x86/bugs: KVM: Add support for SRSO_MSR_FIX

Add support for

CPUID Fn8000_0021_EAX[31] (SRSO_MSR_FIX). If this bit is 1, it
indicates that software may use MSR BP_CFG[BpSpecReduce] to mitigate
SRSO.

Enable BpSpecReduce to mitigate SRSO across guest/host boundaries.

Switch back to enabling the bit when virtualization is enabled and to
clear the bit when virtualization is disabled because using a MSR slot
would clear the bit when the guest is exited and any training the guest
has done, would potentially influence the host kernel when execution
enters the kernel and hasn't VMRUN the guest yet.

More detail on the public thread in Link below.

Co-developed-by: Sean Christopherson <[e-mail]>
Signed-off-by: Sean Christopherson <[e-mail]>
Signed-off-by: Borislav Petkov (AMD) <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

Documentation/admin-guide/hw-vuln/srso.rst

···
 
    (spec_rstack_overflow=ibpb-vmexit)
 
+ * 'Mitigation: Reduced Speculation':
 
+   This mitigation gets automatically enabled when the above one "IBPB on
+   VMEXIT" has been selected and the CPU supports the BpSpecReduce bit.
+
+   It gets automatically enabled on machines which have the
+   SRSO_USER_KERNEL_NO=1 CPUID bit. In that case, the code logic is to switch
+   to the above =ibpb-vmexit mitigation because the user/kernel boundary is
+   not affected anymore and thus "safe RET" is not needed.
+
+   After enabling the IBPB on VMEXIT mitigation option, the BpSpecReduce bit
+   is detected (functionality present on all such machines) and that
+   practically overrides IBPB on VMEXIT as it has a lot less performance
+   impact and takes care of the guest->host attack vector too.
 
 In order to exploit vulnerability, an attacker needs to:
 

arch/x86/include/asm/cpufeatures.h

···
 #define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
 #define X86_FEATURE_SRSO_NO		(20*32+29) /* CPU is not affected by SRSO */
 #define X86_FEATURE_SRSO_USER_KERNEL_NO	(20*32+30) /* CPU is not affected by SRSO across user/kernel boundaries */
+#define X86_FEATURE_SRSO_BP_SPEC_REDUCE	(20*32+31) /*
+						    * BP_CFG[BpSpecReduce] can be used to mitigate SRSO for VMs.
+						    * (SRSO_MSR_FIX in the official doc).
+						    */
 
 /*
  * Extended auxiliary flags: Linux defined - for features scattered in various

arch/x86/include/asm/msr-index.h

···
 
 /* Zen4 */
 #define MSR_ZEN4_BP_CFG                 0xc001102e
+#define MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT 4
 #define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5
 
 /* Fam 19h MSRs */

arch/x86/kernel/cpu/bugs.c

···
 	SRSO_MITIGATION_SAFE_RET,
 	SRSO_MITIGATION_IBPB,
 	SRSO_MITIGATION_IBPB_ON_VMEXIT,
+	SRSO_MITIGATION_BP_SPEC_REDUCE,
 };
 
 enum srso_mitigation_cmd {
···
 	[SRSO_MITIGATION_MICROCODE]		= "Vulnerable: Microcode, no safe RET",
 	[SRSO_MITIGATION_SAFE_RET]		= "Mitigation: Safe RET",
 	[SRSO_MITIGATION_IBPB]			= "Mitigation: IBPB",
-	[SRSO_MITIGATION_IBPB_ON_VMEXIT]	= "Mitigation: IBPB on VMEXIT only"
+	[SRSO_MITIGATION_IBPB_ON_VMEXIT]	= "Mitigation: IBPB on VMEXIT only",
+	[SRSO_MITIGATION_BP_SPEC_REDUCE]	= "Mitigation: Reduced Speculation"
 };
 
 static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE;
···
 	    srso_cmd == SRSO_CMD_OFF) {
 		if (boot_cpu_has(X86_FEATURE_SBPB))
 			x86_pred_cmd = PRED_CMD_SBPB;
-		return;
+		goto out;
 	}
 
 	if (has_microcode) {
···
 		 */
 		if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) {
 			setup_force_cpu_cap(X86_FEATURE_SRSO_NO);
-			return;
+			goto out;
 		}
 
 		if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) {
···
 
 ibpb_on_vmexit:
 	case SRSO_CMD_IBPB_ON_VMEXIT:
+		if (boot_cpu_has(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) {
+			pr_notice("Reducing speculation to address VM/HV SRSO attack vector.\n");
+			srso_mitigation = SRSO_MITIGATION_BP_SPEC_REDUCE;
+			break;
+		}
+
 		if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
 			if (has_microcode) {
 				setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
···
 	}
 
 out:
-	pr_info("%s\n", srso_strings[srso_mitigation]);
+	/*
+	 * Clear the feature flag if this mitigation is not selected as that
+	 * feature flag controls the BpSpecReduce MSR bit toggling in KVM.
+	 */
+	if (srso_mitigation != SRSO_MITIGATION_BP_SPEC_REDUCE)
+		setup_clear_cpu_cap(X86_FEATURE_SRSO_BP_SPEC_REDUCE);
+
+	if (srso_mitigation != SRSO_MITIGATION_NONE)
+		pr_info("%s\n", srso_strings[srso_mitigation]);
 }
 
 #undef pr_fmt

arch/x86/kvm/svm/svm.c

···
 	kvm_cpu_svm_disable();
 
 	amd_pmu_disable_virt();
+
+	if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+		msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
 }
 
 static int svm_enable_virtualization_cpu(void)
···
 
 		rdmsr(MSR_TSC_AUX, sev_es_host_save_area(sd)->tsc_aux, msr_hi);
 	}
+
+	if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
 
 	return 0;
 }

arch/x86/lib/msr.c

···
 {
 	return __flip_bit(msr, bit, true);
 }
+EXPORT_SYMBOL_GPL(msr_set_bit);
 
 /**
  * msr_clear_bit - Clear @bit in a MSR @msr.
···
 {
 	return __flip_bit(msr, bit, false);
 }
+EXPORT_SYMBOL_GPL(msr_clear_bit);
 
 #ifdef CONFIG_TRACEPOINTS
 void do_trace_write_msr(unsigned int msr, u64 val, int failed)