1 files changed, 132 insertions, 55 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2c57fffebf9b..f125bf7ecb6f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -366,6 +366,77 @@ out:
 	cr4_clear_bits(X86_CR4_UMIP);
 }
 
+static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
+static unsigned long cr4_pinned_bits __ro_after_init;
+
+void native_write_cr0(unsigned long val)
+{
+	unsigned long bits_missing = 0;
+
+set_register:
+	asm volatile("mov %0,%%cr0": "+r" (val), "+m" (__force_order));
+
+	if (static_branch_likely(&cr_pinning)) {
+		if (unlikely((val & X86_CR0_WP) != X86_CR0_WP)) {
+			bits_missing = X86_CR0_WP;
+			val |= bits_missing;
+			goto set_register;
+		}
+		/* Warn after we've set the missing bits. */
+		WARN_ONCE(bits_missing, "CR0 WP bit went missing!?\n");
+	}
+}
+EXPORT_SYMBOL(native_write_cr0);
+
+void native_write_cr4(unsigned long val)
+{
+	unsigned long bits_missing = 0;
+
+set_register:
+	asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits));
+
+	if (static_branch_likely(&cr_pinning)) {
+		if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) {
+			bits_missing = ~val & cr4_pinned_bits;
+			val |= bits_missing;
+			goto set_register;
+		}
+		/* Warn after we've set the missing bits. */
+		WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n",
+			  bits_missing);
+	}
+}
+EXPORT_SYMBOL(native_write_cr4);
+
+void cr4_init(void)
+{
+	unsigned long cr4 = __read_cr4();
+
+	if (boot_cpu_has(X86_FEATURE_PCID))
+		cr4 |= X86_CR4_PCIDE;
+	if (static_branch_likely(&cr_pinning))
+		cr4 |= cr4_pinned_bits;
+
+	__write_cr4(cr4);
+
+	/* Initialize cr4 shadow for this CPU. */
+	this_cpu_write(cpu_tlbstate.cr4, cr4);
+}
+
+/*
+ * Once CPU feature detection is finished (and boot params have been
+ * parsed), record any of the sensitive CR bits that are set, and
+ * enable CR pinning.
+ */
+static void __init setup_cr_pinning(void)
+{
+	unsigned long mask;
+
+	mask = (X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP);
+	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & mask;
+	static_key_enable(&cr_pinning.key);
+}
+
 /*
  * Protection Keys are not available in 32-bit mode.
  */
@@ -801,6 +872,30 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
 	}
 }
 
+static void init_cqm(struct cpuinfo_x86 *c)
+{
+	if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
+		c->x86_cache_max_rmid  = -1;
+		c->x86_cache_occ_scale = -1;
+		return;
+	}
+
+	/* will be overridden if occupancy monitoring exists */
+	c->x86_cache_max_rmid = cpuid_ebx(0xf);
+
+	if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) ||
+	    cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) ||
+	    cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) {
+		u32 eax, ebx, ecx, edx;
+
+		/* QoS sub-leaf, EAX=0Fh, ECX=1 */
+		cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
+
+		c->x86_cache_max_rmid  = ecx;
+		c->x86_cache_occ_scale = ebx;
+	}
+}
+
 void get_cpu_cap(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
@@ -823,6 +918,12 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_7_0_EBX] = ebx;
 		c->x86_capability[CPUID_7_ECX] = ecx;
 		c->x86_capability[CPUID_7_EDX] = edx;
+
+		/* Check valid sub-leaf index before accessing it */
+		if (eax >= 1) {
+			cpuid_count(0x00000007, 1, &eax, &ebx, &ecx, &edx);
+			c->x86_capability[CPUID_7_1_EAX] = eax;
+		}
 	}
 
 	/* Extended state features: level 0x0000000d */
@@ -832,33 +933,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_D_1_EAX] = eax;
 	}
 
-	/* Additional Intel-defined flags: level 0x0000000F */
-	if (c->cpuid_level >= 0x0000000F) {
-
-		/* QoS sub-leaf, EAX=0Fh, ECX=0 */
-		cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
-		c->x86_capability[CPUID_F_0_EDX] = edx;
-
-		if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
-			/* will be overridden if occupancy monitoring exists */
-			c->x86_cache_max_rmid = ebx;
-
-			/* QoS sub-leaf, EAX=0Fh, ECX=1 */
-			cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
-			c->x86_capability[CPUID_F_1_EDX] = edx;
-
-			if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) ||
-			      ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) ||
-			       (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) {
-				c->x86_cache_max_rmid = ecx;
-				c->x86_cache_occ_scale = ebx;
-			}
-		} else {
-			c->x86_cache_max_rmid = -1;
-			c->x86_cache_occ_scale = -1;
-		}
-	}
-
 	/* AMD-defined flags: level 0x80000001 */
 	eax = cpuid_eax(0x80000000);
 	c->extended_cpuid_level = eax;
@@ -889,6 +963,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 
 	init_scattered_cpuid_features(c);
 	init_speculation_control(c);
+	init_cqm(c);
 
 	/*
 	 * Clear/Set all flags overridden by options, after probe.
@@ -947,6 +1022,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #define NO_L1TF		BIT(3)
 #define NO_MDS		BIT(4)
 #define MSBDS_ONLY	BIT(5)
+#define NO_SWAPGS	BIT(6)
 
 #define VULNWL(_vendor, _family, _model, _whitelist)	\
 	{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
@@ -973,30 +1049,38 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL_INTEL(ATOM_BONNELL,		NO_SPECULATION),
 	VULNWL_INTEL(ATOM_BONNELL_MID,		NO_SPECULATION),
 
-	VULNWL_INTEL(ATOM_SILVERMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY),
-	VULNWL_INTEL(ATOM_SILVERMONT_X,		NO_SSB | NO_L1TF | MSBDS_ONLY),
-	VULNWL_INTEL(ATOM_SILVERMONT_MID,	NO_SSB | NO_L1TF | MSBDS_ONLY),
-	VULNWL_INTEL(ATOM_AIRMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY),
-	VULNWL_INTEL(XEON_PHI_KNL,		NO_SSB | NO_L1TF | MSBDS_ONLY),
-	VULNWL_INTEL(XEON_PHI_KNM,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(ATOM_SILVERMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_SILVERMONT_X,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_SILVERMONT_MID,	NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_AIRMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(XEON_PHI_KNL,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(XEON_PHI_KNM,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
 
 	VULNWL_INTEL(CORE_YONAH,		NO_SSB),
 
-	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
 
-	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF),
-	VULNWL_INTEL(ATOM_GOLDMONT_X,		NO_MDS | NO_L1TF),
-	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF),
+	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_GOLDMONT_X,		NO_MDS | NO_L1TF | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS),
+
+	/*
+	 * Technically, swapgs isn't serializing on AMD (despite it previously
+	 * being documented as such in the APM).  But according to AMD, %gs is
+	 * updated non-speculatively, and the issuing of %gs-relative memory
+	 * operands will be blocked until the %gs update completes, which is
+	 * good enough for our purposes.
+	 */
 
 	/* AMD Family 0xf - 0x12 */
-	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
-	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
-	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
-	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
 
 	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
-	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS),
-	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS),
+	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
 	{}
 };
 
@@ -1033,6 +1117,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 			setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
 	}
 
+	if (!cpu_matches(NO_SWAPGS))
+		setup_force_cpu_bug(X86_BUG_SWAPGS);
+
 	if (cpu_matches(NO_MELTDOWN))
 		return;
 
@@ -1299,6 +1386,7 @@ static void validate_apic_and_package_id(struct cpuinfo_x86 *c)
 		       cpu, apicid, c->initial_apicid);
 	}
 	BUG_ON(topology_update_package_map(c->phys_proc_id, cpu));
+	BUG_ON(topology_update_die_map(c->cpu_die_id, cpu));
 #else
 	c->logical_proc_id = 0;
 #endif
@@ -1464,6 +1552,7 @@ void __init identify_boot_cpu(void)
 	enable_sep_cpu();
 #endif
 	cpu_detect_tlb(&boot_cpu_data);
+	setup_cr_pinning();
 }
 
 void identify_secondary_cpu(struct cpuinfo_x86 *c)
@@ -1698,12 +1787,6 @@ void cpu_init(void)
 
 	wait_for_master_cpu(cpu);
 
-	/*
-	 * Initialize the CR4 shadow before doing anything that could
-	 * try to read it.
-	 */
-	cr4_init_shadow();
-
 	if (cpu)
 		load_ucode_ap();
 
@@ -1798,12 +1881,6 @@ void cpu_init(void)
 
 	wait_for_master_cpu(cpu);
 
-	/*
-	 * Initialize the CR4 shadow before doing anything that could
-	 * try to read it.
-	 */
-	cr4_init_shadow();
-
 	show_ucode_info_early();
 
 	pr_info("Initializing CPU#%d\n", cpu);