1 files changed, 627 insertions, 45 deletions

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bfca937bdcc3..c37e66e493bf 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -12,34 +12,85 @@
 #include <linux/utsname.h>
 #include <linux/cpu.h>
 #include <linux/module.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
 
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
 #include <asm/cmdline.h>
 #include <asm/bugs.h>
 #include <asm/processor.h>
 #include <asm/processor-flags.h>
 #include <asm/fpu/internal.h>
 #include <asm/msr.h>
+#include <asm/vmx.h>
 #include <asm/paravirt.h>
 #include <asm/alternative.h>
 #include <asm/pgtable.h>
 #include <asm/set_memory.h>
 #include <asm/intel-family.h>
+#include <asm/e820/api.h>
+#include <asm/hypervisor.h>
 
 static void __init spectre_v2_select_mitigation(void);
+static void __init ssb_select_mitigation(void);
+static void __init l1tf_select_mitigation(void);
+
+/* The base value of the SPEC_CTRL MSR that always has to be preserved. */
+u64 x86_spec_ctrl_base;
+EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
+static DEFINE_MUTEX(spec_ctrl_mutex);
+
+/*
+ * The vendor and possibly platform specific bits which can be modified in
+ * x86_spec_ctrl_base.
+ */
+static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS;
+
+/*
+ * AMD specific MSR info for Speculative Store Bypass control.
+ * x86_amd_ls_cfg_ssbd_mask is initialized in identify_boot_cpu().
+ */
+u64 __ro_after_init x86_amd_ls_cfg_base;
+u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask;
 
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
 
+	/*
+	 * identify_boot_cpu() initialized SMT support information, let the
+	 * core code know.
+	 */
+	cpu_smt_check_topology_early();
+
 	if (!IS_ENABLED(CONFIG_SMP)) {
 		pr_info("CPU: ");
 		print_cpu_info(&boot_cpu_data);
 	}
 
+	/*
+	 * Read the SPEC_CTRL MSR to account for reserved bits which may
+	 * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD
+	 * init code as it is not enumerated and depends on the family.
+	 */
+	if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+		rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+
+	/* Allow STIBP in MSR_SPEC_CTRL if supported */
+	if (boot_cpu_has(X86_FEATURE_STIBP))
+		x86_spec_ctrl_mask |= SPEC_CTRL_STIBP;
+
 	/* Select the proper spectre mitigation before patching alternatives */
 	spectre_v2_select_mitigation();
 
+	/*
+	 * Select proper mitigation for any exposure to the Speculative Store
+	 * Bypass vulnerability.
+	 */
+	ssb_select_mitigation();
+
+	l1tf_select_mitigation();
+
 #ifdef CONFIG_X86_32
 	/*
 	 * Check whether we are able to run this kernel safely on SMP.
@@ -88,12 +139,83 @@ static const char *spectre_v2_strings[] = {
 	[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 = SPECTRE_V2_NONE;
+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)
+{
+	u64 msrval, guestval, hostval = x86_spec_ctrl_base;
+	struct thread_info *ti = current_thread_info();
+
+	/* Is MSR_SPEC_CTRL implemented ? */
+	if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) {
+		/*
+		 * Restrict guest_spec_ctrl to supported values. Clear the
+		 * modifiable bits in the host base value and or the
+		 * modifiable bits from the guest value.
+		 */
+		guestval = hostval & ~x86_spec_ctrl_mask;
+		guestval |= guest_spec_ctrl & x86_spec_ctrl_mask;
+
+		/* SSBD controlled in MSR_SPEC_CTRL */
+		if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
+		    static_cpu_has(X86_FEATURE_AMD_SSBD))
+			hostval |= ssbd_tif_to_spec_ctrl(ti->flags);
+
+		if (hostval != guestval) {
+			msrval = setguest ? guestval : hostval;
+			wrmsrl(MSR_IA32_SPEC_CTRL, msrval);
+		}
+	}
+
+	/*
+	 * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update
+	 * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported.
+	 */
+	if (!static_cpu_has(X86_FEATURE_LS_CFG_SSBD) &&
+	    !static_cpu_has(X86_FEATURE_VIRT_SSBD))
+		return;
+
+	/*
+	 * If the host has SSBD mitigation enabled, force it in the host's
+	 * virtual MSR value. If its not permanently enabled, evaluate
+	 * current's TIF_SSBD thread flag.
+	 */
+	if (static_cpu_has(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE))
+		hostval = SPEC_CTRL_SSBD;
+	else
+		hostval = ssbd_tif_to_spec_ctrl(ti->flags);
+
+	/* Sanitize the guest value */
+	guestval = guest_virt_spec_ctrl & SPEC_CTRL_SSBD;
+
+	if (hostval != guestval) {
+		unsigned long tif;
+
+		tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) :
+				 ssbd_spec_ctrl_to_tif(hostval);
+
+		speculative_store_bypass_update(tif);
+	}
+}
+EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl);
+
+static void x86_amd_ssb_disable(void)
+{
+	u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask;
+
+	if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
+		wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD);
+	else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+		wrmsrl(MSR_AMD64_LS_CFG, msrval);
+}
 
 #ifdef RETPOLINE
 static bool spectre_v2_bad_module;
@@ -188,6 +310,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	}
 
 	if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON &&
 	    boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
 		pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
 		return SPECTRE_V2_CMD_AUTO;
@@ -201,21 +324,44 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	return cmd;
 }
 
-/* Check for Skylake-like CPUs (for RSB handling) */
-static bool __init is_skylake_era(void)
+static bool stibp_needed(void)
 {
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-	    boot_cpu_data.x86 == 6) {
-		switch (boot_cpu_data.x86_model) {
-		case INTEL_FAM6_SKYLAKE_MOBILE:
-		case INTEL_FAM6_SKYLAKE_DESKTOP:
-		case INTEL_FAM6_SKYLAKE_X:
-		case INTEL_FAM6_KABYLAKE_MOBILE:
-		case INTEL_FAM6_KABYLAKE_DESKTOP:
-			return true;
-		}
+	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);
 	}
-	return false;
+	mutex_unlock(&spec_ctrl_mutex);
 }
 
 static void __init spectre_v2_select_mitigation(void)
@@ -237,6 +383,13 @@ static void __init spectre_v2_select_mitigation(void)
 
 	case SPECTRE_V2_CMD_FORCE:
 	case SPECTRE_V2_CMD_AUTO:
+		if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
+			mode = SPECTRE_V2_IBRS_ENHANCED;
+			/* Force it so VMEXIT will restore correctly */
+			x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
+			wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+			goto specv2_set_mode;
+		}
 		if (IS_ENABLED(CONFIG_RETPOLINE))
 			goto retpoline_auto;
 		break;
@@ -257,7 +410,8 @@ static void __init spectre_v2_select_mitigation(void)
 	return;
 
 retpoline_auto:
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
 	retpoline_amd:
 		if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
 			pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n");
@@ -274,26 +428,20 @@ retpoline_auto:
 		setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
 	}
 
+specv2_set_mode:
 	spectre_v2_enabled = mode;
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
 	/*
-	 * If neither SMEP nor PTI are available, there is a risk of
-	 * hitting userspace addresses in the RSB after a context switch
-	 * from a shallow call stack to a deeper one. To prevent this fill
-	 * the entire RSB, even when using IBRS.
+	 * If spectre v2 protection has been enabled, unconditionally fill
+	 * RSB during a context switch; this protects against two independent
+	 * issues:
 	 *
-	 * Skylake era CPUs have a separate issue with *underflow* of the
-	 * RSB, when they will predict 'ret' targets from the generic BTB.
-	 * The proper mitigation for this is IBRS. If IBRS is not supported
-	 * or deactivated in favour of retpolines the RSB fill on context
-	 * switch is required.
+	 *	- RSB underflow (and switch to BTB) on Skylake+
+	 *	- SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs
 	 */
-	if ((!boot_cpu_has(X86_FEATURE_PTI) &&
-	     !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
-		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
-		pr_info("Spectre v2 mitigation: Filling RSB on context switch\n");
-	}
+	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)) {
@@ -303,41 +451,475 @@ retpoline_auto:
 
 	/*
 	 * Retpoline means the kernel is safe because it has no indirect
-	 * branches. But firmware isn't, so use IBRS to protect that.
+	 * branches. Enhanced IBRS protects firmware too, so, enable restricted
+	 * speculation around firmware calls only when Enhanced IBRS isn't
+	 * supported.
+	 *
+	 * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because
+	 * the user might select retpoline on the kernel command line and if
+	 * the CPU supports Enhanced IBRS, kernel might un-intentionally not
+	 * enable IBRS around firmware calls.
 	 */
-	if (boot_cpu_has(X86_FEATURE_IBRS)) {
+	if (boot_cpu_has(X86_FEATURE_IBRS) && mode != SPECTRE_V2_IBRS_ENHANCED) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
 		pr_info("Enabling Restricted Speculation for firmware calls\n");
 	}
+
+	/* Enable STIBP if appropriate */
+	arch_smt_update();
+}
+
+#undef pr_fmt
+#define pr_fmt(fmt)	"Speculative Store Bypass: " fmt
+
+static enum ssb_mitigation ssb_mode __ro_after_init = SPEC_STORE_BYPASS_NONE;
+
+/* The kernel command line selection */
+enum ssb_mitigation_cmd {
+	SPEC_STORE_BYPASS_CMD_NONE,
+	SPEC_STORE_BYPASS_CMD_AUTO,
+	SPEC_STORE_BYPASS_CMD_ON,
+	SPEC_STORE_BYPASS_CMD_PRCTL,
+	SPEC_STORE_BYPASS_CMD_SECCOMP,
+};
+
+static const char *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",
+	[SPEC_STORE_BYPASS_SECCOMP]	= "Mitigation: Speculative Store Bypass disabled via prctl and seccomp",
+};
+
+static const struct {
+	const char *option;
+	enum ssb_mitigation_cmd cmd;
+} ssb_mitigation_options[] = {
+	{ "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 */
+	{ "prctl",	SPEC_STORE_BYPASS_CMD_PRCTL },   /* Disable Speculative Store Bypass via prctl */
+	{ "seccomp",	SPEC_STORE_BYPASS_CMD_SECCOMP }, /* Disable Speculative Store Bypass via prctl and seccomp */
+};
+
+static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
+{
+	enum ssb_mitigation_cmd cmd = SPEC_STORE_BYPASS_CMD_AUTO;
+	char arg[20];
+	int ret, i;
+
+	if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) {
+		return SPEC_STORE_BYPASS_CMD_NONE;
+	} else {
+		ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable",
+					  arg, sizeof(arg));
+		if (ret < 0)
+			return SPEC_STORE_BYPASS_CMD_AUTO;
+
+		for (i = 0; i < ARRAY_SIZE(ssb_mitigation_options); i++) {
+			if (!match_option(arg, ret, ssb_mitigation_options[i].option))
+				continue;
+
+			cmd = ssb_mitigation_options[i].cmd;
+			break;
+		}
+
+		if (i >= ARRAY_SIZE(ssb_mitigation_options)) {
+			pr_err("unknown option (%s). Switching to AUTO select\n", arg);
+			return SPEC_STORE_BYPASS_CMD_AUTO;
+		}
+	}
+
+	return cmd;
+}
+
+static enum ssb_mitigation __init __ssb_select_mitigation(void)
+{
+	enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE;
+	enum ssb_mitigation_cmd cmd;
+
+	if (!boot_cpu_has(X86_FEATURE_SSBD))
+		return mode;
+
+	cmd = ssb_parse_cmdline();
+	if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) &&
+	    (cmd == SPEC_STORE_BYPASS_CMD_NONE ||
+	     cmd == SPEC_STORE_BYPASS_CMD_AUTO))
+		return mode;
+
+	switch (cmd) {
+	case SPEC_STORE_BYPASS_CMD_AUTO:
+	case SPEC_STORE_BYPASS_CMD_SECCOMP:
+		/*
+		 * Choose prctl+seccomp as the default mode if seccomp is
+		 * enabled.
+		 */
+		if (IS_ENABLED(CONFIG_SECCOMP))
+			mode = SPEC_STORE_BYPASS_SECCOMP;
+		else
+			mode = SPEC_STORE_BYPASS_PRCTL;
+		break;
+	case SPEC_STORE_BYPASS_CMD_ON:
+		mode = SPEC_STORE_BYPASS_DISABLE;
+		break;
+	case SPEC_STORE_BYPASS_CMD_PRCTL:
+		mode = SPEC_STORE_BYPASS_PRCTL;
+		break;
+	case SPEC_STORE_BYPASS_CMD_NONE:
+		break;
+	}
+
+	/*
+	 * We have three CPU feature flags that are in play here:
+	 *  - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.
+	 *  - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass
+	 *  - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation
+	 */
+	if (mode == SPEC_STORE_BYPASS_DISABLE) {
+		setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE);
+		/*
+		 * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD may
+		 * use a completely different MSR and bit dependent on family.
+		 */
+		if (!static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) &&
+		    !static_cpu_has(X86_FEATURE_AMD_SSBD)) {
+			x86_amd_ssb_disable();
+		} else {
+			x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
+			x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
+			wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+		}
+	}
+
+	return mode;
+}
+
+static void ssb_select_mitigation(void)
+{
+	ssb_mode = __ssb_select_mitigation();
+
+	if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+		pr_info("%s\n", ssb_strings[ssb_mode]);
+}
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "Speculation prctl: " fmt
+
+static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
+{
+	bool update;
+
+	if (ssb_mode != SPEC_STORE_BYPASS_PRCTL &&
+	    ssb_mode != SPEC_STORE_BYPASS_SECCOMP)
+		return -ENXIO;
+
+	switch (ctrl) {
+	case PR_SPEC_ENABLE:
+		/* If speculation is force disabled, enable is not allowed */
+		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);
+		break;
+	case PR_SPEC_DISABLE:
+		task_set_spec_ssb_disable(task);
+		update = !test_and_set_tsk_thread_flag(task, TIF_SSBD);
+		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);
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	/*
+	 * 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();
+
+	return 0;
+}
+
+int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
+			     unsigned long ctrl)
+{
+	switch (which) {
+	case PR_SPEC_STORE_BYPASS:
+		return ssb_prctl_set(task, ctrl);
+	default:
+		return -ENODEV;
+	}
+}
+
+#ifdef CONFIG_SECCOMP
+void arch_seccomp_spec_mitigate(struct task_struct *task)
+{
+	if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP)
+		ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE);
+}
+#endif
+
+static int ssb_prctl_get(struct task_struct *task)
+{
+	switch (ssb_mode) {
+	case SPEC_STORE_BYPASS_DISABLE:
+		return PR_SPEC_DISABLE;
+	case SPEC_STORE_BYPASS_SECCOMP:
+	case SPEC_STORE_BYPASS_PRCTL:
+		if (task_spec_ssb_force_disable(task))
+			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
+		if (task_spec_ssb_disable(task))
+			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
+		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
+	default:
+		if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+			return PR_SPEC_ENABLE;
+		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);
+	default:
+		return -ENODEV;
+	}
+}
+
+void x86_spec_ctrl_setup_ap(void)
+{
+	if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+		wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+
+	if (ssb_mode == SPEC_STORE_BYPASS_DISABLE)
+		x86_amd_ssb_disable();
+}
+
+#undef pr_fmt
+#define pr_fmt(fmt)	"L1TF: " fmt
+
+/* Default mitigation for L1TF-affected CPUs */
+enum l1tf_mitigations l1tf_mitigation __ro_after_init = L1TF_MITIGATION_FLUSH;
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+EXPORT_SYMBOL_GPL(l1tf_mitigation);
+#endif
+enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
+EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation);
+
+/*
+ * These CPUs all support 44bits physical address space internally in the
+ * cache but CPUID can report a smaller number of physical address bits.
+ *
+ * The L1TF mitigation uses the top most address bit for the inversion of
+ * non present PTEs. When the installed memory reaches into the top most
+ * address bit due to memory holes, which has been observed on machines
+ * which report 36bits physical address bits and have 32G RAM installed,
+ * then the mitigation range check in l1tf_select_mitigation() triggers.
+ * This is a false positive because the mitigation is still possible due to
+ * the fact that the cache uses 44bit internally. Use the cache bits
+ * instead of the reported physical bits and adjust them on the affected
+ * machines to 44bit if the reported bits are less than 44.
+ */
+static void override_cache_bits(struct cpuinfo_x86 *c)
+{
+	if (c->x86 != 6)
+		return;
+
+	switch (c->x86_model) {
+	case INTEL_FAM6_NEHALEM:
+	case INTEL_FAM6_WESTMERE:
+	case INTEL_FAM6_SANDYBRIDGE:
+	case INTEL_FAM6_IVYBRIDGE:
+	case INTEL_FAM6_HASWELL_CORE:
+	case INTEL_FAM6_HASWELL_ULT:
+	case INTEL_FAM6_HASWELL_GT3E:
+	case INTEL_FAM6_BROADWELL_CORE:
+	case INTEL_FAM6_BROADWELL_GT3E:
+	case INTEL_FAM6_SKYLAKE_MOBILE:
+	case INTEL_FAM6_SKYLAKE_DESKTOP:
+	case INTEL_FAM6_KABYLAKE_MOBILE:
+	case INTEL_FAM6_KABYLAKE_DESKTOP:
+		if (c->x86_cache_bits < 44)
+			c->x86_cache_bits = 44;
+		break;
+	}
+}
+
+static void __init l1tf_select_mitigation(void)
+{
+	u64 half_pa;
+
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return;
+
+	override_cache_bits(&boot_cpu_data);
+
+	switch (l1tf_mitigation) {
+	case L1TF_MITIGATION_OFF:
+	case L1TF_MITIGATION_FLUSH_NOWARN:
+	case L1TF_MITIGATION_FLUSH:
+		break;
+	case L1TF_MITIGATION_FLUSH_NOSMT:
+	case L1TF_MITIGATION_FULL:
+		cpu_smt_disable(false);
+		break;
+	case L1TF_MITIGATION_FULL_FORCE:
+		cpu_smt_disable(true);
+		break;
+	}
+
+#if CONFIG_PGTABLE_LEVELS == 2
+	pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n");
+	return;
+#endif
+
+	half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
+	if (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);
+		pr_info("However, doing so will make a part of your RAM unusable.\n");
+		pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html might help you decide.\n");
+		return;
+	}
+
+	setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV);
 }
 
+static int __init l1tf_cmdline(char *str)
+{
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return 0;
+
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off"))
+		l1tf_mitigation = L1TF_MITIGATION_OFF;
+	else if (!strcmp(str, "flush,nowarn"))
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOWARN;
+	else if (!strcmp(str, "flush"))
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH;
+	else if (!strcmp(str, "flush,nosmt"))
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT;
+	else if (!strcmp(str, "full"))
+		l1tf_mitigation = L1TF_MITIGATION_FULL;
+	else if (!strcmp(str, "full,force"))
+		l1tf_mitigation = L1TF_MITIGATION_FULL_FORCE;
+
+	return 0;
+}
+early_param("l1tf", l1tf_cmdline);
+
 #undef pr_fmt
 
 #ifdef CONFIG_SYSFS
-ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+
+#define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion"
+
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+static const char *l1tf_vmx_states[] = {
+	[VMENTER_L1D_FLUSH_AUTO]		= "auto",
+	[VMENTER_L1D_FLUSH_NEVER]		= "vulnerable",
+	[VMENTER_L1D_FLUSH_COND]		= "conditional cache flushes",
+	[VMENTER_L1D_FLUSH_ALWAYS]		= "cache flushes",
+	[VMENTER_L1D_FLUSH_EPT_DISABLED]	= "EPT disabled",
+	[VMENTER_L1D_FLUSH_NOT_REQUIRED]	= "flush not necessary"
+};
+
+static ssize_t l1tf_show_state(char *buf)
+{
+	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO)
+		return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);
+
+	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED ||
+	    (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER &&
+	     cpu_smt_control == CPU_SMT_ENABLED))
+		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");
+}
+#else
+static ssize_t l1tf_show_state(char *buf)
+{
+	return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);
+}
+#endif
+
+static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
+			       char *buf, unsigned int bug)
 {
-	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+	int ret;
+
+	if (!boot_cpu_has_bug(bug))
 		return sprintf(buf, "Not affected\n");
-	if (boot_cpu_has(X86_FEATURE_PTI))
-		return sprintf(buf, "Mitigation: PTI\n");
+
+	switch (bug) {
+	case X86_BUG_CPU_MELTDOWN:
+		if (boot_cpu_has(X86_FEATURE_PTI))
+			return sprintf(buf, "Mitigation: PTI\n");
+
+		if (hypervisor_is_type(X86_HYPER_XEN_PV))
+			return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n");
+
+		break;
+
+	case X86_BUG_SPECTRE_V1:
+		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" : "",
+			       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
+			       (x86_spec_ctrl_base & SPEC_CTRL_STIBP) ? ", STIBP" : "",
+			       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]);
+
+	case X86_BUG_L1TF:
+		if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV))
+			return l1tf_show_state(buf);
+		break;
+	default:
+		break;
+	}
+
 	return sprintf(buf, "Vulnerable\n");
 }
 
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_CPU_MELTDOWN);
+}
+
 ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
-		return sprintf(buf, "Not affected\n");
-	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+	return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V1);
 }
 
 ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
-		return sprintf(buf, "Not affected\n");
+	return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2);
+}
+
+ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS);
+}
 
-	return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
-		       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
-		       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
-		       spectre_v2_module_string());
+ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_L1TF);
 }
 #endif