| 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
| ||
|
Message-ID: <20250624055617.1291159-14-raghavendra.kt@amd.com>
Date: Tue, 24 Jun 2025 05:56:17 +0000
From: Raghavendra K T <raghavendra.kt@....com>
To: <raghavendra.kt@....com>
CC: <AneeshKumar.KizhakeVeetil@....com>, <Hasan.Maruf@....com>,
<Michael.Day@....com>, <akpm@...ux-foundation.org>, <bharata@....com>,
<dave.hansen@...el.com>, <david@...hat.com>, <dongjoo.linux.dev@...il.com>,
<feng.tang@...el.com>, <gourry@...rry.net>, <hannes@...xchg.org>,
<honggyu.kim@...com>, <hughd@...gle.com>, <jhubbard@...dia.com>,
<jon.grimm@....com>, <k.shutemov@...il.com>, <kbusch@...a.com>,
<kmanaouil.dev@...il.com>, <leesuyeon0506@...il.com>, <leillc@...gle.com>,
<liam.howlett@...cle.com>, <linux-kernel@...r.kernel.org>,
<linux-mm@...ck.org>, <mgorman@...hsingularity.net>, <mingo@...hat.com>,
<nadav.amit@...il.com>, <nphamcs@...il.com>, <peterz@...radead.org>,
<riel@...riel.com>, <rientjes@...gle.com>, <rppt@...nel.org>,
<santosh.shukla@....com>, <shivankg@....com>, <shy828301@...il.com>,
<sj@...nel.org>, <vbabka@...e.cz>, <weixugc@...gle.com>,
<willy@...radead.org>, <ying.huang@...ux.alibaba.com>, <ziy@...dia.com>,
<Jonathan.Cameron@...wei.com>, <dave@...olabs.net>, <yuanchu@...gle.com>,
<kinseyho@...gle.com>, <hdanton@...a.com>
Subject: [RFC PATCH V2 13/13] prctl: Introduce new prctl to control scanning
A new scalar value (PTEAScanScale) to control per task PTE A bit scanning
is introduced.
0 : scanning disabled
1-10 : scanning enabled.
In future PTEAScanScale could be used to control aggressiveness of
scanning.
CC: linux-doc@...r.kernel.org
CC: Jonathan Corbet <corbet@....net>
CC: linux-fsdevel@...r.kernel.org
Suggested-by: David Rientjes <rientjes@...gle.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@....com>
---
Documentation/filesystems/proc.rst | 2 ++
fs/proc/task_mmu.c | 4 ++++
include/linux/mm_types.h | 3 +++
include/uapi/linux/prctl.h | 7 +++++++
kernel/fork.c | 4 ++++
kernel/sys.c | 25 +++++++++++++++++++++++++
mm/kscand.c | 5 +++++
7 files changed, 50 insertions(+)
Rebasing to upstream tree will change prctl number.
diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index 2a17865dfe39..429409c341ac 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -205,6 +205,7 @@ read the file /proc/PID/status::
VmLib: 1412 kB
VmPTE: 20 kb
VmSwap: 0 kB
+ PTEAScanScale: 0
HugetlbPages: 0 kB
CoreDumping: 0
THP_enabled: 1
@@ -288,6 +289,7 @@ It's slow but very precise.
VmPTE size of page table entries
VmSwap amount of swap used by anonymous private data
(shmem swap usage is not included)
+ PTEAScanScale Integer representing async PTE A bit scan agrression
HugetlbPages size of hugetlb memory portions
CoreDumping process's memory is currently being dumped
(killing the process may lead to a corrupted core)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 994cde10e3f4..6a1a660d9824 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -79,6 +79,10 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
" kB\nVmPTE:\t", mm_pgtables_bytes(mm) >> 10, 8);
SEQ_PUT_DEC(" kB\nVmSwap:\t", swap);
seq_puts(m, " kB\n");
+#ifdef CONFIG_KSCAND
+ seq_put_decimal_ull_width(m, "PTEAScanScale:\t", mm->pte_scan_scale, 8);
+ seq_puts(m, "\n");
+#endif
hugetlb_report_usage(m, mm);
}
#undef SEQ_PUT_DEC
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 571be1ad12ab..ffdb9207cc4f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1112,6 +1112,9 @@ struct mm_struct {
#ifdef CONFIG_KSCAND
/* Tracks promotion node. XXX: use nodemask */
int target_node;
+
+ /* Integer representing PTE A bit scan aggression (0-10) */
+ unsigned int pte_scan_scale;
#endif
/*
* An operation with batched TLB flushing is going on. Anything
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 15c18ef4eb11..2f64a80e5cdf 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -364,4 +364,11 @@ struct prctl_mm_map {
# define PR_TIMER_CREATE_RESTORE_IDS_ON 1
# define PR_TIMER_CREATE_RESTORE_IDS_GET 2
+/* Set/get PTE A bit scan scale */
+#define PR_SET_PTE_A_SCAN_SCALE 78
+#define PR_GET_PTE_A_SCAN_SCALE 79
+# define PR_PTE_A_SCAN_SCALE_MIN 0
+# define PR_PTE_A_SCAN_SCALE_MAX 10
+# define PR_PTE_A_SCAN_SCALE_DEFAULT 1
+
#endif /* _LINUX_PRCTL_H */
diff --git a/kernel/fork.c b/kernel/fork.c
index af6dd315b106..120ee2ba7d30 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -106,6 +106,7 @@
#include <uapi/linux/pidfd.h>
#include <linux/pidfs.h>
#include <linux/tick.h>
+#include <linux/prctl.h>
#include <asm/pgalloc.h>
#include <linux/uaccess.h>
@@ -1311,6 +1312,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
init_tlb_flush_pending(mm);
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS)
mm->pmd_huge_pte = NULL;
+#endif
+#ifdef CONFIG_KSCAND
+ mm->pte_scan_scale = PR_PTE_A_SCAN_SCALE_DEFAULT;
#endif
mm_init_uprobes_state(mm);
hugetlb_count_init(mm);
diff --git a/kernel/sys.c b/kernel/sys.c
index c434968e9f5d..aff92ff2c7dd 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2146,6 +2146,19 @@ static int prctl_set_auxv(struct mm_struct *mm, unsigned long addr,
return 0;
}
+#ifdef CONFIG_KSCAND
+static int prctl_pte_scan_scale_write(unsigned int scale)
+{
+ scale = clamp(scale, PR_PTE_A_SCAN_SCALE_MIN, PR_PTE_A_SCAN_SCALE_MAX);
+ current->mm->pte_scan_scale = scale;
+ return 0;
+}
+
+static unsigned int prctl_pte_scan_scale_read(void)
+{
+ return current->mm->pte_scan_scale;
+}
+#endif
static int prctl_set_mm(int opt, unsigned long addr,
unsigned long arg4, unsigned long arg5)
@@ -2820,6 +2833,18 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
return -EINVAL;
error = posixtimer_create_prctl(arg2);
break;
+#ifdef CONFIG_KSCAND
+ case PR_SET_PTE_A_SCAN_SCALE:
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+ error = prctl_pte_scan_scale_write((unsigned int) arg2);
+ break;
+ case PR_GET_PTE_A_SCAN_SCALE:
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+ error = prctl_pte_scan_scale_read();
+ break;
+#endif
default:
trace_task_prctl_unknown(option, arg2, arg3, arg4, arg5);
error = -EINVAL;
diff --git a/mm/kscand.c b/mm/kscand.c
index 029d6d2bedc3..2be7e71c2c8f 100644
--- a/mm/kscand.c
+++ b/mm/kscand.c
@@ -1228,6 +1228,11 @@ static unsigned long kscand_scan_mm_slot(void)
goto outerloop;
}
+ if (!mm->pte_scan_scale) {
+ next_mm = true;
+ goto outerloop;
+ }
+
mm_target_node = READ_ONCE(mm->target_node);
if (mm_target_node != mm_slot_target_node)
WRITE_ONCE(mm->target_node, mm_slot_target_node);
--
2.34.1
Powered by blists - more mailing lists