From: "Li Zhe" <lizhe.67@bytedance.com>
To: <akpm@linux-foundation.org>, <apopple@nvidia.com>,
<arnd@arndb.de>, <balbirs@nvidia.com>, <bp@alien8.de>,
<dave.hansen@linux.intel.com>, <david@kernel.org>,
<kees@kernel.org>, <mingo@redhat.com>, <muchun.song@linux.dev>,
<rppt@kernel.org>, <tglx@kernel.org>
Cc: <linux-arch@vger.kernel.org>, <linux-hardening@vger.kernel.org>,
<linux-kernel@vger.kernel.org>, <linux-mm@kvack.org>,
<x86@kernel.org>, <lizhe.67@bytedance.com>
Subject: [PATCH v9 8/8] x86/string: extend memcpy_flushcache() fixed-size fastpaths
Date: Mon, 3 Aug 2026 15:09:29 +0800 [thread overview]
Message-ID: <20260803070929.86075-9-lizhe.67@bytedance.com> (raw)
In-Reply-To: <20260803070929.86075-1-lizhe.67@bytedance.com>
The x86 memcpy_nontemporal() helper maps to memcpy_flushcache(), and the
ZONE_DEVICE template-copy path uses it to copy one struct page at a
time.
The relevant copy size is sizeof(struct page). On x86_64, the base struct
page layout is 64 bytes. Adding either the KMSAN metadata pointers or an
out-of-flags last_cpupid field can make it 80 bytes after alignment, and
enabling both can make it 96 bytes.
memcpy_flushcache() currently only has inline fixed-size cases for 4, 8,
and 16 bytes. As a result, these constant-sized struct page copies fall
through to __memcpy_flushcache() even though the compiler knows the copy
size at the call site.
Add fixed-size MOVNTI cases up to 96 bytes so the ZONE_DEVICE
template-copy path can keep these struct page copies in the inline
memcpy_flushcache() path.
This matters for ZONE_DEVICE memmap initialization because the copy
happens once per initialized struct page. For a 100 GB fsdax namespace
with map=dev, this is about 25 million struct page copies during nd_pmem
binding or rebinding.
Tested in a VM with a 100 GB fsdax namespace device configured with
map=dev and a 100 GB devdax namespace (align=2097152) on Intel Ice Lake
server.
Test procedure:
Rebind the nd_pmem and dax_pmem drivers 30 times and collect the memmap
initialization time from the pr_debug() output of
memmap_init_zone_device().
With memcpy_nontemporal() used by the ZONE_DEVICE template-copy path:
Average of rebinds for nd_pmem driver: 150.83 ms
Average of rebinds for dax_pmem driver: 153.55 ms
With this x86 fixed-size fastpath patch applied:
Average of rebinds for nd_pmem driver: 96.79 ms
Average of rebinds for dax_pmem driver: 119.04 ms
This further reduces the average memmap initialization time measured
during rebind by about 35.8% for nd_pmem and 22.5% for dax_pmem.
Signed-off-by: Li Zhe <lizhe.67@bytedance.com>
---
arch/x86/include/asm/string_64.h | 56 +++++++++++++++++++++++++++++++-
1 file changed, 55 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 21ae515ae35a..bc6a9f34b346 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -82,7 +82,35 @@ int strcmp(const char *cs, const char *ct);
#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
#define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1
void __memcpy_flushcache(void *dst, const void *src, size_t cnt);
-static __always_inline void memcpy_flushcache(void *dst, const void *src, size_t cnt)
+
+static __always_inline void movnti_8(void *dst, const void *src)
+{
+ asm volatile("movntiq %1, %0"
+ : "=m"(*(u64 *)dst)
+ : "r"(*(const u64 *)src)
+ : "memory");
+}
+
+static __always_inline void movnti_16(void *dst, const void *src)
+{
+ movnti_8(dst, src);
+ movnti_8(dst + 8, src + 8);
+}
+
+static __always_inline void movnti_32(void *dst, const void *src)
+{
+ movnti_16(dst, src);
+ movnti_16(dst + 16, src + 16);
+}
+
+static __always_inline void movnti_64(void *dst, const void *src)
+{
+ movnti_32(dst, src);
+ movnti_32(dst + 32, src + 32);
+}
+
+static __always_inline void memcpy_flushcache(void *dst, const void *src,
+ size_t cnt)
{
if (__builtin_constant_p(cnt)) {
switch (cnt) {
@@ -96,8 +124,34 @@ static __always_inline void memcpy_flushcache(void *dst, const void *src, size_t
asm ("movntiq %1, %0" : "=m"(*(u64 *)dst) : "r"(*(u64 *)src));
asm ("movntiq %1, %0" : "=m"(*(u64 *)(dst + 8)) : "r"(*(u64 *)(src + 8)));
return;
+ /*
+ * The relevant fixed-size copies here are the
+ * x86_64 struct page sizes: 64, 80, and 96 bytes.
+ * Keep 32-byte and 48-byte copies inline as well
+ * instead of sending those nearby fixed-size
+ * cases back to __memcpy_flushcache().
+ */
+ case 32:
+ movnti_32(dst, src);
+ return;
+ case 48:
+ movnti_32(dst, src);
+ movnti_16(dst + 32, src + 32);
+ return;
+ case 64:
+ movnti_64(dst, src);
+ return;
+ case 80:
+ movnti_64(dst, src);
+ movnti_16(dst + 64, src + 64);
+ return;
+ case 96:
+ movnti_64(dst, src);
+ movnti_32(dst + 64, src + 64);
+ return;
}
}
+
__memcpy_flushcache(dst, src, cnt);
}
--
2.20.1
next prev parent reply other threads:[~2026-08-03 7:13 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-03 7:09 [PATCH v9 0/8] mm: optimize zone-device memmap initialization Li Zhe
2026-08-03 7:09 ` [PATCH v9 1/8] mm: fix stale ZONE_DEVICE refcount comment Li Zhe
2026-08-03 7:09 ` [PATCH v9 2/8] mm: factor zone-device page init helpers out of __init_zone_device_page Li Zhe
2026-08-03 7:09 ` [PATCH v9 3/8] mm: add a set_page_section_from_pfn() helper Li Zhe
2026-08-03 7:09 ` [PATCH v9 4/8] mm: add a template-based fast path for zone-device page init Li Zhe
2026-08-03 8:39 ` Muchun Song
2026-08-05 9:50 ` Li Zhe
2026-08-03 7:09 ` [PATCH v9 5/8] mm: extend the template fast path to zone-device compound tails Li Zhe
2026-08-03 7:09 ` [PATCH v9 6/8] string: introduce memcpy_nontemporal() Li Zhe
2026-08-03 7:09 ` [PATCH v9 7/8] mm: use memcpy_nontemporal() in zone-device template copies Li Zhe
2026-08-03 7:09 ` Li Zhe [this message]
2026-08-04 20:35 ` [PATCH v9 8/8] x86/string: extend memcpy_flushcache() fixed-size fastpaths Borislav Petkov
2026-08-05 11:04 ` Li Zhe
2026-08-03 21:40 ` [PATCH v9 0/8] mm: optimize zone-device memmap initialization Andrew Morton
2026-08-05 9:49 ` Li Zhe
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=20260803070929.86075-9-lizhe.67@bytedance.com \
--to=lizhe.67@bytedance.com \
--cc=akpm@linux-foundation.org \
--cc=apopple@nvidia.com \
--cc=arnd@arndb.de \
--cc=balbirs@nvidia.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=david@kernel.org \
--cc=kees@kernel.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-hardening@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mingo@redhat.com \
--cc=muchun.song@linux.dev \
--cc=rppt@kernel.org \
--cc=tglx@kernel.org \
--cc=x86@kernel.org \
/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