linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ankur Arora <ankur.a.arora@oracle.com>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org, x86@kernel.org
Cc: mingo@kernel.org, bp@alien8.de, luto@kernel.org,
	akpm@linux-foundation.org, mike.kravetz@oracle.com,
	jon.grimm@amd.com, kvm@vger.kernel.org, konrad.wilk@oracle.com,
	boris.ostrovsky@oracle.com,
	Ankur Arora <ankur.a.arora@oracle.com>
Subject: [PATCH v2 05/14] x86/cpuid: add X86_FEATURE_MOVNT_SLOW
Date: Wed, 20 Oct 2021 10:02:56 -0700	[thread overview]
Message-ID: <20211020170305.376118-6-ankur.a.arora@oracle.com> (raw)
In-Reply-To: <20211020170305.376118-1-ankur.a.arora@oracle.com>

Enabled on microarchitectures where MOVNT is slower for
bulk page clearing than the standard cached clear_page()
idiom.

Also add check_movnt_quirks() where we would set this.

Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
---
 arch/x86/include/asm/cpufeatures.h |  1 +
 arch/x86/kernel/cpu/amd.c          |  2 ++
 arch/x86/kernel/cpu/bugs.c         | 15 +++++++++++++++
 arch/x86/kernel/cpu/cpu.h          |  2 ++
 arch/x86/kernel/cpu/intel.c        |  1 +
 5 files changed, 21 insertions(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index d0ce5cfd3ac1..69191f175c2c 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -294,6 +294,7 @@
 #define X86_FEATURE_PER_THREAD_MBA	(11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
 #define X86_FEATURE_SGX1		(11*32+ 8) /* "" Basic SGX */
 #define X86_FEATURE_SGX2		(11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */
+#define X86_FEATURE_MOVNT_SLOW		(11*32+10) /* MOVNT is slow. (see check_movnt_quirks()) */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 2131af9f2fa2..5de83c6fe526 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -915,6 +915,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 >= 0x10)
 		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 
+	check_movnt_quirks(c);
+
 	/* get apicid instead of initial apic id from cpuid */
 	c->apicid = hard_smp_processor_id();
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ecfca3bbcd96..4e1558d22a5f 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -84,6 +84,21 @@ EXPORT_SYMBOL_GPL(mds_idle_clear);
  */
 DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
 
+void check_movnt_quirks(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_64
+	/*
+	 * Check if MOVNT is slower than the model specific clear_page()
+	 * idiom (movq/rep-stosb/rep-stosq etc) for bulk page clearing.
+	 * (Bulk is defined here as LLC-sized or larger.)
+	 *
+	 * Condition this check on CONFIG_X86_64 so we don't have
+	 * to worry about any CONFIG_X86_32 families that don't
+	 * support SSE2/MOVNT.
+	 */
+#endif /* CONFIG_X86_64*/
+}
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 95521302630d..72e3715d63ea 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -83,4 +83,6 @@ extern void update_srbds_msr(void);
 
 extern u64 x86_read_arch_cap_msr(void);
 
+void check_movnt_quirks(struct cpuinfo_x86 *c);
+
 #endif /* ARCH_X86_CPU_H */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 8321c43554a1..36a2f8e88b74 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -666,6 +666,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 		c->x86_cache_alignment = c->x86_clflush_size * 2;
 	if (c->x86 == 6)
 		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+	check_movnt_quirks(c);
 #else
 	/*
 	 * Names for the Pentium II/Celeron processors
-- 
2.29.2


  parent reply	other threads:[~2021-10-20 17:06 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-20 17:02 [PATCH v2 00/14] Use uncached stores while clearing huge pages Ankur Arora
2021-10-20 17:02 ` [PATCH v2 01/14] x86/asm: add memset_movnti() Ankur Arora
2021-10-20 17:02 ` [PATCH v2 02/14] perf bench: " Ankur Arora
2021-10-20 17:02 ` [PATCH v2 03/14] x86/asm: add uncached page clearing Ankur Arora
2021-10-20 17:02 ` [PATCH v2 04/14] x86/asm: add clzero based " Ankur Arora
2021-10-20 17:02 ` Ankur Arora [this message]
2021-10-20 17:02 ` [PATCH v2 06/14] sparse: add address_space __incoherent Ankur Arora
2021-10-20 17:02 ` [PATCH v2 07/14] x86/clear_page: add clear_page_uncached() Ankur Arora
2021-12-08  8:58   ` Yu Xu
2021-12-10  4:37     ` Ankur Arora
2021-12-10  4:48       ` Yu Xu
2021-12-10 14:26         ` Ankur Arora
2021-10-20 17:02 ` [PATCH v2 08/14] mm/clear_page: add clear_page_uncached_threshold() Ankur Arora
2021-10-20 17:03 ` [PATCH v2 09/14] x86/clear_page: add arch_clear_page_uncached_threshold() Ankur Arora
2021-10-20 17:03 ` [PATCH v2 10/14] clear_huge_page: use uncached path Ankur Arora
2021-10-20 17:03 ` [PATCH v2 11/14] gup: add FOLL_HINT_BULK, FAULT_FLAG_UNCACHED Ankur Arora
2021-10-20 17:03 ` [PATCH v2 12/14] gup: use uncached path when clearing large regions Ankur Arora
2021-10-20 18:52 ` [PATCH v2 13/14] vfio_iommu_type1: specify FOLL_HINT_BULK to pin_user_pages() Ankur Arora
2021-10-20 18:52 ` [PATCH v2 14/14] x86/cpu/intel: set X86_FEATURE_MOVNT_SLOW for Skylake Ankur Arora

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=20211020170305.376118-6-ankur.a.arora@oracle.com \
    --to=ankur.a.arora@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=boris.ostrovsky@oracle.com \
    --cc=bp@alien8.de \
    --cc=jon.grimm@amd.com \
    --cc=konrad.wilk@oracle.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mike.kravetz@oracle.com \
    --cc=mingo@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;
as well as URLs for NNTP newsgroup(s).