From: Nico Pache <npache@redhat.com>
To: linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
linux-kselftest@vger.kernel.org, linux-mm@kvack.org
Cc: ryan.roberts@arm.com, anshuman.khandual@arm.com,
catalin.marinas@arm.com, cl@gentwo.org, vbabka@suse.cz,
mhocko@suse.com, apopple@nvidia.com, dave.hansen@linux.intel.com,
will@kernel.org, baohua@kernel.org, jack@suse.cz,
srivatsa@csail.mit.edu, haowenchao22@gmail.com, hughd@google.com,
aneesh.kumar@kernel.org, yang@os.amperecomputing.com,
peterx@redhat.com, ioworker0@gmail.com,
wangkefeng.wang@huawei.com, ziy@nvidia.com, jglisse@google.com,
surenb@google.com, vishal.moola@gmail.com, zokeefe@google.com,
zhengqi.arch@bytedance.com, jhubbard@nvidia.com,
21cnbao@gmail.com, willy@infradead.org,
kirill.shutemov@linux.intel.com, david@redhat.com,
aarcange@redhat.com, raquini@redhat.com, dev.jain@arm.com,
sunnanyong@huawei.com, usamaarif642@gmail.com, audra@redhat.com,
akpm@linux-foundation.org, rostedt@goodmis.org,
mathieu.desnoyers@efficios.com, tiwai@suse.de,
baolin.wang@linux.alibaba.com, corbet@lwn.net, shuah@kernel.org
Subject: [RFC v2 1/5] mm: defer THP insertion to khugepaged
Date: Mon, 10 Feb 2025 17:40:50 -0700 [thread overview]
Message-ID: <20250211004054.222931-2-npache@redhat.com> (raw)
In-Reply-To: <20250211004054.222931-1-npache@redhat.com>
setting /transparent_hugepages/enabled=always allows applications
to benefit from THPs without having to madvise. However, the pf handler
takes very few considerations to decide weather or not to actually use a
THP. This can lead to a lot of wasted memory. khugepaged only operates
on memory that was either allocated with enabled=always or MADV_HUGEPAGE.
Introduce the ability to set enabled=defer, which will prevent THPs from
being allocated by the page fault handler unless madvise is set,
leaving it up to khugepaged to decide which allocations will collapse to a
THP. This should allow applications to benefits from THPs, while curbing
some of the memory waste.
Signed-off-by: Nico Pache <npache@redhat.com>
---
include/linux/huge_mm.h | 15 +++++++++++++--
mm/huge_memory.c | 31 +++++++++++++++++++++++++++----
2 files changed, 40 insertions(+), 6 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 93e509b6c00e..fb381ca720ea 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -44,6 +44,7 @@ enum transparent_hugepage_flag {
TRANSPARENT_HUGEPAGE_UNSUPPORTED,
TRANSPARENT_HUGEPAGE_FLAG,
TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
+ TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG,
TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG,
@@ -177,6 +178,7 @@ static inline bool hugepage_global_enabled(void)
{
return transparent_hugepage_flags &
((1<<TRANSPARENT_HUGEPAGE_FLAG) |
+ (1<<TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG) |
(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG));
}
@@ -186,6 +188,12 @@ static inline bool hugepage_global_always(void)
(1<<TRANSPARENT_HUGEPAGE_FLAG);
}
+static inline bool hugepage_global_defer(void)
+{
+ return transparent_hugepage_flags &
+ (1<<TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG);
+}
+
static inline int highest_order(unsigned long orders)
{
return fls_long(orders) - 1;
@@ -282,13 +290,16 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
unsigned long tva_flags,
unsigned long orders)
{
+ if ((tva_flags & TVA_IN_PF) && hugepage_global_defer() &&
+ !(vm_flags & VM_HUGEPAGE))
+ return 0;
+
/* 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 (vm_flags & VM_HUGEPAGE)
mask |= READ_ONCE(huge_anon_orders_madvise);
- if (hugepage_global_always() ||
+ if (hugepage_global_always() || hugepage_global_defer() ||
((vm_flags & VM_HUGEPAGE) && hugepage_global_enabled()))
mask |= READ_ONCE(huge_anon_orders_inherit);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 3d3ebdc002d5..a5e66a12bae8 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -297,12 +297,15 @@ static ssize_t enabled_show(struct kobject *kobj,
const char *output;
if (test_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags))
- output = "[always] madvise never";
+ output = "[always] madvise defer never";
else if (test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
&transparent_hugepage_flags))
- output = "always [madvise] never";
+ output = "always [madvise] defer never";
+ else if (test_bit(TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG,
+ &transparent_hugepage_flags))
+ output = "always madvise [defer] never";
else
- output = "always madvise [never]";
+ output = "always madvise defer [never]";
return sysfs_emit(buf, "%s\n", output);
}
@@ -315,13 +318,20 @@ static ssize_t enabled_store(struct kobject *kobj,
if (sysfs_streq(buf, "always")) {
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
+ } else if (sysfs_streq(buf, "defer")) {
+ clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
+ set_bit(TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG, &transparent_hugepage_flags);
} else if (sysfs_streq(buf, "madvise")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
} else if (sysfs_streq(buf, "never")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG, &transparent_hugepage_flags);
} else
ret = -EINVAL;
@@ -943,18 +953,31 @@ static int __init setup_transparent_hugepage(char *str)
&transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
&transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG,
+ &transparent_hugepage_flags);
ret = 1;
+ } else if (!strcmp(str, "defer")) {
+ clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
+ &transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
+ &transparent_hugepage_flags);
+ set_bit(TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG,
+ &transparent_hugepage_flags);
} else if (!strcmp(str, "madvise")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
&transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG,
+ &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
- &transparent_hugepage_flags);
+ &transparent_hugepage_flags);
ret = 1;
} else if (!strcmp(str, "never")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
&transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
&transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG,
+ &transparent_hugepage_flags);
ret = 1;
}
out:
--
2.48.1
next prev parent reply other threads:[~2025-02-11 0:41 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-11 0:40 [RFC v2 0/5] mm: introduce THP deferred setting Nico Pache
2025-02-11 0:40 ` Nico Pache [this message]
2025-02-17 14:59 ` [RFC v2 1/5] mm: defer THP insertion to khugepaged Usama Arif
2025-02-17 19:24 ` Nico Pache
2025-02-11 0:40 ` [RFC v2 2/5] mm: document transparent_hugepage=defer usage Nico Pache
2025-02-17 15:04 ` Usama Arif
2025-02-17 19:30 ` Nico Pache
2025-02-11 0:40 ` [RFC v2 3/5] selftests: mm: add defer to thp setting parser Nico Pache
2025-02-11 0:40 ` [RFC v2 4/5] khugepaged: add defer option to mTHP options Nico Pache
2025-02-11 0:40 ` [RFC v2 5/5] mm: document mTHP defer setting Nico Pache
2025-02-17 15:13 ` Usama Arif
2025-02-17 19:40 ` Nico Pache
2025-02-17 14:53 ` [RFC v2 0/5] mm: introduce THP deferred setting Usama Arif
2025-02-17 19:23 ` Nico Pache
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250211004054.222931-2-npache@redhat.com \
--to=npache@redhat.com \
--cc=21cnbao@gmail.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=aneesh.kumar@kernel.org \
--cc=anshuman.khandual@arm.com \
--cc=apopple@nvidia.com \
--cc=audra@redhat.com \
--cc=baohua@kernel.org \
--cc=baolin.wang@linux.alibaba.com \
--cc=catalin.marinas@arm.com \
--cc=cl@gentwo.org \
--cc=corbet@lwn.net \
--cc=dave.hansen@linux.intel.com \
--cc=david@redhat.com \
--cc=dev.jain@arm.com \
--cc=haowenchao22@gmail.com \
--cc=hughd@google.com \
--cc=ioworker0@gmail.com \
--cc=jack@suse.cz \
--cc=jglisse@google.com \
--cc=jhubbard@nvidia.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mhocko@suse.com \
--cc=peterx@redhat.com \
--cc=raquini@redhat.com \
--cc=rostedt@goodmis.org \
--cc=ryan.roberts@arm.com \
--cc=shuah@kernel.org \
--cc=srivatsa@csail.mit.edu \
--cc=sunnanyong@huawei.com \
--cc=surenb@google.com \
--cc=tiwai@suse.de \
--cc=usamaarif642@gmail.com \
--cc=vbabka@suse.cz \
--cc=vishal.moola@gmail.com \
--cc=wangkefeng.wang@huawei.com \
--cc=will@kernel.org \
--cc=willy@infradead.org \
--cc=yang@os.amperecomputing.com \
--cc=zhengqi.arch@bytedance.com \
--cc=ziy@nvidia.com \
--cc=zokeefe@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox