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, 225 insertions, 116 deletions

diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 5dd2a26444ec..fff7cd42b3a3 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -19,9 +19,7 @@
 #include <linux/irqchip/arm-gic-v3.h>
 #include <linux/kvm_host.h>
 
-#include <asm/kvm_mmu.h>
-
-#include "hyp.h"
+#include <asm/kvm_hyp.h>
 
 #define vtr_to_max_lr_idx(v)		((v) & 0xf)
 #define vtr_to_nr_pri_bits(v)		(((u32)(v) >> 29) + 1)
@@ -39,12 +37,133 @@
 		asm volatile("msr_s " __stringify(r) ", %0" : : "r" (__val));\
 	} while (0)
 
-/* vcpu is already in the HYP VA space */
+static u64 __hyp_text __gic_v3_get_lr(unsigned int lr)
+{
+	switch (lr & 0xf) {
+	case 0:
+		return read_gicreg(ICH_LR0_EL2);
+	case 1:
+		return read_gicreg(ICH_LR1_EL2);
+	case 2:
+		return read_gicreg(ICH_LR2_EL2);
+	case 3:
+		return read_gicreg(ICH_LR3_EL2);
+	case 4:
+		return read_gicreg(ICH_LR4_EL2);
+	case 5:
+		return read_gicreg(ICH_LR5_EL2);
+	case 6:
+		return read_gicreg(ICH_LR6_EL2);
+	case 7:
+		return read_gicreg(ICH_LR7_EL2);
+	case 8:
+		return read_gicreg(ICH_LR8_EL2);
+	case 9:
+		return read_gicreg(ICH_LR9_EL2);
+	case 10:
+		return read_gicreg(ICH_LR10_EL2);
+	case 11:
+		return read_gicreg(ICH_LR11_EL2);
+	case 12:
+		return read_gicreg(ICH_LR12_EL2);
+	case 13:
+		return read_gicreg(ICH_LR13_EL2);
+	case 14:
+		return read_gicreg(ICH_LR14_EL2);
+	case 15:
+		return read_gicreg(ICH_LR15_EL2);
+	}
+
+	unreachable();
+}
+
+static void __hyp_text __gic_v3_set_lr(u64 val, int lr)
+{
+	switch (lr & 0xf) {
+	case 0:
+		write_gicreg(val, ICH_LR0_EL2);
+		break;
+	case 1:
+		write_gicreg(val, ICH_LR1_EL2);
+		break;
+	case 2:
+		write_gicreg(val, ICH_LR2_EL2);
+		break;
+	case 3:
+		write_gicreg(val, ICH_LR3_EL2);
+		break;
+	case 4:
+		write_gicreg(val, ICH_LR4_EL2);
+		break;
+	case 5:
+		write_gicreg(val, ICH_LR5_EL2);
+		break;
+	case 6:
+		write_gicreg(val, ICH_LR6_EL2);
+		break;
+	case 7:
+		write_gicreg(val, ICH_LR7_EL2);
+		break;
+	case 8:
+		write_gicreg(val, ICH_LR8_EL2);
+		break;
+	case 9:
+		write_gicreg(val, ICH_LR9_EL2);
+		break;
+	case 10:
+		write_gicreg(val, ICH_LR10_EL2);
+		break;
+	case 11:
+		write_gicreg(val, ICH_LR11_EL2);
+		break;
+	case 12:
+		write_gicreg(val, ICH_LR12_EL2);
+		break;
+	case 13:
+		write_gicreg(val, ICH_LR13_EL2);
+		break;
+	case 14:
+		write_gicreg(val, ICH_LR14_EL2);
+		break;
+	case 15:
+		write_gicreg(val, ICH_LR15_EL2);
+		break;
+	}
+}
+
+static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu, int nr_lr)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	int i;
+	bool expect_mi;
+
+	expect_mi = !!(cpu_if->vgic_hcr & ICH_HCR_UIE);
+
+	for (i = 0; i < nr_lr; i++) {
+		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
+				continue;
+
+		expect_mi |= (!(cpu_if->vgic_lr[i] & ICH_LR_HW) &&
+			      (cpu_if->vgic_lr[i] & ICH_LR_EOI));
+	}
+
+	if (expect_mi) {
+		cpu_if->vgic_misr  = read_gicreg(ICH_MISR_EL2);
+
+		if (cpu_if->vgic_misr & ICH_MISR_EOI)
+			cpu_if->vgic_eisr = read_gicreg(ICH_EISR_EL2);
+		else
+			cpu_if->vgic_eisr = 0;
+	} else {
+		cpu_if->vgic_misr = 0;
+		cpu_if->vgic_eisr = 0;
+	}
+}
+
 void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 	u64 val;
-	u32 max_lr_idx, nr_pri_bits;
 
 	/*
 	 * Make sure stores to the GIC via the memory mapped interface
@@ -53,68 +172,66 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 	dsb(st);
 
 	cpu_if->vgic_vmcr  = read_gicreg(ICH_VMCR_EL2);
-	cpu_if->vgic_misr  = read_gicreg(ICH_MISR_EL2);
-	cpu_if->vgic_eisr  = read_gicreg(ICH_EISR_EL2);
-	cpu_if->vgic_elrsr = read_gicreg(ICH_ELSR_EL2);
 
-	write_gicreg(0, ICH_HCR_EL2);
-	val = read_gicreg(ICH_VTR_EL2);
-	max_lr_idx = vtr_to_max_lr_idx(val);
-	nr_pri_bits = vtr_to_nr_pri_bits(val);
+	if (vcpu->arch.vgic_cpu.live_lrs) {
+		int i;
+		u32 max_lr_idx, nr_pri_bits;
 
-	switch (max_lr_idx) {
-	case 15:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(15)] = read_gicreg(ICH_LR15_EL2);
-	case 14:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(14)] = read_gicreg(ICH_LR14_EL2);
-	case 13:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(13)] = read_gicreg(ICH_LR13_EL2);
-	case 12:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(12)] = read_gicreg(ICH_LR12_EL2);
-	case 11:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(11)] = read_gicreg(ICH_LR11_EL2);
-	case 10:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(10)] = read_gicreg(ICH_LR10_EL2);
-	case 9:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(9)] = read_gicreg(ICH_LR9_EL2);
-	case 8:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(8)] = read_gicreg(ICH_LR8_EL2);
-	case 7:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(7)] = read_gicreg(ICH_LR7_EL2);
-	case 6:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(6)] = read_gicreg(ICH_LR6_EL2);
-	case 5:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(5)] = read_gicreg(ICH_LR5_EL2);
-	case 4:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(4)] = read_gicreg(ICH_LR4_EL2);
-	case 3:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(3)] = read_gicreg(ICH_LR3_EL2);
-	case 2:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(2)] = read_gicreg(ICH_LR2_EL2);
-	case 1:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(1)] = read_gicreg(ICH_LR1_EL2);
-	case 0:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(0)] = read_gicreg(ICH_LR0_EL2);
-	}
+		cpu_if->vgic_elrsr = read_gicreg(ICH_ELSR_EL2);
 
-	switch (nr_pri_bits) {
-	case 7:
-		cpu_if->vgic_ap0r[3] = read_gicreg(ICH_AP0R3_EL2);
-		cpu_if->vgic_ap0r[2] = read_gicreg(ICH_AP0R2_EL2);
-	case 6:
-		cpu_if->vgic_ap0r[1] = read_gicreg(ICH_AP0R1_EL2);
-	default:
-		cpu_if->vgic_ap0r[0] = read_gicreg(ICH_AP0R0_EL2);
-	}
+		write_gicreg(0, ICH_HCR_EL2);
+		val = read_gicreg(ICH_VTR_EL2);
+		max_lr_idx = vtr_to_max_lr_idx(val);
+		nr_pri_bits = vtr_to_nr_pri_bits(val);
 
-	switch (nr_pri_bits) {
-	case 7:
-		cpu_if->vgic_ap1r[3] = read_gicreg(ICH_AP1R3_EL2);
-		cpu_if->vgic_ap1r[2] = read_gicreg(ICH_AP1R2_EL2);
-	case 6:
-		cpu_if->vgic_ap1r[1] = read_gicreg(ICH_AP1R1_EL2);
-	default:
-		cpu_if->vgic_ap1r[0] = read_gicreg(ICH_AP1R0_EL2);
+		save_maint_int_state(vcpu, max_lr_idx + 1);
+
+		for (i = 0; i <= max_lr_idx; i++) {
+			if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
+				continue;
+
+			if (cpu_if->vgic_elrsr & (1 << i)) {
+				cpu_if->vgic_lr[i] &= ~ICH_LR_STATE;
+				continue;
+			}
+
+			cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
+			__gic_v3_set_lr(0, i);
+		}
+
+		switch (nr_pri_bits) {
+		case 7:
+			cpu_if->vgic_ap0r[3] = read_gicreg(ICH_AP0R3_EL2);
+			cpu_if->vgic_ap0r[2] = read_gicreg(ICH_AP0R2_EL2);
+		case 6:
+			cpu_if->vgic_ap0r[1] = read_gicreg(ICH_AP0R1_EL2);
+		default:
+			cpu_if->vgic_ap0r[0] = read_gicreg(ICH_AP0R0_EL2);
+		}
+
+		switch (nr_pri_bits) {
+		case 7:
+			cpu_if->vgic_ap1r[3] = read_gicreg(ICH_AP1R3_EL2);
+			cpu_if->vgic_ap1r[2] = read_gicreg(ICH_AP1R2_EL2);
+		case 6:
+			cpu_if->vgic_ap1r[1] = read_gicreg(ICH_AP1R1_EL2);
+		default:
+			cpu_if->vgic_ap1r[0] = read_gicreg(ICH_AP1R0_EL2);
+		}
+
+		vcpu->arch.vgic_cpu.live_lrs = 0;
+	} else {
+		cpu_if->vgic_misr  = 0;
+		cpu_if->vgic_eisr  = 0;
+		cpu_if->vgic_elrsr = 0xffff;
+		cpu_if->vgic_ap0r[0] = 0;
+		cpu_if->vgic_ap0r[1] = 0;
+		cpu_if->vgic_ap0r[2] = 0;
+		cpu_if->vgic_ap0r[3] = 0;
+		cpu_if->vgic_ap1r[0] = 0;
+		cpu_if->vgic_ap1r[1] = 0;
+		cpu_if->vgic_ap1r[2] = 0;
+		cpu_if->vgic_ap1r[3] = 0;
 	}
 
 	val = read_gicreg(ICC_SRE_EL2);
@@ -128,6 +245,8 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 	u64 val;
 	u32 max_lr_idx, nr_pri_bits;
+	u16 live_lrs = 0;
+	int i;
 
 	/*
 	 * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a
@@ -140,66 +259,46 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	write_gicreg(cpu_if->vgic_sre, ICC_SRE_EL1);
 	isb();
 
-	write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
-	write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);
-
 	val = read_gicreg(ICH_VTR_EL2);
 	max_lr_idx = vtr_to_max_lr_idx(val);
 	nr_pri_bits = vtr_to_nr_pri_bits(val);
 
-	switch (nr_pri_bits) {
-	case 7:
-		 write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2);
-		 write_gicreg(cpu_if->vgic_ap0r[2], ICH_AP0R2_EL2);
-	case 6:
-		 write_gicreg(cpu_if->vgic_ap0r[1], ICH_AP0R1_EL2);
-	default:
-		 write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2);
+	for (i = 0; i <= max_lr_idx; i++) {
+		if (cpu_if->vgic_lr[i] & ICH_LR_STATE)
+			live_lrs |= (1 << i);
 	}
 
-	switch (nr_pri_bits) {
-	case 7:
-		 write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2);
-		 write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2);
-	case 6:
-		 write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2);
-	default:
-		 write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2);
-	}
+	write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);
 
-	switch (max_lr_idx) {
-	case 15:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(15)], ICH_LR15_EL2);
-	case 14:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(14)], ICH_LR14_EL2);
-	case 13:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(13)], ICH_LR13_EL2);
-	case 12:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(12)], ICH_LR12_EL2);
-	case 11:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(11)], ICH_LR11_EL2);
-	case 10:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(10)], ICH_LR10_EL2);
-	case 9:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(9)], ICH_LR9_EL2);
-	case 8:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(8)], ICH_LR8_EL2);
-	case 7:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(7)], ICH_LR7_EL2);
-	case 6:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(6)], ICH_LR6_EL2);
-	case 5:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(5)], ICH_LR5_EL2);
-	case 4:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(4)], ICH_LR4_EL2);
-	case 3:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(3)], ICH_LR3_EL2);
-	case 2:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(2)], ICH_LR2_EL2);
-	case 1:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(1)], ICH_LR1_EL2);
-	case 0:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(0)], ICH_LR0_EL2);
+	if (live_lrs) {
+		write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
+
+		switch (nr_pri_bits) {
+		case 7:
+			write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2);
+			write_gicreg(cpu_if->vgic_ap0r[2], ICH_AP0R2_EL2);
+		case 6:
+			write_gicreg(cpu_if->vgic_ap0r[1], ICH_AP0R1_EL2);
+		default:
+			write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2);
+		}
+
+		switch (nr_pri_bits) {
+		case 7:
+			write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2);
+			write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2);
+		case 6:
+			write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2);
+		default:
+			write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2);
+		}
+
+		for (i = 0; i <= max_lr_idx; i++) {
+			if (!(live_lrs & (1 << i)))
+				continue;
+
+			__gic_v3_set_lr(cpu_if->vgic_lr[i], i);
+		}
 	}
 
 	/*
@@ -209,6 +308,7 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	 */
 	isb();
 	dsb(sy);
+	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
 
 	/*
 	 * Prevent the guest from touching the GIC system registers if
@@ -220,6 +320,15 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	}
 }
 
+void __hyp_text __vgic_v3_init_lrs(void)
+{
+	int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2));
+	int i;
+
+	for (i = 0; i <= max_lr_idx; i++)
+		__gic_v3_set_lr(0, i);
+}
+
 static u64 __hyp_text __vgic_v3_read_ich_vtr_el2(void)
 {
 	return read_gicreg(ICH_VTR_EL2);