_scan_limits); @@ -698,6 +961,7 @@ static void collapse_max_ptes_none(struct collapse_context *c, struct mem_ops *o validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size); } +skip: ops->cleanup_area(p, hpage_pmd_size); pop_settings(); } @@ -781,6 +1045,13 @@ static void collapse_single_pte_entry_compound(struct collapse_context *c, struc p = alloc_hpage(ops); + if (is_tmpfs(ops)) { + /* MADV_DONTNEED won't evict tmpfs pages */ + printf("tmpfs..."); + skip("Skip"); + goto skip; + } + madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE); printf("Split huge page leaving single PTE mapping compound page..."); madvise(p + page_size, hpage_pmd_size - page_size, MADV_DONTNEED); @@ -792,6 +1063,7 @@ static void collapse_single_pte_entry_compound(struct collapse_context *c, struc c->collapse("Collapse PTE table with single PTE mapping compound page", p, 1, ops, true); validate_memory(p, 0, page_size); +skip: ops->cleanup_area(p, hpage_pmd_size); } @@ -1038,9 +1310,70 @@ static void madvise_collapse_existing_thps(struct collapse_context *c, ops->cleanup_area(p, hpage_pmd_size); } +static void usage(void) +{ + fprintf(stderr, "\nUsage: ./khugepaged [dir]\n\n"); + fprintf(stderr, "\t\t: :\n"); + fprintf(stderr, "\t\t: [all|khugepaged|madvise]\n"); + fprintf(stderr, "\t\t: [all|anon|file]\n"); + fprintf(stderr, "\n\t\"file,all\" mem_type requires [dir] argument\n"); + fprintf(stderr, "\n\t\"file,all\" mem_type requires kernel built with\n"); + fprintf(stderr, "\tCONFIG_READ_ONLY_THP_FOR_FS=y\n"); + fprintf(stderr, "\n\tif [dir] is a (sub)directory of a tmpfs mount, tmpfs must be\n"); + fprintf(stderr, "\tmounted with huge=madvise option for khugepaged tests to work\n"); + exit(1); +} + +static void parse_test_type(int argc, const char **argv) +{ + char *buf; + const char *token; + + if (argc == 1) { + /* Backwards compatibility */ + khugepaged_context = &__khugepaged_context; + madvise_context = &__madvise_context; + anon_ops = &__anon_ops; + return; + } + + buf = strdup(argv[1]); + token = strsep(&buf, ":"); + + if (!strcmp(token, "all")) { + khugepaged_context = &__khugepaged_context; + madvise_context = &__madvise_context; + } else if (!strcmp(token, "khugepaged")) { + khugepaged_context = &__khugepaged_context; + } else if (!strcmp(token, "madvise")) { + madvise_context = &__madvise_context; + } else { + usage(); + } + + if (!buf) + usage(); + + if (!strcmp(buf, "all")) { + file_ops = &__file_ops; + anon_ops = &__anon_ops; + } else if (!strcmp(buf, "anon")) { + anon_ops = &__anon_ops; + } else if (!strcmp(buf, "file")) { + file_ops = &__file_ops; + } else { + usage(); + } + + if (!file_ops) + return; + + if (argc != 3) + usage(); +} + int main(int argc, const char **argv) { - struct collapse_context c; struct settings default_settings = { .thp_enabled = THP_MADVISE, .thp_defrag = THP_DEFRAG_ALWAYS, @@ -1051,8 +1384,20 @@ int main(int argc, const char **argv) .alloc_sleep_millisecs = 10, .scan_sleep_millisecs = 10, }, + /* + * When testing file-backed memory, the collapse path + * looks at how many pages are found in the page cache, not + * what pages are mapped. Disable read ahead optimization so + * pages don't find their way into the page cache unless + * we mem_ops->fault() them in. + */ + .read_ahead_kb = 0, }; - const char *tests = argc == 1 ? "all" : argv[1]; + + parse_test_type(argc, argv); + + if (file_ops) + get_finfo(argv[2]); setbuf(stdout, NULL); @@ -1070,43 +1415,61 @@ int main(int argc, const char **argv) alloc_at_fault(); - if (!strcmp(tests, "khugepaged") || !strcmp(tests, "all")) { - printf("\n*** Testing context: khugepaged ***\n"); - c.collapse = &khugepaged_collapse; - c.enforce_pte_scan_limits = true; - - collapse_full(&c, &anon_ops); - collapse_empty(&c, &anon_ops); - collapse_single_pte_entry(&c, &anon_ops); - collapse_max_ptes_none(&c, &anon_ops); - collapse_swapin_single_pte(&c, &anon_ops); - collapse_max_ptes_swap(&c, &anon_ops); - collapse_single_pte_entry_compound(&c, &anon_ops); - collapse_full_of_compound(&c, &anon_ops); - collapse_compound_extreme(&c, &anon_ops); - collapse_fork(&c, &anon_ops); - collapse_fork_compound(&c, &anon_ops); - collapse_max_ptes_shared(&c, &anon_ops); - } - if (!strcmp(tests, "madvise") || !strcmp(tests, "all")) { - printf("\n*** Testing context: madvise ***\n"); - c.collapse = &madvise_collapse; - c.enforce_pte_scan_limits = false; - - collapse_full(&c, &anon_ops); - collapse_empty(&c, &anon_ops); - collapse_single_pte_entry(&c, &anon_ops); - collapse_max_ptes_none(&c, &anon_ops); - collapse_swapin_single_pte(&c, &anon_ops); - collapse_max_ptes_swap(&c, &anon_ops); - collapse_single_pte_entry_compound(&c, &anon_ops); - collapse_full_of_compound(&c, &anon_ops); - collapse_compound_extreme(&c, &anon_ops); - collapse_fork(&c, &anon_ops); - collapse_fork_compound(&c, &anon_ops); - collapse_max_ptes_shared(&c, &anon_ops); - madvise_collapse_existing_thps(&c, &anon_ops); - } +#define TEST(t, c, o) do { \ + if (c && o) { \ + printf("\nRun test: " #t " (%s:%s)\n", c->name, o->name); \ + t(c, o); \ + } \ + } while (0) + + TEST(collapse_full, khugepaged_context, anon_ops); + TEST(collapse_full, khugepaged_context, file_ops); + TEST(collapse_full, madvise_context, anon_ops); + TEST(collapse_full, madvise_context, file_ops); + + TEST(collapse_empty, khugepaged_context, anon_ops); + TEST(collapse_empty, madvise_context, anon_ops); + + TEST(collapse_single_pte_entry, khugepaged_context, anon_ops); + TEST(collapse_single_pte_entry, khugepaged_context, file_ops); + TEST(collapse_single_pte_entry, madvise_context, anon_ops); + TEST(collapse_single_pte_entry, madvise_context, file_ops); + + TEST(collapse_max_ptes_none, khugepaged_context, anon_ops); + TEST(collapse_max_ptes_none, khugepaged_context, file_ops); + TEST(collapse_max_ptes_none, madvise_context, anon_ops); + TEST(collapse_max_ptes_none, madvise_context, file_ops); + + TEST(collapse_single_pte_entry_compound, khugepaged_context, anon_ops); + TEST(collapse_single_pte_entry_compound, khugepaged_context, file_ops); + TEST(collapse_single_pte_entry_compound, madvise_context, anon_ops); + TEST(collapse_single_pte_entry_compound, madvise_context, file_ops); + + TEST(collapse_full_of_compound, khugepaged_context, anon_ops); + TEST(collapse_full_of_compound, khugepaged_context, file_ops); + TEST(collapse_full_of_compound, madvise_context, anon_ops); + TEST(collapse_full_of_compound, madvise_context, file_ops); + + TEST(collapse_compound_extreme, khugepaged_context, anon_ops); + TEST(collapse_compound_extreme, madvise_context, anon_ops); + + TEST(collapse_swapin_single_pte, khugepaged_context, anon_ops); + TEST(collapse_swapin_single_pte, madvise_context, anon_ops); + + TEST(collapse_max_ptes_swap, khugepaged_context, anon_ops); + TEST(collapse_max_ptes_swap, madvise_context, anon_ops); + + TEST(collapse_fork, khugepaged_context, anon_ops); + TEST(collapse_fork, madvise_context, anon_ops); + + TEST(collapse_fork_compound, khugepaged_context, anon_ops); + TEST(collapse_fork_compound, madvise_context, anon_ops); + + TEST(collapse_max_ptes_shared, khugepaged_context, anon_ops); + TEST(collapse_max_ptes_shared, madvise_context, anon_ops); + + TEST(madvise_collapse_existing_thps, madvise_context, anon_ops); + TEST(madvise_collapse_existing_thps, madvise_context, file_ops); restore_settings(0); } -- cgit From d0d35b6010a8bcc12b986f51d29cf3a8635cdbb4 Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Thu, 22 Sep 2022 15:40:44 -0700 Subject: selftests/vm: add thp collapse shmem testing Add memory operations for shmem (memfd) memory, and reuse existing tests with the new memory operations. Shmem tests can be called with "shmem" mem_type, and shmem tests are ran with "all" mem_type as well. Link: https://lkml.kernel.org/r/20220907144521.3115321-9-zokeefe@google.com Link: https://lkml.kernel.org/r/20220922224046.1143204-9-zokeefe@google.com Signed-off-by: Zach O'Keefe Cc: Axel Rasmussen Cc: Chris Kennelly Cc: David Hildenbrand Cc: David Rientjes Cc: Hugh Dickins Cc: James Houghton Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Minchan Kim Cc: Pasha Tatashin Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Vlastimil Babka Cc: Yang Shi Signed-off-by: Andrew Morton --- tools/testing/selftests/vm/khugepaged.c | 57 +++++++++++++++++++++++++++++++-- 1 file changed, 55 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests/vm/khugepaged.c') diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index 08de6141c2af..eabbd2710096 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -59,6 +59,7 @@ struct mem_ops { static struct mem_ops *file_ops; static struct mem_ops *anon_ops; +static struct mem_ops *shmem_ops; struct collapse_context { void (*collapse)(const char *msg, char *p, int nr_hpages, @@ -739,6 +740,40 @@ static bool file_check_huge(void *addr, int nr_hpages) } } +static void *shmem_setup_area(int nr_hpages) +{ + void *p; + unsigned long size = nr_hpages * hpage_pmd_size; + + finfo.fd = memfd_create("khugepaged-selftest-collapse-shmem", 0); + if (finfo.fd < 0) { + perror("memfd_create()"); + exit(EXIT_FAILURE); + } + if (ftruncate(finfo.fd, size)) { + perror("ftruncate()"); + exit(EXIT_FAILURE); + } + p = mmap(BASE_ADDR, size, PROT_READ | PROT_WRITE, MAP_SHARED, finfo.fd, + 0); + if (p != BASE_ADDR) { + perror("mmap()"); + exit(EXIT_FAILURE); + } + return p; +} + +static void shmem_cleanup_area(void *p, unsigned long size) +{ + munmap(p, size); + close(finfo.fd); +} + +static bool shmem_check_huge(void *addr, int nr_hpages) +{ + return check_huge_shmem(addr, nr_hpages, hpage_pmd_size); +} + static struct mem_ops __anon_ops = { .setup_area = &anon_setup_area, .cleanup_area = &anon_cleanup_area, @@ -755,6 +790,14 @@ static struct mem_ops __file_ops = { .name = "file", }; +static struct mem_ops __shmem_ops = { + .setup_area = &shmem_setup_area, + .cleanup_area = &shmem_cleanup_area, + .fault = &anon_fault, + .check_huge = &shmem_check_huge, + .name = "shmem", +}; + static void __madvise_collapse(const char *msg, char *p, int nr_hpages, struct mem_ops *ops, bool expect) { @@ -1315,7 +1358,7 @@ static void usage(void) fprintf(stderr, "\nUsage: ./khugepaged [dir]\n\n"); fprintf(stderr, "\t\t: :\n"); fprintf(stderr, "\t\t: [all|khugepaged|madvise]\n"); - fprintf(stderr, "\t\t: [all|anon|file]\n"); + fprintf(stderr, "\t\t: [all|anon|file|shmem]\n"); fprintf(stderr, "\n\t\"file,all\" mem_type requires [dir] argument\n"); fprintf(stderr, "\n\t\"file,all\" mem_type requires kernel built with\n"); fprintf(stderr, "\tCONFIG_READ_ONLY_THP_FOR_FS=y\n"); @@ -1357,10 +1400,13 @@ static void parse_test_type(int argc, const char **argv) if (!strcmp(buf, "all")) { file_ops = &__file_ops; anon_ops = &__anon_ops; + shmem_ops = &__shmem_ops; } else if (!strcmp(buf, "anon")) { anon_ops = &__anon_ops; } else if (!strcmp(buf, "file")) { file_ops = &__file_ops; + } else if (!strcmp(buf, "shmem")) { + shmem_ops = &__shmem_ops; } else { usage(); } @@ -1377,7 +1423,7 @@ int main(int argc, const char **argv) struct settings default_settings = { .thp_enabled = THP_MADVISE, .thp_defrag = THP_DEFRAG_ALWAYS, - .shmem_enabled = SHMEM_NEVER, + .shmem_enabled = SHMEM_ADVISE, .use_zero_page = 0, .khugepaged = { .defrag = 1, @@ -1424,16 +1470,20 @@ int main(int argc, const char **argv) TEST(collapse_full, khugepaged_context, anon_ops); TEST(collapse_full, khugepaged_context, file_ops); + TEST(collapse_full, khugepaged_context, shmem_ops); TEST(collapse_full, madvise_context, anon_ops); TEST(collapse_full, madvise_context, file_ops); + TEST(collapse_full, madvise_context, shmem_ops); TEST(collapse_empty, khugepaged_context, anon_ops); TEST(collapse_empty, madvise_context, anon_ops); TEST(collapse_single_pte_entry, khugepaged_context, anon_ops); TEST(collapse_single_pte_entry, khugepaged_context, file_ops); + TEST(collapse_single_pte_entry, khugepaged_context, shmem_ops); TEST(collapse_single_pte_entry, madvise_context, anon_ops); TEST(collapse_single_pte_entry, madvise_context, file_ops); + TEST(collapse_single_pte_entry, madvise_context, shmem_ops); TEST(collapse_max_ptes_none, khugepaged_context, anon_ops); TEST(collapse_max_ptes_none, khugepaged_context, file_ops); @@ -1447,8 +1497,10 @@ int main(int argc, const char **argv) TEST(collapse_full_of_compound, khugepaged_context, anon_ops); TEST(collapse_full_of_compound, khugepaged_context, file_ops); + TEST(collapse_full_of_compound, khugepaged_context, shmem_ops); TEST(collapse_full_of_compound, madvise_context, anon_ops); TEST(collapse_full_of_compound, madvise_context, file_ops); + TEST(collapse_full_of_compound, madvise_context, shmem_ops); TEST(collapse_compound_extreme, khugepaged_context, anon_ops); TEST(collapse_compound_extreme, madvise_context, anon_ops); @@ -1470,6 +1522,7 @@ int main(int argc, const char **argv) TEST(madvise_collapse_existing_thps, madvise_context, anon_ops); TEST(madvise_collapse_existing_thps, madvise_context, file_ops); + TEST(madvise_collapse_existing_thps, madvise_context, shmem_ops); restore_settings(0); } -- cgit From 69d9428ce97f28eb1ba8acee552cf46014663d2b Mon Sep 17 00:00:00 2001 From: Zach O'Keefe Date: Thu, 22 Sep 2022 15:40:45 -0700 Subject: selftests/vm: add file/shmem MADV_COLLAPSE selftest for cleared pmd This test tests that MADV_COLLAPSE acting on file/shmem memory for which (1) the file extent mapping by the memory is already a huge page in the page cache, and (2) the pmd mapping this memory in the target process is none. In practice, (1)+(2) is the state left over after khugepaged has successfully collapsed file/shmem memory for a target VMA, but the memory has not yet been refaulted. So, this test in-effect tests MADV_COLLAPSE racing with khugepaged to collapse the memory first. Link: https://lkml.kernel.org/r/20220907144521.3115321-10-zokeefe@google.com Link: https://lkml.kernel.org/r/20220922224046.1143204-10-zokeefe@google.com Signed-off-by: Zach O'Keefe Cc: Axel Rasmussen Cc: Chris Kennelly Cc: David Hildenbrand Cc: David Rientjes Cc: Hugh Dickins Cc: James Houghton Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Minchan Kim Cc: Pasha Tatashin Cc: Peter Xu Cc: Rongwei Wang Cc: SeongJae Park Cc: Song Liu Cc: Vlastimil Babka Cc: Yang Shi Signed-off-by: Andrew Morton --- tools/testing/selftests/vm/khugepaged.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'tools/testing/selftests/vm/khugepaged.c') diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index eabbd2710096..64126c8cd561 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -1353,6 +1353,33 @@ static void madvise_collapse_existing_thps(struct collapse_context *c, ops->cleanup_area(p, hpage_pmd_size); } +/* + * Test race with khugepaged where page tables have been retracted and + * pmd cleared. + */ +static void madvise_retracted_page_tables(struct collapse_context *c, + struct mem_ops *ops) +{ + void *p; + int nr_hpages = 1; + unsigned long size = nr_hpages * hpage_pmd_size; + + p = ops->setup_area(nr_hpages); + ops->fault(p, 0, size); + + /* Let khugepaged collapse and leave pmd cleared */ + if (wait_for_scan("Collapse and leave PMD cleared", p, nr_hpages, + ops)) { + fail("Timeout"); + return; + } + success("OK"); + c->collapse("Install huge PMD from page cache", p, nr_hpages, ops, + true); + validate_memory(p, 0, size); + ops->cleanup_area(p, size); +} + static void usage(void) { fprintf(stderr, "\nUsage: ./khugepaged [dir]\n\n"); @@ -1524,5 +1551,8 @@ int main(int argc, const char **argv) TEST(madvise_collapse_existing_thps, madvise_context, file_ops); TEST(madvise_collapse_existing_thps, madvise_context, shmem_ops); + TEST(madvise_retracted_page_tables, madvise_context, file_ops); + TEST(madvise_retracted_page_tables, madvise_context, shmem_ops); + restore_settings(0); } -- cgit