From: Nico Pache <npache@redhat.com>
To: linux-mm@kvack.org, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org
Cc: akpm@linux-foundation.org, corbet@lwn.net, rostedt@goodmis.org,
mhiramat@kernel.org, mathieu.desnoyers@efficios.com,
david@redhat.com, baohua@kernel.org,
baolin.wang@linux.alibaba.com, ryan.roberts@arm.com,
willy@infradead.org, peterx@redhat.com, shuah@kernel.org,
ziy@nvidia.com, wangkefeng.wang@huawei.com,
usamaarif642@gmail.com, sunnanyong@huawei.com,
vishal.moola@gmail.com, thomas.hellstrom@linux.intel.com,
yang@os.amperecomputing.com, kirill.shutemov@linux.intel.com,
aarcange@redhat.com, raquini@redhat.com, dev.jain@arm.com,
anshuman.khandual@arm.com, catalin.marinas@arm.com,
tiwai@suse.de, will@kernel.org, dave.hansen@linux.intel.com,
jack@suse.cz, cl@gentwo.org, jglisse@google.com,
surenb@google.com, zokeefe@google.com, Liam.Howlett@oracle.com,
lorenzo.stoakes@oracle.com, hannes@cmpxchg.org,
rientjes@google.com, mhocko@suse.com, rdunlap@infradead.org
Subject: [PATCH v5 1/4] mm: defer THP insertion to khugepaged
Date: Mon, 28 Apr 2025 12:29:01 -0600 [thread overview]
Message-ID: <20250428182904.93989-2-npache@redhat.com> (raw)
In-Reply-To: <20250428182904.93989-1-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.
Co-developed-by: Rafael Aquini <raquini@redhat.com>
Signed-off-by: Rafael Aquini <raquini@redhat.com>
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 e3d15c737008..57e6c962afb1 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -48,6 +48,7 @@ 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,
@@ -186,6 +187,7 @@ 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));
}
@@ -195,6 +197,12 @@ 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;
@@ -291,13 +299,16 @@ 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 8af5caa0d9bc..17b66adef029 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;
@@ -954,18 +964,31 @@ 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:[~2025-04-28 18:29 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-04-28 18:29 [PATCH v5 0/4] mm: introduce THP deferred setting Nico Pache
2025-04-28 18:29 ` Nico Pache [this message]
2025-04-29 13:49 ` [PATCH v5 1/4] mm: defer THP insertion to khugepaged Zi Yan
2025-04-30 18:39 ` Nico Pache
2025-04-28 18:29 ` [PATCH v5 2/4] mm: document (m)THP defer usage Nico Pache
2025-04-30 20:15 ` Zi Yan
2025-05-01 22:38 ` Nico Pache
2025-04-28 18:29 ` [PATCH v5 3/4] khugepaged: add defer option to mTHP options Nico Pache
2025-04-30 20:34 ` Zi Yan
2025-05-01 22:53 ` Nico Pache
2025-04-28 18:29 ` [PATCH v5 4/4] selftests: mm: add defer to thp setting parser Nico Pache
2025-04-30 20:40 ` Zi Yan
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=20250428182904.93989-2-npache@redhat.com \
--to=npache@redhat.com \
--cc=Liam.Howlett@oracle.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=anshuman.khandual@arm.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=hannes@cmpxchg.org \
--cc=jack@suse.cz \
--cc=jglisse@google.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=lorenzo.stoakes@oracle.com \
--cc=mathieu.desnoyers@efficios.com \
--cc=mhiramat@kernel.org \
--cc=mhocko@suse.com \
--cc=peterx@redhat.com \
--cc=raquini@redhat.com \
--cc=rdunlap@infradead.org \
--cc=rientjes@google.com \
--cc=rostedt@goodmis.org \
--cc=ryan.roberts@arm.com \
--cc=shuah@kernel.org \
--cc=sunnanyong@huawei.com \
--cc=surenb@google.com \
--cc=thomas.hellstrom@linux.intel.com \
--cc=tiwai@suse.de \
--cc=usamaarif642@gmail.com \
--cc=vishal.moola@gmail.com \
--cc=wangkefeng.wang@huawei.com \
--cc=will@kernel.org \
--cc=willy@infradead.org \
--cc=yang@os.amperecomputing.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;
as well as URLs for NNTP newsgroup(s).