x86/bhi: Mitigate KVM by default

BHI mitigation mode spectre_bhi=auto does not deploy the software
mitigation by default. In a cloud environment, it is a likely scenario
where userspace is trusted but the guests are not trusted. Deploying
system wide mitigation in such cases is not desirable.

Update the auto mode to unconditionally mitigate against malicious
guests. Deploy the software sequence at VMexit in auto mode also, when
hardware mitigation is not available. Unlike the force =on mode,
software sequence is not deployed at syscalls in auto mode.

Suggested-by: Alexandre Chartre <alexandre.chartre@oracle.com>
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Daniel Sneddon <daniel.sneddon@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com>
Reviewed-by: Josh Poimboeuf <jpoimboe@kernel.org>

6 files changed, 23 insertions, 6 deletions

diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst
index 7cb99b09827ce3..b70b1d8bd8e657 100644
--- a/Documentation/admin-guide/hw-vuln/spectre.rst
+++ b/Documentation/admin-guide/hw-vuln/spectre.rst
@@ -439,10 +439,12 @@ The possible values in this file are:
    - System is protected by retpoline
  * - BHI: BHI_DIS_S
    - System is protected by BHI_DIS_S
- * - BHI: SW loop
+ * - BHI: SW loop; KVM SW loop
    - System is protected by software clearing sequence
  * - BHI: Syscall hardening
    - Syscalls are hardened against BHI
+ * - BHI: Syscall hardening; KVM: SW loop
+   - System is protected from userspace attacks by syscall hardening; KVM is protected by software clearing sequence
 
 Full mitigation might require a microcode update from the CPU
 vendor. When the necessary microcode is not available, the kernel will
@@ -669,7 +671,8 @@ kernel command line.
 			unconditionally disable.
 		auto
 			enable if hardware mitigation
-			control(BHI_DIS_S) is available.
+			control(BHI_DIS_S) is available, otherwise
+			enable alternate mitigation in KVM.
 
 For spectre_v2_user see Documentation/admin-guide/kernel-parameters.txt
 
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 2dbe60c1db225d..4fa46302f4368c 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6071,8 +6071,9 @@
 
 			on   - unconditionally enable.
 			off  - unconditionally disable.
-			auto - (default) enable only if hardware mitigation
-			       control(BHI_DIS_S) is available.
+			auto - (default) enable hardware mitigation
+			       (BHI_DIS_S) if available, otherwise enable
+			       alternate mitigation in KVM.
 
 	spectre_v2=	[X86,EARLY] Control mitigation of Spectre variant 2
 			(indirect branch speculation) vulnerability.
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index a2ee9a00e4a7ee..3c7434329661c6 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -469,6 +469,7 @@
 #define X86_FEATURE_CLEAR_BHB_LOOP	(21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */
 #define X86_FEATURE_BHI_CTRL		(21*32+ 2) /* "" BHI_DIS_S HW control available */
 #define X86_FEATURE_CLEAR_BHB_HW	(21*32+ 3) /* "" BHI_DIS_S HW control enabled */
+#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */
 
 /*
  * BUG word(s)
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index aea40204278b64..ff5f1ecc7d1e65 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -330,8 +330,13 @@
 .macro CLEAR_BRANCH_HISTORY
 	ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP
 .endm
+
+.macro CLEAR_BRANCH_HISTORY_VMEXIT
+	ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT
+.endm
 #else
 #define CLEAR_BRANCH_HISTORY
+#define CLEAR_BRANCH_HISTORY_VMEXIT
 #endif
 
 #else /* __ASSEMBLY__ */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 1ab27502988874..295463707e6818 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1668,9 +1668,14 @@ static void __init bhi_select_mitigation(void)
 	if (!IS_ENABLED(CONFIG_X86_64))
 		return;
 
+	/* Mitigate KVM by default */
+	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
+	pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n");
+
 	if (bhi_mitigation == BHI_MITIGATION_AUTO)
 		return;
 
+	/* Mitigate syscalls when the mitigation is forced =on */
 	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP);
 	pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n");
 }
@@ -2811,10 +2816,12 @@ static const char * const spectre_bhi_state(void)
 	else if  (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW))
 		return "; BHI: BHI_DIS_S";
 	else if  (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP))
-		return "; BHI: SW loop";
+		return "; BHI: SW loop, KVM: SW loop";
 	else if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
 		 !(x86_read_arch_cap_msr() & ARCH_CAP_RRSBA))
 		return "; BHI: Retpoline";
+	else if  (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT))
+		return "; BHI: Syscall hardening, KVM: SW loop";
 
 	return "; BHI: Vulnerable (Syscall hardening enabled)";
 }
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 0f3593e10c57d8..f6986dee6f8c7c 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -275,7 +275,7 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL)
 
 	call vmx_spec_ctrl_restore_host
 
-	CLEAR_BRANCH_HISTORY
+	CLEAR_BRANCH_HISTORY_VMEXIT
 
 	/* Put return value in AX */
 	mov %_ASM_BX, %_ASM_AX