Merge tag 'kvm-x86-misc-6.6' of https://github.com/kvm-x86/linux into HEAD

KVM x86 changes for 6.6:

 - Misc cleanups

 - Retry APIC optimized recalculation if a vCPU is added/enabled

 - Overhaul emergency reboot code to bring SVM up to par with VMX, tie the
   "emergency disabling" behavior to KVM actually being loaded, and move all of
   the logic within KVM

 - Fix user triggerable WARNs in SVM where KVM incorrectly assumes the TSC
   ratio MSR can diverge from the default iff TSC scaling is enabled, and clean
   up related code

 - Add a framework to allow "caching" feature flags so that KVM can check if
   the guest can use a feature without needing to search guest CPUID

2 files changed, 50 insertions, 47 deletions

diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index cdd92ab43cda..54cd959cb316 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -48,27 +48,6 @@ struct crash_memmap_data {
 	unsigned int type;
 };
 
-/*
- * This is used to VMCLEAR all VMCSs loaded on the
- * processor. And when loading kvm_intel module, the
- * callback function pointer will be assigned.
- *
- * protected by rcu.
- */
-crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss = NULL;
-EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss);
-
-static inline void cpu_crash_vmclear_loaded_vmcss(void)
-{
-	crash_vmclear_fn *do_vmclear_operation = NULL;
-
-	rcu_read_lock();
-	do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss);
-	if (do_vmclear_operation)
-		do_vmclear_operation();
-	rcu_read_unlock();
-}
-
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
 
 static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
@@ -76,11 +55,6 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
 	crash_save_cpu(regs, cpu);
 
 	/*
-	 * VMCLEAR VMCSs loaded on all cpus if needed.
-	 */
-	cpu_crash_vmclear_loaded_vmcss();
-
-	/*
 	 * Disable Intel PT to stop its logging
 	 */
 	cpu_emergency_stop_pt();
@@ -133,11 +107,6 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 
 	crash_smp_send_stop();
 
-	/*
-	 * VMCLEAR VMCSs loaded on this cpu if needed.
-	 */
-	cpu_crash_vmclear_loaded_vmcss();
-
 	cpu_emergency_disable_virtualization();
 
 	/*
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 3adbe97015c1..830425e6d38e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -22,7 +22,6 @@
 #include <asm/reboot_fixups.h>
 #include <asm/reboot.h>
 #include <asm/pci_x86.h>
-#include <asm/virtext.h>
 #include <asm/cpu.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
@@ -530,9 +529,54 @@ static inline void kb_wait(void)
 
 static inline void nmi_shootdown_cpus_on_restart(void);
 
+#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD)
+/* RCU-protected callback to disable virtualization prior to reboot. */
+static cpu_emergency_virt_cb __rcu *cpu_emergency_virt_callback;
+
+void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback)
+{
+	if (WARN_ON_ONCE(rcu_access_pointer(cpu_emergency_virt_callback)))
+		return;
+
+	rcu_assign_pointer(cpu_emergency_virt_callback, callback);
+}
+EXPORT_SYMBOL_GPL(cpu_emergency_register_virt_callback);
+
+void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback)
+{
+	if (WARN_ON_ONCE(rcu_access_pointer(cpu_emergency_virt_callback) != callback))
+		return;
+
+	rcu_assign_pointer(cpu_emergency_virt_callback, NULL);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(cpu_emergency_unregister_virt_callback);
+
+/*
+ * Disable virtualization, i.e. VMX or SVM, to ensure INIT is recognized during
+ * reboot.  VMX blocks INIT if the CPU is post-VMXON, and SVM blocks INIT if
+ * GIF=0, i.e. if the crash occurred between CLGI and STGI.
+ */
+void cpu_emergency_disable_virtualization(void)
+{
+	cpu_emergency_virt_cb *callback;
+
+	/*
+	 * IRQs must be disabled as KVM enables virtualization in hardware via
+	 * function call IPIs, i.e. IRQs need to be disabled to guarantee
+	 * virtualization stays disabled.
+	 */
+	lockdep_assert_irqs_disabled();
+
+	rcu_read_lock();
+	callback = rcu_dereference(cpu_emergency_virt_callback);
+	if (callback)
+		callback();
+	rcu_read_unlock();
+}
+
 static void emergency_reboot_disable_virtualization(void)
 {
-	/* Just make sure we won't change CPUs while doing this */
 	local_irq_disable();
 
 	/*
@@ -545,7 +589,7 @@ static void emergency_reboot_disable_virtualization(void)
 	 * Do the NMI shootdown even if virtualization is off on _this_ CPU, as
 	 * other CPUs may have virtualization enabled.
 	 */
-	if (cpu_has_vmx() || cpu_has_svm(NULL)) {
+	if (rcu_access_pointer(cpu_emergency_virt_callback)) {
 		/* Safely force _this_ CPU out of VMX/SVM operation. */
 		cpu_emergency_disable_virtualization();
 
@@ -553,7 +597,9 @@ static void emergency_reboot_disable_virtualization(void)
 		nmi_shootdown_cpus_on_restart();
 	}
 }
-
+#else
+static void emergency_reboot_disable_virtualization(void) { }
+#endif /* CONFIG_KVM_INTEL || CONFIG_KVM_AMD */
 
 void __attribute__((weak)) mach_reboot_fixups(void)
 {
@@ -787,21 +833,9 @@ void machine_crash_shutdown(struct pt_regs *regs)
 }
 #endif
 
-
 /* This is the CPU performing the emergency shutdown work. */
 int crashing_cpu = -1;
 
-/*
- * Disable virtualization, i.e. VMX or SVM, to ensure INIT is recognized during
- * reboot.  VMX blocks INIT if the CPU is post-VMXON, and SVM blocks INIT if
- * GIF=0, i.e. if the crash occurred between CLGI and STGI.
- */
-void cpu_emergency_disable_virtualization(void)
-{
-	cpu_emergency_vmxoff();
-	cpu_emergency_svm_disable();
-}
-
 #if defined(CONFIG_SMP)
 
 static nmi_shootdown_cb shootdown_callback;