| 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: <20250211004054.222931-5-npache@redhat.com>
Date: Mon, 10 Feb 2025 17:40:53 -0700
From: Nico Pache <npache@...hat.com>
To: linux-kernel@...r.kernel.org,
linux-doc@...r.kernel.org,
linux-kselftest@...r.kernel.org,
linux-mm@...ck.org
Cc: ryan.roberts@....com,
anshuman.khandual@....com,
catalin.marinas@....com,
cl@...two.org,
vbabka@...e.cz,
mhocko@...e.com,
apopple@...dia.com,
dave.hansen@...ux.intel.com,
will@...nel.org,
baohua@...nel.org,
jack@...e.cz,
srivatsa@...il.mit.edu,
haowenchao22@...il.com,
hughd@...gle.com,
aneesh.kumar@...nel.org,
yang@...amperecomputing.com,
peterx@...hat.com,
ioworker0@...il.com,
wangkefeng.wang@...wei.com,
ziy@...dia.com,
jglisse@...gle.com,
surenb@...gle.com,
vishal.moola@...il.com,
zokeefe@...gle.com,
zhengqi.arch@...edance.com,
jhubbard@...dia.com,
21cnbao@...il.com,
willy@...radead.org,
kirill.shutemov@...ux.intel.com,
david@...hat.com,
aarcange@...hat.com,
raquini@...hat.com,
dev.jain@....com,
sunnanyong@...wei.com,
usamaarif642@...il.com,
audra@...hat.com,
akpm@...ux-foundation.org,
rostedt@...dmis.org,
mathieu.desnoyers@...icios.com,
tiwai@...e.de,
baolin.wang@...ux.alibaba.com,
corbet@....net,
shuah@...nel.org
Subject: [RFC v2 4/5] khugepaged: add defer option to mTHP options
Now that we have defer to globally disable THPs at fault time, lets add
a defer setting to the mTHP options. This will allow khugepaged to
operate at that order, while avoiding it at PF time.
Signed-off-by: Nico Pache <npache@...hat.com>
---
include/linux/huge_mm.h | 5 +++++
mm/huge_memory.c | 38 +++++++++++++++++++++++++++++++++-----
mm/khugepaged.c | 10 +++++-----
3 files changed, 43 insertions(+), 10 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index fb381ca720ea..8173a9ab0f3b 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -92,6 +92,7 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr;
#define TVA_SMAPS (1 << 0) /* Will be used for procfs */
#define TVA_IN_PF (1 << 1) /* Page fault handler */
#define TVA_ENFORCE_SYSFS (1 << 2) /* Obey sysfs configuration */
+#define TVA_IN_KHUGEPAGE ((1 << 2) | (1 << 3)) /* Khugepaged defer support */
#define thp_vma_allowable_order(vma, vm_flags, tva_flags, order) \
(!!thp_vma_allowable_orders(vma, vm_flags, tva_flags, BIT(order)))
@@ -173,6 +174,7 @@ extern unsigned long transparent_hugepage_flags;
extern unsigned long huge_anon_orders_always;
extern unsigned long huge_anon_orders_madvise;
extern unsigned long huge_anon_orders_inherit;
+extern unsigned long huge_anon_orders_defer;
static inline bool hugepage_global_enabled(void)
{
@@ -297,6 +299,9 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
/* Optimization to check if required orders are enabled early. */
if ((tva_flags & TVA_ENFORCE_SYSFS) && vma_is_anonymous(vma)) {
unsigned long mask = READ_ONCE(huge_anon_orders_always);
+
+ if ((tva_flags) & (TVA_IN_KHUGEPAGE))
+ mask |= READ_ONCE(huge_anon_orders_defer);
if (vm_flags & VM_HUGEPAGE)
mask |= READ_ONCE(huge_anon_orders_madvise);
if (hugepage_global_always() || hugepage_global_defer() ||
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a5e66a12bae8..de45595b0f98 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -81,6 +81,7 @@ unsigned long huge_zero_pfn __read_mostly = ~0UL;
unsigned long huge_anon_orders_always __read_mostly;
unsigned long huge_anon_orders_madvise __read_mostly;
unsigned long huge_anon_orders_inherit __read_mostly;
+unsigned long huge_anon_orders_defer __read_mostly;
static bool anon_orders_configured __initdata;
static inline bool file_thp_enabled(struct vm_area_struct *vma)
@@ -505,13 +506,15 @@ static ssize_t anon_enabled_show(struct kobject *kobj,
const char *output;
if (test_bit(order, &huge_anon_orders_always))
- output = "[always] inherit madvise never";
+ output = "[always] inherit madvise defer never";
else if (test_bit(order, &huge_anon_orders_inherit))
- output = "always [inherit] madvise never";
+ output = "always [inherit] madvise defer never";
else if (test_bit(order, &huge_anon_orders_madvise))
- output = "always inherit [madvise] never";
+ output = "always inherit [madvise] defer never";
+ else if (test_bit(order, &huge_anon_orders_defer))
+ output = "always inherit madvise [defer] never";
else
- output = "always inherit madvise [never]";
+ output = "always inherit madvise defer [never]";
return sysfs_emit(buf, "%s\n", output);
}
@@ -527,25 +530,36 @@ static ssize_t anon_enabled_store(struct kobject *kobj,
spin_lock(&huge_anon_orders_lock);
clear_bit(order, &huge_anon_orders_inherit);
clear_bit(order, &huge_anon_orders_madvise);
+ clear_bit(order, &huge_anon_orders_defer);
set_bit(order, &huge_anon_orders_always);
spin_unlock(&huge_anon_orders_lock);
} else if (sysfs_streq(buf, "inherit")) {
spin_lock(&huge_anon_orders_lock);
clear_bit(order, &huge_anon_orders_always);
clear_bit(order, &huge_anon_orders_madvise);
+ clear_bit(order, &huge_anon_orders_defer);
set_bit(order, &huge_anon_orders_inherit);
spin_unlock(&huge_anon_orders_lock);
} else if (sysfs_streq(buf, "madvise")) {
spin_lock(&huge_anon_orders_lock);
clear_bit(order, &huge_anon_orders_always);
clear_bit(order, &huge_anon_orders_inherit);
+ clear_bit(order, &huge_anon_orders_defer);
set_bit(order, &huge_anon_orders_madvise);
spin_unlock(&huge_anon_orders_lock);
+ } else if (sysfs_streq(buf, "defer")) {
+ spin_lock(&huge_anon_orders_lock);
+ clear_bit(order, &huge_anon_orders_always);
+ clear_bit(order, &huge_anon_orders_inherit);
+ clear_bit(order, &huge_anon_orders_madvise);
+ set_bit(order, &huge_anon_orders_defer);
+ spin_unlock(&huge_anon_orders_lock);
} else if (sysfs_streq(buf, "never")) {
spin_lock(&huge_anon_orders_lock);
clear_bit(order, &huge_anon_orders_always);
clear_bit(order, &huge_anon_orders_inherit);
clear_bit(order, &huge_anon_orders_madvise);
+ clear_bit(order, &huge_anon_orders_defer);
spin_unlock(&huge_anon_orders_lock);
} else
ret = -EINVAL;
@@ -991,7 +1005,7 @@ static char str_dup[PAGE_SIZE] __initdata;
static int __init setup_thp_anon(char *str)
{
char *token, *range, *policy, *subtoken;
- unsigned long always, inherit, madvise;
+ unsigned long always, inherit, madvise, defer;
char *start_size, *end_size;
int start, end, nr;
char *p;
@@ -1003,6 +1017,8 @@ static int __init setup_thp_anon(char *str)
always = huge_anon_orders_always;
madvise = huge_anon_orders_madvise;
inherit = huge_anon_orders_inherit;
+ defer = huge_anon_orders_defer;
+
p = str_dup;
while ((token = strsep(&p, ";")) != NULL) {
range = strsep(&token, ":");
@@ -1042,18 +1058,28 @@ static int __init setup_thp_anon(char *str)
bitmap_set(&always, start, nr);
bitmap_clear(&inherit, start, nr);
bitmap_clear(&madvise, start, nr);
+ bitmap_clear(&defer, start, nr);
} else if (!strcmp(policy, "madvise")) {
bitmap_set(&madvise, start, nr);
bitmap_clear(&inherit, start, nr);
bitmap_clear(&always, start, nr);
+ bitmap_clear(&defer, start, nr);
} else if (!strcmp(policy, "inherit")) {
bitmap_set(&inherit, start, nr);
bitmap_clear(&madvise, start, nr);
bitmap_clear(&always, start, nr);
+ bitmap_clear(&defer, start, nr);
+ } else if (!strcmp(policy, "defer")) {
+ bitmap_set(&defer, start, nr);
+ bitmap_clear(&madvise, start, nr);
+ bitmap_clear(&always, start, nr);
+ bitmap_clear(&inherit, start, nr);
} else if (!strcmp(policy, "never")) {
bitmap_clear(&inherit, start, nr);
bitmap_clear(&madvise, start, nr);
bitmap_clear(&always, start, nr);
+ bitmap_clear(&defer, start, nr);
+
} else {
pr_err("invalid policy %s in thp_anon boot parameter\n", policy);
goto err;
@@ -1064,6 +1090,8 @@ static int __init setup_thp_anon(char *str)
huge_anon_orders_always = always;
huge_anon_orders_madvise = madvise;
huge_anon_orders_inherit = inherit;
+ huge_anon_orders_defer = defer;
+
anon_orders_configured = true;
return 1;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index fc30698b8e6e..a83bc812ea64 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -488,7 +488,7 @@ void khugepaged_enter_vma(struct vm_area_struct *vma,
{
if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) &&
hugepage_pmd_enabled()) {
- if (thp_vma_allowable_order(vma, vm_flags, TVA_ENFORCE_SYSFS,
+ if (thp_vma_allowable_order(vma, vm_flags, TVA_IN_KHUGEPAGE,
PMD_ORDER))
__khugepaged_enter(vma->vm_mm);
}
@@ -943,7 +943,7 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
struct collapse_control *cc, int order)
{
struct vm_area_struct *vma;
- unsigned long tva_flags = cc->is_khugepaged ? TVA_ENFORCE_SYSFS : 0;
+ unsigned long tva_flags = cc->is_khugepaged ? TVA_IN_KHUGEPAGE : 0;
if (unlikely(khugepaged_test_exit_or_disable(mm)))
return SCAN_ANY_PROCESS;
@@ -1393,7 +1393,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
bool writable = false;
int chunk_none_count = 0;
int scaled_none = khugepaged_max_ptes_none >> (HPAGE_PMD_ORDER - MIN_MTHP_ORDER);
- unsigned long tva_flags = cc->is_khugepaged ? TVA_ENFORCE_SYSFS : 0;
+ unsigned long tva_flags = cc->is_khugepaged ? TVA_IN_KHUGEPAGE : 0;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
result = find_pmd_or_thp_or_none(mm, address, &pmd);
@@ -2505,7 +2505,7 @@ static int khugepaged_collapse_single_pmd(unsigned long addr, struct mm_struct *
struct collapse_control *cc)
{
int result = SCAN_FAIL;
- unsigned long tva_flags = cc->is_khugepaged ? TVA_ENFORCE_SYSFS : 0;
+ unsigned long tva_flags = cc->is_khugepaged ? TVA_IN_KHUGEPAGE : 0;
if (!*mmap_locked) {
mmap_read_lock(mm);
@@ -2595,7 +2595,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
break;
}
if (!thp_vma_allowable_order(vma, vma->vm_flags,
- TVA_ENFORCE_SYSFS, PMD_ORDER)) {
+ TVA_IN_KHUGEPAGE, PMD_ORDER)) {
skip:
progress++;
continue;
--
2.48.1
Powered by blists - more mailing lists