x86/vmscape: Add conditional IBPB mitigation

VMSCAPE is a vulnerability that exploits insufficient branch predictor
isolation between a guest and a userspace hypervisor (like QEMU). Existing
mitigations already protect kernel/KVM from a malicious guest. Userspace
can additionally be protected by flushing the branch predictors after a
VMexit.

Since it is the userspace that consumes the poisoned branch predictors,
conditionally issue an IBPB after a VMexit and before returning to
userspace. Workloads that frequently switch between hypervisor and
userspace will incur the most overhead from the new IBPB.

This new IBPB is not integrated with the existing IBPB sites. For
instance, a task can use the existing speculation control prctl() to
get an IBPB at context switch time. With this implementation, the
IBPB is doubled up: one at context switch and another before running
userspace.

The intent is to integrate and optimize these cases post-embargo.

[ dhansen: elaborate on suboptimal IBPB solution ]

Suggested-by: Dave Hansen <[e-mail]>
Signed-off-by: Pawan Gupta <[e-mail]>
Signed-off-by: Dave Hansen <[e-mail]>
Reviewed-by: Dave Hansen <[e-mail]>
Reviewed-by: Borislav Petkov (AMD) <[e-mail]>
Acked-by: Sean Christopherson <[e-mail]>

arch/x86/include/asm/cpufeatures.h

···
 #define X86_FEATURE_TSA_SQ_NO		(21*32+11) /* AMD CPU not vulnerable to TSA-SQ */
 #define X86_FEATURE_TSA_L1_NO		(21*32+12) /* AMD CPU not vulnerable to TSA-L1 */
 #define X86_FEATURE_CLEAR_CPU_BUF_VM	(21*32+13) /* Clear CPU buffers using VERW before VMRUN */
+#define X86_FEATURE_IBPB_EXIT_TO_USER	(21*32+14) /* Use IBPB on exit-to-userspace, see VMSCAPE bug */
 
 /*
  * BUG word(s)

arch/x86/include/asm/entry-common.h

···
 	 * 8 (ia32) bits.
 	 */
 	choose_random_kstack_offset(rdtsc());
+
+	/* Avoid unnecessary reads of 'x86_ibpb_exit_to_user' */
+	if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER) &&
+	    this_cpu_read(x86_ibpb_exit_to_user)) {
+		indirect_branch_prediction_barrier();
+		this_cpu_write(x86_ibpb_exit_to_user, false);
+	}
 }
 #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
 

arch/x86/include/asm/nospec-branch.h

···
 		: "memory");
 }
 
+DECLARE_PER_CPU(bool, x86_ibpb_exit_to_user);
+
 static inline void indirect_branch_prediction_barrier(void)
 {
 	asm_inline volatile(ALTERNATIVE("", "call write_ibpb", X86_FEATURE_IBPB)

arch/x86/kernel/cpu/bugs.c

···
 DEFINE_PER_CPU(u64, x86_spec_ctrl_current);
 EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current);
 
+/*
+ * Set when the CPU has run a potentially malicious guest. An IBPB will
+ * be needed to before running userspace. That IBPB will flush the branch
+ * predictor content.
+ */
+DEFINE_PER_CPU(bool, x86_ibpb_exit_to_user);
+EXPORT_PER_CPU_SYMBOL_GPL(x86_ibpb_exit_to_user);
+
 u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB;
 
 static u64 __ro_after_init x86_arch_cap_msr;

arch/x86/kvm/x86.c

···
 		wrmsrq(MSR_IA32_XFD_ERR, 0);
 
 	/*
+	 * Mark this CPU as needing a branch predictor flush before running
+	 * userspace. Must be done before enabling preemption to ensure it gets
+	 * set for the CPU that actually ran the guest, and not the CPU that it
+	 * may migrate to.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER))
+		this_cpu_write(x86_ibpb_exit_to_user, true);
+
+	/*
 	 * Consume any pending interrupts, including the possible source of
 	 * VM-Exit on SVM and any ticks that occur between VM-Exit and now.
 	 * An instruction is required after local_irq_enable() to fully unblock