Commit c64beef7 authored by Kefeng Wang's avatar Kefeng Wang
Browse files

mm: filemap: make mTHP configurable for exec mapping 

hulk inclusion
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I9Q9DF


CVE: NA

-------------------------------------------------

Let's only enable large folio order for exec mapping with large folio support,
also add a new sysfs interface to make it configurable.

Signed-off-by: default avatarKefeng Wang <wangkefeng.wang@huawei.com>
parent 9c1fb418

Documentation/admin-guide/mm/transhuge.rst

+5 −3
Original line number Diff line number Diff line
@@ -203,11 +203,13 @@ PMD-mappable transparent hugepage:: 
	cat /sys/kernel/mm/transparent_hugepage/hpage_pmd_size



The kernel tries to use huge, PMD-mappable page on read page fault for

file exec mapping if CONFIG_READ_ONLY_THP_FOR_FS enabled. It's possible

to enabled the feature by writing 1 or disablt by writing 0::

if CONFIG_READ_ONLY_THP_FOR_FS enabled, or try non-PMD size page(eg,

64K arm64) for file exec mapping, BIT0 for PMD THP, BIT1 for mTHP. It's

possible to enable/disable it by configurate the corresponding bit::



	echo 0x0 >/sys/kernel/mm/transparent_hugepage/thp_exec_enabled

	echo 0x1 >/sys/kernel/mm/transparent_hugepage/thp_exec_enabled

	echo 0x2 >/sys/kernel/mm/transparent_hugepage/thp_exec_enabled

	echo 0x3 >/sys/kernel/mm/transparent_hugepage/thp_exec_enabled



khugepaged will be automatically started when one or more hugepage

sizes are enabled (either by directly setting "always" or "madvise",

include/linux/huge_mm.h

+1 −0
Original line number Diff line number Diff line
@@ -51,6 +51,7 @@ enum transparent_hugepage_flag { 
	TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG,

	TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG,

	TRANSPARENT_HUGEPAGE_FILE_EXEC_THP_FLAG,

	TRANSPARENT_HUGEPAGE_FILE_EXEC_MTHP_FLAG,

};



struct kobject;

mm/filemap.c

+25 −2
Original line number Diff line number Diff line
@@ -46,6 +46,7 @@ 
#include <linux/pipe_fs_i.h>

#include <linux/splice.h>

#include <linux/huge_mm.h>

#include <linux/pgtable.h>

#include <asm/pgalloc.h>

#include <asm/tlbflush.h>

#include "internal.h"
@@ -3141,6 +3142,10 @@ static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio, 
	(transparent_hugepage_flags &			\

	 (1<<TRANSPARENT_HUGEPAGE_FILE_EXEC_THP_FLAG))



#define file_exec_mthp_enabled()			\

	(transparent_hugepage_flags &			\

	 (1<<TRANSPARENT_HUGEPAGE_FILE_EXEC_MTHP_FLAG))



static inline void try_enable_file_exec_thp(struct vm_area_struct *vma,

					    unsigned long *vm_flags,

					    struct file *file)
@@ -3157,6 +3162,24 @@ static inline void try_enable_file_exec_thp(struct vm_area_struct *vma, 
	if (file_exec_thp_enabled())

		hugepage_madvise(vma, vm_flags, MADV_HUGEPAGE);

}



static inline bool file_exec_can_enable_mthp(struct address_space *mapping,

					     unsigned long vm_flags)

{

#ifndef arch_wants_exec_folio_order

	return false;

#endif

	if (!is_exec_mapping(vm_flags))

		return false;



	if (!mapping_large_folio_support(mapping))

		return false;



	if (!file_exec_mthp_enabled())

		return false;



	return true;

}

#endif



/*
@@ -3195,7 +3218,6 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) 
		page_cache_ra_order(&ractl, ra, HPAGE_PMD_ORDER);

		return fpin;

	}

#endif



	/*

	 * Allow arch to request a preferred minimum folio order for executable
@@ -3203,7 +3225,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) 
	 * can contpte-map the folio. Executable memory rarely benefits from

	 * read-ahead anyway, due to its random access nature.

	 */

	if (vm_flags & VM_EXEC) {

	if (file_exec_can_enable_mthp(mapping, vm_flags)) {

		int order = arch_wants_exec_folio_order();



		if (order >= 0) {
@@ -3215,6 +3237,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) 
			return fpin;

		}

	}

#endif



	/* If we don't want any read-ahead, don't bother */

	if (vm_flags & VM_RAND_READ)

mm/huge_memory.c

+48 −14
Original line number Diff line number Diff line
@@ -426,31 +426,67 @@ static struct kobj_attribute hpage_pmd_size_attr = 
	__ATTR_RO(hpage_pmd_size);



#ifdef CONFIG_READ_ONLY_THP_FOR_FS

#define FILE_EXEC_THP_ENABLE	BIT(0)

#else

#define FILE_EXEC_THP_ENABLE	0

#endif



#define FILE_EXEC_MTHP_ENABLE	BIT(1)

#define FILE_EXEC_THP_ALL	(FILE_EXEC_THP_ENABLE | FILE_EXEC_MTHP_ENABLE)



static void thp_exec_enabled_set(enum transparent_hugepage_flag flag,

				 bool enable)

{

	if (enable)

		set_bit(flag, &transparent_hugepage_flags);

	else

		clear_bit(flag, &transparent_hugepage_flags);

}



static ssize_t thp_exec_enabled_show(struct kobject *kobj,

				     struct kobj_attribute *attr, char *buf)

{

	return single_hugepage_flag_show(kobj, attr, buf,

				 TRANSPARENT_HUGEPAGE_FILE_EXEC_THP_FLAG);

	unsigned long val = 0;



#ifdef CONFIG_READ_ONLY_THP_FOR_FS

	if (test_bit(TRANSPARENT_HUGEPAGE_FILE_EXEC_THP_FLAG,

		     &transparent_hugepage_flags))

		val |= FILE_EXEC_THP_ENABLE;

#endif



	if (test_bit(TRANSPARENT_HUGEPAGE_FILE_EXEC_MTHP_FLAG,

		     &transparent_hugepage_flags))

		val |= FILE_EXEC_MTHP_ENABLE;



	return sysfs_emit(buf, "0x%lx\n", val);

}

static ssize_t thp_exec_enabled_store(struct kobject *kobj,

		struct kobj_attribute *attr, const char *buf, size_t count)

{

	size_t ret = single_hugepage_flag_store(kobj, attr, buf, count,

				 TRANSPARENT_HUGEPAGE_FILE_EXEC_THP_FLAG);

	if (ret > 0) {

		int err = start_stop_khugepaged();

	unsigned long val;

	int ret;



		if (err)

			ret = err;

	}

	ret = kstrtoul(buf, 16, &val);

	if (ret < 0)

		return ret;

	if (val & ~FILE_EXEC_THP_ALL)

		return -EINVAL;



#ifdef CONFIG_READ_ONLY_THP_FOR_FS

	thp_exec_enabled_set(TRANSPARENT_HUGEPAGE_FILE_EXEC_THP_FLAG,

			     val & FILE_EXEC_THP_ENABLE);

	ret = start_stop_khugepaged();

	if (ret)

		return ret;

#endif

	thp_exec_enabled_set(TRANSPARENT_HUGEPAGE_FILE_EXEC_MTHP_FLAG,

			     val & FILE_EXEC_MTHP_ENABLE);



	return count;

}

static struct kobj_attribute thp_exec_enabled_attr =

	__ATTR_RW(thp_exec_enabled);



#endif



static struct attribute *hugepage_attr[] = {

	&enabled_attr.attr,

	&defrag_attr.attr,
@@ -459,9 +495,7 @@ static struct attribute *hugepage_attr[] = { 
#ifdef CONFIG_SHMEM

	&shmem_enabled_attr.attr,

#endif

#ifdef CONFIG_READ_ONLY_THP_FOR_FS

	&thp_exec_enabled_attr.attr,

#endif

	NULL,

};