linux-kernel - [PATCH 0/1] prctl: allow overriding system THP policy to always

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250507141132.2773275-1-usamaarif642@gmail.com>
Date: Wed,  7 May 2025 15:00:33 +0100
From: Usama Arif <usamaarif642@...il.com>
To: Andrew Morton <akpm@...ux-foundation.org>,
	david@...hat.com,
	linux-mm@...ck.org
Cc: hannes@...xchg.org,
	shakeel.butt@...ux.dev,
	riel@...riel.com,
	ziy@...dia.com,
	baolin.wang@...ux.alibaba.com,
	lorenzo.stoakes@...cle.com,
	Liam.Howlett@...cle.com,
	npache@...hat.com,
	ryan.roberts@....com,
	linux-kernel@...r.kernel.org,
	kernel-team@...a.com,
	Usama Arif <usamaarif642@...il.com>
Subject: [PATCH 0/1] prctl: allow overriding system THP policy to always

Allowing override of global THP policy per process allows workloads
that have shown to benefit from hugepages to do so, without regressing
workloads that wouldn't benefit. This will allow such types of
workloads to be run/stacked on the same machine.

It also helps in rolling out hugepages in hyperscaler configurations
for workloads that benefit from them, where a single THP policy is
likely to be used across the entire fleet, and prctl will help override it.

An advantage of doing it via prctl vs creating a cgroup specific
option (like /sys/fs/cgroup/test/memory.transparent_hugepage.enabled) is
that this will work even when there are no cgroups present, and my
understanding is there is a strong preference of cgroups controls being
hierarchical which usually means them having a numerical value.

The output and code of test program is below:

[root@vm4 vmuser]# echo madvise > /sys/kernel/mm/transparent_hugepage/enabled
[root@vm4 vmuser]# echo inherit > /sys/kernel/mm/transparent_hugepage/hugepages-2048kB/enabled
[root@vm4 vmuser]# ./a.out
Default THP setting:
THP is not set to 'always'.
PR_SET_THP_ALWAYS = 1
THP is set to 'always'.
PR_SET_THP_ALWAYS = 0
THP is not set to 'always'.

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/mman.h>
#include <sys/prctl.h>

#define PR_SET_THP_ALWAYS 78
#define SIZE 12 * (2 * 1024 * 1024) // 24 MB

void check_smaps(void) {
    FILE *file = fopen("/proc/self/smaps", "r");
    if (!file) {
        perror("fopen");
        return;
    }

    char line[256];
    int is_hugepage = 0;
    while (fgets(line, sizeof(line), file)) {
        // if (strstr(line, "AnonHugePages:"))
        //     printf("%s\n", line);
        if (strstr(line, "AnonHugePages:") && strstr(line, "24576 kB"))
{
            // printf("%s\n", line);
            is_hugepage = 1;
            break;
        }
    }
    fclose(file);
    if (is_hugepage) {
        printf("THP is set to 'always'.\n");
    } else {
        printf("THP is not set to 'always'.\n");
    }
}

void test_mmap_thp(void) {
    char *buffer = (char *)mmap(NULL, SIZE, PROT_READ | PROT_WRITE,
                                MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
    if (buffer == MAP_FAILED) {
        perror("mmap");
        return;
    }
    // Touch the memory to ensure it's allocated
    memset(buffer, 0, SIZE);
    check_smaps();
    munmap(buffer, SIZE);
}

int main() {
    printf("Default THP setting: \n");
    test_mmap_thp();
    printf("PR_SET_THP_ALWAYS = 1 \n");
    prctl(PR_SET_THP_ALWAYS, 1, NULL, NULL, NULL);
    test_mmap_thp();
    printf("PR_SET_THP_ALWAYS = 0 \n");
    prctl(PR_SET_THP_ALWAYS, 0, NULL, NULL, NULL);
    test_mmap_thp();

    return 0;
}

Usama Arif (1):
  prctl: allow overriding system THP policy to always per process

 include/linux/huge_mm.h                          |  3 ++-
 include/linux/mm_types.h                         |  7 ++-----
 include/uapi/linux/prctl.h                       |  3 +++
 kernel/sys.c                                     | 16 ++++++++++++++++
 tools/include/uapi/linux/prctl.h                 |  3 +++
 .../perf/trace/beauty/include/uapi/linux/prctl.h |  3 +++
 6 files changed, 29 insertions(+), 6 deletions(-)

-- 
2.47.1