[PATCH v3 11/21] x86/cpuid: add X86_FEATURE_MOVNT_SLOW

[Ankur Arora]

X86_FEATURE_MOVNT_SLOW denotes that clear_pages_movnti() is slower for
bulk page clearing (defined as LLC-sized or larger) than the standard
cached clear_page() idiom.

Microarchs where this is true would set this via check_movnt_quirks().

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         | 16 ++++++++++++++++
 arch/x86/kernel/cpu/cpu.h          |  2 ++
 arch/x86/kernel/cpu/intel.c        |  2 ++
 5 files changed, 23 insertions(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 393f2bbb5e3a..824bdb1d0da1 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -296,6 +296,7 @@
 #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 0c0b09796ced..a5fe1420388d 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -891,6 +891,8 @@ 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 d879a6c93609..16e293654d34 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -85,6 +85,22 @@ EXPORT_SYMBOL_GPL(mds_idle_clear);
  */
 DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
 
+/*
+ * check_movnt_quirks() sets X86_FEATURE_MOVNT_SLOW for uarchs where
+ * clear_pages_movnti() is slower for bulk page clearing than the standard
+ * cached clear_page() idiom (typically rep-stosb/rep-stosq.)
+ *
+ * (Bulk clearing defined as LLC-sized or larger.)
+ *
+ * x86_64 only since clear_pages_movnti() is only defined there.
+ */
+void check_movnt_quirks(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_64
+
+#endif
+}
+
 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 2a8e584fc991..f53f07bf706f 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 fd5dead8371c..f0dc9b97dc8f 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -701,6 +701,8 @@ 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
-- 
2.31.1