linux-kernel - [PATCH v3 3/7] prctl: introduce PR_DEFAULT_MADV

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

Message-ID: <20250519223307.3601786-4-usamaarif642@gmail.com>
Date: Mon, 19 May 2025 23:29:55 +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,
	laoar.shao@...il.com,
	baolin.wang@...ux.alibaba.com,
	lorenzo.stoakes@...cle.com,
	Liam.Howlett@...cle.com,
	npache@...hat.com,
	ryan.roberts@....com,
	vbabka@...e.cz,
	jannh@...gle.com,
	Arnd Bergmann <arnd@...db.de>,
	linux-kernel@...r.kernel.org,
	linux-doc@...r.kernel.org,
	kernel-team@...a.com,
	Usama Arif <usamaarif642@...il.com>
Subject: [PATCH v3 3/7] prctl: introduce PR_DEFAULT_MADV_NOHUGEPAGE for the process

This is set via the new PR_SET_THP_POLICY prctl. It has 2 affects:
- It sets VM_NOHUGEPAGE and clears VM_HUGEPAGE on the default VMA
  flags (def_flags). This means that every new VMA will not be
  considered for hugepage by default.
- Iterate through every VMA in the process and call hugepage_madvise
  on it, with MADV_NOHUGEPAGE policy.
The policy is inherited during fork+exec.

This effectively allows setting MADV_NOHUGEPAGE on the entire process.
In anenvironment where different types of workloads are stacked on the
same machine,this will allow workloads that benefit from having
hugepages on an madvise basis only to do so, without regressing those
that benefit from having hugepages always.

Signed-off-by: Usama Arif <usamaarif642@...il.com>
---
 include/uapi/linux/prctl.h                         | 1 +
 kernel/sys.c                                       | 7 +++++++
 tools/include/uapi/linux/prctl.h                   | 1 +
 tools/perf/trace/beauty/include/uapi/linux/prctl.h | 1 +
 4 files changed, 10 insertions(+)

diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 15aaa4db5ff8..33a6ef6a5a72 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -367,5 +367,6 @@ struct prctl_mm_map {
 #define PR_SET_THP_POLICY		78
 #define PR_GET_THP_POLICY		79
 #define PR_DEFAULT_MADV_HUGEPAGE	0
+#define PR_DEFAULT_MADV_NOHUGEPAGE	1
 
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index 74397ace62f3..6bb28b3666f7 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2666,6 +2666,8 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			return -EINTR;
 		if (mm->def_flags & VM_HUGEPAGE)
 			error = PR_DEFAULT_MADV_HUGEPAGE;
+		else if (mm->def_flags & VM_NOHUGEPAGE)
+			error = PR_DEFAULT_MADV_NOHUGEPAGE;
 		mmap_write_unlock(mm);
 		break;
 	case PR_SET_THP_POLICY:
@@ -2681,6 +2683,11 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			if (!error)
 				process_default_madv_hugepage(mm, MADV_HUGEPAGE);
 			break;
+		case PR_DEFAULT_MADV_NOHUGEPAGE:
+			error = hugepage_set_vmflags(&mm->def_flags, MADV_NOHUGEPAGE);
+			if (!error)
+				process_default_madv_hugepage(mm, MADV_NOHUGEPAGE);
+			break;
 		default:
 			error = -EINVAL;
 			break;
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index f5945ebfe3f2..e03d0ed890c5 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -331,5 +331,6 @@ struct prctl_mm_map {
 #define PR_SET_THP_POLICY		78
 #define PR_GET_THP_POLICY		79
 #define PR_THP_POLICY_DEFAULT_HUGE	0
+#define PR_THP_POLICY_DEFAULT_NOHUGE	1
 
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 325c72f40a93..d25458f4db9e 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -367,5 +367,6 @@ struct prctl_mm_map {
 #define PR_SET_THP_POLICY		78
 #define PR_GET_THP_POLICY		79
 #define PR_THP_POLICY_DEFAULT_HUGE	0
+#define PR_THP_POLICY_DEFAULT_NOHUGE	1
 
 #endif /* _LINUX_PRCTL_H */
-- 
2.47.1