Commit 681f45de authored by Usama Arif's avatar Usama Arif Committed by Andrew Morton
Browse files

selftests: prctl: introduce tests for disabling THPs completely 

The test will set the global system THP setting to never, madvise or
always depending on the fixture variant and the 2M setting to inherit
before it starts (and reset to original at teardown).  The fixture setup
will also test if PR_SET_THP_DISABLE prctl call can be made to disable all
THPs and skip if it fails.

This tests if the process can:
- successfully get the policy to disable THPs completely.
- never get a hugepage when the THPs are completely disabled
  with the prctl, including with MADV_HUGE and MADV_COLLAPSE.
- successfully reset the policy of the process.
- after reset, only get hugepages with:
  - MADV_COLLAPSE when policy is set to never.
  - MADV_HUGE and MADV_COLLAPSE when policy is set to madvise.
  - always when policy is set to "always".
- never get a THP with MADV_NOHUGEPAGE.
- repeat the above tests in a forked process to make sure
  the policy is carried across forks.

[usamaarif642@gmail.com: return after executing test in child process]
  Link: https://lkml.kernel.org/r/2d0ea708-ecba-4021-b6ca-e93f1413d60a@gmail.com
[usamaarif642@gmail.com: include linux/mman.h for prctl_thp_disable]
  Link: https://lkml.kernel.org/r/20250910204609.1720498-1-usamaarif642@gmail.com
  Link: https://lore.kernel.org/all/c8249725-e91d-4c51-b9bb-40305e61e20d@sirena.org.uk/
Link: https://lkml.kernel.org/r/20250815135549.130506-7-usamaarif642@gmail.com


Signed-off-by: default avatarUsama Arif <usamaarif642@gmail.com>
Acked-by: default avatarDavid Hildenbrand <david@redhat.com>
Reviewed-by: default avatarLorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Jann Horn <jannh@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mariano Pache <npache@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yafang <laoar.shao@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 49850bd0

tools/testing/selftests/mm/.gitignore

+1 −0
Original line number Diff line number Diff line
@@ -58,3 +58,4 @@ pkey_sighandler_tests_32 
pkey_sighandler_tests_64

guard-regions

merge

prctl_thp_disable

tools/testing/selftests/mm/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -86,6 +86,7 @@ TEST_GEN_FILES += on-fault-limit 
TEST_GEN_FILES += pagemap_ioctl

TEST_GEN_FILES += pfnmap

TEST_GEN_FILES += process_madv

TEST_GEN_FILES += prctl_thp_disable

TEST_GEN_FILES += thuge-gen

TEST_GEN_FILES += transhuge-stress

TEST_GEN_FILES += uffd-stress

tools/testing/selftests/mm/prctl_thp_disable.c

0 → 100644
+178 −0
Original line number Diff line number Diff line 
// SPDX-License-Identifier: GPL-2.0

/*

 * Basic tests for PR_GET/SET_THP_DISABLE prctl calls

 *

 * Author(s): Usama Arif <usamaarif642@gmail.com>

 */

#include <stdio.h>

#include <stdlib.h>

#include <string.h>

#include <unistd.h>

#include <sys/mman.h>

#include <linux/mman.h>

#include <sys/prctl.h>

#include <sys/wait.h>



#include "../kselftest_harness.h"

#include "thp_settings.h"

#include "vm_util.h"



enum thp_collapse_type {

	THP_COLLAPSE_NONE,

	THP_COLLAPSE_MADV_NOHUGEPAGE,

	THP_COLLAPSE_MADV_HUGEPAGE,	/* MADV_HUGEPAGE before access */

	THP_COLLAPSE_MADV_COLLAPSE,	/* MADV_COLLAPSE after access */

};



/*

 * Function to mmap a buffer, fault it in, madvise it appropriately (before

 * page fault for MADV_HUGE, and after for MADV_COLLAPSE), and check if the

 * mmap region is huge.

 * Returns:

 * 0 if test doesn't give hugepage

 * 1 if test gives a hugepage

 * -errno if mmap fails

 */

static int test_mmap_thp(enum thp_collapse_type madvise_buf, size_t pmdsize)

{

	char *mem, *mmap_mem;

	size_t mmap_size;

	int ret;



	/* For alignment purposes, we need twice the THP size. */

	mmap_size = 2 * pmdsize;

	mmap_mem = (char *)mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,

				    MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);

	if (mmap_mem == MAP_FAILED)

		return -errno;



	/* We need a THP-aligned memory area. */

	mem = (char *)(((uintptr_t)mmap_mem + pmdsize) & ~(pmdsize - 1));



	if (madvise_buf == THP_COLLAPSE_MADV_HUGEPAGE)

		madvise(mem, pmdsize, MADV_HUGEPAGE);

	else if (madvise_buf == THP_COLLAPSE_MADV_NOHUGEPAGE)

		madvise(mem, pmdsize, MADV_NOHUGEPAGE);



	/* Ensure memory is allocated */

	memset(mem, 1, pmdsize);



	if (madvise_buf == THP_COLLAPSE_MADV_COLLAPSE)

		madvise(mem, pmdsize, MADV_COLLAPSE);



	/* HACK: make sure we have a separate VMA that we can check reliably. */

	mprotect(mem, pmdsize, PROT_READ);



	ret = check_huge_anon(mem, 1, pmdsize);

	munmap(mmap_mem, mmap_size);

	return ret;

}



static void prctl_thp_disable_completely_test(struct __test_metadata *const _metadata,

					      size_t pmdsize,

					      enum thp_enabled thp_policy)

{

	ASSERT_EQ(prctl(PR_GET_THP_DISABLE, NULL, NULL, NULL, NULL), 1);



	/* tests after prctl overrides global policy */

	ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize), 0);



	ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0);



	ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize), 0);



	ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 0);



	/* Reset to global policy */

	ASSERT_EQ(prctl(PR_SET_THP_DISABLE, 0, NULL, NULL, NULL), 0);



	/* tests after prctl is cleared, and only global policy is effective */

	ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize),

		  thp_policy == THP_ALWAYS ? 1 : 0);



	ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0);



	ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize),

		  thp_policy == THP_NEVER ? 0 : 1);



	ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 1);

}



FIXTURE(prctl_thp_disable_completely)

{

	struct thp_settings settings;

	size_t pmdsize;

};



FIXTURE_VARIANT(prctl_thp_disable_completely)

{

	enum thp_enabled thp_policy;

};



FIXTURE_VARIANT_ADD(prctl_thp_disable_completely, never)

{

	.thp_policy = THP_NEVER,

};



FIXTURE_VARIANT_ADD(prctl_thp_disable_completely, madvise)

{

	.thp_policy = THP_MADVISE,

};



FIXTURE_VARIANT_ADD(prctl_thp_disable_completely, always)

{

	.thp_policy = THP_ALWAYS,

};



FIXTURE_SETUP(prctl_thp_disable_completely)

{

	if (!thp_available())

		SKIP(return, "Transparent Hugepages not available\n");



	self->pmdsize = read_pmd_pagesize();

	if (!self->pmdsize)

		SKIP(return, "Unable to read PMD size\n");



	if (prctl(PR_SET_THP_DISABLE, 1, NULL, NULL, NULL))

		SKIP(return, "Unable to disable THPs completely for the process\n");



	thp_save_settings();

	thp_read_settings(&self->settings);

	self->settings.thp_enabled = variant->thp_policy;

	self->settings.hugepages[sz2ord(self->pmdsize, getpagesize())].enabled = THP_INHERIT;

	thp_write_settings(&self->settings);

}



FIXTURE_TEARDOWN(prctl_thp_disable_completely)

{

	thp_restore_settings();

}



TEST_F(prctl_thp_disable_completely, nofork)

{

	prctl_thp_disable_completely_test(_metadata, self->pmdsize, variant->thp_policy);

}



TEST_F(prctl_thp_disable_completely, fork)

{

	int ret = 0;

	pid_t pid;



	/* Make sure prctl changes are carried across fork */

	pid = fork();

	ASSERT_GE(pid, 0);



	if (!pid) {

		prctl_thp_disable_completely_test(_metadata, self->pmdsize, variant->thp_policy);

		return;

	}



	wait(&ret);

	if (WIFEXITED(ret))

		ret = WEXITSTATUS(ret);

	else

		ret = -EINVAL;

	ASSERT_EQ(ret, 0);

}



TEST_HARNESS_MAIN

tools/testing/selftests/mm/thp_settings.c

+8 −1
Original line number Diff line number Diff line
@@ -382,10 +382,17 @@ unsigned long thp_shmem_supported_orders(void) 
	return __thp_supported_orders(true);

}



bool thp_is_enabled(void)

bool thp_available(void)

{

	if (access(THP_SYSFS, F_OK) != 0)

		return false;

	return true;

}



bool thp_is_enabled(void)

{

	if (!thp_available())

		return false;



	int mode = thp_read_string("enabled", thp_enabled_strings);

tools/testing/selftests/mm/thp_settings.h

+1 −0
Original line number Diff line number Diff line
@@ -84,6 +84,7 @@ void thp_set_read_ahead_path(char *path); 
unsigned long thp_supported_orders(void);

unsigned long thp_shmem_supported_orders(void);



bool thp_available(void);

bool thp_is_enabled(void);



#endif /* __THP_SETTINGS_H__ */