[PATCH v2 05/14] x86/cpuid: add X86_FEATURE_MOVNT_SLOW

[Ankur Arora]

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@xxxxxxxxxx>
---
 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