35 files changed, 1128 insertions, 508 deletions

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 1f5d2291c31e..ac78f90aea56 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -36,13 +36,10 @@ obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
-obj-$(CONFIG_INTEL_RDT)	+= intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o
-obj-$(CONFIG_INTEL_RDT)	+= intel_rdt_ctrlmondata.o intel_rdt_pseudo_lock.o
-CFLAGS_intel_rdt_pseudo_lock.o = -I$(src)
-
-obj-$(CONFIG_X86_MCE)			+= mcheck/
+obj-$(CONFIG_X86_MCE)			+= mce/
 obj-$(CONFIG_MTRR)			+= mtrr/
 obj-$(CONFIG_MICROCODE)			+= microcode/
+obj-$(CONFIG_RESCTRL)			+= resctrl/
 
 obj-$(CONFIG_X86_LOCAL_APIC)		+= perfctr-watchdog.o
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index eeea634bee0a..69f6bbb41be0 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -15,6 +15,7 @@
 #include <asm/smp.h>
 #include <asm/pci-direct.h>
 #include <asm/delay.h>
+#include <asm/debugreg.h>
 
 #ifdef CONFIG_X86_64
 # include <asm/mmconfig.h>
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 7eba34df54c3..804c49493938 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -12,6 +12,7 @@
 #include <linux/ktime.h>
 #include <linux/math64.h>
 #include <linux/percpu.h>
+#include <linux/cpufreq.h>
 #include <linux/smp.h>
 
 #include "cpu.h"
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c37e66e493bf..8654b8b0c848 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/nospec.h>
 #include <linux/prctl.h>
+#include <linux/sched/smt.h>
 
 #include <asm/spec-ctrl.h>
 #include <asm/cmdline.h>
@@ -31,6 +32,8 @@
 #include <asm/e820/api.h>
 #include <asm/hypervisor.h>
 
+#include "cpu.h"
+
 static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
@@ -53,6 +56,13 @@ static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS;
 u64 __ro_after_init x86_amd_ls_cfg_base;
 u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask;
 
+/* Control conditional STIBP in switch_to() */
+DEFINE_STATIC_KEY_FALSE(switch_to_cond_stibp);
+/* Control conditional IBPB in switch_mm() */
+DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
+/* Control unconditional IBPB in switch_mm() */
+DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -123,31 +133,6 @@ void __init check_bugs(void)
 #endif
 }
 
-/* The kernel command line selection */
-enum spectre_v2_mitigation_cmd {
-	SPECTRE_V2_CMD_NONE,
-	SPECTRE_V2_CMD_AUTO,
-	SPECTRE_V2_CMD_FORCE,
-	SPECTRE_V2_CMD_RETPOLINE,
-	SPECTRE_V2_CMD_RETPOLINE_GENERIC,
-	SPECTRE_V2_CMD_RETPOLINE_AMD,
-};
-
-static const char *spectre_v2_strings[] = {
-	[SPECTRE_V2_NONE]			= "Vulnerable",
-	[SPECTRE_V2_RETPOLINE_MINIMAL]		= "Vulnerable: Minimal generic ASM retpoline",
-	[SPECTRE_V2_RETPOLINE_MINIMAL_AMD]	= "Vulnerable: Minimal AMD ASM retpoline",
-	[SPECTRE_V2_RETPOLINE_GENERIC]		= "Mitigation: Full generic retpoline",
-	[SPECTRE_V2_RETPOLINE_AMD]		= "Mitigation: Full AMD retpoline",
-	[SPECTRE_V2_IBRS_ENHANCED]		= "Mitigation: Enhanced IBRS",
-};
-
-#undef pr_fmt
-#define pr_fmt(fmt)     "Spectre V2 : " fmt
-
-static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
-	SPECTRE_V2_NONE;
-
 void
 x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
 {
@@ -169,6 +154,10 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
 		    static_cpu_has(X86_FEATURE_AMD_SSBD))
 			hostval |= ssbd_tif_to_spec_ctrl(ti->flags);
 
+		/* Conditional STIBP enabled? */
+		if (static_branch_unlikely(&switch_to_cond_stibp))
+			hostval |= stibp_tif_to_spec_ctrl(ti->flags);
+
 		if (hostval != guestval) {
 			msrval = setguest ? guestval : hostval;
 			wrmsrl(MSR_IA32_SPEC_CTRL, msrval);
@@ -202,7 +191,7 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
 		tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) :
 				 ssbd_spec_ctrl_to_tif(hostval);
 
-		speculative_store_bypass_update(tif);
+		speculation_ctrl_update(tif);
 	}
 }
 EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl);
@@ -217,6 +206,15 @@ static void x86_amd_ssb_disable(void)
 		wrmsrl(MSR_AMD64_LS_CFG, msrval);
 }
 
+#undef pr_fmt
+#define pr_fmt(fmt)     "Spectre V2 : " fmt
+
+static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
+	SPECTRE_V2_NONE;
+
+static enum spectre_v2_user_mitigation spectre_v2_user __ro_after_init =
+	SPECTRE_V2_USER_NONE;
+
 #ifdef RETPOLINE
 static bool spectre_v2_bad_module;
 
@@ -238,67 +236,227 @@ static inline const char *spectre_v2_module_string(void)
 static inline const char *spectre_v2_module_string(void) { return ""; }
 #endif
 
-static void __init spec2_print_if_insecure(const char *reason)
+static inline bool match_option(const char *arg, int arglen, const char *opt)
 {
-	if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
-		pr_info("%s selected on command line.\n", reason);
+	int len = strlen(opt);
+
+	return len == arglen && !strncmp(arg, opt, len);
 }
 
-static void __init spec2_print_if_secure(const char *reason)
+/* The kernel command line selection for spectre v2 */
+enum spectre_v2_mitigation_cmd {
+	SPECTRE_V2_CMD_NONE,
+	SPECTRE_V2_CMD_AUTO,
+	SPECTRE_V2_CMD_FORCE,
+	SPECTRE_V2_CMD_RETPOLINE,
+	SPECTRE_V2_CMD_RETPOLINE_GENERIC,
+	SPECTRE_V2_CMD_RETPOLINE_AMD,
+};
+
+enum spectre_v2_user_cmd {
+	SPECTRE_V2_USER_CMD_NONE,
+	SPECTRE_V2_USER_CMD_AUTO,
+	SPECTRE_V2_USER_CMD_FORCE,
+	SPECTRE_V2_USER_CMD_PRCTL,
+	SPECTRE_V2_USER_CMD_PRCTL_IBPB,
+	SPECTRE_V2_USER_CMD_SECCOMP,
+	SPECTRE_V2_USER_CMD_SECCOMP_IBPB,
+};
+
+static const char * const spectre_v2_user_strings[] = {
+	[SPECTRE_V2_USER_NONE]			= "User space: Vulnerable",
+	[SPECTRE_V2_USER_STRICT]		= "User space: Mitigation: STIBP protection",
+	[SPECTRE_V2_USER_STRICT_PREFERRED]	= "User space: Mitigation: STIBP always-on protection",
+	[SPECTRE_V2_USER_PRCTL]			= "User space: Mitigation: STIBP via prctl",
+	[SPECTRE_V2_USER_SECCOMP]		= "User space: Mitigation: STIBP via seccomp and prctl",
+};
+
+static const struct {
+	const char			*option;
+	enum spectre_v2_user_cmd	cmd;
+	bool				secure;
+} v2_user_options[] __initdata = {
+	{ "auto",		SPECTRE_V2_USER_CMD_AUTO,		false },
+	{ "off",		SPECTRE_V2_USER_CMD_NONE,		false },
+	{ "on",			SPECTRE_V2_USER_CMD_FORCE,		true  },
+	{ "prctl",		SPECTRE_V2_USER_CMD_PRCTL,		false },
+	{ "prctl,ibpb",		SPECTRE_V2_USER_CMD_PRCTL_IBPB,		false },
+	{ "seccomp",		SPECTRE_V2_USER_CMD_SECCOMP,		false },
+	{ "seccomp,ibpb",	SPECTRE_V2_USER_CMD_SECCOMP_IBPB,	false },
+};
+
+static void __init spec_v2_user_print_cond(const char *reason, bool secure)
 {
-	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
-		pr_info("%s selected on command line.\n", reason);
+	if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2) != secure)
+		pr_info("spectre_v2_user=%s forced on command line.\n", reason);
 }
 
-static inline bool retp_compiler(void)
+static enum spectre_v2_user_cmd __init
+spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd)
 {
-	return __is_defined(RETPOLINE);
+	char arg[20];
+	int ret, i;
+
+	switch (v2_cmd) {
+	case SPECTRE_V2_CMD_NONE:
+		return SPECTRE_V2_USER_CMD_NONE;
+	case SPECTRE_V2_CMD_FORCE:
+		return SPECTRE_V2_USER_CMD_FORCE;
+	default:
+		break;
+	}
+
+	ret = cmdline_find_option(boot_command_line, "spectre_v2_user",
+				  arg, sizeof(arg));
+	if (ret < 0)
+		return SPECTRE_V2_USER_CMD_AUTO;
+
+	for (i = 0; i < ARRAY_SIZE(v2_user_options); i++) {
+		if (match_option(arg, ret, v2_user_options[i].option)) {
+			spec_v2_user_print_cond(v2_user_options[i].option,
+						v2_user_options[i].secure);
+			return v2_user_options[i].cmd;
+		}
+	}
+
+	pr_err("Unknown user space protection option (%s). Switching to AUTO select\n", arg);
+	return SPECTRE_V2_USER_CMD_AUTO;
 }
 
-static inline bool match_option(const char *arg, int arglen, const char *opt)
+static void __init
+spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 {
-	int len = strlen(opt);
+	enum spectre_v2_user_mitigation mode = SPECTRE_V2_USER_NONE;
+	bool smt_possible = IS_ENABLED(CONFIG_SMP);
+	enum spectre_v2_user_cmd cmd;
 
-	return len == arglen && !strncmp(arg, opt, len);
+	if (!boot_cpu_has(X86_FEATURE_IBPB) && !boot_cpu_has(X86_FEATURE_STIBP))
+		return;
+
+	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED ||
+	    cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
+		smt_possible = false;
+
+	cmd = spectre_v2_parse_user_cmdline(v2_cmd);
+	switch (cmd) {
+	case SPECTRE_V2_USER_CMD_NONE:
+		goto set_mode;
+	case SPECTRE_V2_USER_CMD_FORCE:
+		mode = SPECTRE_V2_USER_STRICT;
+		break;
+	case SPECTRE_V2_USER_CMD_PRCTL:
+	case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
+		mode = SPECTRE_V2_USER_PRCTL;
+		break;
+	case SPECTRE_V2_USER_CMD_AUTO:
+	case SPECTRE_V2_USER_CMD_SECCOMP:
+	case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
+		if (IS_ENABLED(CONFIG_SECCOMP))
+			mode = SPECTRE_V2_USER_SECCOMP;
+		else
+			mode = SPECTRE_V2_USER_PRCTL;
+		break;
+	}
+
+	/*
+	 * At this point, an STIBP mode other than "off" has been set.
+	 * If STIBP support is not being forced, check if STIBP always-on
+	 * is preferred.
+	 */
+	if (mode != SPECTRE_V2_USER_STRICT &&
+	    boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON))
+		mode = SPECTRE_V2_USER_STRICT_PREFERRED;
+
+	/* Initialize Indirect Branch Prediction Barrier */
+	if (boot_cpu_has(X86_FEATURE_IBPB)) {
+		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
+
+		switch (cmd) {
+		case SPECTRE_V2_USER_CMD_FORCE:
+		case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
+		case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
+			static_branch_enable(&switch_mm_always_ibpb);
+			break;
+		case SPECTRE_V2_USER_CMD_PRCTL:
+		case SPECTRE_V2_USER_CMD_AUTO:
+		case SPECTRE_V2_USER_CMD_SECCOMP:
+			static_branch_enable(&switch_mm_cond_ibpb);
+			break;
+		default:
+			break;
+		}
+
+		pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
+			static_key_enabled(&switch_mm_always_ibpb) ?
+			"always-on" : "conditional");
+	}
+
+	/* If enhanced IBRS is enabled no STIBP required */
+	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
+		return;
+
+	/*
+	 * If SMT is not possible or STIBP is not available clear the STIBP
+	 * mode.
+	 */
+	if (!smt_possible || !boot_cpu_has(X86_FEATURE_STIBP))
+		mode = SPECTRE_V2_USER_NONE;
+set_mode:
+	spectre_v2_user = mode;
+	/* Only print the STIBP mode when SMT possible */
+	if (smt_possible)
+		pr_info("%s\n", spectre_v2_user_strings[mode]);
 }
 
+static const char * const spectre_v2_strings[] = {
+	[SPECTRE_V2_NONE]			= "Vulnerable",
+	[SPECTRE_V2_RETPOLINE_GENERIC]		= "Mitigation: Full generic retpoline",
+	[SPECTRE_V2_RETPOLINE_AMD]		= "Mitigation: Full AMD retpoline",
+	[SPECTRE_V2_IBRS_ENHANCED]		= "Mitigation: Enhanced IBRS",
+};
+
 static const struct {
 	const char *option;
 	enum spectre_v2_mitigation_cmd cmd;
 	bool secure;
-} mitigation_options[] = {
-	{ "off",               SPECTRE_V2_CMD_NONE,              false },
-	{ "on",                SPECTRE_V2_CMD_FORCE,             true },
-	{ "retpoline",         SPECTRE_V2_CMD_RETPOLINE,         false },
-	{ "retpoline,amd",     SPECTRE_V2_CMD_RETPOLINE_AMD,     false },
-	{ "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false },
-	{ "auto",              SPECTRE_V2_CMD_AUTO,              false },
+} mitigation_options[] __initdata = {
+	{ "off",		SPECTRE_V2_CMD_NONE,		  false },
+	{ "on",			SPECTRE_V2_CMD_FORCE,		  true  },
+	{ "retpoline",		SPECTRE_V2_CMD_RETPOLINE,	  false },
+	{ "retpoline,amd",	SPECTRE_V2_CMD_RETPOLINE_AMD,	  false },
+	{ "retpoline,generic",	SPECTRE_V2_CMD_RETPOLINE_GENERIC, false },
+	{ "auto",		SPECTRE_V2_CMD_AUTO,		  false },
 };
 
+static void __init spec_v2_print_cond(const char *reason, bool secure)
+{
+	if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2) != secure)
+		pr_info("%s selected on command line.\n", reason);
+}
+
 static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 {
+	enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO;
 	char arg[20];
 	int ret, i;
-	enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO;
 
 	if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
 		return SPECTRE_V2_CMD_NONE;
-	else {
-		ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg));
-		if (ret < 0)
-			return SPECTRE_V2_CMD_AUTO;
 
-		for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) {
-			if (!match_option(arg, ret, mitigation_options[i].option))
-				continue;
-			cmd = mitigation_options[i].cmd;
-			break;
-		}
+	ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg));
+	if (ret < 0)
+		return SPECTRE_V2_CMD_AUTO;
 
-		if (i >= ARRAY_SIZE(mitigation_options)) {
-			pr_err("unknown option (%s). Switching to AUTO select\n", arg);
-			return SPECTRE_V2_CMD_AUTO;
-		}
+	for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) {
+		if (!match_option(arg, ret, mitigation_options[i].option))
+			continue;
+		cmd = mitigation_options[i].cmd;
+		break;
+	}
+
+	if (i >= ARRAY_SIZE(mitigation_options)) {
+		pr_err("unknown option (%s). Switching to AUTO select\n", arg);
+		return SPECTRE_V2_CMD_AUTO;
 	}
 
 	if ((cmd == SPECTRE_V2_CMD_RETPOLINE ||
@@ -316,54 +474,11 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 		return SPECTRE_V2_CMD_AUTO;
 	}
 
-	if (mitigation_options[i].secure)
-		spec2_print_if_secure(mitigation_options[i].option);
-	else
-		spec2_print_if_insecure(mitigation_options[i].option);
-
+	spec_v2_print_cond(mitigation_options[i].option,
+			   mitigation_options[i].secure);
 	return cmd;
 }
 
-static bool stibp_needed(void)
-{
-	if (spectre_v2_enabled == SPECTRE_V2_NONE)
-		return false;
-
-	if (!boot_cpu_has(X86_FEATURE_STIBP))
-		return false;
-
-	return true;
-}
-
-static void update_stibp_msr(void *info)
-{
-	wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
-}
-
-void arch_smt_update(void)
-{
-	u64 mask;
-
-	if (!stibp_needed())
-		return;
-
-	mutex_lock(&spec_ctrl_mutex);
-	mask = x86_spec_ctrl_base;
-	if (cpu_smt_control == CPU_SMT_ENABLED)
-		mask |= SPEC_CTRL_STIBP;
-	else
-		mask &= ~SPEC_CTRL_STIBP;
-
-	if (mask != x86_spec_ctrl_base) {
-		pr_info("Spectre v2 cross-process SMT mitigation: %s STIBP\n",
-				cpu_smt_control == CPU_SMT_ENABLED ?
-				"Enabling" : "Disabling");
-		x86_spec_ctrl_base = mask;
-		on_each_cpu(update_stibp_msr, NULL, 1);
-	}
-	mutex_unlock(&spec_ctrl_mutex);
-}
-
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -417,14 +532,12 @@ retpoline_auto:
 			pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n");
 			goto retpoline_generic;
 		}
-		mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD :
-					 SPECTRE_V2_RETPOLINE_MINIMAL_AMD;
+		mode = SPECTRE_V2_RETPOLINE_AMD;
 		setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD);
 		setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
 	} else {
 	retpoline_generic:
-		mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC :
-					 SPECTRE_V2_RETPOLINE_MINIMAL;
+		mode = SPECTRE_V2_RETPOLINE_GENERIC;
 		setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
 	}
 
@@ -443,12 +556,6 @@ specv2_set_mode:
 	setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
 	pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
 
-	/* Initialize Indirect Branch Prediction Barrier if supported */
-	if (boot_cpu_has(X86_FEATURE_IBPB)) {
-		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
-		pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n");
-	}
-
 	/*
 	 * Retpoline means the kernel is safe because it has no indirect
 	 * branches. Enhanced IBRS protects firmware too, so, enable restricted
@@ -465,10 +572,68 @@ specv2_set_mode:
 		pr_info("Enabling Restricted Speculation for firmware calls\n");
 	}
 
+	/* Set up IBPB and STIBP depending on the general spectre V2 command */
+	spectre_v2_user_select_mitigation(cmd);
+
 	/* Enable STIBP if appropriate */
 	arch_smt_update();
 }
 
+static void update_stibp_msr(void * __unused)
+{
+	wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+}
+
+/* Update x86_spec_ctrl_base in case SMT state changed. */
+static void update_stibp_strict(void)
+{
+	u64 mask = x86_spec_ctrl_base & ~SPEC_CTRL_STIBP;
+
+	if (sched_smt_active())
+		mask |= SPEC_CTRL_STIBP;
+
+	if (mask == x86_spec_ctrl_base)
+		return;
+
+	pr_info("Update user space SMT mitigation: STIBP %s\n",
+		mask & SPEC_CTRL_STIBP ? "always-on" : "off");
+	x86_spec_ctrl_base = mask;
+	on_each_cpu(update_stibp_msr, NULL, 1);
+}
+
+/* Update the static key controlling the evaluation of TIF_SPEC_IB */
+static void update_indir_branch_cond(void)
+{
+	if (sched_smt_active())
+		static_branch_enable(&switch_to_cond_stibp);
+	else
+		static_branch_disable(&switch_to_cond_stibp);
+}
+
+void arch_smt_update(void)
+{
+	/* Enhanced IBRS implies STIBP. No update required. */
+	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
+		return;
+
+	mutex_lock(&spec_ctrl_mutex);
+
+	switch (spectre_v2_user) {
+	case SPECTRE_V2_USER_NONE:
+		break;
+	case SPECTRE_V2_USER_STRICT:
+	case SPECTRE_V2_USER_STRICT_PREFERRED:
+		update_stibp_strict();
+		break;
+	case SPECTRE_V2_USER_PRCTL:
+	case SPECTRE_V2_USER_SECCOMP:
+		update_indir_branch_cond();
+		break;
+	}
+
+	mutex_unlock(&spec_ctrl_mutex);
+}
+
 #undef pr_fmt
 #define pr_fmt(fmt)	"Speculative Store Bypass: " fmt
 
@@ -483,7 +648,7 @@ enum ssb_mitigation_cmd {
 	SPEC_STORE_BYPASS_CMD_SECCOMP,
 };
 
-static const char *ssb_strings[] = {
+static const char * const ssb_strings[] = {
 	[SPEC_STORE_BYPASS_NONE]	= "Vulnerable",
 	[SPEC_STORE_BYPASS_DISABLE]	= "Mitigation: Speculative Store Bypass disabled",
 	[SPEC_STORE_BYPASS_PRCTL]	= "Mitigation: Speculative Store Bypass disabled via prctl",
@@ -493,7 +658,7 @@ static const char *ssb_strings[] = {
 static const struct {
 	const char *option;
 	enum ssb_mitigation_cmd cmd;
-} ssb_mitigation_options[] = {
+} ssb_mitigation_options[]  __initdata = {
 	{ "auto",	SPEC_STORE_BYPASS_CMD_AUTO },    /* Platform decides */
 	{ "on",		SPEC_STORE_BYPASS_CMD_ON },      /* Disable Speculative Store Bypass */
 	{ "off",	SPEC_STORE_BYPASS_CMD_NONE },    /* Don't touch Speculative Store Bypass */
@@ -604,10 +769,25 @@ static void ssb_select_mitigation(void)
 #undef pr_fmt
 #define pr_fmt(fmt)     "Speculation prctl: " fmt
 
-static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
+static void task_update_spec_tif(struct task_struct *tsk)
 {
-	bool update;
+	/* Force the update of the real TIF bits */
+	set_tsk_thread_flag(tsk, TIF_SPEC_FORCE_UPDATE);
 
+	/*
+	 * Immediately update the speculation control MSRs for the current
+	 * task, but for a non-current task delay setting the CPU
+	 * mitigation until it is scheduled next.
+	 *
+	 * This can only happen for SECCOMP mitigation. For PRCTL it's
+	 * always the current task.
+	 */
+	if (tsk == current)
+		speculation_ctrl_update_current();
+}
+
+static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
+{
 	if (ssb_mode != SPEC_STORE_BYPASS_PRCTL &&
 	    ssb_mode != SPEC_STORE_BYPASS_SECCOMP)
 		return -ENXIO;
@@ -618,28 +798,58 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
 		if (task_spec_ssb_force_disable(task))
 			return -EPERM;
 		task_clear_spec_ssb_disable(task);
-		update = test_and_clear_tsk_thread_flag(task, TIF_SSBD);
+		task_update_spec_tif(task);
 		break;
 	case PR_SPEC_DISABLE:
 		task_set_spec_ssb_disable(task);
-		update = !test_and_set_tsk_thread_flag(task, TIF_SSBD);
+		task_update_spec_tif(task);
 		break;
 	case PR_SPEC_FORCE_DISABLE:
 		task_set_spec_ssb_disable(task);
 		task_set_spec_ssb_force_disable(task);
-		update = !test_and_set_tsk_thread_flag(task, TIF_SSBD);
+		task_update_spec_tif(task);
 		break;
 	default:
 		return -ERANGE;
 	}
+	return 0;
+}
 
-	/*
-	 * If being set on non-current task, delay setting the CPU
-	 * mitigation until it is next scheduled.
-	 */
-	if (task == current && update)
-		speculative_store_bypass_update_current();
-
+static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
+{
+	switch (ctrl) {
+	case PR_SPEC_ENABLE:
+		if (spectre_v2_user == SPECTRE_V2_USER_NONE)
+			return 0;
+		/*
+		 * Indirect branch speculation is always disabled in strict
+		 * mode.
+		 */
+		if (spectre_v2_user == SPECTRE_V2_USER_STRICT ||
+		    spectre_v2_user == SPECTRE_V2_USER_STRICT_PREFERRED)
+			return -EPERM;
+		task_clear_spec_ib_disable(task);
+		task_update_spec_tif(task);
+		break;
+	case PR_SPEC_DISABLE:
+	case PR_SPEC_FORCE_DISABLE:
+		/*
+		 * Indirect branch speculation is always allowed when
+		 * mitigation is force disabled.
+		 */
+		if (spectre_v2_user == SPECTRE_V2_USER_NONE)
+			return -EPERM;
+		if (spectre_v2_user == SPECTRE_V2_USER_STRICT ||
+		    spectre_v2_user == SPECTRE_V2_USER_STRICT_PREFERRED)
+			return 0;
+		task_set_spec_ib_disable(task);
+		if (ctrl == PR_SPEC_FORCE_DISABLE)
+			task_set_spec_ib_force_disable(task);
+		task_update_spec_tif(task);
+		break;
+	default:
+		return -ERANGE;
+	}
 	return 0;
 }
 
@@ -649,6 +859,8 @@ int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
 	switch (which) {
 	case PR_SPEC_STORE_BYPASS:
 		return ssb_prctl_set(task, ctrl);
+	case PR_SPEC_INDIRECT_BRANCH:
+		return ib_prctl_set(task, ctrl);
 	default:
 		return -ENODEV;
 	}
@@ -659,6 +871,8 @@ void arch_seccomp_spec_mitigate(struct task_struct *task)
 {
 	if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP)
 		ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE);
+	if (spectre_v2_user == SPECTRE_V2_USER_SECCOMP)
+		ib_prctl_set(task, PR_SPEC_FORCE_DISABLE);
 }
 #endif
 
@@ -681,11 +895,36 @@ static int ssb_prctl_get(struct task_struct *task)
 	}
 }
 
+static int ib_prctl_get(struct task_struct *task)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+		return PR_SPEC_NOT_AFFECTED;
+
+	switch (spectre_v2_user) {
+	case SPECTRE_V2_USER_NONE:
+		return PR_SPEC_ENABLE;
+	case SPECTRE_V2_USER_PRCTL:
+	case SPECTRE_V2_USER_SECCOMP:
+		if (task_spec_ib_force_disable(task))
+			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
+		if (task_spec_ib_disable(task))
+			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
+		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
+	case SPECTRE_V2_USER_STRICT:
+	case SPECTRE_V2_USER_STRICT_PREFERRED:
+		return PR_SPEC_DISABLE;
+	default:
+		return PR_SPEC_NOT_AFFECTED;
+	}
+}
+
 int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
 {
 	switch (which) {
 	case PR_SPEC_STORE_BYPASS:
 		return ssb_prctl_get(task);
+	case PR_SPEC_INDIRECT_BRANCH:
+		return ib_prctl_get(task);
 	default:
 		return -ENODEV;
 	}
@@ -779,7 +1018,8 @@ static void __init l1tf_select_mitigation(void)
 #endif
 
 	half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
-	if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) {
+	if (l1tf_mitigation != L1TF_MITIGATION_OFF &&
+			e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) {
 		pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n");
 		pr_info("You may make it effective by booting the kernel with mem=%llu parameter.\n",
 				half_pa);
@@ -823,7 +1063,7 @@ early_param("l1tf", l1tf_cmdline);
 #define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion"
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
-static const char *l1tf_vmx_states[] = {
+static const char * const l1tf_vmx_states[] = {
 	[VMENTER_L1D_FLUSH_AUTO]		= "auto",
 	[VMENTER_L1D_FLUSH_NEVER]		= "vulnerable",
 	[VMENTER_L1D_FLUSH_COND]		= "conditional cache flushes",
@@ -839,13 +1079,14 @@ static ssize_t l1tf_show_state(char *buf)
 
 	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED ||
 	    (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER &&
-	     cpu_smt_control == CPU_SMT_ENABLED))
+	     sched_smt_active())) {
 		return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG,
 			       l1tf_vmx_states[l1tf_vmx_mitigation]);
+	}
 
 	return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG,
 		       l1tf_vmx_states[l1tf_vmx_mitigation],
-		       cpu_smt_control == CPU_SMT_ENABLED ? "vulnerable" : "disabled");
+		       sched_smt_active() ? "vulnerable" : "disabled");
 }
 #else
 static ssize_t l1tf_show_state(char *buf)
@@ -854,11 +1095,41 @@ static ssize_t l1tf_show_state(char *buf)
 }
 #endif
 
+static char *stibp_state(void)
+{
+	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
+		return "";
+
+	switch (spectre_v2_user) {
+	case SPECTRE_V2_USER_NONE:
+		return ", STIBP: disabled";
+	case SPECTRE_V2_USER_STRICT:
+		return ", STIBP: forced";
+	case SPECTRE_V2_USER_STRICT_PREFERRED:
+		return ", STIBP: always-on";
+	case SPECTRE_V2_USER_PRCTL:
+	case SPECTRE_V2_USER_SECCOMP:
+		if (static_key_enabled(&switch_to_cond_stibp))
+			return ", STIBP: conditional";
+	}
+	return "";
+}
+
+static char *ibpb_state(void)
+{
+	if (boot_cpu_has(X86_FEATURE_IBPB)) {
+		if (static_key_enabled(&switch_mm_always_ibpb))
+			return ", IBPB: always-on";
+		if (static_key_enabled(&switch_mm_cond_ibpb))
+			return ", IBPB: conditional";
+		return ", IBPB: disabled";
+	}
+	return "";
+}
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
-	int ret;
-
 	if (!boot_cpu_has_bug(bug))
 		return sprintf(buf, "Not affected\n");
 
@@ -876,13 +1147,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 		return sprintf(buf, "Mitigation: __user pointer sanitization\n");
 
 	case X86_BUG_SPECTRE_V2:
-		ret = sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
-			       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+		return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+			       ibpb_state(),
 			       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
-			       (x86_spec_ctrl_base & SPEC_CTRL_STIBP) ? ", STIBP" : "",
+			       stibp_state(),
 			       boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "",
 			       spectre_v2_module_string());
-		return ret;
 
 	case X86_BUG_SPEC_STORE_BYPASS:
 		return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index dc1b9342e9c4..c4d1023fb0ab 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -17,6 +17,7 @@
 #include <linux/pci.h>
 
 #include <asm/cpufeature.h>
+#include <asm/cacheinfo.h>
 #include <asm/amd_nb.h>
 #include <asm/smp.h>
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index ffb181f959d2..cb28e98a0659 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -353,7 +353,7 @@ static __always_inline void setup_umip(struct cpuinfo_x86 *c)
 
 	cr4_set_bits(X86_CR4_UMIP);
 
-	pr_info("x86/cpu: Activated the Intel User Mode Instruction Prevention (UMIP) CPU feature\n");
+	pr_info_once("x86/cpu: User Mode Instruction Prevention (UMIP) activated\n");
 
 	return;
 
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index da5446acc241..5eb946b9a9f3 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -49,9 +49,6 @@ extern void get_cpu_cap(struct cpuinfo_x86 *c);
 extern void get_cpu_address_sizes(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
 extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
-extern u32 get_scattered_cpuid_leaf(unsigned int level,
-				    unsigned int sub_leaf,
-				    enum cpuid_regs_idx reg);
 extern void init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_hygon_cacheinfo(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mce/Makefile
index bcc7c54c7041..9f020c994154 100644
--- a/arch/x86/kernel/cpu/mcheck/Makefile
+++ b/arch/x86/kernel/cpu/mce/Makefile
@@ -1,14 +1,16 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-y				=  mce.o mce-severity.o mce-genpool.o
+obj-y				=  core.o severity.o genpool.o
 
 obj-$(CONFIG_X86_ANCIENT_MCE)	+= winchip.o p5.o
-obj-$(CONFIG_X86_MCE_INTEL)	+= mce_intel.o
-obj-$(CONFIG_X86_MCE_AMD)	+= mce_amd.o
+obj-$(CONFIG_X86_MCE_INTEL)	+= intel.o
+obj-$(CONFIG_X86_MCE_AMD)	+= amd.o
 obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o
+
+mce-inject-y			:= inject.o
 obj-$(CONFIG_X86_MCE_INJECT)	+= mce-inject.o
 
 obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o
 
-obj-$(CONFIG_ACPI_APEI)		+= mce-apei.o
+obj-$(CONFIG_ACPI_APEI)		+= apei.o
 
 obj-$(CONFIG_X86_MCELOG_LEGACY)	+= dev-mcelog.o
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mce/amd.c
index dd33c357548f..89298c83de53 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -23,12 +23,13 @@
 #include <linux/string.h>
 
 #include <asm/amd_nb.h>
+#include <asm/traps.h>
 #include <asm/apic.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 #include <asm/trace/irq_vectors.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 #define NR_BLOCKS         5
 #define THRESHOLD_MAX     0xFFF
@@ -56,7 +57,7 @@
 /* Threshold LVT offset is at MSR0xC0000410[15:12] */
 #define SMCA_THR_LVT_OFF	0xF000
 
-static bool thresholding_en;
+static bool thresholding_irq_en;
 
 static const char * const th_names[] = {
 	"load_store",
@@ -99,7 +100,7 @@ static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init =
 	[0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 }
 };
 
-const char *smca_get_name(enum smca_bank_types t)
+static const char *smca_get_name(enum smca_bank_types t)
 {
 	if (t >= N_SMCA_BANK_TYPES)
 		return NULL;
@@ -534,9 +535,8 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
 
 set_offset:
 	offset = setup_APIC_mce_threshold(offset, new);
-
-	if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt))
-		mce_threshold_vector = amd_threshold_interrupt;
+	if (offset == new)
+		thresholding_irq_en = true;
 
 done:
 	mce_threshold_block_init(&b, offset);
@@ -825,7 +825,7 @@ 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(void)
+asmlinkage __visible void __irq_entry smp_deferred_error_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR);
@@ -1357,9 +1357,6 @@ int mce_threshold_remove_device(unsigned int cpu)
 {
 	unsigned int bank;
 
-	if (!thresholding_en)
-		return 0;
-
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
@@ -1377,9 +1374,6 @@ int mce_threshold_create_device(unsigned int cpu)
 	struct threshold_bank **bp;
 	int err = 0;
 
-	if (!thresholding_en)
-		return 0;
-
 	bp = per_cpu(threshold_banks, cpu);
 	if (bp)
 		return 0;
@@ -1408,9 +1402,6 @@ static __init int threshold_init_device(void)
 {
 	unsigned lcpu = 0;
 
-	if (mce_threshold_vector == amd_threshold_interrupt)
-		thresholding_en = true;
-
 	/* to hit CPUs online before the notifier is up */
 	for_each_online_cpu(lcpu) {
 		int err = mce_threshold_create_device(lcpu);
@@ -1419,6 +1410,9 @@ static __init int threshold_init_device(void)
 			return err;
 	}
 
+	if (thresholding_irq_en)
+		mce_threshold_vector = amd_threshold_interrupt;
+
 	return 0;
 }
 /*
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mce/apei.c
index 2eee85379689..1d9b3ce662a0 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mce/apei.c
@@ -36,7 +36,7 @@
 #include <acpi/ghes.h>
 #include <asm/mce.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 {
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mce/core.c
index 8c66d2fc8f81..672c7225cb1b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -8,8 +8,6 @@
  * Author: Andi Kleen
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
 #include <linux/thread_info.h>
 #include <linux/capability.h>
 #include <linux/miscdevice.h>
@@ -52,7 +50,7 @@
 #include <asm/msr.h>
 #include <asm/reboot.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 static DEFINE_MUTEX(mce_log_mutex);
 
@@ -485,7 +483,7 @@ static void mce_report_event(struct pt_regs *regs)
  * be somewhat complicated (e.g. segment offset would require an instruction
  * parser). So only support physical addresses up to page granuality for now.
  */
-static int mce_usable_address(struct mce *m)
+int mce_usable_address(struct mce *m)
 {
 	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
@@ -505,6 +503,7 @@ static int mce_usable_address(struct mce *m)
 
 	return 1;
 }
+EXPORT_SYMBOL_GPL(mce_usable_address);
 
 bool mce_is_memory_error(struct mce *m)
 {
@@ -534,7 +533,7 @@ bool mce_is_memory_error(struct mce *m)
 }
 EXPORT_SYMBOL_GPL(mce_is_memory_error);
 
-static bool mce_is_correctable(struct mce *m)
+bool mce_is_correctable(struct mce *m)
 {
 	if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
 		return false;
@@ -547,6 +546,7 @@ static bool mce_is_correctable(struct mce *m)
 
 	return true;
 }
+EXPORT_SYMBOL_GPL(mce_is_correctable);
 
 static bool cec_add_mce(struct mce *m)
 {
@@ -684,7 +684,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count);
  * errors here. However this would be quite problematic --
  * we would need to reimplement the Monarch handling and
  * it would mess up the exclusion between exception handler
- * and poll hander -- * so we skip this for now.
+ * and poll handler -- * so we skip this for now.
  * These cases should not happen anyways, or only when the CPU
  * is already totally * confused. In this case it's likely it will
  * not fully execute the machine check handler either.
diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c
index 27f394ac983f..9690ec5c8051 100644
--- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c
@@ -8,14 +8,12 @@
  * Author: Andi Kleen
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
 #include <linux/miscdevice.h>
 #include <linux/slab.h>
 #include <linux/kmod.h>
 #include <linux/poll.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 static BLOCKING_NOTIFIER_HEAD(mce_injector_chain);
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mce/genpool.c
index 217cd4449bc9..3395549c51d3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c
+++ b/arch/x86/kernel/cpu/mce/genpool.c
@@ -10,7 +10,7 @@
 #include <linux/mm.h>
 #include <linux/genalloc.h>
 #include <linux/llist.h>
-#include "mce-internal.h"
+#include "internal.h"
 
 /*
  * printk() is not safe in MCE context. This is a lock-less memory allocator
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 1fc424c40a31..8492ef7d9015 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -38,7 +38,7 @@
 #include <asm/nmi.h>
 #include <asm/smp.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 /*
  * Collect all the MCi_XXX settings
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mce/intel.c
index d05be307d081..e43eb6732630 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -18,7 +18,7 @@
 #include <asm/msr.h>
 #include <asm/mce.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 /*
  * Support for Intel Correct Machine Check Interrupts. This allows
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mce/internal.h
index ceb67cd5918f..af5eab1e65e2 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -2,6 +2,9 @@
 #ifndef __X86_MCE_INTERNAL_H__
 #define __X86_MCE_INTERNAL_H__
 
+#undef pr_fmt
+#define pr_fmt(fmt) "mce: " fmt
+
 #include <linux/device.h>
 #include <asm/mce.h>
 
diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mce/p5.c
index 5cddf831720f..4ae6df556526 100644
--- a/arch/x86/kernel/cpu/mcheck/p5.c
+++ b/arch/x86/kernel/cpu/mce/p5.c
@@ -14,6 +14,8 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 
+#include "internal.h"
+
 /* By default disabled */
 int mce_p5_enabled __read_mostly;
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mce/severity.c
index 44396d521987..dc3e26e905a3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -16,7 +16,7 @@
 #include <asm/mce.h>
 #include <linux/uaccess.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 /*
  * Grade an mce by severity. In general the most severe ones are processed
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c
index 2da67b70ba98..10a3b0599300 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mce/therm_throt.c
@@ -25,11 +25,14 @@
 #include <linux/cpu.h>
 
 #include <asm/processor.h>
+#include <asm/traps.h>
 #include <asm/apic.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 #include <asm/trace/irq_vectors.h>
 
+#include "internal.h"
+
 /* How long to wait between reporting thermal events */
 #define CHECK_INTERVAL		(300 * HZ)
 
@@ -390,7 +393,7 @@ 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 *r)
+asmlinkage __visible void __irq_entry smp_thermal_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	trace_thermal_apic_entry(THERMAL_APIC_VECTOR);
diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index 2b584b319eff..28812cc15300 100644
--- a/arch/x86/kernel/cpu/mcheck/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -6,10 +6,13 @@
 #include <linux/kernel.h>
 
 #include <asm/irq_vectors.h>
+#include <asm/traps.h>
 #include <asm/apic.h>
 #include <asm/mce.h>
 #include <asm/trace/irq_vectors.h>
 
+#include "internal.h"
+
 static void default_threshold_interrupt(void)
 {
 	pr_err("Unexpected threshold interrupt at vector %x\n",
@@ -18,7 +21,7 @@ static void default_threshold_interrupt(void)
 
 void (*mce_threshold_vector)(void) = default_threshold_interrupt;
 
-asmlinkage __visible void __irq_entry smp_threshold_interrupt(void)
+asmlinkage __visible void __irq_entry smp_threshold_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR);
diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mce/winchip.c
index 3b45b270a865..a30ea13cccc2 100644
--- a/arch/x86/kernel/cpu/mcheck/winchip.c
+++ b/arch/x86/kernel/cpu/mce/winchip.c
@@ -13,6 +13,8 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 
+#include "internal.h"
+
 /* Machine check handler for WinChip C6: */
 static void winchip_machine_check(struct pt_regs *regs, long error_code)
 {
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 07b5fc00b188..51adde0a0f1a 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -5,7 +5,7 @@
  *  CPUs and later.
  *
  *  Copyright (C) 2008-2011 Advanced Micro Devices Inc.
- *	          2013-2016 Borislav Petkov <bp@alien8.de>
+ *	          2013-2018 Borislav Petkov <bp@alien8.de>
  *
  *  Author: Peter Oruba <peter.oruba@amd.com>
  *
@@ -38,7 +38,10 @@
 #include <asm/cpu.h>
 #include <asm/msr.h>
 
-static struct equiv_cpu_entry *equiv_cpu_table;
+static struct equiv_cpu_table {
+	unsigned int num_entries;
+	struct equiv_cpu_entry *entry;
+} equiv_table;
 
 /*
  * This points to the current valid container of microcode patches which we will
@@ -63,13 +66,225 @@ static u8 amd_ucode_patch[PATCH_MAX_SIZE];
 static const char
 ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin";
 
-static u16 find_equiv_id(struct equiv_cpu_entry *equiv_table, u32 sig)
+static u16 find_equiv_id(struct equiv_cpu_table *et, u32 sig)
 {
-	for (; equiv_table && equiv_table->installed_cpu; equiv_table++) {
-		if (sig == equiv_table->installed_cpu)
-			return equiv_table->equiv_cpu;
+	unsigned int i;
+
+	if (!et || !et->num_entries)
+		return 0;
+
+	for (i = 0; i < et->num_entries; i++) {
+		struct equiv_cpu_entry *e = &et->entry[i];
+
+		if (sig == e->installed_cpu)
+			return e->equiv_cpu;
+
+		e++;
+	}
+	return 0;
+}
+
+/*
+ * Check whether there is a valid microcode container file at the beginning
+ * of @buf of size @buf_size. Set @early to use this function in the early path.
+ */
+static bool verify_container(const u8 *buf, size_t buf_size, bool early)
+{
+	u32 cont_magic;
+
+	if (buf_size <= CONTAINER_HDR_SZ) {
+		if (!early)
+			pr_debug("Truncated microcode container header.\n");
+
+		return false;
+	}
+
+	cont_magic = *(const u32 *)buf;
+	if (cont_magic != UCODE_MAGIC) {
+		if (!early)
+			pr_debug("Invalid magic value (0x%08x).\n", cont_magic);
+
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * Check whether there is a valid, non-truncated CPU equivalence table at the
+ * beginning of @buf of size @buf_size. Set @early to use this function in the
+ * early path.
+ */
+static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early)
+{
+	const u32 *hdr = (const u32 *)buf;
+	u32 cont_type, equiv_tbl_len;
+
+	if (!verify_container(buf, buf_size, early))
+		return false;
+
+	cont_type = hdr[1];
+	if (cont_type != UCODE_EQUIV_CPU_TABLE_TYPE) {
+		if (!early)
+			pr_debug("Wrong microcode container equivalence table type: %u.\n",
+			       cont_type);
+
+		return false;
+	}
+
+	buf_size -= CONTAINER_HDR_SZ;
+
+	equiv_tbl_len = hdr[2];
+	if (equiv_tbl_len < sizeof(struct equiv_cpu_entry) ||
+	    buf_size < equiv_tbl_len) {
+		if (!early)
+			pr_debug("Truncated equivalence table.\n");
+
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * Check whether there is a valid, non-truncated microcode patch section at the
+ * beginning of @buf of size @buf_size. Set @early to use this function in the
+ * early path.
+ *
+ * On success, @sh_psize returns the patch size according to the section header,
+ * to the caller.
+ */
+static bool
+__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize, bool early)
+{
+	u32 p_type, p_size;
+	const u32 *hdr;
+
+	if (buf_size < SECTION_HDR_SIZE) {
+		if (!early)
+			pr_debug("Truncated patch section.\n");
+
+		return false;
+	}
+
+	hdr = (const u32 *)buf;
+	p_type = hdr[0];
+	p_size = hdr[1];
+
+	if (p_type != UCODE_UCODE_TYPE) {
+		if (!early)
+			pr_debug("Invalid type field (0x%x) in container file section header.\n",
+				p_type);
+
+		return false;
+	}
+
+	if (p_size < sizeof(struct microcode_header_amd)) {
+		if (!early)
+			pr_debug("Patch of size %u too short.\n", p_size);
+
+		return false;
+	}
+
+	*sh_psize = p_size;
+
+	return true;
+}
+
+/*
+ * Check whether the passed remaining file @buf_size is large enough to contain
+ * a patch of the indicated @sh_psize (and also whether this size does not
+ * exceed the per-family maximum). @sh_psize is the size read from the section
+ * header.
+ */
+static unsigned int __verify_patch_size(u8 family, u32 sh_psize, size_t buf_size)
+{
+	u32 max_size;
+
+	if (family >= 0x15)
+		return min_t(u32, sh_psize, buf_size);
+
+#define F1XH_MPB_MAX_SIZE 2048
+#define F14H_MPB_MAX_SIZE 1824
+
+	switch (family) {
+	case 0x10 ... 0x12:
+		max_size = F1XH_MPB_MAX_SIZE;
+		break;
+	case 0x14:
+		max_size = F14H_MPB_MAX_SIZE;
+		break;
+	default:
+		WARN(1, "%s: WTF family: 0x%x\n", __func__, family);
+		return 0;
+		break;
+	}
+
+	if (sh_psize > min_t(u32, buf_size, max_size))
+		return 0;
+
+	return sh_psize;
+}
+
+/*
+ * Verify the patch in @buf.
+ *
+ * Returns:
+ * negative: on error
+ * positive: patch is not for this family, skip it
+ * 0: success
+ */
+static int
+verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool early)
+{
+	struct microcode_header_amd *mc_hdr;
+	unsigned int ret;
+	u32 sh_psize;
+	u16 proc_id;
+	u8 patch_fam;
+
+	if (!__verify_patch_section(buf, buf_size, &sh_psize, early))
+		return -1;
+
+	/*
+	 * The section header length is not included in this indicated size
+	 * but is present in the leftover file length so we need to subtract
+	 * it before passing this value to the function below.
+	 */
+	buf_size -= SECTION_HDR_SIZE;
+
+	/*
+	 * Check if the remaining buffer is big enough to contain a patch of
+	 * size sh_psize, as the section claims.
+	 */
+	if (buf_size < sh_psize) {
+		if (!early)
+			pr_debug("Patch of size %u truncated.\n", sh_psize);
+
+		return -1;
+	}
+
+	ret = __verify_patch_size(family, sh_psize, buf_size);
+	if (!ret) {
+		if (!early)
+			pr_debug("Per-family patch size mismatch.\n");
+		return -1;
+	}
+
+	*patch_size = sh_psize;
+
+	mc_hdr	= (struct microcode_header_amd *)(buf + SECTION_HDR_SIZE);
+	if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
+		if (!early)
+			pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", mc_hdr->patch_id);
+		return -1;
 	}
 
+	proc_id	= mc_hdr->processor_rev_id;
+	patch_fam = 0xf + (proc_id >> 12);
+	if (patch_fam != family)
+		return 1;
+
 	return 0;
 }
 
@@ -80,26 +295,28 @@ static u16 find_equiv_id(struct equiv_cpu_entry *equiv_table, u32 sig)
  * Returns the amount of bytes consumed while scanning. @desc contains all the
  * data we're going to use in later stages of the application.
  */
-static ssize_t parse_container(u8 *ucode, ssize_t size, struct cont_desc *desc)
+static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc)
 {
-	struct equiv_cpu_entry *eq;
-	ssize_t orig_size = size;
+	struct equiv_cpu_table table;
+	size_t orig_size = size;
 	u32 *hdr = (u32 *)ucode;
 	u16 eq_id;
 	u8 *buf;
 
-	/* Am I looking at an equivalence table header? */
-	if (hdr[0] != UCODE_MAGIC ||
-	    hdr[1] != UCODE_EQUIV_CPU_TABLE_TYPE ||
-	    hdr[2] == 0)
-		return CONTAINER_HDR_SZ;
+	if (!verify_equivalence_table(ucode, size, true))
+		return 0;
 
 	buf = ucode;
 
-	eq = (struct equiv_cpu_entry *)(buf + CONTAINER_HDR_SZ);
+	table.entry = (struct equiv_cpu_entry *)(buf + CONTAINER_HDR_SZ);
+	table.num_entries = hdr[2] / sizeof(struct equiv_cpu_entry);
 
-	/* Find the equivalence ID of our CPU in this table: */
-	eq_id = find_equiv_id(eq, desc->cpuid_1_eax);
+	/*
+	 * Find the equivalence ID of our CPU in this table. Even if this table
+	 * doesn't contain a patch for the CPU, scan through the whole container
+	 * so that it can be skipped in case there are other containers appended.
+	 */
+	eq_id = find_equiv_id(&table, desc->cpuid_1_eax);
 
 	buf  += hdr[2] + CONTAINER_HDR_SZ;
 	size -= hdr[2] + CONTAINER_HDR_SZ;
@@ -111,29 +328,29 @@ static ssize_t parse_container(u8 *ucode, ssize_t size, struct cont_desc *desc)
 	while (size > 0) {
 		struct microcode_amd *mc;
 		u32 patch_size;
+		int ret;
+
+		ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size, true);
+		if (ret < 0) {
+			/*
+			 * Patch verification failed, skip to the next
+			 * container, if there's one:
+			 */
+			goto out;
+		} else if (ret > 0) {
+			goto skip;
+		}
 
-		hdr = (u32 *)buf;
-
-		if (hdr[0] != UCODE_UCODE_TYPE)
-			break;
-
-		/* Sanity-check patch size. */
-		patch_size = hdr[1];
-		if (patch_size > PATCH_MAX_SIZE)
-			break;
-
-		/* Skip patch section header: */
-		buf  += SECTION_HDR_SIZE;
-		size -= SECTION_HDR_SIZE;
-
-		mc = (struct microcode_amd *)buf;
+		mc = (struct microcode_amd *)(buf + SECTION_HDR_SIZE);
 		if (eq_id == mc->hdr.processor_rev_id) {
 			desc->psize = patch_size;
 			desc->mc = mc;
 		}
 
-		buf  += patch_size;
-		size -= patch_size;
+skip:
+		/* Skip patch section header too: */
+		buf  += patch_size + SECTION_HDR_SIZE;
+		size -= patch_size + SECTION_HDR_SIZE;
 	}
 
 	/*
@@ -150,6 +367,7 @@ static ssize_t parse_container(u8 *ucode, ssize_t size, struct cont_desc *desc)
 		return 0;
 	}
 
+out:
 	return orig_size - size;
 }
 
@@ -159,15 +377,18 @@ static ssize_t parse_container(u8 *ucode, ssize_t size, struct cont_desc *desc)
  */
 static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc)
 {
-	ssize_t rem = size;
-
-	while (rem >= 0) {
-		ssize_t s = parse_container(ucode, rem, desc);
+	while (size) {
+		size_t s = parse_container(ucode, size, desc);
 		if (!s)
 			return;
 
-		ucode += s;
-		rem   -= s;
+		/* catch wraparound */
+		if (size >= s) {
+			ucode += s;
+			size  -= s;
+		} else {
+			return;
+		}
 	}
 }
 
@@ -364,21 +585,7 @@ void reload_ucode_amd(void)
 static u16 __find_equiv_id(unsigned int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	return find_equiv_id(equiv_cpu_table, uci->cpu_sig.sig);
-}
-
-static u32 find_cpu_family_by_equiv_cpu(u16 equiv_cpu)
-{
-	int i = 0;
-
-	BUG_ON(!equiv_cpu_table);
-
-	while (equiv_cpu_table[i].equiv_cpu != 0) {
-		if (equiv_cpu == equiv_cpu_table[i].equiv_cpu)
-			return equiv_cpu_table[i].installed_cpu;
-		i++;
-	}
-	return 0;
+	return find_equiv_id(&equiv_table, uci->cpu_sig.sig);
 }
 
 /*
@@ -461,43 +668,6 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 	return 0;
 }
 
-static unsigned int verify_patch_size(u8 family, u32 patch_size,
-				      unsigned int size)
-{
-	u32 max_size;
-
-#define F1XH_MPB_MAX_SIZE 2048
-#define F14H_MPB_MAX_SIZE 1824
-#define F15H_MPB_MAX_SIZE 4096
-#define F16H_MPB_MAX_SIZE 3458
-#define F17H_MPB_MAX_SIZE 3200
-
-	switch (family) {
-	case 0x14:
-		max_size = F14H_MPB_MAX_SIZE;
-		break;
-	case 0x15:
-		max_size = F15H_MPB_MAX_SIZE;
-		break;
-	case 0x16:
-		max_size = F16H_MPB_MAX_SIZE;
-		break;
-	case 0x17:
-		max_size = F17H_MPB_MAX_SIZE;
-		break;
-	default:
-		max_size = F1XH_MPB_MAX_SIZE;
-		break;
-	}
-
-	if (patch_size > min_t(u32, size, max_size)) {
-		pr_err("patch size mismatch\n");
-		return 0;
-	}
-
-	return patch_size;
-}
-
 static enum ucode_state apply_microcode_amd(int cpu)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -548,34 +718,34 @@ out:
 	return ret;
 }
 
-static int install_equiv_cpu_table(const u8 *buf)
+static size_t install_equiv_cpu_table(const u8 *buf, size_t buf_size)
 {
-	unsigned int *ibuf = (unsigned int *)buf;
-	unsigned int type = ibuf[1];
-	unsigned int size = ibuf[2];
+	u32 equiv_tbl_len;
+	const u32 *hdr;
 
-	if (type != UCODE_EQUIV_CPU_TABLE_TYPE || !size) {
-		pr_err("empty section/"
-		       "invalid type field in container file section header\n");
-		return -EINVAL;
-	}
+	if (!verify_equivalence_table(buf, buf_size, false))
+		return 0;
+
+	hdr = (const u32 *)buf;
+	equiv_tbl_len = hdr[2];
 
-	equiv_cpu_table = vmalloc(size);
-	if (!equiv_cpu_table) {
+	equiv_table.entry = vmalloc(equiv_tbl_len);
+	if (!equiv_table.entry) {
 		pr_err("failed to allocate equivalent CPU table\n");
-		return -ENOMEM;
+		return 0;
 	}
 
-	memcpy(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size);
+	memcpy(equiv_table.entry, buf + CONTAINER_HDR_SZ, equiv_tbl_len);
+	equiv_table.num_entries = equiv_tbl_len / sizeof(struct equiv_cpu_entry);
 
 	/* add header length */
-	return size + CONTAINER_HDR_SZ;
+	return equiv_tbl_len + CONTAINER_HDR_SZ;
 }
 
 static void free_equiv_cpu_table(void)
 {
-	vfree(equiv_cpu_table);
-	equiv_cpu_table = NULL;
+	vfree(equiv_table.entry);
+	memset(&equiv_table, 0, sizeof(equiv_table));
 }
 
 static void cleanup(void)
@@ -585,47 +755,23 @@ static void cleanup(void)
 }
 
 /*
- * We return the current size even if some of the checks failed so that
+ * Return a non-negative value even if some of the checks failed so that
  * we can skip over the next patch. If we return a negative value, we
  * signal a grave error like a memory allocation has failed and the
  * driver cannot continue functioning normally. In such cases, we tear
  * down everything we've used up so far and exit.
  */
-static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover)
+static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
+				unsigned int *patch_size)
 {
 	struct microcode_header_amd *mc_hdr;
 	struct ucode_patch *patch;
-	unsigned int patch_size, crnt_size, ret;
-	u32 proc_fam;
 	u16 proc_id;
+	int ret;
 
-	patch_size  = *(u32 *)(fw + 4);
-	crnt_size   = patch_size + SECTION_HDR_SIZE;
-	mc_hdr	    = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE);
-	proc_id	    = mc_hdr->processor_rev_id;
-
-	proc_fam = find_cpu_family_by_equiv_cpu(proc_id);
-	if (!proc_fam) {
-		pr_err("No patch family for equiv ID: 0x%04x\n", proc_id);
-		return crnt_size;
-	}
-
-	/* check if patch is for the current family */
-	proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff);
-	if (proc_fam != family)
-		return crnt_size;
-
-	if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
-		pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n",
-			mc_hdr->patch_id);
-		return crnt_size;
-	}
-
-	ret = verify_patch_size(family, patch_size, leftover);
-	if (!ret) {
-		pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id);
-		return crnt_size;
-	}
+	ret = verify_patch(family, fw, leftover, patch_size, false);
+	if (ret)
+		return ret;
 
 	patch = kzalloc(sizeof(*patch), GFP_KERNEL);
 	if (!patch) {
@@ -633,13 +779,16 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover)
 		return -EINVAL;
 	}
 
-	patch->data = kmemdup(fw + SECTION_HDR_SIZE, patch_size, GFP_KERNEL);
+	patch->data = kmemdup(fw + SECTION_HDR_SIZE, *patch_size, GFP_KERNEL);
 	if (!patch->data) {
 		pr_err("Patch data allocation failure.\n");
 		kfree(patch);
 		return -EINVAL;
 	}
 
+	mc_hdr      = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE);
+	proc_id     = mc_hdr->processor_rev_id;
+
 	INIT_LIST_HEAD(&patch->plist);
 	patch->patch_id  = mc_hdr->patch_id;
 	patch->equiv_cpu = proc_id;
@@ -650,39 +799,38 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover)
 	/* ... and add to cache. */
 	update_cache(patch);
 
-	return crnt_size;
+	return 0;
 }
 
 static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
 					     size_t size)
 {
-	enum ucode_state ret = UCODE_ERROR;
-	unsigned int leftover;
 	u8 *fw = (u8 *)data;
-	int crnt_size = 0;
-	int offset;
+	size_t offset;
 
-	offset = install_equiv_cpu_table(data);
-	if (offset < 0) {
-		pr_err("failed to create equivalent cpu table\n");
-		return ret;
-	}
-	fw += offset;
-	leftover = size - offset;
+	offset = install_equiv_cpu_table(data, size);
+	if (!offset)
+		return UCODE_ERROR;
+
+	fw   += offset;
+	size -= offset;
 
 	if (*(u32 *)fw != UCODE_UCODE_TYPE) {
 		pr_err("invalid type field in container file section header\n");
 		free_equiv_cpu_table();
-		return ret;
+		return UCODE_ERROR;
 	}
 
-	while (leftover) {
-		crnt_size = verify_and_add_patch(family, fw, leftover);
-		if (crnt_size < 0)
-			return ret;
+	while (size > 0) {
+		unsigned int crnt_size = 0;
+		int ret;
 
-		fw	 += crnt_size;
-		leftover -= crnt_size;
+		ret = verify_and_add_patch(family, fw, size, &crnt_size);
+		if (ret < 0)
+			return UCODE_ERROR;
+
+		fw   +=  crnt_size + SECTION_HDR_SIZE;
+		size -= (crnt_size + SECTION_HDR_SIZE);
 	}
 
 	return UCODE_OK;
@@ -761,10 +909,8 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 	}
 
 	ret = UCODE_ERROR;
-	if (*(u32 *)fw->data != UCODE_MAGIC) {
-		pr_err("invalid magic value (0x%08x)\n", *(u32 *)fw->data);
+	if (!verify_container(fw->data, fw->size, false))
 		goto fw_release;
-	}
 
 	ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size);
 
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 1c72f3819eb1..e81a2db42df7 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -20,6 +20,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/kexec.h>
+#include <linux/i8253.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 #include <asm/hyperv-tlfs.h>
@@ -295,6 +296,16 @@ static void __init ms_hyperv_init_platform(void)
 	if (efi_enabled(EFI_BOOT))
 		x86_platform.get_nmi_reason = hv_get_nmi_reason;
 
+	/*
+	 * Hyper-V VMs have a PIT emulation quirk such that zeroing the
+	 * counter register during PIT shutdown restarts the PIT. So it
+	 * continues to interrupt @18.2 HZ. Setting i8253_clear_counter
+	 * to false tells pit_shutdown() not to zero the counter so that
+	 * the PIT really is shutdown. Generation 2 VMs don't have a PIT,
+	 * and setting this value has no effect.
+	 */
+	i8253_clear_counter_on_shutdown = false;
+
 #if IS_ENABLED(CONFIG_HYPERV)
 	/*
 	 * Setup the hook to get control post apic initialization.
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index 2e173d47b450..4d36dcc1cf87 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -165,6 +165,8 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 	struct mtrr_gentry gentry;
 	void __user *arg = (void __user *) __arg;
 
+	memset(&gentry, 0, sizeof(gentry));
+
 	switch (cmd) {
 	case MTRRIOC_ADD_ENTRY:
 	case MTRRIOC_SET_ENTRY:
diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile
new file mode 100644
index 000000000000..6895049ceef7
--- /dev/null
+++ b/arch/x86/kernel/cpu/resctrl/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_RESCTRL)	+= core.o rdtgroup.o monitor.o
+obj-$(CONFIG_RESCTRL)	+= ctrlmondata.o pseudo_lock.o
+CFLAGS_pseudo_lock.o = -I$(src)
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/resctrl/core.c
index 44272b7107ad..c3a9dc63edf2 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -22,7 +22,7 @@
  * Software Developer Manual June 2016, volume 3, section 17.17.
  */
 
-#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+#define pr_fmt(fmt)	"resctrl: " fmt
 
 #include <linux/slab.h>
 #include <linux/err.h>
@@ -30,22 +30,19 @@
 #include <linux/cpuhotplug.h>
 
 #include <asm/intel-family.h>
-#include <asm/intel_rdt_sched.h>
-#include "intel_rdt.h"
-
-#define MBA_IS_LINEAR	0x4
-#define MBA_MAX_MBPS	U32_MAX
+#include <asm/resctrl_sched.h>
+#include "internal.h"
 
 /* Mutex to protect rdtgroup access. */
 DEFINE_MUTEX(rdtgroup_mutex);
 
 /*
- * The cached intel_pqr_state is strictly per CPU and can never be
+ * The cached resctrl_pqr_state is strictly per CPU and can never be
  * updated from a remote CPU. Functions which modify the state
  * are called with interrupts disabled and no preemption, which
  * is sufficient for the protection.
  */
-DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
+DEFINE_PER_CPU(struct resctrl_pqr_state, pqr_state);
 
 /*
  * Used to store the max resource name width and max resource data width
@@ -60,9 +57,13 @@ int max_name_width, max_data_width;
 bool rdt_alloc_capable;
 
 static void
-mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
+mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
+		struct rdt_resource *r);
 static void
 cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
+static void
+mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
+	      struct rdt_resource *r);
 
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
 
@@ -72,7 +73,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_L3,
 		.name			= "L3",
 		.domains		= domain_init(RDT_RESOURCE_L3),
-		.msr_base		= IA32_L3_CBM_BASE,
+		.msr_base		= MSR_IA32_L3_CBM_BASE,
 		.msr_update		= cat_wrmsr,
 		.cache_level		= 3,
 		.cache = {
@@ -89,7 +90,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_L3DATA,
 		.name			= "L3DATA",
 		.domains		= domain_init(RDT_RESOURCE_L3DATA),
-		.msr_base		= IA32_L3_CBM_BASE,
+		.msr_base		= MSR_IA32_L3_CBM_BASE,
 		.msr_update		= cat_wrmsr,
 		.cache_level		= 3,
 		.cache = {
@@ -106,7 +107,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_L3CODE,
 		.name			= "L3CODE",
 		.domains		= domain_init(RDT_RESOURCE_L3CODE),
-		.msr_base		= IA32_L3_CBM_BASE,
+		.msr_base		= MSR_IA32_L3_CBM_BASE,
 		.msr_update		= cat_wrmsr,
 		.cache_level		= 3,
 		.cache = {
@@ -123,7 +124,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_L2,
 		.name			= "L2",
 		.domains		= domain_init(RDT_RESOURCE_L2),
-		.msr_base		= IA32_L2_CBM_BASE,
+		.msr_base		= MSR_IA32_L2_CBM_BASE,
 		.msr_update		= cat_wrmsr,
 		.cache_level		= 2,
 		.cache = {
@@ -140,7 +141,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_L2DATA,
 		.name			= "L2DATA",
 		.domains		= domain_init(RDT_RESOURCE_L2DATA),
-		.msr_base		= IA32_L2_CBM_BASE,
+		.msr_base		= MSR_IA32_L2_CBM_BASE,
 		.msr_update		= cat_wrmsr,
 		.cache_level		= 2,
 		.cache = {
@@ -157,7 +158,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_L2CODE,
 		.name			= "L2CODE",
 		.domains		= domain_init(RDT_RESOURCE_L2CODE),
-		.msr_base		= IA32_L2_CBM_BASE,
+		.msr_base		= MSR_IA32_L2_CBM_BASE,
 		.msr_update		= cat_wrmsr,
 		.cache_level		= 2,
 		.cache = {
@@ -174,10 +175,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_MBA,
 		.name			= "MB",
 		.domains		= domain_init(RDT_RESOURCE_MBA),
-		.msr_base		= IA32_MBA_THRTL_BASE,
-		.msr_update		= mba_wrmsr,
 		.cache_level		= 3,
-		.parse_ctrlval		= parse_bw,
 		.format_str		= "%d=%*u",
 		.fflags			= RFTYPE_RES_MB,
 	},
@@ -211,9 +209,10 @@ static inline void cache_alloc_hsw_probe(void)
 	struct rdt_resource *r  = &rdt_resources_all[RDT_RESOURCE_L3];
 	u32 l, h, max_cbm = BIT_MASK(20) - 1;
 
-	if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0))
+	if (wrmsr_safe(MSR_IA32_L3_CBM_BASE, max_cbm, 0))
 		return;
-	rdmsr(IA32_L3_CBM_BASE, l, h);
+
+	rdmsr(MSR_IA32_L3_CBM_BASE, l, h);
 
 	/* If all the bits were set in MSR, return success */
 	if (l != max_cbm)
@@ -259,7 +258,7 @@ static inline bool rdt_get_mb_table(struct rdt_resource *r)
 	return false;
 }
 
-static bool rdt_get_mem_config(struct rdt_resource *r)
+static bool __get_mem_config_intel(struct rdt_resource *r)
 {
 	union cpuid_0x10_3_eax eax;
 	union cpuid_0x10_x_edx edx;
@@ -285,6 +284,30 @@ static bool rdt_get_mem_config(struct rdt_resource *r)
 	return true;
 }
 
+static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
+{
+	union cpuid_0x10_3_eax eax;
+	union cpuid_0x10_x_edx edx;
+	u32 ebx, ecx;
+
+	cpuid_count(0x80000020, 1, &eax.full, &ebx, &ecx, &edx.full);
+	r->num_closid = edx.split.cos_max + 1;
+	r->default_ctrl = MAX_MBA_BW_AMD;
+
+	/* AMD does not use delay */
+	r->membw.delay_linear = false;
+
+	r->membw.min_bw = 0;
+	r->membw.bw_gran = 1;
+	/* Max value is 2048, Data width should be 4 in decimal */
+	r->data_width = 4;
+
+	r->alloc_capable = true;
+	r->alloc_enabled = true;
+
+	return true;
+}
+
 static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
 {
 	union cpuid_0x10_1_eax eax;
@@ -344,6 +367,15 @@ static int get_cache_id(int cpu, int level)
 	return -1;
 }
 
+static void
+mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+{
+	unsigned int i;
+
+	for (i = m->low; i < m->high; i++)
+		wrmsrl(r->msr_base + i, d->ctrl_val[i]);
+}
+
 /*
  * Map the memory b/w percentage value to delay values
  * that can be written to QOS_MSRs.
@@ -359,7 +391,8 @@ u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
 }
 
 static void
-mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
+		struct rdt_resource *r)
 {
 	unsigned int i;
 
@@ -421,7 +454,7 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 	struct list_head *l;
 
 	if (id < 0)
-		return ERR_PTR(id);
+		return ERR_PTR(-ENODEV);
 
 	list_for_each(l, &r->domains) {
 		d = list_entry(l, struct rdt_domain, list);
@@ -639,7 +672,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 
 static void clear_closid_rmid(int cpu)
 {
-	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+	struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state);
 
 	state->default_closid = 0;
 	state->default_rmid = 0;
@@ -648,7 +681,7 @@ static void clear_closid_rmid(int cpu)
 	wrmsr(IA32_PQR_ASSOC, 0, 0);
 }
 
-static int intel_rdt_online_cpu(unsigned int cpu)
+static int resctrl_online_cpu(unsigned int cpu)
 {
 	struct rdt_resource *r;
 
@@ -674,7 +707,7 @@ static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
 	}
 }
 
-static int intel_rdt_offline_cpu(unsigned int cpu)
+static int resctrl_offline_cpu(unsigned int cpu)
 {
 	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
@@ -794,6 +827,19 @@ static bool __init rdt_cpu_has(int flag)
 	return ret;
 }
 
+static __init bool get_mem_config(void)
+{
+	if (!rdt_cpu_has(X86_FEATURE_MBA))
+		return false;
+
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		return __get_mem_config_intel(&rdt_resources_all[RDT_RESOURCE_MBA]);
+	else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		return __rdt_get_mem_config_amd(&rdt_resources_all[RDT_RESOURCE_MBA]);
+
+	return false;
+}
+
 static __init bool get_rdt_alloc_resources(void)
 {
 	bool ret = false;
@@ -818,10 +864,9 @@ static __init bool get_rdt_alloc_resources(void)
 		ret = true;
 	}
 
-	if (rdt_cpu_has(X86_FEATURE_MBA)) {
-		if (rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA]))
-			ret = true;
-	}
+	if (get_mem_config())
+		ret = true;
+
 	return ret;
 }
 
@@ -840,7 +885,7 @@ static __init bool get_rdt_mon_resources(void)
 	return !rdt_get_mon_l3_config(&rdt_resources_all[RDT_RESOURCE_L3]);
 }
 
-static __init void rdt_quirks(void)
+static __init void __check_quirks_intel(void)
 {
 	switch (boot_cpu_data.x86_model) {
 	case INTEL_FAM6_HASWELL_X:
@@ -855,30 +900,91 @@ static __init void rdt_quirks(void)
 	}
 }
 
+static __init void check_quirks(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		__check_quirks_intel();
+}
+
 static __init bool get_rdt_resources(void)
 {
-	rdt_quirks();
 	rdt_alloc_capable = get_rdt_alloc_resources();
 	rdt_mon_capable = get_rdt_mon_resources();
 
 	return (rdt_mon_capable || rdt_alloc_capable);
 }
 
+static __init void rdt_init_res_defs_intel(void)
+{
+	struct rdt_resource *r;
+
+	for_each_rdt_resource(r) {
+		if (r->rid == RDT_RESOURCE_L3 ||
+		    r->rid == RDT_RESOURCE_L3DATA ||
+		    r->rid == RDT_RESOURCE_L3CODE ||
+		    r->rid == RDT_RESOURCE_L2 ||
+		    r->rid == RDT_RESOURCE_L2DATA ||
+		    r->rid == RDT_RESOURCE_L2CODE)
+			r->cbm_validate = cbm_validate_intel;
+		else if (r->rid == RDT_RESOURCE_MBA) {
+			r->msr_base = MSR_IA32_MBA_THRTL_BASE;
+			r->msr_update = mba_wrmsr_intel;
+			r->parse_ctrlval = parse_bw_intel;
+		}
+	}
+}
+
+static __init void rdt_init_res_defs_amd(void)
+{
+	struct rdt_resource *r;
+
+	for_each_rdt_resource(r) {
+		if (r->rid == RDT_RESOURCE_L3 ||
+		    r->rid == RDT_RESOURCE_L3DATA ||
+		    r->rid == RDT_RESOURCE_L3CODE ||
+		    r->rid == RDT_RESOURCE_L2 ||
+		    r->rid == RDT_RESOURCE_L2DATA ||
+		    r->rid == RDT_RESOURCE_L2CODE)
+			r->cbm_validate = cbm_validate_amd;
+		else if (r->rid == RDT_RESOURCE_MBA) {
+			r->msr_base = MSR_IA32_MBA_BW_BASE;
+			r->msr_update = mba_wrmsr_amd;
+			r->parse_ctrlval = parse_bw_amd;
+		}
+	}
+}
+
+static __init void rdt_init_res_defs(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		rdt_init_res_defs_intel();
+	else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		rdt_init_res_defs_amd();
+}
+
 static enum cpuhp_state rdt_online;
 
-static int __init intel_rdt_late_init(void)
+static int __init resctrl_late_init(void)
 {
 	struct rdt_resource *r;
 	int state, ret;
 
+	/*
+	 * Initialize functions(or definitions) that are different
+	 * between vendors here.
+	 */
+	rdt_init_res_defs();
+
+	check_quirks();
+
 	if (!get_rdt_resources())
 		return -ENODEV;
 
 	rdt_init_padding();
 
 	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
-				  "x86/rdt/cat:online:",
-				  intel_rdt_online_cpu, intel_rdt_offline_cpu);
+				  "x86/resctrl/cat:online:",
+				  resctrl_online_cpu, resctrl_offline_cpu);
 	if (state < 0)
 		return state;
 
@@ -890,20 +996,20 @@ static int __init intel_rdt_late_init(void)
 	rdt_online = state;
 
 	for_each_alloc_capable_rdt_resource(r)
-		pr_info("Intel RDT %s allocation detected\n", r->name);
+		pr_info("%s allocation detected\n", r->name);
 
 	for_each_mon_capable_rdt_resource(r)
-		pr_info("Intel RDT %s monitoring detected\n", r->name);
+		pr_info("%s monitoring detected\n", r->name);
 
 	return 0;
 }
 
-late_initcall(intel_rdt_late_init);
+late_initcall(resctrl_late_init);
 
-static void __exit intel_rdt_exit(void)
+static void __exit resctrl_exit(void)
 {
 	cpuhp_remove_state(rdt_online);
 	rdtgroup_exit();
 }
 
-__exitcall(intel_rdt_exit);
+__exitcall(resctrl_exit);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 27937458c231..2dbd990a2eb7 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -23,10 +23,58 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <linux/cpu.h>
 #include <linux/kernfs.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
-#include "intel_rdt.h"
+#include "internal.h"
+
+/*
+ * Check whether MBA bandwidth percentage value is correct. The value is
+ * checked against the minimum and maximum bandwidth values specified by
+ * the hardware. The allocated bandwidth percentage is rounded to the next
+ * control step available on the hardware.
+ */
+static bool bw_validate_amd(char *buf, unsigned long *data,
+			    struct rdt_resource *r)
+{
+	unsigned long bw;
+	int ret;
+
+	ret = kstrtoul(buf, 10, &bw);
+	if (ret) {
+		rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
+		return false;
+	}
+
+	if (bw < r->membw.min_bw || bw > r->default_ctrl) {
+		rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
+				    r->membw.min_bw, r->default_ctrl);
+		return false;
+	}
+
+	*data = roundup(bw, (unsigned long)r->membw.bw_gran);
+	return true;
+}
+
+int parse_bw_amd(struct rdt_parse_data *data, struct rdt_resource *r,
+		 struct rdt_domain *d)
+{
+	unsigned long bw_val;
+
+	if (d->have_new_ctrl) {
+		rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
+		return -EINVAL;
+	}
+
+	if (!bw_validate_amd(data->buf, &bw_val, r))
+		return -EINVAL;
+
+	d->new_ctrl = bw_val;
+	d->have_new_ctrl = true;
+
+	return 0;
+}
 
 /*
  * Check whether MBA bandwidth percentage value is correct. The value is
@@ -64,13 +112,13 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 	return true;
 }
 
-int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
-	     struct rdt_domain *d)
+int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r,
+		   struct rdt_domain *d)
 {
 	unsigned long bw_val;
 
 	if (d->have_new_ctrl) {
-		rdt_last_cmd_printf("duplicate domain %d\n", d->id);
+		rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
 		return -EINVAL;
 	}
 
@@ -88,7 +136,7 @@ int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
  *	are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
  * Additionally Haswell requires at least two bits set.
  */
-static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
+bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
 {
 	unsigned long first_bit, zero_bit, val;
 	unsigned int cbm_len = r->cache.cbm_len;
@@ -96,12 +144,12 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 
 	ret = kstrtoul(buf, 16, &val);
 	if (ret) {
-		rdt_last_cmd_printf("non-hex character in mask %s\n", buf);
+		rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf);
 		return false;
 	}
 
 	if (val == 0 || val > r->default_ctrl) {
-		rdt_last_cmd_puts("mask out of range\n");
+		rdt_last_cmd_puts("Mask out of range\n");
 		return false;
 	}
 
@@ -109,12 +157,12 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
 
 	if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) {
-		rdt_last_cmd_printf("mask %lx has non-consecutive 1-bits\n", val);
+		rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val);
 		return false;
 	}
 
 	if ((zero_bit - first_bit) < r->cache.min_cbm_bits) {
-		rdt_last_cmd_printf("Need at least %d bits in mask\n",
+		rdt_last_cmd_printf("Need at least %d bits in the mask\n",
 				    r->cache.min_cbm_bits);
 		return false;
 	}
@@ -124,6 +172,30 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 }
 
 /*
+ * Check whether a cache bit mask is valid. AMD allows non-contiguous
+ * bitmasks
+ */
+bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r)
+{
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret) {
+		rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf);
+		return false;
+	}
+
+	if (val > r->default_ctrl) {
+		rdt_last_cmd_puts("Mask out of range\n");
+		return false;
+	}
+
+	*data = val;
+	return true;
+}
+
+/*
  * Read one cache bit mask (hex). Check that it is valid for the current
  * resource type.
  */
@@ -134,7 +206,7 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
 	u32 cbm_val;
 
 	if (d->have_new_ctrl) {
-		rdt_last_cmd_printf("duplicate domain %d\n", d->id);
+		rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
 		return -EINVAL;
 	}
 
@@ -144,17 +216,17 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
 	 */
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
 	    rdtgroup_pseudo_locked_in_hierarchy(d)) {
-		rdt_last_cmd_printf("pseudo-locked region in hierarchy\n");
+		rdt_last_cmd_puts("Pseudo-locked region in hierarchy\n");
 		return -EINVAL;
 	}
 
-	if (!cbm_validate(data->buf, &cbm_val, r))
+	if (!r->cbm_validate(data->buf, &cbm_val, r))
 		return -EINVAL;
 
 	if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
 	     rdtgrp->mode == RDT_MODE_SHAREABLE) &&
 	    rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) {
-		rdt_last_cmd_printf("CBM overlaps with pseudo-locked region\n");
+		rdt_last_cmd_puts("CBM overlaps with pseudo-locked region\n");
 		return -EINVAL;
 	}
 
@@ -163,14 +235,14 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
 	 * either is exclusive.
 	 */
 	if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) {
-		rdt_last_cmd_printf("overlaps with exclusive group\n");
+		rdt_last_cmd_puts("Overlaps with exclusive group\n");
 		return -EINVAL;
 	}
 
 	if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) {
 		if (rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
 		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-			rdt_last_cmd_printf("overlaps with other group\n");
+			rdt_last_cmd_puts("Overlaps with other group\n");
 			return -EINVAL;
 		}
 	}
@@ -292,7 +364,7 @@ static int rdtgroup_parse_resource(char *resname, char *tok,
 		if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid)
 			return parse_line(tok, r, rdtgrp);
 	}
-	rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname);
+	rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname);
 	return -EINVAL;
 }
 
@@ -310,9 +382,11 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 		return -EINVAL;
 	buf[nbytes - 1] = '\0';
 
+	cpus_read_lock();
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (!rdtgrp) {
 		rdtgroup_kn_unlock(of->kn);
+		cpus_read_unlock();
 		return -ENOENT;
 	}
 	rdt_last_cmd_clear();
@@ -323,7 +397,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	 */
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
 		ret = -EINVAL;
-		rdt_last_cmd_puts("resource group is pseudo-locked\n");
+		rdt_last_cmd_puts("Resource group is pseudo-locked\n");
 		goto out;
 	}
 
@@ -367,6 +441,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 
 out:
 	rdtgroup_kn_unlock(of->kn);
+	cpus_read_unlock();
 	return ret ?: nbytes;
 }
 
@@ -463,7 +538,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 
 	r = &rdt_resources_all[resid];
 	d = rdt_find_domain(r, domid, NULL);
-	if (!d) {
+	if (IS_ERR_OR_NULL(d)) {
 		ret = -ENOENT;
 		goto out;
 	}
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 3736f6dc9545..822b7db634ee 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -1,20 +1,24 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_INTEL_RDT_H
-#define _ASM_X86_INTEL_RDT_H
+#ifndef _ASM_X86_RESCTRL_INTERNAL_H
+#define _ASM_X86_RESCTRL_INTERNAL_H
 
 #include <linux/sched.h>
 #include <linux/kernfs.h>
 #include <linux/jump_label.h>
 
-#define IA32_L3_QOS_CFG		0xc81
-#define IA32_L2_QOS_CFG		0xc82
-#define IA32_L3_CBM_BASE	0xc90
-#define IA32_L2_CBM_BASE	0xd10
-#define IA32_MBA_THRTL_BASE	0xd50
+#define MSR_IA32_L3_QOS_CFG		0xc81
+#define MSR_IA32_L2_QOS_CFG		0xc82
+#define MSR_IA32_L3_CBM_BASE		0xc90
+#define MSR_IA32_L2_CBM_BASE		0xd10
+#define MSR_IA32_MBA_THRTL_BASE		0xd50
+#define MSR_IA32_MBA_BW_BASE		0xc0000200
 
-#define L3_QOS_CDP_ENABLE	0x01ULL
+#define MSR_IA32_QM_CTR			0x0c8e
+#define MSR_IA32_QM_EVTSEL		0x0c8d
 
-#define L2_QOS_CDP_ENABLE	0x01ULL
+#define L3_QOS_CDP_ENABLE		0x01ULL
+
+#define L2_QOS_CDP_ENABLE		0x01ULL
 
 /*
  * Event IDs are used to program IA32_QM_EVTSEL before reading event
@@ -29,6 +33,9 @@
 #define MBM_CNTR_WIDTH			24
 #define MBM_OVERFLOW_INTERVAL		1000
 #define MAX_MBA_BW			100u
+#define MBA_IS_LINEAR			0x4
+#define MBA_MAX_MBPS			U32_MAX
+#define MAX_MBA_BW_AMD			0x800
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
@@ -69,7 +76,7 @@ struct rmid_read {
 	u64			val;
 };
 
-extern unsigned int intel_cqm_threshold;
+extern unsigned int resctrl_cqm_threshold;
 extern bool rdt_alloc_capable;
 extern bool rdt_mon_capable;
 extern unsigned int rdt_mon_features;
@@ -391,9 +398,9 @@ struct rdt_parse_data {
  * struct rdt_resource - attributes of an RDT resource
  * @rid:		The index of the resource
  * @alloc_enabled:	Is allocation enabled on this machine
- * @mon_enabled:		Is monitoring enabled for this feature
+ * @mon_enabled:	Is monitoring enabled for this feature
  * @alloc_capable:	Is allocation available on this machine
- * @mon_capable:		Is monitor feature available on this machine
+ * @mon_capable:	Is monitor feature available on this machine
  * @name:		Name to use in "schemata" file
  * @num_closid:		Number of CLOSIDs available
  * @cache_level:	Which cache level defines scope of this resource
@@ -405,10 +412,11 @@ struct rdt_parse_data {
  * @cache:		Cache allocation related data
  * @format_str:		Per resource format string to show domain value
  * @parse_ctrlval:	Per resource function pointer to parse control values
- * @evt_list:			List of monitoring events
- * @num_rmid:			Number of RMIDs available
- * @mon_scale:			cqm counter * mon_scale = occupancy in bytes
- * @fflags:			flags to choose base and info files
+ * @cbm_validate	Cache bitmask validate function
+ * @evt_list:		List of monitoring events
+ * @num_rmid:		Number of RMIDs available
+ * @mon_scale:		cqm counter * mon_scale = occupancy in bytes
+ * @fflags:		flags to choose base and info files
  */
 struct rdt_resource {
 	int			rid;
@@ -431,6 +439,7 @@ struct rdt_resource {
 	int (*parse_ctrlval)(struct rdt_parse_data *data,
 			     struct rdt_resource *r,
 			     struct rdt_domain *d);
+	bool (*cbm_validate)(char *buf, u32 *data, struct rdt_resource *r);
 	struct list_head	evt_list;
 	int			num_rmid;
 	unsigned int		mon_scale;
@@ -439,8 +448,10 @@ struct rdt_resource {
 
 int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
 	      struct rdt_domain *d);
-int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
-	     struct rdt_domain *d);
+int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r,
+		   struct rdt_domain *d);
+int parse_bw_amd(struct rdt_parse_data *data, struct rdt_resource *r,
+		 struct rdt_domain *d);
 
 extern struct mutex rdtgroup_mutex;
 
@@ -463,6 +474,10 @@ enum {
 	RDT_NUM_RESOURCES,
 };
 
+#define for_each_rdt_resource(r)					      \
+	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
+	     r++)
+
 #define for_each_capable_rdt_resource(r)				      \
 	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
 	     r++)							      \
@@ -567,5 +582,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
 void cqm_handle_limbo(struct work_struct *work);
 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);
 
-#endif /* _ASM_X86_INTEL_RDT_H */
+#endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index b0f3aed76b75..f33f11f69078 100644
--- a/arch/x86/kernel/cpu/intel_rdt_monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -26,10 +26,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <asm/cpu_device_id.h>
-#include "intel_rdt.h"
-
-#define MSR_IA32_QM_CTR		0x0c8e
-#define MSR_IA32_QM_EVTSEL		0x0c8d
+#include "internal.h"
 
 struct rmid_entry {
 	u32				rmid;
@@ -73,7 +70,7 @@ unsigned int rdt_mon_features;
  * This is the threshold cache occupancy at which we will consider an
  * RMID available for re-allocation.
  */
-unsigned int intel_cqm_threshold;
+unsigned int resctrl_cqm_threshold;
 
 static inline struct rmid_entry *__rmid_entry(u32 rmid)
 {
@@ -107,7 +104,7 @@ static bool rmid_dirty(struct rmid_entry *entry)
 {
 	u64 val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
 
-	return val >= intel_cqm_threshold;
+	return val >= resctrl_cqm_threshold;
 }
 
 /*
@@ -187,7 +184,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 	list_for_each_entry(d, &r->domains, list) {
 		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
 			val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
-			if (val <= intel_cqm_threshold)
+			if (val <= resctrl_cqm_threshold)
 				continue;
 		}
 
@@ -625,6 +622,7 @@ static void l3_mon_evt_init(struct rdt_resource *r)
 
 int rdt_get_mon_l3_config(struct rdt_resource *r)
 {
+	unsigned int cl_size = boot_cpu_data.x86_cache_size;
 	int ret;
 
 	r->mon_scale = boot_cpu_data.x86_cache_occ_scale;
@@ -637,10 +635,10 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
 	 *
 	 * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC.
 	 */
-	intel_cqm_threshold = boot_cpu_data.x86_cache_size * 1024 / r->num_rmid;
+	resctrl_cqm_threshold = cl_size * 1024 / r->num_rmid;
 
 	/* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */
-	intel_cqm_threshold /= r->mon_scale;
+	resctrl_cqm_threshold /= r->mon_scale;
 
 	ret = dom_data_init(r);
 	if (ret)
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 815b4e92522c..14bed6af8377 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -24,14 +24,14 @@
 
 #include <asm/cacheflush.h>
 #include <asm/intel-family.h>
-#include <asm/intel_rdt_sched.h>
+#include <asm/resctrl_sched.h>
 #include <asm/perf_event.h>
 
 #include "../../events/perf_event.h" /* For X86_CONFIG() */
-#include "intel_rdt.h"
+#include "internal.h"
 
 #define CREATE_TRACE_POINTS
-#include "intel_rdt_pseudo_lock_event.h"
+#include "pseudo_lock_event.h"
 
 /*
  * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware
@@ -213,7 +213,7 @@ static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
 	for_each_cpu(cpu, &plr->d->cpu_mask) {
 		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
 		if (!pm_req) {
-			rdt_last_cmd_puts("fail allocating mem for PM QoS\n");
+			rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
 			ret = -ENOMEM;
 			goto out_err;
 		}
@@ -222,7 +222,7 @@ static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
 					     DEV_PM_QOS_RESUME_LATENCY,
 					     30);
 		if (ret < 0) {
-			rdt_last_cmd_printf("fail to add latency req cpu%d\n",
+			rdt_last_cmd_printf("Failed to add latency req CPU%d\n",
 					    cpu);
 			kfree(pm_req);
 			ret = -1;
@@ -289,7 +289,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 	plr->cpu = cpumask_first(&plr->d->cpu_mask);
 
 	if (!cpu_online(plr->cpu)) {
-		rdt_last_cmd_printf("cpu %u associated with cache not online\n",
+		rdt_last_cmd_printf("CPU %u associated with cache not online\n",
 				    plr->cpu);
 		ret = -ENODEV;
 		goto out_region;
@@ -307,7 +307,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 	}
 
 	ret = -1;
-	rdt_last_cmd_puts("unable to determine cache line size\n");
+	rdt_last_cmd_puts("Unable to determine cache line size\n");
 out_region:
 	pseudo_lock_region_clear(plr);
 	return ret;
@@ -361,14 +361,14 @@ static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr)
 	 * KMALLOC_MAX_SIZE.
 	 */
 	if (plr->size > KMALLOC_MAX_SIZE) {
-		rdt_last_cmd_puts("requested region exceeds maximum size\n");
+		rdt_last_cmd_puts("Requested region exceeds maximum size\n");
 		ret = -E2BIG;
 		goto out_region;
 	}
 
 	plr->kmem = kzalloc(plr->size, GFP_KERNEL);
 	if (!plr->kmem) {
-		rdt_last_cmd_puts("unable to allocate memory\n");
+		rdt_last_cmd_puts("Unable to allocate memory\n");
 		ret = -ENOMEM;
 		goto out_region;
 	}
@@ -665,7 +665,7 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
 	 * default closid associated with it.
 	 */
 	if (rdtgrp == &rdtgroup_default) {
-		rdt_last_cmd_puts("cannot pseudo-lock default group\n");
+		rdt_last_cmd_puts("Cannot pseudo-lock default group\n");
 		return -EINVAL;
 	}
 
@@ -707,17 +707,17 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
 	 */
 	prefetch_disable_bits = get_prefetch_disable_bits();
 	if (prefetch_disable_bits == 0) {
-		rdt_last_cmd_puts("pseudo-locking not supported\n");
+		rdt_last_cmd_puts("Pseudo-locking not supported\n");
 		return -EINVAL;
 	}
 
 	if (rdtgroup_monitor_in_progress(rdtgrp)) {
-		rdt_last_cmd_puts("monitoring in progress\n");
+		rdt_last_cmd_puts("Monitoring in progress\n");
 		return -EINVAL;
 	}
 
 	if (rdtgroup_tasks_assigned(rdtgrp)) {
-		rdt_last_cmd_puts("tasks assigned to resource group\n");
+		rdt_last_cmd_puts("Tasks assigned to resource group\n");
 		return -EINVAL;
 	}
 
@@ -727,13 +727,13 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
 	}
 
 	if (rdtgroup_locksetup_user_restrict(rdtgrp)) {
-		rdt_last_cmd_puts("unable to modify resctrl permissions\n");
+		rdt_last_cmd_puts("Unable to modify resctrl permissions\n");
 		return -EIO;
 	}
 
 	ret = pseudo_lock_init(rdtgrp);
 	if (ret) {
-		rdt_last_cmd_puts("unable to init pseudo-lock region\n");
+		rdt_last_cmd_puts("Unable to init pseudo-lock region\n");
 		goto out_release;
 	}
 
@@ -770,7 +770,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
 	if (rdt_mon_capable) {
 		ret = alloc_rmid();
 		if (ret < 0) {
-			rdt_last_cmd_puts("out of RMIDs\n");
+			rdt_last_cmd_puts("Out of RMIDs\n");
 			return ret;
 		}
 		rdtgrp->mon.rmid = ret;
@@ -1304,7 +1304,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 					"pseudo_lock/%u", plr->cpu);
 	if (IS_ERR(thread)) {
 		ret = PTR_ERR(thread);
-		rdt_last_cmd_printf("locking thread returned error %d\n", ret);
+		rdt_last_cmd_printf("Locking thread returned error %d\n", ret);
 		goto out_cstates;
 	}
 
@@ -1322,13 +1322,13 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 		 * the cleared, but not freed, plr struct resulting in an
 		 * empty pseudo-locking loop.
 		 */
-		rdt_last_cmd_puts("locking thread interrupted\n");
+		rdt_last_cmd_puts("Locking thread interrupted\n");
 		goto out_cstates;
 	}
 
 	ret = pseudo_lock_minor_get(&new_minor);
 	if (ret < 0) {
-		rdt_last_cmd_puts("unable to obtain a new minor number\n");
+		rdt_last_cmd_puts("Unable to obtain a new minor number\n");
 		goto out_cstates;
 	}
 
@@ -1360,7 +1360,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 
 	if (IS_ERR(dev)) {
 		ret = PTR_ERR(dev);
-		rdt_last_cmd_printf("failed to create character device: %d\n",
+		rdt_last_cmd_printf("Failed to create character device: %d\n",
 				    ret);
 		goto out_debugfs;
 	}
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h b/arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h
index 2c041e6d9f05..428ebbd4270b 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h
@@ -39,5 +39,5 @@ TRACE_EVENT(pseudo_lock_l3,
 
 #undef TRACE_INCLUDE_PATH
 #define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE intel_rdt_pseudo_lock_event
+#define TRACE_INCLUDE_FILE pseudo_lock_event
 #include <trace/define_trace.h>
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index f27b8115ffa2..8388adf241b2 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -35,8 +35,8 @@
 
 #include <uapi/linux/magic.h>
 
-#include <asm/intel_rdt_sched.h>
-#include "intel_rdt.h"
+#include <asm/resctrl_sched.h>
+#include "internal.h"
 
 DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
 DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
@@ -298,7 +298,7 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 }
 
 /*
- * This is safe against intel_rdt_sched_in() called from __switch_to()
+ * This is safe against resctrl_sched_in() called from __switch_to()
  * because __switch_to() is executed with interrupts disabled. A local call
  * from update_closid_rmid() is proteced against __switch_to() because
  * preemption is disabled.
@@ -317,7 +317,7 @@ static void update_cpu_closid_rmid(void *info)
 	 * executing task might have its own closid selected. Just reuse
 	 * the context switch code.
 	 */
-	intel_rdt_sched_in();
+	resctrl_sched_in();
 }
 
 /*
@@ -345,7 +345,7 @@ static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
 	/* Check whether cpus belong to parent ctrl group */
 	cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask);
 	if (cpumask_weight(tmpmask)) {
-		rdt_last_cmd_puts("can only add CPUs to mongroup that belong to parent\n");
+		rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n");
 		return -EINVAL;
 	}
 
@@ -470,14 +470,14 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 	rdt_last_cmd_clear();
 	if (!rdtgrp) {
 		ret = -ENOENT;
-		rdt_last_cmd_puts("directory was removed\n");
+		rdt_last_cmd_puts("Directory was removed\n");
 		goto unlock;
 	}
 
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
 	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
 		ret = -EINVAL;
-		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		rdt_last_cmd_puts("Pseudo-locking in progress\n");
 		goto unlock;
 	}
 
@@ -487,7 +487,7 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 		ret = cpumask_parse(buf, newmask);
 
 	if (ret) {
-		rdt_last_cmd_puts("bad cpu list/mask\n");
+		rdt_last_cmd_puts("Bad CPU list/mask\n");
 		goto unlock;
 	}
 
@@ -495,7 +495,7 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 	cpumask_andnot(tmpmask, newmask, cpu_online_mask);
 	if (cpumask_weight(tmpmask)) {
 		ret = -EINVAL;
-		rdt_last_cmd_puts("can only assign online cpus\n");
+		rdt_last_cmd_puts("Can only assign online CPUs\n");
 		goto unlock;
 	}
 
@@ -542,7 +542,7 @@ static void move_myself(struct callback_head *head)
 
 	preempt_disable();
 	/* update PQR_ASSOC MSR to make resource group go into effect */
-	intel_rdt_sched_in();
+	resctrl_sched_in();
 	preempt_enable();
 
 	kfree(callback);
@@ -574,7 +574,7 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 		 */
 		atomic_dec(&rdtgrp->waitcount);
 		kfree(callback);
-		rdt_last_cmd_puts("task exited\n");
+		rdt_last_cmd_puts("Task exited\n");
 	} else {
 		/*
 		 * For ctrl_mon groups move both closid and rmid.
@@ -692,7 +692,7 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
 	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
 		ret = -EINVAL;
-		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		rdt_last_cmd_puts("Pseudo-locking in progress\n");
 		goto unlock;
 	}
 
@@ -926,7 +926,7 @@ static int max_threshold_occ_show(struct kernfs_open_file *of,
 {
 	struct rdt_resource *r = of->kn->parent->priv;
 
-	seq_printf(seq, "%u\n", intel_cqm_threshold * r->mon_scale);
+	seq_printf(seq, "%u\n", resctrl_cqm_threshold * r->mon_scale);
 
 	return 0;
 }
@@ -945,7 +945,7 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
 	if (bytes > (boot_cpu_data.x86_cache_size * 1024))
 		return -EINVAL;
 
-	intel_cqm_threshold = bytes / r->mon_scale;
+	resctrl_cqm_threshold = bytes / r->mon_scale;
 
 	return nbytes;
 }
@@ -1029,7 +1029,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d,
 	 * peer RDT CDP resource. Hence the WARN.
 	 */
 	_d_cdp = rdt_find_domain(_r_cdp, d->id, NULL);
-	if (WARN_ON(!_d_cdp)) {
+	if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) {
 		_r_cdp = NULL;
 		ret = -EINVAL;
 	}
@@ -1158,14 +1158,14 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
 		list_for_each_entry(d, &r->domains, list) {
 			if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid],
 						  rdtgrp->closid, false)) {
-				rdt_last_cmd_puts("schemata overlaps\n");
+				rdt_last_cmd_puts("Schemata overlaps\n");
 				return false;
 			}
 		}
 	}
 
 	if (!has_cache) {
-		rdt_last_cmd_puts("cannot be exclusive without CAT/CDP\n");
+		rdt_last_cmd_puts("Cannot be exclusive without CAT/CDP\n");
 		return false;
 	}
 
@@ -1206,7 +1206,7 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
 		goto out;
 
 	if (mode == RDT_MODE_PSEUDO_LOCKED) {
-		rdt_last_cmd_printf("cannot change pseudo-locked group\n");
+		rdt_last_cmd_puts("Cannot change pseudo-locked group\n");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1235,7 +1235,7 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
 			goto out;
 		rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP;
 	} else {
-		rdt_last_cmd_printf("unknown/unsupported mode\n");
+		rdt_last_cmd_puts("Unknown or unsupported mode\n");
 		ret = -EINVAL;
 	}
 
@@ -1722,14 +1722,14 @@ static void l3_qos_cfg_update(void *arg)
 {
 	bool *enable = arg;
 
-	wrmsrl(IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
+	wrmsrl(MSR_IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
 }
 
 static void l2_qos_cfg_update(void *arg)
 {
 	bool *enable = arg;
 
-	wrmsrl(IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
+	wrmsrl(MSR_IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
 }
 
 static inline bool is_mba_linear(void)
@@ -1878,7 +1878,10 @@ static int parse_rdtgroupfs_options(char *data)
 			if (ret)
 				goto out;
 		} else if (!strcmp(token, "mba_MBps")) {
-			ret = set_mba_sc(true);
+			if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+				ret = set_mba_sc(true);
+			else
+				ret = -EINVAL;
 			if (ret)
 				goto out;
 		} else {
@@ -2540,7 +2543,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 			tmp_cbm = d->new_ctrl;
 			if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) <
 			    r->cache.min_cbm_bits) {
-				rdt_last_cmd_printf("no space on %s:%d\n",
+				rdt_last_cmd_printf("No space on %s:%d\n",
 						    r->name, d->id);
 				return -ENOSPC;
 			}
@@ -2557,7 +2560,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 			continue;
 		ret = update_domains(r, rdtgrp->closid);
 		if (ret < 0) {
-			rdt_last_cmd_puts("failed to initialize allocations\n");
+			rdt_last_cmd_puts("Failed to initialize allocations\n");
 			return ret;
 		}
 		rdtgrp->mode = RDT_MODE_SHAREABLE;
@@ -2580,7 +2583,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	rdt_last_cmd_clear();
 	if (!prdtgrp) {
 		ret = -ENODEV;
-		rdt_last_cmd_puts("directory was removed\n");
+		rdt_last_cmd_puts("Directory was removed\n");
 		goto out_unlock;
 	}
 
@@ -2588,7 +2591,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	    (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
 	     prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
 		ret = -EINVAL;
-		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		rdt_last_cmd_puts("Pseudo-locking in progress\n");
 		goto out_unlock;
 	}
 
@@ -2596,7 +2599,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
 	if (!rdtgrp) {
 		ret = -ENOSPC;
-		rdt_last_cmd_puts("kernel out of memory\n");
+		rdt_last_cmd_puts("Kernel out of memory\n");
 		goto out_unlock;
 	}
 	*r = rdtgrp;
@@ -2637,7 +2640,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	if (rdt_mon_capable) {
 		ret = alloc_rmid();
 		if (ret < 0) {
-			rdt_last_cmd_puts("out of RMIDs\n");
+			rdt_last_cmd_puts("Out of RMIDs\n");
 			goto out_destroy;
 		}
 		rdtgrp->mon.rmid = ret;
@@ -2725,7 +2728,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 	kn = rdtgrp->kn;
 	ret = closid_alloc();
 	if (ret < 0) {
-		rdt_last_cmd_puts("out of CLOSIDs\n");
+		rdt_last_cmd_puts("Out of CLOSIDs\n");
 		goto out_common_fail;
 	}
 	closid = ret;
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 772c219b6889..94aa1c72ca98 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -5,9 +5,10 @@
 #include <linux/cpu.h>
 
 #include <asm/pat.h>
+#include <asm/apic.h>
 #include <asm/processor.h>
 
-#include <asm/apic.h>
+#include "cpu.h"
 
 struct cpuid_bit {
 	u16 feature;
@@ -17,7 +18,11 @@ struct cpuid_bit {
 	u32 sub_leaf;
 };
 
-/* Please keep the leaf sorted by cpuid_bit.level for faster search. */
+/*
+ * Please keep the leaf sorted by cpuid_bit.level for faster search.
+ * X86_FEATURE_MBA is supported by both Intel and AMD. But the CPUID
+ * levels are different and there is a separate entry for each.
+ */
 static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
@@ -29,6 +34,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_HW_PSTATE,	CPUID_EDX,  7, 0x80000007, 0 },
 	{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
 	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
+	{ X86_FEATURE_MBA,		CPUID_EBX,  6, 0x80000008, 0 },
 	{ X86_FEATURE_SME,		CPUID_EAX,  0, 0x8000001f, 0 },
 	{ X86_FEATURE_SEV,		CPUID_EAX,  1, 0x8000001f, 0 },
 	{ 0, 0, 0, 0, 0 }
@@ -56,27 +62,3 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, cb->feature);
 	}
 }
-
-u32 get_scattered_cpuid_leaf(unsigned int level, unsigned int sub_leaf,
-			     enum cpuid_regs_idx reg)
-{
-	const struct cpuid_bit *cb;
-	u32 cpuid_val = 0;
-
-	for (cb = cpuid_bits; cb->feature; cb++) {
-
-		if (level > cb->level)
-			continue;
-
-		if (level < cb->level)
-			break;
-
-		if (reg == cb->reg && sub_leaf == cb->sub_leaf) {
-			if (cpu_has(&boot_cpu_data, cb->feature))
-				cpuid_val |= BIT(cb->bit);
-		}
-	}
-
-	return cpuid_val;
-}
-EXPORT_SYMBOL_GPL(get_scattered_cpuid_leaf);
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 71ca064e3794..8f6c784141d1 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -10,6 +10,8 @@
 #include <asm/pat.h>
 #include <asm/processor.h>
 
+#include "cpu.h"
+
 /* leaf 0xb SMT level */
 #define SMT_LEVEL	0
 
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index d9ab49bed8af..0eda91f8eeac 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -77,7 +77,7 @@ static __init int setup_vmw_sched_clock(char *s)
 }
 early_param("no-vmw-sched-clock", setup_vmw_sched_clock);
 
-static unsigned long long vmware_sched_clock(void)
+static unsigned long long notrace vmware_sched_clock(void)
 {
 	unsigned long long ns;