Merge branch 'x86/entry' into ras/core

to fixup conflicts in arch/x86/kernel/cpu/mce/core.c so MCE specific follow
up patches can be applied without creating a horrible merge conflict
afterwards.

25 files changed, 501 insertions, 221 deletions

diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c
index 676022e71791..1da9b1c9a2db 100644
--- a/arch/x86/kernel/cpu/acrn.c
+++ b/arch/x86/kernel/cpu/acrn.c
@@ -10,10 +10,10 @@
  */
 
 #include <linux/interrupt.h>
-#include <asm/acrn.h>
 #include <asm/apic.h>
 #include <asm/desc.h>
 #include <asm/hypervisor.h>
+#include <asm/idtentry.h>
 #include <asm/irq_regs.h>
 
 static uint32_t __init acrn_detect(void)
@@ -24,7 +24,7 @@ static uint32_t __init acrn_detect(void)
 static void __init acrn_init_platform(void)
 {
 	/* Setup the IDT for ACRN hypervisor callback */
-	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, acrn_hv_callback_vector);
+	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_acrn_hv_callback);
 }
 
 static bool acrn_x2apic_available(void)
@@ -39,7 +39,7 @@ static bool acrn_x2apic_available(void)
 
 static void (*acrn_intr_handler)(void);
 
-__visible void __irq_entry acrn_hv_vector_handler(struct pt_regs *regs)
+DEFINE_IDTENTRY_SYSVEC(sysvec_acrn_hv_callback)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
@@ -50,13 +50,12 @@ __visible void __irq_entry acrn_hv_vector_handler(struct pt_regs *regs)
 	 * will block the interrupt whose vector is lower than
 	 * HYPERVISOR_CALLBACK_VECTOR.
 	 */
-	entering_ack_irq();
+	ack_APIC_irq();
 	inc_irq_stat(irq_hv_callback_count);
 
 	if (acrn_intr_handler)
 		acrn_intr_handler();
 
-	exiting_irq();
 	set_irq_regs(old_regs);
 }
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 547ad7bbf0e0..d4806eac9325 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -18,6 +18,7 @@
 #include <asm/pci-direct.h>
 #include <asm/delay.h>
 #include <asm/debugreg.h>
+#include <asm/resctrl.h>
 
 #ifdef CONFIG_X86_64
 # include <asm/mmconfig.h>
@@ -597,6 +598,8 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 			x86_amd_ls_cfg_ssbd_mask = 1ULL << bit;
 		}
 	}
+
+	resctrl_cpu_detect(c);
 }
 
 static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
@@ -1142,8 +1145,7 @@ static const int amd_erratum_383[] =
 
 /* #1054: Instructions Retired Performance Counter May Be Inaccurate */
 static const int amd_erratum_1054[] =
-	AMD_OSVW_ERRATUM(0, AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
-
+	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
 
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 {
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ed54b3b21c39..b6f887be440c 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -15,6 +15,7 @@
 #include <linux/nospec.h>
 #include <linux/prctl.h>
 #include <linux/sched/smt.h>
+#include <linux/pgtable.h>
 
 #include <asm/spec-ctrl.h>
 #include <asm/cmdline.h>
@@ -26,7 +27,6 @@
 #include <asm/vmx.h>
 #include <asm/paravirt.h>
 #include <asm/alternative.h>
-#include <asm/pgtable.h>
 #include <asm/set_memory.h>
 #include <asm/intel-family.h>
 #include <asm/e820/api.h>
@@ -41,6 +41,7 @@ static void __init l1tf_select_mitigation(void);
 static void __init mds_select_mitigation(void);
 static void __init mds_print_mitigation(void);
 static void __init taa_select_mitigation(void);
+static void __init srbds_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR that always has to be preserved. */
 u64 x86_spec_ctrl_base;
@@ -108,6 +109,7 @@ void __init check_bugs(void)
 	l1tf_select_mitigation();
 	mds_select_mitigation();
 	taa_select_mitigation();
+	srbds_select_mitigation();
 
 	/*
 	 * As MDS and TAA mitigations are inter-related, print MDS
@@ -398,6 +400,97 @@ static int __init tsx_async_abort_parse_cmdline(char *str)
 early_param("tsx_async_abort", tsx_async_abort_parse_cmdline);
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"SRBDS: " fmt
+
+enum srbds_mitigations {
+	SRBDS_MITIGATION_OFF,
+	SRBDS_MITIGATION_UCODE_NEEDED,
+	SRBDS_MITIGATION_FULL,
+	SRBDS_MITIGATION_TSX_OFF,
+	SRBDS_MITIGATION_HYPERVISOR,
+};
+
+static enum srbds_mitigations srbds_mitigation __ro_after_init = SRBDS_MITIGATION_FULL;
+
+static const char * const srbds_strings[] = {
+	[SRBDS_MITIGATION_OFF]		= "Vulnerable",
+	[SRBDS_MITIGATION_UCODE_NEEDED]	= "Vulnerable: No microcode",
+	[SRBDS_MITIGATION_FULL]		= "Mitigation: Microcode",
+	[SRBDS_MITIGATION_TSX_OFF]	= "Mitigation: TSX disabled",
+	[SRBDS_MITIGATION_HYPERVISOR]	= "Unknown: Dependent on hypervisor status",
+};
+
+static bool srbds_off;
+
+void update_srbds_msr(void)
+{
+	u64 mcu_ctrl;
+
+	if (!boot_cpu_has_bug(X86_BUG_SRBDS))
+		return;
+
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return;
+
+	if (srbds_mitigation == SRBDS_MITIGATION_UCODE_NEEDED)
+		return;
+
+	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+
+	switch (srbds_mitigation) {
+	case SRBDS_MITIGATION_OFF:
+	case SRBDS_MITIGATION_TSX_OFF:
+		mcu_ctrl |= RNGDS_MITG_DIS;
+		break;
+	case SRBDS_MITIGATION_FULL:
+		mcu_ctrl &= ~RNGDS_MITG_DIS;
+		break;
+	default:
+		break;
+	}
+
+	wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+}
+
+static void __init srbds_select_mitigation(void)
+{
+	u64 ia32_cap;
+
+	if (!boot_cpu_has_bug(X86_BUG_SRBDS))
+		return;
+
+	/*
+	 * Check to see if this is one of the MDS_NO systems supporting
+	 * TSX that are only exposed to SRBDS when TSX is enabled.
+	 */
+	ia32_cap = x86_read_arch_cap_msr();
+	if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM))
+		srbds_mitigation = SRBDS_MITIGATION_TSX_OFF;
+	else if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR;
+	else if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL))
+		srbds_mitigation = SRBDS_MITIGATION_UCODE_NEEDED;
+	else if (cpu_mitigations_off() || srbds_off)
+		srbds_mitigation = SRBDS_MITIGATION_OFF;
+
+	update_srbds_msr();
+	pr_info("%s\n", srbds_strings[srbds_mitigation]);
+}
+
+static int __init srbds_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!boot_cpu_has_bug(X86_BUG_SRBDS))
+		return 0;
+
+	srbds_off = !strcmp(str, "off");
+	return 0;
+}
+early_param("srbds", srbds_parse_cmdline);
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V1 : " fmt
 
 enum spectre_v1_mitigation {
@@ -1528,6 +1621,11 @@ static char *ibpb_state(void)
 	return "";
 }
 
+static ssize_t srbds_show_state(char *buf)
+{
+	return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]);
+}
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -1572,6 +1670,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_ITLB_MULTIHIT:
 		return itlb_multihit_show_state(buf);
 
+	case X86_BUG_SRBDS:
+		return srbds_show_state(buf);
+
 	default:
 		break;
 	}
@@ -1618,4 +1719,9 @@ ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT);
 }
+
+ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index bed0cb83fe24..043d93cdcaad 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -21,6 +21,7 @@
 #include <linux/smp.h>
 #include <linux/io.h>
 #include <linux/syscore_ops.h>
+#include <linux/pgtable.h>
 
 #include <asm/stackprotector.h>
 #include <asm/perf_event.h>
@@ -35,7 +36,6 @@
 #include <asm/vsyscall.h>
 #include <linux/topology.h>
 #include <linux/cpumask.h>
-#include <asm/pgtable.h>
 #include <linux/atomic.h>
 #include <asm/proto.h>
 #include <asm/setup.h>
@@ -387,7 +387,30 @@ set_register:
 			  bits_missing);
 	}
 }
-EXPORT_SYMBOL(native_write_cr4);
+#if IS_MODULE(CONFIG_LKDTM)
+EXPORT_SYMBOL_GPL(native_write_cr4);
+#endif
+
+void cr4_update_irqsoff(unsigned long set, unsigned long clear)
+{
+	unsigned long newval, cr4 = this_cpu_read(cpu_tlbstate.cr4);
+
+	lockdep_assert_irqs_disabled();
+
+	newval = (cr4 & ~clear) | set;
+	if (newval != cr4) {
+		this_cpu_write(cpu_tlbstate.cr4, newval);
+		__write_cr4(newval);
+	}
+}
+EXPORT_SYMBOL(cr4_update_irqsoff);
+
+/* Read the CR4 shadow. */
+unsigned long cr4_read_shadow(void)
+{
+	return this_cpu_read(cpu_tlbstate.cr4);
+}
+EXPORT_SYMBOL_GPL(cr4_read_shadow);
 
 void cr4_init(void)
 {
@@ -854,30 +877,6 @@ 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;
@@ -945,7 +944,6 @@ 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.
@@ -1075,9 +1073,30 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	{}
 };
 
-static bool __init cpu_matches(unsigned long which)
+#define VULNBL_INTEL_STEPPINGS(model, steppings, issues)		   \
+	X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6,		   \
+					    INTEL_FAM6_##model, steppings, \
+					    X86_FEATURE_ANY, issues)
+
+#define SRBDS		BIT(0)
+
+static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
+	VULNBL_INTEL_STEPPINGS(IVYBRIDGE,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(HASWELL,		X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(HASWELL_L,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(HASWELL_G,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(BROADWELL_G,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(BROADWELL,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE_L,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE,		X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE_L,	X86_STEPPINGS(0x0, 0xC),	SRBDS),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE,	X86_STEPPINGS(0x0, 0xD),	SRBDS),
+	{}
+};
+
+static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long which)
 {
-	const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist);
+	const struct x86_cpu_id *m = x86_match_cpu(table);
 
 	return m && !!(m->driver_data & which);
 }
@@ -1097,31 +1116,34 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	u64 ia32_cap = x86_read_arch_cap_msr();
 
 	/* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */
-	if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO))
+	if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) &&
+	    !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO))
 		setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT);
 
-	if (cpu_matches(NO_SPECULATION))
+	if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
 
-	if (!cpu_matches(NO_SPECTRE_V2))
+	if (!cpu_matches(cpu_vuln_whitelist, NO_SPECTRE_V2))
 		setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
 
-	if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) &&
+	if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) &&
+	    !(ia32_cap & ARCH_CAP_SSB_NO) &&
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
 
 	if (ia32_cap & ARCH_CAP_IBRS_ALL)
 		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
 
-	if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) {
+	if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) &&
+	    !(ia32_cap & ARCH_CAP_MDS_NO)) {
 		setup_force_cpu_bug(X86_BUG_MDS);
-		if (cpu_matches(MSBDS_ONLY))
+		if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY))
 			setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
 	}
 
-	if (!cpu_matches(NO_SWAPGS))
+	if (!cpu_matches(cpu_vuln_whitelist, NO_SWAPGS))
 		setup_force_cpu_bug(X86_BUG_SWAPGS);
 
 	/*
@@ -1139,7 +1161,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	     (ia32_cap & ARCH_CAP_TSX_CTRL_MSR)))
 		setup_force_cpu_bug(X86_BUG_TAA);
 
-	if (cpu_matches(NO_MELTDOWN))
+	/*
+	 * SRBDS affects CPUs which support RDRAND or RDSEED and are listed
+	 * in the vulnerability blacklist.
+	 */
+	if ((cpu_has(c, X86_FEATURE_RDRAND) ||
+	     cpu_has(c, X86_FEATURE_RDSEED)) &&
+	    cpu_matches(cpu_vuln_blacklist, SRBDS))
+		    setup_force_cpu_bug(X86_BUG_SRBDS);
+
+	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 
 	/* Rogue Data Cache Load? No! */
@@ -1148,7 +1179,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 
 	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 
-	if (cpu_matches(NO_L1TF))
+	if (cpu_matches(cpu_vuln_whitelist, NO_L1TF))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_L1TF);
@@ -1377,20 +1408,6 @@ static void generic_identify(struct cpuinfo_x86 *c)
 #endif
 }
 
-static void x86_init_cache_qos(struct cpuinfo_x86 *c)
-{
-	/*
-	 * The heavy lifting of max_rmid and cache_occ_scale are handled
-	 * in get_cpu_cap().  Here we just set the max_rmid for the boot_cpu
-	 * in case CQM bits really aren't there in this CPU.
-	 */
-	if (c != &boot_cpu_data) {
-		boot_cpu_data.x86_cache_max_rmid =
-			min(boot_cpu_data.x86_cache_max_rmid,
-			    c->x86_cache_max_rmid);
-	}
-}
-
 /*
  * Validate that ACPI/mptables have the same information about the
  * effective APIC id and update the package map.
@@ -1503,7 +1520,6 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 #endif
 
 	x86_init_rdrand(c);
-	x86_init_cache_qos(c);
 	setup_pku(c);
 
 	/*
@@ -1591,6 +1607,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 	mtrr_ap_init();
 	validate_apic_and_package_id(c);
 	x86_spec_ctrl_setup_ap();
+	update_srbds_msr();
 }
 
 static __init int setup_noclflush(char *arg)
@@ -1689,25 +1706,6 @@ void syscall_init(void)
 	       X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
 }
 
-DEFINE_PER_CPU(int, debug_stack_usage);
-DEFINE_PER_CPU(u32, debug_idt_ctr);
-
-void debug_stack_set_zero(void)
-{
-	this_cpu_inc(debug_idt_ctr);
-	load_current_idt();
-}
-NOKPROBE_SYMBOL(debug_stack_set_zero);
-
-void debug_stack_reset(void)
-{
-	if (WARN_ON(!this_cpu_read(debug_idt_ctr)))
-		return;
-	if (this_cpu_dec_return(debug_idt_ctr) == 0)
-		load_current_idt();
-}
-NOKPROBE_SYMBOL(debug_stack_reset);
-
 #else	/* CONFIG_X86_64 */
 
 DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 37fdefd14f28..fb538fccd24c 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -77,6 +77,7 @@ extern void detect_ht(struct cpuinfo_x86 *c);
 unsigned int aperfmperf_get_khz(int cpu);
 
 extern void x86_spec_ctrl_setup_ap(void);
+extern void update_srbds_msr(void);
 
 extern u64 x86_read_arch_cap_msr(void);
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index bf08d4508ecb..63926c94eb5f 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
+#include <linux/pgtable.h>
 
 #include <linux/string.h>
 #include <linux/bitops.h>
@@ -11,7 +12,6 @@
 #include <linux/uaccess.h>
 
 #include <asm/cpufeature.h>
-#include <asm/pgtable.h>
 #include <asm/msr.h>
 #include <asm/bugs.h>
 #include <asm/cpu.h>
@@ -22,6 +22,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/cmdline.h>
 #include <asm/traps.h>
+#include <asm/resctrl.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
@@ -322,6 +323,11 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		detect_ht_early(c);
 }
 
+static void bsp_init_intel(struct cpuinfo_x86 *c)
+{
+	resctrl_cpu_detect(c);
+}
+
 #ifdef CONFIG_X86_32
 /*
  *	Early probe support logic for ppro memory erratum #50
@@ -961,6 +967,7 @@ static const struct cpu_dev intel_cpu_dev = {
 #endif
 	.c_detect_tlb	= intel_detect_tlb,
 	.c_early_init   = early_init_intel,
+	.c_bsp_init	= bsp_init_intel,
 	.c_init		= init_intel,
 	.c_x86_vendor	= X86_VENDOR_INTEL,
 };
@@ -1119,35 +1126,53 @@ void switch_to_sld(unsigned long tifn)
 	sld_update_msr(!(tifn & _TIF_SLD));
 }
 
-#define SPLIT_LOCK_CPU(model) {X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY}
-
 /*
- * The following processors have the split lock detection feature. But
- * since they don't have the IA32_CORE_CAPABILITIES MSR, the feature cannot
- * be enumerated. Enable it by family and model matching on these
- * processors.
+ * Bits in the IA32_CORE_CAPABILITIES are not architectural, so they should
+ * only be trusted if it is confirmed that a CPU model implements a
+ * specific feature at a particular bit position.
+ *
+ * The possible driver data field values:
+ *
+ * - 0: CPU models that are known to have the per-core split-lock detection
+ *	feature even though they do not enumerate IA32_CORE_CAPABILITIES.
+ *
+ * - 1: CPU models which may enumerate IA32_CORE_CAPABILITIES and if so use
+ *      bit 5 to enumerate the per-core split-lock detection feature.
  */
 static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = {
-	SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_X),
-	SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_L),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		0),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		0),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	1),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	1),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	1),
 	{}
 };
 
 void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c)
 {
-	u64 ia32_core_caps = 0;
+	const struct x86_cpu_id *m;
+	u64 ia32_core_caps;
 
-	if (c->x86_vendor != X86_VENDOR_INTEL)
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return;
-	if (cpu_has(c, X86_FEATURE_CORE_CAPABILITIES)) {
-		/* Enumerate features reported in IA32_CORE_CAPABILITIES MSR. */
+
+	m = x86_match_cpu(split_lock_cpu_ids);
+	if (!m)
+		return;
+
+	switch (m->driver_data) {
+	case 0:
+		break;
+	case 1:
+		if (!cpu_has(c, X86_FEATURE_CORE_CAPABILITIES))
+			return;
 		rdmsrl(MSR_IA32_CORE_CAPS, ia32_core_caps);
-	} else if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
-		/* Enumerate split lock detection by family and model. */
-		if (x86_match_cpu(split_lock_cpu_ids))
-			ia32_core_caps |= MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT;
+		if (!(ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT))
+			return;
+		break;
+	default:
+		return;
 	}
 
-	if (ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT)
-		split_lock_setup();
+	split_lock_setup();
 }
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index d3482eb43ff3..ad6776081e60 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -39,13 +39,18 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
 	const struct x86_cpu_id *m;
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	for (m = match; m->vendor | m->family | m->model | m->feature; m++) {
+	for (m = match;
+	     m->vendor | m->family | m->model | m->steppings | m->feature;
+	     m++) {
 		if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor)
 			continue;
 		if (m->family != X86_FAMILY_ANY && c->x86 != m->family)
 			continue;
 		if (m->model != X86_MODEL_ANY && c->x86_model != m->model)
 			continue;
+		if (m->steppings != X86_STEPPING_ANY &&
+		    !(BIT(c->x86_stepping) & m->steppings))
+			continue;
 		if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature))
 			continue;
 		return m;
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index ea3cf714b7ad..99be063fcb1b 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -921,14 +921,13 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
 	mce_log(&m);
 }
 
-asmlinkage __visible void __irq_entry smp_deferred_error_interrupt(struct pt_regs *regs)
+DEFINE_IDTENTRY_SYSVEC(sysvec_deferred_error)
 {
-	entering_irq();
 	trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR);
 	inc_irq_stat(irq_deferred_error_count);
 	deferred_error_int_vector();
 	trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR);
-	exiting_ack_irq();
+	ack_APIC_irq();
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 02e1f165f148..30413325de22 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -42,6 +42,8 @@
 #include <linux/export.h>
 #include <linux/jump_label.h>
 #include <linux/set_memory.h>
+#include <linux/task_work.h>
+#include <linux/hardirq.h>
 
 #include <asm/intel-family.h>
 #include <asm/processor.h>
@@ -128,7 +130,7 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
 BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain);
 
 /* Do initial initialization of a struct mce */
-void mce_setup(struct mce *m)
+noinstr void mce_setup(struct mce *m)
 {
 	memset(m, 0, sizeof(struct mce));
 	m->cpu = m->extcpu = smp_processor_id();
@@ -138,12 +140,12 @@ void mce_setup(struct mce *m)
 	m->cpuid = cpuid_eax(1);
 	m->socketid = cpu_data(m->extcpu).phys_proc_id;
 	m->apicid = cpu_data(m->extcpu).initial_apicid;
-	rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap);
+	m->mcgcap = __rdmsr(MSR_IA32_MCG_CAP);
 
 	if (this_cpu_has(X86_FEATURE_INTEL_PPIN))
-		rdmsrl(MSR_PPIN, m->ppin);
+		m->ppin = __rdmsr(MSR_PPIN);
 	else if (this_cpu_has(X86_FEATURE_AMD_PPIN))
-		rdmsrl(MSR_AMD_PPIN, m->ppin);
+		m->ppin = __rdmsr(MSR_AMD_PPIN);
 
 	m->microcode = boot_cpu_data.microcode;
 }
@@ -1057,23 +1059,6 @@ static void mce_clear_state(unsigned long *toclear)
 	}
 }
 
-static int do_memory_failure(struct mce *m)
-{
-	int flags = MF_ACTION_REQUIRED;
-	int ret;
-
-	pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr);
-	if (!(m->mcgstatus & MCG_STATUS_RIPV))
-		flags |= MF_MUST_KILL;
-	ret = memory_failure(m->addr >> PAGE_SHIFT, flags);
-	if (ret)
-		pr_err("Memory error not recovered");
-	else
-		set_mce_nospec(m->addr >> PAGE_SHIFT);
-	return ret;
-}
-
-
 /*
  * Cases where we avoid rendezvous handler timeout:
  * 1) If this CPU is offline.
@@ -1086,13 +1071,15 @@ static int do_memory_failure(struct mce *m)
  * kdump kernel establishing a new #MC handler where a broadcasted MCE
  * might not get handled properly.
  */
-static bool __mc_check_crashing_cpu(int cpu)
+static noinstr bool mce_check_crashing_cpu(void)
 {
+	unsigned int cpu = smp_processor_id();
+
 	if (cpu_is_offline(cpu) ||
 	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
 		u64 mcgstatus;
 
-		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+		mcgstatus = __rdmsr(MSR_IA32_MCG_STATUS);
 
 		if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) {
 			if (mcgstatus & MCG_STATUS_LMCES)
@@ -1100,7 +1087,7 @@ static bool __mc_check_crashing_cpu(int cpu)
 		}
 
 		if (mcgstatus & MCG_STATUS_RIPV) {
-			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
+			__wrmsr(MSR_IA32_MCG_STATUS, 0, 0);
 			return true;
 		}
 	}
@@ -1175,6 +1162,29 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
 	*m = *final;
 }
 
+static void kill_me_now(struct callback_head *ch)
+{
+	force_sig(SIGBUS);
+}
+
+static void kill_me_maybe(struct callback_head *cb)
+{
+	struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me);
+	int flags = MF_ACTION_REQUIRED;
+
+	pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr);
+	if (!(p->mce_status & MCG_STATUS_RIPV))
+		flags |= MF_MUST_KILL;
+
+	if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags)) {
+		set_mce_nospec(p->mce_addr >> PAGE_SHIFT);
+		return;
+	}
+
+	pr_err("Memory error not recovered");
+	kill_me_now(cb);
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -1193,12 +1203,11 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
  * backing the user stack, tracing that reads the user stack will cause
  * potentially infinite recursion.
  */
-void notrace do_machine_check(struct pt_regs *regs, long error_code)
+void noinstr do_machine_check(struct pt_regs *regs)
 {
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
 	struct mca_config *cfg = &mca_cfg;
-	int cpu = smp_processor_id();
 	struct mce m, *final;
 	char *msg = NULL;
 	int worst = 0;
@@ -1227,11 +1236,6 @@ void notrace do_machine_check(struct pt_regs *regs, long error_code)
 	 */
 	int lmce = 1;
 
-	if (__mc_check_crashing_cpu(cpu))
-		return;
-
-	ist_enter(regs);
-
 	this_cpu_inc(mce_exception_count);
 
 	mce_gather_info(&m, regs);
@@ -1319,17 +1323,19 @@ void notrace do_machine_check(struct pt_regs *regs, long error_code)
 	sync_core();
 
 	if (worst != MCE_AR_SEVERITY && !kill_it)
-		goto out_ist;
+		return;
 
 	/* Fault was in user mode and we need to take some action */
 	if ((m.cs & 3) == 3) {
-		ist_begin_non_atomic(regs);
-		local_irq_enable();
-
-		if (kill_it || do_memory_failure(&m))
-			force_sig(SIGBUS);
-		local_irq_disable();
-		ist_end_non_atomic();
+		/* If this triggers there is no way to recover. Die hard. */
+		BUG_ON(!on_thread_stack() || !user_mode(regs));
+
+		current->mce_addr = m.addr;
+		current->mce_status = m.mcgstatus;
+		current->mce_kill_me.func = kill_me_maybe;
+		if (kill_it)
+			current->mce_kill_me.func = kill_me_now;
+		task_work_add(current, &current->mce_kill_me, true);
 	} else {
 		/*
 		 * Handle an MCE which has happened in kernel space but from
@@ -1341,16 +1347,12 @@ void notrace do_machine_check(struct pt_regs *regs, long error_code)
 		 * proper one.
 		 */
 		if (m.kflags & MCE_IN_KERNEL_RECOV) {
-			if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0))
+			if (!fixup_exception(regs, X86_TRAP_MC, 0, 0))
 				mce_panic("Failed kernel mode recovery", &m, msg);
 		}
 	}
-
-out_ist:
-	ist_exit(regs);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
-NOKPROBE_SYMBOL(do_machine_check);
 
 #ifndef CONFIG_MEMORY_FAILURE
 int memory_failure(unsigned long pfn, int flags)
@@ -1876,21 +1878,84 @@ bool filter_mce(struct mce *m)
 }
 
 /* Handle unconfigured int18 (should never happen) */
-static void unexpected_machine_check(struct pt_regs *regs, long error_code)
+static noinstr void unexpected_machine_check(struct pt_regs *regs)
 {
+	instrumentation_begin();
 	pr_err("CPU#%d: Unexpected int18 (Machine Check)\n",
 	       smp_processor_id());
+	instrumentation_end();
 }
 
 /* Call the installed machine check handler for this CPU setup. */
-void (*machine_check_vector)(struct pt_regs *, long error_code) =
-						unexpected_machine_check;
+void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check;
+
+static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
+{
+	/*
+	 * Only required when from kernel mode. See
+	 * mce_check_crashing_cpu() for details.
+	 */
+	if (machine_check_vector == do_machine_check &&
+	    mce_check_crashing_cpu())
+		return;
+
+	nmi_enter();
+	/*
+	 * The call targets are marked noinstr, but objtool can't figure
+	 * that out because it's an indirect call. Annotate it.
+	 */
+	instrumentation_begin();
+	trace_hardirqs_off_finish();
+	machine_check_vector(regs);
+	if (regs->flags & X86_EFLAGS_IF)
+		trace_hardirqs_on_prepare();
+	instrumentation_end();
+	nmi_exit();
+}
+
+static __always_inline void exc_machine_check_user(struct pt_regs *regs)
+{
+	idtentry_enter_user(regs);
+	instrumentation_begin();
+	machine_check_vector(regs);
+	instrumentation_end();
+	idtentry_exit_user(regs);
+}
 
-dotraplinkage notrace void do_mce(struct pt_regs *regs, long error_code)
+#ifdef CONFIG_X86_64
+/* MCE hit kernel mode */
+DEFINE_IDTENTRY_MCE(exc_machine_check)
 {
-	machine_check_vector(regs, error_code);
+	unsigned long dr7;
+
+	dr7 = local_db_save();
+	exc_machine_check_kernel(regs);
+	local_db_restore(dr7);
+}
+
+/* The user mode variant. */
+DEFINE_IDTENTRY_MCE_USER(exc_machine_check)
+{
+	unsigned long dr7;
+
+	dr7 = local_db_save();
+	exc_machine_check_user(regs);
+	local_db_restore(dr7);
 }
-NOKPROBE_SYMBOL(do_mce);
+#else
+/* 32bit unified entry point */
+DEFINE_IDTENTRY_MCE(exc_machine_check)
+{
+	unsigned long dr7;
+
+	dr7 = local_db_save();
+	if (user_mode(regs))
+		exc_machine_check_user(regs);
+	else
+		exc_machine_check_kernel(regs);
+	local_db_restore(dr7);
+}
+#endif
 
 /*
  * Called for each booted CPU to set up machine checks.
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 3413b41b8d55..0593b192eb8f 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -146,9 +146,9 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs)
 		regs.cs = m->cs;
 		pregs = &regs;
 	}
-	/* in mcheck exeception handler, irq will be disabled */
+	/* do_machine_check() expects interrupts disabled -- at least */
 	local_irq_save(flags);
-	do_machine_check(pregs, 0);
+	do_machine_check(pregs);
 	local_irq_restore(flags);
 	m->finished = 0;
 }
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 55f5c7b755f2..6473070b5da4 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -9,7 +9,7 @@
 #include <asm/mce.h>
 
 /* Pointer to the installed machine check handler for this CPU setup. */
-extern void (*machine_check_vector)(struct pt_regs *, long error_code);
+extern void (*machine_check_vector)(struct pt_regs *);
 
 enum severity_level {
 	MCE_NO_SEVERITY,
diff --git a/arch/x86/kernel/cpu/mce/p5.c b/arch/x86/kernel/cpu/mce/p5.c
index 4ae6df556526..19e90cae8e97 100644
--- a/arch/x86/kernel/cpu/mce/p5.c
+++ b/arch/x86/kernel/cpu/mce/p5.c
@@ -7,6 +7,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/smp.h>
+#include <linux/hardirq.h>
 
 #include <asm/processor.h>
 #include <asm/traps.h>
@@ -20,12 +21,11 @@
 int mce_p5_enabled __read_mostly;
 
 /* Machine check handler for Pentium class Intel CPUs: */
-static void pentium_machine_check(struct pt_regs *regs, long error_code)
+static noinstr void pentium_machine_check(struct pt_regs *regs)
 {
 	u32 loaddr, hi, lotype;
 
-	ist_enter(regs);
-
+	instrumentation_begin();
 	rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi);
 	rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi);
 
@@ -38,8 +38,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code)
 	}
 
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
-
-	ist_exit(regs);
+	instrumentation_end();
 }
 
 /* Set up machine check reporting for processors with Intel style MCE: */
diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c
index f36dc0742085..a7cd2d203ced 100644
--- a/arch/x86/kernel/cpu/mce/therm_throt.c
+++ b/arch/x86/kernel/cpu/mce/therm_throt.c
@@ -614,14 +614,13 @@ static void unexpected_thermal_interrupt(void)
 
 static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
 
-asmlinkage __visible void __irq_entry smp_thermal_interrupt(struct pt_regs *regs)
+DEFINE_IDTENTRY_SYSVEC(sysvec_thermal)
 {
-	entering_irq();
 	trace_thermal_apic_entry(THERMAL_APIC_VECTOR);
 	inc_irq_stat(irq_thermal_count);
 	smp_thermal_vector();
 	trace_thermal_apic_exit(THERMAL_APIC_VECTOR);
-	exiting_ack_irq();
+	ack_APIC_irq();
 }
 
 /* Thermal monitoring depends on APIC, ACPI and clock modulation */
diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index 28812cc15300..6a059a035021 100644
--- a/arch/x86/kernel/cpu/mce/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -21,12 +21,11 @@ static void default_threshold_interrupt(void)
 
 void (*mce_threshold_vector)(void) = default_threshold_interrupt;
 
-asmlinkage __visible void __irq_entry smp_threshold_interrupt(struct pt_regs *regs)
+DEFINE_IDTENTRY_SYSVEC(sysvec_threshold)
 {
-	entering_irq();
 	trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR);
 	inc_irq_stat(irq_threshold_count);
 	mce_threshold_vector();
 	trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR);
-	exiting_ack_irq();
+	ack_APIC_irq();
 }
diff --git a/arch/x86/kernel/cpu/mce/winchip.c b/arch/x86/kernel/cpu/mce/winchip.c
index a30ea13cccc2..9c9f0abd2d7f 100644
--- a/arch/x86/kernel/cpu/mce/winchip.c
+++ b/arch/x86/kernel/cpu/mce/winchip.c
@@ -6,6 +6,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <linux/hardirq.h>
 
 #include <asm/processor.h>
 #include <asm/traps.h>
@@ -16,14 +17,12 @@
 #include "internal.h"
 
 /* Machine check handler for WinChip C6: */
-static void winchip_machine_check(struct pt_regs *regs, long error_code)
+static noinstr void winchip_machine_check(struct pt_regs *regs)
 {
-	ist_enter(regs);
-
+	instrumentation_begin();
 	pr_emerg("CPU0: Machine Check Exception.\n");
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
-
-	ist_exit(regs);
+	instrumentation_end();
 }
 
 /* Set up machine check reporting on the Winchip C6 series */
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 7019d4b2df0c..baec68b7e010 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -545,8 +545,7 @@ static int __wait_for_cpus(atomic_t *t, long long timeout)
 /*
  * Returns:
  * < 0 - on error
- *   0 - no update done
- *   1 - microcode was updated
+ *   0 - success (no update done or microcode was updated)
  */
 static int __reload_late(void *info)
 {
@@ -573,11 +572,11 @@ static int __reload_late(void *info)
 	else
 		goto wait_for_siblings;
 
-	if (err > UCODE_NFOUND) {
-		pr_warn("Error reloading microcode on CPU %d\n", cpu);
+	if (err >= UCODE_NFOUND) {
+		if (err == UCODE_ERROR)
+			pr_warn("Error reloading microcode on CPU %d\n", cpu);
+
 		ret = -1;
-	} else if (err == UCODE_UPDATED || err == UCODE_OK) {
-		ret = 1;
 	}
 
 wait_for_siblings:
@@ -608,7 +607,7 @@ static int microcode_reload_late(void)
 	atomic_set(&late_cpus_out, 0);
 
 	ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
-	if (ret > 0)
+	if (ret == 0)
 		microcode_check();
 
 	pr_info("Reload completed, microcode revision: 0x%x\n", boot_cpu_data.microcode);
@@ -649,7 +648,7 @@ static ssize_t reload_store(struct device *dev,
 put:
 	put_online_cpus();
 
-	if (ret >= 0)
+	if (ret == 0)
 		ret = size;
 
 	return ret;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index caa032ce3fe3..af94f05a5c66 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -23,6 +23,7 @@
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 #include <asm/desc.h>
+#include <asm/idtentry.h>
 #include <asm/irq_regs.h>
 #include <asm/i8259.h>
 #include <asm/apic.h>
@@ -40,11 +41,10 @@ static void (*hv_stimer0_handler)(void);
 static void (*hv_kexec_handler)(void);
 static void (*hv_crash_handler)(struct pt_regs *regs);
 
-__visible void __irq_entry hyperv_vector_handler(struct pt_regs *regs)
+DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	entering_irq();
 	inc_irq_stat(irq_hv_callback_count);
 	if (vmbus_handler)
 		vmbus_handler();
@@ -52,7 +52,6 @@ __visible void __irq_entry hyperv_vector_handler(struct pt_regs *regs)
 	if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)
 		ack_APIC_irq();
 
-	exiting_irq();
 	set_irq_regs(old_regs);
 }
 
@@ -73,19 +72,16 @@ EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq);
  * Routines to do per-architecture handling of stimer0
  * interrupts when in Direct Mode
  */
-
-__visible void __irq_entry hv_stimer0_vector_handler(struct pt_regs *regs)
+DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_stimer0)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	entering_irq();
 	inc_irq_stat(hyperv_stimer0_count);
 	if (hv_stimer0_handler)
 		hv_stimer0_handler();
 	add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0);
 	ack_APIC_irq();
 
-	exiting_irq();
 	set_irq_regs(old_regs);
 }
 
@@ -227,8 +223,8 @@ static void __init ms_hyperv_init_platform(void)
 	ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.hints    = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
 
-	pr_info("Hyper-V: features 0x%x, hints 0x%x\n",
-		ms_hyperv.features, ms_hyperv.hints);
+	pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n",
+		ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features);
 
 	ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS);
 	ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS);
@@ -263,6 +259,16 @@ static void __init ms_hyperv_init_platform(void)
 			cpuid_eax(HYPERV_CPUID_NESTED_FEATURES);
 	}
 
+	/*
+	 * Hyper-V expects to get crash register data or kmsg when
+	 * crash enlightment is available and system crashes. Set
+	 * crash_kexec_post_notifiers to be true to make sure that
+	 * calling crash enlightment interface before running kdump
+	 * kernel.
+	 */
+	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE)
+		crash_kexec_post_notifiers = true;
+
 #ifdef CONFIG_X86_LOCAL_APIC
 	if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
 	    ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
@@ -321,17 +327,19 @@ static void __init ms_hyperv_init_platform(void)
 	x86_platform.apic_post_init = hyperv_init;
 	hyperv_setup_mmu_ops();
 	/* Setup the IDT for hypervisor callback */
-	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
+	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_hyperv_callback);
 
 	/* Setup the IDT for reenlightenment notifications */
-	if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT)
+	if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT) {
 		alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR,
-				hyperv_reenlightenment_vector);
+				asm_sysvec_hyperv_reenlightenment);
+	}
 
 	/* Setup the IDT for stimer0 */
-	if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE)
+	if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE) {
 		alloc_intr_gate(HYPERV_STIMER0_VECTOR,
-				hv_stimer0_callback_vector);
+				asm_sysvec_hyperv_stimer0);
+	}
 
 # ifdef CONFIG_SMP
 	smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu;
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 51b9190c628b..23ad8e953dfb 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -761,7 +761,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 
 	/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
 	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-	__flush_tlb();
+	flush_tlb_local();
 
 	/* Save MTRR state */
 	rdmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
@@ -778,7 +778,7 @@ static void post_set(void) __releases(set_atomicity_lock)
 {
 	/* Flush TLBs (no need to flush caches - they are disabled) */
 	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-	__flush_tlb();
+	flush_tlb_local();
 
 	/* Intel (P6) standard MTRRs */
 	mtrr_wrmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 9556930cd8c1..a5ee607a3b89 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -63,6 +63,10 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
 		case 15:
 			return msr - MSR_P4_BPU_PERFCTR0;
 		}
+		fallthrough;
+	case X86_VENDOR_ZHAOXIN:
+	case X86_VENDOR_CENTAUR:
+		return msr - MSR_ARCH_PERFMON_PERFCTR0;
 	}
 	return 0;
 }
@@ -92,6 +96,10 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
 		case 15:
 			return msr - MSR_P4_BSU_ESCR0;
 		}
+		fallthrough;
+	case X86_VENDOR_ZHAOXIN:
+	case X86_VENDOR_CENTAUR:
+		return msr - MSR_ARCH_PERFMON_EVENTSEL0;
 	}
 	return 0;
 
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 89049b343c7a..12f967c6b603 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -22,7 +22,7 @@
 #include <linux/cpuhotplug.h>
 
 #include <asm/intel-family.h>
-#include <asm/resctrl_sched.h>
+#include <asm/resctrl.h>
 #include "internal.h"
 
 /* Mutex to protect rdtgroup access. */
@@ -578,6 +578,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 	d->id = id;
 	cpumask_set_cpu(cpu, &d->cpu_mask);
 
+	rdt_domain_reconfigure_cdp(r);
+
 	if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
 		kfree(d);
 		return;
@@ -956,6 +958,36 @@ static __init void rdt_init_res_defs(void)
 
 static enum cpuhp_state rdt_online;
 
+/* Runs once on the BSP during boot. */
+void resctrl_cpu_detect(struct cpuinfo_x86 *c)
+{
+	if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
+		c->x86_cache_max_rmid  = -1;
+		c->x86_cache_occ_scale = -1;
+		c->x86_cache_mbm_width_offset = -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;
+		if (c->x86_vendor == X86_VENDOR_INTEL)
+			c->x86_cache_mbm_width_offset = eax & 0xff;
+		else
+			c->x86_cache_mbm_width_offset = -1;
+	}
+}
+
 static int __init resctrl_late_init(void)
 {
 	struct rdt_resource *r;
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 055c8613b531..934c8fb8a64a 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -495,14 +495,16 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 	return ret;
 }
 
-void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
-		    struct rdtgroup *rdtgrp, int evtid, int first)
+void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
+		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
+		    int evtid, int first)
 {
 	/*
 	 * setup the parameters to send to the IPI to read the data.
 	 */
 	rr->rgrp = rdtgrp;
 	rr->evtid = evtid;
+	rr->r = r;
 	rr->d = d;
 	rr->val = 0;
 	rr->first = first;
@@ -539,7 +541,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		goto out;
 	}
 
-	mon_event_read(&rr, d, rdtgrp, evtid, false);
+	mon_event_read(&rr, r, d, rdtgrp, evtid, false);
 
 	if (rr.val & RMID_VAL_ERROR)
 		seq_puts(m, "Error\n");
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 181c992f448c..f20a47d120b1 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -31,7 +31,7 @@
 
 #define CQM_LIMBOCHECK_INTERVAL	1000
 
-#define MBM_CNTR_WIDTH			24
+#define MBM_CNTR_WIDTH_BASE		24
 #define MBM_OVERFLOW_INTERVAL		1000
 #define MAX_MBA_BW			100u
 #define MBA_IS_LINEAR			0x4
@@ -40,6 +40,12 @@
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
+/*
+ * With the above fields in use 62 bits remain in MSR_IA32_QM_CTR for
+ * data to be returned. The counter width is discovered from the hardware
+ * as an offset from MBM_CNTR_WIDTH_BASE.
+ */
+#define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE)
 
 
 struct rdt_fs_context {
@@ -87,6 +93,7 @@ union mon_data_bits {
 
 struct rmid_read {
 	struct rdtgroup		*rgrp;
+	struct rdt_resource	*r;
 	struct rdt_domain	*d;
 	int			evtid;
 	bool			first;
@@ -460,6 +467,7 @@ struct rdt_resource {
 	struct list_head	evt_list;
 	int			num_rmid;
 	unsigned int		mon_scale;
+	unsigned int		mbm_width;
 	unsigned long		fflags;
 };
 
@@ -587,8 +595,9 @@ void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 				    unsigned int dom_id);
 void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 				    struct rdt_domain *d);
-void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
-		    struct rdtgroup *rdtgrp, int evtid, int first);
+void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
+		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
+		    int evtid, int first);
 void mbm_setup_overflow_handler(struct rdt_domain *dom,
 				unsigned long delay_ms);
 void mbm_handle_overflow(struct work_struct *work);
@@ -601,5 +610,6 @@ bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
 void __check_limbo(struct rdt_domain *d, bool force_free);
 bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r);
 bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r);
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 773124b0e18a..837d7d012b7b 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -214,9 +214,9 @@ void free_rmid(u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr)
+static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 {
-	u64 shift = 64 - MBM_CNTR_WIDTH, chunks;
+	u64 shift = 64 - width, chunks;
 
 	chunks = (cur_msr << shift) - (prev_msr << shift);
 	return chunks >>= shift;
@@ -256,7 +256,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 		return 0;
 	}
 
-	chunks = mbm_overflow_count(m->prev_msr, tval);
+	chunks = mbm_overflow_count(m->prev_msr, tval, rr->r->mbm_width);
 	m->chunks += chunks;
 	m->prev_msr = tval;
 
@@ -278,7 +278,7 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
 		return;
 
-	chunks = mbm_overflow_count(m->prev_bw_msr, tval);
+	chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width);
 	m->chunks_bw += chunks;
 	m->chunks = m->chunks_bw;
 	cur_bw = (chunks * r->mon_scale) >> 20;
@@ -433,11 +433,12 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	}
 }
 
-static void mbm_update(struct rdt_domain *d, int rmid)
+static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 {
 	struct rmid_read rr;
 
 	rr.first = false;
+	rr.r = r;
 	rr.d = d;
 
 	/*
@@ -510,6 +511,7 @@ void mbm_handle_overflow(struct work_struct *work)
 	struct rdtgroup *prgrp, *crgrp;
 	int cpu = smp_processor_id();
 	struct list_head *head;
+	struct rdt_resource *r;
 	struct rdt_domain *d;
 
 	mutex_lock(&rdtgroup_mutex);
@@ -517,16 +519,18 @@ void mbm_handle_overflow(struct work_struct *work)
 	if (!static_branch_likely(&rdt_mon_enable_key))
 		goto out_unlock;
 
-	d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]);
+	r = &rdt_resources_all[RDT_RESOURCE_L3];
+
+	d = get_domain_from_cpu(cpu, r);
 	if (!d)
 		goto out_unlock;
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
-		mbm_update(d, prgrp->mon.rmid);
+		mbm_update(r, d, prgrp->mon.rmid);
 
 		head = &prgrp->mon.crdtgrp_list;
 		list_for_each_entry(crgrp, head, mon.crdtgrp_list)
-			mbm_update(d, crgrp->mon.rmid);
+			mbm_update(r, d, crgrp->mon.rmid);
 
 		if (is_mba_sc(NULL))
 			update_mba_bw(prgrp, d);
@@ -614,11 +618,18 @@ static void l3_mon_evt_init(struct rdt_resource *r)
 
 int rdt_get_mon_l3_config(struct rdt_resource *r)
 {
+	unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
 	unsigned int cl_size = boot_cpu_data.x86_cache_size;
 	int ret;
 
 	r->mon_scale = boot_cpu_data.x86_cache_occ_scale;
 	r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
+	r->mbm_width = MBM_CNTR_WIDTH_BASE;
+
+	if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
+		r->mbm_width += mbm_offset;
+	else if (mbm_offset > MBM_CNTR_WIDTH_OFFSET_MAX)
+		pr_warn("Ignoring impossible MBM counter offset\n");
 
 	/*
 	 * A reasonable upper limit on the max threshold is the number
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index d7623e1b927d..0daf2f1cf7a8 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -24,7 +24,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/intel-family.h>
-#include <asm/resctrl_sched.h>
+#include <asm/resctrl.h>
 #include <asm/perf_event.h>
 
 #include "../../events/perf_event.h" /* For X86_CONFIG() */
@@ -1326,9 +1326,9 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 	 * pseudo-locked region will still be here on return.
 	 *
 	 * The mutex has to be released temporarily to avoid a potential
-	 * deadlock with the mm->mmap_sem semaphore which is obtained in
-	 * the device_create() and debugfs_create_dir() callpath below
-	 * as well as before the mmap() callback is called.
+	 * deadlock with the mm->mmap_lock which is obtained in the
+	 * device_create() and debugfs_create_dir() callpath below as well as
+	 * before the mmap() callback is called.
 	 */
 	mutex_unlock(&rdtgroup_mutex);
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 064e9ef44cd6..23b4b61319d3 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -29,7 +29,7 @@
 
 #include <uapi/linux/magic.h>
 
-#include <asm/resctrl_sched.h>
+#include <asm/resctrl.h>
 #include "internal.h"
 
 DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
@@ -1859,6 +1859,19 @@ static int set_cache_qos_cfg(int level, bool enable)
 	return 0;
 }
 
+/* Restore the qos cfg state when a domain comes online */
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
+{
+	if (!r->alloc_capable)
+		return;
+
+	if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA])
+		l2_qos_cfg_update(&r->alloc_enabled);
+
+	if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA])
+		l3_qos_cfg_update(&r->alloc_enabled);
+}
+
 /*
  * Enable or disable the MBA software controller
  * which helps user specify bandwidth in MBps.
@@ -2459,7 +2472,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 			goto out_destroy;
 
 		if (is_mbm_event(mevt->evtid))
-			mon_event_read(&rr, d, prgrp, mevt->evtid, true);
+			mon_event_read(&rr, r, d, prgrp, mevt->evtid, true);
 	}
 	kernfs_activate(kn);
 	return 0;
@@ -3072,7 +3085,8 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 	 * If the rdtgroup is a mon group and parent directory
 	 * is a valid "mon_groups" directory, remove the mon group.
 	 */
-	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) {
+	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn &&
+	    rdtgrp != &rdtgroup_default) {
 		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
 		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
 			ret = rdtgroup_ctrl_remove(kn, rdtgrp);
@@ -3185,10 +3199,10 @@ int __init rdtgroup_init(void)
 	 * during the debugfs directory creation also &sb->s_type->i_mutex_key
 	 * (the lockdep class of inode->i_rwsem). Other filesystem
 	 * interactions (eg. SyS_getdents) have the lock ordering:
-	 * &sb->s_type->i_mutex_key --> &mm->mmap_sem
-	 * During mmap(), called with &mm->mmap_sem, the rdtgroup_mutex
+	 * &sb->s_type->i_mutex_key --> &mm->mmap_lock
+	 * During mmap(), called with &mm->mmap_lock, the rdtgroup_mutex
 	 * is taken, thus creating dependency:
-	 * &mm->mmap_sem --> rdtgroup_mutex for the latter that can cause
+	 * &mm->mmap_lock --> rdtgroup_mutex for the latter that can cause
 	 * issues considering the other two lock dependencies.
 	 * By creating the debugfs directory here we avoid a dependency
 	 * that may cause deadlock (even though file operations cannot