Merge branch 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cpu handling changes from Ingo Molnar:
 "Bigger changes:

   - Intel CPU hardware-enablement: new vector instructions support
     (AVX-512), by Fenghua Yu.

   - Support the clflushopt instruction and use it in appropriate
     places.  clflushopt is similar to clflush but with more relaxed
     ordering, by Ross Zwisler.

   - MSR accessor cleanups, by Borislav Petkov.

   - 'forcepae' boot flag for those who have way too much time to spend
     on way too old Pentium-M systems and want to live way too
     dangerously, by Chris Bainbridge"

* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, cpu: Add forcepae parameter for booting PAE kernels on PAE-disabled Pentium M
  Rename TAINT_UNSAFE_SMP to TAINT_CPU_OUT_OF_SPEC
  x86, intel: Make MSR_IA32_MISC_ENABLE bit constants systematic
  x86, Intel: Convert to the new bit access MSR accessors
  x86, AMD: Convert to the new bit access MSR accessors
  x86: Add another set of MSR accessor functions
  x86: Use clflushopt in drm_clflush_virt_range
  x86: Use clflushopt in drm_clflush_page
  x86: Use clflushopt in clflush_cache_range
  x86: Add support for the clflushopt instruction
  x86, AVX-512: Enable AVX-512 States Context Switch
  x86, AVX-512: AVX-512 Feature Detection

2 files changed, 43 insertions, 60 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c67ffa6..ce8b8ff 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -218,7 +218,7 @@ static void amd_k7_smp_check(struct cpuinfo_x86 *c)
 	 */
 	WARN_ONCE(1, "WARNING: This combination of AMD"
 		" processors is not suitable for SMP.\n");
-	add_taint(TAINT_UNSAFE_SMP, LOCKDEP_NOW_UNRELIABLE);
+	add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE);
 }
 
 static void init_amd_k7(struct cpuinfo_x86 *c)
@@ -233,9 +233,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c)
 	if (c->x86_model >= 6 && c->x86_model <= 10) {
 		if (!cpu_has(c, X86_FEATURE_XMM)) {
 			printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
-			rdmsr(MSR_K7_HWCR, l, h);
-			l &= ~0x00008000;
-			wrmsr(MSR_K7_HWCR, l, h);
+			msr_clear_bit(MSR_K7_HWCR, 15);
 			set_cpu_cap(c, X86_FEATURE_XMM);
 		}
 	}
@@ -509,14 +507,8 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 #endif
 
 	/* F16h erratum 793, CVE-2013-6885 */
-	if (c->x86 == 0x16 && c->x86_model <= 0xf) {
-		u64 val;
-
-		rdmsrl(MSR_AMD64_LS_CFG, val);
-		if (!(val & BIT(15)))
-			wrmsrl(MSR_AMD64_LS_CFG, val | BIT(15));
-	}
-
+	if (c->x86 == 0x16 && c->x86_model <= 0xf)
+		msr_set_bit(MSR_AMD64_LS_CFG, 15);
 }
 
 static const int amd_erratum_383[];
@@ -536,11 +528,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 	 * Errata 63 for SH-B3 steppings
 	 * Errata 122 for all steppings (F+ have it disabled by default)
 	 */
-	if (c->x86 == 0xf) {
-		rdmsrl(MSR_K7_HWCR, value);
-		value |= 1 << 6;
-		wrmsrl(MSR_K7_HWCR, value);
-	}
+	if (c->x86 == 0xf)
+		msr_set_bit(MSR_K7_HWCR, 6);
 #endif
 
 	early_init_amd(c);
@@ -623,14 +612,11 @@ static void init_amd(struct cpuinfo_x86 *c)
 	    (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
 	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
 
-		if (!rdmsrl_safe(0xc0011005, &value)) {
-			value |= 1ULL << 54;
-			wrmsrl_safe(0xc0011005, value);
+		if (msr_set_bit(0xc0011005, 54) > 0) {
 			rdmsrl(0xc0011005, value);
-			if (value & (1ULL << 54)) {
+			if (value & BIT_64(54)) {
 				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
-				printk(KERN_INFO FW_INFO "CPU: Re-enabling "
-				  "disabled Topology Extensions Support\n");
+				pr_info(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
 			}
 		}
 	}
@@ -709,19 +695,12 @@ static void init_amd(struct cpuinfo_x86 *c)
 		 * Disable GART TLB Walk Errors on Fam10h. We do this here
 		 * because this is always needed when GART is enabled, even in a
 		 * kernel which has no MCE support built in.
-		 * BIOS should disable GartTlbWlk Errors themself. If
-		 * it doesn't do it here as suggested by the BKDG.
+		 * BIOS should disable GartTlbWlk Errors already. If
+		 * it doesn't, do it here as suggested by the BKDG.
 		 *
 		 * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
 		 */
-		u64 mask;
-		int err;
-
-		err = rdmsrl_safe(MSR_AMD64_MCx_MASK(4), &mask);
-		if (err == 0) {
-			mask |= (1 << 10);
-			wrmsrl_safe(MSR_AMD64_MCx_MASK(4), mask);
-		}
+		msr_set_bit(MSR_AMD64_MCx_MASK(4), 10);
 
 		/*
 		 * On family 10h BIOS may not have properly enabled WC+ support,
@@ -733,10 +712,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 		 * NOTE: we want to use the _safe accessors so as not to #GP kvm
 		 * guests on older kvm hosts.
 		 */
-
-		rdmsrl_safe(MSR_AMD64_BU_CFG2, &value);
-		value &= ~(1ULL << 24);
-		wrmsrl_safe(MSR_AMD64_BU_CFG2, value);
+		msr_clear_bit(MSR_AMD64_BU_CFG2, 24);
 
 		if (cpu_has_amd_erratum(c, amd_erratum_383))
 			set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 5cd9bfa..897d620 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -31,11 +31,8 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 
 	/* Unmask CPUID levels if masked: */
 	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
-		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-
-		if (misc_enable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID) {
-			misc_enable &= ~MSR_IA32_MISC_ENABLE_LIMIT_CPUID;
-			wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+		if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
+				  MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) {
 			c->cpuid_level = cpuid_eax(0);
 			get_cpu_cap(c);
 		}
@@ -129,16 +126,10 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	 * Ingo Molnar reported a Pentium D (model 6) and a Xeon
 	 * (model 2) with the same problem.
 	 */
-	if (c->x86 == 15) {
-		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-
-		if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
-			printk(KERN_INFO "kmemcheck: Disabling fast string operations\n");
-
-			misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING;
-			wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-		}
-	}
+	if (c->x86 == 15)
+		if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
+				  MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0)
+			pr_info("kmemcheck: Disabling fast string operations\n");
 #endif
 
 	/*
@@ -195,10 +186,16 @@ static void intel_smp_check(struct cpuinfo_x86 *c)
 	}
 }
 
-static void intel_workarounds(struct cpuinfo_x86 *c)
+static int forcepae;
+static int __init forcepae_setup(char *__unused)
 {
-	unsigned long lo, hi;
+	forcepae = 1;
+	return 1;
+}
+__setup("forcepae", forcepae_setup);
 
+static void intel_workarounds(struct cpuinfo_x86 *c)
+{
 #ifdef CONFIG_X86_F00F_BUG
 	/*
 	 * All current models of Pentium and Pentium with MMX technology CPUs
@@ -225,16 +222,26 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 		clear_cpu_cap(c, X86_FEATURE_SEP);
 
 	/*
+	 * PAE CPUID issue: many Pentium M report no PAE but may have a
+	 * functionally usable PAE implementation.
+	 * Forcefully enable PAE if kernel parameter "forcepae" is present.
+	 */
+	if (forcepae) {
+		printk(KERN_WARNING "PAE forced!\n");
+		set_cpu_cap(c, X86_FEATURE_PAE);
+		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE);
+	}
+
+	/*
 	 * P4 Xeon errata 037 workaround.
 	 * Hardware prefetcher may cause stale data to be loaded into the cache.
 	 */
 	if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) {
-		rdmsr(MSR_IA32_MISC_ENABLE, lo, hi);
-		if ((lo & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE) == 0) {
-			printk (KERN_INFO "CPU: C0 stepping P4 Xeon detected.\n");
-			printk (KERN_INFO "CPU: Disabling hardware prefetching (Errata 037)\n");
-			lo |= MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE;
-			wrmsr(MSR_IA32_MISC_ENABLE, lo, hi);
+		if (msr_set_bit(MSR_IA32_MISC_ENABLE,
+				MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
+		    > 0) {
+			pr_info("CPU: C0 stepping P4 Xeon detected.\n");
+			pr_info("CPU: Disabling hardware prefetching (Errata 037)\n");
 		}
 	}