Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "One of the largest releases for KVM...  Hardly any generic
  changes, but lots of architecture-specific updates.

  ARM:
   - VHE support so that we can run the kernel at EL2 on ARMv8.1 systems
   - PMU support for guests
   - 32bit world switch rewritten in C
   - various optimizations to the vgic save/restore code.

  PPC:
   - enabled KVM-VFIO integration ("VFIO device")
   - optimizations to speed up IPIs between vcpus
   - in-kernel handling of IOMMU hypercalls
   - support for dynamic DMA windows (DDW).

  s390:
   - provide the floating point registers via sync regs;
   - separated instruction vs.  data accesses
   - dirty log improvements for huge guests
   - bugfixes and documentation improvements.

  x86:
   - Hyper-V VMBus hypercall userspace exit
   - alternative implementation of lowest-priority interrupts using
     vector hashing (for better VT-d posted interrupt support)
   - fixed guest debugging with nested virtualizations
   - improved interrupt tracking in the in-kernel IOAPIC
   - generic infrastructure for tracking writes to guest
     memory - currently its only use is to speedup the legacy shadow
     paging (pre-EPT) case, but in the future it will be used for
     virtual GPUs as well
   - much cleanup (LAPIC, kvmclock, MMU, PIT), including ubsan fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (217 commits)
  KVM: x86: remove eager_fpu field of struct kvm_vcpu_arch
  KVM: x86: disable MPX if host did not enable MPX XSAVE features
  arm64: KVM: vgic-v3: Only wipe LRs on vcpu exit
  arm64: KVM: vgic-v3: Reset LRs at boot time
  arm64: KVM: vgic-v3: Do not save an LR known to be empty
  arm64: KVM: vgic-v3: Save maintenance interrupt state only if required
  arm64: KVM: vgic-v3: Avoid accessing ICH registers
  KVM: arm/arm64: vgic-v2: Make GICD_SGIR quicker to hit
  KVM: arm/arm64: vgic-v2: Only wipe LRs on vcpu exit
  KVM: arm/arm64: vgic-v2: Reset LRs at boot time
  KVM: arm/arm64: vgic-v2: Do not save an LR known to be empty
  KVM: arm/arm64: vgic-v2: Move GICH_ELRSR saving to its own function
  KVM: arm/arm64: vgic-v2: Save maintenance interrupt state only if required
  KVM: arm/arm64: vgic-v2: Avoid accessing GICH registers
  KVM: s390: allocate only one DMA page per VM
  KVM: s390: enable STFLE interpretation only if enabled for the guest
  KVM: s390: wake up when the VCPU cpu timer expires
  KVM: s390: step the VCPU timer while in enabled wait
  KVM: s390: protect VCPU cpu timer with a seqcount
  KVM: s390: step VCPU cpu timer during kvm_run ioctl
  ...

1 files changed, 59 insertions, 37 deletions

diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index f0dd9d42bc7b..5152b3898155 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -75,7 +75,7 @@ static int arch_timer_ppi[MAX_TIMER_PPI];
 
 static struct clock_event_device __percpu *arch_timer_evt;
 
-static bool arch_timer_use_virtual = true;
+static enum ppi_nr arch_timer_uses_ppi = VIRT_PPI;
 static bool arch_timer_c3stop;
 static bool arch_timer_mem_use_virtual;
 
@@ -271,16 +271,22 @@ static void __arch_timer_setup(unsigned type,
 		clk->name = "arch_sys_timer";
 		clk->rating = 450;
 		clk->cpumask = cpumask_of(smp_processor_id());
-		if (arch_timer_use_virtual) {
-			clk->irq = arch_timer_ppi[VIRT_PPI];
+		clk->irq = arch_timer_ppi[arch_timer_uses_ppi];
+		switch (arch_timer_uses_ppi) {
+		case VIRT_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_virt;
 			clk->set_state_oneshot_stopped = arch_timer_shutdown_virt;
 			clk->set_next_event = arch_timer_set_next_event_virt;
-		} else {
-			clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
+			break;
+		case PHYS_SECURE_PPI:
+		case PHYS_NONSECURE_PPI:
+		case HYP_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_phys;
 			clk->set_state_oneshot_stopped = arch_timer_shutdown_phys;
 			clk->set_next_event = arch_timer_set_next_event_phys;
+			break;
+		default:
+			BUG();
 		}
 	} else {
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
@@ -350,17 +356,20 @@ static void arch_counter_set_user_access(void)
 	arch_timer_set_cntkctl(cntkctl);
 }
 
+static bool arch_timer_has_nonsecure_ppi(void)
+{
+	return (arch_timer_uses_ppi == PHYS_SECURE_PPI &&
+		arch_timer_ppi[PHYS_NONSECURE_PPI]);
+}
+
 static int arch_timer_setup(struct clock_event_device *clk)
 {
 	__arch_timer_setup(ARCH_CP15_TIMER, clk);
 
-	if (arch_timer_use_virtual)
-		enable_percpu_irq(arch_timer_ppi[VIRT_PPI], 0);
-	else {
-		enable_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI], 0);
-		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
-			enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0);
-	}
+	enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], 0);
+
+	if (arch_timer_has_nonsecure_ppi())
+		enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0);
 
 	arch_counter_set_user_access();
 	if (IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM))
@@ -402,7 +411,7 @@ static void arch_timer_banner(unsigned type)
 		     (unsigned long)arch_timer_rate / 1000000,
 		     (unsigned long)(arch_timer_rate / 10000) % 100,
 		     type & ARCH_CP15_TIMER ?
-			arch_timer_use_virtual ? "virt" : "phys" :
+		     (arch_timer_uses_ppi == VIRT_PPI) ? "virt" : "phys" :
 			"",
 		     type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ?  "/" : "",
 		     type & ARCH_MEM_TIMER ?
@@ -472,7 +481,7 @@ static void __init arch_counter_register(unsigned type)
 
 	/* Register the CP15 based counter if we have one */
 	if (type & ARCH_CP15_TIMER) {
-		if (IS_ENABLED(CONFIG_ARM64) || arch_timer_use_virtual)
+		if (IS_ENABLED(CONFIG_ARM64) || arch_timer_uses_ppi == VIRT_PPI)
 			arch_timer_read_counter = arch_counter_get_cntvct;
 		else
 			arch_timer_read_counter = arch_counter_get_cntpct;
@@ -502,13 +511,9 @@ static void arch_timer_stop(struct clock_event_device *clk)
 	pr_debug("arch_timer_teardown disable IRQ%d cpu #%d\n",
 		 clk->irq, smp_processor_id());
 
-	if (arch_timer_use_virtual)
-		disable_percpu_irq(arch_timer_ppi[VIRT_PPI]);
-	else {
-		disable_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI]);
-		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
-			disable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI]);
-	}
+	disable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi]);
+	if (arch_timer_has_nonsecure_ppi())
+		disable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI]);
 
 	clk->set_state_shutdown(clk);
 }
@@ -574,12 +579,14 @@ static int __init arch_timer_register(void)
 		goto out;
 	}
 
-	if (arch_timer_use_virtual) {
-		ppi = arch_timer_ppi[VIRT_PPI];
+	ppi = arch_timer_ppi[arch_timer_uses_ppi];
+	switch (arch_timer_uses_ppi) {
+	case VIRT_PPI:
 		err = request_percpu_irq(ppi, arch_timer_handler_virt,
 					 "arch_timer", arch_timer_evt);
-	} else {
-		ppi = arch_timer_ppi[PHYS_SECURE_PPI];
+		break;
+	case PHYS_SECURE_PPI:
+	case PHYS_NONSECURE_PPI:
 		err = request_percpu_irq(ppi, arch_timer_handler_phys,
 					 "arch_timer", arch_timer_evt);
 		if (!err && arch_timer_ppi[PHYS_NONSECURE_PPI]) {
@@ -590,6 +597,13 @@ static int __init arch_timer_register(void)
 				free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
 						arch_timer_evt);
 		}
+		break;
+	case HYP_PPI:
+		err = request_percpu_irq(ppi, arch_timer_handler_phys,
+					 "arch_timer", arch_timer_evt);
+		break;
+	default:
+		BUG();
 	}
 
 	if (err) {
@@ -614,15 +628,10 @@ static int __init arch_timer_register(void)
 out_unreg_notify:
 	unregister_cpu_notifier(&arch_timer_cpu_nb);
 out_free_irq:
-	if (arch_timer_use_virtual)
-		free_percpu_irq(arch_timer_ppi[VIRT_PPI], arch_timer_evt);
-	else {
-		free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
+	free_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], arch_timer_evt);
+	if (arch_timer_has_nonsecure_ppi())
+		free_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI],
 				arch_timer_evt);
-		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
-			free_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI],
-					arch_timer_evt);
-	}
 
 out_free:
 	free_percpu(arch_timer_evt);
@@ -709,12 +718,25 @@ static void __init arch_timer_init(void)
 	 *
 	 * If no interrupt provided for virtual timer, we'll have to
 	 * stick to the physical timer. It'd better be accessible...
+	 *
+	 * On ARMv8.1 with VH extensions, the kernel runs in HYP. VHE
+	 * accesses to CNTP_*_EL1 registers are silently redirected to
+	 * their CNTHP_*_EL2 counterparts, and use a different PPI
+	 * number.
 	 */
 	if (is_hyp_mode_available() || !arch_timer_ppi[VIRT_PPI]) {
-		arch_timer_use_virtual = false;
+		bool has_ppi;
+
+		if (is_kernel_in_hyp_mode()) {
+			arch_timer_uses_ppi = HYP_PPI;
+			has_ppi = !!arch_timer_ppi[HYP_PPI];
+		} else {
+			arch_timer_uses_ppi = PHYS_SECURE_PPI;
+			has_ppi = (!!arch_timer_ppi[PHYS_SECURE_PPI] ||
+				   !!arch_timer_ppi[PHYS_NONSECURE_PPI]);
+		}
 
-		if (!arch_timer_ppi[PHYS_SECURE_PPI] ||
-		    !arch_timer_ppi[PHYS_NONSECURE_PPI]) {
+		if (!has_ppi) {
 			pr_warn("arch_timer: No interrupt available, giving up\n");
 			return;
 		}
@@ -747,7 +769,7 @@ static void __init arch_timer_of_init(struct device_node *np)
 	 */
 	if (IS_ENABLED(CONFIG_ARM) &&
 	    of_property_read_bool(np, "arm,cpu-registers-not-fw-configured"))
-			arch_timer_use_virtual = false;
+		arch_timer_uses_ppi = PHYS_SECURE_PPI;
 
 	arch_timer_init();
 }