x86/bugs: KVM: Add support for SRSO_MSR_FIX

commit 8442df2b49ed9bcd67833ad4f091d15ac91efd00 upstream.

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 <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20241202120416.6054-1-bp@kernel.org
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/Documentation/admin-guide/hw-vuln/srso.rst b/Documentation/admin-guide/hw-vuln/srso.rst
index 2ad1c05b8c88396bbf835a8fcc7fcb00291bc30c..66af95251a3d1bbb720f29da379f70098e80ba77 100644 (file)
--- a/Documentation/admin-guide/hw-vuln/srso.rst
+++ b/Documentation/admin-guide/hw-vuln/srso.rst
@@ -104,7 +104,20 @@ The possible values in this file are:
 
    (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:
 

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 3fc47f25cafcd7810a89ec3a8709b30f679eb7bf..16a8c1f3ff6558a51065c4f4b5c9019c89155154 100644 (file)
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -465,6 +465,10 @@
 #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

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 2b6e3127ef4e2d9232c165e50e9acd5d1f703cc5..21d07aa9400c7a8aa26ec137e124afbd6c0006b2 100644 (file)
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -728,6 +728,7 @@
 
 /* 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 */

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c3ea29efe26fd7b63d5449f618cbfee00269cbff..f3cb559a598df56deed7aea07ae7a4193ba45a07 100644 (file)
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -2718,6 +2718,7 @@ enum srso_mitigation {
        SRSO_MITIGATION_SAFE_RET,
        SRSO_MITIGATION_IBPB,
        SRSO_MITIGATION_IBPB_ON_VMEXIT,
+       SRSO_MITIGATION_BP_SPEC_REDUCE,
 };
 
 enum srso_mitigation_cmd {
@@ -2735,7 +2736,8 @@ static const char * const srso_strings[] = {
        [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;
@@ -2774,7 +2776,7 @@ static void __init srso_select_mitigation(void)
            srso_cmd == SRSO_CMD_OFF) {
                if (boot_cpu_has(X86_FEATURE_SBPB))
                        x86_pred_cmd = PRED_CMD_SBPB;
-               return;
+               goto out;
        }
 
        if (has_microcode) {
@@ -2786,7 +2788,7 @@ static void __init srso_select_mitigation(void)
                 */
                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) {
@@ -2866,6 +2868,12 @@ static void __init srso_select_mitigation(void)
 
 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);
@@ -2887,7 +2895,15 @@ 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

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index f4872a53905b2b912a034e12077d71d97607c15f..353ad32c1be6086dc0c86defebfe2d52eee95647 100644 (file)
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -608,6 +608,9 @@ static void svm_disable_virtualization_cpu(void)
        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)
@@ -685,6 +688,9 @@ 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;
 }
 

diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 4bf4fad5b148ef37804e77f42d0676ca13823749..5a18ecc04a6c35823ba2503bfac5906bf8fe0d2c 100644 (file)
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -103,6 +103,7 @@ int msr_set_bit(u32 msr, u8 bit)
 {
        return __flip_bit(msr, bit, true);
 }
+EXPORT_SYMBOL_GPL(msr_set_bit);
 
 /**
  * msr_clear_bit - Clear @bit in a MSR @msr.
@@ -118,6 +119,7 @@ int msr_clear_bit(u32 msr, u8 bit)
 {
        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)