[PATCH 00/16] KVM: arm64: Add NV GICv3 support

[PATCH 00/16] KVM: arm64: Add NV GICv3 support

[Marc Zyngier]

As a pendant to the timer code, here's the basic support for GICv3 for
NV.

Compared to the versions that have existed in the past, this is a
significant improvement, as the maintenance interrupt is finally
behaving correctly, and I have dropped the horrible hacks that only
gave the impression something was working.

The code is much simpler, isolated, and can even make some sense if
you have the correct pink-ish glasses.

As for the timer code, this has been tested as part of my integration
branch [1].

[1] https://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms.git/log/?h=kvm-arm64/nv-next

Andre Przywara (1):
  KVM: arm64: nv: Allow userland to set VGIC maintenance IRQ

Jintack Lim (1):
  KVM: arm64: nv: Respect virtual HCR_EL2.TWx setting

Marc Zyngier (12):
  arm64: sysreg: Add layout for ICH_HCR_EL2
  arm64: sysreg: Add layout for ICH_VTR_EL2
  arm64: sysreg: Add layout for ICH_MISR_EL2
  KVM: arm64: nv: Load timer before the GIC
  KVM: arm64: nv: Add ICH_*_EL2 registers to vpcu_sysreg
  KVM: arm64: nv: Plumb handling of GICv3 EL2 accesses
  KVM: arm64: nv: Sanitise ICH_HCR_EL2 accesses
  KVM: arm64: nv: Nested GICv3 emulation
  KVM: arm64: nv: Handle L2->L1 transition on interrupt injection
  KVM: arm64: nv: Add Maintenance Interrupt emulation
  KVM: arm64: nv: Propagate used_lrs between L1 and L0 contexts
  KVM: arm64: nv: Fold GICv3 host trapping requirements into guest setup

Oliver Upton (2):
  KVM: arm64: Move host SVE/SME state flags out of vCPU
  KVM: arm64: nv: Request vPE doorbell upon nested ERET to L2

 .../virt/kvm/devices/arm-vgic-v3.rst          |  12 +-
 arch/arm64/include/asm/kvm_emulate.h          |  13 +
 arch/arm64/include/asm/kvm_host.h             |  71 ++-
 arch/arm64/include/asm/kvm_hyp.h              |   2 +
 arch/arm64/include/asm/sysreg.h               |  30 --
 arch/arm64/include/uapi/asm/kvm.h             |   1 +
 arch/arm64/kvm/Makefile                       |   2 +-
 arch/arm64/kvm/arm.c                          |  13 +-
 arch/arm64/kvm/emulate-nested.c               |  18 +-
 arch/arm64/kvm/fpsimd.c                       |  12 +-
 arch/arm64/kvm/handle_exit.c                  |   6 +-
 arch/arm64/kvm/hyp/vgic-v3-sr.c               |  16 +-
 arch/arm64/kvm/nested.c                       |  12 +
 arch/arm64/kvm/sys_regs.c                     |  95 +++-
 arch/arm64/kvm/vgic-sys-reg-v3.c              |   8 +-
 arch/arm64/kvm/vgic/vgic-init.c               |  22 +
 arch/arm64/kvm/vgic/vgic-kvm-device.c         |  29 +-
 arch/arm64/kvm/vgic/vgic-v3-nested.c          | 409 ++++++++++++++++++
 arch/arm64/kvm/vgic/vgic-v3.c                 |  44 +-
 arch/arm64/kvm/vgic/vgic-v4.c                 |  18 +-
 arch/arm64/kvm/vgic/vgic.c                    |  38 ++
 arch/arm64/kvm/vgic/vgic.h                    |   6 +
 arch/arm64/tools/sysreg                       |  48 ++
 drivers/irqchip/irq-apple-aic.c               |   8 +-
 include/kvm/arm_vgic.h                        |  10 +
 tools/arch/arm/include/uapi/asm/kvm.h         |   1 +
 tools/arch/arm64/include/asm/sysreg.h         |  30 --
 27 files changed, 841 insertions(+), 133 deletions(-)
 create mode 100644 arch/arm64/kvm/vgic/vgic-v3-nested.c

-- 
2.39.2

[PATCH 01/16] arm64: sysreg: Add layout for ICH_HCR_EL2

[Marc Zyngier]

The ICH_HCR_EL2-related macros are missing a number of control
bits that we are about to handle. Take this opportunity to fully
describe the layout of that register as part of the automatic
generation infrastructure.

This results in a bit of churn, unfortunately.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/sysreg.h       | 12 ------------
 arch/arm64/kvm/emulate-nested.c       | 16 ++++++++--------
 arch/arm64/kvm/hyp/vgic-v3-sr.c       | 14 +++++++-------
 arch/arm64/kvm/vgic/vgic-v3.c         | 17 +++++++++--------
 arch/arm64/tools/sysreg               | 22 ++++++++++++++++++++++
 drivers/irqchip/irq-apple-aic.c       |  8 ++++----
 tools/arch/arm64/include/asm/sysreg.h | 12 ------------
 7 files changed, 50 insertions(+), 51 deletions(-)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index b8303a83c0bff..3e84ef8f5b311 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -561,7 +561,6 @@
 
 #define SYS_ICH_VSEIR_EL2		sys_reg(3, 4, 12, 9, 4)
 #define SYS_ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
-#define SYS_ICH_HCR_EL2			sys_reg(3, 4, 12, 11, 0)
 #define SYS_ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
 #define SYS_ICH_MISR_EL2		sys_reg(3, 4, 12, 11, 2)
 #define SYS_ICH_EISR_EL2		sys_reg(3, 4, 12, 11, 3)
@@ -1011,17 +1010,6 @@
 #define ICH_LR_PRIORITY_SHIFT	48
 #define ICH_LR_PRIORITY_MASK	(0xffULL << ICH_LR_PRIORITY_SHIFT)
 
-/* ICH_HCR_EL2 bit definitions */
-#define ICH_HCR_EN		(1 << 0)
-#define ICH_HCR_UIE		(1 << 1)
-#define ICH_HCR_NPIE		(1 << 3)
-#define ICH_HCR_TC		(1 << 10)
-#define ICH_HCR_TALL0		(1 << 11)
-#define ICH_HCR_TALL1		(1 << 12)
-#define ICH_HCR_TDIR		(1 << 14)
-#define ICH_HCR_EOIcount_SHIFT	27
-#define ICH_HCR_EOIcount_MASK	(0x1f << ICH_HCR_EOIcount_SHIFT)
-
 /* ICH_VMCR_EL2 bit definitions */
 #define ICH_VMCR_ACK_CTL_SHIFT	2
 #define ICH_VMCR_ACK_CTL_MASK	(1 << ICH_VMCR_ACK_CTL_SHIFT)
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 1ffbfd1c3cf2e..c460b8403aec5 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -395,26 +395,26 @@ static const struct trap_bits coarse_trap_bits[] = {
 	},
 	[CGT_ICH_HCR_TC] = {
 		.index		= ICH_HCR_EL2,
-		.value		= ICH_HCR_TC,
-		.mask		= ICH_HCR_TC,
+		.value		= ICH_HCR_EL2_TC,
+		.mask		= ICH_HCR_EL2_TC,
 		.behaviour	= BEHAVE_FORWARD_RW,
 	},
 	[CGT_ICH_HCR_TALL0] = {
 		.index		= ICH_HCR_EL2,
-		.value		= ICH_HCR_TALL0,
-		.mask		= ICH_HCR_TALL0,
+		.value		= ICH_HCR_EL2_TALL0,
+		.mask		= ICH_HCR_EL2_TALL0,
 		.behaviour	= BEHAVE_FORWARD_RW,
 	},
 	[CGT_ICH_HCR_TALL1] = {
 		.index		= ICH_HCR_EL2,
-		.value		= ICH_HCR_TALL1,
-		.mask		= ICH_HCR_TALL1,
+		.value		= ICH_HCR_EL2_TALL1,
+		.mask		= ICH_HCR_EL2_TALL1,
 		.behaviour	= BEHAVE_FORWARD_RW,
 	},
 	[CGT_ICH_HCR_TDIR] = {
 		.index		= ICH_HCR_EL2,
-		.value		= ICH_HCR_TDIR,
-		.mask		= ICH_HCR_TDIR,
+		.value		= ICH_HCR_EL2_TDIR,
+		.mask		= ICH_HCR_EL2_TDIR,
 		.behaviour	= BEHAVE_FORWARD_RW,
 	},
 };
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 3f9741e51d41b..b47dede973b3c 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -218,7 +218,7 @@ void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
 
 		elrsr = read_gicreg(ICH_ELRSR_EL2);
 
-		write_gicreg(cpu_if->vgic_hcr & ~ICH_HCR_EN, ICH_HCR_EL2);
+		write_gicreg(cpu_if->vgic_hcr & ~ICH_HCR_EL2_En, ICH_HCR_EL2);
 
 		for (i = 0; i < used_lrs; i++) {
 			if (elrsr & (1 << i))
@@ -274,7 +274,7 @@ void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
 	 * system registers to trap to EL1 (duh), force ICC_SRE_EL1.SRE to 1
 	 * so that the trap bits can take effect. Yes, we *loves* the GIC.
 	 */
-	if (!(cpu_if->vgic_hcr & ICH_HCR_EN)) {
+	if (!(cpu_if->vgic_hcr & ICH_HCR_EL2_En)) {
 		write_gicreg(ICC_SRE_EL1_SRE, ICC_SRE_EL1);
 		isb();
 	} else if (!cpu_if->vgic_sre) {
@@ -752,7 +752,7 @@ static void __vgic_v3_bump_eoicount(void)
 	u32 hcr;
 
 	hcr = read_gicreg(ICH_HCR_EL2);
-	hcr += 1 << ICH_HCR_EOIcount_SHIFT;
+	hcr += 1 << ICH_HCR_EL2_EOIcount_SHIFT;
 	write_gicreg(hcr, ICH_HCR_EL2);
 }
 
@@ -1069,7 +1069,7 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu,
 	case SYS_ICC_EOIR0_EL1:
 	case SYS_ICC_HPPIR0_EL1:
 	case SYS_ICC_IAR0_EL1:
-		return ich_hcr & ICH_HCR_TALL0;
+		return ich_hcr & ICH_HCR_EL2_TALL0;
 
 	case SYS_ICC_IGRPEN1_EL1:
 		if (is_read &&
@@ -1090,10 +1090,10 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu,
 	case SYS_ICC_EOIR1_EL1:
 	case SYS_ICC_HPPIR1_EL1:
 	case SYS_ICC_IAR1_EL1:
-		return ich_hcr & ICH_HCR_TALL1;
+		return ich_hcr & ICH_HCR_EL2_TALL1;
 
 	case SYS_ICC_DIR_EL1:
-		if (ich_hcr & ICH_HCR_TDIR)
+		if (ich_hcr & ICH_HCR_EL2_TDIR)
 			return true;
 
 		fallthrough;
@@ -1101,7 +1101,7 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu,
 	case SYS_ICC_RPR_EL1:
 	case SYS_ICC_CTLR_EL1:
 	case SYS_ICC_PMR_EL1:
-		return ich_hcr & ICH_HCR_TC;
+		return ich_hcr & ICH_HCR_EL2_TC;
 
 	default:
 		return false;
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index f267bc2486a18..6c21be12959d6 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -23,7 +23,7 @@ void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
 
-	cpuif->vgic_hcr |= ICH_HCR_UIE;
+	cpuif->vgic_hcr |= ICH_HCR_EL2_UIE;
 }
 
 static bool lr_signals_eoi_mi(u64 lr_val)
@@ -41,7 +41,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 
 	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
 
-	cpuif->vgic_hcr &= ~ICH_HCR_UIE;
+	cpuif->vgic_hcr &= ~ICH_HCR_EL2_UIE;
 
 	for (lr = 0; lr < cpuif->used_lrs; lr++) {
 		u64 val = cpuif->vgic_lr[lr];
@@ -291,7 +291,7 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
 					    ICH_VTR_PRI_BITS_SHIFT) + 1;
 
 	/* Get the show on the road... */
-	vgic_v3->vgic_hcr = ICH_HCR_EN;
+	vgic_v3->vgic_hcr = ICH_HCR_EL2_En;
 }
 
 void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu)
@@ -300,18 +300,19 @@ void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu)
 
 	/* Hide GICv3 sysreg if necessary */
 	if (!kvm_has_gicv3(vcpu->kvm)) {
-		vgic_v3->vgic_hcr |= ICH_HCR_TALL0 | ICH_HCR_TALL1 | ICH_HCR_TC;
+		vgic_v3->vgic_hcr |= (ICH_HCR_EL2_TALL0 | ICH_HCR_EL2_TALL1 |
+				      ICH_HCR_EL2_TC);
 		return;
 	}
 
 	if (group0_trap)
-		vgic_v3->vgic_hcr |= ICH_HCR_TALL0;
+		vgic_v3->vgic_hcr |= ICH_HCR_EL2_TALL0;
 	if (group1_trap)
-		vgic_v3->vgic_hcr |= ICH_HCR_TALL1;
+		vgic_v3->vgic_hcr |= ICH_HCR_EL2_TALL1;
 	if (common_trap)
-		vgic_v3->vgic_hcr |= ICH_HCR_TC;
+		vgic_v3->vgic_hcr |= ICH_HCR_EL2_TC;
 	if (dir_trap)
-		vgic_v3->vgic_hcr |= ICH_HCR_TDIR;
+		vgic_v3->vgic_hcr |= ICH_HCR_EL2_TDIR;
 }
 
 int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq)
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index b081b54d6d227..9938926421b5c 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -2938,6 +2938,28 @@ Field	31:16	PhyPARTID29
 Field	15:0	PhyPARTID28
 EndSysreg
 
+Sysreg	ICH_HCR_EL2	3	4	12	11	0
+Res0	63:32
+Field	31:27	EOIcount
+Res0	26:16
+Field	15	DVIM
+Field	14	TDIR
+Field	13	TSEI
+Field	12	TALL1
+Field	11	TALL0
+Field	10	TC
+Res0	9
+Field	8	vSGIEOICount
+Field	7	VGrp1DIE
+Field	6	VGrp1EIE
+Field	5	VGrp0DIE
+Field	4	VGrp0EIE
+Field	3	NPIE
+Field	2	LRENPIE
+Field	1	UIE
+Field	0	En
+EndSysreg
+
 Sysreg	CONTEXTIDR_EL2	3	4	13	0	1
 Fields	CONTEXTIDR_ELx
 EndSysreg
diff --git a/drivers/irqchip/irq-apple-aic.c b/drivers/irqchip/irq-apple-aic.c
index da5250f0155cf..7a5cc26529f82 100644
--- a/drivers/irqchip/irq-apple-aic.c
+++ b/drivers/irqchip/irq-apple-aic.c
@@ -409,15 +409,15 @@ static void __exception_irq_entry aic_handle_irq(struct pt_regs *regs)
 	 * in use, and be cleared when coming back from the handler.
 	 */
 	if (is_kernel_in_hyp_mode() &&
-	    (read_sysreg_s(SYS_ICH_HCR_EL2) & ICH_HCR_EN) &&
+	    (read_sysreg_s(SYS_ICH_HCR_EL2) & ICH_HCR_EL2_En) &&
 	    read_sysreg_s(SYS_ICH_MISR_EL2) != 0) {
 		generic_handle_domain_irq(aic_irqc->hw_domain,
 					  AIC_FIQ_HWIRQ(AIC_VGIC_MI));
 
-		if (unlikely((read_sysreg_s(SYS_ICH_HCR_EL2) & ICH_HCR_EN) &&
+		if (unlikely((read_sysreg_s(SYS_ICH_HCR_EL2) & ICH_HCR_EL2_En) &&
 			     read_sysreg_s(SYS_ICH_MISR_EL2))) {
 			pr_err_ratelimited("vGIC IRQ fired and not handled by KVM, disabling.\n");
-			sysreg_clear_set_s(SYS_ICH_HCR_EL2, ICH_HCR_EN, 0);
+			sysreg_clear_set_s(SYS_ICH_HCR_EL2, ICH_HCR_EL2_En, 0);
 		}
 	}
 }
@@ -840,7 +840,7 @@ static int aic_init_cpu(unsigned int cpu)
 				   VM_TMR_FIQ_ENABLE_V | VM_TMR_FIQ_ENABLE_P, 0);
 
 		/* vGIC maintenance IRQ */
-		sysreg_clear_set_s(SYS_ICH_HCR_EL2, ICH_HCR_EN, 0);
+		sysreg_clear_set_s(SYS_ICH_HCR_EL2, ICH_HCR_EL2_En, 0);
 	}
 
 	/* PMC FIQ */
diff --git a/tools/arch/arm64/include/asm/sysreg.h b/tools/arch/arm64/include/asm/sysreg.h
index cd8420e8c3ad8..d314ccab7560a 100644
--- a/tools/arch/arm64/include/asm/sysreg.h
+++ b/tools/arch/arm64/include/asm/sysreg.h
@@ -420,7 +420,6 @@
 
 #define SYS_ICH_VSEIR_EL2		sys_reg(3, 4, 12, 9, 4)
 #define SYS_ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
-#define SYS_ICH_HCR_EL2			sys_reg(3, 4, 12, 11, 0)
 #define SYS_ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
 #define SYS_ICH_MISR_EL2		sys_reg(3, 4, 12, 11, 2)
 #define SYS_ICH_EISR_EL2		sys_reg(3, 4, 12, 11, 3)
@@ -654,17 +653,6 @@
 #define ICH_LR_PRIORITY_SHIFT	48
 #define ICH_LR_PRIORITY_MASK	(0xffULL << ICH_LR_PRIORITY_SHIFT)
 
-/* ICH_HCR_EL2 bit definitions */
-#define ICH_HCR_EN		(1 << 0)
-#define ICH_HCR_UIE		(1 << 1)
-#define ICH_HCR_NPIE		(1 << 3)
-#define ICH_HCR_TC		(1 << 10)
-#define ICH_HCR_TALL0		(1 << 11)
-#define ICH_HCR_TALL1		(1 << 12)
-#define ICH_HCR_TDIR		(1 << 14)
-#define ICH_HCR_EOIcount_SHIFT	27
-#define ICH_HCR_EOIcount_MASK	(0x1f << ICH_HCR_EOIcount_SHIFT)
-
 /* ICH_VMCR_EL2 bit definitions */
 #define ICH_VMCR_ACK_CTL_SHIFT	2
 #define ICH_VMCR_ACK_CTL_MASK	(1 << ICH_VMCR_ACK_CTL_SHIFT)
-- 
2.39.2

[PATCH 02/16] arm64: sysreg: Add layout for ICH_VTR_EL2

[Marc Zyngier]

The ICH_VTR_EL2-related macros are missing a number of config
bits that we are about to handle. Take this opportunity to fully
describe the layout of that register as part of the automatic
generation infrastructure.

This results in a bit of churn to repaint constants that are now
generated with a different format.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/sysreg.h       | 13 -------------
 arch/arm64/kvm/vgic-sys-reg-v3.c      |  8 ++++----
 arch/arm64/kvm/vgic/vgic-v3.c         | 16 +++++++---------
 arch/arm64/tools/sysreg               | 14 ++++++++++++++
 tools/arch/arm64/include/asm/sysreg.h | 13 -------------
 5 files changed, 25 insertions(+), 39 deletions(-)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 3e84ef8f5b311..cf74ebcd46d95 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -561,7 +561,6 @@
 
 #define SYS_ICH_VSEIR_EL2		sys_reg(3, 4, 12, 9, 4)
 #define SYS_ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
-#define SYS_ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
 #define SYS_ICH_MISR_EL2		sys_reg(3, 4, 12, 11, 2)
 #define SYS_ICH_EISR_EL2		sys_reg(3, 4, 12, 11, 3)
 #define SYS_ICH_ELRSR_EL2		sys_reg(3, 4, 12, 11, 5)
@@ -1030,18 +1029,6 @@
 #define ICH_VMCR_ENG1_SHIFT	1
 #define ICH_VMCR_ENG1_MASK	(1 << ICH_VMCR_ENG1_SHIFT)
 
-/* ICH_VTR_EL2 bit definitions */
-#define ICH_VTR_PRI_BITS_SHIFT	29
-#define ICH_VTR_PRI_BITS_MASK	(7 << ICH_VTR_PRI_BITS_SHIFT)
-#define ICH_VTR_ID_BITS_SHIFT	23
-#define ICH_VTR_ID_BITS_MASK	(7 << ICH_VTR_ID_BITS_SHIFT)
-#define ICH_VTR_SEIS_SHIFT	22
-#define ICH_VTR_SEIS_MASK	(1 << ICH_VTR_SEIS_SHIFT)
-#define ICH_VTR_A3V_SHIFT	21
-#define ICH_VTR_A3V_MASK	(1 << ICH_VTR_A3V_SHIFT)
-#define ICH_VTR_TDS_SHIFT	19
-#define ICH_VTR_TDS_MASK	(1 << ICH_VTR_TDS_SHIFT)
-
 /*
  * Permission Indirection Extension (PIE) permission encodings.
  * Encodings with the _O suffix, have overlays applied (Permission Overlay Extension).
diff --git a/arch/arm64/kvm/vgic-sys-reg-v3.c b/arch/arm64/kvm/vgic-sys-reg-v3.c
index 9e7c486b48c2e..5eacb4b3250a1 100644
--- a/arch/arm64/kvm/vgic-sys-reg-v3.c
+++ b/arch/arm64/kvm/vgic-sys-reg-v3.c
@@ -35,12 +35,12 @@ static int set_gic_ctlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 
 	vgic_v3_cpu->num_id_bits = host_id_bits;
 
-	host_seis = FIELD_GET(ICH_VTR_SEIS_MASK, kvm_vgic_global_state.ich_vtr_el2);
+	host_seis = FIELD_GET(ICH_VTR_EL2_SEIS, kvm_vgic_global_state.ich_vtr_el2);
 	seis = FIELD_GET(ICC_CTLR_EL1_SEIS_MASK, val);
 	if (host_seis != seis)
 		return -EINVAL;
 
-	host_a3v = FIELD_GET(ICH_VTR_A3V_MASK, kvm_vgic_global_state.ich_vtr_el2);
+	host_a3v = FIELD_GET(ICH_VTR_EL2_A3V, kvm_vgic_global_state.ich_vtr_el2);
 	a3v = FIELD_GET(ICC_CTLR_EL1_A3V_MASK, val);
 	if (host_a3v != a3v)
 		return -EINVAL;
@@ -68,10 +68,10 @@ static int get_gic_ctlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 	val |= FIELD_PREP(ICC_CTLR_EL1_PRI_BITS_MASK, vgic_v3_cpu->num_pri_bits - 1);
 	val |= FIELD_PREP(ICC_CTLR_EL1_ID_BITS_MASK, vgic_v3_cpu->num_id_bits);
 	val |= FIELD_PREP(ICC_CTLR_EL1_SEIS_MASK,
-			  FIELD_GET(ICH_VTR_SEIS_MASK,
+			  FIELD_GET(ICH_VTR_EL2_SEIS,
 				    kvm_vgic_global_state.ich_vtr_el2));
 	val |= FIELD_PREP(ICC_CTLR_EL1_A3V_MASK,
-			  FIELD_GET(ICH_VTR_A3V_MASK, kvm_vgic_global_state.ich_vtr_el2));
+			  FIELD_GET(ICH_VTR_EL2_A3V, kvm_vgic_global_state.ich_vtr_el2));
 	/*
 	 * The VMCR.CTLR value is in ICC_CTLR_EL1 layout.
 	 * Extract it directly using ICC_CTLR_EL1 reg definitions.
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 6c21be12959d6..0bdecbbe74898 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -283,12 +283,10 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
 		vgic_v3->vgic_sre = 0;
 	}
 
-	vcpu->arch.vgic_cpu.num_id_bits = (kvm_vgic_global_state.ich_vtr_el2 &
-					   ICH_VTR_ID_BITS_MASK) >>
-					   ICH_VTR_ID_BITS_SHIFT;
-	vcpu->arch.vgic_cpu.num_pri_bits = ((kvm_vgic_global_state.ich_vtr_el2 &
-					    ICH_VTR_PRI_BITS_MASK) >>
-					    ICH_VTR_PRI_BITS_SHIFT) + 1;
+	vcpu->arch.vgic_cpu.num_id_bits = FIELD_GET(ICH_VTR_EL2_IDbits,
+						    kvm_vgic_global_state.ich_vtr_el2);
+	vcpu->arch.vgic_cpu.num_pri_bits = FIELD_GET(ICH_VTR_EL2_PRIbits,
+						     kvm_vgic_global_state.ich_vtr_el2) + 1;
 
 	/* Get the show on the road... */
 	vgic_v3->vgic_hcr = ICH_HCR_EL2_En;
@@ -632,7 +630,7 @@ static const struct midr_range broken_seis[] = {
 
 static bool vgic_v3_broken_seis(void)
 {
-	return ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) &&
+	return ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_EL2_SEIS) &&
 		is_midr_in_range_list(read_cpuid_id(), broken_seis));
 }
 
@@ -706,10 +704,10 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	if (vgic_v3_broken_seis()) {
 		kvm_info("GICv3 with broken locally generated SEI\n");
 
-		kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_SEIS_MASK;
+		kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_EL2_SEIS;
 		group0_trap = true;
 		group1_trap = true;
-		if (ich_vtr_el2 & ICH_VTR_TDS_MASK)
+		if (ich_vtr_el2 & ICH_VTR_EL2_TDS)
 			dir_trap = true;
 		else
 			common_trap = true;
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index 9938926421b5c..f5927d345eea3 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -2960,6 +2960,20 @@ Field	1	UIE
 Field	0	En
 EndSysreg
 
+Sysreg	ICH_VTR_EL2	3	4	12	11	1
+Res0	63:32
+Field	31:29	PRIbits
+Field	28:26	PREbits
+Field	25:23	IDbits
+Field	22	SEIS
+Field	21	A3V
+Field	20	nV4
+Field	19	TDS
+Field	18	DVIM
+Res0	17:5
+Field	4:0	ListRegs
+EndSysreg
+
 Sysreg	CONTEXTIDR_EL2	3	4	13	0	1
 Fields	CONTEXTIDR_ELx
 EndSysreg
diff --git a/tools/arch/arm64/include/asm/sysreg.h b/tools/arch/arm64/include/asm/sysreg.h
index d314ccab7560a..f43e303d31d25 100644
--- a/tools/arch/arm64/include/asm/sysreg.h
+++ b/tools/arch/arm64/include/asm/sysreg.h
@@ -420,7 +420,6 @@
 
 #define SYS_ICH_VSEIR_EL2		sys_reg(3, 4, 12, 9, 4)
 #define SYS_ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
-#define SYS_ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
 #define SYS_ICH_MISR_EL2		sys_reg(3, 4, 12, 11, 2)
 #define SYS_ICH_EISR_EL2		sys_reg(3, 4, 12, 11, 3)
 #define SYS_ICH_ELRSR_EL2		sys_reg(3, 4, 12, 11, 5)
@@ -673,18 +672,6 @@
 #define ICH_VMCR_ENG1_SHIFT	1
 #define ICH_VMCR_ENG1_MASK	(1 << ICH_VMCR_ENG1_SHIFT)
 
-/* ICH_VTR_EL2 bit definitions */
-#define ICH_VTR_PRI_BITS_SHIFT	29
-#define ICH_VTR_PRI_BITS_MASK	(7 << ICH_VTR_PRI_BITS_SHIFT)
-#define ICH_VTR_ID_BITS_SHIFT	23
-#define ICH_VTR_ID_BITS_MASK	(7 << ICH_VTR_ID_BITS_SHIFT)
-#define ICH_VTR_SEIS_SHIFT	22
-#define ICH_VTR_SEIS_MASK	(1 << ICH_VTR_SEIS_SHIFT)
-#define ICH_VTR_A3V_SHIFT	21
-#define ICH_VTR_A3V_MASK	(1 << ICH_VTR_A3V_SHIFT)
-#define ICH_VTR_TDS_SHIFT	19
-#define ICH_VTR_TDS_MASK	(1 << ICH_VTR_TDS_SHIFT)
-
 /*
  * Permission Indirection Extension (PIE) permission encodings.
  * Encodings with the _O suffix, have overlays applied (Permission Overlay Extension).
-- 
2.39.2

[PATCH 03/16] arm64: sysreg: Add layout for ICH_MISR_EL2

[Marc Zyngier]

The ICH_MISR_EL2-related macros are missing a number of status
bits that we are about to handle. Take this opportunity to fully
describe the layout of that register as part of the automatic
generation infrastructure.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/sysreg.h       |  5 -----
 arch/arm64/tools/sysreg               | 12 ++++++++++++
 tools/arch/arm64/include/asm/sysreg.h |  5 -----
 3 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index cf74ebcd46d95..815e9b0bdff27 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -561,7 +561,6 @@
 
 #define SYS_ICH_VSEIR_EL2		sys_reg(3, 4, 12, 9, 4)
 #define SYS_ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
-#define SYS_ICH_MISR_EL2		sys_reg(3, 4, 12, 11, 2)
 #define SYS_ICH_EISR_EL2		sys_reg(3, 4, 12, 11, 3)
 #define SYS_ICH_ELRSR_EL2		sys_reg(3, 4, 12, 11, 5)
 #define SYS_ICH_VMCR_EL2		sys_reg(3, 4, 12, 11, 7)
@@ -991,10 +990,6 @@
 #define TRFCR_ELx_E0TRE			BIT(0)
 
 /* GIC Hypervisor interface registers */
-/* ICH_MISR_EL2 bit definitions */
-#define ICH_MISR_EOI		(1 << 0)
-#define ICH_MISR_U		(1 << 1)
-
 /* ICH_LR*_EL2 bit definitions */
 #define ICH_LR_VIRTUAL_ID_MASK	((1ULL << 32) - 1)
 
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index f5927d345eea3..a601231a088d7 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -2974,6 +2974,18 @@ Res0	17:5
 Field	4:0	ListRegs
 EndSysreg
 
+Sysreg	ICH_MISR_EL2	3	4	12	11	2
+Res0	63:8
+Field	7	VGrp1D
+Field	6	VGrp1E
+Field	5	VGrp0D
+Field	4	VGrp0E
+Field	3	NP
+Field	2	LRENP
+Field	1	U
+Field	0	EOI
+EndSysreg
+
 Sysreg	CONTEXTIDR_EL2	3	4	13	0	1
 Fields	CONTEXTIDR_ELx
 EndSysreg
diff --git a/tools/arch/arm64/include/asm/sysreg.h b/tools/arch/arm64/include/asm/sysreg.h
index f43e303d31d25..0169bd3137caf 100644
--- a/tools/arch/arm64/include/asm/sysreg.h
+++ b/tools/arch/arm64/include/asm/sysreg.h
@@ -420,7 +420,6 @@
 
 #define SYS_ICH_VSEIR_EL2		sys_reg(3, 4, 12, 9, 4)
 #define SYS_ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
-#define SYS_ICH_MISR_EL2		sys_reg(3, 4, 12, 11, 2)
 #define SYS_ICH_EISR_EL2		sys_reg(3, 4, 12, 11, 3)
 #define SYS_ICH_ELRSR_EL2		sys_reg(3, 4, 12, 11, 5)
 #define SYS_ICH_VMCR_EL2		sys_reg(3, 4, 12, 11, 7)
@@ -634,10 +633,6 @@
 #define TRFCR_ELx_E0TRE			BIT(0)
 
 /* GIC Hypervisor interface registers */
-/* ICH_MISR_EL2 bit definitions */
-#define ICH_MISR_EOI		(1 << 0)
-#define ICH_MISR_U		(1 << 1)
-
 /* ICH_LR*_EL2 bit definitions */
 #define ICH_LR_VIRTUAL_ID_MASK	((1ULL << 32) - 1)
 
-- 
2.39.2

[PATCH 04/16] KVM: arm64: Move host SVE/SME state flags out of vCPU

[Marc Zyngier]

From: Oliver Upton <oliver.upton@linux.dev>

We're running a bit tight on vCPU state flags, and there's no good
reason for tracking bits of host state in the vCPU. Rather than do the
unspeakable and add another byte of sflags, move some of the obvious
host bits over to kvm_host_data where they really belong.

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20240823212703.3576061-3-oliver.upton@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 26 ++++++++++++++++----------
 arch/arm64/kvm/fpsimd.c           | 12 ++++++------
 2 files changed, 22 insertions(+), 16 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e18e9244d17a4..8cc25845b4be3 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -610,6 +610,12 @@ struct cpu_sve_state {
  * field.
  */
 struct kvm_host_data {
+	/* SVE enabled for EL0 */
+#define HOST_SVE_ENABLED	0
+	/* SME enabled for EL0 */
+#define HOST_SME_ENABLED	1
+	unsigned long flags;
+
 	struct kvm_cpu_context host_ctxt;
 
 	/*
@@ -913,22 +919,18 @@ struct kvm_vcpu_arch {
 /* Save TRBE context if active  */
 #define DEBUG_STATE_SAVE_TRBE	__vcpu_single_flag(iflags, BIT(6))
 
-/* SVE enabled for host EL0 */
-#define HOST_SVE_ENABLED	__vcpu_single_flag(sflags, BIT(0))
-/* SME enabled for EL0 */
-#define HOST_SME_ENABLED	__vcpu_single_flag(sflags, BIT(1))
 /* Physical CPU not in supported_cpus */
-#define ON_UNSUPPORTED_CPU	__vcpu_single_flag(sflags, BIT(2))
+#define ON_UNSUPPORTED_CPU	__vcpu_single_flag(sflags, BIT(0))
 /* WFIT instruction trapped */
-#define IN_WFIT			__vcpu_single_flag(sflags, BIT(3))
+#define IN_WFIT			__vcpu_single_flag(sflags, BIT(1))
 /* vcpu system registers loaded on physical CPU */
-#define SYSREGS_ON_CPU		__vcpu_single_flag(sflags, BIT(4))
+#define SYSREGS_ON_CPU		__vcpu_single_flag(sflags, BIT(2))
 /* Software step state is Active-pending */
-#define DBG_SS_ACTIVE_PENDING	__vcpu_single_flag(sflags, BIT(5))
+#define DBG_SS_ACTIVE_PENDING	__vcpu_single_flag(sflags, BIT(3))
 /* PMUSERENR for the guest EL0 is on physical CPU */
-#define PMUSERENR_ON_CPU	__vcpu_single_flag(sflags, BIT(6))
+#define PMUSERENR_ON_CPU	__vcpu_single_flag(sflags, BIT(4))
 /* WFI instruction trapped */
-#define IN_WFI			__vcpu_single_flag(sflags, BIT(7))
+#define IN_WFI			__vcpu_single_flag(sflags, BIT(5))
 
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
@@ -1307,6 +1309,10 @@ DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data);
 	 &this_cpu_ptr_hyp_sym(kvm_host_data)->f)
 #endif
 
+#define host_data_set_flag(nr)		set_bit(nr, host_data_ptr(flags))
+#define host_data_test_flag(nr)		test_bit(nr, host_data_ptr(flags))
+#define host_data_clear_flag(nr)	clear_bit(nr, host_data_ptr(flags))
+
 /* Check whether the FP regs are owned by the guest */
 static inline bool guest_owns_fp_regs(void)
 {
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index ea5484ce1f3ba..0e0f37d1990a3 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -65,14 +65,14 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 	*host_data_ptr(fpsimd_state) = kern_hyp_va(&current->thread.uw.fpsimd_state);
 	*host_data_ptr(fpmr_ptr) = kern_hyp_va(&current->thread.uw.fpmr);
 
-	vcpu_clear_flag(vcpu, HOST_SVE_ENABLED);
+	host_data_clear_flag(HOST_SVE_ENABLED);
 	if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
-		vcpu_set_flag(vcpu, HOST_SVE_ENABLED);
+		host_data_set_flag(HOST_SVE_ENABLED);
 
 	if (system_supports_sme()) {
-		vcpu_clear_flag(vcpu, HOST_SME_ENABLED);
+		host_data_clear_flag(HOST_SME_ENABLED);
 		if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN)
-			vcpu_set_flag(vcpu, HOST_SME_ENABLED);
+			host_data_set_flag(HOST_SME_ENABLED);
 
 		/*
 		 * If PSTATE.SM is enabled then save any pending FP
@@ -168,7 +168,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 	 */
 	if (has_vhe() && system_supports_sme()) {
 		/* Also restore EL0 state seen on entry */
-		if (vcpu_get_flag(vcpu, HOST_SME_ENABLED))
+		if (host_data_test_flag(HOST_SME_ENABLED))
 			sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_SMEN);
 		else
 			sysreg_clear_set(CPACR_EL1,
@@ -227,7 +227,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 		 * for EL0.  To avoid spurious traps, restore the trap state
 		 * seen by kvm_arch_vcpu_load_fp():
 		 */
-		if (vcpu_get_flag(vcpu, HOST_SVE_ENABLED))
+		if (host_data_test_flag(HOST_SVE_ENABLED))
 			sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN);
 		else
 			sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0);
-- 
2.39.2

[PATCH 05/16] KVM: arm64: nv: Load timer before the GIC

[Marc Zyngier]

In order for vgic_v3_load_nested to be able to observe which timer
interrupts have the HW bit set for the current context, the timers
must have been loaded in the new mode and the right timer mapped
to their corresponding HW IRQs.

At the moment, we load the GIC first, meaning that timer interrupts
injected to an L2 guest will never have the HW bit set (we see the
old configuration).

Swapping the two loads solves this particular problem.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/arm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index a102c3aebdbc4..3115c44ed4042 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -596,8 +596,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	vcpu->cpu = cpu;
 
-	kvm_vgic_load(vcpu);
 	kvm_timer_vcpu_load(vcpu);
+	kvm_vgic_load(vcpu);
 	if (has_vhe())
 		kvm_vcpu_load_vhe(vcpu);
 	kvm_arch_vcpu_load_fp(vcpu);
-- 
2.39.2

[PATCH 06/16] KVM: arm64: nv: Add ICH_*_EL2 registers to vpcu_sysreg

[Marc Zyngier]

FEAT_NV2 comes with a bunch of register-to-memory redirection
involving the ICH_*_EL2 registers (LRs, APRs, VMCR, HCR).

Adds them to the vcpu_sysreg enumeration.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 8cc25845b4be3..218047cd0296d 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -554,7 +554,33 @@ enum vcpu_sysreg {
 	VNCR(CNTP_CVAL_EL0),
 	VNCR(CNTP_CTL_EL0),
 
+	VNCR(ICH_LR0_EL2),
+	VNCR(ICH_LR1_EL2),
+	VNCR(ICH_LR2_EL2),
+	VNCR(ICH_LR3_EL2),
+	VNCR(ICH_LR4_EL2),
+	VNCR(ICH_LR5_EL2),
+	VNCR(ICH_LR6_EL2),
+	VNCR(ICH_LR7_EL2),
+	VNCR(ICH_LR8_EL2),
+	VNCR(ICH_LR9_EL2),
+	VNCR(ICH_LR10_EL2),
+	VNCR(ICH_LR11_EL2),
+	VNCR(ICH_LR12_EL2),
+	VNCR(ICH_LR13_EL2),
+	VNCR(ICH_LR14_EL2),
+	VNCR(ICH_LR15_EL2),
+
+	VNCR(ICH_AP0R0_EL2),
+	VNCR(ICH_AP0R1_EL2),
+	VNCR(ICH_AP0R2_EL2),
+	VNCR(ICH_AP0R3_EL2),
+	VNCR(ICH_AP1R0_EL2),
+	VNCR(ICH_AP1R1_EL2),
+	VNCR(ICH_AP1R2_EL2),
+	VNCR(ICH_AP1R3_EL2),
 	VNCR(ICH_HCR_EL2),
+	VNCR(ICH_VMCR_EL2),
 
 	NR_SYS_REGS	/* Nothing after this line! */
 };
-- 
2.39.2

[PATCH 07/16] KVM: arm64: nv: Plumb handling of GICv3 EL2 accesses

[Marc Zyngier]

Wire the handling of all GICv3 EL2 registers, and provide emulation
for all the non memory-backed registers (ICC_SRE_EL2, ICH_VTR_EL2,
ICH_MISR_EL2, ICH_ELRSR_EL2, and ICH_EISR_EL2).

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/Makefile              |   2 +-
 arch/arm64/kvm/sys_regs.c            |  95 +++++++++++++++++++-
 arch/arm64/kvm/vgic/vgic-v3-nested.c | 125 +++++++++++++++++++++++++++
 include/kvm/arm_vgic.h               |   4 +
 4 files changed, 224 insertions(+), 2 deletions(-)
 create mode 100644 arch/arm64/kvm/vgic/vgic-v3-nested.c

diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 3cf7adb2b5038..209bc76263f10 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -23,7 +23,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
 	 vgic/vgic-v3.o vgic/vgic-v4.o \
 	 vgic/vgic-mmio.o vgic/vgic-mmio-v2.o \
 	 vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \
-	 vgic/vgic-its.o vgic/vgic-debug.o
+	 vgic/vgic-its.o vgic/vgic-debug.o vgic/vgic-v3-nested.o
 
 kvm-$(CONFIG_HW_PERF_EVENTS)  += pmu-emul.o pmu.o
 kvm-$(CONFIG_ARM64_PTR_AUTH)  += pauth.o
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 83c6b4a07ef56..c6d09c25b2522 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -17,6 +17,7 @@
 #include <linux/mm.h>
 #include <linux/printk.h>
 #include <linux/uaccess.h>
+#include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/arm_pmuv3.h>
 #include <asm/cacheflush.h>
@@ -531,7 +532,13 @@ static bool access_gic_sre(struct kvm_vcpu *vcpu,
 	if (p->is_write)
 		return ignore_write(vcpu, p);
 
-	p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre;
+	if (p->Op1 == 4) {	/* ICC_SRE_EL2 */
+		p->regval = (ICC_SRE_EL2_ENABLE | ICC_SRE_EL2_SRE |
+			     ICC_SRE_EL1_DIB | ICC_SRE_EL1_DFB);
+	} else {		/* ICC_SRE_EL1 */
+		p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre;
+	}
+
 	return true;
 }
 
@@ -2402,6 +2409,59 @@ static bool access_zcr_el2(struct kvm_vcpu *vcpu,
 	vq = SYS_FIELD_GET(ZCR_ELx, LEN, p->regval) + 1;
 	vq = min(vq, vcpu_sve_max_vq(vcpu));
 	vcpu_write_sys_reg(vcpu, vq - 1, ZCR_EL2);
+
+	return true;
+}
+
+static bool access_gic_vtr(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = kvm_vgic_global_state.ich_vtr_el2;
+	p->regval &= ~(ICH_VTR_EL2_DVIM 	|
+		       ICH_VTR_EL2_A3V		|
+		       ICH_VTR_EL2_IDbits);
+	p->regval |= ICH_VTR_EL2_nV4;
+
+	return true;
+}
+
+static bool access_gic_misr(struct kvm_vcpu *vcpu,
+			    struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = vgic_v3_get_misr(vcpu);
+
+	return true;
+}
+
+static bool access_gic_eisr(struct kvm_vcpu *vcpu,
+			    struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = vgic_v3_get_eisr(vcpu);
+
+	return true;
+}
+
+static bool access_gic_elrsr(struct kvm_vcpu *vcpu,
+			     struct sys_reg_params *p,
+			     const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = vgic_v3_get_elrsr(vcpu);
+
 	return true;
 }
 
@@ -3050,7 +3110,40 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(RVBAR_EL2, access_rw, reset_val, 0),
 	{ SYS_DESC(SYS_RMR_EL2), undef_access },
 
+	EL2_REG_VNCR(ICH_AP0R0_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP0R1_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP0R2_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP0R3_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP1R0_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP1R1_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP1R2_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP1R3_EL2, reset_val, 0),
+
+	{ SYS_DESC(SYS_ICC_SRE_EL2), access_gic_sre },
+
 	EL2_REG_VNCR(ICH_HCR_EL2, reset_val, 0),
+	{ SYS_DESC(SYS_ICH_VTR_EL2), access_gic_vtr },
+	{ SYS_DESC(SYS_ICH_MISR_EL2), access_gic_misr },
+	{ SYS_DESC(SYS_ICH_EISR_EL2), access_gic_eisr },
+	{ SYS_DESC(SYS_ICH_ELRSR_EL2), access_gic_elrsr },
+	EL2_REG_VNCR(ICH_VMCR_EL2, reset_val, 0),
+
+	EL2_REG_VNCR(ICH_LR0_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR1_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR2_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR3_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR4_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR5_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR6_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR7_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR8_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR9_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR10_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR11_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR12_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR13_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR14_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR15_EL2, reset_val, 0),
 
 	EL2_REG(CONTEXTIDR_EL2, access_rw, reset_val, 0),
 	EL2_REG(TPIDR_EL2, access_rw, reset_val, 0),
diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
new file mode 100644
index 0000000000000..48bfd2f556a36
--- /dev/null
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/cpu.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/uaccess.h>
+
+#include <kvm/arm_vgic.h>
+
+#include <asm/kvm_arm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_nested.h>
+
+#include "vgic.h"
+
+#define ICH_LRN(n)	(ICH_LR0_EL2 + (n))
+
+struct mi_state {
+	u16	eisr;
+	u16	elrsr;
+	bool	pend;
+};
+
+/*
+ * Nesting GICv3 support
+ *
+ * System register emulation:
+ *
+ * We get two classes of registers:
+ *
+ * - those backed by memory (LRs, APRs, HCR, VMCR): L1 can freely access
+ *   them, and L0 doesn't see a thing.
+ *
+ * - those that always trap (ELRSR, EISR, MISR): these are status registers
+ *   that are built on the fly based on the in-memory state.
+ *
+ * Only L1 can access the ICH_*_EL2 registers. A non-NV L2 obviously cannot,
+ * and a NV L2 would either access the VNCR page provided by L1 (memory
+ * based registers), or see the access redirected to L1 (registers that
+ * trap) thanks to NV being set by L1.
+ */
+
+static bool lr_triggers_eoi(u64 lr)
+{
+	return !(lr & (ICH_LR_STATE | ICH_LR_HW)) && (lr & ICH_LR_EOI);
+}
+
+static void vgic_compute_mi_state(struct kvm_vcpu *vcpu, struct mi_state *mi_state)
+{
+	u16 eisr = 0, elrsr = 0;
+	bool pend = false;
+
+	for (int i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
+		u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
+
+		if (lr_triggers_eoi(lr))
+			eisr |= BIT(i);
+		if (!(lr & ICH_LR_STATE))
+			elrsr |= BIT(i);
+		pend |= (lr & ICH_LR_PENDING_BIT);
+	}
+
+	mi_state->eisr	= eisr;
+	mi_state->elrsr	= elrsr;
+	mi_state->pend	= pend;
+}
+
+u16 vgic_v3_get_eisr(struct kvm_vcpu *vcpu)
+{
+	struct mi_state mi_state;
+
+	vgic_compute_mi_state(vcpu, &mi_state);
+	return mi_state.eisr;
+}
+
+u16 vgic_v3_get_elrsr(struct kvm_vcpu *vcpu)
+{
+	struct mi_state mi_state;
+
+	vgic_compute_mi_state(vcpu, &mi_state);
+	return mi_state.elrsr;
+}
+
+u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu)
+{
+	struct mi_state mi_state;
+	u64 reg = 0, hcr, vmcr;
+
+	hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
+	vmcr = __vcpu_sys_reg(vcpu, ICH_VMCR_EL2);
+
+	vgic_compute_mi_state(vcpu, &mi_state);
+
+	if (mi_state.eisr)
+		reg |= ICH_MISR_EL2_EOI;
+
+	if (__vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_UIE) {
+		int used_lrs = kvm_vgic_global_state.nr_lr;
+
+		used_lrs -= hweight16(mi_state.elrsr);
+		reg |= (used_lrs <= 1) ? ICH_MISR_EL2_U : 0;
+	}
+
+	if ((hcr & ICH_HCR_EL2_LRENPIE) && FIELD_GET(ICH_HCR_EL2_EOIcount_MASK, hcr))
+		reg |= ICH_MISR_EL2_LRENP;
+
+	if ((hcr & ICH_HCR_EL2_NPIE) && !mi_state.pend)
+		reg |= ICH_MISR_EL2_NP;
+
+	if ((hcr & ICH_HCR_EL2_VGrp0EIE) && (vmcr & ICH_VMCR_ENG0_MASK))
+		reg |= ICH_MISR_EL2_VGrp0E;
+
+	if ((hcr & ICH_HCR_EL2_VGrp0DIE) && !(vmcr & ICH_VMCR_ENG0_MASK))
+		reg |= ICH_MISR_EL2_VGrp0D;
+
+	if ((hcr & ICH_HCR_EL2_VGrp1EIE) && (vmcr & ICH_VMCR_ENG1_MASK))
+		reg |= ICH_MISR_EL2_VGrp1E;
+
+	if ((hcr & ICH_HCR_EL2_VGrp1DIE) && !(vmcr & ICH_VMCR_ENG1_MASK))
+		reg |= ICH_MISR_EL2_VGrp1D;
+
+	return reg;
+}
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 3a8ccfda34d29..5017fcc71e604 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -389,6 +389,10 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
 void kvm_vgic_load(struct kvm_vcpu *vcpu);
 void kvm_vgic_put(struct kvm_vcpu *vcpu);
 
+u16 vgic_v3_get_eisr(struct kvm_vcpu *vcpu);
+u16 vgic_v3_get_elrsr(struct kvm_vcpu *vcpu);
+u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu);
+
 #define irqchip_in_kernel(k)	(!!((k)->arch.vgic.in_kernel))
 #define vgic_initialized(k)	((k)->arch.vgic.initialized)
 #define vgic_ready(k)		((k)->arch.vgic.ready)
-- 
2.39.2

[PATCH 08/16] KVM: arm64: nv: Sanitise ICH_HCR_EL2 accesses

[Marc Zyngier]

As ICH_HCR_EL2 is a VNCR accessor when runnintg NV, add some
sanitising to what gets written. Crucially, mark TDIR as RES0
if the HW doesn't support it (unlikely, but hey...), as well
as anything GICv4 related, since we only expose a GICv3 to the
uest.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/nested.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 9b36218b48def..37f7ef2f44bd8 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1271,6 +1271,15 @@ int kvm_init_nv_sysregs(struct kvm *kvm)
 		res0 |= MDCR_EL2_EnSTEPOP;
 	set_sysreg_masks(kvm, MDCR_EL2, res0, res1);
 
+	/* ICH_HCR_EL2 */
+	res0 = ICH_HCR_EL2_RES0;
+	res1 = ICH_HCR_EL2_RES1;
+	if (!(kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_EL2_TDS))
+		res0 |= ICH_HCR_EL2_TDIR;
+	/* No GICv4 is presented to the guest */
+	res0 |= ICH_HCR_EL2_DVIM | ICH_HCR_EL2_vSGIEOICount;
+	set_sysreg_masks(kvm, ICH_HCR_EL2, res0, res1);
+
 	return 0;
 }
 
-- 
2.39.2

[PATCH 09/16] KVM: arm64: nv: Nested GICv3 emulation

[Marc Zyngier]

When entering a nested VM, we set up the hypervisor control interface
based on what the guest hypervisor has set. Especially, we investigate
each list register written by the guest hypervisor whether HW bit is
set.  If so, we translate hw irq number from the guest's point of view
to the real hardware irq number if there is a mapping.

Co-developed-by: Jintack Lim <jintack@cs.columbia.edu>
Signed-off-by: Jintack Lim <jintack@cs.columbia.edu>
[Christoffer: Redesigned execution flow around vcpu load/put]
Co-developed-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
[maz: Rewritten to support GICv3 instead of GICv2, NV2 support]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_hyp.h     |   2 +
 arch/arm64/kvm/hyp/vgic-v3-sr.c      |   2 +-
 arch/arm64/kvm/vgic/vgic-v3-nested.c | 218 +++++++++++++++++++++++++++
 arch/arm64/kvm/vgic/vgic-v3.c        |  11 ++
 arch/arm64/kvm/vgic/vgic.c           |   6 +
 arch/arm64/kvm/vgic/vgic.h           |   4 +
 include/kvm/arm_vgic.h               |   2 +
 7 files changed, 244 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index c838309e4ec47..e6be1f5d0967f 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -76,6 +76,8 @@ DECLARE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 
 int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu);
 
+u64 __gic_v3_get_lr(unsigned int lr);
+
 void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if);
 void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if);
 void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if);
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index b47dede973b3c..ed363aa3027e5 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -18,7 +18,7 @@
 #define vtr_to_nr_pre_bits(v)		((((u32)(v) >> 26) & 7) + 1)
 #define vtr_to_nr_apr_regs(v)		(1 << (vtr_to_nr_pre_bits(v) - 5))
 
-static u64 __gic_v3_get_lr(unsigned int lr)
+u64 __gic_v3_get_lr(unsigned int lr)
 {
 	switch (lr & 0xf) {
 	case 0:
diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index 48bfd2f556a36..3d80bfb37de00 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -16,6 +16,8 @@
 #include "vgic.h"
 
 #define ICH_LRN(n)	(ICH_LR0_EL2 + (n))
+#define ICH_AP0RN(n)	(ICH_AP0R0_EL2 + (n))
+#define ICH_AP1RN(n)	(ICH_AP1R0_EL2 + (n))
 
 struct mi_state {
 	u16	eisr;
@@ -23,9 +25,54 @@ struct mi_state {
 	bool	pend;
 };
 
+/*
+ * The shadow registers loaded to the hardware when running a L2 guest
+ * with the virtual IMO/FMO bits set.
+ */
+struct shadow_if {
+	struct vgic_v3_cpu_if	cpuif;
+	unsigned long		lr_map;
+};
+
+static DEFINE_PER_CPU(struct shadow_if, shadow_if);
+
 /*
  * Nesting GICv3 support
  *
+ * On a non-nesting VM (only running at EL0/EL1), the host hypervisor
+ * completely controls the interrupts injected via the list registers.
+ * Consequently, most of the state that is modified by the guest (by ACK-ing
+ * and EOI-ing interrupts) is synced by KVM on each entry/exit, so that we
+ * keep a semi-consistent view of the interrupts.
+ *
+ * This still applies for a NV guest, but only while "InHost" (either
+ * running at EL2, or at EL0 with HCR_EL2.{E2H.TGE}=={1,1}.
+ *
+ * When running a L2 guest ("not InHost"), things are radically different,
+ * as the L1 guest is in charge of provisioning the interrupts via its own
+ * view of the ICH_LR*_EL2 registers, which conveniently live in the VNCR
+ * page.  This means that the flow described above does work (there is no
+ * state to rebuild in the L0 hypervisor), and that most things happed on L2
+ * load/put:
+ *
+ * - on L2 load: move the in-memory L1 vGIC configuration into a shadow,
+ *   per-CPU data structure that is used to populate the actual LRs. This is
+ *   an extra copy that we could avoid, but life is short. In the process,
+ *   we remap any interrupt that has the HW bit set to the mapped interrupt
+ *   on the host, should the host consider it a HW one. This allows the HW
+ *   deactivation to take its course, such as for the timer.
+ *
+ * - on L2 put: perform the inverse transformation, so that the result of L2
+ *   running becomes visible to L1 in the VNCR-accessible registers.
+ *
+ * - there is nothing to do on L2 entry, as everything will have happenned
+ *   on load. However, this is the point where we detect that an interrupt
+ *   targeting L1 and prepare the grand switcheroo.
+ *
+ * - on L2 exit: emulate the HW bit, and deactivate corresponding the L1
+ *   interrupt. The L0 active state will be cleared by the HW if the L1
+ *   interrupt was itself backed by a HW interrupt.
+ *
  * System register emulation:
  *
  * We get two classes of registers:
@@ -42,6 +89,26 @@ struct mi_state {
  * trap) thanks to NV being set by L1.
  */
 
+bool vgic_state_is_nested(struct kvm_vcpu *vcpu)
+{
+	u64 xmo;
+
+	if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
+		xmo = __vcpu_sys_reg(vcpu, HCR_EL2) & (HCR_IMO | HCR_FMO);
+		WARN_ONCE(xmo && xmo != (HCR_IMO | HCR_FMO),
+			  "Separate virtual IRQ/FIQ settings not supported\n");
+
+		return !!xmo;
+	}
+
+	return false;
+}
+
+static struct shadow_if *get_shadow_if(void)
+{
+	return this_cpu_ptr(&shadow_if);
+}
+
 static bool lr_triggers_eoi(u64 lr)
 {
 	return !(lr & (ICH_LR_STATE | ICH_LR_HW)) && (lr & ICH_LR_EOI);
@@ -123,3 +190,154 @@ u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu)
 
 	return reg;
 }
+
+/*
+ * For LRs which have HW bit set such as timer interrupts, we modify them to
+ * have the host hardware interrupt number instead of the virtual one programmed
+ * by the guest hypervisor.
+ */
+static void vgic_v3_create_shadow_lr(struct kvm_vcpu *vcpu,
+				     struct vgic_v3_cpu_if *s_cpu_if)
+{
+	unsigned long lr_map = 0;
+	int index = 0;
+
+	for (int i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
+		u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
+		struct vgic_irq *irq;
+
+		if (!(lr & ICH_LR_STATE))
+			lr = 0;
+
+		if (!(lr & ICH_LR_HW))
+			goto next;
+
+		/* We have the HW bit set, check for validity of pINTID */
+		irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
+		if (!irq || !irq->hw || irq->intid > VGIC_MAX_SPI ) {
+			/* There was no real mapping, so nuke the HW bit */
+			lr &= ~ICH_LR_HW;
+			if (irq)
+				vgic_put_irq(vcpu->kvm, irq);
+			goto next;
+		}
+
+		/* It is illegal to have the EOI bit set with HW */
+		lr &= ~ICH_LR_EOI;
+
+		/* Translate the virtual mapping to the real one */
+		lr &= ~ICH_LR_PHYS_ID_MASK;
+		lr |= FIELD_PREP(ICH_LR_PHYS_ID_MASK, (u64)irq->hwintid);
+
+		vgic_put_irq(vcpu->kvm, irq);
+
+next:
+		s_cpu_if->vgic_lr[index] = lr;
+		if (lr) {
+			lr_map |= BIT(i);
+			index++;
+		}
+	}
+
+	container_of(s_cpu_if, struct shadow_if, cpuif)->lr_map = lr_map;
+	s_cpu_if->used_lrs = index;
+}
+
+void vgic_v3_sync_nested(struct kvm_vcpu *vcpu)
+{
+	struct shadow_if *shadow_if = get_shadow_if();
+	int i, index = 0;
+
+	for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) {
+		u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
+		struct vgic_irq *irq;
+
+		if (!(lr & ICH_LR_HW) || !(lr & ICH_LR_STATE))
+			goto next;
+
+		/*
+		 * If we had a HW lr programmed by the guest hypervisor, we
+		 * need to emulate the HW effect between the guest hypervisor
+		 * and the nested guest.
+		 */
+		irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
+		if (WARN_ON(!irq)) /* Shouldn't happen as we check on load */
+			goto next;
+
+		lr = __gic_v3_get_lr(index);
+		if (!(lr & ICH_LR_STATE))
+			irq->active = false;
+
+		vgic_put_irq(vcpu->kvm, irq);
+	next:
+		index++;
+	}
+}
+
+static void vgic_v3_create_shadow_state(struct kvm_vcpu *vcpu,
+					struct vgic_v3_cpu_if *s_cpu_if)
+{
+	struct vgic_v3_cpu_if *host_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	int i;
+
+	s_cpu_if->vgic_hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
+	s_cpu_if->vgic_vmcr = __vcpu_sys_reg(vcpu, ICH_VMCR_EL2);
+	s_cpu_if->vgic_sre = host_if->vgic_sre;
+
+	for (i = 0; i < 4; i++) {
+		s_cpu_if->vgic_ap0r[i] = __vcpu_sys_reg(vcpu, ICH_AP0RN(i));
+		s_cpu_if->vgic_ap1r[i] = __vcpu_sys_reg(vcpu, ICH_AP1RN(i));
+	}
+
+	vgic_v3_create_shadow_lr(vcpu, s_cpu_if);
+}
+
+void vgic_v3_load_nested(struct kvm_vcpu *vcpu)
+{
+	struct shadow_if *shadow_if = get_shadow_if();
+	struct vgic_v3_cpu_if *cpu_if = &shadow_if->cpuif;
+
+	BUG_ON(!vgic_state_is_nested(vcpu));
+
+	vgic_v3_create_shadow_state(vcpu, cpu_if);
+
+	__vgic_v3_restore_vmcr_aprs(cpu_if);
+	__vgic_v3_activate_traps(cpu_if);
+
+	__vgic_v3_restore_state(cpu_if);
+}
+
+void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
+{
+	struct shadow_if *shadow_if = get_shadow_if();
+	struct vgic_v3_cpu_if *s_cpu_if = &shadow_if->cpuif;
+	int i;
+
+	__vgic_v3_save_vmcr_aprs(s_cpu_if);
+	__vgic_v3_deactivate_traps(s_cpu_if);
+	__vgic_v3_save_state(s_cpu_if);
+
+	/*
+	 * Translate the shadow state HW fields back to the virtual ones
+	 * before copying the shadow struct back to the nested one.
+	 */
+	__vcpu_sys_reg(vcpu, ICH_HCR_EL2) = s_cpu_if->vgic_hcr;
+	__vcpu_sys_reg(vcpu, ICH_VMCR_EL2) = s_cpu_if->vgic_vmcr;
+
+	for (i = 0; i < 4; i++) {
+		__vcpu_sys_reg(vcpu, ICH_AP0RN(i)) = s_cpu_if->vgic_ap0r[i];
+		__vcpu_sys_reg(vcpu, ICH_AP1RN(i)) = s_cpu_if->vgic_ap1r[i];
+	}
+
+	for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) {
+		u64 val = __vcpu_sys_reg(vcpu, ICH_LRN(i));
+
+		val &= ~ICH_LR_STATE;
+		val |= s_cpu_if->vgic_lr[i] & ICH_LR_STATE;
+
+		__vcpu_sys_reg(vcpu, ICH_LRN(i)) = val;
+		s_cpu_if->vgic_lr[i] = 0;
+	}
+
+	shadow_if->lr_map = 0;
+}
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 0bdecbbe74898..67e89bf708e6d 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -733,6 +733,12 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
+	/* If the vgic is nested, perform the full state loading */
+	if (vgic_state_is_nested(vcpu)) {
+		vgic_v3_load_nested(vcpu);
+		return;
+	}
+
 	kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if);
 
 	if (has_vhe())
@@ -745,6 +751,11 @@ void vgic_v3_put(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
+	if (vgic_state_is_nested(vcpu)) {
+		vgic_v3_put_nested(vcpu);
+		return;
+	}
+
 	kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if);
 	WARN_ON(vgic_v4_put(vcpu));
 
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index cc8c6b9b5dd8b..324c547e1b4d8 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -872,6 +872,12 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
 	int used_lrs;
 
+	/* If nesting, emulate the HW effect from L0 to L1 */
+	if (vgic_state_is_nested(vcpu)) {
+		vgic_v3_sync_nested(vcpu);
+		return;
+	}
+
 	/* An empty ap_list_head implies used_lrs == 0 */
 	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
 		return;
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 122d95b4e2845..cf0c084e5d347 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -353,4 +353,8 @@ static inline bool kvm_has_gicv3(struct kvm *kvm)
 	return kvm_has_feat(kvm, ID_AA64PFR0_EL1, GIC, IMP);
 }
 
+void vgic_v3_sync_nested(struct kvm_vcpu *vcpu);
+void vgic_v3_load_nested(struct kvm_vcpu *vcpu);
+void vgic_v3_put_nested(struct kvm_vcpu *vcpu);
+
 #endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 5017fcc71e604..1b373cb870fe4 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -437,6 +437,8 @@ int vgic_v4_load(struct kvm_vcpu *vcpu);
 void vgic_v4_commit(struct kvm_vcpu *vcpu);
 int vgic_v4_put(struct kvm_vcpu *vcpu);
 
+bool vgic_state_is_nested(struct kvm_vcpu *vcpu);
+
 /* CPU HP callbacks */
 void kvm_vgic_cpu_up(void);
 void kvm_vgic_cpu_down(void);
-- 
2.39.2

[PATCH 10/16] KVM: arm64: nv: Handle L2->L1 transition on interrupt injection

[Marc Zyngier]

An interrupt being delivered to L1 while running L2 must result
in the correct exception being delivered to L1.

This means that if, on entry to L2, we found ourselves with pending
interrupts in the L1 distributor, we need to take immediate action.
This is done by posting a request which will prevent the entry in
L2, and deliver an IRQ exception to L1, forcing the switch.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 17 +++++++++--------
 arch/arm64/kvm/arm.c              |  5 +++++
 arch/arm64/kvm/nested.c           |  3 +++
 arch/arm64/kvm/vgic/vgic.c        | 23 +++++++++++++++++++++++
 4 files changed, 40 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 218047cd0296d..cb969c096d7bd 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -44,14 +44,15 @@
 
 #define KVM_REQ_SLEEP \
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
-#define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
-#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
-#define KVM_REQ_RELOAD_GICv4	KVM_ARCH_REQ(4)
-#define KVM_REQ_RELOAD_PMU	KVM_ARCH_REQ(5)
-#define KVM_REQ_SUSPEND		KVM_ARCH_REQ(6)
-#define KVM_REQ_RESYNC_PMU_EL0	KVM_ARCH_REQ(7)
-#define KVM_REQ_NESTED_S2_UNMAP	KVM_ARCH_REQ(8)
+#define KVM_REQ_IRQ_PENDING		KVM_ARCH_REQ(1)
+#define KVM_REQ_VCPU_RESET		KVM_ARCH_REQ(2)
+#define KVM_REQ_RECORD_STEAL		KVM_ARCH_REQ(3)
+#define KVM_REQ_RELOAD_GICv4		KVM_ARCH_REQ(4)
+#define KVM_REQ_RELOAD_PMU		KVM_ARCH_REQ(5)
+#define KVM_REQ_SUSPEND			KVM_ARCH_REQ(6)
+#define KVM_REQ_RESYNC_PMU_EL0		KVM_ARCH_REQ(7)
+#define KVM_REQ_NESTED_S2_UNMAP		KVM_ARCH_REQ(8)
+#define KVM_REQ_GUEST_HYP_IRQ_PENDING	KVM_ARCH_REQ(9)
 
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 3115c44ed4042..5e353b2c225b4 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1153,6 +1153,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * preserved on VMID roll-over if the task was preempted,
 		 * making a thread's VMID inactive. So we need to call
 		 * kvm_arm_vmid_update() in non-premptible context.
+		 *
+		 * Note that this must happen after the check_vcpu_request()
+		 * call to pick the correct s2_mmu structure, as a pending
+		 * nested exception (IRQ, for example) can trigger a change
+		 * in translation regime.
 		 */
 		if (kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid) &&
 		    has_vhe())
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 37f7ef2f44bd8..2b511d30939b3 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1295,4 +1295,7 @@ void check_nested_vcpu_requests(struct kvm_vcpu *vcpu)
 		}
 		write_unlock(&vcpu->kvm->mmu_lock);
 	}
+
+	if (kvm_check_request(KVM_REQ_GUEST_HYP_IRQ_PENDING, vcpu))
+		kvm_inject_nested_irq(vcpu);
 }
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index 324c547e1b4d8..9734a71b85611 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -906,6 +906,29 @@ static inline void vgic_restore_state(struct kvm_vcpu *vcpu)
 /* Flush our emulation state into the GIC hardware before entering the guest. */
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * If in a nested state, we must return early. Two possibilities:
+	 *
+	 * - If we have any pending IRQ for the guest and the guest
+	 *   expects IRQs to be handled in its virtual EL2 mode (the
+	 *   virtual IMO bit is set) and it is not already running in
+	 *   virtual EL2 mode, then we have to emulate an IRQ
+	 *   exception to virtual EL2.
+	 *
+	 *   We do that by placing a request to ourselves which will
+	 *   abort the entry procedure and inject the exception at the
+	 *   beginning of the run loop.
+	 *
+	 * - Otherwise, do exactly *NOTHING*. The guest state is
+	 *   already loaded, and we can carry on with running it.
+	 */
+	if (vgic_state_is_nested(vcpu)) {
+		if (kvm_vgic_vcpu_pending_irq(vcpu))
+			kvm_make_request(KVM_REQ_GUEST_HYP_IRQ_PENDING, vcpu);
+
+		return;
+	}
+
 	/*
 	 * If there are no virtual interrupts active or pending for this
 	 * VCPU, then there is no work to do and we can bail out without
-- 
2.39.2

[PATCH 11/16] KVM: arm64: nv: Add Maintenance Interrupt emulation

[Marc Zyngier]

Emulating the vGIC means emulating the dreaded Maintenance Interrupt.

This is a two-pronged problem:

- while running L2, getting an MI translates into an MI injected
  in the L1 based on the state of the HW.

- while running L1, we must accurately reflect the state of the
  MI line, based on the in-memory state.

The MI INTID is added to the distributor, as expected on any
virtualisation-capable implementation, and further patches
will allow its configuration.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/arm.c                 |  6 ++++
 arch/arm64/kvm/vgic/vgic-init.c      | 22 ++++++++++++++
 arch/arm64/kvm/vgic/vgic-v3-nested.c | 45 ++++++++++++++++++++++++++++
 arch/arm64/kvm/vgic/vgic.c           |  9 ++++++
 arch/arm64/kvm/vgic/vgic.h           |  2 ++
 include/kvm/arm_vgic.h               |  4 +++
 6 files changed, 88 insertions(+)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 5e353b2c225b4..756cc4e74e10f 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -824,6 +824,12 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 	if (ret)
 		return ret;
 
+	if (vcpu_has_nv(vcpu)) {
+		ret = kvm_vgic_vcpu_nv_init(vcpu);
+		if (ret)
+			return ret;
+	}
+
 	/*
 	 * This needs to happen after any restriction has been applied
 	 * to the feature set.
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index bc7e22ab5d812..d2724315a70e9 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -180,6 +180,20 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 	return 0;
 }
 
+int kvm_vgic_vcpu_nv_init(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	guard(mutex)(&vcpu->kvm->arch.config_lock);
+
+	/* Cope with vintage userspace. Maybe we should fail instead */
+	if (vcpu->kvm->arch.vgic.maint_irq == 0)
+		vcpu->kvm->arch.vgic.maint_irq = kvm_vgic_global_state.maint_irq;
+	ret = kvm_vgic_set_owner(vcpu, vcpu->kvm->arch.vgic.maint_irq, vcpu);
+
+	return ret;
+}
+
 static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
@@ -588,12 +602,20 @@ void kvm_vgic_cpu_down(void)
 
 static irqreturn_t vgic_maintenance_handler(int irq, void *data)
 {
+	struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)data;
+
 	/*
 	 * We cannot rely on the vgic maintenance interrupt to be
 	 * delivered synchronously. This means we can only use it to
 	 * exit the VM, and we perform the handling of EOIed
 	 * interrupts on the exit path (see vgic_fold_lr_state).
+	 *
+	 * Of course, NV throws a wrench in this plan, and needs
+	 * something special.
 	 */
+	if (vcpu && vgic_state_is_nested(vcpu))
+		vgic_v3_handle_nested_maint_irq(vcpu);
+
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index 3d80bfb37de00..fba499a20aec8 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -73,6 +73,24 @@ static DEFINE_PER_CPU(struct shadow_if, shadow_if);
  *   interrupt. The L0 active state will be cleared by the HW if the L1
  *   interrupt was itself backed by a HW interrupt.
  *
+ * Maintenance Interrupt (MI) management:
+ *
+ * Since the L2 guest runs the vgic in its full glory, MIs get delivered and
+ * used as a handover point between L2 and L1.
+ *
+ * - on delivery of a MI to L0 while L2 is running: make the L1 MI pending,
+ *   and let it rip. This will initiate a vcpu_put() on L2, and allow L1 to
+ *   run and process the MI.
+ *
+ * - L1 MI is a fully virtual interrupt, not linked to the host's MI. Its
+ *   state must be computed at each entry/exit of the guest, much like we do
+ *   it for the PMU interrupt.
+ *
+ * - because most of the ICH_*_EL2 registers live in the VNCR page, the
+ *   quality of emulation is poor: L1 can setup the vgic so that an MI would
+ *   immediately fire, and not observe anything until the next exit. Trying
+ *   to read ICH_MISR_EL2 would do the trick, for example.
+ *
  * System register emulation:
  *
  * We get two classes of registers:
@@ -341,3 +359,30 @@ void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
 
 	shadow_if->lr_map = 0;
 }
+
+/*
+ * If we exit a L2 VM with a pending maintenance interrupt from the GIC,
+ * then we need to forward this to L1 so that it can re-sync the appropriate
+ * LRs and sample level triggered interrupts again.
+ */
+void vgic_v3_handle_nested_maint_irq(struct kvm_vcpu *vcpu)
+{
+	bool state = read_sysreg_s(SYS_ICH_MISR_EL2);
+
+	/* This will force a switch back to L1 if the level is high */
+	kvm_vgic_inject_irq(vcpu->kvm, vcpu,
+			    vcpu->kvm->arch.vgic.maint_irq, state, vcpu);
+
+	sysreg_clear_set_s(SYS_ICH_HCR_EL2, ICH_HCR_EL2_En, 0);
+}
+
+void vgic_v3_nested_update_mi(struct kvm_vcpu *vcpu)
+{
+	bool level;
+
+	level  = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En;
+	if (level)
+		level &= vgic_v3_get_misr(vcpu);
+	kvm_vgic_inject_irq(vcpu->kvm, vcpu,
+			    vcpu->kvm->arch.vgic.maint_irq, level, vcpu);
+}
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index 9734a71b85611..8f8096d489252 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -878,6 +878,9 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 		return;
 	}
 
+	if (vcpu_has_nv(vcpu))
+		vgic_v3_nested_update_mi(vcpu);
+
 	/* An empty ap_list_head implies used_lrs == 0 */
 	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
 		return;
@@ -921,6 +924,9 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 	 *
 	 * - Otherwise, do exactly *NOTHING*. The guest state is
 	 *   already loaded, and we can carry on with running it.
+	 *
+	 * If we have NV, but are not in a nested state, compute the
+	 * maintenance interrupt state, as it may fire.
 	 */
 	if (vgic_state_is_nested(vcpu)) {
 		if (kvm_vgic_vcpu_pending_irq(vcpu))
@@ -929,6 +935,9 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 		return;
 	}
 
+	if (vcpu_has_nv(vcpu))
+		vgic_v3_nested_update_mi(vcpu);
+
 	/*
 	 * If there are no virtual interrupts active or pending for this
 	 * VCPU, then there is no work to do and we can bail out without
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index cf0c084e5d347..0c5a63712702b 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -356,5 +356,7 @@ static inline bool kvm_has_gicv3(struct kvm *kvm)
 void vgic_v3_sync_nested(struct kvm_vcpu *vcpu);
 void vgic_v3_load_nested(struct kvm_vcpu *vcpu);
 void vgic_v3_put_nested(struct kvm_vcpu *vcpu);
+void vgic_v3_handle_nested_maint_irq(struct kvm_vcpu *vcpu);
+void vgic_v3_nested_update_mi(struct kvm_vcpu *vcpu);
 
 #endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 1b373cb870fe4..b33166f05124c 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -249,6 +249,9 @@ struct vgic_dist {
 
 	int			nr_spis;
 
+	/* The GIC maintenance IRQ for nested hypervisors. */
+	u32			maint_irq;
+
 	/* base addresses in guest physical address space: */
 	gpa_t			vgic_dist_base;		/* distributor */
 	union {
@@ -369,6 +372,7 @@ extern struct static_key_false vgic_v3_cpuif_trap;
 int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev_addr);
 void kvm_vgic_early_init(struct kvm *kvm);
 int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu);
+int kvm_vgic_vcpu_nv_init(struct kvm_vcpu *vcpu);
 int kvm_vgic_create(struct kvm *kvm, u32 type);
 void kvm_vgic_destroy(struct kvm *kvm);
 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
-- 
2.39.2

Re: [PATCH 11/16] KVM: arm64: nv: Add Maintenance Interrupt emulation

[Marc Zyngier]

On Tue, 17 Dec 2024 15:13:26 +0000,
Marc Zyngier <maz@kernel.org> wrote:
> 
> Emulating the vGIC means emulating the dreaded Maintenance Interrupt.
> 
> This is a two-pronged problem:
> 
> - while running L2, getting an MI translates into an MI injected
>   in the L1 based on the state of the HW.
> 
> - while running L1, we must accurately reflect the state of the
>   MI line, based on the in-memory state.
> 
> The MI INTID is added to the distributor, as expected on any
> virtualisation-capable implementation, and further patches
> will allow its configuration.
> 
> Signed-off-by: Marc Zyngier <maz@kernel.org>
> ---
>  arch/arm64/kvm/arm.c                 |  6 ++++
>  arch/arm64/kvm/vgic/vgic-init.c      | 22 ++++++++++++++
>  arch/arm64/kvm/vgic/vgic-v3-nested.c | 45 ++++++++++++++++++++++++++++
>  arch/arm64/kvm/vgic/vgic.c           |  9 ++++++
>  arch/arm64/kvm/vgic/vgic.h           |  2 ++
>  include/kvm/arm_vgic.h               |  4 +++
>  6 files changed, 88 insertions(+)
> 
> diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
> index 5e353b2c225b4..756cc4e74e10f 100644
> --- a/arch/arm64/kvm/arm.c
> +++ b/arch/arm64/kvm/arm.c
> @@ -824,6 +824,12 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
>  	if (ret)
>  		return ret;
>  
> +	if (vcpu_has_nv(vcpu)) {
> +		ret = kvm_vgic_vcpu_nv_init(vcpu);
> +		if (ret)
> +			return ret;
> +	}
> +
>  	/*
>  	 * This needs to happen after any restriction has been applied
>  	 * to the feature set.
> diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
> index bc7e22ab5d812..d2724315a70e9 100644
> --- a/arch/arm64/kvm/vgic/vgic-init.c
> +++ b/arch/arm64/kvm/vgic/vgic-init.c
> @@ -180,6 +180,20 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
>  	return 0;
>  }
>  
> +int kvm_vgic_vcpu_nv_init(struct kvm_vcpu *vcpu)
> +{
> +	int ret;
> +
> +	guard(mutex)(&vcpu->kvm->arch.config_lock);
> +
> +	/* Cope with vintage userspace. Maybe we should fail instead */
> +	if (vcpu->kvm->arch.vgic.maint_irq == 0)
> +		vcpu->kvm->arch.vgic.maint_irq = kvm_vgic_global_state.maint_irq;

Well, that didn't take too long, and Joey did hit a bug here. Although
the two fields have the same name, they represent something totally
different:

- kvm_vgic_global_state.maint_irq is the interrupt number Linux uses
  for the host. It's just a number, without any signification other
  than for the kernel's own stuff.

- vcpu->kvm->arch.vgic.maint_irq is an GIC INTID. Really not the same
  thing as the above.

What this should read is something like:

diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index d2724315a70e9..8d92b05639588 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -188,7 +188,7 @@ int kvm_vgic_vcpu_nv_init(struct kvm_vcpu *vcpu)
 
 	/* Cope with vintage userspace. Maybe we should fail instead */
 	if (vcpu->kvm->arch.vgic.maint_irq == 0)
-		vcpu->kvm->arch.vgic.maint_irq = kvm_vgic_global_state.maint_irq;
+		vcpu->kvm->arch.vgic.maint_irq = irq_get_irq_data(kvm_vgic_global_state.maint_irq)->hwirq;
 	ret = kvm_vgic_set_owner(vcpu, vcpu->kvm->arch.vgic.maint_irq, vcpu);
 
 	return ret;

So I guess there are two things that need to happen:

- rename vcpu->kvm->arch.vgic.maint_irq to something like "mi_intid"

- make the damn thing fail, as the comment suggests. We don't have any
  legacy worth speaking of anyway.

Another thing is that Joey (who really didn't waste any time finding
issues) pointed out that we happily allow NV without GICv3. Clearly,
this should also be prevented.

Thanks Joey!

	M.

-- 
Without deviation from the norm, progress is not possible.

[PATCH 12/16] KVM: arm64: nv: Respect virtual HCR_EL2.TWx setting

[Marc Zyngier]

From: Jintack Lim <jintack.lim@linaro.org>

Forward exceptions due to WFI or WFE instructions to the virtual EL2 if
they are not coming from the virtual EL2 and virtual HCR_EL2.TWx is set.

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h | 13 +++++++++++++
 arch/arm64/kvm/handle_exit.c         |  6 +++++-
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index cf811009a33c9..5d2af20f75890 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -281,6 +281,19 @@ static __always_inline u64 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu)
 	return vcpu->arch.fault.esr_el2;
 }
 
+static inline bool guest_hyp_wfx_traps_enabled(const struct kvm_vcpu *vcpu)
+{
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+	bool is_wfe = !!(esr & ESR_ELx_WFx_ISS_WFE);
+	u64 hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2);
+
+	if (!vcpu_has_nv(vcpu) || vcpu_is_el2(vcpu))
+		return false;
+
+	return ((is_wfe && (hcr_el2 & HCR_TWE)) ||
+		(!is_wfe && (hcr_el2 & HCR_TWI)));
+}
+
 static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu)
 {
 	u64 esr = kvm_vcpu_get_esr(vcpu);
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index d7c2990e7c9ed..206eb6698db70 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -129,8 +129,12 @@ static int kvm_handle_fpasimd(struct kvm_vcpu *vcpu)
 static int kvm_handle_wfx(struct kvm_vcpu *vcpu)
 {
 	u64 esr = kvm_vcpu_get_esr(vcpu);
+	bool is_wfe = !!(esr & ESR_ELx_WFx_ISS_WFE);
 
-	if (esr & ESR_ELx_WFx_ISS_WFE) {
+	if (guest_hyp_wfx_traps_enabled(vcpu))
+		return kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
+	if (is_wfe) {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
 		vcpu->stat.wfe_exit_stat++;
 	} else {
-- 
2.39.2

[PATCH 13/16] KVM: arm64: nv: Request vPE doorbell upon nested ERET to L2

[Marc Zyngier]

From: Oliver Upton <oliver.upton@linux.dev>

Running an L2 guest with GICv4 enabled goes absolutely nowhere, and gets
into a vicious cycle of nested ERET followed by nested exception entry
into the L1.

When KVM does a put on a runnable vCPU, it marks the vPE as nonresident
but does not request a doorbell IRQ. Behind the scenes in the ITS
driver's view of the vCPU, its_vpe::pending_last gets set to true to
indicate that context is still runnable.

This comes to a head when doing the nested ERET into L2. The vPE doesn't
get scheduled on the redistributor as it is exclusively part of the L1's
VGIC context. kvm_vgic_vcpu_pending_irq() returns true because the vPE
appears runnable, and KVM does a nested exception entry into the L1
before L2 ever gets off the ground.

This issue can be papered over by requesting a doorbell IRQ when
descheduling a vPE as part of a nested ERET. KVM needs this anyway to
kick the vCPU out of the L2 when an IRQ becomes pending for the L1.

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20240823212703.3576061-4-oliver.upton@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h |  2 ++
 arch/arm64/kvm/emulate-nested.c   |  2 ++
 arch/arm64/kvm/vgic/vgic-v4.c     | 18 +++++++++++++++++-
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index cb969c096d7bd..18d9166761972 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -958,6 +958,8 @@ struct kvm_vcpu_arch {
 #define PMUSERENR_ON_CPU	__vcpu_single_flag(sflags, BIT(4))
 /* WFI instruction trapped */
 #define IN_WFI			__vcpu_single_flag(sflags, BIT(5))
+/* KVM is currently emulating a nested ERET */
+#define IN_NESTED_ERET		__vcpu_single_flag(sflags, BIT(6))
 
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index c460b8403aec5..69233dcc81a46 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -2434,6 +2434,7 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	}
 
 	preempt_disable();
+	vcpu_set_flag(vcpu, IN_NESTED_ERET);
 	kvm_arch_vcpu_put(vcpu);
 
 	if (!esr_iss_is_eretax(esr))
@@ -2445,6 +2446,7 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	*vcpu_cpsr(vcpu) = spsr;
 
 	kvm_arch_vcpu_load(vcpu, smp_processor_id());
+	vcpu_clear_flag(vcpu, IN_NESTED_ERET);
 	preempt_enable();
 
 	kvm_pmu_nested_transition(vcpu);
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index eedecbbbcf31b..0d9fb235c0180 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -336,6 +336,22 @@ void vgic_v4_teardown(struct kvm *kvm)
 	its_vm->vpes = NULL;
 }
 
+static inline bool vgic_v4_want_doorbell(struct kvm_vcpu *vcpu)
+{
+	if (vcpu_get_flag(vcpu, IN_WFI))
+		return true;
+
+	if (likely(!vcpu_has_nv(vcpu)))
+		return false;
+
+	/*
+	 * GICv4 hardware is only ever used for the L1. Mark the vPE (i.e. the
+	 * L1 context) nonresident and request a doorbell to kick us out of the
+	 * L2 when an IRQ becomes pending.
+	 */
+	return vcpu_get_flag(vcpu, IN_NESTED_ERET);
+}
+
 int vgic_v4_put(struct kvm_vcpu *vcpu)
 {
 	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
@@ -343,7 +359,7 @@ int vgic_v4_put(struct kvm_vcpu *vcpu)
 	if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident)
 		return 0;
 
-	return its_make_vpe_non_resident(vpe, !!vcpu_get_flag(vcpu, IN_WFI));
+	return its_make_vpe_non_resident(vpe, vgic_v4_want_doorbell(vcpu));
 }
 
 int vgic_v4_load(struct kvm_vcpu *vcpu)
-- 
2.39.2

[PATCH 14/16] KVM: arm64: nv: Propagate used_lrs between L1 and L0 contexts

[Marc Zyngier]

We have so far made sure that L1 and L0 vgic contexts were
totally independent. There is however one spot of bother with
this approach, and that's in the GICv3 emulation code required by
our fruity friends.

The issue is that the emulation code needs to know how many LRs
are in flight. And while it is easy to reach the L0 version through
the vcpu pointer, doing so for the L1 is much more complicated,
as these structures are private to the nested code.

We could simply expose that structure and pick one or the other
depending on the context, but this seems extra complexity for not
much benefit.

Instead, just propagate the number of used LRs from the nested code
into the L0 context, and be done with it. Should this become a burden,
it can be easily rectified.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/vgic/vgic-v3-nested.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index fba499a20aec8..b81bfa85ebb19 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -323,6 +323,12 @@ void vgic_v3_load_nested(struct kvm_vcpu *vcpu)
 	__vgic_v3_activate_traps(cpu_if);
 
 	__vgic_v3_restore_state(cpu_if);
+
+	/*
+	 * Propagate the number of used LRs for the benefit of the HYP
+	 * GICv3 emulation code. Yes, this is a pretty sorry hack.
+	 */
+	vcpu->arch.vgic_cpu.vgic_v3.used_lrs = cpu_if->used_lrs;
 }
 
 void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
@@ -358,6 +364,7 @@ void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
 	}
 
 	shadow_if->lr_map = 0;
+	vcpu->arch.vgic_cpu.vgic_v3.used_lrs = 0;
 }
 
 /*
-- 
2.39.2

[PATCH 15/16] KVM: arm64: nv: Fold GICv3 host trapping requirements into guest setup

[Marc Zyngier]

Popular HW that is able to use NV also has a broken vgic implementation
that requires trapping.

On such HW, propagate the host trap bits into the guest's shadow
ICH_HCR_EL2 register, making sure we don't allow an L2 guest to bring
the system down.

This involves a bit of tweaking so that the emulation code correctly
poicks up the shadow state as needed, and to only partially sync
ICH_HCR_EL2 back with the guest state to capture EOIcount.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/vgic/vgic-v3-nested.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index b81bfa85ebb19..778ffb62de21c 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -296,9 +296,19 @@ static void vgic_v3_create_shadow_state(struct kvm_vcpu *vcpu,
 					struct vgic_v3_cpu_if *s_cpu_if)
 {
 	struct vgic_v3_cpu_if *host_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u64 val = 0;
 	int i;
 
-	s_cpu_if->vgic_hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
+	/*
+	 * If we're on a system with a broken vgic that requires
+	 * trapping, propagate the trapping requirements.
+	 *
+	 * Ah, the smell of rotten fruits...
+	 */
+	if (static_branch_unlikely(&vgic_v3_cpuif_trap))
+		val = host_if->vgic_hcr & (ICH_HCR_EL2_TALL0 | ICH_HCR_EL2_TALL1 |
+					   ICH_HCR_EL2_TC | ICH_HCR_EL2_TDIR);
+	s_cpu_if->vgic_hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) | val;
 	s_cpu_if->vgic_vmcr = __vcpu_sys_reg(vcpu, ICH_VMCR_EL2);
 	s_cpu_if->vgic_sre = host_if->vgic_sre;
 
@@ -335,6 +345,7 @@ void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
 {
 	struct shadow_if *shadow_if = get_shadow_if();
 	struct vgic_v3_cpu_if *s_cpu_if = &shadow_if->cpuif;
+	u64 val;
 	int i;
 
 	__vgic_v3_save_vmcr_aprs(s_cpu_if);
@@ -345,7 +356,10 @@ void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
 	 * Translate the shadow state HW fields back to the virtual ones
 	 * before copying the shadow struct back to the nested one.
 	 */
-	__vcpu_sys_reg(vcpu, ICH_HCR_EL2) = s_cpu_if->vgic_hcr;
+	val = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
+	val &= ~ICH_HCR_EL2_EOIcount_MASK;
+	val |= (s_cpu_if->vgic_hcr & ICH_HCR_EL2_EOIcount_MASK);
+	__vcpu_sys_reg(vcpu, ICH_HCR_EL2) = val;
 	__vcpu_sys_reg(vcpu, ICH_VMCR_EL2) = s_cpu_if->vgic_vmcr;
 
 	for (i = 0; i < 4; i++) {
@@ -354,7 +368,7 @@ void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
 	}
 
 	for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) {
-		u64 val = __vcpu_sys_reg(vcpu, ICH_LRN(i));
+		val = __vcpu_sys_reg(vcpu, ICH_LRN(i));
 
 		val &= ~ICH_LR_STATE;
 		val |= s_cpu_if->vgic_lr[i] & ICH_LR_STATE;
-- 
2.39.2

[PATCH 16/16] KVM: arm64: nv: Allow userland to set VGIC maintenance IRQ

[Marc Zyngier]

From: Andre Przywara <andre.przywara@arm.com>

The VGIC maintenance IRQ signals various conditions about the LRs, when
the GIC's virtualization extension is used.
So far we didn't need it, but nested virtualization needs to know about
this interrupt, so add a userland interface to setup the IRQ number.
The architecture mandates that it must be a PPI, on top of that this code
only exports a per-device option, so the PPI is the same on all VCPUs.

Signed-off-by: Andre Przywara <andre.przywara@arm.com>
[added some bits of documentation]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 .../virt/kvm/devices/arm-vgic-v3.rst          | 12 +++++++-
 arch/arm64/include/uapi/asm/kvm.h             |  1 +
 arch/arm64/kvm/vgic/vgic-kvm-device.c         | 29 +++++++++++++++++--
 tools/arch/arm/include/uapi/asm/kvm.h         |  1 +
 4 files changed, 40 insertions(+), 3 deletions(-)

diff --git a/Documentation/virt/kvm/devices/arm-vgic-v3.rst b/Documentation/virt/kvm/devices/arm-vgic-v3.rst
index 5817edb4e0467..e860498b1e359 100644
--- a/Documentation/virt/kvm/devices/arm-vgic-v3.rst
+++ b/Documentation/virt/kvm/devices/arm-vgic-v3.rst
@@ -291,8 +291,18 @@ Groups:
       |    Aff3    |    Aff2    |    Aff1    |    Aff0    |
 
   Errors:
-
     =======  =============================================
     -EINVAL  vINTID is not multiple of 32 or info field is
 	     not VGIC_LEVEL_INFO_LINE_LEVEL
     =======  =============================================
+
+  KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ
+   Attributes:
+
+    The attr field of kvm_device_attr encodes the following values:
+
+      bits:     | 31   ....    5 | 4  ....  0 |
+      values:   |      RES0      |   vINTID   |
+
+    The vINTID specifies which interrupt is generated when the vGIC
+    must generate a maintenance interrupt. This must be a PPI.
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 66736ff04011e..05d53d3de5b3b 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -406,6 +406,7 @@ enum {
 #define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
 #define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO  7
 #define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
+#define KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ  9
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT	10
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
 			(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c
index 5f4f57aaa23ec..ff986424e7e5f 100644
--- a/arch/arm64/kvm/vgic/vgic-kvm-device.c
+++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c
@@ -303,6 +303,12 @@ static int vgic_get_common_attr(struct kvm_device *dev,
 			     VGIC_NR_PRIVATE_IRQS, uaddr);
 		break;
 	}
+	case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ: {
+		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+
+		r = put_user(dev->kvm->arch.vgic.maint_irq, uaddr);
+		break;
+	}
 	}
 
 	return r;
@@ -517,7 +523,7 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
 	struct vgic_reg_attr reg_attr;
 	gpa_t addr;
 	struct kvm_vcpu *vcpu;
-	bool uaccess;
+	bool uaccess, post_init = true;
 	u32 val;
 	int ret;
 
@@ -533,6 +539,9 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
 		/* Sysregs uaccess is performed by the sysreg handling code */
 		uaccess = false;
 		break;
+	case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ:
+		post_init = false;
+		fallthrough;
 	default:
 		uaccess = true;
 	}
@@ -552,7 +561,7 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
 
 	mutex_lock(&dev->kvm->arch.config_lock);
 
-	if (unlikely(!vgic_initialized(dev->kvm))) {
+	if (post_init != vgic_initialized(dev->kvm)) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -582,6 +591,19 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
 		}
 		break;
 	}
+	case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ:
+		if (!is_write) {
+			val = dev->kvm->arch.vgic.maint_irq;
+			ret = 0;
+			break;
+		}
+
+		ret = -EINVAL;
+		if ((val < VGIC_NR_PRIVATE_IRQS) && (val >= VGIC_NR_SGIS)) {
+			dev->kvm->arch.vgic.maint_irq = val;
+			ret = 0;
+		}
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -608,6 +630,7 @@ static int vgic_v3_set_attr(struct kvm_device *dev,
 	case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS:
 	case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS:
 	case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO:
+	case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ:
 		return vgic_v3_attr_regs_access(dev, attr, true);
 	default:
 		return vgic_set_common_attr(dev, attr);
@@ -622,6 +645,7 @@ static int vgic_v3_get_attr(struct kvm_device *dev,
 	case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS:
 	case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS:
 	case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO:
+	case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ:
 		return vgic_v3_attr_regs_access(dev, attr, false);
 	default:
 		return vgic_get_common_attr(dev, attr);
@@ -645,6 +669,7 @@ static int vgic_v3_has_attr(struct kvm_device *dev,
 	case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS:
 		return vgic_v3_has_attr_regs(dev, attr);
 	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS:
+	case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ:
 		return 0;
 	case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: {
 		if (((attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >>
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 03cd7c19a683b..d5dd969028175 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -246,6 +246,7 @@ struct kvm_vcpu_events {
 #define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
 #define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO  7
 #define KVM_DEV_ARM_VGIC_GRP_ITS_REGS	8
+#define KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ	9
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT	10
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
 			(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
-- 
2.39.2