[PATCH v3 00/66] KVM: arm64: ARMv8.3/8.4 Nested Virtualization support

[PATCH v3 00/66] KVM: arm64: ARMv8.3/8.4 Nested Virtualization support

[Marc Zyngier]

This is a rework of the NV series that I posted 10 months ago[1], as a
lot of the KVM code has changed since, and the series apply anymore
(not that anybody really cares as the the HW is, as usual, made of
unobtainium...).

From the previous version:

- Integration with the new page-table code
- New exception injection code
- No more messing with the nVHE code
- No AArch32!!!!
- Rebased on v5.10-rc4 + kvmarm/next for 5.11

From a functionality perspective, you can expect a L2 guest to work,
but don't even think of L3, as we only partially emulate the
ARMv8.{3,4}-NV extensions themselves. Same thing for vgic, debug, PMU,
as well as anything that would require a Stage-1 PTW. What we want to
achieve is that with NV disabled, there is no performance overhead and
no regression.

The series is roughly divided in 5 parts: exception handling, memory
virtualization, interrupts and timers for ARMv8.3, followed by the
ARMv8.4 support. There are of course some dependencies, but you'll
hopefully get the gist of it.

For the most courageous of you, I've put out a branch[2]. Of course,
you'll need some userspace. Andre maintains a hacked version of
kvmtool[3] that takes a --nested option, allowing the guest to be
started at EL2. You can run the whole stack in the Foundation
model. Don't be in a hurry ;-).

And to be clear: although Jintack and Christoffer have written tons of
the stuff originaly, I'm the one responsible for breaking it!

[1] https://lore.kernel.org/r/20200211174938.27809-1-maz@kernel.org
[2] git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms.git kvm-arm64/nv-5.11.-WIP
[3] git://linux-arm.org/kvmtool.git nv/nv-wip-5.2-rc5

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

Christoffer Dall (15):
  KVM: arm64: nv: Introduce nested virtualization VCPU feature
  KVM: arm64: nv: Reset VCPU to EL2 registers if VCPU nested virt is set
  KVM: arm64: nv: Allow userspace to set PSR_MODE_EL2x
  KVM: arm64: nv: Add nested virt VCPU primitives for vEL2 VCPU state
  KVM: arm64: nv: Reset VMPIDR_EL2 and VPIDR_EL2 to sane values
  KVM: arm64: nv: Handle trapped ERET from virtual EL2
  KVM: arm64: nv: Emulate PSTATE.M for a guest hypervisor
  KVM: arm64: nv: Trap EL1 VM register accesses in virtual EL2
  KVM: arm64: nv: Only toggle cache for virtual EL2 when SCTLR_EL2
    changes
  KVM: arm64: nv: Implement nested Stage-2 page table walk logic
  KVM: arm64: nv: Unmap/flush shadow stage 2 page tables
  KVM: arm64: nv: arch_timer: Support hyp timer emulation
  KVM: arm64: nv: vgic: Emulate the HW bit in software
  KVM: arm64: nv: Add nested GICv3 tracepoints
  KVM: arm64: nv: Sync nested timer state with ARMv8.4

Jintack Lim (19):
  arm64: Add ARM64_HAS_NESTED_VIRT cpufeature
  KVM: arm64: nv: Handle HCR_EL2.NV system register traps
  KVM: arm64: nv: Support virtual EL2 exceptions
  KVM: arm64: nv: Inject HVC exceptions to the virtual EL2
  KVM: arm64: nv: Trap SPSR_EL1, ELR_EL1 and VBAR_EL1 from virtual EL2
  KVM: arm64: nv: Trap CPACR_EL1 access in virtual EL2
  KVM: arm64: nv: Handle PSCI call via smc from the guest
  KVM: arm64: nv: Respect virtual HCR_EL2.TWX setting
  KVM: arm64: nv: Respect virtual CPTR_EL2.{TFP,FPEN} settings
  KVM: arm64: nv: Respect the virtual HCR_EL2.NV bit setting
  KVM: arm64: nv: Respect virtual HCR_EL2.TVM and TRVM settings
  KVM: arm64: nv: Respect the virtual HCR_EL2.NV1 bit setting
  KVM: arm64: nv: Emulate EL12 register accesses from the virtual EL2
  KVM: arm64: nv: Configure HCR_EL2 for nested virtualization
  KVM: arm64: nv: Introduce sys_reg_desc.forward_trap
  KVM: arm64: nv: Set a handler for the system instruction traps
  KVM: arm64: nv: Trap and emulate AT instructions from virtual EL2
  KVM: arm64: nv: Trap and emulate TLBI instructions from virtual EL2
  KVM: arm64: nv: Nested GICv3 Support

Marc Zyngier (31):
  KVM: arm64: nv: Add EL2 system registers to vcpu context
  KVM: arm64: nv: Add non-VHE-EL2->EL1 translation helpers
  KVM: arm64: nv: Handle virtual EL2 registers in
    vcpu_read/write_sys_reg()
  KVM: arm64: nv: Handle SPSR_EL2 specially
  KVM: arm64: nv: Handle HCR_EL2.E2H specially
  KVM: arm64: nv: Save/Restore vEL2 sysregs
  KVM: arm64: nv: Forward debug traps to the nested guest
  KVM: arm64: nv: Filter out unsupported features from ID regs
  KVM: arm64: nv: Hide RAS from nested guests
  KVM: arm64: nv: Support multiple nested Stage-2 mmu structures
  KVM: arm64: nv: Handle shadow stage 2 page faults
  KVM: arm64: nv: Restrict S2 RD/WR permissions to match the guest's
  KVM: arm64: nv: Fold guest's HCR_EL2 configuration into the host's
  KVM: arm64: nv: Add handling of EL2-specific timer registers
  KVM: arm64: nv: Load timer before the GIC
  KVM: arm64: nv: Don't load the GICv4 context on entering a nested
    guest
  KVM: arm64: nv: Implement maintenance interrupt forwarding
  KVM: arm64: nv: Allow userspace to request KVM_ARM_VCPU_NESTED_VIRT
  KVM: arm64: nv: Add handling of ARMv8.4-TTL TLB invalidation
  KVM: arm64: nv: Invalidate TLBs based on shadow S2 TTL-like
    information
  KVM: arm64: Allow populating S2 SW bits
  KVM: arm64: nv: Tag shadow S2 entries with nested level
  KVM: arm64: nv: Add include containing the VNCR_EL2 offsets
  KVM: arm64: Map VNCR-capable registers to a separate page
  KVM: arm64: nv: Move nested vgic state into the sysreg file
  KVM: arm64: Add ARMv8.4 Enhanced Nested Virt cpufeature
  KVM: arm64: nv: Synchronize PSTATE early on exit
  KVM: arm64: nv: Allocate VNCR page when required
  KVM: arm64: nv: Enable ARMv8.4-NV support
  KVM: arm64: nv: Fast-track 'InHost' exception returns
  KVM: arm64: nv: Fast-track EL1 TLBIs for VHE guests

 .../admin-guide/kernel-parameters.txt         |    4 +
 .../virt/kvm/devices/arm-vgic-v3.rst          |   12 +-
 arch/arm64/include/asm/cpucaps.h              |    2 +
 arch/arm64/include/asm/esr.h                  |    6 +
 arch/arm64/include/asm/kvm_arm.h              |   28 +-
 arch/arm64/include/asm/kvm_asm.h              |    4 +
 arch/arm64/include/asm/kvm_emulate.h          |  145 +-
 arch/arm64/include/asm/kvm_host.h             |  175 ++-
 arch/arm64/include/asm/kvm_hyp.h              |    2 +
 arch/arm64/include/asm/kvm_mmu.h              |   17 +-
 arch/arm64/include/asm/kvm_nested.h           |  152 ++
 arch/arm64/include/asm/kvm_pgtable.h          |   10 +
 arch/arm64/include/asm/sysreg.h               |  104 +-
 arch/arm64/include/asm/vncr_mapping.h         |   73 +
 arch/arm64/include/uapi/asm/kvm.h             |    2 +
 arch/arm64/kernel/cpufeature.c                |   35 +
 arch/arm64/kvm/Makefile                       |    4 +-
 arch/arm64/kvm/arch_timer.c                   |  189 ++-
 arch/arm64/kvm/arm.c                          |   34 +-
 arch/arm64/kvm/at.c                           |  231 ++++
 arch/arm64/kvm/emulate-nested.c               |  186 +++
 arch/arm64/kvm/guest.c                        |    6 +
 arch/arm64/kvm/handle_exit.c                  |   81 +-
 arch/arm64/kvm/hyp/exception.c                |   44 +-
 arch/arm64/kvm/hyp/include/hyp/switch.h       |   31 +-
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h    |   28 +-
 arch/arm64/kvm/hyp/nvhe/switch.c              |   10 +-
 arch/arm64/kvm/hyp/nvhe/sysreg-sr.c           |    2 +-
 arch/arm64/kvm/hyp/pgtable.c                  |    6 +
 arch/arm64/kvm/hyp/vgic-v3-sr.c               |    2 +-
 arch/arm64/kvm/hyp/vhe/switch.c               |  207 ++-
 arch/arm64/kvm/hyp/vhe/sysreg-sr.c            |  125 +-
 arch/arm64/kvm/hyp/vhe/tlb.c                  |   83 ++
 arch/arm64/kvm/inject_fault.c                 |   62 +-
 arch/arm64/kvm/mmu.c                          |  183 ++-
 arch/arm64/kvm/nested.c                       |  908 ++++++++++++
 arch/arm64/kvm/reset.c                        |   14 +-
 arch/arm64/kvm/sys_regs.c                     | 1226 ++++++++++++++++-
 arch/arm64/kvm/sys_regs.h                     |    6 +
 arch/arm64/kvm/trace_arm.h                    |   65 +-
 arch/arm64/kvm/vgic/vgic-init.c               |   30 +
 arch/arm64/kvm/vgic/vgic-kvm-device.c         |   22 +
 arch/arm64/kvm/vgic/vgic-nested-trace.h       |  137 ++
 arch/arm64/kvm/vgic/vgic-v3-nested.c          |  240 ++++
 arch/arm64/kvm/vgic/vgic-v3.c                 |   39 +-
 arch/arm64/kvm/vgic/vgic.c                    |   44 +
 arch/arm64/kvm/vgic/vgic.h                    |   10 +
 include/kvm/arm_arch_timer.h                  |    7 +
 include/kvm/arm_vgic.h                        |   16 +
 tools/arch/arm/include/uapi/asm/kvm.h         |    1 +
 50 files changed, 4890 insertions(+), 160 deletions(-)
 create mode 100644 arch/arm64/include/asm/kvm_nested.h
 create mode 100644 arch/arm64/include/asm/vncr_mapping.h
 create mode 100644 arch/arm64/kvm/at.c
 create mode 100644 arch/arm64/kvm/emulate-nested.c
 create mode 100644 arch/arm64/kvm/nested.c
 create mode 100644 arch/arm64/kvm/vgic/vgic-nested-trace.h
 create mode 100644 arch/arm64/kvm/vgic/vgic-v3-nested.c

-- 
2.29.2

[PATCH v3 01/66] arm64: Add ARM64_HAS_NESTED_VIRT cpufeature

[Marc Zyngier]

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

Add a new ARM64_HAS_NESTED_VIRT feature to indicate that the
CPU has the ARMv8.3 nested virtualization capability.

This will be used to support nested virtualization in KVM.

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 .../admin-guide/kernel-parameters.txt         |  4 +++
 arch/arm64/include/asm/cpucaps.h              |  1 +
 arch/arm64/kernel/cpufeature.c                | 25 +++++++++++++++++++
 3 files changed, 30 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index ee9f13776388..727e49640124 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2285,6 +2285,10 @@
 			[KVM,ARM] Allow use of GICv4 for direct injection of
 			LPIs.
 
+	kvm-arm.nested=
+			[KVM,ARM] Allow nested virtualization in KVM/ARM.
+			Default is 0 (disabled)
+
 	kvm_cma_resv_ratio=n [PPC]
 			Reserves given percentage from system memory area for
 			contiguous memory allocation for KVM hash pagetable
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index b77d997b173b..6c5b84692a01 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -16,6 +16,7 @@
 #define ARM64_WORKAROUND_CAVIUM_23154		6
 #define ARM64_WORKAROUND_834220			7
 #define ARM64_HAS_NO_HW_PREFETCH		8
+#define ARM64_HAS_NESTED_VIRT			9
 #define ARM64_HAS_VIRT_HOST_EXTN		11
 #define ARM64_WORKAROUND_CAVIUM_27456		12
 #define ARM64_HAS_32BIT_EL0			13
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d96f4554282d..eaeea8a88292 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1577,6 +1577,21 @@ static void cpu_copy_el2regs(const struct arm64_cpu_capabilities *__unused)
 	if (!alternative_is_applied(ARM64_HAS_VIRT_HOST_EXTN))
 		write_sysreg(read_sysreg(tpidr_el1), tpidr_el2);
 }
+
+static bool nested_param;
+static bool has_nested_virt_support(const struct arm64_cpu_capabilities *cap,
+				    int scope)
+{
+	return has_cpuid_feature(cap, scope) &&
+		nested_param;
+}
+
+static int __init kvmarm_nested_cfg(char *buf)
+{
+	return strtobool(buf, &nested_param);
+}
+
+early_param("kvm-arm.nested", kvmarm_nested_cfg);
 #endif
 
 static void cpu_has_fwb(const struct arm64_cpu_capabilities *__unused)
@@ -1790,6 +1805,16 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = runs_at_el2,
 		.cpu_enable = cpu_copy_el2regs,
 	},
+	{
+		.desc = "Nested Virtualization Support",
+		.capability = ARM64_HAS_NESTED_VIRT,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_nested_virt_support,
+		.sys_reg = SYS_ID_AA64MMFR2_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64MMFR2_NV_SHIFT,
+		.min_field_value = 1,
+	},
 #endif	/* CONFIG_ARM64_VHE */
 	{
 		.desc = "32-bit EL0 Support",
-- 
2.29.2

[PATCH v3 02/66] KVM: arm64: nv: Introduce nested virtualization VCPU feature

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@arm.com>

Introduce the feature bit and a primitive that checks if the feature is
set behind a static key check based on the cpus_have_const_cap check.

Checking nested_virt_in_use() on systems without nested virt enabled
should have neglgible overhead.

We don't yet allow userspace to actually set this feature.

Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h | 14 ++++++++++++++
 arch/arm64/include/uapi/asm/kvm.h   |  1 +
 2 files changed, 15 insertions(+)
 create mode 100644 arch/arm64/include/asm/kvm_nested.h

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
new file mode 100644
index 000000000000..1028ac65a897
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ARM64_KVM_NESTED_H
+#define __ARM64_KVM_NESTED_H
+
+#include <linux/kvm_host.h>
+
+static inline bool nested_virt_in_use(const struct kvm_vcpu *vcpu)
+{
+	return (!__is_defined(__KVM_NVHE_HYPERVISOR__) &&
+		cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) &&
+		test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features));
+}
+
+#endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 24223adae150..fe3cb67f0d26 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -106,6 +106,7 @@ struct kvm_regs {
 #define KVM_ARM_VCPU_SVE		4 /* enable SVE for this CPU */
 #define KVM_ARM_VCPU_PTRAUTH_ADDRESS	5 /* VCPU uses address authentication */
 #define KVM_ARM_VCPU_PTRAUTH_GENERIC	6 /* VCPU uses generic authentication */
+#define KVM_ARM_VCPU_HAS_EL2		7 /* Support nested virtualization */
 
 struct kvm_vcpu_init {
 	__u32 target;
-- 
2.29.2

[PATCH v3 03/66] KVM: arm64: nv: Reset VCPU to EL2 registers if VCPU nested virt is set

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@arm.com>

Reset the VCPU with PSTATE.M = EL2h when the nested virtualization
feature is enabled on the VCPU.

Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
[maz: rework register reset not to use empty data structures]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/reset.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 47f3f035f3ea..2d2c780e6c69 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -27,6 +27,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_nested.h>
 #include <asm/virt.h>
 
 /* Maximum phys_shift supported for any VM on this host */
@@ -38,6 +39,9 @@ static u32 kvm_ipa_limit;
 #define VCPU_RESET_PSTATE_EL1	(PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \
 				 PSR_F_BIT | PSR_D_BIT)
 
+#define VCPU_RESET_PSTATE_EL2	(PSR_MODE_EL2h | PSR_A_BIT | PSR_I_BIT | \
+				 PSR_F_BIT | PSR_D_BIT)
+
 #define VCPU_RESET_PSTATE_SVC	(PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
 				 PSR_AA32_I_BIT | PSR_AA32_F_BIT)
 
@@ -224,11 +228,18 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	switch (vcpu->arch.target) {
 	default:
 		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
-			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) {
+			/*
+			 * The CPU must support 32bit EL1, and 32bit
+			 * NV is just not a thing...
+			 */
+			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) ||
+			    nested_virt_in_use(vcpu)) {
 				ret = -EINVAL;
 				goto out;
 			}
 			pstate = VCPU_RESET_PSTATE_SVC;
+		} else if (nested_virt_in_use(vcpu)) {
+			pstate = VCPU_RESET_PSTATE_EL2;
 		} else {
 			pstate = VCPU_RESET_PSTATE_EL1;
 		}
-- 
2.29.2

[PATCH v3 04/66] KVM: arm64: nv: Allow userspace to set PSR_MODE_EL2x

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@linaro.org>

We were not allowing userspace to set a more privileged mode for the VCPU
than EL1, but we should allow this when nested virtualization is enabled
for the VCPU.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/guest.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 9bbd30e62799..171936da30b1 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -24,6 +24,7 @@
 #include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_nested.h>
 #include <asm/sigcontext.h>
 
 #include "trace.h"
@@ -242,6 +243,11 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 			if (vcpu_el1_is_32bit(vcpu))
 				return -EINVAL;
 			break;
+		case PSR_MODE_EL2h:
+		case PSR_MODE_EL2t:
+			if (vcpu_el1_is_32bit(vcpu) || !nested_virt_in_use(vcpu))
+				return -EINVAL;
+			break;
 		default:
 			err = -EINVAL;
 			goto out;
-- 
2.29.2

[PATCH v3 05/66] KVM: arm64: nv: Add EL2 system registers to vcpu context

[Marc Zyngier]

Add the minimal set of EL2 system registers to the vcpu context.
Nothing uses them just yet.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 34 ++++++++++++++++++++++++++++++-
 1 file changed, 33 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 11beda85ee7e..d731cf7a56cb 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -206,12 +206,44 @@ enum vcpu_sysreg {
 	CNTP_CVAL_EL0,
 	CNTP_CTL_EL0,
 
-	/* 32bit specific registers. Keep them at the end of the range */
+	/* 32bit specific registers. */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
 	FPEXC32_EL2,	/* Floating-Point Exception Control Register */
 	DBGVCR32_EL2,	/* Debug Vector Catch Register */
 
+	/* EL2 registers */
+	VPIDR_EL2,	/* Virtualization Processor ID Register */
+	VMPIDR_EL2,	/* Virtualization Multiprocessor ID Register */
+	SCTLR_EL2,	/* System Control Register (EL2) */
+	ACTLR_EL2,	/* Auxiliary Control Register (EL2) */
+	HCR_EL2,	/* Hypervisor Configuration Register */
+	MDCR_EL2,	/* Monitor Debug Configuration Register (EL2) */
+	CPTR_EL2,	/* Architectural Feature Trap Register (EL2) */
+	HSTR_EL2,	/* Hypervisor System Trap Register */
+	HACR_EL2,	/* Hypervisor Auxiliary Control Register */
+	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
+	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
+	TCR_EL2,	/* Translation Control Register (EL2) */
+	VTTBR_EL2,	/* Virtualization Translation Table Base Register */
+	VTCR_EL2,	/* Virtualization Translation Control Register */
+	SPSR_EL2,	/* EL2 saved program status register */
+	ELR_EL2,	/* EL2 exception link register */
+	AFSR0_EL2,	/* Auxiliary Fault Status Register 0 (EL2) */
+	AFSR1_EL2,	/* Auxiliary Fault Status Register 1 (EL2) */
+	ESR_EL2,	/* Exception Syndrome Register (EL2) */
+	FAR_EL2,	/* Hypervisor IPA Fault Address Register */
+	HPFAR_EL2,	/* Hypervisor IPA Fault Address Register */
+	MAIR_EL2,	/* Memory Attribute Indirection Register (EL2) */
+	AMAIR_EL2,	/* Auxiliary Memory Attribute Indirection Register (EL2) */
+	VBAR_EL2,	/* Vector Base Address Register (EL2) */
+	RVBAR_EL2,	/* Reset Vector Base Address Register */
+	RMR_EL2,	/* Reset Management Register */
+	CONTEXTIDR_EL2,	/* Context ID Register (EL2) */
+	TPIDR_EL2,	/* EL2 Software Thread ID Register */
+	CNTHCTL_EL2,	/* Counter-timer Hypervisor Control register */
+	SP_EL2,		/* EL2 Stack Pointer */
+
 	NR_SYS_REGS	/* Nothing after this line! */
 };
 
-- 
2.29.2

[PATCH v3 06/66] KVM: arm64: nv: Add nested virt VCPU primitives for vEL2 VCPU state

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@arm.com>

When running a nested hypervisor we commonly have to figure out if
the VCPU mode is running in the context of a guest hypervisor or guest
guest, or just a normal guest.

Add convenient primitives for this.

Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h | 55 ++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index c8f550a53516..e3e22d364dc9 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -173,6 +173,61 @@ static __always_inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
 		vcpu_gp_regs(vcpu)->regs[reg_num] = val;
 }
 
+static inline bool vcpu_mode_el2_ctxt(const struct kvm_cpu_context *ctxt)
+{
+	unsigned long cpsr = ctxt->regs.pstate;
+
+	switch (cpsr & (PSR_MODE32_BIT | PSR_MODE_MASK)) {
+	case PSR_MODE_EL2h:
+	case PSR_MODE_EL2t:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline bool vcpu_mode_el2(const struct kvm_vcpu *vcpu)
+{
+	return vcpu_mode_el2_ctxt(&vcpu->arch.ctxt);
+}
+
+static inline bool __vcpu_el2_e2h_is_set(const struct kvm_cpu_context *ctxt)
+{
+	return ctxt_sys_reg(ctxt, HCR_EL2) & HCR_E2H;
+}
+
+static inline bool vcpu_el2_e2h_is_set(const struct kvm_vcpu *vcpu)
+{
+	return __vcpu_el2_e2h_is_set(&vcpu->arch.ctxt);
+}
+
+static inline bool __vcpu_el2_tge_is_set(const struct kvm_cpu_context *ctxt)
+{
+	return ctxt_sys_reg(ctxt, HCR_EL2) & HCR_TGE;
+}
+
+static inline bool vcpu_el2_tge_is_set(const struct kvm_vcpu *vcpu)
+{
+	return __vcpu_el2_tge_is_set(&vcpu->arch.ctxt);
+}
+
+static inline bool __is_hyp_ctxt(const struct kvm_cpu_context *ctxt)
+{
+	/*
+	 * We are in a hypervisor context if the vcpu mode is EL2 or
+	 * E2H and TGE bits are set. The latter means we are in the user space
+	 * of the VHE kernel. ARMv8.1 ARM describes this as 'InHost'
+	 */
+	return vcpu_mode_el2_ctxt(ctxt) ||
+		(__vcpu_el2_e2h_is_set(ctxt) && __vcpu_el2_tge_is_set(ctxt)) ||
+		WARN_ON(__vcpu_el2_tge_is_set(ctxt));
+}
+
+static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu)
+{
+	return __is_hyp_ctxt(&vcpu->arch.ctxt);
+}
+
 /*
  * The layout of SPSR for an AArch32 state is different when observed from an
  * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32
-- 
2.29.2

[PATCH v3 07/66] KVM: arm64: nv: Handle HCR_EL2.NV system register traps

[Marc Zyngier]

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

ARM v8.3 introduces a new bit in the HCR_EL2, which is the NV bit. When
this bit is set, accessing EL2 registers in EL1 traps to EL2. In
addition, executing the following instructions in EL1 will trap to EL2:
tlbi, at, eret, and msr/mrs instructions to access SP_EL1. Most of the
instructions that trap to EL2 with the NV bit were undef at EL1 prior to
ARM v8.3. The only instruction that was not undef is eret.

This patch sets up a handler for EL2 registers and SP_EL1 register
accesses at EL1. The host hypervisor keeps those register values in
memory, and will emulate their behavior.

This patch doesn't set the NV bit yet. It will be set in a later patch
once nested virtualization support is completed.

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
[maz: added SCTLR_EL2 RES0/RES1 handling]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/sysreg.h |  44 ++++++++++++-
 arch/arm64/kvm/sys_regs.c       | 112 ++++++++++++++++++++++++++++++--
 2 files changed, 150 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 82521cdbfc1c..05b49eafbb49 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -469,19 +469,50 @@
 
 #define SYS_PMCCFILTR_EL0		sys_reg(3, 3, 14, 15, 7)
 
+#define SYS_VPIDR_EL2			sys_reg(3, 4, 0, 0, 0)
+#define SYS_VMPIDR_EL2			sys_reg(3, 4, 0, 0, 5)
+
 #define SYS_SCTLR_EL2			sys_reg(3, 4, 1, 0, 0)
+#define SYS_ACTLR_EL2			sys_reg(3, 4, 1, 0, 1)
+#define SYS_HCR_EL2			sys_reg(3, 4, 1, 1, 0)
+#define SYS_MDCR_EL2			sys_reg(3, 4, 1, 1, 1)
+#define SYS_CPTR_EL2			sys_reg(3, 4, 1, 1, 2)
+#define SYS_HSTR_EL2			sys_reg(3, 4, 1, 1, 3)
+#define SYS_HACR_EL2			sys_reg(3, 4, 1, 1, 7)
+
 #define SYS_ZCR_EL2			sys_reg(3, 4, 1, 2, 0)
+
+#define SYS_TTBR0_EL2			sys_reg(3, 4, 2, 0, 0)
+#define SYS_TTBR1_EL2			sys_reg(3, 4, 2, 0, 1)
+#define SYS_TCR_EL2			sys_reg(3, 4, 2, 0, 2)
+#define SYS_VTTBR_EL2			sys_reg(3, 4, 2, 1, 0)
+#define SYS_VTCR_EL2			sys_reg(3, 4, 2, 1, 2)
+
 #define SYS_DACR32_EL2			sys_reg(3, 4, 3, 0, 0)
+
 #define SYS_SPSR_EL2			sys_reg(3, 4, 4, 0, 0)
 #define SYS_ELR_EL2			sys_reg(3, 4, 4, 0, 1)
+#define SYS_SP_EL1			sys_reg(3, 4, 4, 1, 0)
+
 #define SYS_IFSR32_EL2			sys_reg(3, 4, 5, 0, 1)
+#define SYS_AFSR0_EL2			sys_reg(3, 4, 5, 1, 0)
+#define SYS_AFSR1_EL2			sys_reg(3, 4, 5, 1, 1)
 #define SYS_ESR_EL2			sys_reg(3, 4, 5, 2, 0)
 #define SYS_VSESR_EL2			sys_reg(3, 4, 5, 2, 3)
 #define SYS_FPEXC32_EL2			sys_reg(3, 4, 5, 3, 0)
 #define SYS_TFSR_EL2			sys_reg(3, 4, 5, 6, 0)
 #define SYS_FAR_EL2			sys_reg(3, 4, 6, 0, 0)
 
-#define SYS_VDISR_EL2			sys_reg(3, 4, 12, 1,  1)
+#define SYS_FAR_EL2			sys_reg(3, 4, 6, 0, 0)
+#define SYS_HPFAR_EL2			sys_reg(3, 4, 6, 0, 4)
+
+#define SYS_MAIR_EL2			sys_reg(3, 4, 10, 2, 0)
+#define SYS_AMAIR_EL2			sys_reg(3, 4, 10, 3, 0)
+
+#define SYS_VBAR_EL2			sys_reg(3, 4, 12, 0, 0)
+#define SYS_RVBAR_EL2			sys_reg(3, 4, 12, 0, 1)
+#define SYS_RMR_EL2			sys_reg(3, 4, 12, 0, 2)
+#define SYS_VDISR_EL2			sys_reg(3, 4, 12, 1, 1)
 #define __SYS__AP0Rx_EL2(x)		sys_reg(3, 4, 12, 8, x)
 #define SYS_ICH_AP0R0_EL2		__SYS__AP0Rx_EL2(0)
 #define SYS_ICH_AP0R1_EL2		__SYS__AP0Rx_EL2(1)
@@ -523,15 +554,24 @@
 #define SYS_ICH_LR14_EL2		__SYS__LR8_EL2(6)
 #define SYS_ICH_LR15_EL2		__SYS__LR8_EL2(7)
 
+#define SYS_CONTEXTIDR_EL2		sys_reg(3, 4, 13, 0, 1)
+#define SYS_TPIDR_EL2			sys_reg(3, 4, 13, 0, 2)
+
+#define SYS_CNTVOFF_EL2			sys_reg(3, 4, 14, 0, 3)
+#define SYS_CNTHCTL_EL2			sys_reg(3, 4, 14, 1, 0)
+
 /* VHE encodings for architectural EL0/1 system registers */
 #define SYS_SCTLR_EL12			sys_reg(3, 5, 1, 0, 0)
 #define SYS_CPACR_EL12			sys_reg(3, 5, 1, 0, 2)
 #define SYS_ZCR_EL12			sys_reg(3, 5, 1, 2, 0)
+
 #define SYS_TTBR0_EL12			sys_reg(3, 5, 2, 0, 0)
 #define SYS_TTBR1_EL12			sys_reg(3, 5, 2, 0, 1)
 #define SYS_TCR_EL12			sys_reg(3, 5, 2, 0, 2)
+
 #define SYS_SPSR_EL12			sys_reg(3, 5, 4, 0, 0)
 #define SYS_ELR_EL12			sys_reg(3, 5, 4, 0, 1)
+
 #define SYS_AFSR0_EL12			sys_reg(3, 5, 5, 1, 0)
 #define SYS_AFSR1_EL12			sys_reg(3, 5, 5, 1, 1)
 #define SYS_ESR_EL12			sys_reg(3, 5, 5, 2, 0)
@@ -549,6 +589,8 @@
 #define SYS_CNTV_CTL_EL02		sys_reg(3, 5, 14, 3, 1)
 #define SYS_CNTV_CVAL_EL02		sys_reg(3, 5, 14, 3, 2)
 
+#define SYS_SP_EL2			sys_reg(3, 6,  4, 1, 0)
+
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_DSSBS	(BIT(44))
 #define SCTLR_ELx_ATA	(BIT(43))
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 3313dedfa505..c049867a39bc 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -104,6 +104,57 @@ static u32 get_ccsidr(u32 csselr)
 	return ccsidr;
 }
 
+static bool access_rw(struct kvm_vcpu *vcpu,
+		      struct sys_reg_params *p,
+		      const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		vcpu_write_sys_reg(vcpu, p->regval, r->reg);
+	else
+		p->regval = vcpu_read_sys_reg(vcpu, r->reg);
+
+	return true;
+}
+
+static bool access_wi(struct kvm_vcpu *vcpu,
+		      struct sys_reg_params *p,
+		      const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	p->regval = vcpu_read_sys_reg(vcpu, r->reg);
+	return true;
+}
+
+static bool access_sctlr_el2(struct kvm_vcpu *vcpu,
+			     struct sys_reg_params *p,
+			     const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		u64 val = p->regval;
+
+		if (vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)) {
+			val &= ~(GENMASK_ULL(63,45) | GENMASK_ULL(34, 32) |
+				 BIT_ULL(17));
+			val |=  SCTLR_EL1_RES1;
+		} else {
+			val &= ~(GENMASK_ULL(63,45) | BIT_ULL(42) |
+				 GENMASK_ULL(39, 38) | GENMASK_ULL(35, 32) |
+				 BIT_ULL(26) | BIT_ULL(24) | BIT_ULL(20) |
+				 BIT_ULL(17) | GENMASK_ULL(15, 14) |
+				 GENMASK(10, 7));
+			val |=  SCTLR_EL2_RES1;
+		}
+
+		vcpu_write_sys_reg(vcpu, val, r->reg);
+	} else {
+		p->regval = vcpu_read_sys_reg(vcpu, r->reg);
+	}
+
+	return true;
+}
+
 /*
  * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
  */
@@ -342,12 +393,9 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu,
 			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *r)
 {
-	if (p->is_write) {
-		vcpu_write_sys_reg(vcpu, p->regval, r->reg);
+	access_rw(vcpu, p, r);
+	if (p->is_write)
 		vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
-	} else {
-		p->regval = vcpu_read_sys_reg(vcpu, r->reg);
-	}
 
 	trace_trap_reg(__func__, r->reg, p->is_write, p->regval);
 
@@ -1314,6 +1362,18 @@ static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	.set_user = set_raz_id_reg,		\
 }
 
+static bool access_sp_el1(struct kvm_vcpu *vcpu,
+			  struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		__vcpu_sys_reg(vcpu, SP_EL1) = p->regval;
+	else
+		p->regval = __vcpu_sys_reg(vcpu, SP_EL1);
+
+	return true;
+}
+
 /*
  * Architected system registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
@@ -1692,9 +1752,51 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	 */
 	{ SYS_DESC(SYS_PMCCFILTR_EL0), access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 },
 
+	{ SYS_DESC(SYS_VPIDR_EL2), access_rw, reset_val, VPIDR_EL2, 0 },
+	{ SYS_DESC(SYS_VMPIDR_EL2), access_rw, reset_val, VMPIDR_EL2, 0 },
+
+	{ SYS_DESC(SYS_SCTLR_EL2), access_sctlr_el2, reset_val, SCTLR_EL2, SCTLR_EL2_RES1 },
+	{ SYS_DESC(SYS_ACTLR_EL2), access_rw, reset_val, ACTLR_EL2, 0 },
+	{ SYS_DESC(SYS_HCR_EL2), access_rw, reset_val, HCR_EL2, 0 },
+	{ SYS_DESC(SYS_MDCR_EL2), access_rw, reset_val, MDCR_EL2, 0 },
+	{ SYS_DESC(SYS_CPTR_EL2), access_rw, reset_val, CPTR_EL2, CPTR_EL2_RES1 },
+	{ SYS_DESC(SYS_HSTR_EL2), access_rw, reset_val, HSTR_EL2, 0 },
+	{ SYS_DESC(SYS_HACR_EL2), access_rw, reset_val, HACR_EL2, 0 },
+
+	{ SYS_DESC(SYS_TTBR0_EL2), access_rw, reset_val, TTBR0_EL2, 0 },
+	{ SYS_DESC(SYS_TTBR1_EL2), access_rw, reset_val, TTBR1_EL2, 0 },
+	{ SYS_DESC(SYS_TCR_EL2), access_rw, reset_val, TCR_EL2, TCR_EL2_RES1 },
+	{ SYS_DESC(SYS_VTTBR_EL2), access_rw, reset_val, VTTBR_EL2, 0 },
+	{ SYS_DESC(SYS_VTCR_EL2), access_rw, reset_val, VTCR_EL2, 0 },
+
 	{ SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 },
+	{ SYS_DESC(SYS_SPSR_EL2), access_rw, reset_val, SPSR_EL2, 0 },
+	{ SYS_DESC(SYS_ELR_EL2), access_rw, reset_val, ELR_EL2, 0 },
+	{ SYS_DESC(SYS_SP_EL1), access_sp_el1},
+
 	{ SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 },
+	{ SYS_DESC(SYS_AFSR0_EL2), access_rw, reset_val, AFSR0_EL2, 0 },
+	{ SYS_DESC(SYS_AFSR1_EL2), access_rw, reset_val, AFSR1_EL2, 0 },
+	{ SYS_DESC(SYS_ESR_EL2), access_rw, reset_val, ESR_EL2, 0 },
 	{ SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x700 },
+
+	{ SYS_DESC(SYS_FAR_EL2), access_rw, reset_val, FAR_EL2, 0 },
+	{ SYS_DESC(SYS_HPFAR_EL2), access_rw, reset_val, HPFAR_EL2, 0 },
+
+	{ SYS_DESC(SYS_MAIR_EL2), access_rw, reset_val, MAIR_EL2, 0 },
+	{ SYS_DESC(SYS_AMAIR_EL2), access_rw, reset_val, AMAIR_EL2, 0 },
+
+	{ SYS_DESC(SYS_VBAR_EL2), access_rw, reset_val, VBAR_EL2, 0 },
+	{ SYS_DESC(SYS_RVBAR_EL2), access_rw, reset_val, RVBAR_EL2, 0 },
+	{ SYS_DESC(SYS_RMR_EL2), access_wi, reset_val, RMR_EL2, 1 },
+
+	{ SYS_DESC(SYS_CONTEXTIDR_EL2), access_rw, reset_val, CONTEXTIDR_EL2, 0 },
+	{ SYS_DESC(SYS_TPIDR_EL2), access_rw, reset_val, TPIDR_EL2, 0 },
+
+	{ SYS_DESC(SYS_CNTVOFF_EL2), access_rw, reset_val, CNTVOFF_EL2, 0 },
+	{ SYS_DESC(SYS_CNTHCTL_EL2), access_rw, reset_val, CNTHCTL_EL2, 0 },
+
+	{ SYS_DESC(SYS_SP_EL2), NULL, reset_unknown, SP_EL2 },
 };
 
 static bool trap_dbgidr(struct kvm_vcpu *vcpu,
-- 
2.29.2

[PATCH v3 08/66] KVM: arm64: nv: Reset VMPIDR_EL2 and VPIDR_EL2 to sane values

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@arm.com>

The VMPIDR_EL2 and VPIDR_EL2 are architecturally UNKNOWN at reset, but
let's be nice to a guest hypervisor behaving foolishly and reset these
to something reasonable anyway.

Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/sys_regs.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index c049867a39bc..cc7a86624e36 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -621,7 +621,7 @@ static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	vcpu_write_sys_reg(vcpu, actlr, ACTLR_EL1);
 }
 
-static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+static u64 compute_reset_mpidr(struct kvm_vcpu *vcpu)
 {
 	u64 mpidr;
 
@@ -635,7 +635,24 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	mpidr = (vcpu->vcpu_id & 0x0f) << MPIDR_LEVEL_SHIFT(0);
 	mpidr |= ((vcpu->vcpu_id >> 4) & 0xff) << MPIDR_LEVEL_SHIFT(1);
 	mpidr |= ((vcpu->vcpu_id >> 12) & 0xff) << MPIDR_LEVEL_SHIFT(2);
-	vcpu_write_sys_reg(vcpu, (1ULL << 31) | mpidr, MPIDR_EL1);
+	mpidr |= (1ULL << 31);
+
+	return mpidr;
+}
+
+static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+	vcpu_write_sys_reg(vcpu, compute_reset_mpidr(vcpu), MPIDR_EL1);
+}
+
+static void reset_vmpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+	vcpu_write_sys_reg(vcpu, compute_reset_mpidr(vcpu), VMPIDR_EL2);
+}
+
+static void reset_vpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+	vcpu_write_sys_reg(vcpu, read_cpuid_id(), VPIDR_EL2);
 }
 
 static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
@@ -1752,8 +1769,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	 */
 	{ SYS_DESC(SYS_PMCCFILTR_EL0), access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 },
 
-	{ SYS_DESC(SYS_VPIDR_EL2), access_rw, reset_val, VPIDR_EL2, 0 },
-	{ SYS_DESC(SYS_VMPIDR_EL2), access_rw, reset_val, VMPIDR_EL2, 0 },
+	{ SYS_DESC(SYS_VPIDR_EL2), access_rw, reset_vpidr, VPIDR_EL2 },
+	{ SYS_DESC(SYS_VMPIDR_EL2), access_rw, reset_vmpidr, VMPIDR_EL2 },
 
 	{ SYS_DESC(SYS_SCTLR_EL2), access_sctlr_el2, reset_val, SCTLR_EL2, SCTLR_EL2_RES1 },
 	{ SYS_DESC(SYS_ACTLR_EL2), access_rw, reset_val, ACTLR_EL2, 0 },
-- 
2.29.2

[PATCH v3 09/66] KVM: arm64: nv: Support virtual EL2 exceptions

[Marc Zyngier]

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

Support injecting exceptions and performing exception returns to and
from virtual EL2.  This must be done entirely in software except when
taking an exception from vEL0 to vEL2 when the virtual HCR_EL2.{E2H,TGE}
== {1,1}  (a VHE guest hypervisor).

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
[maz: switch to common exception injection framework]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_arm.h     |  17 +++
 arch/arm64/include/asm/kvm_emulate.h |  10 ++
 arch/arm64/kvm/Makefile              |   2 +-
 arch/arm64/kvm/emulate-nested.c      | 176 +++++++++++++++++++++++++++
 arch/arm64/kvm/hyp/exception.c       |  44 +++++--
 arch/arm64/kvm/inject_fault.c        |  62 ++++++++--
 arch/arm64/kvm/trace_arm.h           |  59 +++++++++
 7 files changed, 352 insertions(+), 18 deletions(-)
 create mode 100644 arch/arm64/kvm/emulate-nested.c

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 4e90c2debf70..e9e10e498785 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -332,4 +332,21 @@
 #define CPACR_EL1_TTA		(1 << 28)
 #define CPACR_EL1_DEFAULT	(CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN)
 
+#define kvm_mode_names				\
+	{ PSR_MODE_EL0t,	"EL0t" },	\
+	{ PSR_MODE_EL1t,	"EL1t" },	\
+	{ PSR_MODE_EL1h,	"EL1h" },	\
+	{ PSR_MODE_EL2t,	"EL2t" },	\
+	{ PSR_MODE_EL2h,	"EL2h" },	\
+	{ PSR_MODE_EL3t,	"EL3t" },	\
+	{ PSR_MODE_EL3h,	"EL3h" },	\
+	{ PSR_AA32_MODE_USR,	"32-bit USR" },	\
+	{ PSR_AA32_MODE_FIQ,	"32-bit FIQ" },	\
+	{ PSR_AA32_MODE_IRQ,	"32-bit IRQ" },	\
+	{ PSR_AA32_MODE_SVC,	"32-bit SVC" },	\
+	{ PSR_AA32_MODE_ABT,	"32-bit ABT" },	\
+	{ PSR_AA32_MODE_HYP,	"32-bit HYP" },	\
+	{ PSR_AA32_MODE_UND,	"32-bit UND" },	\
+	{ PSR_AA32_MODE_SYS,	"32-bit SYS" }
+
 #endif /* __ARM64_KVM_ARM_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index e3e22d364dc9..deffd3cc4443 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -33,6 +33,12 @@ enum exception_type {
 	except_type_serror	= 0x180,
 };
 
+#define kvm_exception_type_names		\
+	{ except_type_sync,	"SYNC"   },	\
+	{ except_type_irq,	"IRQ"    },	\
+	{ except_type_fiq,	"FIQ"    },	\
+	{ except_type_serror,	"SERROR" }
+
 bool kvm_condition_valid32(const struct kvm_vcpu *vcpu);
 void kvm_skip_instr32(struct kvm_vcpu *vcpu);
 
@@ -41,6 +47,10 @@ void kvm_inject_vabt(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 
+void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu);
+int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2);
+int kvm_inject_nested_irq(struct kvm_vcpu *vcpu);
+
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
 	return !(vcpu->arch.hcr_el2 & HCR_RW);
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 60fd181df624..672acdf1e993 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -17,11 +17,11 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 guest.o debug.o reset.o sys_regs.o \
 	 vgic-sys-reg-v3.o fpsimd.o pmu.o \
 	 arch_timer.o \
+	 emulate-nested.o \
 	 vgic/vgic.o vgic/vgic-init.o \
 	 vgic/vgic-irqfd.o vgic/vgic-v2.o \
 	 vgic/vgic-v3.o vgic/vgic-v4.o \
 	 vgic/vgic-mmio.o vgic/vgic-mmio-v2.o \
 	 vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \
 	 vgic/vgic-its.o vgic/vgic-debug.o
-
 kvm-$(CONFIG_KVM_ARM_PMU)  += pmu-emul.o
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
new file mode 100644
index 000000000000..ee91bcd925d8
--- /dev/null
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -0,0 +1,176 @@
+/*
+ * Copyright (C) 2016 - Linaro and Columbia University
+ * Author: Jintack Lim <jintack.lim@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_nested.h>
+
+#include "hyp/include/hyp/adjust_pc.h"
+
+#include "trace.h"
+
+void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
+{
+	u64 spsr, elr, mode;
+	bool direct_eret;
+
+	/*
+	 * Going through the whole put/load motions is a waste of time
+	 * if this is a VHE guest hypervisor returning to its own
+	 * userspace, or the hypervisor performing a local exception
+	 * return. No need to save/restore registers, no need to
+	 * switch S2 MMU. Just do the canonical ERET.
+	 */
+	spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2);
+	mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+	direct_eret  = (mode == PSR_MODE_EL0t &&
+			vcpu_el2_e2h_is_set(vcpu) &&
+			vcpu_el2_tge_is_set(vcpu));
+	direct_eret |= (mode == PSR_MODE_EL2h || mode == PSR_MODE_EL2t);
+
+	if (direct_eret) {
+		*vcpu_pc(vcpu) = vcpu_read_sys_reg(vcpu, ELR_EL2);
+		*vcpu_cpsr(vcpu) = spsr;
+		trace_kvm_nested_eret(vcpu, *vcpu_pc(vcpu), spsr);
+		return;
+	}
+
+	preempt_disable();
+	kvm_arch_vcpu_put(vcpu);
+
+	elr = __vcpu_sys_reg(vcpu, ELR_EL2);
+
+	trace_kvm_nested_eret(vcpu, elr, spsr);
+
+	/*
+	 * Note that the current exception level is always the virtual EL2,
+	 * since we set HCR_EL2.NV bit only when entering the virtual EL2.
+	 */
+	*vcpu_pc(vcpu) = elr;
+	*vcpu_cpsr(vcpu) = spsr;
+
+	kvm_arch_vcpu_load(vcpu, smp_processor_id());
+	preempt_enable();
+}
+
+static void kvm_inject_el2_exception(struct kvm_vcpu *vcpu, u64 esr_el2,
+				     enum exception_type type)
+{
+	trace_kvm_inject_nested_exception(vcpu, esr_el2, type);
+
+	switch (type) {
+	case except_type_sync:
+		vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_ELx_SYNC;
+		break;
+	case except_type_irq:
+		vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_ELx_IRQ;
+		break;
+	default:
+		WARN_ONCE(1, "Unsupported EL2 exception injection %d\n", type);
+	}
+
+	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL2		|
+			     KVM_ARM64_PENDING_EXCEPTION);
+
+	vcpu_write_sys_reg(vcpu, esr_el2, ESR_EL2);
+}
+
+/*
+ * Emulate taking an exception to EL2.
+ * See ARM ARM J8.1.2 AArch64.TakeException()
+ */
+static int kvm_inject_nested(struct kvm_vcpu *vcpu, u64 esr_el2,
+			     enum exception_type type)
+{
+	u64 pstate, mode;
+	bool direct_inject;
+
+	if (!nested_virt_in_use(vcpu)) {
+		kvm_err("Unexpected call to %s for the non-nesting configuration\n",
+				__func__);
+		return -EINVAL;
+	}
+
+	/*
+	 * As for ERET, we can avoid doing too much on the injection path by
+	 * checking that we either took the exception from a VHE host
+	 * userspace or from vEL2. In these cases, there is no change in
+	 * translation regime (or anything else), so let's do as little as
+	 * possible.
+	 */
+	pstate = *vcpu_cpsr(vcpu);
+	mode = pstate & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+	direct_inject  = (mode == PSR_MODE_EL0t &&
+			  vcpu_el2_e2h_is_set(vcpu) &&
+			  vcpu_el2_tge_is_set(vcpu));
+	direct_inject |= (mode == PSR_MODE_EL2h || mode == PSR_MODE_EL2t);
+
+	if (direct_inject) {
+		kvm_inject_el2_exception(vcpu, esr_el2, type);
+		return 1;
+	}
+
+	preempt_disable();
+	kvm_arch_vcpu_put(vcpu);
+
+	kvm_inject_el2_exception(vcpu, esr_el2, type);
+
+	/*
+	 * A hard requirement is that a switch between EL1 and EL2
+	 * contexts has to happen between a put/load, so that we can
+	 * pick the correct timer and interrupt configuration, among
+	 * other things.
+	 *
+	 * Make sure the exception actually took place before we load
+	 * the new context.
+	 */
+	__adjust_pc(vcpu);
+
+	kvm_arch_vcpu_load(vcpu, smp_processor_id());
+	preempt_enable();
+
+	return 1;
+}
+
+int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2)
+{
+	return kvm_inject_nested(vcpu, esr_el2, except_type_sync);
+}
+
+int kvm_inject_nested_irq(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Do not inject an irq if the:
+	 *  - Current exception level is EL2, and
+	 *  - virtual HCR_EL2.TGE == 0
+	 *  - virtual HCR_EL2.IMO == 0
+	 *
+	 * See Table D1-17 "Physical interrupt target and masking when EL3 is
+	 * not implemented and EL2 is implemented" in ARM DDI 0487C.a.
+	 */
+
+	if (vcpu_mode_el2(vcpu) && !vcpu_el2_tge_is_set(vcpu) &&
+	    !(__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_IMO))
+		return 1;
+
+	/* esr_el2 value doesn't matter for exits due to irqs. */
+	return kvm_inject_nested(vcpu, 0, except_type_irq);
+}
diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
index 73629094f903..7c8b3681dafd 100644
--- a/arch/arm64/kvm/hyp/exception.c
+++ b/arch/arm64/kvm/hyp/exception.c
@@ -22,7 +22,9 @@ static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 {
 	u64 val;
 
-	if (__vcpu_read_sys_reg_from_cpu(reg, &val))
+	if (unlikely(nested_virt_in_use(vcpu)))
+		return vcpu_read_sys_reg(vcpu, reg);
+	else if (__vcpu_read_sys_reg_from_cpu(reg, &val))
 		return val;
 
 	return __vcpu_sys_reg(vcpu, reg);
@@ -30,14 +32,26 @@ static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 
 static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 {
-	if (__vcpu_write_sys_reg_to_cpu(val, reg))
+	if (unlikely(nested_virt_in_use(vcpu)))
+		vcpu_write_sys_reg(vcpu, val, reg);
+	else if (__vcpu_write_sys_reg_to_cpu(val, reg))
 		return;
 
 	 __vcpu_sys_reg(vcpu, reg) = val;
 }
 
-static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, u64 val)
+static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
+			      u64 val)
 {
+	if (unlikely(nested_virt_in_use(vcpu))) {
+		if (target_mode == PSR_MODE_EL1h)
+			vcpu_write_sys_reg(vcpu, val, SPSR_EL1);
+		else
+			vcpu_write_sys_reg(vcpu, val, SPSR_EL2);
+
+		return;
+	}
+
 	write_sysreg_el1(val, SYS_SPSR);
 }
 
@@ -97,6 +111,11 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
 		sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1);
 		__vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1);
 		break;
+	case PSR_MODE_EL2h:
+		vbar = __vcpu_read_sys_reg(vcpu, VBAR_EL2);
+		sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL2);
+		__vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL2);
+		break;
 	default:
 		/* Don't do that */
 		BUG();
@@ -148,7 +167,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
 	new |= target_mode;
 
 	*vcpu_cpsr(vcpu) = new;
-	__vcpu_write_spsr(vcpu, old);
+	__vcpu_write_spsr(vcpu, target_mode, old);
 }
 
 /*
@@ -319,11 +338,22 @@ void kvm_inject_exception(struct kvm_vcpu *vcpu)
 		      KVM_ARM64_EXCEPT_AA64_EL1):
 			enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync);
 			break;
+
+		case (KVM_ARM64_EXCEPT_AA64_ELx_SYNC |
+		      KVM_ARM64_EXCEPT_AA64_EL2):
+			enter_exception64(vcpu, PSR_MODE_EL2h, except_type_sync);
+			break;
+
+		case (KVM_ARM64_EXCEPT_AA64_ELx_IRQ |
+		      KVM_ARM64_EXCEPT_AA64_EL2):
+			enter_exception64(vcpu, PSR_MODE_EL2h, except_type_irq);
+			break;
+
 		default:
 			/*
-			 * Only EL1_SYNC makes sense so far, EL2_{SYNC,IRQ}
-			 * will be implemented at some point. Everything
-			 * else gets silently ignored.
+			 * Only EL1_SYNC and EL2_{SYNC,IRQ} makes
+			 * sense so far. Everything else gets silently
+			 * ignored.
 			 */
 			break;
 		}
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index b47df73e98d7..530562eb09fd 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -14,17 +14,50 @@
 #include <asm/kvm_emulate.h>
 #include <asm/esr.h>
 
+static void pend_sync_exception(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_ELx_SYNC	|
+			     KVM_ARM64_PENDING_EXCEPTION);
+
+	/* If not nesting, EL1 is the only possible exception target */
+	if (likely(!nested_virt_in_use(vcpu))) {
+		vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_EL1;
+		return;
+	}
+
+	/*
+	 * With NV, we need to pick between EL1 and EL2. Note that we
+	 * never deal with a nesting exception here, hence never
+	 * changing context, and the exception itself can be delayed
+	 * until the next entry.
+	 */
+	switch(*vcpu_cpsr(vcpu) & PSR_MODE_MASK) {
+	case PSR_MODE_EL2h:
+	case PSR_MODE_EL2t:
+		vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_EL2;
+		break;
+	case PSR_MODE_EL1h:
+	case PSR_MODE_EL1t:
+		vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_EL1;
+		break;
+	case PSR_MODE_EL0t:
+		if (vcpu_el2_tge_is_set(vcpu) & HCR_TGE)
+			vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_EL2;
+		else
+			vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_EL1;
+		break;
+	default:
+		BUG();
+	}
+}
+
 static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
 {
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
 	bool is_aarch32 = vcpu_mode_is_32bit(vcpu);
 	u32 esr = 0;
 
-	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1		|
-			     KVM_ARM64_EXCEPT_AA64_ELx_SYNC	|
-			     KVM_ARM64_PENDING_EXCEPTION);
-
-	vcpu_write_sys_reg(vcpu, addr, FAR_EL1);
+	pend_sync_exception(vcpu);
 
 	/*
 	 * Build an {i,d}abort, depending on the level and the
@@ -45,16 +78,22 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
 	if (!is_iabt)
 		esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT;
 
-	vcpu_write_sys_reg(vcpu, esr | ESR_ELx_FSC_EXTABT, ESR_EL1);
+	esr |= ESR_ELx_FSC_EXTABT;
+
+	if (vcpu->arch.flags & KVM_ARM64_EXCEPT_AA64_EL1) {
+		vcpu_write_sys_reg(vcpu, addr, FAR_EL1);
+		vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
+	} else {
+		vcpu_write_sys_reg(vcpu, addr, FAR_EL2);
+		vcpu_write_sys_reg(vcpu, esr, ESR_EL2);
+	}
 }
 
 static void inject_undef64(struct kvm_vcpu *vcpu)
 {
 	u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
 
-	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1		|
-			     KVM_ARM64_EXCEPT_AA64_ELx_SYNC	|
-			     KVM_ARM64_PENDING_EXCEPTION);
+	pend_sync_exception(vcpu);
 
 	/*
 	 * Build an unknown exception, depending on the instruction
@@ -63,7 +102,10 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 	if (kvm_vcpu_trap_il_is32bit(vcpu))
 		esr |= ESR_ELx_IL;
 
-	vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
+	if (vcpu->arch.flags & KVM_ARM64_EXCEPT_AA64_EL1)
+		vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
+	else
+		vcpu_write_sys_reg(vcpu, esr, ESR_EL2);
 }
 
 #define DFSR_FSC_EXTABT_LPAE	0x10
diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h
index ff0444352bba..5707011c4f47 100644
--- a/arch/arm64/kvm/trace_arm.h
+++ b/arch/arm64/kvm/trace_arm.h
@@ -2,6 +2,7 @@
 #if !defined(_TRACE_ARM_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_ARM_ARM64_KVM_H
 
+#include <asm/kvm_emulate.h>
 #include <kvm/arm_arch_timer.h>
 #include <linux/tracepoint.h>
 
@@ -367,6 +368,64 @@ TRACE_EVENT(kvm_timer_emulate,
 		  __entry->timer_idx, __entry->should_fire)
 );
 
+TRACE_EVENT(kvm_nested_eret,
+	TP_PROTO(struct kvm_vcpu *vcpu, unsigned long elr_el2,
+		 unsigned long spsr_el2),
+	TP_ARGS(vcpu, elr_el2, spsr_el2),
+
+	TP_STRUCT__entry(
+		__field(struct kvm_vcpu *,	vcpu)
+		__field(unsigned long,		elr_el2)
+		__field(unsigned long,		spsr_el2)
+		__field(unsigned long,		target_mode)
+		__field(unsigned long,		hcr_el2)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu = vcpu;
+		__entry->elr_el2 = elr_el2;
+		__entry->spsr_el2 = spsr_el2;
+		__entry->target_mode = spsr_el2 & (PSR_MODE_MASK | PSR_MODE32_BIT);
+		__entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2);
+	),
+
+	TP_printk("elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx",
+		  __entry->elr_el2, __entry->spsr_el2,
+		  __print_symbolic(__entry->target_mode, kvm_mode_names),
+		  __entry->hcr_el2)
+);
+
+TRACE_EVENT(kvm_inject_nested_exception,
+	TP_PROTO(struct kvm_vcpu *vcpu, u64 esr_el2, int type),
+	TP_ARGS(vcpu, esr_el2, type),
+
+	TP_STRUCT__entry(
+		__field(struct kvm_vcpu *,		vcpu)
+		__field(unsigned long,			esr_el2)
+		__field(int,				type)
+		__field(unsigned long,			spsr_el2)
+		__field(unsigned long,			pc)
+		__field(unsigned long,			source_mode)
+		__field(unsigned long,			hcr_el2)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu = vcpu;
+		__entry->esr_el2 = esr_el2;
+		__entry->type = type;
+		__entry->spsr_el2 = *vcpu_cpsr(vcpu);
+		__entry->pc = *vcpu_pc(vcpu);
+		__entry->source_mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
+		__entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2);
+	),
+
+	TP_printk("%s: esr_el2 0x%lx elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx",
+		  __print_symbolic(__entry->type, kvm_exception_type_names),
+		  __entry->esr_el2, __entry->pc, __entry->spsr_el2,
+		  __print_symbolic(__entry->source_mode, kvm_mode_names),
+		  __entry->hcr_el2)
+);
+
 #endif /* _TRACE_ARM_ARM64_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
-- 
2.29.2

[PATCH v3 10/66] KVM: arm64: nv: Inject HVC exceptions to the virtual EL2

[Marc Zyngier]

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

As we expect all PSCI calls from the L1 hypervisor to be performed
using SMC when nested virtualization is enabled, it is clear that
all HVC instruction from the VM (including from the virtual EL2)
are supposed to handled in the virtual EL2.

Forward these to EL2 as required.

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
[maz: add handling of HCR_EL2.HCD]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/handle_exit.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index cebe39f3b1b6..5245ac818e4f 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -16,6 +16,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_nested.h>
 #include <asm/debug-monitors.h>
 #include <asm/traps.h>
 
@@ -40,6 +41,16 @@ static int handle_hvc(struct kvm_vcpu *vcpu)
 			    kvm_vcpu_hvc_get_imm(vcpu));
 	vcpu->stat.hvc_exit_stat++;
 
+	/* Forward hvc instructions to the virtual EL2 if the guest has EL2. */
+	if (nested_virt_in_use(vcpu)) {
+		if (vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_HCD)
+			kvm_inject_undefined(vcpu);
+		else
+			kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
+		return 1;
+	}
+
 	ret = kvm_hvc_call_handler(vcpu);
 	if (ret < 0) {
 		vcpu_set_reg(vcpu, 0, ~0UL);
-- 
2.29.2

[PATCH v3 11/66] KVM: arm64: nv: Handle trapped ERET from virtual EL2

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@arm.com>

When a guest hypervisor running virtual EL2 in EL1 executes an ERET
instruction, we will have set HCR_EL2.NV which traps ERET to EL2, so
that we can emulate the exception return in software.

Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/esr.h     |  5 +++++
 arch/arm64/include/asm/kvm_arm.h |  2 +-
 arch/arm64/kvm/handle_exit.c     | 10 ++++++++++
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 22c81f1edda2..ab63b7b3ea14 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -251,6 +251,11 @@
 		(((e) & ESR_ELx_SYS64_ISS_OP2_MASK) >>		\
 		 ESR_ELx_SYS64_ISS_OP2_SHIFT))
 
+/* ISS field definitions for ERET/ERETAA/ERETAB trapping */
+
+#define ESR_ELx_ERET_ISS_ERET_ERETAx	0x2
+#define ESR_ELx_ERET_ISS_ERETA_ERATAB	0x1
+
 /*
  * ISS field definitions for floating-point exception traps
  * (FP_EXC_32/FP_EXC_64).
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index e9e10e498785..4cf745f79985 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -326,7 +326,7 @@
 	ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \
 	ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \
 	ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \
-	ECN(BKPT32), ECN(VECTOR32), ECN(BRK64)
+	ECN(BKPT32), ECN(VECTOR32), ECN(BRK64), ECN(ERET)
 
 #define CPACR_EL1_FPEN		(3 << 20)
 #define CPACR_EL1_TTA		(1 << 28)
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 5245ac818e4f..56f8a77b9d4a 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -183,6 +183,15 @@ static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int kvm_handle_eret(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_ERET_ISS_ERET_ERETAx)
+		return kvm_handle_ptrauth(vcpu);
+
+	kvm_emulate_nested_eret(vcpu);
+	return 1;
+}
+
 static exit_handle_fn arm_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]	= kvm_handle_unknown_ec,
 	[ESR_ELx_EC_WFx]	= kvm_handle_wfx,
@@ -197,6 +206,7 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_SMC64]	= handle_smc,
 	[ESR_ELx_EC_SYS64]	= kvm_handle_sys_reg,
 	[ESR_ELx_EC_SVE]	= handle_sve,
+	[ESR_ELx_EC_ERET]	= kvm_handle_eret,
 	[ESR_ELx_EC_IABT_LOW]	= kvm_handle_guest_abort,
 	[ESR_ELx_EC_DABT_LOW]	= kvm_handle_guest_abort,
 	[ESR_ELx_EC_SOFTSTP_LOW]= kvm_handle_guest_debug,
-- 
2.29.2

[PATCH v3 12/66] KVM: arm64: nv: Add non-VHE-EL2->EL1 translation helpers

[Marc Zyngier]

Some EL2 system registers immediately affect the current execution
of the system, so we need to use their respective EL1 counterparts.
For this we need to define a mapping between the two. In general,
this only affects non-VHE guest hypervisors, as VHE system registers
are compatible with the EL1 counterparts.

These helpers will get used in subsequent patches.

Co-developed-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h | 50 +++++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 1028ac65a897..67a2c0d05233 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -2,6 +2,7 @@
 #ifndef __ARM64_KVM_NESTED_H
 #define __ARM64_KVM_NESTED_H
 
+#include <linux/bitfield.h>
 #include <linux/kvm_host.h>
 
 static inline bool nested_virt_in_use(const struct kvm_vcpu *vcpu)
@@ -11,4 +12,53 @@ static inline bool nested_virt_in_use(const struct kvm_vcpu *vcpu)
 		test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features));
 }
 
+/* Translation helpers from non-VHE EL2 to EL1 */
+static inline u64 tcr_el2_ips_to_tcr_el1_ps(u64 tcr_el2)
+{
+	return (u64)FIELD_GET(TCR_EL2_PS_MASK, tcr_el2) << TCR_IPS_SHIFT;
+}
+
+static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr)
+{
+	return TCR_EPD1_MASK |				/* disable TTBR1_EL1 */
+	       ((tcr & TCR_EL2_TBI) ? TCR_TBI0 : 0) |
+	       tcr_el2_ips_to_tcr_el1_ps(tcr) |
+	       (tcr & TCR_EL2_TG0_MASK) |
+	       (tcr & TCR_EL2_ORGN0_MASK) |
+	       (tcr & TCR_EL2_IRGN0_MASK) |
+	       (tcr & TCR_EL2_T0SZ_MASK);
+}
+
+static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2)
+{
+	u64 cpacr_el1 = 0;
+
+	if (!(cptr_el2 & CPTR_EL2_TFP))
+		cpacr_el1 |= CPACR_EL1_FPEN;
+	if (cptr_el2 & CPTR_EL2_TTA)
+		cpacr_el1 |= CPACR_EL1_TTA;
+	if (!(cptr_el2 & CPTR_EL2_TZ))
+		cpacr_el1 |= CPACR_EL1_ZEN;
+
+	return cpacr_el1;
+}
+
+static inline u64 translate_sctlr_el2_to_sctlr_el1(u64 sctlr)
+{
+	/* Bit 20 is RES1 in SCTLR_EL1, but RES0 in SCTLR_EL2 */
+	return sctlr | BIT(20);
+}
+
+static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0)
+{
+	/* Force ASID to 0 (ASID 0 or RES0) */
+	return ttbr0 & ~GENMASK_ULL(63, 48);
+}
+
+static inline u64 translate_cnthctl_el2_to_cntkctl_el1(u64 cnthctl)
+{
+	return ((FIELD_GET(CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN, cnthctl) << 10) |
+		(cnthctl & (CNTHCTL_EVNTI | CNTHCTL_EVNTDIR | CNTHCTL_EVNTEN)));
+}
+
 #endif /* __ARM64_KVM_NESTED_H */
-- 
2.29.2

[PATCH v3 13/66] KVM: arm64: nv: Handle virtual EL2 registers in vcpu_read/write_sys_reg()

[Marc Zyngier]

KVM internally uses accessor functions when reading or writing the
guest's system registers. This takes care of accessing either the stored
copy or using the "live" EL1 system registers when the host uses VHE.

With the introduction of virtual EL2 we add a bunch of EL2 system
registers, which now must also be taken care of:
- If the guest is running in vEL2, and we access an EL1 sysreg, we must
  revert to the stored version of that, and not use the CPU's copy.
- If the guest is running in vEL1, and we access an EL2 sysreg, we must
  also use the stored version, since the CPU carries the EL1 copy.
- Some EL2 system registers are supposed to affect the current execution
  of the system, so we need to put them into their respective EL1
  counterparts. For this we need to define a mapping between the two.
  This is done using the newly introduced struct el2_sysreg_map.
- Some EL2 system registers have a different format than their EL1
  counterpart, so we need to translate them before writing them to the
  CPU. This is done using an (optional) translate function in the map.
- There are the three special registers SP_EL2, SPSR_EL2 and ELR_EL2,
  which need some separate handling (SPSR_EL2 is being handled in a
  separate patch).

All of these cases are now wrapped into the existing accessor functions,
so KVM users wouldn't need to care whether they access EL2 or EL1
registers and also which state the guest is in.

This handles what was formerly known as the "shadow state" dynamically,
without requiring a separate copy for each vCPU EL.

Co-developed-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/sys_regs.c | 144 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 140 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index cc7a86624e36..d5a855cb65ca 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -23,6 +23,7 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_nested.h>
 #include <asm/perf_event.h>
 #include <asm/sysreg.h>
 
@@ -63,23 +64,158 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu,
 	return false;
 }
 
+#define PURE_EL2_SYSREG(el2)						\
+	case el2: {							\
+		*el1r = el2;						\
+		return true;						\
+	}
+
+#define MAPPED_EL2_SYSREG(el2, el1, fn)					\
+	case el2: {							\
+		*xlate = fn;						\
+		*el1r = el1;						\
+		return true;						\
+	}
+
+static bool get_el2_mapping(unsigned int reg,
+			    unsigned int *el1r, u64 (**xlate)(u64))
+{
+	switch (reg) {
+		PURE_EL2_SYSREG(  VPIDR_EL2	);
+		PURE_EL2_SYSREG(  VMPIDR_EL2	);
+		PURE_EL2_SYSREG(  ACTLR_EL2	);
+		PURE_EL2_SYSREG(  HCR_EL2	);
+		PURE_EL2_SYSREG(  MDCR_EL2	);
+		PURE_EL2_SYSREG(  HSTR_EL2	);
+		PURE_EL2_SYSREG(  HACR_EL2	);
+		PURE_EL2_SYSREG(  VTTBR_EL2	);
+		PURE_EL2_SYSREG(  VTCR_EL2	);
+		PURE_EL2_SYSREG(  RVBAR_EL2	);
+		PURE_EL2_SYSREG(  RMR_EL2	);
+		PURE_EL2_SYSREG(  TPIDR_EL2	);
+		PURE_EL2_SYSREG(  HPFAR_EL2	);
+		PURE_EL2_SYSREG(  ELR_EL2	);
+		PURE_EL2_SYSREG(  SPSR_EL2	);
+		MAPPED_EL2_SYSREG(SCTLR_EL2,   SCTLR_EL1,
+				  translate_sctlr_el2_to_sctlr_el1	     );
+		MAPPED_EL2_SYSREG(CPTR_EL2,    CPACR_EL1,
+				  translate_cptr_el2_to_cpacr_el1	     );
+		MAPPED_EL2_SYSREG(TTBR0_EL2,   TTBR0_EL1,
+				  translate_ttbr0_el2_to_ttbr0_el1	     );
+		MAPPED_EL2_SYSREG(TTBR1_EL2,   TTBR1_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(TCR_EL2,     TCR_EL1,
+				  translate_tcr_el2_to_tcr_el1		     );
+		MAPPED_EL2_SYSREG(VBAR_EL2,    VBAR_EL1,    NULL	     );
+		MAPPED_EL2_SYSREG(AFSR0_EL2,   AFSR0_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(AFSR1_EL2,   AFSR1_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(ESR_EL2,     ESR_EL1,     NULL	     );
+		MAPPED_EL2_SYSREG(FAR_EL2,     FAR_EL1,     NULL	     );
+		MAPPED_EL2_SYSREG(MAIR_EL2,    MAIR_EL1,    NULL	     );
+		MAPPED_EL2_SYSREG(AMAIR_EL2,   AMAIR_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(CNTHCTL_EL2, CNTKCTL_EL1,
+				  translate_cnthctl_el2_to_cntkctl_el1	     );
+	default:
+		return false;
+	}
+}
+
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 {
 	u64 val = 0x8badf00d8badf00d;
+	u64 (*xlate)(u64) = NULL;
+	unsigned int el1r;
+
+	if (!vcpu->arch.sysregs_loaded_on_cpu)
+		goto memory_read;
+
+	if (unlikely(get_el2_mapping(reg, &el1r, &xlate))) {
+		if (!is_hyp_ctxt(vcpu))
+			goto memory_read;
+
+		/*
+		 * ELR_EL2 is special cased for now.
+		 */
+		switch (reg) {
+		case ELR_EL2:
+			return read_sysreg_el1(SYS_ELR);
+		}
+
+		/*
+		 * If this register does not have an EL1 counterpart,
+		 * then read the stored EL2 version.
+		 */
+		if (reg == el1r)
+			goto memory_read;
+
+		/*
+		 * If we have a non-VHE guest and that the sysreg
+		 * requires translation to be used at EL1, use the
+		 * in-memory copy instead.
+		 */
+		if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
+			goto memory_read;
+
+		/* Get the current version of the EL1 counterpart. */
+		WARN_ON(!__vcpu_read_sys_reg_from_cpu(el1r, &val));
+		return val;
+	}
+
+	/* EL1 register can't be on the CPU if the guest is in vEL2. */
+	if (unlikely(is_hyp_ctxt(vcpu)))
+		goto memory_read;
 
-	if (vcpu->arch.sysregs_loaded_on_cpu &&
-	    __vcpu_read_sys_reg_from_cpu(reg, &val))
+	if (__vcpu_read_sys_reg_from_cpu(reg, &val))
 		return val;
 
+memory_read:
 	return __vcpu_sys_reg(vcpu, reg);
 }
 
 void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 {
-	if (vcpu->arch.sysregs_loaded_on_cpu &&
-	    __vcpu_write_sys_reg_to_cpu(val, reg))
+	u64 (*xlate)(u64) = NULL;
+	unsigned int el1r;
+
+	if (!vcpu->arch.sysregs_loaded_on_cpu)
+		goto memory_write;
+
+	if (unlikely(get_el2_mapping(reg, &el1r, &xlate))) {
+		if (!is_hyp_ctxt(vcpu))
+			goto memory_write;
+
+		/*
+		 * Always store a copy of the write to memory to avoid having
+		 * to reverse-translate virtual EL2 system registers for a
+		 * non-VHE guest hypervisor.
+		 */
+		__vcpu_sys_reg(vcpu, reg) = val;
+
+		switch (reg) {
+		case ELR_EL2:
+			write_sysreg_el1(val, SYS_ELR);
+			return;
+		}
+
+		/* No EL1 counterpart? We're done here.? */
+		if (reg == el1r)
+			return;
+
+		if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
+			val = xlate(val);
+
+		/* Redirect this to the EL1 version of the register. */
+		WARN_ON(!__vcpu_write_sys_reg_to_cpu(val, el1r));
+		return;
+	}
+
+	/* EL1 register can't be on the CPU if the guest is in vEL2. */
+	if (unlikely(is_hyp_ctxt(vcpu)))
+		goto memory_write;
+
+	if (__vcpu_write_sys_reg_to_cpu(val, reg))
 		return;
 
+memory_write:
 	 __vcpu_sys_reg(vcpu, reg) = val;
 }
 
-- 
2.29.2

[PATCH v3 14/66] KVM: arm64: nv: Handle SPSR_EL2 specially

[Marc Zyngier]

SPSR_EL2 needs special attention when running nested on ARMv8.3:

If taking an exception while running at vEL2 (actually EL1), the
HW will update the SPSR_EL1 register with the EL1 mode. We need
to track this in order to make sure that accesses to the virtual
view of SPSR_EL2 is correct.

To do so, we place an illegal value in SPSR_EL1.M, and patch it
accordingly if required when accessing it.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h | 37 ++++++++++++++++++++++++++++
 arch/arm64/kvm/sys_regs.c            | 23 +++++++++++++++--
 2 files changed, 58 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index deffd3cc4443..5c7dc659e8c4 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -238,6 +238,43 @@ static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu)
 	return __is_hyp_ctxt(&vcpu->arch.ctxt);
 }
 
+static inline u64 __fixup_spsr_el2_write(struct kvm_cpu_context *ctxt, u64 val)
+{
+	if (!__vcpu_el2_e2h_is_set(ctxt)) {
+		/*
+		 * Clear the .M field when writing SPSR to the CPU, so that we
+		 * can detect when the CPU clobbered our SPSR copy during a
+		 * local exception.
+		 */
+		val &= ~0xc;
+	}
+
+	return val;
+}
+
+static inline u64 __fixup_spsr_el2_read(const struct kvm_cpu_context *ctxt, u64 val)
+{
+	if (__vcpu_el2_e2h_is_set(ctxt))
+		return val;
+
+	/*
+	 * SPSR.M == 0 means the CPU has not touched the SPSR, so the
+	 * register has still the value we saved on the last write.
+	 */
+	if ((val & 0xc) == 0)
+		return ctxt_sys_reg(ctxt, SPSR_EL2);
+
+	/*
+	 * Otherwise there was a "local" exception on the CPU,
+	 * which from the guest's point of view was being taken from
+	 * EL2 to EL2, although it actually happened to be from
+	 * EL1 to EL1.
+	 * So we need to fix the .M field in SPSR, to make it look
+	 * like EL2, which is what the guest would expect.
+	 */
+	return (val & ~0x0c) | CurrentEL_EL2;
+}
+
 /*
  * The layout of SPSR for an AArch32 state is different when observed from an
  * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index d5a855cb65ca..77a2d452b79d 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -133,11 +133,14 @@ u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 			goto memory_read;
 
 		/*
-		 * ELR_EL2 is special cased for now.
+		 * ELR_EL2 and SPSR_EL2 are special cased for now.
 		 */
 		switch (reg) {
 		case ELR_EL2:
 			return read_sysreg_el1(SYS_ELR);
+		case SPSR_EL2:
+			val = read_sysreg_el1(SYS_SPSR);
+			return __fixup_spsr_el2_read(&vcpu->arch.ctxt, val);
 		}
 
 		/*
@@ -194,6 +197,10 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 		case ELR_EL2:
 			write_sysreg_el1(val, SYS_ELR);
 			return;
+		case SPSR_EL2:
+			val = __fixup_spsr_el2_write(&vcpu->arch.ctxt, val);
+			write_sysreg_el1(val, SYS_SPSR);
+			return;
 		}
 
 		/* No EL1 counterpart? We're done here.? */
@@ -1527,6 +1534,18 @@ static bool access_sp_el1(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_spsr_el2(struct kvm_vcpu *vcpu,
+			    struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		vcpu_write_sys_reg(vcpu, p->regval, SPSR_EL2);
+	else
+		p->regval = vcpu_read_sys_reg(vcpu, SPSR_EL2);
+
+	return true;
+}
+
 /*
  * Architected system registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
@@ -1923,7 +1942,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_VTCR_EL2), access_rw, reset_val, VTCR_EL2, 0 },
 
 	{ SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 },
-	{ SYS_DESC(SYS_SPSR_EL2), access_rw, reset_val, SPSR_EL2, 0 },
+	{ SYS_DESC(SYS_SPSR_EL2), access_spsr_el2, reset_val, SPSR_EL2, 0 },
 	{ SYS_DESC(SYS_ELR_EL2), access_rw, reset_val, ELR_EL2, 0 },
 	{ SYS_DESC(SYS_SP_EL1), access_sp_el1},
 
-- 
2.29.2

[PATCH v3 15/66] KVM: arm64: nv: Handle HCR_EL2.E2H specially

[Marc Zyngier]

HCR_EL2.E2H is nasty, as a flip of this bit completely changes the way
we deal with a lot of the state. So when the guest flips this bit
(sysregs are live), do the put/load dance so that we have a consistent
state.

Yes, this is slow. Don't do it.

Suggested-by: Alexandru Elisei <alexandru.elisei@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/sys_regs.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 77a2d452b79d..e7db4d809674 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -183,9 +183,24 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 		goto memory_write;
 
 	if (unlikely(get_el2_mapping(reg, &el1r, &xlate))) {
+		bool need_put_load;
+
 		if (!is_hyp_ctxt(vcpu))
 			goto memory_write;
 
+		/*
+		 * HCR_EL2.E2H is nasty: it changes the way we interpret a
+		 * lot of the EL2 state, so treat is as a full state
+		 * transition.
+		 */
+		need_put_load = ((reg == HCR_EL2) &&
+				 vcpu_el2_e2h_is_set(vcpu) != !!(val & HCR_E2H));
+
+		if (need_put_load) {
+			preempt_disable();
+			kvm_arch_vcpu_put(vcpu);
+		}
+
 		/*
 		 * Always store a copy of the write to memory to avoid having
 		 * to reverse-translate virtual EL2 system registers for a
@@ -193,6 +208,11 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 		 */
 		__vcpu_sys_reg(vcpu, reg) = val;
 
+		if (need_put_load) {
+			kvm_arch_vcpu_load(vcpu, smp_processor_id());
+			preempt_enable();
+		}
+
 		switch (reg) {
 		case ELR_EL2:
 			write_sysreg_el1(val, SYS_ELR);
-- 
2.29.2

[PATCH v3 16/66] KVM: arm64: nv: Save/Restore vEL2 sysregs

[Marc Zyngier]

Whenever we need to restore the guest's system registers to the CPU, we
now need to take care of the EL2 system registers as well. Most of them
are accessed via traps only, but some have an immediate effect and also
a guest running in VHE mode would expect them to be accessible via their
EL1 encoding, which we do not trap.

For vEL2 we write the virtual EL2 registers with an identical format directly
into their EL1 counterpart, and translate the few registers that have a
different format for the same effect on the execution when running a
non-VHE guest guest hypervisor.

Based on an initial patch from Andre Przywara, rewritten many times
since.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h |   5 +-
 arch/arm64/kvm/hyp/nvhe/sysreg-sr.c        |   2 +-
 arch/arm64/kvm/hyp/vhe/sysreg-sr.c         | 125 ++++++++++++++++++++-
 3 files changed, 127 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index cce43bfe158f..e3901c73893e 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -71,9 +71,10 @@ static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt_sys_reg(ctxt, TPIDRRO_EL0),	tpidrro_el0);
 }
 
-static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt,
+					      u64 mpidr)
 {
-	write_sysreg(ctxt_sys_reg(ctxt, MPIDR_EL1),	vmpidr_el2);
+	write_sysreg(mpidr,				vmpidr_el2);
 	write_sysreg(ctxt_sys_reg(ctxt, CSSELR_EL1),	csselr_el1);
 
 	if (has_vhe() ||
diff --git a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
index 29305022bc04..dba101565de3 100644
--- a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
@@ -28,7 +28,7 @@ void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
 
 void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
 {
-	__sysreg_restore_el1_state(ctxt);
+	__sysreg_restore_el1_state(ctxt, ctxt_sys_reg(ctxt, MPIDR_EL1));
 	__sysreg_restore_common_state(ctxt);
 	__sysreg_restore_user_state(ctxt);
 	__sysreg_restore_el2_return_state(ctxt);
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
index 2a0b8c88d74f..53835fcc0ac6 100644
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -13,6 +13,96 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
+#include <asm/kvm_nested.h>
+
+static void __sysreg_save_vel2_state(struct kvm_cpu_context *ctxt)
+{
+	/* These registers are common with EL1 */
+	ctxt_sys_reg(ctxt, CSSELR_EL1)	= read_sysreg(csselr_el1);
+	ctxt_sys_reg(ctxt, PAR_EL1)	= read_sysreg(par_el1);
+	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
+
+	ctxt_sys_reg(ctxt, ESR_EL2)	= read_sysreg_el1(SYS_ESR);
+	ctxt_sys_reg(ctxt, AFSR0_EL2)	= read_sysreg_el1(SYS_AFSR0);
+	ctxt_sys_reg(ctxt, AFSR1_EL2)	= read_sysreg_el1(SYS_AFSR1);
+	ctxt_sys_reg(ctxt, FAR_EL2)	= read_sysreg_el1(SYS_FAR);
+	ctxt_sys_reg(ctxt, MAIR_EL2)	= read_sysreg_el1(SYS_MAIR);
+	ctxt_sys_reg(ctxt, VBAR_EL2)	= read_sysreg_el1(SYS_VBAR);
+	ctxt_sys_reg(ctxt, CONTEXTIDR_EL2) = read_sysreg_el1(SYS_CONTEXTIDR);
+	ctxt_sys_reg(ctxt, AMAIR_EL2)	= read_sysreg_el1(SYS_AMAIR);
+
+	/*
+	 * In VHE mode those registers are compatible between EL1 and EL2,
+	 * and the guest uses the _EL1 versions on the CPU naturally.
+	 * So we save them into their _EL2 versions here.
+	 * For nVHE mode we trap accesses to those registers, so our
+	 * _EL2 copy in sys_regs[] is always up-to-date and we don't need
+	 * to save anything here.
+	 */
+	if (__vcpu_el2_e2h_is_set(ctxt)) {
+		ctxt_sys_reg(ctxt, SCTLR_EL2)	= read_sysreg_el1(SYS_SCTLR);
+		ctxt_sys_reg(ctxt, CPTR_EL2)	= read_sysreg_el1(SYS_CPACR);
+		ctxt_sys_reg(ctxt, TTBR0_EL2)	= read_sysreg_el1(SYS_TTBR0);
+		ctxt_sys_reg(ctxt, TTBR1_EL2)	= read_sysreg_el1(SYS_TTBR1);
+		ctxt_sys_reg(ctxt, TCR_EL2)	= read_sysreg_el1(SYS_TCR);
+		ctxt_sys_reg(ctxt, CNTHCTL_EL2)	= read_sysreg_el1(SYS_CNTKCTL);
+	}
+
+	ctxt_sys_reg(ctxt, SP_EL2)	= read_sysreg(sp_el1);
+	ctxt_sys_reg(ctxt, ELR_EL2)	= read_sysreg_el1(SYS_ELR);
+	ctxt_sys_reg(ctxt, SPSR_EL2)	= __fixup_spsr_el2_read(ctxt, read_sysreg_el1(SYS_SPSR));
+}
+
+static void __sysreg_restore_vel2_state(struct kvm_cpu_context *ctxt)
+{
+	u64 val;
+
+	/* These registers are common with EL1 */
+	write_sysreg(ctxt_sys_reg(ctxt, CSSELR_EL1),	csselr_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1),	par_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1),	tpidr_el1);
+
+	write_sysreg(read_cpuid_id(),			vpidr_el2);
+	write_sysreg(ctxt_sys_reg(ctxt, MPIDR_EL1),	vmpidr_el2);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, MAIR_EL2),	SYS_MAIR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, VBAR_EL2),	SYS_VBAR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, CONTEXTIDR_EL2),SYS_CONTEXTIDR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AMAIR_EL2),	SYS_AMAIR);
+
+	if (__vcpu_el2_e2h_is_set(ctxt)) {
+		/*
+		 * In VHE mode those registers are compatible between
+		 * EL1 and EL2.
+		 */
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL2),	SYS_SCTLR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, CPTR_EL2),	SYS_CPACR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR0_EL2),	SYS_TTBR0);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR1_EL2),	SYS_TTBR1);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL2),	SYS_TCR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, CNTHCTL_EL2), SYS_CNTKCTL);
+	} else {
+		val = translate_sctlr_el2_to_sctlr_el1(ctxt_sys_reg(ctxt, SCTLR_EL2));
+		write_sysreg_el1(val, SYS_SCTLR);
+		val = translate_cptr_el2_to_cpacr_el1(ctxt_sys_reg(ctxt, CPTR_EL2));
+		write_sysreg_el1(val, SYS_CPACR);
+		val = translate_ttbr0_el2_to_ttbr0_el1(ctxt_sys_reg(ctxt, TTBR0_EL2));
+		write_sysreg_el1(val, SYS_TTBR0);
+		val = translate_tcr_el2_to_tcr_el1(ctxt_sys_reg(ctxt, TCR_EL2));
+		write_sysreg_el1(val, SYS_TCR);
+		val = translate_cnthctl_el2_to_cntkctl_el1(ctxt_sys_reg(ctxt, CNTHCTL_EL2));
+		write_sysreg_el1(val, SYS_CNTKCTL);
+	}
+
+	write_sysreg_el1(ctxt_sys_reg(ctxt, ESR_EL2),	SYS_ESR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR0_EL2),	SYS_AFSR0);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR1_EL2),	SYS_AFSR1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, FAR_EL2),	SYS_FAR);
+	write_sysreg(ctxt_sys_reg(ctxt, SP_EL2),	sp_el1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL2),	SYS_ELR);
+
+	val = __fixup_spsr_el2_write(ctxt, ctxt_sys_reg(ctxt, SPSR_EL2));
+	write_sysreg_el1(val,	SYS_SPSR);
+}
 
 /*
  * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
@@ -65,6 +155,7 @@ void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
 	struct kvm_cpu_context *host_ctxt;
+	u64 mpidr;
 
 	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
 	__sysreg_save_user_state(host_ctxt);
@@ -77,7 +168,29 @@ void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu)
 	 */
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_user_state(guest_ctxt);
-	__sysreg_restore_el1_state(guest_ctxt);
+
+	if (unlikely(__is_hyp_ctxt(guest_ctxt))) {
+		__sysreg_restore_vel2_state(guest_ctxt);
+	} else {
+		if (nested_virt_in_use(vcpu)) {
+			/*
+			 * Only set VPIDR_EL2 for nested VMs, as this is the
+			 * only time it changes. We'll restore the MIDR_EL1
+			 * view on put.
+			 */
+			write_sysreg(ctxt_sys_reg(guest_ctxt, VPIDR_EL2), vpidr_el2);
+
+			/*
+			 * As we're restoring a nested guest, set the value
+			 * provided by the guest hypervisor.
+			 */
+			mpidr = ctxt_sys_reg(guest_ctxt, VMPIDR_EL2);
+		} else {
+			mpidr = ctxt_sys_reg(guest_ctxt, MPIDR_EL1);
+		}
+
+		__sysreg_restore_el1_state(guest_ctxt, mpidr);
+	}
 
 	vcpu->arch.sysregs_loaded_on_cpu = true;
 
@@ -103,12 +216,20 @@ void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu)
 	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
 	deactivate_traps_vhe_put();
 
-	__sysreg_save_el1_state(guest_ctxt);
+	if (unlikely(__is_hyp_ctxt(guest_ctxt)))
+		__sysreg_save_vel2_state(guest_ctxt);
+	else
+		__sysreg_save_el1_state(guest_ctxt);
+
 	__sysreg_save_user_state(guest_ctxt);
 	__sysreg32_save_state(vcpu);
 
 	/* Restore host user state */
 	__sysreg_restore_user_state(host_ctxt);
 
+	/* If leaving a nesting guest, restore MPIDR_EL1 default view */
+	if (nested_virt_in_use(vcpu))
+		write_sysreg(read_cpuid_id(),	vpidr_el2);
+
 	vcpu->arch.sysregs_loaded_on_cpu = false;
 }
-- 
2.29.2

[PATCH v3 17/66] KVM: arm64: nv: Emulate PSTATE.M for a guest hypervisor

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@arm.com>

We can no longer blindly copy the VCPU's PSTATE into SPSR_EL2 and return
to the guest and vice versa when taking an exception to the hypervisor,
because we emulate virtual EL2 in EL1 and therefore have to translate
the mode field from EL2 to EL1 and vice versa.

Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 43 +++++++++++++++++++++-
 1 file changed, 41 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index e3901c73893e..92715fa01e88 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -51,10 +51,32 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, SPSR_EL1)	= read_sysreg_el1(SYS_SPSR);
 }
 
+static inline u64 from_hw_pstate(const struct kvm_cpu_context *ctxt)
+{
+	u64 reg = read_sysreg_el2(SYS_SPSR);
+
+	if (__is_hyp_ctxt(ctxt)) {
+		u64 mode = reg & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+		switch (mode) {
+		case PSR_MODE_EL1t:
+			mode = PSR_MODE_EL2t;
+			break;
+		case PSR_MODE_EL1h:
+			mode = PSR_MODE_EL2h;
+			break;
+		}
+
+		return (reg & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode;
+	}
+
+	return reg;
+}
+
 static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->regs.pc			= read_sysreg_el2(SYS_ELR);
-	ctxt->regs.pstate		= read_sysreg_el2(SYS_SPSR);
+	ctxt->regs.pstate		= from_hw_pstate(ctxt);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
 		ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2);
@@ -131,9 +153,26 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt,
 	write_sysreg_el1(ctxt_sys_reg(ctxt, SPSR_EL1),	SYS_SPSR);
 }
 
+/* Read the VCPU state's PSTATE, but translate (v)EL2 to EL1. */
+static inline u64 to_hw_pstate(const struct kvm_cpu_context *ctxt)
+{
+	u64 mode = ctxt->regs.pstate & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+	switch (mode) {
+	case PSR_MODE_EL2t:
+		mode = PSR_MODE_EL1t;
+		break;
+	case PSR_MODE_EL2h:
+		mode = PSR_MODE_EL1h;
+		break;
+	}
+
+	return (ctxt->regs.pstate & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode;
+}
+
 static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
 {
-	u64 pstate = ctxt->regs.pstate;
+	u64 pstate = to_hw_pstate(ctxt);
 	u64 mode = pstate & PSR_AA32_MODE_MASK;
 
 	/*
-- 
2.29.2

[PATCH v3 18/66] KVM: arm64: nv: Trap EL1 VM register accesses in virtual EL2

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@linaro.org>

When running in virtual EL2 mode, we actually run the hardware in EL1
and therefore have to use the EL1 registers to ensure correct operation.

By setting the HCR.TVM and HCR.TVRM we ensure that the virtual EL2 mode
doesn't shoot itself in the foot when setting up what it believes to be
a different mode's system register state (for example when preparing to
switch to a VM).

We can leverage the existing sysregs infrastructure to support trapped
accesses to these registers.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/switch.h |  4 +---
 arch/arm64/kvm/hyp/nvhe/switch.c        |  2 +-
 arch/arm64/kvm/hyp/vhe/switch.c         |  7 ++++++-
 arch/arm64/kvm/sys_regs.c               | 19 ++++++++++++++++---
 4 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 84473574c2e7..424b074e4377 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -101,10 +101,8 @@ static inline void __deactivate_traps_common(void)
 	write_sysreg(0, pmuserenr_el0);
 }
 
-static inline void ___activate_traps(struct kvm_vcpu *vcpu)
+static inline void ___activate_traps(struct kvm_vcpu *vcpu, u64 hcr)
 {
-	u64 hcr = vcpu->arch.hcr_el2;
-
 	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
 		hcr |= HCR_TVM;
 
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index f3d0e9eca56c..07bf5c03631b 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -37,7 +37,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
 
-	___activate_traps(vcpu);
+	___activate_traps(vcpu, vcpu->arch.hcr_el2);
 	__activate_traps_common(vcpu);
 
 	val = CPTR_EL2_DEFAULT;
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index af8e940d0f03..3d8a4402b52c 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -36,9 +36,14 @@ DEFINE_PER_CPU(unsigned long, kvm_hyp_vector);
 
 static void __activate_traps(struct kvm_vcpu *vcpu)
 {
+	u64 hcr = vcpu->arch.hcr_el2;
 	u64 val;
 
-	___activate_traps(vcpu);
+	/* Trap VM sysreg accesses if an EL2 guest is not using VHE. */
+	if (vcpu_mode_el2(vcpu) && !vcpu_el2_e2h_is_set(vcpu))
+		hcr |= HCR_TVM | HCR_TRVM;
+
+	___activate_traps(vcpu, hcr);
 
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_EL1_TTA;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e7db4d809674..540a7faaaee3 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -361,8 +361,15 @@ static void get_access_mask(const struct sys_reg_desc *r, u64 *mask, u64 *shift)
 
 /*
  * Generic accessor for VM registers. Only called as long as HCR_TVM
- * is set. If the guest enables the MMU, we stop trapping the VM
- * sys_regs and leave it in complete control of the caches.
+ * is set.
+ *
+ * This is set in two cases: either (1) we're running at vEL2, or (2)
+ * we're running at EL1 and the guest has its MMU off.
+ *
+ * (1) TVM/TRVM is set, as we need to virtualise some of the VM
+ * registers for the guest hypervisor
+ * (2) Once the guest enables the MMU, we stop trapping the VM sys_regs
+ * and leave it in complete control of the caches.
  */
 static bool access_vm_reg(struct kvm_vcpu *vcpu,
 			  struct sys_reg_params *p,
@@ -371,7 +378,13 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
 	bool was_enabled = vcpu_has_cache_enabled(vcpu);
 	u64 val, mask, shift;
 
-	BUG_ON(!p->is_write);
+	/* We don't expect TRVM on the host */
+	BUG_ON(!vcpu_mode_el2(vcpu) && !p->is_write);
+
+	if (!p->is_write) {
+		p->regval = vcpu_read_sys_reg(vcpu, r->reg);
+		return true;
+	}
 
 	get_access_mask(r, &mask, &shift);
 
-- 
2.29.2

[PATCH v3 19/66] KVM: arm64: nv: Trap SPSR_EL1, ELR_EL1 and VBAR_EL1 from virtual EL2

[Marc Zyngier]

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

For the same reason we trap virtual memory register accesses at virtual
EL2, we need to trap SPSR_EL1, ELR_EL1 and VBAR_EL1 accesses. ARM v8.3
introduces the HCR_EL2.NV1 bit to be able to trap on those register
accesses in EL1. Do not set this bit until the whole nesting support is
completed.

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/sys_regs.c | 29 ++++++++++++++++++++++++++++-
 1 file changed, 28 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 540a7faaaee3..5185f148f25e 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1567,6 +1567,30 @@ static bool access_sp_el1(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_elr(struct kvm_vcpu *vcpu,
+		       struct sys_reg_params *p,
+		       const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		vcpu_write_sys_reg(vcpu, p->regval, ELR_EL1);
+	else
+		p->regval = vcpu_read_sys_reg(vcpu, ELR_EL1);
+
+	return true;
+}
+
+static bool access_spsr(struct kvm_vcpu *vcpu,
+			struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		__vcpu_sys_reg(vcpu, SPSR_EL1) = p->regval;
+	else
+		p->regval = __vcpu_sys_reg(vcpu, SPSR_EL1);
+
+	return true;
+}
+
 static bool access_spsr_el2(struct kvm_vcpu *vcpu,
 			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *r)
@@ -1728,6 +1752,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	PTRAUTH_KEY(APDB),
 	PTRAUTH_KEY(APGA),
 
+	{ SYS_DESC(SYS_SPSR_EL1), access_spsr},
+	{ SYS_DESC(SYS_ELR_EL1), access_elr},
+
 	{ SYS_DESC(SYS_AFSR0_EL1), access_vm_reg, reset_unknown, AFSR0_EL1 },
 	{ SYS_DESC(SYS_AFSR1_EL1), access_vm_reg, reset_unknown, AFSR1_EL1 },
 	{ SYS_DESC(SYS_ESR_EL1), access_vm_reg, reset_unknown, ESR_EL1 },
@@ -1759,7 +1786,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_LORC_EL1), trap_loregion },
 	{ SYS_DESC(SYS_LORID_EL1), trap_loregion },
 
-	{ SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 },
+	{ SYS_DESC(SYS_VBAR_EL1), access_rw, reset_val, VBAR_EL1, 0 },
 	{ SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 },
 
 	{ SYS_DESC(SYS_ICC_IAR0_EL1), write_to_read_only },
-- 
2.29.2

[PATCH v3 20/66] KVM: arm64: nv: Trap CPACR_EL1 access in virtual EL2

[Marc Zyngier]

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

For the same reason we trap virtual memory register accesses in virtual
EL2, we trap CPACR_EL1 access too; We allow the virtual EL2 mode to
access EL1 system register state instead of the virtual EL2 one.

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_arm.h | 2 +-
 arch/arm64/kvm/hyp/vhe/switch.c  | 3 +++
 arch/arm64/kvm/sys_regs.c        | 2 +-
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 4cf745f79985..3bd29fd01d80 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -269,7 +269,7 @@
 #define CPTR_EL2_TFP_SHIFT 10
 
 /* Hyp Coprocessor Trap Register */
-#define CPTR_EL2_TCPAC	(1 << 31)
+#define CPTR_EL2_TCPAC	(1U << 31)
 #define CPTR_EL2_TAM	(1 << 30)
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 3d8a4402b52c..66358f8ec5ad 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -68,6 +68,9 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		__activate_traps_fpsimd32(vcpu);
 	}
 
+	if (vcpu_mode_el2(vcpu) && !vcpu_el2_e2h_is_set(vcpu))
+		val |= CPTR_EL2_TCPAC;
+	
 	write_sysreg(val, cpacr_el1);
 
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 5185f148f25e..4410d399f8e2 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1736,7 +1736,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_SCTLR_EL1), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
 	{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
-	{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
+	{ SYS_DESC(SYS_CPACR_EL1), access_rw, reset_val, CPACR_EL1, 0 },
 
 	{ SYS_DESC(SYS_RGSR_EL1), undef_access },
 	{ SYS_DESC(SYS_GCR_EL1), undef_access },
-- 
2.29.2

[PATCH v3 21/66] KVM: arm64: nv: Handle PSCI call via smc from the guest

[Marc Zyngier]

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

VMs used to execute hvc #0 for the psci call if EL3 is not implemented.
However, when we come to provide the virtual EL2 mode to the VM, the
host OS inside the VM calls kvm_call_hyp() which is also hvc #0. So,
it's hard to differentiate between them from the host hypervisor's point
of view.

So, let the VM execute smc instruction for the psci call. On ARMv8.3,
even if EL3 is not implemented, a smc instruction executed at non-secure
EL1 is trapped to EL2 if HCR_EL2.TSC==1, rather than being treated as
UNDEFINED. So, the host hypervisor can handle this psci call without any
confusion.

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/handle_exit.c | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 56f8a77b9d4a..fe1dc0551991 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -62,6 +62,8 @@ static int handle_hvc(struct kvm_vcpu *vcpu)
 
 static int handle_smc(struct kvm_vcpu *vcpu)
 {
+	int ret;
+
 	/*
 	 * "If an SMC instruction executed at Non-secure EL1 is
 	 * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a
@@ -69,10 +71,28 @@ static int handle_smc(struct kvm_vcpu *vcpu)
 	 *
 	 * We need to advance the PC after the trap, as it would
 	 * otherwise return to the same address...
+	 *
+	 * If imm is non-zero, it's not defined, so just skip it.
+	 */
+	if (kvm_vcpu_hvc_get_imm(vcpu)) {
+		vcpu_set_reg(vcpu, 0, ~0UL);
+		kvm_incr_pc(vcpu);
+		return 1;
+	}
+
+	/*
+	 * If imm is zero, it's a psci call.
+	 * Note that on ARMv8.3, even if EL3 is not implemented, SMC executed
+	 * at Non-secure EL1 is trapped to EL2 if HCR_EL2.TSC==1, rather than
+	 * being treated as UNDEFINED.
 	 */
-	vcpu_set_reg(vcpu, 0, ~0UL);
+	ret = kvm_hvc_call_handler(vcpu);
+	if (ret < 0)
+		vcpu_set_reg(vcpu, 0, ~0UL);
+
 	kvm_incr_pc(vcpu);
-	return 1;
+
+	return ret;
 }
 
 /*
-- 
2.29.2

[PATCH v3 22/66] 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_nested.h |  2 ++
 arch/arm64/kvm/Makefile             |  2 +-
 arch/arm64/kvm/handle_exit.c        | 11 +++++++-
 arch/arm64/kvm/nested.c             | 40 +++++++++++++++++++++++++++++
 4 files changed, 53 insertions(+), 2 deletions(-)
 create mode 100644 arch/arm64/kvm/nested.c

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 67a2c0d05233..4c2ac9650a3e 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -61,4 +61,6 @@ static inline u64 translate_cnthctl_el2_to_cntkctl_el1(u64 cnthctl)
 		(cnthctl & (CNTHCTL_EVNTI | CNTHCTL_EVNTDIR | CNTHCTL_EVNTEN)));
 }
 
+int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe);
+
 #endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 672acdf1e993..7bb1d1314cad 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -17,7 +17,7 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 guest.o debug.o reset.o sys_regs.o \
 	 vgic-sys-reg-v3.o fpsimd.o pmu.o \
 	 arch_timer.o \
-	 emulate-nested.o \
+	 emulate-nested.o nested.o \
 	 vgic/vgic.o vgic/vgic-init.o \
 	 vgic/vgic-irqfd.o vgic/vgic-v2.o \
 	 vgic/vgic-v3.o vgic/vgic-v4.o \
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index fe1dc0551991..a2437b2380f1 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -119,7 +119,16 @@ static int handle_no_fpsimd(struct kvm_vcpu *vcpu)
  */
 static int kvm_handle_wfx(struct kvm_vcpu *vcpu)
 {
-	if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
+	bool is_wfe = !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_WFx_ISS_WFE);
+
+	if (nested_virt_in_use(vcpu)) {
+		int ret = handle_wfx_nested(vcpu, is_wfe);
+
+		if (ret != -EINVAL)
+			return ret;
+	}
+
+	if (is_wfe) {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
 		vcpu->stat.wfe_exit_stat++;
 		kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
new file mode 100644
index 000000000000..42a96c8d2adc
--- /dev/null
+++ b/arch/arm64/kvm/nested.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 - Columbia University and Linaro Ltd.
+ * Author: Jintack Lim <jintack.lim@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_emulate.h>
+
+/*
+ * Inject wfx to the virtual EL2 if this is not from the virtual EL2 and
+ * the virtual HCR_EL2.TWX is set. Otherwise, let the host hypervisor
+ * handle this.
+ */
+int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe)
+{
+	u64 hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2);
+
+	if (vcpu_mode_el2(vcpu))
+		return -EINVAL;
+
+	if ((is_wfe && (hcr_el2 & HCR_TWE)) || (!is_wfe && (hcr_el2 & HCR_TWI)))
+		return kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
+	return -EINVAL;
+}
-- 
2.29.2

[PATCH v3 23/66] KVM: arm64: nv: Respect virtual CPTR_EL2.{TFP,FPEN} settings

[Marc Zyngier]

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

Forward traps due to FP/ASIMD register accesses to the virtual EL2
if virtual CPTR_EL2.TFP is set (with HCR_EL2.E2H == 0) or
CPTR_EL2.FPEN is configure to do so (with HCR_EL2.E2h == 1).

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
[maz: account for HCR_EL2.E2H when testing for TFP/FPEN, with
 all the hard work actually being done by Chase Conklin]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h    | 26 +++++++++++++++++++++++++
 arch/arm64/kvm/handle_exit.c            | 16 +++++++++++----
 arch/arm64/kvm/hyp/include/hyp/switch.h | 11 +++++++++--
 3 files changed, 47 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 5c7dc659e8c4..a000e6e05091 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -11,12 +11,14 @@
 #ifndef __ARM64_KVM_EMULATE_H__
 #define __ARM64_KVM_EMULATE_H__
 
+#include <linux/bitfield.h>
 #include <linux/kvm_host.h>
 
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_hyp.h>
+#include <asm/kvm_nested.h>
 #include <asm/ptrace.h>
 #include <asm/cputype.h>
 #include <asm/virt.h>
@@ -321,6 +323,30 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 	return mode != PSR_MODE_EL0t;
 }
 
+static inline bool guest_hyp_fpsimd_traps_enabled(const struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	if (!nested_virt_in_use(vcpu))
+		return false;
+
+	val = vcpu_read_sys_reg(vcpu, CPTR_EL2);
+
+	if (!vcpu_el2_e2h_is_set(vcpu))
+		return (val & CPTR_EL2_TFP);
+
+	switch (FIELD_GET(CPACR_EL1_FPEN, val)) {
+	case 0b00:
+	case 0b10:
+		return true;
+	case 0b01:
+		return vcpu_el2_tge_is_set(vcpu) && !vcpu_mode_el2(vcpu);
+	case 0b11:
+	default:		/* GCC is dumb */
+		return false;
+	}
+}
+
 static __always_inline u32 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.fault.esr_el2;
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index a2437b2380f1..5276e8563367 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -96,11 +96,19 @@ static int handle_smc(struct kvm_vcpu *vcpu)
 }
 
 /*
- * Guest access to FP/ASIMD registers are routed to this handler only
- * when the system doesn't support FP/ASIMD.
+ * This handles the cases where the system does not support FP/ASIMD or when
+ * we are running nested virtualization and the guest hypervisor is trapping
+ * FP/ASIMD accesses by its guest guest.
+ *
+ * All other handling of guest vs. host FP/ASIMD register state is handled in
+ * fixup_guest_exit().
  */
-static int handle_no_fpsimd(struct kvm_vcpu *vcpu)
+static int kvm_handle_fpasimd(struct kvm_vcpu *vcpu)
 {
+	if (guest_hyp_fpsimd_traps_enabled(vcpu))
+		return kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
+	/* This is the case when the system doesn't support FP/ASIMD. */
 	kvm_inject_undefined(vcpu);
 	return 1;
 }
@@ -243,7 +251,7 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_BREAKPT_LOW]= kvm_handle_guest_debug,
 	[ESR_ELx_EC_BKPT32]	= kvm_handle_guest_debug,
 	[ESR_ELx_EC_BRK64]	= kvm_handle_guest_debug,
-	[ESR_ELx_EC_FP_ASIMD]	= handle_no_fpsimd,
+	[ESR_ELx_EC_FP_ASIMD]	= kvm_handle_fpasimd,
 	[ESR_ELx_EC_PAC]	= kvm_handle_ptrauth,
 };
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 424b074e4377..e5e201314c87 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -223,11 +223,18 @@ static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 	    esr_ec != ESR_ELx_EC_SVE)
 		return false;
 
-	/* Don't handle SVE traps for non-SVE vcpus here: */
-	if (!sve_guest)
+	/*
+	 * Don't handle SVE traps for non-SVE vcpus here. This
+	 * includes NV guests for the time being.
+	 */
+	if (!sve_guest) {
 		if (esr_ec != ESR_ELx_EC_FP_ASIMD)
 			return false;
 
+		if (guest_hyp_fpsimd_traps_enabled(vcpu))
+			return false;
+	}
+
 	/* Valid trap.  Switch the context: */
 
 	if (vhe) {
-- 
2.29.2

[PATCH v3 24/66] KVM: arm64: nv: Respect the virtual HCR_EL2.NV bit setting

[Marc Zyngier]

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

Forward traps due to HCR_EL2.NV bit to the virtual EL2 if they are not
coming from the virtual EL2 and the virtual HCR_EL2.NV bit is set.

In addition to EL2 register accesses, setting NV bit will also make EL12
register accesses trap to EL2. To emulate this for the virtual EL2,
forword traps due to EL12 register accessses to the virtual EL2 if the
virtual HCR_EL2.NV bit is set.

This is for recursive nested virtualization.

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
[Moved code to emulate-nested.c]
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_arm.h    |  1 +
 arch/arm64/include/asm/kvm_nested.h |  2 ++
 arch/arm64/kvm/emulate-nested.c     | 27 +++++++++++++++++++++++++++
 arch/arm64/kvm/handle_exit.c        |  7 +++++++
 arch/arm64/kvm/sys_regs.c           | 24 ++++++++++++++++++++++++
 5 files changed, 61 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 3bd29fd01d80..c18edb1b35bf 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -14,6 +14,7 @@
 /* Hyp Configuration Register (HCR) bits */
 #define HCR_ATA		(UL(1) << 56)
 #define HCR_FWB		(UL(1) << 46)
+#define HCR_NV		(UL(1) << 42)
 #define HCR_API		(UL(1) << 41)
 #define HCR_APK		(UL(1) << 40)
 #define HCR_TEA		(UL(1) << 37)
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 4c2ac9650a3e..26cba7b4d743 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -62,5 +62,7 @@ static inline u64 translate_cnthctl_el2_to_cntkctl_el1(u64 cnthctl)
 }
 
 int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe);
+extern bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit);
+extern bool forward_nv_traps(struct kvm_vcpu *vcpu);
 
 #endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index ee91bcd925d8..feb9b5eded96 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -25,11 +25,38 @@
 
 #include "trace.h"
 
+bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit)
+{
+	bool control_bit_set;
+
+	if (!nested_virt_in_use(vcpu))
+		return false;
+
+	control_bit_set = __vcpu_sys_reg(vcpu, HCR_EL2) & control_bit;
+	if (!vcpu_mode_el2(vcpu) && control_bit_set) {
+		kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+		return true;
+	}
+	return false;
+}
+
+bool forward_nv_traps(struct kvm_vcpu *vcpu)
+{
+	return forward_traps(vcpu, HCR_NV);
+}
+
 void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 {
 	u64 spsr, elr, mode;
 	bool direct_eret;
 
+	/*
+	 * Forward this trap to the virtual EL2 if the virtual
+	 * HCR_EL2.NV bit is set and this is coming from !EL2.
+	 */
+	if (forward_nv_traps(vcpu))
+		return;
+
 	/*
 	 * Going through the whole put/load motions is a waste of time
 	 * if this is a VHE guest hypervisor returning to its own
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 5276e8563367..0ad20457d0f1 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -64,6 +64,13 @@ static int handle_smc(struct kvm_vcpu *vcpu)
 {
 	int ret;
 
+	/*
+	 * Forward this trapped smc instruction to the virtual EL2 if
+	 * the guest has asked for it.
+	 */
+	if (forward_traps(vcpu, HCR_TSC))
+		return 1;
+
 	/*
 	 * "If an SMC instruction executed at Non-secure EL1 is
 	 * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 4410d399f8e2..8b0be7f0f44d 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -267,10 +267,19 @@ static u32 get_ccsidr(u32 csselr)
 	return ccsidr;
 }
 
+static bool el12_reg(struct sys_reg_params *p)
+{
+	/* All *_EL12 registers have Op1=5. */
+	return (p->Op1 == 5);
+}
+
 static bool access_rw(struct kvm_vcpu *vcpu,
 		      struct sys_reg_params *p,
 		      const struct sys_reg_desc *r)
 {
+	if (el12_reg(p) && forward_nv_traps(vcpu))
+		return false;
+
 	if (p->is_write)
 		vcpu_write_sys_reg(vcpu, p->regval, r->reg);
 	else
@@ -294,6 +303,9 @@ static bool access_sctlr_el2(struct kvm_vcpu *vcpu,
 			     struct sys_reg_params *p,
 			     const struct sys_reg_desc *r)
 {
+	if (el12_reg(p) && forward_nv_traps(vcpu))
+		return false;
+
 	if (p->is_write) {
 		u64 val = p->regval;
 
@@ -378,6 +390,9 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
 	bool was_enabled = vcpu_has_cache_enabled(vcpu);
 	u64 val, mask, shift;
 
+	if (el12_reg(p) && forward_nv_traps(vcpu))
+		return false;
+
 	/* We don't expect TRVM on the host */
 	BUG_ON(!vcpu_mode_el2(vcpu) && !p->is_write);
 
@@ -1571,6 +1586,9 @@ static bool access_elr(struct kvm_vcpu *vcpu,
 		       struct sys_reg_params *p,
 		       const struct sys_reg_desc *r)
 {
+	if (el12_reg(p) && forward_nv_traps(vcpu))
+		return false;
+
 	if (p->is_write)
 		vcpu_write_sys_reg(vcpu, p->regval, ELR_EL1);
 	else
@@ -1583,6 +1601,9 @@ static bool access_spsr(struct kvm_vcpu *vcpu,
 			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
 {
+	if (el12_reg(p) && forward_nv_traps(vcpu))
+		return false;
+
 	if (p->is_write)
 		__vcpu_sys_reg(vcpu, SPSR_EL1) = p->regval;
 	else
@@ -1595,6 +1616,9 @@ static bool access_spsr_el2(struct kvm_vcpu *vcpu,
 			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *r)
 {
+	if (el12_reg(p) && forward_nv_traps(vcpu))
+		return false;
+
 	if (p->is_write)
 		vcpu_write_sys_reg(vcpu, p->regval, SPSR_EL2);
 	else
-- 
2.29.2

[PATCH v3 25/66] KVM: arm64: nv: Respect virtual HCR_EL2.TVM and TRVM settings

[Marc Zyngier]

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

Forward the EL1 virtual memory register traps to the virtual EL2 if they
are not coming from the virtual EL2 and the virtual HCR_EL2.TVM or TRVM
bit is set.

This is for recursive nested virtualization.

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/sys_regs.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 8b0be7f0f44d..d09fda0fd76f 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -393,6 +393,13 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
 	if (el12_reg(p) && forward_nv_traps(vcpu))
 		return false;
 
+	if (!el12_reg(p)) {
+		u64 bit = p->is_write ? HCR_TVM : HCR_TRVM;
+
+		if (forward_traps(vcpu, bit))
+			return false;
+	}
+
 	/* We don't expect TRVM on the host */
 	BUG_ON(!vcpu_mode_el2(vcpu) && !p->is_write);
 
-- 
2.29.2

[PATCH v3 26/66] KVM: arm64: nv: Respect the virtual HCR_EL2.NV1 bit setting

[Marc Zyngier]

From: Jintack Lim <jintack@cs.columbia.edu>

Forward ELR_EL1, SPSR_EL1 and VBAR_EL1 traps to the virtual EL2 if the
virtual HCR_EL2.NV bit is set.

This is for recursive nested virtualization.

Signed-off-by: Jintack Lim <jintack@cs.columbia.edu>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_arm.h |  1 +
 arch/arm64/kvm/sys_regs.c        | 28 +++++++++++++++++++++++++++-
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index c18edb1b35bf..3d2abc40d3a2 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -14,6 +14,7 @@
 /* Hyp Configuration Register (HCR) bits */
 #define HCR_ATA		(UL(1) << 56)
 #define HCR_FWB		(UL(1) << 46)
+#define HCR_NV1		(UL(1) << 43)
 #define HCR_NV		(UL(1) << 42)
 #define HCR_API		(UL(1) << 41)
 #define HCR_APK		(UL(1) << 40)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index d09fda0fd76f..ea511e569ee0 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -299,6 +299,22 @@ static bool access_wi(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+/* This function is to support the recursive nested virtualization */
+static bool forward_nv1_traps(struct kvm_vcpu *vcpu, struct sys_reg_params *p)
+{
+	return forward_traps(vcpu, HCR_NV1);
+}
+
+static bool access_vbar_el1(struct kvm_vcpu *vcpu,
+			    struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	if (forward_nv1_traps(vcpu, p))
+		return false;
+
+	return access_rw(vcpu, p, r);
+}
+
 static bool access_sctlr_el2(struct kvm_vcpu *vcpu,
 			     struct sys_reg_params *p,
 			     const struct sys_reg_desc *r)
@@ -1589,6 +1605,7 @@ static bool access_sp_el1(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+
 static bool access_elr(struct kvm_vcpu *vcpu,
 		       struct sys_reg_params *p,
 		       const struct sys_reg_desc *r)
@@ -1596,6 +1613,9 @@ static bool access_elr(struct kvm_vcpu *vcpu,
 	if (el12_reg(p) && forward_nv_traps(vcpu))
 		return false;
 
+	if (!el12_reg(p) && forward_nv1_traps(vcpu, p))
+		return false;
+
 	if (p->is_write)
 		vcpu_write_sys_reg(vcpu, p->regval, ELR_EL1);
 	else
@@ -1611,6 +1631,9 @@ static bool access_spsr(struct kvm_vcpu *vcpu,
 	if (el12_reg(p) && forward_nv_traps(vcpu))
 		return false;
 
+	if (!el12_reg(p) && forward_nv1_traps(vcpu, p))
+		return false;
+
 	if (p->is_write)
 		__vcpu_sys_reg(vcpu, SPSR_EL1) = p->regval;
 	else
@@ -1626,6 +1649,9 @@ static bool access_spsr_el2(struct kvm_vcpu *vcpu,
 	if (el12_reg(p) && forward_nv_traps(vcpu))
 		return false;
 
+	if (!el12_reg(p) && forward_nv1_traps(vcpu, p))
+		return false;
+
 	if (p->is_write)
 		vcpu_write_sys_reg(vcpu, p->regval, SPSR_EL2);
 	else
@@ -1817,7 +1843,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_LORC_EL1), trap_loregion },
 	{ SYS_DESC(SYS_LORID_EL1), trap_loregion },
 
-	{ SYS_DESC(SYS_VBAR_EL1), access_rw, reset_val, VBAR_EL1, 0 },
+	{ SYS_DESC(SYS_VBAR_EL1), access_vbar_el1, reset_val, VBAR_EL1, 0 },
 	{ SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 },
 
 	{ SYS_DESC(SYS_ICC_IAR0_EL1), write_to_read_only },
-- 
2.29.2

[PATCH v3 27/66] KVM: arm64: nv: Emulate EL12 register accesses from the virtual EL2

[Marc Zyngier]

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

With HCR_EL2.NV bit set, accesses to EL12 registers in the virtual EL2
trap to EL2. Handle those traps just like we do for EL1 registers.

One exception is CNTKCTL_EL12. We don't trap on CNTKCTL_EL1 for non-VHE
virtual EL2 because we don't have to. However, accessing CNTKCTL_EL12
will trap since it's one of the EL12 registers controlled by HCR_EL2.NV
bit.  Therefore, add a handler for it and don't treat it as a
non-trap-registers when preparing a shadow context.

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/sys_regs.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index ea511e569ee0..dc8a33ebad5f 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2085,6 +2085,23 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_CNTVOFF_EL2), access_rw, reset_val, CNTVOFF_EL2, 0 },
 	{ SYS_DESC(SYS_CNTHCTL_EL2), access_rw, reset_val, CNTHCTL_EL2, 0 },
 
+	{ SYS_DESC(SYS_SCTLR_EL12), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
+	{ SYS_DESC(SYS_CPACR_EL12), access_rw, reset_val, CPACR_EL1, 0 },
+	{ SYS_DESC(SYS_TTBR0_EL12), access_vm_reg, reset_unknown, TTBR0_EL1 },
+	{ SYS_DESC(SYS_TTBR1_EL12), access_vm_reg, reset_unknown, TTBR1_EL1 },
+	{ SYS_DESC(SYS_TCR_EL12), access_vm_reg, reset_val, TCR_EL1, 0 },
+	{ SYS_DESC(SYS_SPSR_EL12), access_spsr},
+	{ SYS_DESC(SYS_ELR_EL12), access_elr},
+	{ SYS_DESC(SYS_AFSR0_EL12), access_vm_reg, reset_unknown, AFSR0_EL1 },
+	{ SYS_DESC(SYS_AFSR1_EL12), access_vm_reg, reset_unknown, AFSR1_EL1 },
+	{ SYS_DESC(SYS_ESR_EL12), access_vm_reg, reset_unknown, ESR_EL1 },
+	{ SYS_DESC(SYS_FAR_EL12), access_vm_reg, reset_unknown, FAR_EL1 },
+	{ SYS_DESC(SYS_MAIR_EL12), access_vm_reg, reset_unknown, MAIR_EL1 },
+	{ SYS_DESC(SYS_AMAIR_EL12), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
+	{ SYS_DESC(SYS_VBAR_EL12), access_rw, reset_val, VBAR_EL1, 0 },
+	{ SYS_DESC(SYS_CONTEXTIDR_EL12), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
+	{ SYS_DESC(SYS_CNTKCTL_EL12), access_rw, reset_val, CNTKCTL_EL1, 0 },
+
 	{ SYS_DESC(SYS_SP_EL2), NULL, reset_unknown, SP_EL2 },
 };
 
-- 
2.29.2

[PATCH v3 28/66] KVM: arm64: nv: Forward debug traps to the nested guest

[Marc Zyngier]

On handling a debug trap, check whether we need to forward it to the
guest before handling it.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h | 2 ++
 arch/arm64/kvm/emulate-nested.c     | 9 +++++++--
 arch/arm64/kvm/sys_regs.c           | 3 +++
 3 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 26cba7b4d743..07c15f51cf86 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -62,6 +62,8 @@ static inline u64 translate_cnthctl_el2_to_cntkctl_el1(u64 cnthctl)
 }
 
 int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe);
+extern bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg,
+			    u64 control_bit);
 extern bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit);
 extern bool forward_nv_traps(struct kvm_vcpu *vcpu);
 
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index feb9b5eded96..df4661515183 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -25,14 +25,14 @@
 
 #include "trace.h"
 
-bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit)
+bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg, u64 control_bit)
 {
 	bool control_bit_set;
 
 	if (!nested_virt_in_use(vcpu))
 		return false;
 
-	control_bit_set = __vcpu_sys_reg(vcpu, HCR_EL2) & control_bit;
+	control_bit_set = __vcpu_sys_reg(vcpu, reg) & control_bit;
 	if (!vcpu_mode_el2(vcpu) && control_bit_set) {
 		kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
 		return true;
@@ -40,6 +40,11 @@ bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit)
 	return false;
 }
 
+bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit)
+{
+	return __forward_traps(vcpu, HCR_EL2, control_bit);
+}
+
 bool forward_nv_traps(struct kvm_vcpu *vcpu)
 {
 	return forward_traps(vcpu, HCR_NV);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index dc8a33ebad5f..80cf0c0761b9 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -607,6 +607,9 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu,
 			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *r)
 {
+	if (__forward_traps(vcpu, MDCR_EL2, MDCR_EL2_TDA | MDCR_EL2_TDE))
+		return false;
+
 	access_rw(vcpu, p, r);
 	if (p->is_write)
 		vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
-- 
2.29.2

[PATCH v3 29/66] KVM: arm64: nv: Configure HCR_EL2 for nested virtualization

[Marc Zyngier]

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

We enable nested virtualization by setting the HCR NV and NV1 bit.

When the virtual E2H bit is set, we can support EL2 register accesses
via EL1 registers from the virtual EL2 by doing trap-and-emulate. A
better alternative, however, is to allow the virtual EL2 to access EL2
register states without trap. This can be easily achieved by not traping
EL1 registers since those registers already have EL2 register states.

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/vhe/switch.c | 36 ++++++++++++++++++++++++++++++---
 1 file changed, 33 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 66358f8ec5ad..940d88ffd53e 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -39,9 +39,39 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 	u64 hcr = vcpu->arch.hcr_el2;
 	u64 val;
 
-	/* Trap VM sysreg accesses if an EL2 guest is not using VHE. */
-	if (vcpu_mode_el2(vcpu) && !vcpu_el2_e2h_is_set(vcpu))
-		hcr |= HCR_TVM | HCR_TRVM;
+	if (is_hyp_ctxt(vcpu)) {
+		hcr |= HCR_NV;
+
+		if (!vcpu_el2_e2h_is_set(vcpu)) {
+			/*
+			 * For a guest hypervisor on v8.0, trap and emulate
+			 * the EL1 virtual memory control register accesses.
+			 */
+			hcr |= HCR_TVM | HCR_TRVM | HCR_NV1;
+		} else {
+			/*
+			 * For a guest hypervisor on v8.1 (VHE), allow to
+			 * access the EL1 virtual memory control registers
+			 * natively. These accesses are to access EL2 register
+			 * states.
+			 * Note that we still need to respect the virtual
+			 * HCR_EL2 state.
+			 */
+			u64 vhcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2);
+
+			/*
+			 * We already set TVM to handle set/way cache maint
+			 * ops traps, this somewhat collides with the nested
+			 * virt trapping for nVHE. So turn this off for now
+			 * here, in the hope that VHE guests won't ever do this.
+			 * TODO: find out whether it's worth to support both
+			 * cases at the same time.
+			 */
+			hcr &= ~HCR_TVM;
+
+			hcr |= vhcr_el2 & (HCR_TVM | HCR_TRVM);
+		}
+	}
 
 	___activate_traps(vcpu, hcr);
 
-- 
2.29.2

[PATCH v3 30/66] KVM: arm64: nv: Only toggle cache for virtual EL2 when SCTLR_EL2 changes

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@linaro.org>

So far we were flushing almost the entire universe whenever a VM would
load/unload the SCTLR_EL1 and the two versions of that register had
different MMU enabled settings.  This turned out to be so slow that it
prevented forward progress for a nested VM, because a scheduler timer
tick interrupt would always be pending when we reached the nested VM.

To avoid this problem, we consider the SCTLR_EL2 when evaluating if
caches are on or off when entering virtual EL2 (because this is the
value that we end up shadowing onto the hardware EL1 register).

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_mmu.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index e52d82aeadca..76a8a0ca45b8 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -125,6 +125,7 @@ alternative_cb_end
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
+#include <asm/kvm_emulate.h>
 
 void kvm_update_va_mask(struct alt_instr *alt,
 			__le32 *origptr, __le32 *updptr, int nr_inst);
@@ -201,7 +202,10 @@ struct kvm;
 
 static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 {
-	return (vcpu_read_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
+	if (vcpu_mode_el2(vcpu))
+		return (__vcpu_sys_reg(vcpu, SCTLR_EL2) & 0b101) == 0b101;
+	else
+		return (vcpu_read_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
 }
 
 static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
-- 
2.29.2

[PATCH v3 31/66] KVM: arm64: nv: Filter out unsupported features from ID regs

[Marc Zyngier]

As there is a number of features that we either can't support,
or don't want to support right away with NV, let's add some
basic filtering so that we don't advertize silly things to the
EL2 guest.

Whilst we are at it, avertize ARMv8.4-TTL as well as ARMv8.5-GTG.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h |   6 ++
 arch/arm64/kvm/nested.c             | 152 ++++++++++++++++++++++++++++
 arch/arm64/kvm/sys_regs.c           |   4 +-
 3 files changed, 161 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 07c15f51cf86..026ddaad972c 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -67,4 +67,10 @@ extern bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg,
 extern bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit);
 extern bool forward_nv_traps(struct kvm_vcpu *vcpu);
 
+struct sys_reg_params;
+struct sys_reg_desc;
+
+void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
+			  const struct sys_reg_desc *r);
+
 #endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 42a96c8d2adc..9fb44bc7db3f 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -20,6 +20,10 @@
 #include <linux/kvm_host.h>
 
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_nested.h>
+#include <asm/sysreg.h>
+
+#include "sys_regs.h"
 
 /*
  * Inject wfx to the virtual EL2 if this is not from the virtual EL2 and
@@ -38,3 +42,151 @@ int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe)
 
 	return -EINVAL;
 }
+
+#define FEATURE(x)	(GENMASK_ULL(x##_SHIFT + 3, x##_SHIFT))
+
+/*
+ * Our emulated CPU doesn't support all the possible features. For the
+ * sake of simplicity (and probably mental sanity), wipe out a number
+ * of feature bits we don't intend to support for the time being.
+ * This list should get updated as new features get added to the NV
+ * support, and new extension to the architecture.
+ */
+void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	u32 id = sys_reg((u32)r->Op0, (u32)r->Op1,
+			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
+	u64 val, tmp;
+
+	if (!nested_virt_in_use(v))
+		return;
+
+	val = p->regval;
+
+	switch (id) {
+	case SYS_ID_AA64ISAR0_EL1:
+		/* Support everything but O.S. and Range TLBIs */
+		val &= ~(FEATURE(ID_AA64ISAR0_TLB)	|
+			 GENMASK_ULL(27, 24)		|
+			 GENMASK_ULL(3, 0));
+		break;
+
+	case SYS_ID_AA64ISAR1_EL1:
+		/* Support everything but PtrAuth and Spec Invalidation */
+		val &= ~(GENMASK_ULL(63, 56)		|
+			 FEATURE(ID_AA64ISAR1_SPECRES)	|
+			 FEATURE(ID_AA64ISAR1_GPI)	|
+			 FEATURE(ID_AA64ISAR1_GPA)	|
+			 FEATURE(ID_AA64ISAR1_API)	|
+			 FEATURE(ID_AA64ISAR1_APA));
+		break;
+
+	case SYS_ID_AA64PFR0_EL1:
+		/* No AMU, MPAM, S-EL2, RAS or SVE */
+		val &= ~(GENMASK_ULL(55, 52)		|
+			 FEATURE(ID_AA64PFR0_AMU)	|
+			 FEATURE(ID_AA64PFR0_MPAM)	|
+			 FEATURE(ID_AA64PFR0_SEL2)	|
+			 FEATURE(ID_AA64PFR0_RAS)	|
+			 FEATURE(ID_AA64PFR0_SVE)	|
+			 FEATURE(ID_AA64PFR0_EL2));
+		/* 64bit EL2 only */
+		val |= FIELD_PREP(FEATURE(ID_AA64PFR0_EL2), 0b0001);
+		break;
+
+	case SYS_ID_AA64PFR1_EL1:
+		/* Only support SSBS */
+		val &= FEATURE(ID_AA64PFR1_SSBS);
+		break;
+
+	case SYS_ID_AA64MMFR0_EL1:
+		/* Hide ECV, FGT, ExS, Secure Memory */
+		val &= ~(GENMASK_ULL(63, 43)			|
+			 FEATURE(ID_AA64MMFR0_TGRAN4_2)		|
+			 FEATURE(ID_AA64MMFR0_TGRAN16_2)	|
+			 FEATURE(ID_AA64MMFR0_TGRAN64_2)	|
+			 FEATURE(ID_AA64MMFR0_SNSMEM));
+
+		/* Disallow unsupported S2 page sizes */
+		switch (PAGE_SIZE) {
+		case SZ_64K:
+			val |= FIELD_PREP(FEATURE(ID_AA64MMFR0_TGRAN16_2), 0b0001);
+			/* Fall through */
+		case SZ_16K:
+			val |= FIELD_PREP(FEATURE(ID_AA64MMFR0_TGRAN4_2), 0b0001);
+			/* Fall through */
+		case SZ_4K:
+			/* Support everything */
+			break;
+		}
+		/* Advertize supported S2 page sizes */
+		switch (PAGE_SIZE) {
+		case SZ_4K:
+			val |= FIELD_PREP(FEATURE(ID_AA64MMFR0_TGRAN4_2), 0b0010);
+			/* Fall through */
+		case SZ_16K:
+			val |= FIELD_PREP(FEATURE(ID_AA64MMFR0_TGRAN16_2), 0b0010);
+			/* Fall through */
+		case SZ_64K:
+			val |= FIELD_PREP(FEATURE(ID_AA64MMFR0_TGRAN64_2), 0b0010);
+			break;
+		}
+		/* Cap PARange to 40bits */
+		tmp = FIELD_GET(FEATURE(ID_AA64MMFR0_PARANGE), val);
+		if (tmp > 0b0010) {
+			val &= ~FEATURE(ID_AA64MMFR0_PARANGE);
+			val |= FIELD_PREP(FEATURE(ID_AA64MMFR0_PARANGE), 0b0010);
+		}
+		break;
+
+	case SYS_ID_AA64MMFR1_EL1:
+		val &= (FEATURE(ID_AA64MMFR1_PAN)	|
+			FEATURE(ID_AA64MMFR1_LOR)	|
+			FEATURE(ID_AA64MMFR1_HPD)	|
+			FEATURE(ID_AA64MMFR1_VHE)	|
+			FEATURE(ID_AA64MMFR1_VMIDBITS));
+		break;
+
+	case SYS_ID_AA64MMFR2_EL1:
+		val &= ~(FEATURE(ID_AA64MMFR2_EVT)	|
+			 FEATURE(ID_AA64MMFR2_BBM)	|
+			 FEATURE(ID_AA64MMFR2_TTL)	|
+			 GENMASK_ULL(47, 44)		|
+			 FEATURE(ID_AA64MMFR2_ST)	|
+			 FEATURE(ID_AA64MMFR2_CCIDX)	|
+			 FEATURE(ID_AA64MMFR2_LVA));
+
+		/* Force TTL support */
+		val |= FIELD_PREP(FEATURE(ID_AA64MMFR2_TTL), 0b0001);
+		break;
+
+	case SYS_ID_AA64DFR0_EL1:
+		/* Only limited support for PMU, Debug, BPs and WPs */
+		val &= (FEATURE(ID_AA64DFR0_PMSVER)	|
+			FEATURE(ID_AA64DFR0_WRPS)	|
+			FEATURE(ID_AA64DFR0_BRPS)	|
+			FEATURE(ID_AA64DFR0_DEBUGVER));
+
+		/* Cap PMU to ARMv8.1 */
+		tmp = FIELD_GET(FEATURE(ID_AA64DFR0_PMUVER), val);
+		if (tmp > 0b0100) {
+			val &= ~FEATURE(ID_AA64DFR0_PMUVER);
+			val |= FIELD_PREP(FEATURE(ID_AA64DFR0_PMUVER), 0b0100);
+		}
+		/* Cap Debug to ARMv8.1 */
+		tmp = FIELD_GET(FEATURE(ID_AA64DFR0_DEBUGVER), val);
+		if (tmp > 0b0111) {
+			val &= ~FEATURE(ID_AA64DFR0_DEBUGVER);
+			val |= FIELD_PREP(FEATURE(ID_AA64DFR0_DEBUGVER), 0b0111);
+		}
+		break;
+
+	default:
+		/* Unknown register, just wipe it clean */
+		val = 0;
+		break;
+	}
+
+	p->regval = val;
+}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 80cf0c0761b9..d011b8156c52 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1372,8 +1372,10 @@ static bool access_id_reg(struct kvm_vcpu *vcpu,
 			  const struct sys_reg_desc *r)
 {
 	bool raz = sysreg_visible_as_raz(vcpu, r);
+	bool ret = __access_id_reg(vcpu, p, r, raz);
 
-	return __access_id_reg(vcpu, p, r, raz);
+	access_nested_id_reg(vcpu, p, r);
+	return ret;
 }
 
 static bool access_raz_id_reg(struct kvm_vcpu *vcpu,
-- 
2.29.2

[PATCH v3 32/66] KVM: arm64: nv: Hide RAS from nested guests

[Marc Zyngier]

We don't want to expose complicated features to guests until we have
a good grasp on the basic CPU emulation. So let's pretend that RAS,
doesn't exist in a nested guest. We already hide the feature bits,
let's now make sure VDISR_EL1 will UNDEF.

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

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index d011b8156c52..090ce14306ba 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -527,6 +527,14 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 		return read_zero(vcpu, p);
 }
 
+static bool trap_undef(struct kvm_vcpu *vcpu,
+		       struct sys_reg_params *p,
+		       const struct sys_reg_desc *r)
+{
+	kvm_inject_undefined(vcpu);
+	return false;
+}
+
 /*
  * ARMv8.1 mandates at least a trivial LORegion implementation, where all the
  * RW registers are RES0 (which we can implement as RAZ/WI). On an ARMv8.0
@@ -2083,6 +2091,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_VBAR_EL2), access_rw, reset_val, VBAR_EL2, 0 },
 	{ SYS_DESC(SYS_RVBAR_EL2), access_rw, reset_val, RVBAR_EL2, 0 },
 	{ SYS_DESC(SYS_RMR_EL2), access_wi, reset_val, RMR_EL2, 1 },
+	{ SYS_DESC(SYS_VDISR_EL2), trap_undef },
 
 	{ SYS_DESC(SYS_CONTEXTIDR_EL2), access_rw, reset_val, CONTEXTIDR_EL2, 0 },
 	{ SYS_DESC(SYS_TPIDR_EL2), access_rw, reset_val, TPIDR_EL2, 0 },
-- 
2.29.2

[PATCH v3 33/66] KVM: arm64: nv: Support multiple nested Stage-2 mmu structures

[Marc Zyngier]

Add Stage-2 mmu data structures for virtual EL2 and for nested guests.
We don't yet populate shadow Stage-2 page tables, but we now have a
framework for getting to a shadow Stage-2 pgd.

We allocate twice the number of vcpus as Stage-2 mmu structures because
that's sufficient for each vcpu running two translation regimes without
having to flush the Stage-2 page tables.

Co-developed-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h   |  29 +++++
 arch/arm64/include/asm/kvm_mmu.h    |   8 ++
 arch/arm64/include/asm/kvm_nested.h |   7 ++
 arch/arm64/kvm/arm.c                |  16 ++-
 arch/arm64/kvm/mmu.c                |  18 ++-
 arch/arm64/kvm/nested.c             | 183 ++++++++++++++++++++++++++++
 6 files changed, 250 insertions(+), 11 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d731cf7a56cb..d99e51e7cbee 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -95,14 +95,43 @@ struct kvm_s2_mmu {
 	int __percpu *last_vcpu_ran;
 
 	struct kvm *kvm;
+
+	/*
+	 * For a shadow stage-2 MMU, the virtual vttbr programmed by the guest
+	 * hypervisor.  Unused for kvm_arch->mmu. Set to 1 when the structure
+	 * contains no valid information.
+	 */
+	u64	vttbr;
+
+	/* true when this represents a nested context where virtual HCR_EL2.VM == 1 */
+	bool	nested_stage2_enabled;
+
+	/*
+	 *  0: Nobody is currently using this, check vttbr for validity
+	 * >0: Somebody is actively using this.
+	 */
+	atomic_t refcnt;
 };
 
+static inline bool kvm_s2_mmu_valid(struct kvm_s2_mmu *mmu)
+{
+	return !(mmu->vttbr & 1);
+}
+
 struct kvm_arch_memory_slot {
 };
 
 struct kvm_arch {
 	struct kvm_s2_mmu mmu;
 
+	/*
+	 * Stage 2 paging stage for VMs with nested virtual using a virtual
+	 * VMID.
+	 */
+	struct kvm_s2_mmu *nested_mmus;
+	size_t nested_mmus_size;
+	int nested_mmus_next;
+
 	/* VTCR_EL2 value for this VM */
 	u64    vtcr;
 
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 76a8a0ca45b8..ec39015bb2a6 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -126,6 +126,7 @@ alternative_cb_end
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_nested.h>
 
 void kvm_update_va_mask(struct alt_instr *alt,
 			__le32 *origptr, __le32 *updptr, int nr_inst);
@@ -184,6 +185,7 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 			     void **haddr);
 void free_hyp_pgds(void);
 
+void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
 void stage2_unmap_vm(struct kvm *kvm);
 int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu);
 void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
@@ -306,5 +308,11 @@ static __always_inline void __load_guest_stage2(struct kvm_s2_mmu *mmu)
 	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
 }
 
+static inline u64 get_vmid(u64 vttbr)
+{
+	return (vttbr & VTTBR_VMID_MASK(kvm_get_vmid_bits())) >>
+		VTTBR_VMID_SHIFT;
+}
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 026ddaad972c..473ecd1d60d0 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -61,6 +61,13 @@ static inline u64 translate_cnthctl_el2_to_cntkctl_el1(u64 cnthctl)
 		(cnthctl & (CNTHCTL_EVNTI | CNTHCTL_EVNTDIR | CNTHCTL_EVNTEN)));
 }
 
+extern void kvm_init_nested(struct kvm *kvm);
+extern int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu);
+extern void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu);
+extern struct kvm_s2_mmu *lookup_s2_mmu(struct kvm *kvm, u64 vttbr, u64 hcr);
+extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
+extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
+
 int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe);
 extern bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg,
 			    u64 control_bit);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 6e637d2b4cfb..1656dd80bbc4 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -35,6 +35,7 @@
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_nested.h>
 #include <asm/kvm_emulate.h>
 #include <asm/sections.h>
 
@@ -142,6 +143,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		return ret;
 
+	kvm_init_nested(kvm);
+
 	ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP);
 	if (ret)
 		goto out_free_stage2_pgd;
@@ -385,6 +388,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	struct kvm_s2_mmu *mmu;
 	int *last_ran;
 
+	if (nested_virt_in_use(vcpu))
+		kvm_vcpu_load_hw_mmu(vcpu);
+
 	mmu = vcpu->arch.hw_mmu;
 	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
@@ -426,6 +432,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_vgic_put(vcpu);
 	kvm_vcpu_pmu_restore_host(vcpu);
 
+	if (nested_virt_in_use(vcpu))
+		kvm_vcpu_put_hw_mmu(vcpu);
+
 	vcpu->cpu = -1;
 }
 
@@ -1026,8 +1035,13 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 
 	vcpu->arch.target = phys_target;
 
+	/* Prepare for nested if required */
+	ret = kvm_vcpu_init_nested(vcpu);
+
 	/* Now we know what it is, we can reset it. */
-	ret = kvm_reset_vcpu(vcpu);
+	if (!ret)
+		ret = kvm_reset_vcpu(vcpu);
+
 	if (ret) {
 		vcpu->arch.target = -1;
 		bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 1f41173e6149..2f0302211af3 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -113,7 +113,7 @@ static bool kvm_is_device_pfn(unsigned long pfn)
  * does.
  */
 /**
- * unmap_stage2_range -- Clear stage2 page table entries to unmap a range
+ * kvm_unmap_stage2_range -- Clear stage2 page table entries to unmap a range
  * @mmu:   The KVM stage-2 MMU pointer
  * @start: The intermediate physical base address of the range to unmap
  * @size:  The size of the area to unmap
@@ -136,7 +136,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
 				   may_block));
 }
 
-static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
+void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
 {
 	__unmap_stage2_range(mmu, start, size, true);
 }
@@ -391,6 +391,9 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
 	mmu->pgt = pgt;
 	mmu->pgd_phys = __pa(pgt->pgd);
 	mmu->vmid.vmid_gen = 0;
+
+	kvm_init_nested_s2_mmu(mmu);
+
 	return 0;
 
 out_destroy_pgtable:
@@ -435,7 +438,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
 
 		if (!(vma->vm_flags & VM_PFNMAP)) {
 			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
-			unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
+			kvm_unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
 		}
 		hva = vm_end;
 	} while (hva < reg_end);
@@ -1360,7 +1363,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 
 	spin_lock(&kvm->mmu_lock);
 	if (ret)
-		unmap_stage2_range(&kvm->arch.mmu, mem->guest_phys_addr, mem->memory_size);
+		kvm_unmap_stage2_range(&kvm->arch.mmu, mem->guest_phys_addr, mem->memory_size);
 	else if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
 		stage2_flush_memslot(kvm, memslot);
 	spin_unlock(&kvm->mmu_lock);
@@ -1377,11 +1380,6 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 {
 }
 
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
-	kvm_free_stage2_pgd(&kvm->arch.mmu);
-}
-
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
@@ -1389,7 +1387,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	phys_addr_t size = slot->npages << PAGE_SHIFT;
 
 	spin_lock(&kvm->mmu_lock);
-	unmap_stage2_range(&kvm->arch.mmu, gpa, size);
+	kvm_unmap_stage2_range(&kvm->arch.mmu, gpa, size);
 	spin_unlock(&kvm->mmu_lock);
 }
 
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 9fb44bc7db3f..8e85d2ef24d9 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -19,12 +19,177 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
+#include <asm/kvm_arm.h>
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_mmu.h>
 #include <asm/kvm_nested.h>
 #include <asm/sysreg.h>
 
 #include "sys_regs.h"
 
+void kvm_init_nested(struct kvm *kvm)
+{
+	kvm->arch.nested_mmus = NULL;
+	kvm->arch.nested_mmus_size = 0;
+}
+
+int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_s2_mmu *tmp;
+	int num_mmus;
+	int ret = -ENOMEM;
+
+	if (!test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features))
+		return 0;
+
+	if (!cpus_have_final_cap(ARM64_HAS_NESTED_VIRT))
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+
+	/*
+	 * Let's treat memory allocation failures as benign: If we fail to
+	 * allocate anything, return an error and keep the allocated array
+	 * alive. Userspace may try to recover by intializing the vcpu
+	 * again, and there is no reason to affect the whole VM for this.
+	 */
+	num_mmus = atomic_read(&kvm->online_vcpus) * 2;
+	tmp = krealloc(kvm->arch.nested_mmus,
+		       num_mmus * sizeof(*kvm->arch.nested_mmus),
+		       GFP_KERNEL | __GFP_ZERO);
+	if (tmp) {
+		if (kvm_init_stage2_mmu(kvm, &tmp[num_mmus - 1]) ||
+		    kvm_init_stage2_mmu(kvm, &tmp[num_mmus - 2])) {
+			kvm_free_stage2_pgd(&tmp[num_mmus - 1]);
+			kvm_free_stage2_pgd(&tmp[num_mmus - 2]);
+		} else {
+			kvm->arch.nested_mmus_size = num_mmus;
+			ret = 0;
+		}
+
+		kvm->arch.nested_mmus = tmp;
+	}
+
+	mutex_unlock(&kvm->lock);
+	return ret;
+}
+
+/* Must be called with kvm->lock held */
+struct kvm_s2_mmu *lookup_s2_mmu(struct kvm *kvm, u64 vttbr, u64 hcr)
+{
+	bool nested_stage2_enabled = hcr & HCR_VM;
+	int i;
+
+	/* Don't consider the CnP bit for the vttbr match */
+	vttbr = vttbr & ~VTTBR_CNP_BIT;
+
+	/*
+	 * Two possibilities when looking up a S2 MMU context:
+	 *
+	 * - either S2 is enabled in the guest, and we need a context that
+         *   is S2-enabled and matches the full VTTBR (VMID+BADDR), which
+         *   makes it safe from a TLB conflict perspective (a broken guest
+         *   won't be able to generate them),
+	 *
+	 * - or S2 is disabled, and we need a context that is S2-disabled
+         *   and matches the VMID only, as all TLBs are tagged by VMID even
+         *   if S2 translation is enabled.
+	 */
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (!kvm_s2_mmu_valid(mmu))
+			continue;
+
+		if (nested_stage2_enabled &&
+		    mmu->nested_stage2_enabled &&
+		    vttbr == mmu->vttbr)
+			return mmu;
+
+		if (!nested_stage2_enabled &&
+		    !mmu->nested_stage2_enabled &&
+		    get_vmid(vttbr) == get_vmid(mmu->vttbr))
+			return mmu;
+	}
+	return NULL;
+}
+
+static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+	u64 hcr= vcpu_read_sys_reg(vcpu, HCR_EL2);
+	struct kvm_s2_mmu *s2_mmu;
+	int i;
+
+	s2_mmu = lookup_s2_mmu(kvm, vttbr, hcr);
+	if (s2_mmu)
+		goto out;
+
+	/*
+	 * Make sure we don't always search from the same point, or we
+	 * will always reuse a potentially active context, leaving
+	 * free contexts unused.
+	 */
+	for (i = kvm->arch.nested_mmus_next;
+	     i < (kvm->arch.nested_mmus_size + kvm->arch.nested_mmus_next);
+	     i++) {
+		s2_mmu = &kvm->arch.nested_mmus[i % kvm->arch.nested_mmus_size];
+
+		if (atomic_read(&s2_mmu->refcnt) == 0)
+			break;
+	}
+	BUG_ON(atomic_read(&s2_mmu->refcnt)); /* We have struct MMUs to spare */
+
+	/* Set the scene for the next search */
+	kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size;
+
+	if (kvm_s2_mmu_valid(s2_mmu)) {
+		/* Clear the old state */
+		kvm_unmap_stage2_range(s2_mmu, 0, kvm_phys_size(kvm));
+		if (s2_mmu->vmid.vmid_gen)
+			kvm_call_hyp(__kvm_tlb_flush_vmid, s2_mmu);
+	}
+
+	/*
+	 * The virtual VMID (modulo CnP) will be used as a key when matching
+	 * an existing kvm_s2_mmu.
+	 */
+	s2_mmu->vttbr = vttbr & ~VTTBR_CNP_BIT;
+	s2_mmu->nested_stage2_enabled = hcr & HCR_VM;
+
+out:
+	atomic_inc(&s2_mmu->refcnt);
+	return s2_mmu;
+}
+
+void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu)
+{
+	mmu->vttbr = 1;
+	mmu->nested_stage2_enabled = false;
+	atomic_set(&mmu->refcnt, 0);
+}
+
+void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
+{
+	if (is_hyp_ctxt(vcpu)) {
+		vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
+	} else {
+		spin_lock(&vcpu->kvm->mmu_lock);
+		vcpu->arch.hw_mmu = get_s2_mmu_nested(vcpu);
+		spin_unlock(&vcpu->kvm->mmu_lock);
+	}
+}
+
+void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.hw_mmu != &vcpu->kvm->arch.mmu) {
+		atomic_dec(&vcpu->arch.hw_mmu->refcnt);
+		vcpu->arch.hw_mmu = NULL;
+	}
+}
+
 /*
  * Inject wfx to the virtual EL2 if this is not from the virtual EL2 and
  * the virtual HCR_EL2.TWX is set. Otherwise, let the host hypervisor
@@ -43,6 +208,24 @@ int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe)
 	return -EINVAL;
 }
 
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+	int i;
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		WARN_ON(atomic_read(&mmu->refcnt));
+
+		if (!atomic_read(&mmu->refcnt))
+			kvm_free_stage2_pgd(mmu);
+	}
+	kfree(kvm->arch.nested_mmus);
+	kvm->arch.nested_mmus = NULL;
+	kvm->arch.nested_mmus_size = 0;
+	kvm_free_stage2_pgd(&kvm->arch.mmu);
+}
+
 #define FEATURE(x)	(GENMASK_ULL(x##_SHIFT + 3, x##_SHIFT))
 
 /*
-- 
2.29.2

[PATCH v3 34/66] KVM: arm64: nv: Implement nested Stage-2 page table walk logic

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@linaro.org>

Based on the pseudo-code in the ARM ARM, implement a stage 2 software
page table walker.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
[maz: heavily reworked for future ARMv8.4-TTL support]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/esr.h        |   1 +
 arch/arm64/include/asm/kvm_arm.h    |   2 +
 arch/arm64/include/asm/kvm_nested.h |  13 ++
 arch/arm64/kvm/nested.c             | 276 ++++++++++++++++++++++++++++
 4 files changed, 292 insertions(+)

diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index ab63b7b3ea14..e099eba5e616 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -127,6 +127,7 @@
 #define ESR_ELx_CM 		(UL(1) << ESR_ELx_CM_SHIFT)
 
 /* ISS field definitions for exceptions taken in to Hyp */
+#define ESR_ELx_FSC_ADDRSZ	(0x00)
 #define ESR_ELx_CV		(UL(1) << 24)
 #define ESR_ELx_COND_SHIFT	(20)
 #define ESR_ELx_COND_MASK	(UL(0xF) << ESR_ELx_COND_SHIFT)
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 3d2abc40d3a2..347e9e9b015c 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -264,6 +264,8 @@
 #define VTTBR_VMID_SHIFT  (UL(48))
 #define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
 
+#define SCTLR_EE	(UL(1) << 25)
+
 /* Hyp System Trap Register */
 #define HSTR_EL2_T(x)	(1 << x)
 
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 473ecd1d60d0..b784d7891851 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -68,6 +68,19 @@ extern struct kvm_s2_mmu *lookup_s2_mmu(struct kvm *kvm, u64 vttbr, u64 hcr);
 extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
 extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
 
+struct kvm_s2_trans {
+	phys_addr_t output;
+	unsigned long block_size;
+	bool writable;
+	bool readable;
+	int level;
+	u32 esr;
+	u64 upper_attr;
+};
+
+extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
+			      struct kvm_s2_trans *result);
+
 int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe);
 extern bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg,
 			    u64 control_bit);
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 8e85d2ef24d9..ff970221a219 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -75,6 +75,282 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
+struct s2_walk_info {
+	int	     (*read_desc)(phys_addr_t pa, u64 *desc, void *data);
+	void	     *data;
+	u64	     baddr;
+	unsigned int max_pa_bits;
+	unsigned int pgshift;
+	unsigned int pgsize;
+	unsigned int ps;
+	unsigned int sl;
+	unsigned int t0sz;
+	bool	     be;
+	bool	     el1_aarch32;
+};
+
+static unsigned int ps_to_output_size(unsigned int ps)
+{
+	switch (ps) {
+	case 0: return 32;
+	case 1: return 36;
+	case 2: return 40;
+	case 3: return 42;
+	case 4: return 44;
+	case 5:
+	default:
+		return 48;
+	}
+}
+
+static u32 compute_fsc(int level, u32 fsc)
+{
+	return fsc | (level & 0x3);
+}
+
+static int esr_s2_fault(struct kvm_vcpu *vcpu, int level, u32 fsc)
+{
+	u32 esr;
+
+	esr = kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC;
+	esr |= compute_fsc(level, fsc);
+	return esr;
+}
+
+static int check_base_s2_limits(struct s2_walk_info *wi,
+				int level, int input_size, int stride)
+{
+	int start_size;
+
+	/* Check translation limits */
+	switch (wi->pgsize) {
+	case SZ_64K:
+		if (level == 0 || (level == 1 && wi->max_pa_bits <= 42))
+			return -EFAULT;
+		break;
+	case SZ_16K:
+		if (level == 0 || (level == 1 && wi->max_pa_bits <= 40))
+			return -EFAULT;
+		break;
+	case SZ_4K:
+		if (level < 0 || (level == 0 && wi->max_pa_bits <= 42))
+			return -EFAULT;
+		break;
+	}
+
+	/* Check input size limits */
+	if (input_size > wi->max_pa_bits &&
+	    (!wi->el1_aarch32 || input_size > 40))
+		return -EFAULT;
+
+	/* Check number of entries in starting level table */
+	start_size = input_size - ((3 - level) * stride + wi->pgshift);
+	if (start_size < 1 || start_size > stride + 4)
+		return -EFAULT;
+
+	return 0;
+}
+
+/* Check if output is within boundaries */
+static int check_output_size(struct s2_walk_info *wi, phys_addr_t output)
+{
+	unsigned int output_size = ps_to_output_size(wi->ps);
+
+	if (output_size > wi->max_pa_bits)
+		output_size = wi->max_pa_bits;
+
+	if (output_size != 48 && (output & GENMASK_ULL(47, output_size)))
+		return -1;
+
+	return 0;
+}
+
+/*
+ * This is essentially a C-version of the pseudo code from the ARM ARM
+ * AArch64.TranslationTableWalk  function.  I strongly recommend looking at
+ * that pseudocode in trying to understand this.
+ *
+ * Must be called with the kvm->srcu read lock held
+ */
+static int walk_nested_s2_pgd(phys_addr_t ipa,
+			      struct s2_walk_info *wi, struct kvm_s2_trans *out)
+{
+	int first_block_level, level, stride, input_size, base_lower_bound;
+	phys_addr_t base_addr;
+	unsigned int addr_top, addr_bottom;
+	u64 desc;  /* page table entry */
+	int ret;
+	phys_addr_t paddr;
+
+	switch (wi->pgsize) {
+	case SZ_64K:
+	case SZ_16K:
+		level = 3 - wi->sl;
+		first_block_level = 2;
+		break;
+	case SZ_4K:
+		level = 2 - wi->sl;
+		first_block_level = 1;
+		break;
+	default:
+		/* GCC is braindead */
+		unreachable();
+	}
+
+	stride = wi->pgshift - 3;
+	input_size = 64 - wi->t0sz;
+	if (input_size > 48 || input_size < 25)
+		return -EFAULT;
+
+	ret = check_base_s2_limits(wi, level, input_size, stride);
+	if (WARN_ON(ret))
+		return ret;
+
+	base_lower_bound = 3 + input_size - ((3 - level) * stride +
+			   wi->pgshift);
+	base_addr = wi->baddr & GENMASK_ULL(47, base_lower_bound);
+
+	if (check_output_size(wi, base_addr)) {
+		out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
+		return 1;
+	}
+
+	addr_top = input_size - 1;
+
+	while (1) {
+		phys_addr_t index;
+
+		addr_bottom = (3 - level) * stride + wi->pgshift;
+		index = (ipa & GENMASK_ULL(addr_top, addr_bottom))
+			>> (addr_bottom - 3);
+
+		paddr = base_addr | index;
+		ret = wi->read_desc(paddr, &desc, wi->data);
+		if (ret < 0)
+			return ret;
+
+		/*
+		 * Handle reversedescriptors if endianness differs between the
+		 * host and the guest hypervisor.
+		 */
+		if (wi->be)
+			desc = be64_to_cpu(desc);
+		else
+			desc = le64_to_cpu(desc);
+
+		/* Check for valid descriptor at this point */
+		if (!(desc & 1) || ((desc & 3) == 1 && level == 3)) {
+			out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT);
+			out->upper_attr = desc;
+			return 1;
+		}
+
+		/* We're at the final level or block translation level */
+		if ((desc & 3) == 1 || level == 3)
+			break;
+
+		if (check_output_size(wi, desc)) {
+			out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
+			out->upper_attr = desc;
+			return 1;
+		}
+
+		base_addr = desc & GENMASK_ULL(47, wi->pgshift);
+
+		level += 1;
+		addr_top = addr_bottom - 1;
+	}
+
+	if (level < first_block_level) {
+		out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT);
+		out->upper_attr = desc;
+		return 1;
+	}
+
+	/*
+	 * We don't use the contiguous bit in the stage-2 ptes, so skip check
+	 * for misprogramming of the contiguous bit.
+	 */
+
+	if (check_output_size(wi, desc)) {
+		out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
+		out->upper_attr = desc;
+		return 1;
+	}
+
+	if (!(desc & BIT(10))) {
+		out->esr = compute_fsc(level, ESR_ELx_FSC_ACCESS);
+		out->upper_attr = desc;
+		return 1;
+	}
+
+	/* Calculate and return the result */
+	paddr = (desc & GENMASK_ULL(47, addr_bottom)) |
+		(ipa & GENMASK_ULL(addr_bottom - 1, 0));
+	out->output = paddr;
+	out->block_size = 1UL << ((3 - level) * stride + wi->pgshift);
+	out->readable = desc & (0b01 << 6);
+	out->writable = desc & (0b10 << 6);
+	out->level = level;
+	out->upper_attr = desc & GENMASK_ULL(63, 52);
+	return 0;
+}
+
+static int read_guest_s2_desc(phys_addr_t pa, u64 *desc, void *data)
+{
+	struct kvm_vcpu *vcpu = data;
+
+	return kvm_read_guest(vcpu->kvm, pa, desc, sizeof(*desc));
+}
+
+static void vtcr_to_walk_info(u64 vtcr, struct s2_walk_info *wi)
+{
+	wi->t0sz = vtcr & TCR_EL2_T0SZ_MASK;
+
+	switch (vtcr & VTCR_EL2_TG0_MASK) {
+	case VTCR_EL2_TG0_4K:
+		wi->pgshift = 12;	 break;
+	case VTCR_EL2_TG0_16K:
+		wi->pgshift = 14;	 break;
+	case VTCR_EL2_TG0_64K:
+	default:
+		wi->pgshift = 16;	 break;
+	}
+
+	wi->pgsize = 1UL << wi->pgshift;
+	wi->ps = (vtcr & VTCR_EL2_PS_MASK) >> VTCR_EL2_PS_SHIFT;
+	wi->sl = (vtcr & VTCR_EL2_SL0_MASK) >> VTCR_EL2_SL0_SHIFT;
+	wi->max_pa_bits = VTCR_EL2_IPA(vtcr);
+}
+
+int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
+		       struct kvm_s2_trans *result)
+{
+	u64 vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+	struct s2_walk_info wi;
+	int ret;
+
+	result->esr = 0;
+
+	if (!nested_virt_in_use(vcpu))
+		return 0;
+
+	wi.read_desc = read_guest_s2_desc;
+	wi.data = vcpu;
+	wi.baddr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+
+	vtcr_to_walk_info(vtcr, &wi);
+
+	wi.be = vcpu_read_sys_reg(vcpu, SCTLR_EL2) & SCTLR_EE;
+	wi.el1_aarch32 = vcpu_mode_is_32bit(vcpu);
+
+	ret = walk_nested_s2_pgd(gipa, &wi, result);
+	if (ret)
+		result->esr |= (kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC);
+
+	return ret;
+}
+
 /* Must be called with kvm->lock held */
 struct kvm_s2_mmu *lookup_s2_mmu(struct kvm *kvm, u64 vttbr, u64 hcr)
 {
-- 
2.29.2

[PATCH v3 35/66] KVM: arm64: nv: Handle shadow stage 2 page faults

[Marc Zyngier]

If we are faulting on a shadow stage 2 translation, we first walk the
guest hypervisor's stage 2 page table to see if it has a mapping. If
not, we inject a stage 2 page fault to the virtual EL2. Otherwise, we
create a mapping in the shadow stage 2 page table.

Note that we have to deal with two IPAs when we got a shadow stage 2
page fault. One is the address we faulted on, and is in the L2 guest
phys space. The other is from the guest stage-2 page table walk, and is
in the L1 guest phys space.  To differentiate them, we rename variables
so that fault_ipa is used for the former and ipa is used for the latter.

Co-developed-by: Christoffer Dall <christoffer.dall@linaro.org>
Co-developed-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
[maz: rewrote this multiple times...]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h |  6 ++
 arch/arm64/include/asm/kvm_nested.h  | 18 ++++++
 arch/arm64/kvm/mmu.c                 | 93 ++++++++++++++++++++++------
 arch/arm64/kvm/nested.c              | 39 ++++++++++++
 4 files changed, 138 insertions(+), 18 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index a000e6e05091..b447817d9dee 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -586,4 +586,10 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
 	vcpu->arch.flags |= KVM_ARM64_INCREMENT_PC;
 }
 
+static inline bool kvm_is_shadow_s2_fault(struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.hw_mmu != &vcpu->kvm->arch.mmu &&
+		vcpu->arch.hw_mmu->nested_stage2_enabled);
+}
+
 #endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index b784d7891851..4f93a5dab183 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -78,9 +78,27 @@ struct kvm_s2_trans {
 	u64 upper_attr;
 };
 
+static inline phys_addr_t kvm_s2_trans_output(struct kvm_s2_trans *trans)
+{
+	return trans->output;
+}
+
+static inline unsigned long kvm_s2_trans_size(struct kvm_s2_trans *trans)
+{
+	return trans->block_size;
+}
+
+static inline u32 kvm_s2_trans_esr(struct kvm_s2_trans *trans)
+{
+	return trans->esr;
+}
+
 extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
 			      struct kvm_s2_trans *result);
 
+extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
+				    struct kvm_s2_trans *trans);
+extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
 int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe);
 extern bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg,
 			    u64 control_bit);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 2f0302211af3..aa8e2ed7acfe 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -699,7 +699,7 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
 static unsigned long
 transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
 			    unsigned long hva, kvm_pfn_t *pfnp,
-			    phys_addr_t *ipap)
+			    phys_addr_t *ipap, phys_addr_t *fault_ipap)
 {
 	kvm_pfn_t pfn = *pfnp;
 
@@ -728,6 +728,7 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
 		 * to PG_head and switch the pfn from a tail page to the head
 		 * page accordingly.
 		 */
+		*fault_ipap &= PMD_MASK;
 		*ipap &= PMD_MASK;
 		kvm_release_pfn_clean(pfn);
 		pfn &= ~(PTRS_PER_PMD - 1);
@@ -742,14 +743,16 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
 }
 
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
-			  struct kvm_memory_slot *memslot, unsigned long hva,
-			  unsigned long fault_status)
+			  struct kvm_s2_trans *nested,
+			  struct kvm_memory_slot *memslot,
+			  unsigned long hva, unsigned long fault_status)
 {
 	int ret = 0;
-	bool write_fault, writable, force_pte = false;
+	bool write_fault, writable;
 	bool exec_fault;
 	bool device = false;
 	unsigned long mmu_seq;
+	phys_addr_t ipa = fault_ipa;
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
 	struct vm_area_struct *vma;
@@ -760,6 +763,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	unsigned long vma_pagesize;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt;
+	unsigned long max_map_size = PUD_SIZE;
 
 	write_fault = kvm_is_write_fault(vcpu);
 	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
@@ -786,7 +790,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 	if (logging_active ||
 	    (vma->vm_flags & VM_PFNMAP)) {
-		force_pte = true;
+		max_map_size = vma_pagesize = PAGE_SIZE;
 		vma_shift = PAGE_SHIFT;
 	}
 
@@ -806,7 +810,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		fallthrough;
 	case CONT_PTE_SHIFT:
 		vma_shift = PAGE_SHIFT;
-		force_pte = true;
+		max_map_size = PAGE_SIZE;
 		fallthrough;
 	case PAGE_SHIFT:
 		break;
@@ -815,10 +819,25 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 	vma_pagesize = 1UL << vma_shift;
+
+	if (kvm_is_shadow_s2_fault(vcpu)) {
+		ipa = kvm_s2_trans_output(nested);
+
+		/*
+		 * If we're about to create a shadow stage 2 entry, then we
+		 * can only create a block mapping if the guest stage 2 page
+		 * table uses at least as big a mapping.
+		 */
+		max_map_size = min(kvm_s2_trans_size(nested), max_map_size);
+	}
+
+	vma_pagesize = min(vma_pagesize, max_map_size);
+
 	if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE)
 		fault_ipa &= ~(vma_pagesize - 1);
 
-	gfn = fault_ipa >> PAGE_SHIFT;
+	gfn = ipa >> PAGE_SHIFT;
+
 	mmap_read_unlock(current->mm);
 
 	/*
@@ -856,7 +875,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 	if (kvm_is_device_pfn(pfn)) {
 		device = true;
-		force_pte = true;
+		max_map_size = PAGE_SIZE;
 	} else if (logging_active && !write_fault) {
 		/*
 		 * Only actually map the page as writable if this was a write
@@ -877,9 +896,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * If we are not forced to use page mapping, check if we are
 	 * backed by a THP and thus use block mapping if possible.
 	 */
-	if (vma_pagesize == PAGE_SIZE && !force_pte)
-		vma_pagesize = transparent_hugepage_adjust(memslot, hva,
-							   &pfn, &fault_ipa);
+	if (vma_pagesize == PAGE_SIZE && max_map_size >= PMD_SIZE)
+		vma_pagesize = transparent_hugepage_adjust(memslot, hva, &pfn,
+							   &ipa, &fault_ipa);
 	if (writable) {
 		prot |= KVM_PGTABLE_PROT_W;
 		kvm_set_pfn_dirty(pfn);
@@ -947,8 +966,10 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 {
 	unsigned long fault_status;
-	phys_addr_t fault_ipa;
+	phys_addr_t fault_ipa; /* The address we faulted on */
+	phys_addr_t ipa; /* Always the IPA in the L1 guest phys space */
 	struct kvm_memory_slot *memslot;
+	struct kvm_s2_trans nested_trans;
 	unsigned long hva;
 	bool is_iabt, write_fault, writable;
 	gfn_t gfn;
@@ -956,7 +977,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 
 	fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
 
-	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
+	ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
 	/* Synchronous External Abort? */
@@ -977,6 +998,12 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	/* Check the stage-2 fault is trans. fault or write fault */
 	if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
 	    fault_status != FSC_ACCESS) {
+		/*
+		 * We must never see an address size fault on shadow stage 2
+		 * page table walk, because we would have injected an addr
+		 * size fault when we walked the nested s2 page and not
+		 * create the shadow entry.
+		 */
 		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
 			kvm_vcpu_trap_get_class(vcpu),
 			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
@@ -986,7 +1013,36 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
 
-	gfn = fault_ipa >> PAGE_SHIFT;
+	/*
+	 * We may have faulted on a shadow stage 2 page table if we are
+	 * running a nested guest.  In this case, we have to resolve the L2
+	 * IPA to the L1 IPA first, before knowing what kind of memory should
+	 * back the L1 IPA.
+	 *
+	 * If the shadow stage 2 page table walk faults, then we simply inject
+	 * this to the guest and carry on.
+	 */
+	if (kvm_is_shadow_s2_fault(vcpu)) {
+		u32 esr;
+
+		ret = kvm_walk_nested_s2(vcpu, fault_ipa, &nested_trans);
+		esr = kvm_s2_trans_esr(&nested_trans);
+		if (esr)
+			kvm_inject_s2_fault(vcpu, esr);
+		if (ret)
+			goto out_unlock;
+
+		ret = kvm_s2_handle_perm_fault(vcpu, &nested_trans);
+		esr = kvm_s2_trans_esr(&nested_trans);
+		if (esr)
+			kvm_inject_s2_fault(vcpu, esr);
+		if (ret)
+			goto out_unlock;
+
+		ipa = kvm_s2_trans_output(&nested_trans);
+	}
+
+	gfn = ipa >> PAGE_SHIFT;
 	memslot = gfn_to_memslot(vcpu->kvm, gfn);
 	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
 	write_fault = kvm_is_write_fault(vcpu);
@@ -1030,13 +1086,13 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		 * faulting VA. This is always 12 bits, irrespective
 		 * of the page size.
 		 */
-		fault_ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1);
-		ret = io_mem_abort(vcpu, fault_ipa);
+		ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1);
+		ret = io_mem_abort(vcpu, ipa);
 		goto out_unlock;
 	}
 
 	/* Userspace should not be able to register out-of-bounds IPAs */
-	VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm));
+	VM_BUG_ON(ipa >= kvm_phys_size(vcpu->kvm));
 
 	if (fault_status == FSC_ACCESS) {
 		handle_access_fault(vcpu, fault_ipa);
@@ -1044,7 +1100,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		goto out_unlock;
 	}
 
-	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
+	ret = user_mem_abort(vcpu, fault_ipa, &nested_trans,
+			     memslot, hva, fault_status);
 	if (ret == 0)
 		ret = 1;
 out:
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index ff970221a219..a64895ec6907 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -466,6 +466,45 @@ void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
 	}
 }
 
+/*
+ * Returns non-zero if permission fault is handled by injecting it to the next
+ * level hypervisor.
+ */
+int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu, struct kvm_s2_trans *trans)
+{
+	unsigned long fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
+	bool forward_fault = false;
+
+	trans->esr = 0;
+
+	if (fault_status != FSC_PERM)
+		return 0;
+
+	if (kvm_vcpu_trap_is_iabt(vcpu)) {
+		forward_fault = (trans->upper_attr & BIT(54));
+	} else {
+		bool write_fault = kvm_is_write_fault(vcpu);
+
+		forward_fault = ((write_fault && !trans->writable) ||
+				 (!write_fault && !trans->readable));
+	}
+
+	if (forward_fault) {
+		trans->esr = esr_s2_fault(vcpu, trans->level, ESR_ELx_FSC_PERM);
+		return 1;
+	}
+
+	return 0;
+}
+
+int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2)
+{
+	vcpu_write_sys_reg(vcpu, vcpu->arch.fault.far_el2, FAR_EL2);
+	vcpu_write_sys_reg(vcpu, vcpu->arch.fault.hpfar_el2, HPFAR_EL2);
+
+	return kvm_inject_nested_sync(vcpu, esr_el2);
+}
+
 /*
  * Inject wfx to the virtual EL2 if this is not from the virtual EL2 and
  * the virtual HCR_EL2.TWX is set. Otherwise, let the host hypervisor
-- 
2.29.2

[PATCH v3 36/66] KVM: arm64: nv: Restrict S2 RD/WR permissions to match the guest's

[Marc Zyngier]

When mapping a page in a shadow stage-2, special care must be
taken not to be more permissive than the guest is (writable or
readable page when the guest hasn't set that permission).

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h | 15 +++++++++++++++
 arch/arm64/kvm/mmu.c                | 14 +++++++++++++-
 arch/arm64/kvm/nested.c             |  2 +-
 3 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 4f93a5dab183..3f3d8e10bd99 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -93,6 +93,21 @@ static inline u32 kvm_s2_trans_esr(struct kvm_s2_trans *trans)
 	return trans->esr;
 }
 
+static inline bool kvm_s2_trans_readable(struct kvm_s2_trans *trans)
+{
+	return trans->readable;
+}
+
+static inline bool kvm_s2_trans_writable(struct kvm_s2_trans *trans)
+{
+	return trans->writable;
+}
+
+static inline bool kvm_s2_trans_executable(struct kvm_s2_trans *trans)
+{
+	return !(trans->upper_attr & BIT(54));
+}
+
 extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
 			      struct kvm_s2_trans *result);
 
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index aa8e2ed7acfe..6f973efb2cc3 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -887,6 +887,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (exec_fault && device)
 		return -ENOEXEC;
 
+	/*
+	 * Potentially reduce shadow S2 permissions to match the guest's own
+	 * S2. For exec faults, we'd only reach this point if the guest
+	 * actually allowed it (see kvm_s2_handle_perm_fault).
+	 */
+	if (kvm_is_shadow_s2_fault(vcpu)) {
+		writable &= kvm_s2_trans_writable(nested);
+		if (!kvm_s2_trans_readable(nested))
+			prot &= ~KVM_PGTABLE_PROT_R;
+	}
+
 	spin_lock(&kvm->mmu_lock);
 	pgt = vcpu->arch.hw_mmu->pgt;
 	if (mmu_notifier_retry(kvm, mmu_seq))
@@ -915,7 +926,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 	if (device)
 		prot |= KVM_PGTABLE_PROT_DEVICE;
-	else if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
+	else if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC) &&
+		 kvm_s2_trans_executable(nested))
 		prot |= KVM_PGTABLE_PROT_X;
 
 	if (fault_status == FSC_PERM && !(logging_active && writable)) {
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index a64895ec6907..551aee363cc3 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -481,7 +481,7 @@ int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu, struct kvm_s2_trans *trans)
 		return 0;
 
 	if (kvm_vcpu_trap_is_iabt(vcpu)) {
-		forward_fault = (trans->upper_attr & BIT(54));
+		forward_fault = !kvm_s2_trans_executable(trans);
 	} else {
 		bool write_fault = kvm_is_write_fault(vcpu);
 
-- 
2.29.2

[PATCH v3 37/66] KVM: arm64: nv: Unmap/flush shadow stage 2 page tables

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@linaro.org>

Unmap/flush shadow stage 2 page tables for the nested VMs as well as the
stage 2 page table for the guest hypervisor.

Note: A bunch of the code in mmu.c relating to MMU notifiers is
currently dealt with in an extremely abrupt way, for example by clearing
out an entire shadow stage-2 table. This will be handled in a more
efficient way using the reverse mapping feature in a later version of
the patch series.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_mmu.h    |  3 +++
 arch/arm64/include/asm/kvm_nested.h |  3 +++
 arch/arm64/kvm/mmu.c                | 34 ++++++++++++++++++++++---
 arch/arm64/kvm/nested.c             | 39 +++++++++++++++++++++++++++++
 4 files changed, 75 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index ec39015bb2a6..e2c58ad46bd1 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -183,6 +183,8 @@ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
 			   void __iomem **haddr);
 int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 			     void **haddr);
+void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu,
+			    phys_addr_t addr, phys_addr_t end);
 void free_hyp_pgds(void);
 
 void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
@@ -191,6 +193,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu);
 void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			  phys_addr_t pa, unsigned long size, bool writable);
+void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
 
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
 
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 3f3d8e10bd99..2987806850f0 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -114,6 +114,9 @@ extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
 extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
 				    struct kvm_s2_trans *trans);
 extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
+extern void kvm_nested_s2_wp(struct kvm *kvm);
+extern void kvm_nested_s2_clear(struct kvm *kvm);
+extern void kvm_nested_s2_flush(struct kvm *kvm);
 int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe);
 extern bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg,
 			    u64 control_bit);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 6f973efb2cc3..36cb9fa22153 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -141,13 +141,20 @@ void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
 	__unmap_stage2_range(mmu, start, size, true);
 }
 
+void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu,
+			    phys_addr_t addr, phys_addr_t end)
+{
+	stage2_apply_range_resched(mmu->kvm, addr, end, kvm_pgtable_stage2_flush);
+}
+
 static void stage2_flush_memslot(struct kvm *kvm,
 				 struct kvm_memory_slot *memslot)
 {
 	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
 	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
+	struct kvm_s2_mmu *mmu = &kvm->arch.mmu;
 
-	stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_flush);
+	kvm_stage2_flush_range(mmu, addr, end);
 }
 
 /**
@@ -170,6 +177,8 @@ static void stage2_flush_vm(struct kvm *kvm)
 	kvm_for_each_memslot(memslot, slots)
 		stage2_flush_memslot(kvm, memslot);
 
+	kvm_nested_s2_flush(kvm);
+
 	spin_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
@@ -465,6 +474,8 @@ void stage2_unmap_vm(struct kvm *kvm)
 	kvm_for_each_memslot(memslot, slots)
 		stage2_unmap_memslot(kvm, memslot);
 
+	kvm_nested_s2_clear(kvm);
+
 	spin_unlock(&kvm->mmu_lock);
 	mmap_read_unlock(current->mm);
 	srcu_read_unlock(&kvm->srcu, idx);
@@ -539,7 +550,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
  * @addr:	Start address of range
  * @end:	End address of range
  */
-static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
+void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
 {
 	struct kvm *kvm = mmu->kvm;
 	stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_wrprotect);
@@ -571,7 +582,8 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
 
 	spin_lock(&kvm->mmu_lock);
-	stage2_wp_range(&kvm->arch.mmu, start, end);
+	kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
+	kvm_nested_s2_wp(kvm);
 	spin_unlock(&kvm->mmu_lock);
 	kvm_flush_remote_tlbs(kvm);
 }
@@ -595,7 +607,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
 	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
 
-	stage2_wp_range(&kvm->arch.mmu, start, end);
+	kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
 }
 
 /*
@@ -610,6 +622,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 		gfn_t gfn_offset, unsigned long mask)
 {
 	kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
+	kvm_nested_s2_wp(kvm);
 }
 
 static void clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
@@ -1164,6 +1177,7 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *dat
 	bool may_block = flags & MMU_NOTIFIER_RANGE_BLOCKABLE;
 
 	__unmap_stage2_range(&kvm->arch.mmu, gpa, size, may_block);
+	kvm_nested_s2_clear(kvm);
 	return 0;
 }
 
@@ -1192,6 +1206,7 @@ static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data
 	 */
 	kvm_pgtable_stage2_map(kvm->arch.mmu.pgt, gpa, PAGE_SIZE,
 			       __pfn_to_phys(*pfn), KVM_PGTABLE_PROT_R, NULL);
+	kvm_nested_s2_clear(kvm);
 	return 0;
 }
 
@@ -1223,12 +1238,22 @@ static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 	kpte = kvm_pgtable_stage2_mkold(kvm->arch.mmu.pgt, gpa);
 	pte = __pte(kpte);
 	return pte_valid(pte) && pte_young(pte);
+
+	/*
+	 * TODO: Handle nested_mmu structures here using the reverse mapping in
+	 * a later version of patch series.
+	 */
 }
 
 static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
 	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
 	return kvm_pgtable_stage2_is_young(kvm->arch.mmu.pgt, gpa);
+
+	/*
+	 * TODO: Handle nested_mmu structures here using the reverse mapping in
+	 * a later version of patch series.
+	 */
 }
 
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
@@ -1457,6 +1482,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 
 	spin_lock(&kvm->mmu_lock);
 	kvm_unmap_stage2_range(&kvm->arch.mmu, gpa, size);
+	kvm_nested_s2_clear(kvm);
 	spin_unlock(&kvm->mmu_lock);
 }
 
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 551aee363cc3..e78c6c093afc 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -505,6 +505,45 @@ int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2)
 	return kvm_inject_nested_sync(vcpu, esr_el2);
 }
 
+/* expects kvm->mmu_lock to be held */
+void kvm_nested_s2_wp(struct kvm *kvm)
+{
+	int i;
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (kvm_s2_mmu_valid(mmu))
+			kvm_stage2_wp_range(mmu, 0, kvm_phys_size(kvm));
+	}
+}
+
+/* expects kvm->mmu_lock to be held */
+void kvm_nested_s2_clear(struct kvm *kvm)
+{
+	int i;
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (kvm_s2_mmu_valid(mmu))
+			kvm_unmap_stage2_range(mmu, 0, kvm_phys_size(kvm));
+	}
+}
+
+/* expects kvm->mmu_lock to be held */
+void kvm_nested_s2_flush(struct kvm *kvm)
+{
+	int i;
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (kvm_s2_mmu_valid(mmu))
+			kvm_stage2_flush_range(mmu, 0, kvm_phys_size(kvm));
+	}
+}
+
 /*
  * Inject wfx to the virtual EL2 if this is not from the virtual EL2 and
  * the virtual HCR_EL2.TWX is set. Otherwise, let the host hypervisor
-- 
2.29.2

[PATCH v3 38/66] KVM: arm64: nv: Introduce sys_reg_desc.forward_trap

[Marc Zyngier]

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

This introduces a function prototype to determine if we need to forward
system instruction traps to the virtual EL2. The implementation of
forward_trap functions for each system instruction will be added in
later patches.

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/sys_regs.c | 8 ++++++++
 arch/arm64/kvm/sys_regs.h | 6 ++++++
 2 files changed, 14 insertions(+)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 090ce14306ba..8f1378dfec6c 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2490,6 +2490,14 @@ static void perform_access(struct kvm_vcpu *vcpu,
 	 */
 	BUG_ON(!r->access);
 
+	/*
+	 * Forward this trap to the virtual EL2 if the guest hypervisor has
+	 * configured to trap the current instruction.
+	 */
+	if (nested_virt_in_use(vcpu) && r->forward_trap
+	    && unlikely(r->forward_trap(vcpu)))
+		return;
+
 	/* Skip instruction if instructed so */
 	if (likely(r->access(vcpu, params, r)))
 		kvm_incr_pc(vcpu);
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index 9d0621417c2a..62ca4119069a 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -58,6 +58,12 @@ struct sys_reg_desc {
 	int (*set_user)(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 			const struct kvm_one_reg *reg, void __user *uaddr);
 
+	/*
+	 * Forward the trap to the virtual EL2 if the guest hypervisor has
+	 * configured to trap the current instruction.
+	 */
+	bool (*forward_trap)(struct kvm_vcpu *vcpu);
+
 	/* Return mask of REG_* runtime visibility overrides */
 	unsigned int (*visibility)(const struct kvm_vcpu *vcpu,
 				   const struct sys_reg_desc *rd);
-- 
2.29.2

[PATCH v3 39/66] KVM: arm64: nv: Set a handler for the system instruction traps

[Marc Zyngier]

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

When HCR.NV bit is set, execution of the EL2 translation regime address
aranslation instructions and TLB maintenance instructions are trapped to
EL2. In addition, execution of the EL1 translation regime address
aranslation instructions and TLB maintenance instructions that are only
accessible from EL2 and above are trapped to EL2. In these cases,
ESR_EL2.EC will be set to 0x18.

Rework the system instruction emulation framework to handle potentially
all system instruction traps other than MSR/MRS instructions. Those
system instructions would be AT and TLBI instructions controlled by
HCR_EL2.NV, AT, and TTLB bits.

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
[maz: squashed two patches together, redispatched various bits around]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h |  4 +--
 arch/arm64/kvm/handle_exit.c      |  2 +-
 arch/arm64/kvm/sys_regs.c         | 48 +++++++++++++++++++++++++------
 3 files changed, 42 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d99e51e7cbee..bf60c50eec17 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -369,7 +369,7 @@ struct kvm_vcpu_arch {
 	/*
 	 * Guest registers we preserve during guest debugging.
 	 *
-	 * These shadow registers are updated by the kvm_handle_sys_reg
+	 * These shadow registers are updated by the kvm_handle_sys
 	 * trap handler if the guest accesses or updates them while we
 	 * are using guest debug.
 	 */
@@ -681,7 +681,7 @@ int kvm_handle_cp14_32(struct kvm_vcpu *vcpu);
 int kvm_handle_cp14_64(struct kvm_vcpu *vcpu);
 int kvm_handle_cp15_32(struct kvm_vcpu *vcpu);
 int kvm_handle_cp15_64(struct kvm_vcpu *vcpu);
-int kvm_handle_sys_reg(struct kvm_vcpu *vcpu);
+int kvm_handle_sys(struct kvm_vcpu *vcpu);
 
 void kvm_reset_sys_regs(struct kvm_vcpu *vcpu);
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 0ad20457d0f1..6e1be999bb00 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -248,7 +248,7 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_SMC32]	= handle_smc,
 	[ESR_ELx_EC_HVC64]	= handle_hvc,
 	[ESR_ELx_EC_SMC64]	= handle_smc,
-	[ESR_ELx_EC_SYS64]	= kvm_handle_sys_reg,
+	[ESR_ELx_EC_SYS64]	= kvm_handle_sys,
 	[ESR_ELx_EC_SVE]	= handle_sve,
 	[ESR_ELx_EC_ERET]	= kvm_handle_eret,
 	[ESR_ELx_EC_IABT_LOW]	= kvm_handle_guest_abort,
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 8f1378dfec6c..35aa1a51aa7d 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1685,10 +1685,6 @@ static bool access_spsr_el2(struct kvm_vcpu *vcpu,
  * more demanding guest...
  */
 static const struct sys_reg_desc sys_reg_descs[] = {
-	{ SYS_DESC(SYS_DC_ISW), access_dcsw },
-	{ SYS_DESC(SYS_DC_CSW), access_dcsw },
-	{ SYS_DESC(SYS_DC_CISW), access_dcsw },
-
 	DBG_BCR_BVR_WCR_WVR_EL1(0),
 	DBG_BCR_BVR_WCR_WVR_EL1(1),
 	{ SYS_DESC(SYS_MDCCINT_EL1), trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
@@ -2119,6 +2115,14 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_SP_EL2), NULL, reset_unknown, SP_EL2 },
 };
 
+#define SYS_INSN_TO_DESC(insn, access_fn, forward_fn)	\
+	{ SYS_DESC((insn)), (access_fn), NULL, 0, 0, NULL, NULL, (forward_fn) }
+static struct sys_reg_desc sys_insn_descs[] = {
+	{ SYS_DESC(SYS_DC_ISW), access_dcsw },
+	{ SYS_DESC(SYS_DC_CSW), access_dcsw },
+	{ SYS_DESC(SYS_DC_CISW), access_dcsw },
+};
+
 static bool trap_dbgidr(struct kvm_vcpu *vcpu,
 			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
@@ -2686,6 +2690,24 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
+static int emulate_sys_instr(struct kvm_vcpu *vcpu, struct sys_reg_params *p)
+{
+	const struct sys_reg_desc *r;
+
+	/* Search from the system instruction table. */
+	r = find_reg(p, sys_insn_descs, ARRAY_SIZE(sys_insn_descs));
+
+	if (likely(r)) {
+		perform_access(vcpu, p, r);
+	} else {
+		kvm_err("Unsupported guest sys instruction at: %lx\n",
+			*vcpu_pc(vcpu));
+		print_sys_reg_instr(p);
+		kvm_inject_undefined(vcpu);
+	}
+	return 1;
+}
+
 /**
  * kvm_reset_sys_regs - sets system registers to reset value
  * @vcpu: The VCPU pointer
@@ -2703,10 +2725,11 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
 }
 
 /**
- * kvm_handle_sys_reg -- handles a mrs/msr trap on a guest sys_reg access
+ * kvm_handle_sys-- handles a system instruction or mrs/msr instruction trap
+		    on a guest execution
  * @vcpu: The VCPU pointer
  */
-int kvm_handle_sys_reg(struct kvm_vcpu *vcpu)
+int kvm_handle_sys(struct kvm_vcpu *vcpu)
 {
 	struct sys_reg_params params;
 	unsigned long esr = kvm_vcpu_get_esr(vcpu);
@@ -2723,10 +2746,16 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu)
 	params.regval = vcpu_get_reg(vcpu, Rt);
 	params.is_write = !(esr & 1);
 
-	ret = emulate_sys_reg(vcpu, &params);
+	if (params.Op0 == 1) {
+		/* System instructions */
+		ret = emulate_sys_instr(vcpu, &params);
+	} else {
+		/* MRS/MSR instructions */
+		ret = emulate_sys_reg(vcpu, &params);
+		if (!params.is_write)
+			vcpu_set_reg(vcpu, Rt, params.regval);
+	}
 
-	if (!params.is_write)
-		vcpu_set_reg(vcpu, Rt, params.regval);
 	return ret;
 }
 
@@ -3142,6 +3171,7 @@ void kvm_sys_reg_table_init(void)
 	BUG_ON(check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs), true));
 	BUG_ON(check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs), true));
 	BUG_ON(check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs), false));
+	BUG_ON(check_sysreg_table(sys_insn_descs, ARRAY_SIZE(sys_insn_descs), false));
 
 	/* We abuse the reset function to overwrite the table itself. */
 	for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++)
-- 
2.29.2

[PATCH v3 40/66] KVM: arm64: nv: Trap and emulate AT instructions from virtual EL2

[Marc Zyngier]

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

When supporting nested virtualization a guest hypervisor executing AT
instructions must be trapped and emulated by the host hypervisor,
because untrapped AT instructions operating on S1E1 will use the wrong
translation regieme (the one used to emulate virtual EL2 in EL1 instead
of virtual EL1) and AT instructions operating on S12 will not work from
EL1.

This patch does several things.

1. List and define all AT system instructions to emulate and document
the emulation design.

2. Implement AT instruction handling logic in EL2. This will be used to
emulate AT instructions executed in the virtual EL2.

AT instruction emulation works by loading the proper processor
context, which depends on the trapped instruction and the virtual
HCR_EL2, to the EL1 virtual memory control registers and executing AT
instructions. Note that ctxt->hw_sys_regs is expected to have the
proper processor context before calling the handling
function(__kvm_at_insn) implemented in this patch.

4. Emulate AT S1E[01] instructions by issuing the same instructions in
EL2. We set the physical EL1 registers, NV and NV1 bits as described in
the AT instruction emulation overview.

5. Emulate AT A12E[01] instructions in two steps: First, do the stage-1
translation by reusing the existing AT emulation functions.  Second, do
the stage-2 translation by walking the guest hypervisor's stage-2 page
table in software. Record the translation result to PAR_EL1.

6. Emulate AT S1E2 instructions by issuing the corresponding S1E1
instructions in EL2. We set the physical EL1 registers and the HCR_EL2
register as described in the AT instruction emulation overview.

7. Forward system instruction traps to the virtual EL2 if the corresponding
virtual AT bit is set in the virtual HCR_EL2.

  [ Much logic above has been reworked by Marc Zyngier ]

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
---
 arch/arm64/include/asm/kvm_arm.h |   2 +
 arch/arm64/include/asm/kvm_asm.h |   2 +
 arch/arm64/include/asm/sysreg.h  |  17 +++
 arch/arm64/kvm/Makefile          |   2 +-
 arch/arm64/kvm/at.c              | 231 +++++++++++++++++++++++++++++++
 arch/arm64/kvm/hyp/vhe/switch.c  |  13 +-
 arch/arm64/kvm/sys_regs.c        | 201 ++++++++++++++++++++++++++-
 7 files changed, 463 insertions(+), 5 deletions(-)
 create mode 100644 arch/arm64/kvm/at.c

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 347e9e9b015c..0d88a7c51dec 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -14,6 +14,7 @@
 /* Hyp Configuration Register (HCR) bits */
 #define HCR_ATA		(UL(1) << 56)
 #define HCR_FWB		(UL(1) << 46)
+#define HCR_AT		(UL(1) << 44)
 #define HCR_NV1		(UL(1) << 43)
 #define HCR_NV		(UL(1) << 42)
 #define HCR_API		(UL(1) << 41)
@@ -110,6 +111,7 @@
 #define VTCR_EL2_TG0_16K	TCR_TG0_16K
 #define VTCR_EL2_TG0_64K	TCR_TG0_64K
 #define VTCR_EL2_SH0_MASK	TCR_SH0_MASK
+#define VTCR_EL2_SH0_SHIFT	TCR_SH0_SHIFT
 #define VTCR_EL2_SH0_INNER	TCR_SH0_INNER
 #define VTCR_EL2_ORGN0_MASK	TCR_ORGN0_MASK
 #define VTCR_EL2_ORGN0_WBWA	TCR_ORGN0_WBWA
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index fa8e886998a3..8bda33d026ca 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -189,6 +189,8 @@ extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
 extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
+extern void __kvm_at_s1e01(struct kvm_vcpu *vcpu, u32 op, u64 vaddr);
+extern void __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 05b49eafbb49..4131a0c5df6e 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -591,6 +591,23 @@
 
 #define SYS_SP_EL2			sys_reg(3, 6,  4, 1, 0)
 
+/* AT instructions */
+#define AT_Op0 1
+#define AT_CRn 7
+
+#define OP_AT_S1E1R	sys_insn(AT_Op0, 0, AT_CRn, 8, 0)
+#define OP_AT_S1E1W	sys_insn(AT_Op0, 0, AT_CRn, 8, 1)
+#define OP_AT_S1E0R	sys_insn(AT_Op0, 0, AT_CRn, 8, 2)
+#define OP_AT_S1E0W	sys_insn(AT_Op0, 0, AT_CRn, 8, 3)
+#define OP_AT_S1E1RP	sys_insn(AT_Op0, 0, AT_CRn, 9, 0)
+#define OP_AT_S1E1WP	sys_insn(AT_Op0, 0, AT_CRn, 9, 1)
+#define OP_AT_S1E2R	sys_insn(AT_Op0, 4, AT_CRn, 8, 0)
+#define OP_AT_S1E2W	sys_insn(AT_Op0, 4, AT_CRn, 8, 1)
+#define OP_AT_S12E1R	sys_insn(AT_Op0, 4, AT_CRn, 8, 4)
+#define OP_AT_S12E1W	sys_insn(AT_Op0, 4, AT_CRn, 8, 5)
+#define OP_AT_S12E0R	sys_insn(AT_Op0, 4, AT_CRn, 8, 6)
+#define OP_AT_S12E0W	sys_insn(AT_Op0, 4, AT_CRn, 8, 7)
+
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_DSSBS	(BIT(44))
 #define SCTLR_ELx_ATA	(BIT(43))
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 7bb1d1314cad..8a23991f82b2 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -17,7 +17,7 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 guest.o debug.o reset.o sys_regs.o \
 	 vgic-sys-reg-v3.o fpsimd.o pmu.o \
 	 arch_timer.o \
-	 emulate-nested.o nested.o \
+	 emulate-nested.o nested.o at.o \
 	 vgic/vgic.o vgic/vgic-init.o \
 	 vgic/vgic-irqfd.o vgic/vgic-v2.o \
 	 vgic/vgic-v3.o vgic/vgic-v4.o \
diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
new file mode 100644
index 000000000000..c345ef98ca1e
--- /dev/null
+++ b/arch/arm64/kvm/at.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 - Linaro Ltd
+ * Author: Jintack Lim <jintack.lim@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+
+struct mmu_config {
+	u64	ttbr0;
+	u64	ttbr1;
+	u64	tcr;
+	u64	sctlr;
+	u64	vttbr;
+	u64	vtcr;
+	u64	hcr;
+};
+
+static void __mmu_config_save(struct mmu_config *config)
+{
+	config->ttbr0	= read_sysreg_el1(SYS_TTBR0);
+	config->ttbr1	= read_sysreg_el1(SYS_TTBR1);
+	config->tcr	= read_sysreg_el1(SYS_TCR);
+	config->sctlr	= read_sysreg_el1(SYS_SCTLR);
+	config->vttbr	= read_sysreg(vttbr_el2);
+	config->vtcr	= read_sysreg(vtcr_el2);
+	config->hcr	= read_sysreg(hcr_el2);
+}
+
+static void __mmu_config_restore(struct mmu_config *config)
+{
+	write_sysreg_el1(config->ttbr0,	SYS_TTBR0);
+	write_sysreg_el1(config->ttbr1,	SYS_TTBR1);
+	write_sysreg_el1(config->tcr,	SYS_TCR);
+	write_sysreg_el1(config->sctlr,	SYS_SCTLR);
+	write_sysreg(config->vttbr,	vttbr_el2);
+	write_sysreg(config->vtcr,	vtcr_el2);
+	write_sysreg(config->hcr,	hcr_el2);
+
+	isb();
+}
+
+void __kvm_at_s1e01(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
+{
+	struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
+	struct mmu_config config;
+	struct kvm_s2_mmu *mmu;
+
+	spin_lock(&vcpu->kvm->mmu_lock);
+
+	/*
+	 * If HCR_EL2.{E2H,TGE} == {1,1}, the MMU context is already
+	 * the right one (as we trapped from vEL2).
+	 */
+	if (vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu))
+		goto skip_mmu_switch;
+
+	/*
+	 * FIXME: Obtaining the S2 MMU for a guest guest is horribly
+	 * racy, and we may not find it (evicted by another vcpu, for
+	 * example).
+	 */
+	mmu = lookup_s2_mmu(vcpu->kvm,
+			    vcpu_read_sys_reg(vcpu, VTTBR_EL2),
+			    vcpu_read_sys_reg(vcpu, HCR_EL2));
+
+	if (WARN_ON(!mmu))
+		goto out;
+
+	/* We've trapped, so everything is live on the CPU. */
+	__mmu_config_save(&config);
+
+	write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR0_EL1),	SYS_TTBR0);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR1_EL1),	SYS_TTBR1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1),	SYS_SCTLR);
+	write_sysreg(kvm_get_vttbr(mmu),		vttbr_el2);
+	/*
+	 * REVISIT: do we need anything from the guest's VTCR_EL2? If
+	 * looks like keeping the hosts configuration is the right
+	 * thing to do at this stage (and we could avoid save/restore
+	 * it. Keep the host's version for now.
+	 */
+	write_sysreg((config.hcr & ~HCR_TGE) | HCR_VM,	hcr_el2);
+
+	isb();
+
+skip_mmu_switch:
+
+	switch (op) {
+	case OP_AT_S1E1R:
+	case OP_AT_S1E1RP:
+		asm volatile("at s1e1r, %0" : : "r" (vaddr));
+		break;
+	case OP_AT_S1E1W:
+	case OP_AT_S1E1WP:
+		asm volatile("at s1e1w, %0" : : "r" (vaddr));
+		break;
+	case OP_AT_S1E0R:
+		asm volatile("at s1e0r, %0" : : "r" (vaddr));
+		break;
+	case OP_AT_S1E0W:
+		asm volatile("at s1e0w, %0" : : "r" (vaddr));
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	isb();
+
+	ctxt_sys_reg(ctxt, PAR_EL1) = read_sysreg(par_el1);
+
+	/*
+	 * Failed? let's leave the building now.
+	 *
+	 * FIXME: how about a failed translation because the shadow S2
+	 * wasn't populated? We may need to perform a SW PTW,
+	 * populating our shadow S2 and retry the instruction.
+	 */
+	if (ctxt_sys_reg(ctxt, PAR_EL1) & 1)
+		goto nopan;
+
+	/* No PAN? No problem. */
+	if (!(*vcpu_cpsr(vcpu) & PSR_PAN_BIT))
+		goto nopan;
+
+	/*
+	 * For PAN-involved AT operations, perform the same
+	 * translation, using EL0 this time.
+	 */
+	switch (op) {
+	case OP_AT_S1E1RP:
+		asm volatile("at s1e0r, %0" : : "r" (vaddr));
+		break;
+	case OP_AT_S1E1WP:
+		asm volatile("at s1e0w, %0" : : "r" (vaddr));
+		break;
+	default:
+		goto nopan;
+	}
+
+	/*
+	 * If the EL0 translation has succeeded, we need to pretend
+	 * the AT operation has failed, as the PAN setting forbids
+	 * such a translation.
+	 *
+	 * FIXME: we hardcode a Level-3 permission fault. We really
+	 * should return the real fault level.
+	 */
+	if (!(read_sysreg(par_el1) & 1))
+		ctxt_sys_reg(ctxt, PAR_EL1) = 0x1f;
+
+nopan:
+	if (!(vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)))
+		__mmu_config_restore(&config);
+
+out:
+	spin_unlock(&vcpu->kvm->mmu_lock);
+}
+
+void __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
+{
+	struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
+	struct mmu_config config;
+	struct kvm_s2_mmu *mmu;
+	u64 val;
+
+	spin_lock(&vcpu->kvm->mmu_lock);
+
+	mmu = &vcpu->kvm->arch.mmu;
+
+	/* We've trapped, so everything is live on the CPU. */
+	__mmu_config_save(&config);
+
+	if (vcpu_el2_e2h_is_set(vcpu)) {
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR0_EL2),	SYS_TTBR0);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR1_EL2),	SYS_TTBR1);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL2),	SYS_TCR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL2),	SYS_SCTLR);
+
+		val = config.hcr;
+	} else {
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR0_EL2),	SYS_TTBR0);
+		val = translate_tcr_el2_to_tcr_el1(ctxt_sys_reg(ctxt, TCR_EL2));
+		write_sysreg_el1(val, SYS_TCR);
+		val = translate_sctlr_el2_to_sctlr_el1(ctxt_sys_reg(ctxt, SCTLR_EL2));
+		write_sysreg_el1(val, SYS_SCTLR);
+
+		val = config.hcr | HCR_NV | HCR_NV1;
+	}
+
+	write_sysreg(kvm_get_vttbr(mmu),		vttbr_el2);
+	/* FIXME: write S2 MMU VTCR_EL2? */
+	write_sysreg((val & ~HCR_TGE) | HCR_VM,		hcr_el2);
+
+	isb();
+
+	switch (op) {
+	case OP_AT_S1E2R:
+		asm volatile("at s1e1r, %0" : : "r" (vaddr));
+		break;
+	case OP_AT_S1E2W:
+		asm volatile("at s1e1w, %0" : : "r" (vaddr));
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	isb();
+
+	/* FIXME: handle failed translation due to shadow S2 */
+	ctxt_sys_reg(ctxt, PAR_EL1) = read_sysreg(par_el1);
+
+	__mmu_config_restore(&config);
+	spin_unlock(&vcpu->kvm->mmu_lock);
+}
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 940d88ffd53e..396d329e015d 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -45,9 +45,10 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		if (!vcpu_el2_e2h_is_set(vcpu)) {
 			/*
 			 * For a guest hypervisor on v8.0, trap and emulate
-			 * the EL1 virtual memory control register accesses.
+			 * the EL1 virtual memory control register accesses
+			 * as well as the AT S1 operations.
 			 */
-			hcr |= HCR_TVM | HCR_TRVM | HCR_NV1;
+			hcr |= HCR_TVM | HCR_TRVM | HCR_AT | HCR_NV1;
 		} else {
 			/*
 			 * For a guest hypervisor on v8.1 (VHE), allow to
@@ -70,6 +71,14 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 			hcr &= ~HCR_TVM;
 
 			hcr |= vhcr_el2 & (HCR_TVM | HCR_TRVM);
+
+			/*
+			 * If we're using the EL1 translation regime
+			 * (TGE clear), then ensure that AT S1 ops are
+			 * trapped too.
+			 */
+			if (!vcpu_el2_tge_is_set(vcpu))
+				hcr |= HCR_AT;
 		}
 	}
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 35aa1a51aa7d..6b7a7ce9b1a3 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1618,6 +1618,10 @@ static bool access_sp_el1(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool forward_at_traps(struct kvm_vcpu *vcpu)
+{
+	return forward_traps(vcpu, HCR_AT);
+}
 
 static bool access_elr(struct kvm_vcpu *vcpu,
 		       struct sys_reg_params *p,
@@ -2115,12 +2119,205 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_SP_EL2), NULL, reset_unknown, SP_EL2 },
 };
 
-#define SYS_INSN_TO_DESC(insn, access_fn, forward_fn)	\
-	{ SYS_DESC((insn)), (access_fn), NULL, 0, 0, NULL, NULL, (forward_fn) }
+static bool handle_s1e01(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	int sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+
+	__kvm_at_s1e01(vcpu, sys_encoding, p->regval);
+
+	return true;
+}
+
+static bool handle_s1e2(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
+{
+	int sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+
+	__kvm_at_s1e2(vcpu, sys_encoding, p->regval);
+
+	return true;
+}
+
+static u64 setup_par_aborted(u32 esr)
+{
+	u64 par = 0;
+
+	/* S [9]: fault in the stage 2 translation */
+	par |= (1 << 9);
+	/* FST [6:1]: Fault status code  */
+	par |= (esr << 1);
+	/* F [0]: translation is aborted */
+	par |= 1;
+
+	return par;
+}
+
+static u64 setup_par_completed(struct kvm_vcpu *vcpu, struct kvm_s2_trans *out)
+{
+	u64 par, vtcr_sh0;
+
+	/* F [0]: Translation is completed successfully */
+	par = 0;
+	/* ATTR [63:56] */
+	par |= out->upper_attr;
+	/* PA [47:12] */
+	par |= out->output & GENMASK_ULL(11, 0);
+	/* RES1 [11] */
+	par |= (1UL << 11);
+	/* SH [8:7]: Shareability attribute */
+	vtcr_sh0 = vcpu_read_sys_reg(vcpu, VTCR_EL2) & VTCR_EL2_SH0_MASK;
+	par |= (vtcr_sh0 >> VTCR_EL2_SH0_SHIFT) << 7;
+
+	return par;
+}
+
+static bool handle_s12(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+		       const struct sys_reg_desc *r, bool write)
+{
+	u64 par, va;
+	u32 esr;
+	phys_addr_t ipa;
+	struct kvm_s2_trans out;
+	int ret;
+
+	/* Do the stage-1 translation */
+	handle_s1e01(vcpu, p, r);
+	par = vcpu_read_sys_reg(vcpu, PAR_EL1);
+	if (par & 1) {
+		/* The stage-1 translation aborted */
+		return true;
+	}
+
+	/* Do the stage-2 translation */
+	va = p->regval;
+	ipa = (par & GENMASK_ULL(47, 12)) | (va & GENMASK_ULL(11, 0));
+	out.esr = 0;
+	ret = kvm_walk_nested_s2(vcpu, ipa, &out);
+	if (ret < 0)
+		return false;
+
+	/* Check if the stage-2 PTW is aborted */
+	if (out.esr) {
+		esr = out.esr;
+		goto s2_trans_abort;
+	}
+
+	/* Check the access permission */
+	if ((!write && !out.readable) || (write && !out.writable)) {
+		esr = ESR_ELx_FSC_PERM;
+		esr |= out.level & 0x3;
+		goto s2_trans_abort;
+	}
+
+	vcpu_write_sys_reg(vcpu, setup_par_completed(vcpu, &out), PAR_EL1);
+	return true;
+
+s2_trans_abort:
+	vcpu_write_sys_reg(vcpu, setup_par_aborted(esr), PAR_EL1);
+	return true;
+}
+
+static bool handle_s12r(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
+{
+	return handle_s12(vcpu, p, r, false);
+}
+
+static bool handle_s12w(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
+{
+	return handle_s12(vcpu, p, r, true);
+}
+
+/*
+ * AT instruction emulation
+ *
+ * We emulate AT instructions executed in the virtual EL2.
+ * Basic strategy for the stage-1 translation emulation is to load proper
+ * context, which depends on the trapped instruction and the virtual HCR_EL2,
+ * to the EL1 virtual memory control registers and execute S1E[01] instructions
+ * in EL2. See below for more detail.
+ *
+ * For the stage-2 translation, which is necessary for S12E[01] emulation,
+ * we walk the guest hypervisor's stage-2 page table in software.
+ *
+ * The stage-1 translation emulations can be divided into two groups depending
+ * on the translation regime.
+ *
+ * 1. EL2 AT instructions: S1E2x
+ * +-----------------------------------------------------------------------+
+ * |                             |         Setting for the emulation       |
+ * | Virtual HCR_EL2.E2H on trap |-----------------------------------------+
+ * |                             | Phys EL1 regs | Phys NV, NV1 | Phys TGE |
+ * |-----------------------------------------------------------------------|
+ * |             0               |     vEL2      |    (1, 1)    |    0     |
+ * |             1               |     vEL2      |    (0, 0)    |    0     |
+ * +-----------------------------------------------------------------------+
+ *
+ * We emulate the EL2 AT instructions by loading virtual EL2 context
+ * to the EL1 virtual memory control registers and executing corresponding
+ * EL1 AT instructions.
+ *
+ * We set physical NV and NV1 bits to use EL2 page table format for non-VHE
+ * guest hypervisor (i.e. HCR_EL2.E2H == 0). As a VHE guest hypervisor uses the
+ * EL1 page table format, we don't set those bits.
+ *
+ * We should clear physical TGE bit not to use the EL2 translation regime when
+ * the host uses the VHE feature.
+ *
+ *
+ * 2. EL0/EL1 AT instructions: S1E[01]x, S12E1x
+ * +----------------------------------------------------------------------+
+ * |   Virtual HCR_EL2 on trap  |        Setting for the emulation        |
+ * |----------------------------------------------------------------------+
+ * | (vE2H, vTGE) | (vNV, vNV1) | Phys EL1 regs | Phys NV, NV1 | Phys TGE |
+ * |----------------------------------------------------------------------|
+ * |    (0, 0)*   |   (0, 0)    |      vEL1     |    (0, 0)    |    0     |
+ * |    (0, 0)    |   (1, 1)    |      vEL1     |    (1, 1)    |    0     |
+ * |    (1, 1)    |   (0, 0)    |      vEL2     |    (0, 0)    |    0     |
+ * |    (1, 1)    |   (1, 1)    |      vEL2     |    (1, 1)    |    0     |
+ * +----------------------------------------------------------------------+
+ *
+ * *For (0, 0) in the 'Virtual HCR_EL2 on trap' column, it actually means
+ *  (1, 1). Keep them (0, 0) just for the readability.
+ *
+ * We set physical EL1 virtual memory control registers depending on
+ * (vE2H, vTGE) pair. When the pair is (0, 0) where AT instructions are
+ * supposed to use EL0/EL1 translation regime, we load the EL1 registers with
+ * the virtual EL1 registers (i.e. EL1 registers from the guest hypervisor's
+ * point of view). When the pair is (1, 1), however, AT instructions are defined
+ * to apply EL2 translation regime. To emulate this behavior, we load the EL1
+ * registers with the virtual EL2 context. (i.e the shadow registers)
+ *
+ * We respect the virtual NV and NV1 bit for the emulation. When those bits are
+ * set, it means that a guest hypervisor would like to use EL2 page table format
+ * for the EL1 translation regime. We emulate this by setting the physical
+ * NV and NV1 bits.
+ */
+
+#define SYS_INSN_TO_DESC(insn, access_fn, forward_fn)			\
+	{ SYS_DESC(OP_##insn), (access_fn), NULL, 0, 0,			\
+	  NULL, NULL, (forward_fn) }
 static struct sys_reg_desc sys_insn_descs[] = {
 	{ SYS_DESC(SYS_DC_ISW), access_dcsw },
+
+	SYS_INSN_TO_DESC(AT_S1E1R, handle_s1e01, forward_at_traps),
+	SYS_INSN_TO_DESC(AT_S1E1W, handle_s1e01, forward_at_traps),
+	SYS_INSN_TO_DESC(AT_S1E0R, handle_s1e01, forward_at_traps),
+	SYS_INSN_TO_DESC(AT_S1E0W, handle_s1e01, forward_at_traps),
+	SYS_INSN_TO_DESC(AT_S1E1RP, handle_s1e01, forward_at_traps),
+	SYS_INSN_TO_DESC(AT_S1E1WP, handle_s1e01, forward_at_traps),
+
 	{ SYS_DESC(SYS_DC_CSW), access_dcsw },
 	{ SYS_DESC(SYS_DC_CISW), access_dcsw },
+
+	SYS_INSN_TO_DESC(AT_S1E2R, handle_s1e2, forward_nv_traps),
+	SYS_INSN_TO_DESC(AT_S1E2W, handle_s1e2, forward_nv_traps),
+	SYS_INSN_TO_DESC(AT_S12E1R, handle_s12r, forward_nv_traps),
+	SYS_INSN_TO_DESC(AT_S12E1W, handle_s12w, forward_nv_traps),
+	SYS_INSN_TO_DESC(AT_S12E0R, handle_s12r, forward_nv_traps),
+	SYS_INSN_TO_DESC(AT_S12E0W, handle_s12w, forward_nv_traps),
 };
 
 static bool trap_dbgidr(struct kvm_vcpu *vcpu,
-- 
2.29.2

[PATCH v3 41/66] KVM: arm64: nv: Trap and emulate TLBI instructions from virtual EL2

[Marc Zyngier]

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

When supporting nested virtualization a guest hypervisor executing TLBI
instructions must be trapped and emulated by the host hypervisor,
because the guest hypervisor can only affect physical TLB entries
relating to its own execution environment (virtual EL2 in EL1) but not
to the nested guests as required by the semantics of the instructions
and TLBI instructions might also result in updates (invalidations) to
shadow page tables.

This patch does several things.

1. List and define all TLBI system instructions to emulate.

2. Emulate TLBI ALLE2(IS) instruction executed in the virtual EL2. Since
we emulate the virtual EL2 in the EL1, we invalidate EL1&0 regime stage
1 TLB entries with setting vttbr_el2 having the VMID of the virtual EL2.

3. Emulate TLBI VAE2* instruction executed in the virtual EL2. Based on the
same principle as TLBI ALLE2 instruction, we can simply emulate those
instructions by executing corresponding VAE1* instructions with the
virtual EL2's VMID assigned by the host hypervisor.

Note that we are able to emulate TLBI ALLE2IS precisely by only
invalidating stage 1 TLB entries via TLBI VMALL1IS instruction, but to
make it simeple, we reuse the existing function, __kvm_tlb_flush_vmid(),
which invalidates both of stage 1 and 2 TLB entries.

4. TLBI ALLE1(IS) instruction invalidates all EL1&0 regime stage 1 and 2
TLB entries (on all PEs in the same Inner Shareable domain). To emulate
these instructions, we first need to clear all the mappings in the
shadow page tables since executing those instructions implies the change
of mappings in the stage 2 page tables maintained by the guest
hypervisor.  We then need to invalidate all EL1&0 regime stage 1 and 2
TLB entries of all VMIDs, which are assigned by the host hypervisor, for
this VM.

5. Based on the same principle as TLBI ALLE1(IS) emulation, we clear the
mappings in the shadow stage-2 page tables and invalidate TLB entries.
But this time we do it only for the current VMID from the guest
hypervisor's perspective, not for all VMIDs.

6. Based on the same principle as TLBI ALLE1(IS) and TLBI VMALLS12E1(IS)
emulation, we clear the mappings in the shadow stage-2 page tables and
invalidate TLB entries. We do it only for one mapping for the current
VMID from the guest hypervisor's view.

7. Forward system instruction traps to the virtual EL2 if a
corresponding bit in the virtual HCR_EL2 is set.

8. Even though a guest hypervisor can execute TLBI instructions that are
accesible at EL1 without trap, it's wrong; All those TLBI instructions
work based on current VMID, and when running a guest hypervisor current
VMID is the one for itself, not the one from the virtual vttbr_el2. So
letting a guest hypervisor execute those TLBI instructions results in
invalidating its own TLB entries and leaving invalid TLB entries
unhandled.

Therefore we trap and emulate those TLBI instructions. The emulation is
simple; we find a shadow VMID mapped to the virtual vttbr_el2, set it in
the physical vttbr_el2, then execute the same instruction in EL2.

We don't set HCR_EL2.TTLB bit yet.

  [ Changes performed by Marc Zynger:

    The TLBI handling code more or less directly execute the same
    instruction that has been trapped (with an EL2->EL1 conversion
    in the case of an EL2 TLBI), but that's unfortunately not enough:

    - TLBIs must be upgraded to the Inner Shareable domain to account
      for vcpu migration, just like we already have with HCR_EL2.FB.

    - The DSB instruction that synchronises these must thus be on
      the Inner Shareable domain as well.

    - Prior to executing the TLBI, we need another DSB ISHST to make
      sure that the update to the page tables is now visible.

      Ordering of system instructions fixed

    - The current TLB invalidation code is pretty buggy, as it assume a
      page mapping. On the contrary, it is likely that TLB invalidation
      will cover more than a single page, and the size should be decided
      by the guests configuration (and not the host's).

      Since we don't cache the guest mapping sizes in the shadow PT yet,
      let's assume the worse case (a block mapping) and invalidate that.

      Take this opportunity to fix the decoding of the parameter (it
      isn't a straight IPA).

    - In general, we always emulate local TBL invalidations as being
      as upgraded to the Inner Shareable domain so that we can easily
      deal with vcpu migration. This is consistent with the fact that
      we set HCR_EL2.FB when running non-nested VMs.

      So let's emulate TLBI ALLE2 as ALLE2IS.
  ]

  [ Changes performed by Christoffer Dall:

    Sometimes when we are invalidating the TLB for a certain S2 MMU
    context, this context can also have EL2 context associated with it
    and we have to invalidate this too.
  ]

Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_asm.h |   2 +
 arch/arm64/include/asm/sysreg.h  |  36 ++++++
 arch/arm64/kvm/hyp/vhe/switch.c  |   8 +-
 arch/arm64/kvm/hyp/vhe/tlb.c     |  81 ++++++++++++
 arch/arm64/kvm/mmu.c             |  18 ++-
 arch/arm64/kvm/sys_regs.c        | 212 +++++++++++++++++++++++++++++++
 6 files changed, 352 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 8bda33d026ca..2fae66fb2c86 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -187,6 +187,8 @@ extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
 				     int level);
 extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
 extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu);
+extern void __kvm_tlb_vae2is(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding);
+extern void __kvm_tlb_el1_instr(struct kvm_s2_mmu *mmu, u64 val, u64 sys_encoding);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 extern void __kvm_at_s1e01(struct kvm_vcpu *vcpu, u32 op, u64 vaddr);
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 4131a0c5df6e..814fb57b55d9 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -608,6 +608,42 @@
 #define OP_AT_S12E0R	sys_insn(AT_Op0, 4, AT_CRn, 8, 6)
 #define OP_AT_S12E0W	sys_insn(AT_Op0, 4, AT_CRn, 8, 7)
 
+/* TLBI instructions */
+#define TLBI_Op0	1
+#define TLBI_Op1_EL1	0	/* Accessible from EL1 or higher */
+#define TLBI_Op1_EL2	4	/* Accessible from EL2 or higher */
+#define TLBI_CRn	8
+#define tlbi_insn_el1(CRm, Op2)	sys_insn(TLBI_Op0, TLBI_Op1_EL1, TLBI_CRn, (CRm), (Op2))
+#define tlbi_insn_el2(CRm, Op2)	sys_insn(TLBI_Op0, TLBI_Op1_EL2, TLBI_CRn, (CRm), (Op2))
+
+#define OP_TLBI_VMALLE1IS	tlbi_insn_el1(3, 0)
+#define OP_TLBI_VAE1IS		tlbi_insn_el1(3, 1)
+#define OP_TLBI_ASIDE1IS	tlbi_insn_el1(3, 2)
+#define OP_TLBI_VAAE1IS		tlbi_insn_el1(3, 3)
+#define OP_TLBI_VALE1IS		tlbi_insn_el1(3, 5)
+#define OP_TLBI_VAALE1IS	tlbi_insn_el1(3, 7)
+#define OP_TLBI_VMALLE1		tlbi_insn_el1(7, 0)
+#define OP_TLBI_VAE1		tlbi_insn_el1(7, 1)
+#define OP_TLBI_ASIDE1		tlbi_insn_el1(7, 2)
+#define OP_TLBI_VAAE1		tlbi_insn_el1(7, 3)
+#define OP_TLBI_VALE1		tlbi_insn_el1(7, 5)
+#define OP_TLBI_VAALE1		tlbi_insn_el1(7, 7)
+
+#define OP_TLBI_IPAS2E1IS	tlbi_insn_el2(0, 1)
+#define OP_TLBI_IPAS2LE1IS	tlbi_insn_el2(0, 5)
+#define OP_TLBI_ALLE2IS		tlbi_insn_el2(3, 0)
+#define OP_TLBI_VAE2IS		tlbi_insn_el2(3, 1)
+#define OP_TLBI_ALLE1IS		tlbi_insn_el2(3, 4)
+#define OP_TLBI_VALE2IS		tlbi_insn_el2(3, 5)
+#define OP_TLBI_VMALLS12E1IS	tlbi_insn_el2(3, 6)
+#define OP_TLBI_IPAS2E1		tlbi_insn_el2(4, 1)
+#define OP_TLBI_IPAS2LE1	tlbi_insn_el2(4, 5)
+#define OP_TLBI_ALLE2		tlbi_insn_el2(7, 0)
+#define OP_TLBI_VAE2		tlbi_insn_el2(7, 1)
+#define OP_TLBI_ALLE1		tlbi_insn_el2(7, 4)
+#define OP_TLBI_VALE2		tlbi_insn_el2(7, 5)
+#define OP_TLBI_VMALLS12E1	tlbi_insn_el2(7, 6)
+
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_DSSBS	(BIT(44))
 #define SCTLR_ELx_ATA	(BIT(43))
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 396d329e015d..bac6ccc2595c 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -48,7 +48,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 			 * the EL1 virtual memory control register accesses
 			 * as well as the AT S1 operations.
 			 */
-			hcr |= HCR_TVM | HCR_TRVM | HCR_AT | HCR_NV1;
+			hcr |= HCR_TVM | HCR_TRVM | HCR_AT | HCR_TTLB | HCR_NV1;
 		} else {
 			/*
 			 * For a guest hypervisor on v8.1 (VHE), allow to
@@ -74,11 +74,11 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 
 			/*
 			 * If we're using the EL1 translation regime
-			 * (TGE clear), then ensure that AT S1 ops are
-			 * trapped too.
+			 * (TGE clear), then ensure that AT S1 and
+			 * TLBI E1 ops are trapped too.
 			 */
 			if (!vcpu_el2_tge_is_set(vcpu))
-				hcr |= HCR_AT;
+				hcr |= HCR_AT | HCR_TTLB;
 		}
 	}
 
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index fd7895945bbc..52fda1d61308 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -160,3 +160,84 @@ void __kvm_flush_vm_context(void)
 
 	dsb(ish);
 }
+
+void __kvm_tlb_vae2is(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
+{
+	struct tlb_inv_context cxt;
+
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	__tlb_switch_to_guest(mmu, &cxt);
+
+	/*
+	 * Execute the EL1 version of TLBI VAE2* instruction, forcing
+	 * an upgrade to the Inner Shareable domain in order to
+	 * perform the invalidation on all CPUs.
+	 */
+	switch (sys_encoding) {
+	case OP_TLBI_VAE2:
+	case OP_TLBI_VAE2IS:
+		__tlbi(vae1is, va);
+		break;
+	case OP_TLBI_VALE2:
+	case OP_TLBI_VALE2IS:
+		__tlbi(vale1is, va);
+		break;
+	default:
+		break;
+	}
+	dsb(ish);
+	isb();
+
+	__tlb_switch_to_host(&cxt);
+}
+
+void __kvm_tlb_el1_instr(struct kvm_s2_mmu *mmu, u64 val, u64 sys_encoding)
+{
+	struct tlb_inv_context cxt;
+
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	__tlb_switch_to_guest(mmu, &cxt);
+
+	/*
+	 * Execute the same instruction as the guest hypervisor did,
+	 * expanding the scope of local TLB invalidations to the Inner
+	 * Shareable domain so that it takes place on all CPUs. This
+	 * is equivalent to having HCR_EL2.FB set.
+	 */
+	switch (sys_encoding) {
+	case OP_TLBI_VMALLE1:
+	case OP_TLBI_VMALLE1IS:
+		__tlbi(vmalle1is);
+		break;
+	case OP_TLBI_VAE1:
+	case OP_TLBI_VAE1IS:
+		__tlbi(vae1is, val);
+		break;
+	case OP_TLBI_ASIDE1:
+	case OP_TLBI_ASIDE1IS:
+		__tlbi(aside1is, val);
+		break;
+	case OP_TLBI_VAAE1:
+	case OP_TLBI_VAAE1IS:
+		__tlbi(vaae1is, val);
+		break;
+	case OP_TLBI_VALE1:
+	case OP_TLBI_VALE1IS:
+		__tlbi(vale1is, val);
+		break;
+	case OP_TLBI_VAALE1:
+	case OP_TLBI_VAALE1IS:
+		__tlbi(vaale1is, val);
+		break;
+	default:
+		break;
+	}
+	dsb(ish);
+	isb();
+
+	__tlb_switch_to_host(&cxt);
+}
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 36cb9fa22153..5fb13995190e 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -80,7 +80,23 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot)
  */
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
-	kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
+	struct kvm_s2_mmu *mmu = &kvm->arch.mmu;
+
+	if (mmu == &kvm->arch.mmu) {
+		/*
+		 * For a normal (i.e. non-nested) guest, flush entries for the
+		 * given VMID *
+		 */
+		kvm_call_hyp(__kvm_tlb_flush_vmid, mmu);
+	} else {
+		/*
+		 * When supporting nested virtualization, we can have multiple
+		 * VMIDs in play for each VCPU in the VM, so it's really not
+		 * worth it to try to quiesce the system and flush all the
+		 * VMIDs that may be in use, instead just nuke the whole thing.
+		 */
+		kvm_call_hyp(__kvm_flush_vm_context);
+	}
 }
 
 static bool kvm_is_device_pfn(unsigned long pfn)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 6b7a7ce9b1a3..ecd61a6b06d1 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1623,6 +1623,11 @@ static bool forward_at_traps(struct kvm_vcpu *vcpu)
 	return forward_traps(vcpu, HCR_AT);
 }
 
+static bool forward_ttlb_traps(struct kvm_vcpu *vcpu)
+{
+	return forward_traps(vcpu, HCR_TTLB);
+}
+
 static bool access_elr(struct kvm_vcpu *vcpu,
 		       struct sys_reg_params *p,
 		       const struct sys_reg_desc *r)
@@ -2230,6 +2235,185 @@ static bool handle_s12w(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return handle_s12(vcpu, p, r, true);
 }
 
+static bool handle_alle2is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	/*
+	 * To emulate invalidating all EL2 regime stage 1 TLB entries for all
+	 * PEs, executing TLBI VMALLE1IS is enough. But reuse the existing
+	 * interface for the simplicity; invalidating stage 2 entries doesn't
+	 * affect the correctness.
+	 */
+	__kvm_tlb_flush_vmid(&vcpu->kvm->arch.mmu);
+	return true;
+}
+
+static bool handle_vae2is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	int sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+
+	/*
+	 * Based on the same principle as TLBI ALLE2 instruction
+	 * emulation, we emulate TLBI VAE2* instructions by executing
+	 * corresponding TLBI VAE1* instructions with the virtual
+	 * EL2's VMID assigned by the host hypervisor.
+	 */
+	__kvm_tlb_vae2is(&vcpu->kvm->arch.mmu, p->regval, sys_encoding);
+	return true;
+}
+
+static bool handle_alle1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	struct kvm_s2_mmu *mmu = &vcpu->kvm->arch.mmu;
+	spin_lock(&vcpu->kvm->mmu_lock);
+
+	/*
+	 * Clear all mappings in the shadow page tables and invalidate the stage
+	 * 1 and 2 TLB entries via kvm_tlb_flush_vmid_ipa().
+	 */
+	kvm_nested_s2_clear(vcpu->kvm);
+
+	if (mmu->vmid.vmid_gen) {
+		/*
+		 * Invalidate the stage 1 and 2 TLB entries for the host OS
+		 * in a VM only if there is one.
+		 */
+		__kvm_tlb_flush_vmid(mmu);
+	}
+
+	spin_unlock(&vcpu->kvm->mmu_lock);
+
+	return true;
+}
+
+static bool handle_vmalls12e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+				const struct sys_reg_desc *r)
+{
+	u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+	struct kvm_s2_mmu *mmu;
+
+	spin_lock(&vcpu->kvm->mmu_lock);
+
+	mmu = lookup_s2_mmu(vcpu->kvm, vttbr, HCR_VM);
+	if (mmu)
+		kvm_unmap_stage2_range(mmu, 0, kvm_phys_size(vcpu->kvm));
+
+	mmu = lookup_s2_mmu(vcpu->kvm, vttbr, 0);
+	if (mmu)
+		kvm_unmap_stage2_range(mmu, 0, kvm_phys_size(vcpu->kvm));
+
+	spin_unlock(&vcpu->kvm->mmu_lock);
+
+	return true;
+}
+
+static bool handle_ipas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			     const struct sys_reg_desc *r)
+{
+	u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+	u64 vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+	struct kvm_s2_mmu *mmu;
+	u64 base_addr;
+	int max_size;
+
+	/*
+	 * We drop a number of things from the supplied value:
+	 *
+	 * - NS bit: we're non-secure only.
+	 *
+	 * - TTL field: We already have the granule size from the
+	 *   VTCR_EL2.TG0 field, and the level is only relevant to the
+	 *   guest's S2PT.
+	 *
+	 * - IPA[51:48]: We don't support 52bit IPA just yet...
+	 *
+	 * And of course, adjust the IPA to be on an actual address.
+	 */
+	base_addr = (p->regval & GENMASK_ULL(35, 0)) << 12;
+
+	/* Compute the maximum extent of the invalidation */
+	switch ((vtcr & VTCR_EL2_TG0_MASK)) {
+	case VTCR_EL2_TG0_4K:
+		max_size = SZ_1G;
+		break;
+	case VTCR_EL2_TG0_16K:
+		max_size = SZ_32M;
+		break;
+	case VTCR_EL2_TG0_64K:
+		/*
+		 * No, we do not support 52bit IPA in nested yet. Once
+		 * we do, this should be 4TB.
+		 */
+		/* FIXME: remove the 52bit PA support from the IDregs */
+		max_size = SZ_512M;
+		break;
+	default:
+		BUG();
+	}
+
+	spin_lock(&vcpu->kvm->mmu_lock);
+
+	mmu = lookup_s2_mmu(vcpu->kvm, vttbr, HCR_VM);
+	if (mmu)
+		kvm_unmap_stage2_range(mmu, base_addr, max_size);
+
+	mmu = lookup_s2_mmu(vcpu->kvm, vttbr, 0);
+	if (mmu)
+		kvm_unmap_stage2_range(mmu, base_addr, max_size);
+
+	spin_unlock(&vcpu->kvm->mmu_lock);
+
+	return true;
+}
+
+static bool handle_tlbi_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+
+	/*
+	 * If we're here, this is because we've trapped on a EL1 TLBI
+	 * instruction that affects the EL1 translation regime while
+	 * we're running in a context that doesn't allow us to let the
+	 * HW do its thing (aka vEL2):
+	 *
+	 * - HCR_EL2.E2H == 0 : a non-VHE guest
+	 * - HCR_EL2.{E2H,TGE} == { 1, 0 } : a VHE guest in guest mode
+	 *
+	 * We don't expect these helpers to ever be called when running
+	 * in a vEL1 context.
+	 */
+
+	WARN_ON(!vcpu_mode_el2(vcpu));
+
+	mutex_lock(&vcpu->kvm->lock);
+
+	if ((__vcpu_sys_reg(vcpu, HCR_EL2) & (HCR_E2H | HCR_TGE)) != (HCR_E2H | HCR_TGE)) {
+		u64 virtual_vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+		struct kvm_s2_mmu *mmu;
+
+		mmu = lookup_s2_mmu(vcpu->kvm, virtual_vttbr, HCR_VM);
+		if (mmu)
+			__kvm_tlb_el1_instr(mmu, p->regval, sys_encoding);
+
+		mmu = lookup_s2_mmu(vcpu->kvm, virtual_vttbr, 0);
+		if (mmu)
+			__kvm_tlb_el1_instr(mmu, p->regval, sys_encoding);
+	} else {
+		/*
+		 * ARMv8.4-NV allows the guest to change TGE behind
+		 * our back, so we always trap EL1 TLBIs from vEL2...
+		 */
+		__kvm_tlb_el1_instr(&vcpu->kvm->arch.mmu, p->regval, sys_encoding);
+	}
+
+	mutex_unlock(&vcpu->kvm->lock);
+
+	return true;
+}
+
 /*
  * AT instruction emulation
  *
@@ -2312,12 +2496,40 @@ static struct sys_reg_desc sys_insn_descs[] = {
 	{ SYS_DESC(SYS_DC_CSW), access_dcsw },
 	{ SYS_DESC(SYS_DC_CISW), access_dcsw },
 
+	SYS_INSN_TO_DESC(TLBI_VMALLE1IS, handle_tlbi_el1, forward_ttlb_traps),
+	SYS_INSN_TO_DESC(TLBI_VAE1IS, handle_tlbi_el1, forward_ttlb_traps),
+	SYS_INSN_TO_DESC(TLBI_ASIDE1IS, handle_tlbi_el1, forward_ttlb_traps),
+	SYS_INSN_TO_DESC(TLBI_VAAE1IS, handle_tlbi_el1, forward_ttlb_traps),
+	SYS_INSN_TO_DESC(TLBI_VALE1IS, handle_tlbi_el1, forward_ttlb_traps),
+	SYS_INSN_TO_DESC(TLBI_VAALE1IS, handle_tlbi_el1, forward_ttlb_traps),
+	SYS_INSN_TO_DESC(TLBI_VMALLE1, handle_tlbi_el1, forward_ttlb_traps),
+	SYS_INSN_TO_DESC(TLBI_VAE1, handle_tlbi_el1, forward_ttlb_traps),
+	SYS_INSN_TO_DESC(TLBI_ASIDE1, handle_tlbi_el1, forward_ttlb_traps),
+	SYS_INSN_TO_DESC(TLBI_VAAE1, handle_tlbi_el1, forward_ttlb_traps),
+	SYS_INSN_TO_DESC(TLBI_VALE1, handle_tlbi_el1, forward_ttlb_traps),
+	SYS_INSN_TO_DESC(TLBI_VAALE1, handle_tlbi_el1, forward_ttlb_traps),
+
 	SYS_INSN_TO_DESC(AT_S1E2R, handle_s1e2, forward_nv_traps),
 	SYS_INSN_TO_DESC(AT_S1E2W, handle_s1e2, forward_nv_traps),
 	SYS_INSN_TO_DESC(AT_S12E1R, handle_s12r, forward_nv_traps),
 	SYS_INSN_TO_DESC(AT_S12E1W, handle_s12w, forward_nv_traps),
 	SYS_INSN_TO_DESC(AT_S12E0R, handle_s12r, forward_nv_traps),
 	SYS_INSN_TO_DESC(AT_S12E0W, handle_s12w, forward_nv_traps),
+
+	SYS_INSN_TO_DESC(TLBI_IPAS2E1IS, handle_ipas2e1is, forward_nv_traps),
+	SYS_INSN_TO_DESC(TLBI_IPAS2LE1IS, handle_ipas2e1is, forward_nv_traps),
+	SYS_INSN_TO_DESC(TLBI_ALLE2IS, handle_alle2is, forward_nv_traps),
+	SYS_INSN_TO_DESC(TLBI_VAE2IS, handle_vae2is, forward_nv_traps),
+	SYS_INSN_TO_DESC(TLBI_ALLE1IS, handle_alle1is, forward_nv_traps),
+	SYS_INSN_TO_DESC(TLBI_VALE2IS, handle_vae2is, forward_nv_traps),
+	SYS_INSN_TO_DESC(TLBI_VMALLS12E1IS, handle_vmalls12e1is, forward_nv_traps),
+	SYS_INSN_TO_DESC(TLBI_IPAS2E1, handle_ipas2e1is, forward_nv_traps),
+	SYS_INSN_TO_DESC(TLBI_IPAS2LE1, handle_ipas2e1is, forward_nv_traps),
+	SYS_INSN_TO_DESC(TLBI_ALLE2, handle_alle2is, forward_nv_traps),
+	SYS_INSN_TO_DESC(TLBI_VAE2, handle_vae2is, forward_nv_traps),
+	SYS_INSN_TO_DESC(TLBI_ALLE1, handle_alle1is, forward_nv_traps),
+	SYS_INSN_TO_DESC(TLBI_VALE2, handle_vae2is, forward_nv_traps),
+	SYS_INSN_TO_DESC(TLBI_VMALLS12E1, handle_vmalls12e1is, forward_nv_traps),
 };
 
 static bool trap_dbgidr(struct kvm_vcpu *vcpu,
-- 
2.29.2

[PATCH v3 42/66] KVM: arm64: nv: Fold guest's HCR_EL2 configuration into the host's

[Marc Zyngier]

When entering a L2 guest (nested virt enabled, but not in hypervisor
context), we need to honor the traps the L1 guest has asked enabled.

For now, just OR the guest's HCR_EL2 into the host's. We may have to do
some filtering in the future though.

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

diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index bac6ccc2595c..d9dc470c7790 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -80,6 +80,8 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 			if (!vcpu_el2_tge_is_set(vcpu))
 				hcr |= HCR_AT | HCR_TTLB;
 		}
+	} else if (nested_virt_in_use(vcpu)) {
+		hcr |= __vcpu_sys_reg(vcpu, HCR_EL2);
 	}
 
 	___activate_traps(vcpu, hcr);
-- 
2.29.2

[PATCH v3 43/66] KVM: arm64: nv: arch_timer: Support hyp timer emulation

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@arm.com>

Emulating EL2 also means emulating the EL2 timers. To do so, we expand
our timer framework to deal with at most 4 timers. At any given time,
two timers are using the HW timers, and the two others are purely
emulated.

The role of deciding which is which at any given time is left to a
mapping function which is called every time we need to make such a
decision.

Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
[maz: added CNTVOFF support, general reworking for v4.8]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h |   4 +
 arch/arm64/kvm/arch_timer.c       | 152 +++++++++++++++++++++++++++++-
 arch/arm64/kvm/sys_regs.c         |   7 +-
 arch/arm64/kvm/trace_arm.h        |   6 +-
 arch/arm64/kvm/vgic/vgic.c        |  15 +++
 include/kvm/arm_arch_timer.h      |   6 ++
 include/kvm/arm_vgic.h            |   1 +
 7 files changed, 186 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index bf60c50eec17..f3743e45ded1 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -272,6 +272,10 @@ enum vcpu_sysreg {
 	TPIDR_EL2,	/* EL2 Software Thread ID Register */
 	CNTHCTL_EL2,	/* Counter-timer Hypervisor Control register */
 	SP_EL2,		/* EL2 Stack Pointer */
+	CNTHP_CTL_EL2,
+	CNTHP_CVAL_EL2,
+	CNTHV_CTL_EL2,
+	CNTHV_CVAL_EL2,
 
 	NR_SYS_REGS	/* Nothing after this line! */
 };
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 32ba6fbc3814..1c2be6391951 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -15,6 +15,7 @@
 #include <asm/arch_timer.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
+#include <asm/kvm_nested.h>
 
 #include <kvm/arm_vgic.h>
 #include <kvm/arm_arch_timer.h>
@@ -39,6 +40,16 @@ static const struct kvm_irq_level default_vtimer_irq = {
 	.level	= 1,
 };
 
+static const struct kvm_irq_level default_hptimer_irq = {
+	.irq	= 26,
+	.level	= 1,
+};
+
+static const struct kvm_irq_level default_hvtimer_irq = {
+	.irq	= 28,
+	.level	= 1,
+};
+
 static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx);
 static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
 				 struct arch_timer_context *timer_ctx);
@@ -60,6 +71,10 @@ u32 timer_get_ctl(struct arch_timer_context *ctxt)
 		return __vcpu_sys_reg(vcpu, CNTV_CTL_EL0);
 	case TIMER_PTIMER:
 		return __vcpu_sys_reg(vcpu, CNTP_CTL_EL0);
+	case TIMER_HVTIMER:
+		return __vcpu_sys_reg(vcpu, CNTHV_CTL_EL2);
+	case TIMER_HPTIMER:
+		return __vcpu_sys_reg(vcpu, CNTHP_CTL_EL2);
 	default:
 		WARN_ON(1);
 		return 0;
@@ -75,6 +90,10 @@ u64 timer_get_cval(struct arch_timer_context *ctxt)
 		return __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
 	case TIMER_PTIMER:
 		return __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
+	case TIMER_HVTIMER:
+		return __vcpu_sys_reg(vcpu, CNTHV_CVAL_EL2);
+	case TIMER_HPTIMER:
+		return __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2);
 	default:
 		WARN_ON(1);
 		return 0;
@@ -104,6 +123,12 @@ static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl)
 	case TIMER_PTIMER:
 		__vcpu_sys_reg(vcpu, CNTP_CTL_EL0) = ctl;
 		break;
+	case TIMER_HVTIMER:
+		__vcpu_sys_reg(vcpu, CNTHV_CTL_EL2) = ctl;
+		break;
+	case TIMER_HPTIMER:
+		__vcpu_sys_reg(vcpu, CNTHP_CTL_EL2) = ctl;
+		break;
 	default:
 		WARN_ON(1);
 	}
@@ -120,6 +145,12 @@ static void timer_set_cval(struct arch_timer_context *ctxt, u64 cval)
 	case TIMER_PTIMER:
 		__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = cval;
 		break;
+	case TIMER_HVTIMER:
+		__vcpu_sys_reg(vcpu, CNTHV_CVAL_EL2) = cval;
+		break;
+	case TIMER_HPTIMER:
+		__vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = cval;
+		break;
 	default:
 		WARN_ON(1);
 	}
@@ -145,13 +176,27 @@ u64 kvm_phys_timer_read(void)
 
 static void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map)
 {
-	if (has_vhe()) {
+	if (nested_virt_in_use(vcpu)) {
+		if (is_hyp_ctxt(vcpu)) {
+			map->direct_vtimer = vcpu_hvtimer(vcpu);
+			map->direct_ptimer = vcpu_hptimer(vcpu);
+			map->emul_vtimer = vcpu_vtimer(vcpu);
+			map->emul_ptimer = vcpu_ptimer(vcpu);
+		} else {
+			map->direct_vtimer = vcpu_vtimer(vcpu);
+			map->direct_ptimer = vcpu_ptimer(vcpu);
+			map->emul_vtimer = vcpu_hvtimer(vcpu);
+			map->emul_ptimer = vcpu_hptimer(vcpu);
+		}
+	} else if (has_vhe()) {
 		map->direct_vtimer = vcpu_vtimer(vcpu);
 		map->direct_ptimer = vcpu_ptimer(vcpu);
+		map->emul_vtimer = NULL;
 		map->emul_ptimer = NULL;
 	} else {
 		map->direct_vtimer = vcpu_vtimer(vcpu);
 		map->direct_ptimer = NULL;
+		map->emul_vtimer = NULL;
 		map->emul_ptimer = vcpu_ptimer(vcpu);
 	}
 
@@ -324,9 +369,11 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx)
 
 		switch (index) {
 		case TIMER_VTIMER:
+		case TIMER_HVTIMER:
 			cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL);
 			break;
 		case TIMER_PTIMER:
+		case TIMER_HPTIMER:
 			cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL);
 			break;
 		case NR_KVM_TIMERS:
@@ -357,6 +404,7 @@ bool kvm_timer_is_pending(struct kvm_vcpu *vcpu)
 
 	return kvm_timer_should_fire(map.direct_vtimer) ||
 	       kvm_timer_should_fire(map.direct_ptimer) ||
+	       kvm_timer_should_fire(map.emul_vtimer) ||
 	       kvm_timer_should_fire(map.emul_ptimer);
 }
 
@@ -437,6 +485,7 @@ static void timer_save_state(struct arch_timer_context *ctx)
 
 	switch (index) {
 	case TIMER_VTIMER:
+	case TIMER_HVTIMER:
 		timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTV_CTL));
 		timer_set_cval(ctx, read_sysreg_el0(SYS_CNTV_CVAL));
 
@@ -446,6 +495,7 @@ static void timer_save_state(struct arch_timer_context *ctx)
 
 		break;
 	case TIMER_PTIMER:
+	case TIMER_HPTIMER:
 		timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL));
 		timer_set_cval(ctx, read_sysreg_el0(SYS_CNTP_CVAL));
 
@@ -483,6 +533,7 @@ static void kvm_timer_blocking(struct kvm_vcpu *vcpu)
 	 */
 	if (!kvm_timer_irq_can_fire(map.direct_vtimer) &&
 	    !kvm_timer_irq_can_fire(map.direct_ptimer) &&
+	    !kvm_timer_irq_can_fire(map.emul_vtimer) &&
 	    !kvm_timer_irq_can_fire(map.emul_ptimer))
 		return;
 
@@ -516,11 +567,13 @@ static void timer_restore_state(struct arch_timer_context *ctx)
 
 	switch (index) {
 	case TIMER_VTIMER:
+	case TIMER_HVTIMER:
 		write_sysreg_el0(timer_get_cval(ctx), SYS_CNTV_CVAL);
 		isb();
 		write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL);
 		break;
 	case TIMER_PTIMER:
+	case TIMER_HPTIMER:
 		write_sysreg_el0(timer_get_cval(ctx), SYS_CNTP_CVAL);
 		isb();
 		write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTP_CTL);
@@ -597,6 +650,40 @@ static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu)
 		enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags);
 }
 
+static void kvm_timer_vcpu_load_nested_switch(struct kvm_vcpu *vcpu,
+					      struct timer_map *map)
+{
+	int hw, ret;
+
+	if (!irqchip_in_kernel(vcpu->kvm))
+		return;
+
+	/*
+	 * We only ever unmap the vtimer irq on a VHE system that runs nested
+	 * virtualization, in which case we have both a valid emul_vtimer,
+	 * emul_ptimer, direct_vtimer, and direct_ptimer.
+	 *
+	 * Since this is called from kvm_timer_vcpu_load(), a change between
+	 * vEL2 and vEL1/0 will have just happened, and the timer_map will
+	 * represent this, and therefore we switch the emul/direct mappings
+	 * below.
+	 */
+	hw = kvm_vgic_get_map(vcpu, map->direct_vtimer->irq.irq);
+	if (hw < 0) {
+		kvm_vgic_unmap_phys_irq(vcpu, map->emul_vtimer->irq.irq);
+		kvm_vgic_unmap_phys_irq(vcpu, map->emul_ptimer->irq.irq);
+
+		ret = kvm_vgic_map_phys_irq(vcpu,
+					    map->direct_vtimer->host_timer_irq,
+					    map->direct_vtimer->irq.irq,
+					    kvm_arch_timer_get_input_level);
+		ret = kvm_vgic_map_phys_irq(vcpu,
+					    map->direct_ptimer->host_timer_irq,
+					    map->direct_ptimer->irq.irq,
+					    kvm_arch_timer_get_input_level);
+	}
+}
+
 void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = vcpu_timer(vcpu);
@@ -608,6 +695,9 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu)
 	get_timer_map(vcpu, &map);
 
 	if (static_branch_likely(&has_gic_active_state)) {
+		if (nested_virt_in_use(vcpu))
+			kvm_timer_vcpu_load_nested_switch(vcpu, &map);
+
 		kvm_timer_vcpu_load_gic(map.direct_vtimer);
 		if (map.direct_ptimer)
 			kvm_timer_vcpu_load_gic(map.direct_ptimer);
@@ -623,6 +713,8 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu)
 	if (map.direct_ptimer)
 		timer_restore_state(map.direct_ptimer);
 
+	if (map.emul_vtimer)
+		timer_emulate(map.emul_vtimer);
 	if (map.emul_ptimer)
 		timer_emulate(map.emul_ptimer);
 }
@@ -668,6 +760,8 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 	 * In any case, we re-schedule the hrtimer for the physical timer when
 	 * coming back to the VCPU thread in kvm_timer_vcpu_load().
 	 */
+	if (map.emul_vtimer)
+		soft_timer_cancel(&map.emul_vtimer->hrtimer);
 	if (map.emul_ptimer)
 		soft_timer_cancel(&map.emul_ptimer->hrtimer);
 
@@ -728,10 +822,14 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
 	 */
 	timer_set_ctl(vcpu_vtimer(vcpu), 0);
 	timer_set_ctl(vcpu_ptimer(vcpu), 0);
+	timer_set_ctl(vcpu_hvtimer(vcpu), 0);
+	timer_set_ctl(vcpu_hptimer(vcpu), 0);
 
 	if (timer->enabled) {
 		kvm_timer_update_irq(vcpu, false, vcpu_vtimer(vcpu));
 		kvm_timer_update_irq(vcpu, false, vcpu_ptimer(vcpu));
+		kvm_timer_update_irq(vcpu, false, vcpu_hvtimer(vcpu));
+		kvm_timer_update_irq(vcpu, false, vcpu_hptimer(vcpu));
 
 		if (irqchip_in_kernel(vcpu->kvm)) {
 			kvm_vgic_reset_mapped_irq(vcpu, map.direct_vtimer->irq.irq);
@@ -740,6 +838,8 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
 		}
 	}
 
+	if (map.emul_vtimer)
+		soft_timer_cancel(&map.emul_vtimer->hrtimer);
 	if (map.emul_ptimer)
 		soft_timer_cancel(&map.emul_ptimer->hrtimer);
 
@@ -770,30 +870,47 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 	struct arch_timer_cpu *timer = vcpu_timer(vcpu);
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
+	struct arch_timer_context *hvtimer = vcpu_hvtimer(vcpu);
+	struct arch_timer_context *hptimer = vcpu_hptimer(vcpu);
 
 	vtimer->vcpu = vcpu;
 	ptimer->vcpu = vcpu;
+	hvtimer->vcpu = vcpu;
+	hptimer->vcpu = vcpu;
 
 	/* Synchronize cntvoff across all vtimers of a VM. */
 	update_vtimer_cntvoff(vcpu, kvm_phys_timer_read());
 	timer_set_offset(ptimer, 0);
+	timer_set_offset(hvtimer, 0);
+	timer_set_offset(hptimer, 0);
 
 	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	timer->bg_timer.function = kvm_bg_timer_expire;
 
 	hrtimer_init(&vtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	hrtimer_init(&ptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
+	hrtimer_init(&hvtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
+	hrtimer_init(&hptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
+
 	vtimer->hrtimer.function = kvm_hrtimer_expire;
 	ptimer->hrtimer.function = kvm_hrtimer_expire;
+	hvtimer->hrtimer.function = kvm_hrtimer_expire;
+	hptimer->hrtimer.function = kvm_hrtimer_expire;
 
 	vtimer->irq.irq = default_vtimer_irq.irq;
 	ptimer->irq.irq = default_ptimer_irq.irq;
+	hvtimer->irq.irq = default_hvtimer_irq.irq;
+	hptimer->irq.irq = default_hptimer_irq.irq;
 
 	vtimer->host_timer_irq = host_vtimer_irq;
 	ptimer->host_timer_irq = host_ptimer_irq;
+	hvtimer->host_timer_irq = host_vtimer_irq;
+	hptimer->host_timer_irq = host_ptimer_irq;
 
 	vtimer->host_timer_irq_flags = host_vtimer_irq_flags;
 	ptimer->host_timer_irq_flags = host_ptimer_irq_flags;
+	hvtimer->host_timer_irq_flags = host_vtimer_irq_flags;
+	hptimer->host_timer_irq_flags = host_ptimer_irq_flags;
 }
 
 static void kvm_timer_init_interrupt(void *info)
@@ -900,6 +1017,10 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 		val = kvm_phys_timer_read() - timer_get_offset(timer);
 		break;
 
+	case TIMER_REG_VOFF:
+		val = timer_get_offset(timer);
+		break;
+
 	default:
 		BUG();
 	}
@@ -942,6 +1063,10 @@ static void kvm_arm_timer_write(struct kvm_vcpu *vcpu,
 		timer_set_cval(timer, val);
 		break;
 
+	case TIMER_REG_VOFF:
+		timer_set_offset(timer, val);
+		break;
+
 	default:
 		BUG();
 	}
@@ -1079,7 +1204,7 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
 
 static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu)
 {
-	int vtimer_irq, ptimer_irq;
+	int vtimer_irq, ptimer_irq, hvtimer_irq, hptimer_irq;
 	int i, ret;
 
 	vtimer_irq = vcpu_vtimer(vcpu)->irq.irq;
@@ -1092,9 +1217,21 @@ static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu)
 	if (ret)
 		return false;
 
+	hvtimer_irq = vcpu_hvtimer(vcpu)->irq.irq;
+	ret = kvm_vgic_set_owner(vcpu, hvtimer_irq, vcpu_hvtimer(vcpu));
+	if (ret)
+		return false;
+
+	hptimer_irq = vcpu_hptimer(vcpu)->irq.irq;
+	ret = kvm_vgic_set_owner(vcpu, hptimer_irq, vcpu_hptimer(vcpu));
+	if (ret)
+		return false;
+
 	kvm_for_each_vcpu(i, vcpu, vcpu->kvm) {
 		if (vcpu_vtimer(vcpu)->irq.irq != vtimer_irq ||
-		    vcpu_ptimer(vcpu)->irq.irq != ptimer_irq)
+		    vcpu_ptimer(vcpu)->irq.irq != ptimer_irq ||
+		    vcpu_hvtimer(vcpu)->irq.irq != hvtimer_irq ||
+		    vcpu_hptimer(vcpu)->irq.irq != hptimer_irq)
 			return false;
 	}
 
@@ -1110,6 +1247,10 @@ bool kvm_arch_timer_get_input_level(int vintid)
 		timer = vcpu_vtimer(vcpu);
 	else if (vintid == vcpu_ptimer(vcpu)->irq.irq)
 		timer = vcpu_ptimer(vcpu);
+	else if (vintid == vcpu_hvtimer(vcpu)->irq.irq)
+		timer = vcpu_hvtimer(vcpu);
+	else if (vintid == vcpu_hptimer(vcpu)->irq.irq)
+		timer = vcpu_hptimer(vcpu);
 	else
 		BUG();
 
@@ -1191,6 +1332,7 @@ static void set_timer_irqs(struct kvm *kvm, int vtimer_irq, int ptimer_irq)
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		vcpu_vtimer(vcpu)->irq.irq = vtimer_irq;
 		vcpu_ptimer(vcpu)->irq.irq = ptimer_irq;
+		/* TODO: Add support for hv/hp timers */
 	}
 }
 
@@ -1201,6 +1343,8 @@ int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
 	int irq;
 
+	/* TODO: Add support for hv/hp timers */
+
 	if (!irqchip_in_kernel(vcpu->kvm))
 		return -EINVAL;
 
@@ -1233,6 +1377,8 @@ int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 	struct arch_timer_context *timer;
 	int irq;
 
+	/* TODO: Add support for hv/hp timers */
+
 	switch (attr->attr) {
 	case KVM_ARM_VCPU_TIMER_IRQ_VTIMER:
 		timer = vcpu_vtimer(vcpu);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index ecd61a6b06d1..98ff5b42a6b5 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1290,6 +1290,11 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
 		tmr = TIMER_PTIMER;
 		treg = TIMER_REG_CVAL;
 		break;
+	case SYS_CNTVOFF_EL2:
+		tmr = TIMER_VTIMER;
+		treg = TIMER_REG_VOFF;
+		break;
+
 	default:
 		BUG();
 	}
@@ -2101,7 +2106,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_CONTEXTIDR_EL2), access_rw, reset_val, CONTEXTIDR_EL2, 0 },
 	{ SYS_DESC(SYS_TPIDR_EL2), access_rw, reset_val, TPIDR_EL2, 0 },
 
-	{ SYS_DESC(SYS_CNTVOFF_EL2), access_rw, reset_val, CNTVOFF_EL2, 0 },
+	{ SYS_DESC(SYS_CNTVOFF_EL2), access_arch_timer },
 	{ SYS_DESC(SYS_CNTHCTL_EL2), access_rw, reset_val, CNTHCTL_EL2, 0 },
 
 	{ SYS_DESC(SYS_SCTLR_EL12), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h
index 5707011c4f47..49f4cb52d35d 100644
--- a/arch/arm64/kvm/trace_arm.h
+++ b/arch/arm64/kvm/trace_arm.h
@@ -272,6 +272,7 @@ TRACE_EVENT(kvm_get_timer_map,
 		__field(	unsigned long,		vcpu_id	)
 		__field(	int,			direct_vtimer	)
 		__field(	int,			direct_ptimer	)
+		__field(	int,			emul_vtimer	)
 		__field(	int,			emul_ptimer	)
 	),
 
@@ -280,14 +281,17 @@ TRACE_EVENT(kvm_get_timer_map,
 		__entry->direct_vtimer		= arch_timer_ctx_index(map->direct_vtimer);
 		__entry->direct_ptimer =
 			(map->direct_ptimer) ? arch_timer_ctx_index(map->direct_ptimer) : -1;
+		__entry->emul_vtimer =
+			(map->emul_vtimer) ? arch_timer_ctx_index(map->emul_vtimer) : -1;
 		__entry->emul_ptimer =
 			(map->emul_ptimer) ? arch_timer_ctx_index(map->emul_ptimer) : -1;
 	),
 
-	TP_printk("VCPU: %ld, dv: %d, dp: %d, ep: %d",
+	TP_printk("VCPU: %ld, dv: %d, dp: %d, ev: %d, ep: %d",
 		  __entry->vcpu_id,
 		  __entry->direct_vtimer,
 		  __entry->direct_ptimer,
+		  __entry->emul_vtimer,
 		  __entry->emul_ptimer)
 );
 
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index 1c597c9885fa..2af93dc80689 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -573,6 +573,21 @@ int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid)
 	return 0;
 }
 
+int kvm_vgic_get_map(struct kvm_vcpu *vcpu, unsigned int vintid)
+{
+	struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid);
+	unsigned long flags;
+	int ret = -1;
+
+	raw_spin_lock_irqsave(&irq->irq_lock, flags);
+	if (irq->hw)
+		ret = irq->hwintid;
+	raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+
+	vgic_put_irq(vcpu->kvm, irq);
+	return ret;
+}
+
 /**
  * kvm_vgic_set_owner - Set the owner of an interrupt for a VM
  *
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index 51c19381108c..063f613fbc7e 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -13,6 +13,8 @@
 enum kvm_arch_timers {
 	TIMER_PTIMER,
 	TIMER_VTIMER,
+	TIMER_HVTIMER,
+	TIMER_HPTIMER,
 	NR_KVM_TIMERS
 };
 
@@ -21,6 +23,7 @@ enum kvm_arch_timer_regs {
 	TIMER_REG_CVAL,
 	TIMER_REG_TVAL,
 	TIMER_REG_CTL,
+	TIMER_REG_VOFF,
 };
 
 struct arch_timer_context {
@@ -47,6 +50,7 @@ struct arch_timer_context {
 struct timer_map {
 	struct arch_timer_context *direct_vtimer;
 	struct arch_timer_context *direct_ptimer;
+	struct arch_timer_context *emul_vtimer;
 	struct arch_timer_context *emul_ptimer;
 };
 
@@ -91,6 +95,8 @@ bool kvm_arch_timer_get_input_level(int vintid);
 #define vcpu_get_timer(v,t)	(&vcpu_timer(v)->timers[(t)])
 #define vcpu_vtimer(v)	(&(v)->arch.timer_cpu.timers[TIMER_VTIMER])
 #define vcpu_ptimer(v)	(&(v)->arch.timer_cpu.timers[TIMER_PTIMER])
+#define vcpu_hvtimer(v)	(&(v)->arch.timer_cpu.timers[TIMER_HVTIMER])
+#define vcpu_hptimer(v)	(&(v)->arch.timer_cpu.timers[TIMER_HPTIMER])
 
 #define arch_timer_ctx_index(ctx)	((ctx) - vcpu_timer((ctx)->vcpu)->timers)
 
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 3d74f1060bd1..4749c4748e5a 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -353,6 +353,7 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
 int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq,
 			  u32 vintid, bool (*get_input_level)(int vindid));
 int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid);
+int kvm_vgic_get_map(struct kvm_vcpu *vcpu, unsigned int vintid);
 bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid);
 
 int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
-- 
2.29.2

[PATCH v3 44/66] KVM: arm64: nv: Add handling of EL2-specific timer registers

[Marc Zyngier]

Add the required handling for EL2 and EL02 registers, as
well as EL1 registers used in the E2H context.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/sysreg.h |  6 +++
 arch/arm64/kvm/sys_regs.c       | 87 +++++++++++++++++++++++++++++++++
 2 files changed, 93 insertions(+)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 814fb57b55d9..d047954400d4 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -559,6 +559,12 @@
 
 #define SYS_CNTVOFF_EL2			sys_reg(3, 4, 14, 0, 3)
 #define SYS_CNTHCTL_EL2			sys_reg(3, 4, 14, 1, 0)
+#define SYS_CNTHP_TVAL_EL2		sys_reg(3, 4, 14, 2, 0)
+#define SYS_CNTHP_CTL_EL2		sys_reg(3, 4, 14, 2, 1)
+#define SYS_CNTHP_CVAL_EL2		sys_reg(3, 4, 14, 2, 2)
+#define SYS_CNTHV_TVAL_EL2		sys_reg(3, 4, 14, 3, 0)
+#define SYS_CNTHV_CTL_EL2		sys_reg(3, 4, 14, 3, 1)
+#define SYS_CNTHV_CVAL_EL2		sys_reg(3, 4, 14, 3, 2)
 
 /* VHE encodings for architectural EL0/1 system registers */
 #define SYS_SCTLR_EL12			sys_reg(3, 5, 1, 0, 0)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 98ff5b42a6b5..560b44325e98 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1276,20 +1276,92 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
 
 	switch (reg) {
 	case SYS_CNTP_TVAL_EL0:
+		if (vcpu_mode_el2(vcpu) && vcpu_el2_e2h_is_set(vcpu))
+			tmr = TIMER_HPTIMER;
+		else
+			tmr = TIMER_PTIMER;
+		treg = TIMER_REG_TVAL;
+		break;
+
 	case SYS_AARCH32_CNTP_TVAL:
+	case SYS_CNTP_TVAL_EL02:
 		tmr = TIMER_PTIMER;
 		treg = TIMER_REG_TVAL;
 		break;
+
+	case SYS_CNTV_TVAL_EL02:
+		tmr = TIMER_VTIMER;
+		treg = TIMER_REG_TVAL;
+		break;
+
+	case SYS_CNTHP_TVAL_EL2:
+		tmr = TIMER_HPTIMER;
+		treg = TIMER_REG_TVAL;
+		break;
+
+	case SYS_CNTHV_TVAL_EL2:
+		tmr = TIMER_HVTIMER;
+		treg = TIMER_REG_TVAL;
+		break;
+
 	case SYS_CNTP_CTL_EL0:
+		if (vcpu_mode_el2(vcpu) && vcpu_el2_e2h_is_set(vcpu))
+			tmr = TIMER_HPTIMER;
+		else
+			tmr = TIMER_PTIMER;
+		treg = TIMER_REG_CTL;
+		break;
+
 	case SYS_AARCH32_CNTP_CTL:
+	case SYS_CNTP_CTL_EL02:
 		tmr = TIMER_PTIMER;
 		treg = TIMER_REG_CTL;
 		break;
+
+	case SYS_CNTV_CTL_EL02:
+		tmr = TIMER_VTIMER;
+		treg = TIMER_REG_CTL;
+		break;
+
+	case SYS_CNTHP_CTL_EL2:
+		tmr = TIMER_HPTIMER;
+		treg = TIMER_REG_CTL;
+		break;
+
+	case SYS_CNTHV_CTL_EL2:
+		tmr = TIMER_HVTIMER;
+		treg = TIMER_REG_CTL;
+		break;
+
 	case SYS_CNTP_CVAL_EL0:
+		if (vcpu_mode_el2(vcpu) && vcpu_el2_e2h_is_set(vcpu))
+			tmr = TIMER_HPTIMER;
+		else
+			tmr = TIMER_PTIMER;
+		treg = TIMER_REG_CVAL;
+		break;
+
 	case SYS_AARCH32_CNTP_CVAL:
+	case SYS_CNTP_CVAL_EL02:
 		tmr = TIMER_PTIMER;
 		treg = TIMER_REG_CVAL;
 		break;
+
+	case SYS_CNTV_CVAL_EL02:
+		tmr = TIMER_VTIMER;
+		treg = TIMER_REG_CVAL;
+		break;
+
+	case SYS_CNTHP_CVAL_EL2:
+		tmr = TIMER_HPTIMER;
+		treg = TIMER_REG_CVAL;
+		break;
+
+	case SYS_CNTHV_CVAL_EL2:
+		tmr = TIMER_HVTIMER;
+		treg = TIMER_REG_CVAL;
+		break;
+
 	case SYS_CNTVOFF_EL2:
 		tmr = TIMER_VTIMER;
 		treg = TIMER_REG_VOFF;
@@ -2109,6 +2181,13 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_CNTVOFF_EL2), access_arch_timer },
 	{ SYS_DESC(SYS_CNTHCTL_EL2), access_rw, reset_val, CNTHCTL_EL2, 0 },
 
+	{ SYS_DESC(SYS_CNTHP_TVAL_EL2), access_arch_timer },
+	{ SYS_DESC(SYS_CNTHP_CTL_EL2), access_arch_timer },
+	{ SYS_DESC(SYS_CNTHP_CVAL_EL2), access_arch_timer },
+	{ SYS_DESC(SYS_CNTHV_TVAL_EL2), access_arch_timer },
+	{ SYS_DESC(SYS_CNTHV_CTL_EL2), access_arch_timer },
+	{ SYS_DESC(SYS_CNTHV_CVAL_EL2), access_arch_timer },
+
 	{ SYS_DESC(SYS_SCTLR_EL12), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
 	{ SYS_DESC(SYS_CPACR_EL12), access_rw, reset_val, CPACR_EL1, 0 },
 	{ SYS_DESC(SYS_TTBR0_EL12), access_vm_reg, reset_unknown, TTBR0_EL1 },
@@ -2126,6 +2205,14 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_CONTEXTIDR_EL12), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
 	{ SYS_DESC(SYS_CNTKCTL_EL12), access_rw, reset_val, CNTKCTL_EL1, 0 },
 
+	{ SYS_DESC(SYS_CNTP_TVAL_EL02), access_arch_timer },
+	{ SYS_DESC(SYS_CNTP_CTL_EL02), access_arch_timer },
+	{ SYS_DESC(SYS_CNTP_CVAL_EL02), access_arch_timer },
+
+	{ SYS_DESC(SYS_CNTV_TVAL_EL02), access_arch_timer },
+	{ SYS_DESC(SYS_CNTV_CTL_EL02), access_arch_timer },
+	{ SYS_DESC(SYS_CNTV_CVAL_EL02), access_arch_timer },
+
 	{ SYS_DESC(SYS_SP_EL2), NULL, reset_unknown, SP_EL2 },
 };
 
-- 
2.29.2

[PATCH v3 45/66] 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 1656dd80bbc4..2e042185e625 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -405,8 +405,8 @@ 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_sysregs_vhe(vcpu);
 	kvm_arch_vcpu_load_fp(vcpu);
-- 
2.29.2

[PATCH v3 46/66] KVM: arm64: nv: Nested GICv3 Support

[Marc Zyngier]

From: Jintack Lim <jintack@cs.columbia.edu>

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.

Signed-off-by: Jintack Lim <jintack@cs.columbia.edu>
[Rewritten to support GICv3 instead of GICv2]
Signed-off-by: Marc Zyngier <maz@kernel.org>
[Redesigned execution flow around vcpu load/put]
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
---
 arch/arm64/include/asm/kvm_emulate.h |   8 +-
 arch/arm64/include/asm/kvm_host.h    |   9 +-
 arch/arm64/include/asm/kvm_nested.h  |   1 +
 arch/arm64/kvm/Makefile              |   2 +-
 arch/arm64/kvm/arm.c                 |  13 +-
 arch/arm64/kvm/nested.c              |  16 +++
 arch/arm64/kvm/sys_regs.c            | 179 ++++++++++++++++++++++++++-
 arch/arm64/kvm/vgic/vgic-v3-nested.c | 178 ++++++++++++++++++++++++++
 arch/arm64/kvm/vgic/vgic-v3.c        |  26 ++++
 arch/arm64/kvm/vgic/vgic.c           |  27 ++++
 include/kvm/arm_vgic.h               |  18 +++
 11 files changed, 468 insertions(+), 9 deletions(-)
 create mode 100644 arch/arm64/kvm/vgic/vgic-v3-nested.c

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index b447817d9dee..44b395854430 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -497,7 +497,13 @@ static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 
 static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 {
-	return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
+	/*
+	 * Use the in-memory view for MPIDR_EL1. It can't be changed by the
+	 * guest, and is also accessed from the context of *another* vcpu,
+	 * so anything using some other state (such as the NV state that is
+	 * used by vcpu_read_sys_reg) will eventually go wrong.
+	 */
+	return __vcpu_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
 }
 
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f3743e45ded1..bd91b4219d5e 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -42,10 +42,11 @@
 
 #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_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_GUEST_HYP_IRQ_PENDING	KVM_ARCH_REQ(5)
 
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 2987806850f0..5fa3c634c8e1 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -67,6 +67,7 @@ extern void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu);
 extern struct kvm_s2_mmu *lookup_s2_mmu(struct kvm *kvm, u64 vttbr, u64 hcr);
 extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
 extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
+extern void check_nested_vcpu_requests(struct kvm_vcpu *vcpu);
 
 struct kvm_s2_trans {
 	phys_addr_t output;
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 8a23991f82b2..0c15321c0827 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -23,5 +23,5 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 vgic/vgic-v3.o vgic/vgic-v4.o \
 	 vgic/vgic-mmio.o vgic/vgic-mmio-v2.o \
 	 vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \
-	 vgic/vgic-its.o vgic/vgic-debug.o
+	 vgic/vgic-its.o vgic/vgic-debug.o vgic/vgic-v3-nested.o
 kvm-$(CONFIG_KVM_ARM_PMU)  += pmu-emul.o
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 2e042185e625..818ec91801e2 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -692,6 +692,8 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
 			vgic_v4_load(vcpu);
 			preempt_enable();
 		}
+
+		check_nested_vcpu_requests(vcpu);
 	}
 }
 
@@ -738,9 +740,16 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		cond_resched();
 
-		update_vmid(&vcpu->arch.hw_mmu->vmid);
-
+		/*
+		 * A nested exeption triggered by a vcpu request (such
+		 * as an interrupt injected in a guest hypervisor) can
+		 * change the currently used VMID (by switching to a
+		 * different translation regime. It is thus necesary
+		 * to update the VMID *after* all requests have been
+		 * processed.
+		 */
 		check_vcpu_requests(vcpu);
+		update_vmid(&vcpu->arch.hw_mmu->vmid);
 
 		/*
 		 * Preparing the interrupts to be injected also
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index e78c6c093afc..9574fde823e6 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -580,6 +580,22 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 	kvm_free_stage2_pgd(&kvm->arch.mmu);
 }
 
+bool vgic_state_is_nested(struct kvm_vcpu *vcpu)
+{
+	bool imo = __vcpu_sys_reg(vcpu, HCR_EL2) & HCR_IMO;
+	bool fmo = __vcpu_sys_reg(vcpu, HCR_EL2) & HCR_FMO;
+
+	WARN_ONCE(imo != fmo, "Separate virtual IRQ/FIQ settings not supported\n");
+
+	return nested_virt_in_use(vcpu) && imo && fmo && !is_hyp_ctxt(vcpu);
+}
+
+void check_nested_vcpu_requests(struct kvm_vcpu *vcpu)
+{
+	if (kvm_check_request(KVM_REQ_GUEST_HYP_IRQ_PENDING, vcpu))
+		kvm_inject_nested_irq(vcpu);
+}
+
 #define FEATURE(x)	(GENMASK_ULL(x##_SHIFT + 3, x##_SHIFT))
 
 /*
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 560b44325e98..60d2fb6edc93 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -15,6 +15,8 @@
 #include <linux/printk.h>
 #include <linux/uaccess.h>
 
+#include <linux/irqchip/arm-gic-v3.h>
+
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
 #include <asm/debug-monitors.h>
@@ -455,6 +457,19 @@ static bool access_actlr(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+/*
+ * The architecture says that non-secure write accesses to this register from
+ * EL1 are trapped to EL2, if either:
+ *  - HCR_EL2.FMO==1, or
+ *  - HCR_EL2.IMO==1
+ */
+static bool sgi_traps_to_vel2(struct kvm_vcpu *vcpu)
+{
+	return (nested_virt_in_use(vcpu) &&
+		!vcpu_mode_el2(vcpu) &&
+		!!(vcpu_read_sys_reg(vcpu, HCR_EL2) & (HCR_IMO | HCR_FMO)));
+}
+
 /*
  * Trap handler for the GICv3 SGI generation system register.
  * Forward the request to the VGIC emulation.
@@ -470,6 +485,11 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu,
 	if (!p->is_write)
 		return read_from_write_only(vcpu, p, r);
 
+	if (sgi_traps_to_vel2(vcpu)) {
+		kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+		return false;
+	}
+
 	/*
 	 * In a system where GICD_CTLR.DS=1, a ICC_SGI0R_EL1 access generates
 	 * Group0 SGIs only, while ICC_SGI1R_EL1 can generate either group,
@@ -513,7 +533,13 @@ 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;
 }
 
@@ -1759,6 +1785,122 @@ static bool access_spsr_el2(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_gic_apr(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.nested_vgic_v3;
+	u32 index, *base;
+
+	index = r->Op2;
+	if (r->CRm == 8)
+		base = cpu_if->vgic_ap0r;
+	else
+		base = cpu_if->vgic_ap1r;
+
+	if (p->is_write)
+		base[index] = p->regval;
+	else
+		p->regval = base[index];
+
+	return true;
+}
+
+static bool access_gic_hcr(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.nested_vgic_v3;
+
+	if (p->is_write)
+		cpu_if->vgic_hcr = p->regval;
+	else
+		p->regval = cpu_if->vgic_hcr;
+
+	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;
+
+	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;
+}
+
+static bool access_gic_vmcr(struct kvm_vcpu *vcpu,
+			    struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.nested_vgic_v3;
+
+	if (p->is_write)
+		cpu_if->vgic_vmcr = p->regval;
+	else
+		p->regval = cpu_if->vgic_vmcr;
+
+	return true;
+}
+
+static bool access_gic_lr(struct kvm_vcpu *vcpu,
+			  struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.nested_vgic_v3;
+	u32 index;
+
+	index = p->Op2;
+	if (p->CRm == 13)
+		index += 8;
+
+	if (p->is_write)
+		cpu_if->vgic_lr[index] = p->regval;
+	else
+		p->regval = cpu_if->vgic_lr[index];
+
+	return true;
+}
+
 /*
  * Architected system registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
@@ -2175,6 +2317,41 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_RMR_EL2), access_wi, reset_val, RMR_EL2, 1 },
 	{ SYS_DESC(SYS_VDISR_EL2), trap_undef },
 
+	{ SYS_DESC(SYS_ICH_AP0R0_EL2), access_gic_apr },
+	{ SYS_DESC(SYS_ICH_AP0R1_EL2), access_gic_apr },
+	{ SYS_DESC(SYS_ICH_AP0R2_EL2), access_gic_apr },
+	{ SYS_DESC(SYS_ICH_AP0R3_EL2), access_gic_apr },
+	{ SYS_DESC(SYS_ICH_AP1R0_EL2), access_gic_apr },
+	{ SYS_DESC(SYS_ICH_AP1R1_EL2), access_gic_apr },
+	{ SYS_DESC(SYS_ICH_AP1R2_EL2), access_gic_apr },
+	{ SYS_DESC(SYS_ICH_AP1R3_EL2), access_gic_apr },
+
+	{ SYS_DESC(SYS_ICC_SRE_EL2), access_gic_sre },
+
+	{ SYS_DESC(SYS_ICH_HCR_EL2), access_gic_hcr },
+	{ 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 },
+	{ SYS_DESC(SYS_ICH_VMCR_EL2), access_gic_vmcr },
+
+	{ SYS_DESC(SYS_ICH_LR0_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR1_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR2_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR3_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR4_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR5_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR6_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR7_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR8_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR9_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR10_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR11_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR12_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR13_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR14_EL2), access_gic_lr },
+	{ SYS_DESC(SYS_ICH_LR15_EL2), access_gic_lr },
+
 	{ SYS_DESC(SYS_CONTEXTIDR_EL2), access_rw, reset_val, CONTEXTIDR_EL2, 0 },
 	{ SYS_DESC(SYS_TPIDR_EL2), access_rw, reset_val, TPIDR_EL2, 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 000000000000..bfe0ccde514f
--- /dev/null
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -0,0 +1,178 @@
+#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 <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_arm.h>
+#include <kvm/arm_vgic.h>
+
+#include "vgic.h"
+
+static inline struct vgic_v3_cpu_if *vcpu_nested_if(struct kvm_vcpu *vcpu)
+{
+	return &vcpu->arch.vgic_cpu.nested_vgic_v3;
+}
+
+static inline struct vgic_v3_cpu_if *vcpu_shadow_if(struct kvm_vcpu *vcpu)
+{
+	return &vcpu->arch.vgic_cpu.shadow_vgic_v3;
+}
+
+static inline bool lr_triggers_eoi(u64 lr)
+{
+	return !(lr & (ICH_LR_STATE | ICH_LR_HW)) && (lr & ICH_LR_EOI);
+}
+
+u16 vgic_v3_get_eisr(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
+	u16 reg = 0;
+	int i;
+
+	for (i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
+		if (lr_triggers_eoi(cpu_if->vgic_lr[i]))
+			reg |= BIT(i);
+	}
+
+	return reg;
+}
+
+u16 vgic_v3_get_elrsr(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
+	u16 reg = 0;
+	int i;
+
+	for (i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
+		if (!(cpu_if->vgic_lr[i] & ICH_LR_STATE))
+			reg |= BIT(i);
+	}
+
+	return reg;
+}
+
+u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
+	int nr_lr = kvm_vgic_global_state.nr_lr;
+	u64 reg = 0;
+
+	if (vgic_v3_get_eisr(vcpu))
+		reg |= ICH_MISR_EOI;
+
+	if (cpu_if->vgic_hcr & ICH_HCR_UIE) {
+		int used_lrs;
+
+		used_lrs = nr_lr - hweight16(vgic_v3_get_elrsr(vcpu));
+		if (used_lrs <= 1)
+			reg |= ICH_MISR_U;
+	}
+
+	/* TODO: Support remaining bits in this register */
+	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 *cpu_if = vcpu_nested_if(vcpu);
+	struct vgic_v3_cpu_if *s_cpu_if = vcpu_shadow_if(vcpu);
+	struct vgic_irq *irq;
+	int i, used_lrs = 0;
+
+	for (i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
+		u64 lr = cpu_if->vgic_lr[i];
+		int l1_irq;
+
+		if (!(lr & ICH_LR_HW))
+			goto next;
+
+		/* We have the HW bit set */
+		l1_irq = (lr & ICH_LR_PHYS_ID_MASK) >> ICH_LR_PHYS_ID_SHIFT;
+		irq = vgic_get_irq(vcpu->kvm, vcpu, l1_irq);
+
+		if (!irq || !irq->hw) {
+			/* There was no real mapping, so nuke the HW bit */
+			lr &= ~ICH_LR_HW;
+			if (irq)
+				vgic_put_irq(vcpu->kvm, irq);
+			goto next;
+		}
+
+		/* Translate the virtual mapping to the real one */
+		lr &= ~ICH_LR_EOI; /* Why? */
+		lr &= ~ICH_LR_PHYS_ID_MASK;
+		lr |= (u64)irq->hwintid << ICH_LR_PHYS_ID_SHIFT;
+		vgic_put_irq(vcpu->kvm, irq);
+
+next:
+		s_cpu_if->vgic_lr[i] = lr;
+		used_lrs = i + 1;
+	}
+
+	s_cpu_if->used_lrs = used_lrs;
+}
+
+/*
+ * Change the shadow HWIRQ field back to the virtual value before copying over
+ * the entire shadow struct to the nested state.
+ */
+static void vgic_v3_fixup_shadow_lr_state(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
+	struct vgic_v3_cpu_if *s_cpu_if = vcpu_shadow_if(vcpu);
+	int lr;
+
+	for (lr = 0; lr < kvm_vgic_global_state.nr_lr; lr++) {
+		s_cpu_if->vgic_lr[lr] &= ~ICH_LR_PHYS_ID_MASK;
+		s_cpu_if->vgic_lr[lr] |= cpu_if->vgic_lr[lr] & ICH_LR_PHYS_ID_MASK;
+	}
+}
+
+void vgic_v3_load_nested(struct kvm_vcpu *vcpu)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+	vgic_cpu->shadow_vgic_v3 = vgic_cpu->nested_vgic_v3;
+	vgic_v3_create_shadow_lr(vcpu);
+	__vgic_v3_restore_state(vcpu_shadow_if(vcpu));
+}
+
+void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+	__vgic_v3_save_state(vcpu_shadow_if(vcpu));
+
+	/*
+	 * Translate the shadow state HW fields back to the virtual ones
+	 * before copying the shadow struct back to the nested one.
+	 */
+	vgic_v3_fixup_shadow_lr_state(vcpu);
+	vgic_cpu->nested_vgic_v3 = vgic_cpu->shadow_vgic_v3;
+}
+
+void vgic_v3_handle_nested_maint_irq(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
+
+	/*
+	 * If we exit a nested VM with a pending maintenance interrupt from the
+	 * GIC, then we need to forward this to the guest hypervisor so that it
+	 * can re-sync the appropriate LRs and sample level triggered interrupts
+	 * again.
+	 */
+	if (vgic_state_is_nested(vcpu) &&
+	    (cpu_if->vgic_hcr & ICH_HCR_EN) &&
+	    vgic_v3_get_misr(vcpu))
+		kvm_inject_nested_irq(vcpu);
+}
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 9cdf39a94a63..e4c5c27552da 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -6,6 +6,7 @@
 #include <kvm/arm_vgic.h>
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_nested.h>
 #include <asm/kvm_asm.h>
 
 #include "vgic.h"
@@ -289,6 +290,12 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
 		vgic_v3->vgic_sre = (ICC_SRE_EL1_DIB |
 				     ICC_SRE_EL1_DFB |
 				     ICC_SRE_EL1_SRE);
+		/*
+		 * If nesting is allowed, force GICv3 onto the nested
+		 * guests as well.
+		 */
+		if (nested_virt_in_use(vcpu))
+			vcpu->arch.vgic_cpu.nested_vgic_v3.vgic_sre = vgic_v3->vgic_sre;
 		vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE;
 	} else {
 		vgic_v3->vgic_sre = 0;
@@ -654,6 +661,13 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
+	/*
+	 * vgic_v3_load_nested only affects the LRs in the shadow
+	 * state, so it is fine to pass the nested state around.
+	 */
+	if (vgic_state_is_nested(vcpu))
+		cpu_if = &vcpu->arch.vgic_cpu.nested_vgic_v3;
+
 	/*
 	 * If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen
 	 * is dependent on ICC_SRE_EL1.SRE, and we have to perform the
@@ -667,6 +681,9 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 	if (has_vhe())
 		__vgic_v3_activate_traps(cpu_if);
 
+	if (vgic_state_is_nested(vcpu))
+		vgic_v3_load_nested(vcpu);
+
 	WARN_ON(vgic_v4_load(vcpu));
 }
 
@@ -674,6 +691,9 @@ void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
+	if (vgic_state_is_nested(vcpu))
+		cpu_if = &vcpu->arch.vgic_cpu.shadow_vgic_v3;
+
 	if (likely(cpu_if->vgic_sre))
 		cpu_if->vgic_vmcr = kvm_call_hyp_ret(__vgic_v3_read_vmcr);
 }
@@ -686,8 +706,14 @@ void vgic_v3_put(struct kvm_vcpu *vcpu)
 
 	vgic_v3_vmcr_sync(vcpu);
 
+	if (vgic_state_is_nested(vcpu))
+		cpu_if = &vcpu->arch.vgic_cpu.shadow_vgic_v3;
+
 	kvm_call_hyp(__vgic_v3_save_aprs, cpu_if);
 
 	if (has_vhe())
 		__vgic_v3_deactivate_traps(cpu_if);
+
+	if (vgic_state_is_nested(vcpu))
+		vgic_v3_put_nested(vcpu);
 }
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index 2af93dc80689..eae63e5c8322 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -876,6 +876,10 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
 	int used_lrs;
 
+	/* If nesting, this is a load/put affair, not flush/sync. */
+	if (vgic_state_is_nested(vcpu))
+		return;
+
 	/* An empty ap_list_head implies used_lrs == 0 */
 	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
 		return;
@@ -920,6 +924,29 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 	    !vgic_supports_direct_msis(vcpu->kvm))
 		return;
 
+	/*
+	 * 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;
+	}
+
 	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
 
 	if (!list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) {
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 4749c4748e5a..4c6e61398f63 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -306,6 +306,15 @@ struct vgic_cpu {
 
 	struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS];
 
+	/* CPU vif control registers for the virtual GICH interface */
+	struct vgic_v3_cpu_if	nested_vgic_v3;
+
+	/*
+	 * The shadow vif control register loaded to the hardware when
+	 * running a nested L2 guest with the virtual IMO/FMO bit set.
+	 */
+	struct vgic_v3_cpu_if	shadow_vgic_v3;
+
 	raw_spinlock_t ap_list_lock;	/* Protects the ap_list */
 
 	/*
@@ -362,6 +371,13 @@ void kvm_vgic_load(struct kvm_vcpu *vcpu);
 void kvm_vgic_put(struct kvm_vcpu *vcpu);
 void kvm_vgic_vmcr_sync(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);
+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)
@@ -406,4 +422,6 @@ 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 need_db);
 
+bool vgic_state_is_nested(struct kvm_vcpu *vcpu);
+
 #endif /* __KVM_ARM_VGIC_H */
-- 
2.29.2

[PATCH v3 47/66] KVM: arm64: nv: Don't load the GICv4 context on entering a nested guest

[Marc Zyngier]

When entering a nested guest (vgic_state_is_nested() == true),
special care must be taken *not* to make the vPE resident, as
these are interrupts targetting the L1 guest, and not any
nested guest.

By not making the vPE resident, we guarantee that the delivery
of an vLPI will result in a doorbell, forcing an exit from the
nested guest and a switch to the L1 guest to handle the interrupt.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/vgic/vgic-v3.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index e4c5c27552da..47ea2a0f3ae4 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -683,8 +683,8 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 
 	if (vgic_state_is_nested(vcpu))
 		vgic_v3_load_nested(vcpu);
-
-	WARN_ON(vgic_v4_load(vcpu));
+	else
+		WARN_ON(vgic_v4_load(vcpu));
 }
 
 void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)
@@ -702,6 +702,12 @@ void vgic_v3_put(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
+	/*
+	 * vgic_v4_put will do nothing if we were not resident. This
+	 * covers both the cases where we've blocked (we already have
+	 * done a vgic_v4_put) and when running a nested guest (the
+	 * vPE was never resident in order to generate a doorbell).
+	 */
 	WARN_ON(vgic_v4_put(vcpu, false));
 
 	vgic_v3_vmcr_sync(vcpu);
-- 
2.29.2

[PATCH v3 48/66] KVM: arm64: nv: vgic: Emulate the HW bit in software

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@arm.com>

Should the guest hypervisor use the HW bit in the LRs, we need to
emulate the deactivation from the L2 guest into the L1 distributor
emulation, which is handled by L0.

It's all good fun.

Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
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 | 32 ++++++++++++++++++++++++++++
 arch/arm64/kvm/vgic/vgic.c           |  6 ++++--
 include/kvm/arm_vgic.h               |  1 +
 5 files changed, 40 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index c0450828378b..ce6880280e92 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -57,6 +57,8 @@ 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 80406f463c28..b44c8977b4f3 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 bfe0ccde514f..3ee3438b5e22 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -138,6 +138,38 @@ static void vgic_v3_fixup_shadow_lr_state(struct kvm_vcpu *vcpu)
 	}
 }
 
+void vgic_v3_sync_nested(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
+	struct vgic_v3_cpu_if *s_cpu_if = vcpu_shadow_if(vcpu);
+	struct vgic_irq *irq;
+	int i;
+
+	for (i = 0; i < s_cpu_if->used_lrs; i++) {
+		u64 lr = cpu_if->vgic_lr[i];
+		int l1_irq;
+
+		if (!(lr & ICH_LR_HW) || !(lr & ICH_LR_STATE))
+			continue;
+
+		/*
+		 * 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.
+		 */
+		l1_irq = (lr & ICH_LR_PHYS_ID_MASK) >> ICH_LR_PHYS_ID_SHIFT;
+		irq = vgic_get_irq(vcpu->kvm, vcpu, l1_irq);
+		if (!irq)
+			continue; /* oh well, the guest hyp is broken */
+
+		lr = __gic_v3_get_lr(i);
+		if (!(lr & ICH_LR_STATE))
+			irq->active = false;
+
+		vgic_put_irq(vcpu->kvm, irq);
+	}
+}
+
 void vgic_v3_load_nested(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index eae63e5c8322..e1527ea60486 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -876,9 +876,11 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
 	int used_lrs;
 
-	/* If nesting, this is a load/put affair, not flush/sync. */
-	if (vgic_state_is_nested(vcpu))
+	/* 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))
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 4c6e61398f63..bf08135a0b78 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -371,6 +371,7 @@ void kvm_vgic_load(struct kvm_vcpu *vcpu);
 void kvm_vgic_put(struct kvm_vcpu *vcpu);
 void kvm_vgic_vmcr_sync(struct kvm_vcpu *vcpu);
 
+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);
-- 
2.29.2

[PATCH v3 49/66] KVM: arm64: nv: vgic: 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         | 22 +++++++++++++++++++
 include/kvm/arm_vgic.h                        |  3 +++
 tools/arch/arm/include/uapi/asm/kvm.h         |  1 +
 5 files changed, 38 insertions(+), 1 deletion(-)

diff --git a/Documentation/virt/kvm/devices/arm-vgic-v3.rst b/Documentation/virt/kvm/devices/arm-vgic-v3.rst
index 5dd3bff51978..da48bc9a6046 100644
--- a/Documentation/virt/kvm/devices/arm-vgic-v3.rst
+++ b/Documentation/virt/kvm/devices/arm-vgic-v3.rst
@@ -284,8 +284,18 @@ 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 fe3cb67f0d26..24c5752b1cc1 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -335,6 +335,7 @@ 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)
diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c
index 44419679f91a..dfb1d7cc66b3 100644
--- a/arch/arm64/kvm/vgic/vgic-kvm-device.c
+++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c
@@ -241,6 +241,12 @@ 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;
@@ -627,6 +633,21 @@ static int vgic_v3_set_attr(struct kvm_device *dev,
 		reg = tmp32;
 		return vgic_v3_attr_regs_access(dev, attr, &reg, true);
 	}
+	case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ: {
+		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+		u32 val;
+
+		if (get_user(val, uaddr))
+			return -EFAULT;
+
+		/* Must be a PPI. */
+		if ((val >= VGIC_NR_PRIVATE_IRQS) || (val < VGIC_NR_SGIS))
+			return -EINVAL;
+
+		dev->kvm->arch.vgic.maint_irq = val;
+
+		return 0;
+	}
 	case KVM_DEV_ARM_VGIC_GRP_CTRL: {
 		int ret;
 
@@ -712,6 +733,7 @@ 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/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index bf08135a0b78..e02bc45e9508 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -219,6 +219,9 @@ 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 {
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 03cd7c19a683..d5dd96902817 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)
-- 
2.29.2

[PATCH v3 50/66] KVM: arm64: nv: Implement maintenance interrupt forwarding

[Marc Zyngier]

When we take a maintenance interrupt, we need to decide whether
it is generated on an action from the guest, or if it is something
that needs to be forwarded to the guest hypervisor.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/vgic/vgic-init.c      | 30 ++++++++++++++++++++++++++++
 arch/arm64/kvm/vgic/vgic-v3-nested.c | 25 +++++++++++++++++++----
 2 files changed, 51 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 32e32d67a127..4cfaa36b7f91 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -6,10 +6,12 @@
 #include <linux/uaccess.h>
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
+#include <linux/irq.h>
 #include <linux/kvm_host.h>
 #include <kvm/arm_vgic.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_nested.h>
 #include "vgic.h"
 
 /*
@@ -221,6 +223,16 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	if (!irqchip_in_kernel(vcpu->kvm))
 		return 0;
 
+	if (nested_virt_in_use(vcpu)) {
+		/* FIXME: remove this hack */
+		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);
+		if (ret)
+			return ret;
+	}
+
 	/*
 	 * If we are creating a VCPU with a GICv3 we must also register the
 	 * KVM io device for the redistributor that belongs to this VCPU.
@@ -462,12 +474,23 @@ static int vgic_init_cpu_dying(unsigned int cpu)
 
 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).
 	 */
+
+	/* If not nested, deactivate */
+	if (!vcpu || !vgic_state_is_nested(vcpu)) {
+		irq_set_irqchip_state(irq, IRQCHIP_STATE_ACTIVE, false);
+		return IRQ_HANDLED;
+	}
+
+	/* Assume nested from now */
+	vgic_v3_handle_nested_maint_irq(vcpu);
 	return IRQ_HANDLED;
 }
 
@@ -538,6 +561,13 @@ int kvm_vgic_hyp_init(void)
 		return ret;
 	}
 
+	ret = irq_set_vcpu_affinity(kvm_vgic_global_state.maint_irq,
+				    kvm_get_running_vcpus());
+	if (ret) {
+		kvm_err("Error setting vcpu affinity\n");
+		goto out_free_irq;
+	}
+
 	ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
 				"kvm/arm/vgic:starting",
 				vgic_init_cpu_starting, vgic_init_cpu_dying);
diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index 3ee3438b5e22..4ba426e2324d 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -173,10 +173,20 @@ void vgic_v3_sync_nested(struct kvm_vcpu *vcpu)
 void vgic_v3_load_nested(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_irq *irq;
+	unsigned long flags;
 
 	vgic_cpu->shadow_vgic_v3 = vgic_cpu->nested_vgic_v3;
 	vgic_v3_create_shadow_lr(vcpu);
 	__vgic_v3_restore_state(vcpu_shadow_if(vcpu));
+
+	irq = vgic_get_irq(vcpu->kvm, vcpu, vcpu->kvm->arch.vgic.maint_irq);
+	raw_spin_lock_irqsave(&irq->irq_lock, flags);
+	if (irq->line_level || irq->active)
+		irq_set_irqchip_state(kvm_vgic_global_state.maint_irq,
+				      IRQCHIP_STATE_ACTIVE, true);
+	raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+	vgic_put_irq(vcpu->kvm, irq);
 }
 
 void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
@@ -191,11 +201,14 @@ void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
 	 */
 	vgic_v3_fixup_shadow_lr_state(vcpu);
 	vgic_cpu->nested_vgic_v3 = vgic_cpu->shadow_vgic_v3;
+	irq_set_irqchip_state(kvm_vgic_global_state.maint_irq,
+			      IRQCHIP_STATE_ACTIVE, false);
 }
 
 void vgic_v3_handle_nested_maint_irq(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
+	bool state;
 
 	/*
 	 * If we exit a nested VM with a pending maintenance interrupt from the
@@ -203,8 +216,12 @@ void vgic_v3_handle_nested_maint_irq(struct kvm_vcpu *vcpu)
 	 * can re-sync the appropriate LRs and sample level triggered interrupts
 	 * again.
 	 */
-	if (vgic_state_is_nested(vcpu) &&
-	    (cpu_if->vgic_hcr & ICH_HCR_EN) &&
-	    vgic_v3_get_misr(vcpu))
-		kvm_inject_nested_irq(vcpu);
+	if (!vgic_state_is_nested(vcpu))
+		return;
+
+	state  = cpu_if->vgic_hcr & ICH_HCR_EN;
+	state &= vgic_v3_get_misr(vcpu);
+
+	kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+			    vcpu->kvm->arch.vgic.maint_irq, state, vcpu);
 }
-- 
2.29.2

[PATCH v3 51/66] KVM: arm64: nv: Add nested GICv3 tracepoints

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@arm.com>

Adding tracepoints to be able to peek into the shadow LRs used when
running a guest guest.

Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/vgic/vgic-nested-trace.h | 137 ++++++++++++++++++++++++
 arch/arm64/kvm/vgic/vgic-v3-nested.c    |  13 ++-
 2 files changed, 149 insertions(+), 1 deletion(-)
 create mode 100644 arch/arm64/kvm/vgic/vgic-nested-trace.h

diff --git a/arch/arm64/kvm/vgic/vgic-nested-trace.h b/arch/arm64/kvm/vgic/vgic-nested-trace.h
new file mode 100644
index 000000000000..f1a074c791a6
--- /dev/null
+++ b/arch/arm64/kvm/vgic/vgic-nested-trace.h
@@ -0,0 +1,137 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#if !defined(_TRACE_VGIC_NESTED_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_VGIC_NESTED_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+
+#define SLR_ENTRY_VALS(x)							\
+	" ",									\
+	!!(__entry->lrs[x] & ICH_LR_HW),		   			\
+	!!(__entry->lrs[x] & ICH_LR_PENDING_BIT),	   			\
+	!!(__entry->lrs[x] & ICH_LR_ACTIVE_BIT),	   			\
+	__entry->lrs[x] & ICH_LR_VIRTUAL_ID_MASK,				\
+	(__entry->lrs[x] & ICH_LR_PHYS_ID_MASK) >> ICH_LR_PHYS_ID_SHIFT,	\
+	(__entry->orig_lrs[x] & ICH_LR_PHYS_ID_MASK) >> ICH_LR_PHYS_ID_SHIFT
+
+TRACE_EVENT(vgic_create_shadow_lrs,
+	TP_PROTO(struct kvm_vcpu *vcpu, int nr_lr, u64 *lrs, u64 *orig_lrs),
+	TP_ARGS(vcpu, nr_lr, lrs, orig_lrs),
+
+	TP_STRUCT__entry(
+		__field(	int,	nr_lr			)
+		__array(	u64,	lrs,		16	)
+		__array(	u64,	orig_lrs,	16	)
+	),
+
+	TP_fast_assign(
+		__entry->nr_lr		= nr_lr;
+		memcpy(__entry->lrs, lrs, 16 * sizeof(u64));
+		memcpy(__entry->orig_lrs, orig_lrs, 16 * sizeof(u64));
+	),
+
+	TP_printk("nr_lr: %d\n"
+		  "%50sLR[ 0]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[ 1]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[ 2]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[ 3]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[ 4]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[ 5]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[ 6]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[ 7]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[ 8]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[ 9]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[10]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[11]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[12]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[13]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[14]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)\n"
+		  "%50sLR[15]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu (%5llu)",
+		  __entry->nr_lr,
+		  SLR_ENTRY_VALS(0), SLR_ENTRY_VALS(1), SLR_ENTRY_VALS(2),
+		  SLR_ENTRY_VALS(3), SLR_ENTRY_VALS(4), SLR_ENTRY_VALS(5),
+		  SLR_ENTRY_VALS(6), SLR_ENTRY_VALS(7), SLR_ENTRY_VALS(8),
+		  SLR_ENTRY_VALS(9), SLR_ENTRY_VALS(10), SLR_ENTRY_VALS(11),
+		  SLR_ENTRY_VALS(12), SLR_ENTRY_VALS(13), SLR_ENTRY_VALS(14),
+		  SLR_ENTRY_VALS(15))
+);
+
+#define LR_ENTRY_VALS(x)							\
+	" ",									\
+	!!(__entry->lrs[x] & ICH_LR_HW),		   			\
+	!!(__entry->lrs[x] & ICH_LR_PENDING_BIT),	   			\
+	!!(__entry->lrs[x] & ICH_LR_ACTIVE_BIT),	   			\
+	__entry->lrs[x] & ICH_LR_VIRTUAL_ID_MASK,				\
+	(__entry->lrs[x] & ICH_LR_PHYS_ID_MASK) >> ICH_LR_PHYS_ID_SHIFT
+
+TRACE_EVENT(vgic_put_nested,
+	TP_PROTO(struct kvm_vcpu *vcpu, int nr_lr, u64 *lrs),
+	TP_ARGS(vcpu, nr_lr, lrs),
+
+	TP_STRUCT__entry(
+		__field(	int,	nr_lr			)
+		__array(	u64,	lrs,		16	)
+	),
+
+	TP_fast_assign(
+		__entry->nr_lr		= nr_lr;
+		memcpy(__entry->lrs, lrs, 16 * sizeof(u64));
+	),
+
+	TP_printk("nr_lr: %d\n"
+		  "%50sLR[ 0]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[ 1]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[ 2]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[ 3]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[ 4]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[ 5]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[ 6]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[ 7]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[ 8]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[ 9]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[10]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[11]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[12]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[13]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[14]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu\n"
+		  "%50sLR[15]: HW: %d P: %d: A: %d vINTID: %5llu pINTID: %5llu",
+		  __entry->nr_lr,
+		  LR_ENTRY_VALS(0), LR_ENTRY_VALS(1), LR_ENTRY_VALS(2),
+		  LR_ENTRY_VALS(3), LR_ENTRY_VALS(4), LR_ENTRY_VALS(5),
+		  LR_ENTRY_VALS(6), LR_ENTRY_VALS(7), LR_ENTRY_VALS(8),
+		  LR_ENTRY_VALS(9), LR_ENTRY_VALS(10), LR_ENTRY_VALS(11),
+		  LR_ENTRY_VALS(12), LR_ENTRY_VALS(13), LR_ENTRY_VALS(14),
+		  LR_ENTRY_VALS(15))
+);
+
+TRACE_EVENT(vgic_nested_hw_emulate,
+	TP_PROTO(int lr, u64 lr_val, u32 l1_intid),
+	TP_ARGS(lr, lr_val, l1_intid),
+
+	TP_STRUCT__entry(
+		__field(	int,	lr		)
+		__field(	u64,	lr_val		)
+		__field(	u32,	l1_intid	)
+	),
+
+	TP_fast_assign(
+		__entry->lr		= lr;
+		__entry->lr_val		= lr_val;
+		__entry->l1_intid	= l1_intid;
+	),
+
+	TP_printk("lr: %d LR %llx L1 INTID: %u\n",
+		  __entry->lr, __entry->lr_val, __entry->l1_intid)
+);
+
+#endif /* _TRACE_VGIC_NESTED_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH vgic/
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE vgic-nested-trace
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index 4ba426e2324d..94b1edb67011 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -13,6 +13,9 @@
 
 #include "vgic.h"
 
+#define CREATE_TRACE_POINTS
+#include "vgic-nested-trace.h"
+
 static inline struct vgic_v3_cpu_if *vcpu_nested_if(struct kvm_vcpu *vcpu)
 {
 	return &vcpu->arch.vgic_cpu.nested_vgic_v3;
@@ -119,6 +122,9 @@ static void vgic_v3_create_shadow_lr(struct kvm_vcpu *vcpu)
 		used_lrs = i + 1;
 	}
 
+	trace_vgic_create_shadow_lrs(vcpu, kvm_vgic_global_state.nr_lr,
+				     s_cpu_if->vgic_lr, cpu_if->vgic_lr);
+
 	s_cpu_if->used_lrs = used_lrs;
 }
 
@@ -163,8 +169,10 @@ void vgic_v3_sync_nested(struct kvm_vcpu *vcpu)
 			continue; /* oh well, the guest hyp is broken */
 
 		lr = __gic_v3_get_lr(i);
-		if (!(lr & ICH_LR_STATE))
+		if (!(lr & ICH_LR_STATE)) {
+			trace_vgic_nested_hw_emulate(i, lr, l1_irq);
 			irq->active = false;
+		}
 
 		vgic_put_irq(vcpu->kvm, irq);
 	}
@@ -195,6 +203,9 @@ void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
 
 	__vgic_v3_save_state(vcpu_shadow_if(vcpu));
 
+	trace_vgic_put_nested(vcpu, kvm_vgic_global_state.nr_lr,
+			      vcpu_shadow_if(vcpu)->vgic_lr);
+
 	/*
 	 * Translate the shadow state HW fields back to the virtual ones
 	 * before copying the shadow struct back to the nested one.
-- 
2.29.2

[PATCH v3 52/66] KVM: arm64: nv: Allow userspace to request KVM_ARM_VCPU_NESTED_VIRT

[Marc Zyngier]

Since we're (almost) feature complete, let's allow userspace to
request KVM_ARM_VCPU_NESTED_VIRT by bumping the KVM_VCPU_MAX_FEATURES
up.

It's going to be great...

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

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index bd91b4219d5e..9e190a65e78b 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -38,7 +38,7 @@
 
 #define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS
 
-#define KVM_VCPU_MAX_FEATURES 7
+#define KVM_VCPU_MAX_FEATURES 8
 
 #define KVM_REQ_SLEEP \
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-- 
2.29.2

[PATCH v3 53/66] KVM: arm64: nv: Add handling of ARMv8.4-TTL TLB invalidation

[Marc Zyngier]

Support guest-provided information information to find out about
the range of required invalidation.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h |  1 +
 arch/arm64/kvm/nested.c             | 57 +++++++++++++++++++++
 arch/arm64/kvm/sys_regs.c           | 79 +++++++++++++++++++----------
 3 files changed, 109 insertions(+), 28 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 5fa3c634c8e1..7c47ad655e2e 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -123,6 +123,7 @@ extern bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg,
 			    u64 control_bit);
 extern bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit);
 extern bool forward_nv_traps(struct kvm_vcpu *vcpu);
+unsigned int ttl_to_size(u8 ttl);
 
 struct sys_reg_params;
 struct sys_reg_desc;
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 9574fde823e6..05b711e730b6 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -351,6 +351,63 @@ int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
 	return ret;
 }
 
+
+unsigned int ttl_to_size(u8 ttl)
+{
+	int level = ttl & 3;
+	int gran = (ttl >> 2) & 3;
+	unsigned int max_size = 0;
+
+	switch (gran) {
+	case TLBI_TTL_TG_4K:
+		switch (level) {
+		case 0:
+			break;
+		case 1:
+			max_size = SZ_1G;
+			break;
+		case 2:
+			max_size = SZ_2M;
+			break;
+		case 3:
+			max_size = SZ_4K;
+			break;
+		}
+		break;
+	case TLBI_TTL_TG_16K:
+		switch (level) {
+		case 0:
+		case 1:
+			break;
+		case 2:
+			max_size = SZ_32M;
+			break;
+		case 3:
+			max_size = SZ_16K;
+			break;
+		}
+		break;
+	case TLBI_TTL_TG_64K:
+		switch (level) {
+		case 0:
+		case 1:
+			/* No 52bit IPA support */
+			break;
+		case 2:
+			max_size = SZ_512M;
+			break;
+		case 3:
+			max_size = SZ_64K;
+			break;
+		}
+		break;
+	default:			/* No size information */
+		break;
+	}
+
+	return max_size;
+}
+
 /* Must be called with kvm->lock held */
 struct kvm_s2_mmu *lookup_s2_mmu(struct kvm *kvm, u64 vttbr, u64 hcr)
 {
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 60d2fb6edc93..61094f5e955e 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -9,6 +9,7 @@
  *          Christoffer Dall <c.dall@virtualopensystems.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/bsearch.h>
 #include <linux/kvm_host.h>
 #include <linux/mm.h>
@@ -2578,59 +2579,81 @@ static bool handle_vmalls12e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return true;
 }
 
+static unsigned long compute_tlb_inval_range(struct kvm_vcpu *vcpu,
+					     struct kvm_s2_mmu *mmu,
+					     u64 val)
+{
+	unsigned long max_size;
+	u8 ttl = 0;
+
+	if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL)) {
+		ttl = FIELD_GET(GENMASK_ULL(47, 44), val);
+	}
+
+	max_size = ttl_to_size(ttl);
+
+	if (!max_size) {
+		u64 vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+
+		/* Compute the maximum extent of the invalidation */
+		switch ((vtcr & VTCR_EL2_TG0_MASK)) {
+		case VTCR_EL2_TG0_4K:
+			max_size = SZ_1G;
+			break;
+		case VTCR_EL2_TG0_16K:
+			max_size = SZ_32M;
+			break;
+		case VTCR_EL2_TG0_64K:
+			/*
+			 * No, we do not support 52bit IPA in nested yet. Once
+			 * we do, this should be 4TB.
+			 */
+			/* FIXME: remove the 52bit PA support from the IDregs */
+			max_size = SZ_512M;
+			break;
+		default:
+			BUG();
+		}
+	}
+
+	WARN_ON(!max_size);
+	return max_size;
+}
+
 static bool handle_ipas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			     const struct sys_reg_desc *r)
 {
 	u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
-	u64 vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
 	struct kvm_s2_mmu *mmu;
 	u64 base_addr;
-	int max_size;
+	unsigned long max_size;
 
 	/*
 	 * We drop a number of things from the supplied value:
 	 *
 	 * - NS bit: we're non-secure only.
 	 *
-	 * - TTL field: We already have the granule size from the
-	 *   VTCR_EL2.TG0 field, and the level is only relevant to the
-	 *   guest's S2PT.
-	 *
 	 * - IPA[51:48]: We don't support 52bit IPA just yet...
 	 *
 	 * And of course, adjust the IPA to be on an actual address.
 	 */
 	base_addr = (p->regval & GENMASK_ULL(35, 0)) << 12;
 
-	/* Compute the maximum extent of the invalidation */
-	switch ((vtcr & VTCR_EL2_TG0_MASK)) {
-	case VTCR_EL2_TG0_4K:
-		max_size = SZ_1G;
-		break;
-	case VTCR_EL2_TG0_16K:
-		max_size = SZ_32M;
-		break;
-	case VTCR_EL2_TG0_64K:
-		/*
-		 * No, we do not support 52bit IPA in nested yet. Once
-		 * we do, this should be 4TB.
-		 */
-		/* FIXME: remove the 52bit PA support from the IDregs */
-		max_size = SZ_512M;
-		break;
-	default:
-		BUG();
-	}
-
 	spin_lock(&vcpu->kvm->mmu_lock);
 
 	mmu = lookup_s2_mmu(vcpu->kvm, vttbr, HCR_VM);
-	if (mmu)
+	if (mmu) {
+		max_size = compute_tlb_inval_range(vcpu, mmu, p->regval);
+		base_addr &= ~(max_size - 1);
 		kvm_unmap_stage2_range(mmu, base_addr, max_size);
+	}
 
 	mmu = lookup_s2_mmu(vcpu->kvm, vttbr, 0);
-	if (mmu)
+	if (mmu) {
+		max_size = compute_tlb_inval_range(vcpu, mmu, p->regval);
+		base_addr &= ~(max_size - 1);
 		kvm_unmap_stage2_range(mmu, base_addr, max_size);
+	}
 
 	spin_unlock(&vcpu->kvm->mmu_lock);
 
-- 
2.29.2

[PATCH v3 54/66] KVM: arm64: nv: Invalidate TLBs based on shadow S2 TTL-like information

[Marc Zyngier]

In order to be able to make S2 TLB invalidations more performant on NV,
let's use a scheme derived from the ARMv8.4 TTL extension.

If bits [56:55] in the descriptor are non-zero, they indicate a level
which can be used as an invalidation range.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h |  4 ++
 arch/arm64/kvm/nested.c             | 98 +++++++++++++++++++++++++++++
 arch/arm64/kvm/sys_regs.c           | 13 ++--
 3 files changed, 110 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 7c47ad655e2e..34499c496ae6 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -123,6 +123,8 @@ extern bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg,
 			    u64 control_bit);
 extern bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit);
 extern bool forward_nv_traps(struct kvm_vcpu *vcpu);
+u8 get_guest_mapping_ttl(struct kvm_vcpu *vcpu, struct kvm_s2_mmu *mmu,
+			 u64 addr);
 unsigned int ttl_to_size(u8 ttl);
 
 struct sys_reg_params;
@@ -131,4 +133,6 @@ struct sys_reg_desc;
 void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
 			  const struct sys_reg_desc *r);
 
+#define KVM_NV_GUEST_MAP_SZ	GENMASK_ULL(56, 55)
+
 #endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 05b711e730b6..eef8f9873814 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -16,6 +16,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/bitfield.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
@@ -351,6 +352,29 @@ int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
 	return ret;
 }
 
+static int read_host_s2_desc(phys_addr_t pa, u64 *desc, void *data)
+{
+	u64 *va = phys_to_virt(pa);
+
+	*desc = *va;
+
+	return 0;
+}
+
+static int kvm_walk_shadow_s2(struct kvm_s2_mmu *mmu, phys_addr_t gipa,
+			      struct kvm_s2_trans *result)
+{
+	struct s2_walk_info wi = { };
+
+	wi.read_desc = read_host_s2_desc;
+	wi.baddr = mmu->pgd_phys;
+
+	vtcr_to_walk_info(mmu->kvm->arch.vtcr, &wi);
+
+	wi.be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
+
+	return walk_nested_s2_pgd(gipa, &wi, result);
+}
 
 unsigned int ttl_to_size(u8 ttl)
 {
@@ -408,6 +432,80 @@ unsigned int ttl_to_size(u8 ttl)
 	return max_size;
 }
 
+/*
+ * Compute the equivalent of the TTL field by parsing the shadow PT.
+ * The granule size is extracted from VTCR_EL2.TG0 while the level is
+ * retrieved from first entry carrying the level as a tag.
+ */
+u8 get_guest_mapping_ttl(struct kvm_vcpu *vcpu, struct kvm_s2_mmu *mmu,
+			 u64 addr)
+{
+	u64 tmp, sz = 0, vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+	struct kvm_s2_trans out;
+	u8 ttl, level;
+
+	switch (vtcr & VTCR_EL2_TG0_MASK) {
+	case VTCR_EL2_TG0_4K:
+		ttl = (1 << 2);
+		break;
+	case VTCR_EL2_TG0_16K:
+		ttl = (2 << 2);
+		break;
+	case VTCR_EL2_TG0_64K:
+		ttl = (3 << 2);
+		break;
+	default:
+		BUG();
+	}
+
+	tmp = addr;
+
+again:
+	/* Iteratively compute the block sizes for a particular granule size */
+	switch (vtcr & VTCR_EL2_TG0_MASK) {
+	case VTCR_EL2_TG0_4K:
+		if	(sz < SZ_4K)	sz = SZ_4K;
+		else if (sz < SZ_2M)	sz = SZ_2M;
+		else if (sz < SZ_1G)	sz = SZ_1G;
+		else			sz = 0;
+		break;
+	case VTCR_EL2_TG0_16K:
+		if	(sz < SZ_16K)	sz = SZ_16K;
+		else if (sz < SZ_32M)	sz = SZ_32M;
+		else			sz = 0;
+		break;
+	case VTCR_EL2_TG0_64K:
+		if	(sz < SZ_64K)	sz = SZ_64K;
+		else if (sz < SZ_512M)	sz = SZ_512M;
+		else			sz = 0;
+		break;
+	default:
+		BUG();
+	}
+
+	if (sz == 0)
+		return 0;
+
+	tmp &= ~(sz - 1);
+	out = (struct kvm_s2_trans) { };
+	kvm_walk_shadow_s2(mmu, tmp, &out);
+	level = FIELD_GET(KVM_NV_GUEST_MAP_SZ, out.upper_attr);
+	if (!level)
+		goto again;
+
+	ttl |= level;
+
+	/*
+	 * We now have found some level information in the shadow S2. Check
+	 * that the resulting range is actually including the original IPA.
+	 */
+	sz = ttl_to_size(ttl);
+	if (addr < (tmp + sz))
+		return ttl;
+
+	return 0;
+}
+
 /* Must be called with kvm->lock held */
 struct kvm_s2_mmu *lookup_s2_mmu(struct kvm *kvm, u64 vttbr, u64 hcr)
 {
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 61094f5e955e..bd0a3e861ca5 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2584,10 +2584,13 @@ static unsigned long compute_tlb_inval_range(struct kvm_vcpu *vcpu,
 					     u64 val)
 {
 	unsigned long max_size;
-	u8 ttl = 0;
+	u8 ttl;
 
-	if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL)) {
-		ttl = FIELD_GET(GENMASK_ULL(47, 44), val);
+	ttl = FIELD_GET(GENMASK_ULL(47, 44), val);
+
+	if (!(cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL) && ttl)) {
+		u64 addr = (val & GENMASK_ULL(35, 0)) << 12;
+		ttl = get_guest_mapping_ttl(vcpu, mmu, addr);
 	}
 
 	max_size = ttl_to_size(ttl);
@@ -2628,6 +2631,8 @@ static bool handle_ipas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	u64 base_addr;
 	unsigned long max_size;
 
+	spin_lock(&vcpu->kvm->mmu_lock);
+
 	/*
 	 * We drop a number of things from the supplied value:
 	 *
@@ -2639,8 +2644,6 @@ static bool handle_ipas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	 */
 	base_addr = (p->regval & GENMASK_ULL(35, 0)) << 12;
 
-	spin_lock(&vcpu->kvm->mmu_lock);
-
 	mmu = lookup_s2_mmu(vcpu->kvm, vttbr, HCR_VM);
 	if (mmu) {
 		max_size = compute_tlb_inval_range(vcpu, mmu, p->regval);
-- 
2.29.2

[PATCH v3 55/66] KVM: arm64: Allow populating S2 SW bits

[Marc Zyngier]

The S2 page table code doesn't use the SW bits yet, but we are about
to need them to encode some guest Stage-2 information (its mapping size
in the form of the TTL encoding).

Propagate the SW bits specified by the caller, and store them into
the corresponding entry.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_pgtable.h | 10 ++++++++++
 arch/arm64/kvm/hyp/pgtable.c         |  6 ++++++
 2 files changed, 16 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 52ab38db04c7..90a369185702 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -35,6 +35,10 @@ struct kvm_pgtable {
  * @KVM_PGTABLE_PROT_W:		Write permission.
  * @KVM_PGTABLE_PROT_R:		Read permission.
  * @KVM_PGTABLE_PROT_DEVICE:	Device attributes.
+ * @KVM_PGTABLE_PROT_S2_SW0:	SW bit 0.
+ * @KVM_PGTABLE_PROT_S2_SW1:	SW bit 1.
+ * @KVM_PGTABLE_PROT_S2_SW2:	SW bit 2.
+ * @KVM_PGTABLE_PROT_S2_SW3:	SW bit 3.
  */
 enum kvm_pgtable_prot {
 	KVM_PGTABLE_PROT_X			= BIT(0),
@@ -42,6 +46,12 @@ enum kvm_pgtable_prot {
 	KVM_PGTABLE_PROT_R			= BIT(2),
 
 	KVM_PGTABLE_PROT_DEVICE			= BIT(3),
+
+	/* Cunningly, this matches the PTE bits... */
+	KVM_PGTABLE_PROT_S2_SW0			= BIT(55),
+	KVM_PGTABLE_PROT_S2_SW1			= BIT(56),
+	KVM_PGTABLE_PROT_S2_SW2			= BIT(57),
+	KVM_PGTABLE_PROT_S2_SW3			= BIT(58),
 };
 
 #define PAGE_HYP		(KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W)
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 0271b4a3b9fe..9ee53e71a939 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -44,6 +44,7 @@
 #define KVM_PTE_LEAF_ATTR_HI_S1_XN	BIT(54)
 
 #define KVM_PTE_LEAF_ATTR_HI_S2_XN	BIT(54)
+#define KVM_PTE_LEAF_ATTR_HI_S2_SW	GENMASK(58, 55)
 
 struct kvm_pgtable_walk_data {
 	struct kvm_pgtable		*pgt;
@@ -457,6 +458,7 @@ static int stage2_map_set_prot_attr(enum kvm_pgtable_prot prot,
 
 	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh);
 	attr |= KVM_PTE_LEAF_ATTR_LO_S2_AF;
+	attr |= prot & KVM_PTE_LEAF_ATTR_HI_S2_SW;
 	data->attr = attr;
 	return 0;
 }
@@ -805,6 +807,10 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 	if (prot & KVM_PGTABLE_PROT_X)
 		clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN;
 
+	/* Always propagate the SW bits */
+	clr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_HI_S2_SW, 0xf);
+	set |= prot & KVM_PTE_LEAF_ATTR_HI_S2_SW;
+
 	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level);
 	if (!ret)
 		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, pgt->mmu, addr, level);
-- 
2.29.2

[PATCH v3 56/66] KVM: arm64: nv: Tag shadow S2 entries with nested level

[Marc Zyngier]

Populate bits [56:55] of the leaf entry with the level provided
by the guest's S2 translation.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h | 8 ++++++++
 arch/arm64/kvm/mmu.c                | 6 ++++++
 2 files changed, 14 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 34499c496ae6..36f2cd2c6fdf 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -5,6 +5,8 @@
 #include <linux/bitfield.h>
 #include <linux/kvm_host.h>
 
+#include <asm/kvm_pgtable.h>
+
 static inline bool nested_virt_in_use(const struct kvm_vcpu *vcpu)
 {
 	return (!__is_defined(__KVM_NVHE_HYPERVISOR__) &&
@@ -135,4 +137,10 @@ void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
 
 #define KVM_NV_GUEST_MAP_SZ	GENMASK_ULL(56, 55)
 
+static inline u64 kvm_encode_nested_level(struct kvm_s2_trans *trans)
+{
+	return FIELD_PREP(KVM_PGTABLE_PROT_S2_SW1 | KVM_PGTABLE_PROT_S2_SW0,
+			  trans->level);
+}
+
 #endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 5fb13995190e..0994b3264d28 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -920,11 +920,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * Potentially reduce shadow S2 permissions to match the guest's own
 	 * S2. For exec faults, we'd only reach this point if the guest
 	 * actually allowed it (see kvm_s2_handle_perm_fault).
+	 *
+	 * Also encode the level of the nested translation in the SW bits of
+	 * the PTE/PMD/PUD. This will be retrived on TLB invalidation from
+	 * the guest.
 	 */
 	if (kvm_is_shadow_s2_fault(vcpu)) {
 		writable &= kvm_s2_trans_writable(nested);
 		if (!kvm_s2_trans_readable(nested))
 			prot &= ~KVM_PGTABLE_PROT_R;
+
+		prot |= kvm_encode_nested_level(nested);
 	}
 
 	spin_lock(&kvm->mmu_lock);
-- 
2.29.2

[PATCH v3 57/66] KVM: arm64: nv: Add include containing the VNCR_EL2 offsets

[Marc Zyngier]

VNCR_EL2 points to a page containing a number of system registers
accessed by a guest hypervisor when ARMv8.4-NV is enabled.

Let's document the offsets in that page, as we are going to use
this layout.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/vncr_mapping.h | 73 +++++++++++++++++++++++++++
 1 file changed, 73 insertions(+)
 create mode 100644 arch/arm64/include/asm/vncr_mapping.h

diff --git a/arch/arm64/include/asm/vncr_mapping.h b/arch/arm64/include/asm/vncr_mapping.h
new file mode 100644
index 000000000000..64c46d658fc8
--- /dev/null
+++ b/arch/arm64/include/asm/vncr_mapping.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * System register offsets in the VNCR page
+ * All offsets are *byte* displacements!
+ */
+
+#ifndef __ARM64_VNCR_MAPPING_H__
+#define __ARM64_VNCR_MAPPING_H__
+
+#define VNCR_VTTBR_EL2          0x020
+#define VNCR_VTCR_EL2           0x040
+#define VNCR_VMPIDR_EL2         0x050
+#define VNCR_CNTVOFF_EL2        0x060
+#define VNCR_HCR_EL2            0x078
+#define VNCR_HSTR_EL2           0x080
+#define VNCR_VPIDR_EL2          0x088
+#define VNCR_TPIDR_EL2          0x090
+#define VNCR_VNCR_EL2           0x0B0
+#define VNCR_CPACR_EL1          0x100
+#define VNCR_CONTEXTIDR_EL1     0x108
+#define VNCR_SCTLR_EL1          0x110
+#define VNCR_ACTLR_EL1          0x118
+#define VNCR_TCR_EL1            0x120
+#define VNCR_AFSR0_EL1          0x128
+#define VNCR_AFSR1_EL1          0x130
+#define VNCR_ESR_EL1            0x138
+#define VNCR_MAIR_EL1           0x140
+#define VNCR_AMAIR_EL1          0x148
+#define VNCR_MDSCR_EL1          0x158
+#define VNCR_SPSR_EL1           0x160
+#define VNCR_CNTV_CVAL_EL0      0x168
+#define VNCR_CNTV_CTL_EL0       0x170
+#define VNCR_CNTP_CVAL_EL0      0x178
+#define VNCR_CNTP_CTL_EL0       0x180
+#define VNCR_SCXTNUM_EL1        0x188
+#define VNCR_ZCR_EL1            0x1E0
+#define VNCR_TTBR0_EL1          0x200
+#define VNCR_TTBR1_EL1          0x210
+#define VNCR_FAR_EL1            0x220
+#define VNCR_ELR_EL1            0x230
+#define VNCR_SP_EL1             0x240
+#define VNCR_VBAR_EL1           0x250
+#define VNCR_ICH_LR0_EL2        0x400
+//      VNCR_ICH_LRN_EL2(n)     VNCR_ICH_LR0_EL2+8*((n) & 7)
+#define VNCR_ICH_AP0R0_EL2      0x480
+//      VNCR_ICH_AP0RN_EL2(n)   VNCR_ICH_AP0R0_EL2+8*((n) & 3)
+#define VNCR_ICH_AP1R0_EL2      0x4A0
+//      VNCR_ICH_AP1RN_EL2(n)   VNCR_ICH_AP1R0_EL2+8*((n) & 3)
+#define VNCR_ICH_HCR_EL2        0x4C0
+#define VNCR_ICH_VMCR_EL2       0x4C8
+#define VNCR_VDISR_EL2          0x500
+#define VNCR_PMBLIMITR_EL1      0x800
+#define VNCR_PMBPTR_EL1         0x810
+#define VNCR_PMBSR_EL1          0x820
+#define VNCR_PMSCR_EL1          0x828
+#define VNCR_PMSEVFR_EL1        0x830
+#define VNCR_PMSICR_EL1         0x838
+#define VNCR_PMSIRR_EL1         0x840
+#define VNCR_PMSLATFR_EL1       0x848
+#define VNCR_TRFCR_EL1          0x880
+#define VNCR_MPAM1_EL1          0x900
+#define VNCR_MPAMHCR_EL2        0x930
+#define VNCR_MPAMVPMV_EL2       0x938
+#define VNCR_MPAMVPM0_EL2       0x940
+#define VNCR_MPAMVPM1_EL2       0x948
+#define VNCR_MPAMVPM2_EL2       0x950
+#define VNCR_MPAMVPM3_EL2       0x958
+#define VNCR_MPAMVPM4_EL2       0x960
+#define VNCR_MPAMVPM5_EL2       0x968
+#define VNCR_MPAMVPM6_EL2       0x970
+#define VNCR_MPAMVPM7_EL2       0x978
+
+#endif /* __ARM64_VNCR_MAPPING_H__ */
-- 
2.29.2

[PATCH v3 58/66] KVM: arm64: Map VNCR-capable registers to a separate page

[Marc Zyngier]

With ARMv8.4-NV, registers that can be directly accessed in memory
by the guest have to live at architected offsets in a special page.

Let's annotate the sysreg enum to reflect the offset at which they
are in this page, whith a little twist:

If running on HW that doesn't have the ARMv8.4-NV feature, or even
a VM that doesn't use NV, we store all the system registers in the
usual sys_regs array. The only difference with the pre-8.4
situation is that VNCR-capable registers are at a "similar" offset
as in the VNCR page (we can compute the actual offset at compile
time), and that the sys_regs array is both bigger and sparse.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 97 ++++++++++++++++++++-----------
 1 file changed, 63 insertions(+), 34 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 9e190a65e78b..a4832df71a52 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -26,6 +26,7 @@
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/thread_info.h>
+#include <asm/vncr_mapping.h>
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
@@ -171,31 +172,32 @@ struct kvm_vcpu_fault_info {
 	u64 disr_el1;		/* Deferred [SError] Status Register */
 };
 
+/*
+ * VNCR() just places the VNCR_capable registers in the enum after
+ * __VNCR_START__, and the value (after correction) to be an 8-byte offset
+ * from the VNCR base. As we don't require the enum to be otherwise ordered,
+ * we need the terrible hack below to ensure that we correctly size the
+ * sys_regs array, no matter what.
+ *
+ * The __MAX__ macro has been lifted from Sean Eron Anderson's wonderful
+ * treasure trove of bit hacks:
+ * https://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
+ */
+#define __MAX__(x,y)	((x) ^ (((x) ^ (y)) & -((x) < (y))))
+#define VNCR(r)						\
+	__before_##r,					\
+	r = __VNCR_START__ + ((VNCR_ ## r) / 8),	\
+	__after_##r = __MAX__(__before_##r - 1, r)
+
 enum vcpu_sysreg {
 	__INVALID_SYSREG__,   /* 0 is reserved as an invalid value */
 	MPIDR_EL1,	/* MultiProcessor Affinity Register */
 	CSSELR_EL1,	/* Cache Size Selection Register */
-	SCTLR_EL1,	/* System Control Register */
-	ACTLR_EL1,	/* Auxiliary Control Register */
-	CPACR_EL1,	/* Coprocessor Access Control */
-	ZCR_EL1,	/* SVE Control */
-	TTBR0_EL1,	/* Translation Table Base Register 0 */
-	TTBR1_EL1,	/* Translation Table Base Register 1 */
-	TCR_EL1,	/* Translation Control Register */
-	ESR_EL1,	/* Exception Syndrome Register */
-	AFSR0_EL1,	/* Auxiliary Fault Status Register 0 */
-	AFSR1_EL1,	/* Auxiliary Fault Status Register 1 */
-	FAR_EL1,	/* Fault Address Register */
-	MAIR_EL1,	/* Memory Attribute Indirection Register */
-	VBAR_EL1,	/* Vector Base Address Register */
-	CONTEXTIDR_EL1,	/* Context ID Register */
 	TPIDR_EL0,	/* Thread ID, User R/W */
 	TPIDRRO_EL0,	/* Thread ID, User R/O */
 	TPIDR_EL1,	/* Thread ID, Privileged */
-	AMAIR_EL1,	/* Aux Memory Attribute Indirection Register */
 	CNTKCTL_EL1,	/* Timer Control Register (EL1) */
 	PAR_EL1,	/* Physical Address Register */
-	MDSCR_EL1,	/* Monitor Debug System Control Register */
 	MDCCINT_EL1,	/* Monitor Debug Comms Channel Interrupt Enable Reg */
 	DISR_EL1,	/* Deferred Interrupt Status Register */
 
@@ -226,16 +228,6 @@ enum vcpu_sysreg {
 	APGAKEYLO_EL1,
 	APGAKEYHI_EL1,
 
-	ELR_EL1,
-	SP_EL1,
-	SPSR_EL1,
-
-	CNTVOFF_EL2,
-	CNTV_CVAL_EL0,
-	CNTV_CTL_EL0,
-	CNTP_CVAL_EL0,
-	CNTP_CTL_EL0,
-
 	/* 32bit specific registers. */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
@@ -243,20 +235,14 @@ enum vcpu_sysreg {
 	DBGVCR32_EL2,	/* Debug Vector Catch Register */
 
 	/* EL2 registers */
-	VPIDR_EL2,	/* Virtualization Processor ID Register */
-	VMPIDR_EL2,	/* Virtualization Multiprocessor ID Register */
 	SCTLR_EL2,	/* System Control Register (EL2) */
 	ACTLR_EL2,	/* Auxiliary Control Register (EL2) */
-	HCR_EL2,	/* Hypervisor Configuration Register */
 	MDCR_EL2,	/* Monitor Debug Configuration Register (EL2) */
 	CPTR_EL2,	/* Architectural Feature Trap Register (EL2) */
-	HSTR_EL2,	/* Hypervisor System Trap Register */
 	HACR_EL2,	/* Hypervisor Auxiliary Control Register */
 	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
 	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
 	TCR_EL2,	/* Translation Control Register (EL2) */
-	VTTBR_EL2,	/* Virtualization Translation Table Base Register */
-	VTCR_EL2,	/* Virtualization Translation Control Register */
 	SPSR_EL2,	/* EL2 saved program status register */
 	ELR_EL2,	/* EL2 exception link register */
 	AFSR0_EL2,	/* Auxiliary Fault Status Register 0 (EL2) */
@@ -270,7 +256,6 @@ enum vcpu_sysreg {
 	RVBAR_EL2,	/* Reset Vector Base Address Register */
 	RMR_EL2,	/* Reset Management Register */
 	CONTEXTIDR_EL2,	/* Context ID Register (EL2) */
-	TPIDR_EL2,	/* EL2 Software Thread ID Register */
 	CNTHCTL_EL2,	/* Counter-timer Hypervisor Control register */
 	SP_EL2,		/* EL2 Stack Pointer */
 	CNTHP_CTL_EL2,
@@ -278,6 +263,41 @@ enum vcpu_sysreg {
 	CNTHV_CTL_EL2,
 	CNTHV_CVAL_EL2,
 
+	__VNCR_START__,	/* Any VNCR-capable reg goes after this point */
+
+	VNCR(SCTLR_EL1),/* System Control Register */
+	VNCR(ACTLR_EL1),/* Auxiliary Control Register */
+	VNCR(CPACR_EL1),/* Coprocessor Access Control */
+	VNCR(ZCR_EL1),	/* SVE Control */
+	VNCR(TTBR0_EL1),/* Translation Table Base Register 0 */
+	VNCR(TTBR1_EL1),/* Translation Table Base Register 1 */
+	VNCR(TCR_EL1),	/* Translation Control Register */
+	VNCR(ESR_EL1),	/* Exception Syndrome Register */
+	VNCR(AFSR0_EL1),/* Auxiliary Fault Status Register 0 */
+	VNCR(AFSR1_EL1),/* Auxiliary Fault Status Register 1 */
+	VNCR(FAR_EL1),	/* Fault Address Register */
+	VNCR(MAIR_EL1),	/* Memory Attribute Indirection Register */
+	VNCR(VBAR_EL1),	/* Vector Base Address Register */
+	VNCR(CONTEXTIDR_EL1),	/* Context ID Register */
+	VNCR(AMAIR_EL1),/* Aux Memory Attribute Indirection Register */
+	VNCR(MDSCR_EL1),/* Monitor Debug System Control Register */
+	VNCR(ELR_EL1),
+	VNCR(SP_EL1),
+	VNCR(SPSR_EL1),
+	VNCR(VPIDR_EL2),/* Virtualization Processor ID Register */
+	VNCR(VMPIDR_EL2),/* Virtualization Multiprocessor ID Register */
+	VNCR(HCR_EL2),	/* Hypervisor Configuration Register */
+	VNCR(HSTR_EL2),	/* Hypervisor System Trap Register */
+	VNCR(VTTBR_EL2),/* Virtualization Translation Table Base Register */
+	VNCR(VTCR_EL2),	/* Virtualization Translation Control Register */
+	VNCR(TPIDR_EL2),/* EL2 Software Thread ID Register */
+
+	VNCR(CNTVOFF_EL2),
+	VNCR(CNTV_CVAL_EL0),
+	VNCR(CNTV_CTL_EL0),
+	VNCR(CNTP_CVAL_EL0),
+	VNCR(CNTP_CTL_EL0),
+
 	NR_SYS_REGS	/* Nothing after this line! */
 };
 
@@ -294,6 +314,9 @@ struct kvm_cpu_context {
 	u64 sys_regs[NR_SYS_REGS];
 
 	struct kvm_vcpu *__hyp_running_vcpu;
+
+	/* This pointer has to be 4kB aligned. */
+	u64 *vncr_array;
 };
 
 struct kvm_pmu_events {
@@ -489,7 +512,13 @@ struct kvm_vcpu_arch {
  * for system registers that are never context switched, but only
  * emulated.
  */
-#define __ctxt_sys_reg(c,r)	(&(c)->sys_regs[(r)])
+static inline u64 *__ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
+{
+	if (unlikely(r >= __VNCR_START__ && ctxt->vncr_array))
+		return &ctxt->vncr_array[r - __VNCR_START__];
+
+	return (u64 *)&ctxt->sys_regs[r];
+}
 
 #define ctxt_sys_reg(c,r)	(*__ctxt_sys_reg(c,r))
 
-- 
2.29.2

[PATCH v3 59/66] KVM: arm64: nv: Move nested vgic state into the sysreg file

[Marc Zyngier]

The vgic nested state needs to be accessible from the VNCR page, and
thus needs to be part of the normal sysreg file. Let's move it there.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h    |  9 +++
 arch/arm64/kvm/sys_regs.c            | 53 +++++++++++------
 arch/arm64/kvm/vgic/vgic-v3-nested.c | 88 ++++++++++++++--------------
 arch/arm64/kvm/vgic/vgic-v3.c        | 17 ++++--
 arch/arm64/kvm/vgic/vgic.h           | 10 ++++
 include/kvm/arm_vgic.h               |  7 ---
 6 files changed, 110 insertions(+), 74 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index a4832df71a52..78630bd5124d 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -298,6 +298,15 @@ enum vcpu_sysreg {
 	VNCR(CNTP_CVAL_EL0),
 	VNCR(CNTP_CTL_EL0),
 
+	VNCR(ICH_LR0_EL2),
+	ICH_LR15_EL2 = ICH_LR0_EL2 + 15,
+	VNCR(ICH_AP0R0_EL2),
+	ICH_AP0R3_EL2 = ICH_AP0R0_EL2 + 3,
+	VNCR(ICH_AP1R0_EL2),
+	ICH_AP1R3_EL2 = ICH_AP1R0_EL2 + 3,
+	VNCR(ICH_HCR_EL2),
+	VNCR(ICH_VMCR_EL2),
+
 	NR_SYS_REGS	/* Nothing after this line! */
 };
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index bd0a3e861ca5..c7b004982ea9 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1790,17 +1790,17 @@ static bool access_gic_apr(struct kvm_vcpu *vcpu,
 			   struct sys_reg_params *p,
 			   const struct sys_reg_desc *r)
 {
-	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.nested_vgic_v3;
-	u32 index, *base;
+	u64 *base;
+	u8 index;
 
 	index = r->Op2;
 	if (r->CRm == 8)
-		base = cpu_if->vgic_ap0r;
+		base = __ctxt_sys_reg(&vcpu->arch.ctxt, ICH_AP0R0_EL2);
 	else
-		base = cpu_if->vgic_ap1r;
+		base = __ctxt_sys_reg(&vcpu->arch.ctxt, ICH_AP1R0_EL2);
 
 	if (p->is_write)
-		base[index] = p->regval;
+		base[index] = lower_32_bits(p->regval);
 	else
 		p->regval = base[index];
 
@@ -1811,12 +1811,10 @@ static bool access_gic_hcr(struct kvm_vcpu *vcpu,
 			   struct sys_reg_params *p,
 			   const struct sys_reg_desc *r)
 {
-	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.nested_vgic_v3;
-
 	if (p->is_write)
-		cpu_if->vgic_hcr = p->regval;
+		__vcpu_sys_reg(vcpu, ICH_HCR_EL2) = lower_32_bits(p->regval);
 	else
-		p->regval = cpu_if->vgic_hcr;
+		p->regval = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
 
 	return true;
 }
@@ -1873,12 +1871,19 @@ static bool access_gic_vmcr(struct kvm_vcpu *vcpu,
 			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *r)
 {
-	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.nested_vgic_v3;
-
 	if (p->is_write)
-		cpu_if->vgic_vmcr = p->regval;
+		__vcpu_sys_reg(vcpu, ICH_VMCR_EL2) = (p->regval	&
+						      (ICH_VMCR_ENG0_MASK	|
+						       ICH_VMCR_ENG1_MASK	|
+						       ICH_VMCR_PMR_MASK	|
+						       ICH_VMCR_BPR0_MASK	|
+						       ICH_VMCR_BPR1_MASK	|
+						       ICH_VMCR_EOIM_MASK	|
+						       ICH_VMCR_CBPR_MASK	|
+						       ICH_VMCR_FIQ_EN_MASK	|
+						       ICH_VMCR_ACK_CTL_MASK));
 	else
-		p->regval = cpu_if->vgic_vmcr;
+		p->regval = __vcpu_sys_reg(vcpu, ICH_VMCR_EL2);
 
 	return true;
 }
@@ -1887,17 +1892,29 @@ static bool access_gic_lr(struct kvm_vcpu *vcpu,
 			  struct sys_reg_params *p,
 			  const struct sys_reg_desc *r)
 {
-	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.nested_vgic_v3;
 	u32 index;
+	u64 *base;
 
+	base = __ctxt_sys_reg(&vcpu->arch.ctxt, ICH_LR0_EL2);
 	index = p->Op2;
 	if (p->CRm == 13)
 		index += 8;
 
-	if (p->is_write)
-		cpu_if->vgic_lr[index] = p->regval;
-	else
-		p->regval = cpu_if->vgic_lr[index];
+	if (p->is_write) {
+		u64 mask = (ICH_LR_VIRTUAL_ID_MASK	|
+			    ICH_LR_GROUP		|
+			    ICH_LR_HW			|
+			    ICH_LR_STATE);
+
+		if (p->regval & ICH_LR_HW)
+			mask |= ICH_LR_PHYS_ID_MASK;
+		else
+			mask |= ICH_LR_EOI;
+
+		base[index] = p->regval & mask;
+	} else {
+		p->regval = base[index];
+	}
 
 	return true;
 }
diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index 94b1edb67011..51f7a521e829 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -16,11 +16,6 @@
 #define CREATE_TRACE_POINTS
 #include "vgic-nested-trace.h"
 
-static inline struct vgic_v3_cpu_if *vcpu_nested_if(struct kvm_vcpu *vcpu)
-{
-	return &vcpu->arch.vgic_cpu.nested_vgic_v3;
-}
-
 static inline struct vgic_v3_cpu_if *vcpu_shadow_if(struct kvm_vcpu *vcpu)
 {
 	return &vcpu->arch.vgic_cpu.shadow_vgic_v3;
@@ -33,12 +28,11 @@ static inline bool lr_triggers_eoi(u64 lr)
 
 u16 vgic_v3_get_eisr(struct kvm_vcpu *vcpu)
 {
-	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
 	u16 reg = 0;
 	int i;
 
 	for (i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
-		if (lr_triggers_eoi(cpu_if->vgic_lr[i]))
+		if (lr_triggers_eoi(__vcpu_sys_reg(vcpu, ICH_LRN(i))))
 			reg |= BIT(i);
 	}
 
@@ -47,12 +41,11 @@ u16 vgic_v3_get_eisr(struct kvm_vcpu *vcpu)
 
 u16 vgic_v3_get_elrsr(struct kvm_vcpu *vcpu)
 {
-	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
 	u16 reg = 0;
 	int i;
 
 	for (i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
-		if (!(cpu_if->vgic_lr[i] & ICH_LR_STATE))
+		if (!(__vcpu_sys_reg(vcpu, ICH_LRN(i)) & ICH_LR_STATE))
 			reg |= BIT(i);
 	}
 
@@ -61,14 +54,13 @@ u16 vgic_v3_get_elrsr(struct kvm_vcpu *vcpu)
 
 u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu)
 {
-	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
 	int nr_lr = kvm_vgic_global_state.nr_lr;
 	u64 reg = 0;
 
 	if (vgic_v3_get_eisr(vcpu))
 		reg |= ICH_MISR_EOI;
 
-	if (cpu_if->vgic_hcr & ICH_HCR_UIE) {
+	if (__vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_UIE) {
 		int used_lrs;
 
 		used_lrs = nr_lr - hweight16(vgic_v3_get_elrsr(vcpu));
@@ -87,13 +79,12 @@ u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu)
  */
 static void vgic_v3_create_shadow_lr(struct kvm_vcpu *vcpu)
 {
-	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
 	struct vgic_v3_cpu_if *s_cpu_if = vcpu_shadow_if(vcpu);
 	struct vgic_irq *irq;
 	int i, used_lrs = 0;
 
 	for (i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
-		u64 lr = cpu_if->vgic_lr[i];
+		u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
 		int l1_irq;
 
 		if (!(lr & ICH_LR_HW))
@@ -123,36 +114,20 @@ static void vgic_v3_create_shadow_lr(struct kvm_vcpu *vcpu)
 	}
 
 	trace_vgic_create_shadow_lrs(vcpu, kvm_vgic_global_state.nr_lr,
-				     s_cpu_if->vgic_lr, cpu_if->vgic_lr);
+				     s_cpu_if->vgic_lr,
+				     __ctxt_sys_reg(&vcpu->arch.ctxt, ICH_LR0_EL2));
 
 	s_cpu_if->used_lrs = used_lrs;
 }
 
-/*
- * Change the shadow HWIRQ field back to the virtual value before copying over
- * the entire shadow struct to the nested state.
- */
-static void vgic_v3_fixup_shadow_lr_state(struct kvm_vcpu *vcpu)
-{
-	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
-	struct vgic_v3_cpu_if *s_cpu_if = vcpu_shadow_if(vcpu);
-	int lr;
-
-	for (lr = 0; lr < kvm_vgic_global_state.nr_lr; lr++) {
-		s_cpu_if->vgic_lr[lr] &= ~ICH_LR_PHYS_ID_MASK;
-		s_cpu_if->vgic_lr[lr] |= cpu_if->vgic_lr[lr] & ICH_LR_PHYS_ID_MASK;
-	}
-}
-
 void vgic_v3_sync_nested(struct kvm_vcpu *vcpu)
 {
-	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
 	struct vgic_v3_cpu_if *s_cpu_if = vcpu_shadow_if(vcpu);
 	struct vgic_irq *irq;
 	int i;
 
 	for (i = 0; i < s_cpu_if->used_lrs; i++) {
-		u64 lr = cpu_if->vgic_lr[i];
+		u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
 		int l1_irq;
 
 		if (!(lr & ICH_LR_HW) || !(lr & ICH_LR_STATE))
@@ -178,14 +153,27 @@ void vgic_v3_sync_nested(struct kvm_vcpu *vcpu)
 	}
 }
 
+void vgic_v3_create_shadow_state(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.shadow_vgic_v3;
+	int i;
+
+	cpu_if->vgic_hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
+	cpu_if->vgic_vmcr = __vcpu_sys_reg(vcpu, ICH_VMCR_EL2);
+
+	for (i = 0; i < 4; i++) {
+		cpu_if->vgic_ap0r[i] = __vcpu_sys_reg(vcpu, ICH_AP0RN(i));
+		cpu_if->vgic_ap1r[i] = __vcpu_sys_reg(vcpu, ICH_AP1RN(i));
+	}
+
+	vgic_v3_create_shadow_lr(vcpu);
+}
+
 void vgic_v3_load_nested(struct kvm_vcpu *vcpu)
 {
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_irq *irq;
 	unsigned long flags;
 
-	vgic_cpu->shadow_vgic_v3 = vgic_cpu->nested_vgic_v3;
-	vgic_v3_create_shadow_lr(vcpu);
 	__vgic_v3_restore_state(vcpu_shadow_if(vcpu));
 
 	irq = vgic_get_irq(vcpu->kvm, vcpu, vcpu->kvm->arch.vgic.maint_irq);
@@ -199,26 +187,40 @@ void vgic_v3_load_nested(struct kvm_vcpu *vcpu)
 
 void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
 {
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_v3_cpu_if *s_cpu_if = vcpu_shadow_if(vcpu);
+	int i;
 
-	__vgic_v3_save_state(vcpu_shadow_if(vcpu));
+	__vgic_v3_save_state(s_cpu_if);
 
-	trace_vgic_put_nested(vcpu, kvm_vgic_global_state.nr_lr,
-			      vcpu_shadow_if(vcpu)->vgic_lr);
+	trace_vgic_put_nested(vcpu, kvm_vgic_global_state.nr_lr, s_cpu_if->vgic_lr);
 
 	/*
 	 * Translate the shadow state HW fields back to the virtual ones
 	 * before copying the shadow struct back to the nested one.
 	 */
-	vgic_v3_fixup_shadow_lr_state(vcpu);
-	vgic_cpu->nested_vgic_v3 = vgic_cpu->shadow_vgic_v3;
+	__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 (i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
+		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;
+	}
+
 	irq_set_irqchip_state(kvm_vgic_global_state.maint_irq,
 			      IRQCHIP_STATE_ACTIVE, false);
 }
 
 void vgic_v3_handle_nested_maint_irq(struct kvm_vcpu *vcpu)
 {
-	struct vgic_v3_cpu_if *cpu_if = vcpu_nested_if(vcpu);
 	bool state;
 
 	/*
@@ -230,7 +232,7 @@ void vgic_v3_handle_nested_maint_irq(struct kvm_vcpu *vcpu)
 	if (!vgic_state_is_nested(vcpu))
 		return;
 
-	state  = cpu_if->vgic_hcr & ICH_HCR_EN;
+	state  = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EN;
 	state &= vgic_v3_get_misr(vcpu);
 
 	kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 47ea2a0f3ae4..d3b36eea8665 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -292,10 +292,11 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
 				     ICC_SRE_EL1_SRE);
 		/*
 		 * If nesting is allowed, force GICv3 onto the nested
-		 * guests as well.
+		 * guests as well by setting the shadow state to the
+		 * same value.
 		 */
 		if (nested_virt_in_use(vcpu))
-			vcpu->arch.vgic_cpu.nested_vgic_v3.vgic_sre = vgic_v3->vgic_sre;
+			vcpu->arch.vgic_cpu.shadow_vgic_v3.vgic_sre = vgic_v3->vgic_sre;
 		vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE;
 	} else {
 		vgic_v3->vgic_sre = 0;
@@ -662,11 +663,15 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
 	/*
-	 * vgic_v3_load_nested only affects the LRs in the shadow
-	 * state, so it is fine to pass the nested state around.
+	 * If the vgic is in nested state, populate the shadow state
+	 * from the guest's nested state. As vgic_v3_load_nested()
+	 * will only load LRs, let's deal with the rest of the state
+	 * here as if it was a non-nested state. Cunning.
 	 */
-	if (vgic_state_is_nested(vcpu))
-		cpu_if = &vcpu->arch.vgic_cpu.nested_vgic_v3;
+	if (vgic_state_is_nested(vcpu)) {
+		vgic_v3_create_shadow_state(vcpu);
+		cpu_if = &vcpu->arch.vgic_cpu.shadow_vgic_v3;
+	}
 
 	/*
 	 * If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 64fcd7511110..8f513a122699 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -318,4 +318,14 @@ int vgic_v4_init(struct kvm *kvm);
 void vgic_v4_teardown(struct kvm *kvm);
 void vgic_v4_configure_vsgis(struct kvm *kvm);
 
+void vgic_v3_sync_nested(struct kvm_vcpu *vcpu);
+void vgic_v3_create_shadow_state(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);
+
+#define ICH_LRN(n)	(ICH_LR0_EL2 + (n))
+#define ICH_AP0RN(n)	(ICH_AP0R0_EL2 + (n))
+#define ICH_AP1RN(n)	(ICH_AP1R0_EL2 + (n))
+
 #endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index e02bc45e9508..7c46a8fba2aa 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -309,9 +309,6 @@ struct vgic_cpu {
 
 	struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS];
 
-	/* CPU vif control registers for the virtual GICH interface */
-	struct vgic_v3_cpu_if	nested_vgic_v3;
-
 	/*
 	 * The shadow vif control register loaded to the hardware when
 	 * running a nested L2 guest with the virtual IMO/FMO bit set.
@@ -374,10 +371,6 @@ void kvm_vgic_load(struct kvm_vcpu *vcpu);
 void kvm_vgic_put(struct kvm_vcpu *vcpu);
 void kvm_vgic_vmcr_sync(struct kvm_vcpu *vcpu);
 
-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);
 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);
-- 
2.29.2

[PATCH v3 60/66] KVM: arm64: Add ARMv8.4 Enhanced Nested Virt cpufeature

[Marc Zyngier]

Add the detection code for the ARMv8.4-NV feature.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/cpucaps.h    |  1 +
 arch/arm64/include/asm/kvm_nested.h |  6 ++++++
 arch/arm64/kernel/cpufeature.c      | 10 ++++++++++
 3 files changed, 17 insertions(+)

diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 6c5b84692a01..31619c73e320 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -17,6 +17,7 @@
 #define ARM64_WORKAROUND_834220			7
 #define ARM64_HAS_NO_HW_PREFETCH		8
 #define ARM64_HAS_NESTED_VIRT			9
+#define ARM64_HAS_ENHANCED_NESTED_VIRT		10
 #define ARM64_HAS_VIRT_HOST_EXTN		11
 #define ARM64_WORKAROUND_CAVIUM_27456		12
 #define ARM64_HAS_32BIT_EL0			13
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 36f2cd2c6fdf..c3c57eaa493a 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -14,6 +14,12 @@ static inline bool nested_virt_in_use(const struct kvm_vcpu *vcpu)
 		test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features));
 }
 
+static inline bool enhanced_nested_virt_in_use(const struct kvm_vcpu *vcpu)
+{
+	return cpus_have_final_cap(ARM64_HAS_ENHANCED_NESTED_VIRT) &&
+		nested_virt_in_use(vcpu);
+}
+
 /* Translation helpers from non-VHE EL2 to EL1 */
 static inline u64 tcr_el2_ips_to_tcr_el1_ps(u64 tcr_el2)
 {
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index eaeea8a88292..855c37d2f941 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1815,6 +1815,16 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.field_pos = ID_AA64MMFR2_NV_SHIFT,
 		.min_field_value = 1,
 	},
+	{
+		.desc = "Enhanced Nested Virtualization Support",
+		.capability = ARM64_HAS_ENHANCED_NESTED_VIRT,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_nested_virt_support,
+		.sys_reg = SYS_ID_AA64MMFR2_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64MMFR2_NV_SHIFT,
+		.min_field_value = 2,
+	},
 #endif	/* CONFIG_ARM64_VHE */
 	{
 		.desc = "32-bit EL0 Support",
-- 
2.29.2

[PATCH v3 61/66] KVM: arm64: nv: Synchronize PSTATE early on exit

[Marc Zyngier]

The NV code relies on predicates such as is_hyp_ctxt() being
reliable. In turn, is_hyp_ctxt() relies on things like PSTATE
and the virtual HCR_EL2 being accurate.

But with ARMv8.4-NV removing trapping for a large part of the
EL2 system registers (among which HCR_EL2), we can't use such
trapping to synchronize the rest of the state.

Let's look at the following sequence for a VHE guest:

 (1) enter guest in host EL0
 (2) guest traps to guest vEL2 (no hypervisor intervention)
 (3) guest clears virtual HCR_EL2.TGE (no trap either)
 (4) host interrupt fires, exit
 (5) is_hyp_ctxt() now says "guest" (PSTATE.M==EL1 and TGE==0)

It is obvious that such behaviour would be rather unfortunate,
and lead to interesting, difficult to catch bugs specially if
preemption kicks in (yes, I wasted a whole week chasing this one).

In order to preserve the invariant that a guest entered in host
context must exit in the same context, we must make sure that
is_hyp_ctxt() works correctly. Since we can always observe the
guest value of HCR_EL2.{E2H,TGE} in the VNCR_EL2 page, we solely
need to synchronize PSTATE as early as possible.

This basically amounts to moving from_hw_pstate() as close
as possible to the guest exit point, and fixup_guest_exit()
seems as good a place as any.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/switch.h    | 16 ++++--
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 26 ++--------
 arch/arm64/kvm/hyp/nvhe/switch.c           |  8 ++-
 arch/arm64/kvm/hyp/vhe/switch.c            | 57 +++++++++++++++++++++-
 4 files changed, 78 insertions(+), 29 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index e5e201314c87..3b56841eb328 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -407,11 +407,11 @@ static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
 }
 
 /*
- * Return true when we were able to fixup the guest exit and should return to
- * the guest, false when we should restore the host state and return to the
- * main run loop.
+ * Prologue for the guest fixup, populating ESR_EL2 and fixing up PC
+ * if required.
  */
-static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+static inline void fixup_guest_exit_prologue(struct kvm_vcpu *vcpu,
+					     u64 *exit_code)
 {
 	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
 		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
@@ -430,7 +430,15 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 		if (esr_ec == ESR_ELx_EC_HVC32 || esr_ec == ESR_ELx_EC_HVC64)
 			write_sysreg_el2(read_sysreg_el2(SYS_ELR) - 4, SYS_ELR);
 	}
+}
 
+/*
+ * Return true when we were able to fixup the guest exit and should return to
+ * the guest, false when we should restore the host state and return to the
+ * main run loop.
+ */
+static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
 	/*
 	 * We're using the raw exception code in order to only process
 	 * the trap if no SError is pending. We will come back to the
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 92715fa01e88..1931c8667d52 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -51,32 +51,12 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, SPSR_EL1)	= read_sysreg_el1(SYS_SPSR);
 }
 
-static inline u64 from_hw_pstate(const struct kvm_cpu_context *ctxt)
-{
-	u64 reg = read_sysreg_el2(SYS_SPSR);
-
-	if (__is_hyp_ctxt(ctxt)) {
-		u64 mode = reg & (PSR_MODE_MASK | PSR_MODE32_BIT);
-
-		switch (mode) {
-		case PSR_MODE_EL1t:
-			mode = PSR_MODE_EL2t;
-			break;
-		case PSR_MODE_EL1h:
-			mode = PSR_MODE_EL2h;
-			break;
-		}
-
-		return (reg & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode;
-	}
-
-	return reg;
-}
-
 static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 {
+	/* On VHE, PSTATE is saved in fixup_guest_exit_vhe() */
+	if (!has_vhe())
+		ctxt->regs.pstate 	= read_sysreg_el2(SYS_SPSR);
 	ctxt->regs.pc			= read_sysreg_el2(SYS_ELR);
-	ctxt->regs.pstate		= from_hw_pstate(ctxt);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
 		ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2);
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 07bf5c03631b..fb49757d3446 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -166,6 +166,12 @@ static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
 		write_sysreg(pmu->events_host, pmcntenset_el0);
 }
 
+static bool fixup_guest_exit_nvhe(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	fixup_guest_exit_prologue(vcpu, exit_code);
+	return fixup_guest_exit(vcpu, exit_code);
+}
+
 /* Switch to the guest for legacy non-VHE systems */
 int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 {
@@ -219,7 +225,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 		exit_code = __guest_enter(vcpu);
 
 		/* And we're baaack! */
-	} while (fixup_guest_exit(vcpu, &exit_code));
+	} while (fixup_guest_exit_nvhe(vcpu, &exit_code));
 
 	__sysreg_save_state_nvhe(guest_ctxt);
 	__sysreg32_save_state(vcpu);
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index d9dc470c7790..4d80596e32a5 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -156,12 +156,60 @@ void deactivate_traps_vhe_put(void)
 	__deactivate_traps_common();
 }
 
+static bool fixup_guest_exit_vhe(struct kvm_vcpu *vcpu, u64 *exit_code,
+				 bool hyp_ctxt)
+{
+	u64 pstate = read_sysreg_el2(SYS_SPSR);
+
+	/*
+	 * Sync pstate back as early as possible, so that is_hyp_ctxt()
+	 * reflects the exact context. It is otherwise possible to get
+	 * confused with a VHE guest and ARMv8.4-NV, such as:
+	 *
+	 * (1) enter guest in host EL0
+	 * (2) guest traps to guest vEL2 (no hypervisor intervention)
+	 * (3) guest clears virtual HCR_EL2.TGE (no trap either)
+	 * (4) host interrupt fires, exit
+	 * (5) is_hyp_ctxt() now says "guest" (pstate.M==EL1 and TGE==0)
+	 *
+	 * If host preemption occurs, vcpu_load/put() will be very confused.
+	 *
+	 * Consider this as the prologue before the fixup prologue...
+	 */
+
+	if (unlikely(hyp_ctxt)) {
+		u64 mode = pstate & PSR_MODE_MASK;
+
+		switch (mode) {
+		case PSR_MODE_EL1t:
+			mode = PSR_MODE_EL2t;
+			break;
+		case PSR_MODE_EL1h:
+			mode = PSR_MODE_EL2h;
+			break;
+		}
+
+		pstate = (pstate & ~PSR_MODE_MASK) | mode;
+	}
+
+	*vcpu_cpsr(vcpu) = pstate;
+
+	fixup_guest_exit_prologue(vcpu, exit_code);
+
+	if (*exit_code == ARM_EXCEPTION_TRAP) {
+		/* more to come here */
+	}
+
+	return fixup_guest_exit(vcpu, exit_code);
+}
+
 /* Switch to the guest for VHE systems running in EL2 */
 static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
 	u64 exit_code;
+	bool hyp_ctxt;
 
 	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
 	host_ctxt->__hyp_running_vcpu = vcpu;
@@ -188,12 +236,19 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	sysreg_restore_guest_state_vhe(guest_ctxt);
 	__debug_switch_to_guest(vcpu);
 
+	/*
+	 * Being in HYP context or not is an invariant here. If we enter in
+	 * a given context, we exit in the same context. We can thus only
+	 * sample the context once.
+	 */
+	WRITE_ONCE(hyp_ctxt, is_hyp_ctxt(vcpu));
+
 	do {
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu);
 
 		/* And we're baaack! */
-	} while (fixup_guest_exit(vcpu, &exit_code));
+	} while (fixup_guest_exit_vhe(vcpu, &exit_code, READ_ONCE(hyp_ctxt)));
 
 	sysreg_save_guest_state_vhe(guest_ctxt);
 
-- 
2.29.2

[PATCH v3 62/66] KVM: arm64: nv: Sync nested timer state with ARMv8.4

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@arm.com>

Emulating the ARMv8.4-NV timers is a bit odd, as the timers can
be reconfigured behind our back without the hypervisor even
noticing. In the VHE case, that's an actual regression in the
architecture...

Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/arch_timer.c  | 37 ++++++++++++++++++++++++++++++++++++
 arch/arm64/kvm/arm.c         |  3 +++
 include/kvm/arm_arch_timer.h |  1 +
 3 files changed, 41 insertions(+)

diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 1c2be6391951..5af09d9adfe0 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -778,6 +778,43 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 	set_cntvoff(0);
 }
 
+void kvm_timer_sync_nested(struct kvm_vcpu *vcpu)
+{
+	if (!is_hyp_ctxt(vcpu))
+		return;
+
+	/*
+	 * Guest hypervisors using ARMv8.4 enhanced nested virt support have
+	 * their EL1 timer register accesses redirected to the VNCR page.
+	 */
+	if (!vcpu_el2_e2h_is_set(vcpu)) {
+		/*
+		 * For a non-VHE guest hypervisor, we update the hardware
+		 * timer registers with the latest value written by the guest
+		 * to the VNCR page and let the hardware take care of the
+		 * rest.
+		 */
+		write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CTL_EL0),  SYS_CNTV_CTL);
+		write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CVAL_EL0), SYS_CNTV_CVAL);
+		write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CTL_EL0),  SYS_CNTP_CTL);
+		write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0), SYS_CNTP_CVAL);
+	} else {
+		/*
+		 * For a VHE guest hypervisor, the emulated state (which
+		 * is stored in the VNCR page) could have been updated behind
+		 * our back, and we must reset the emulation of the timers.
+		 */
+
+		struct timer_map map;
+		get_timer_map(vcpu, &map);
+
+		soft_timer_cancel(&map.emul_vtimer->hrtimer);
+		soft_timer_cancel(&map.emul_ptimer->hrtimer);
+		timer_emulate(map.emul_vtimer);
+		timer_emulate(map.emul_ptimer);
+	}
+}
+
 /*
  * With a userspace irqchip we have to check if the guest de-asserted the
  * timer and if so, unmask the timer irq signal on the host interrupt
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 818ec91801e2..e8f009ed096b 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -849,6 +849,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		if (static_branch_unlikely(&userspace_irqchip_in_use))
 			kvm_timer_sync_user(vcpu);
 
+		if (enhanced_nested_virt_in_use(vcpu))
+			kvm_timer_sync_nested(vcpu);
+
 		kvm_arch_vcpu_ctxsync_fp(vcpu);
 
 		/*
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index 063f613fbc7e..2e20916e9025 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -68,6 +68,7 @@ int kvm_timer_hyp_init(bool);
 int kvm_timer_enable(struct kvm_vcpu *vcpu);
 int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
+void kvm_timer_sync_nested(struct kvm_vcpu *vcpu);
 void kvm_timer_sync_user(struct kvm_vcpu *vcpu);
 bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu);
 void kvm_timer_update_run(struct kvm_vcpu *vcpu);
-- 
2.29.2

[PATCH v3 63/66] KVM: arm64: nv: Allocate VNCR page when required

[Marc Zyngier]

If running a NV guest on an ARMv8.4-NV capable system, let's
allocate an additional page that will be used by the hypervisor
to fulfill system register accesses.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 3 ++-
 arch/arm64/kvm/nested.c           | 8 ++++++++
 arch/arm64/kvm/reset.c            | 1 +
 3 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 78630bd5124d..dada0678c28e 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -523,7 +523,8 @@ struct kvm_vcpu_arch {
  */
 static inline u64 *__ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
 {
-	if (unlikely(r >= __VNCR_START__ && ctxt->vncr_array))
+	if (unlikely(cpus_have_final_cap(ARM64_HAS_ENHANCED_NESTED_VIRT) &&
+		     r >= __VNCR_START__ && ctxt->vncr_array))
 		return &ctxt->vncr_array[r - __VNCR_START__];
 
 	return (u64 *)&ctxt->sys_regs[r];
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index eef8f9873814..88147ec99755 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -47,6 +47,12 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
 	if (!cpus_have_final_cap(ARM64_HAS_NESTED_VIRT))
 		return -EINVAL;
 
+	if (cpus_have_final_cap(ARM64_HAS_ENHANCED_NESTED_VIRT)) {
+		vcpu->arch.ctxt.vncr_array = (u64 *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+		if (!vcpu->arch.ctxt.vncr_array)
+			return -ENOMEM;
+	}
+
 	mutex_lock(&kvm->lock);
 
 	/*
@@ -64,6 +70,8 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
 		    kvm_init_stage2_mmu(kvm, &tmp[num_mmus - 2])) {
 			kvm_free_stage2_pgd(&tmp[num_mmus - 1]);
 			kvm_free_stage2_pgd(&tmp[num_mmus - 2]);
+			free_page((unsigned long)vcpu->arch.ctxt.vncr_array);
+			vcpu->arch.ctxt.vncr_array = NULL;
 		} else {
 			kvm->arch.nested_mmus_size = num_mmus;
 			ret = 0;
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 2d2c780e6c69..d281eb39036f 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -150,6 +150,7 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu)
 void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	kfree(vcpu->arch.sve_state);
+	free_page((unsigned long)vcpu->arch.ctxt.vncr_array);
 }
 
 static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
-- 
2.29.2

[PATCH v3 64/66] KVM: arm64: nv: Enable ARMv8.4-NV support

[Marc Zyngier]

As all the VNCR-capable system registers are nicely separated
from the rest of the crowd, let's set HCR_EL2.NV2 on and let
the ball rolling.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_arm.h     |  1 +
 arch/arm64/include/asm/kvm_emulate.h | 23 +++++++++++++----------
 arch/arm64/include/asm/sysreg.h      |  1 +
 arch/arm64/kvm/hyp/vhe/switch.c      | 14 +++++++++++++-
 4 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 0d88a7c51dec..37cd86aac727 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -14,6 +14,7 @@
 /* Hyp Configuration Register (HCR) bits */
 #define HCR_ATA		(UL(1) << 56)
 #define HCR_FWB		(UL(1) << 46)
+#define HCR_NV2		(UL(1) << 45)
 #define HCR_AT		(UL(1) << 44)
 #define HCR_NV1		(UL(1) << 43)
 #define HCR_NV		(UL(1) << 42)
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 44b395854430..3afe937b81f1 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -242,21 +242,24 @@ static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu)
 
 static inline u64 __fixup_spsr_el2_write(struct kvm_cpu_context *ctxt, u64 val)
 {
-	if (!__vcpu_el2_e2h_is_set(ctxt)) {
-		/*
-		 * Clear the .M field when writing SPSR to the CPU, so that we
-		 * can detect when the CPU clobbered our SPSR copy during a
-		 * local exception.
-		 */
-		val &= ~0xc;
-	}
+	struct kvm_vcpu *vcpu = container_of(ctxt, struct kvm_vcpu, arch.ctxt);
+
+	if (enhanced_nested_virt_in_use(vcpu) || __vcpu_el2_e2h_is_set(ctxt))
+		return val;
 
-	return val;
+	/*
+	 * Clear the .M field when writing SPSR to the CPU, so that we
+	 * can detect when the CPU clobbered our SPSR copy during a
+	 * local exception.
+	 */
+	return val &= ~0xc;
 }
 
 static inline u64 __fixup_spsr_el2_read(const struct kvm_cpu_context *ctxt, u64 val)
 {
-	if (__vcpu_el2_e2h_is_set(ctxt))
+	struct kvm_vcpu *vcpu = container_of(ctxt, struct kvm_vcpu, arch.ctxt);
+
+	if (enhanced_nested_virt_in_use(vcpu) || __vcpu_el2_e2h_is_set(ctxt))
 		return val;
 
 	/*
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index d047954400d4..4cb55cf3c1d9 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -487,6 +487,7 @@
 #define SYS_TCR_EL2			sys_reg(3, 4, 2, 0, 2)
 #define SYS_VTTBR_EL2			sys_reg(3, 4, 2, 1, 0)
 #define SYS_VTCR_EL2			sys_reg(3, 4, 2, 1, 2)
+#define SYS_VNCR_EL2			sys_reg(3, 4, 2, 2, 0)
 
 #define SYS_DACR32_EL2			sys_reg(3, 4, 3, 0, 0)
 
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 4d80596e32a5..6d57d09b8503 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -48,7 +48,13 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 			 * the EL1 virtual memory control register accesses
 			 * as well as the AT S1 operations.
 			 */
-			hcr |= HCR_TVM | HCR_TRVM | HCR_AT | HCR_TTLB | HCR_NV1;
+			if (enhanced_nested_virt_in_use(vcpu)) {
+				hcr &= ~HCR_TVM;
+			} else {
+				hcr |= HCR_TVM | HCR_TRVM | HCR_TTLB;
+			}
+
+			hcr |= HCR_AT | HCR_NV1;
 		} else {
 			/*
 			 * For a guest hypervisor on v8.1 (VHE), allow to
@@ -80,6 +86,12 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 			if (!vcpu_el2_tge_is_set(vcpu))
 				hcr |= HCR_AT | HCR_TTLB;
 		}
+
+		if (enhanced_nested_virt_in_use(vcpu)) {
+			hcr |= HCR_AT | HCR_TTLB | HCR_NV2;
+			write_sysreg_s(vcpu->arch.ctxt.vncr_array,
+				       SYS_VNCR_EL2);
+		}
 	} else if (nested_virt_in_use(vcpu)) {
 		hcr |= __vcpu_sys_reg(vcpu, HCR_EL2);
 	}
-- 
2.29.2

[PATCH v3 65/66] KVM: arm64: nv: Fast-track 'InHost' exception returns

[Marc Zyngier]

A significant part of the ARMv8.3-NV extension is to trap ERET
instructions so that the hypervisor gets a chance to switch
from a vEL2 L1 guest to an EL1 L2 guest.

But this also has the unfortunate consequence of trapping ERET
in unsuspecting circumstances, such as staying at vEL2 (interrupt
handling while being in the guest hypervisor), or returning to host
userspace in the case of a VHE guest.

Although we already make some effort to handle these ERET quicker
by not doing the put/load dance, it is still way too far down the
line for it to be efficient enough.

For these cases, it would ideal to ERET directly, no question asked.
Of course, we can't do that. But the next best thing is to do it as
early as possible, in fixup_guest_exit(), much as we would handle
FPSIMD exceptions.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/emulate-nested.c | 26 ++--------------
 arch/arm64/kvm/hyp/vhe/switch.c | 53 ++++++++++++++++++++++++++++++++-
 2 files changed, 54 insertions(+), 25 deletions(-)

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index df4661515183..43197ff4a806 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -52,8 +52,7 @@ bool forward_nv_traps(struct kvm_vcpu *vcpu)
 
 void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 {
-	u64 spsr, elr, mode;
-	bool direct_eret;
+	u64 spsr, elr;
 
 	/*
 	 * Forward this trap to the virtual EL2 if the virtual
@@ -62,31 +61,10 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	if (forward_nv_traps(vcpu))
 		return;
 
-	/*
-	 * Going through the whole put/load motions is a waste of time
-	 * if this is a VHE guest hypervisor returning to its own
-	 * userspace, or the hypervisor performing a local exception
-	 * return. No need to save/restore registers, no need to
-	 * switch S2 MMU. Just do the canonical ERET.
-	 */
-	spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2);
-	mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT);
-
-	direct_eret  = (mode == PSR_MODE_EL0t &&
-			vcpu_el2_e2h_is_set(vcpu) &&
-			vcpu_el2_tge_is_set(vcpu));
-	direct_eret |= (mode == PSR_MODE_EL2h || mode == PSR_MODE_EL2t);
-
-	if (direct_eret) {
-		*vcpu_pc(vcpu) = vcpu_read_sys_reg(vcpu, ELR_EL2);
-		*vcpu_cpsr(vcpu) = spsr;
-		trace_kvm_nested_eret(vcpu, *vcpu_pc(vcpu), spsr);
-		return;
-	}
-
 	preempt_disable();
 	kvm_arch_vcpu_put(vcpu);
 
+	spsr = __vcpu_sys_reg(vcpu, SPSR_EL2);
 	elr = __vcpu_sys_reg(vcpu, ELR_EL2);
 
 	trace_kvm_nested_eret(vcpu, elr, spsr);
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 6d57d09b8503..c90aed418f73 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -168,6 +168,56 @@ void deactivate_traps_vhe_put(void)
 	__deactivate_traps_common();
 }
 
+static bool __hyp_handle_eret(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
+	u64 spsr, mode;
+
+	/*
+	 * Going through the whole put/load motions is a waste of time
+	 * if this is a VHE guest hypervisor returning to its own
+	 * userspace, or the hypervisor performing a local exception
+	 * return. No need to save/restore registers, no need to
+	 * switch S2 MMU. Just do the canonical ERET. Unless the trap
+	 * has to be forwarded further down the line, of course...
+	 */
+	if (kvm_vcpu_trap_get_class(vcpu) != ESR_ELx_EC_ERET)
+		return false;
+
+	/*
+	 * Let the trap forwarding be handled by the normal exception
+	 * handling code.
+	 */
+	if (__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV)
+		return false;
+
+	spsr = read_sysreg_el1(SYS_SPSR);
+	spsr = __fixup_spsr_el2_read(ctxt, spsr);
+	mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+	switch (mode) {
+	case PSR_MODE_EL0t:
+		if (!(vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)))
+			return false;
+		break;
+	case PSR_MODE_EL2t:
+		mode = PSR_MODE_EL1t;
+		break;
+	case PSR_MODE_EL2h:
+		mode = PSR_MODE_EL1h;
+		break;
+	default:
+		return false;
+	}
+
+	spsr = (spsr & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode;
+
+	write_sysreg_el2(spsr, SYS_SPSR);
+	write_sysreg_el2(read_sysreg_el1(SYS_ELR), SYS_ELR);
+
+	return true;
+}
+
 static bool fixup_guest_exit_vhe(struct kvm_vcpu *vcpu, u64 *exit_code,
 				 bool hyp_ctxt)
 {
@@ -209,7 +259,8 @@ static bool fixup_guest_exit_vhe(struct kvm_vcpu *vcpu, u64 *exit_code,
 	fixup_guest_exit_prologue(vcpu, exit_code);
 
 	if (*exit_code == ARM_EXCEPTION_TRAP) {
-		/* more to come here */
+		if (__hyp_handle_eret(vcpu))
+			return true;
 	}
 
 	return fixup_guest_exit(vcpu, exit_code);
-- 
2.29.2

[PATCH v3 66/66] KVM: arm64: nv: Fast-track EL1 TLBIs for VHE guests

[Marc Zyngier]

Due to the way ARMv8.4-NV suppresses traps when accessing EL2
system registers, we can't track when the guest changes its
HCR_EL2.TGE setting. This means we always trap EL1 TLBIs,
even if they don't affect any guest.

This obviously has a huge impact on performance, as we handle
TLBI traps as a normal exit, and a normal VHE host issues
thousands of TLBIs when booting (and quite a few when running
userspace).

A cheap way to reduce the overhead is to handle the limited
case of {E2H,TGE}=={1,1} as a guest fixup, as we already have
the right mmu configuration in place. Just execute the decoded
instruction right away and return to the guest.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/vhe/switch.c | 36 +++++++++++++++++++++++++++++++++
 arch/arm64/kvm/hyp/vhe/tlb.c    |  6 ++++--
 arch/arm64/kvm/sys_regs.c       | 25 ++++++++---------------
 3 files changed, 48 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index c90aed418f73..0b9bc36340a5 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -168,6 +168,39 @@ void deactivate_traps_vhe_put(void)
 	__deactivate_traps_common();
 }
 
+static bool __hyp_handle_tlbi_el1(struct kvm_vcpu *vcpu)
+{
+	u32 instr;
+	u64 val;
+
+	/*
+	 * Ideally, we would never trap on EL1 TLB invalidations when the
+	 * guest's HCR_EL2.{E2H,TGE} == {1,1}. But "thanks" to ARMv8.4, we
+	 * don't trap writes to HCR_EL2, meaning that we can't track
+	 * changes to the virtual TGE bit. So we leave HCR_EL2.TTLB set on
+	 * the host. Oopsie...
+	 *
+	 * In order to speed-up EL1 TLBIs from the vEL2 guest when TGE is
+	 * set, try and handle these invalidation as quickly as possible,
+	 * without fully exiting (unless this needs forwarding).
+	 */
+	if (kvm_vcpu_trap_get_class(vcpu) != ESR_ELx_EC_SYS64 ||
+	    !vcpu_mode_el2(vcpu) ||
+	    (__vcpu_sys_reg(vcpu, HCR_EL2) & (HCR_E2H | HCR_TGE)) != (HCR_E2H | HCR_TGE))
+		return false;
+
+	instr = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
+	if (sys_reg_Op0(instr) != TLBI_Op0 ||
+	    sys_reg_Op1(instr) != TLBI_Op1_EL1)
+		return false;
+
+	val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu));
+	__kvm_tlb_el1_instr(NULL, val, instr);
+	__kvm_skip_instr(vcpu);
+
+	return true;
+}
+
 static bool __hyp_handle_eret(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
@@ -261,6 +294,9 @@ static bool fixup_guest_exit_vhe(struct kvm_vcpu *vcpu, u64 *exit_code,
 	if (*exit_code == ARM_EXCEPTION_TRAP) {
 		if (__hyp_handle_eret(vcpu))
 			return true;
+
+		if (__hyp_handle_tlbi_el1(vcpu))
+			return true;
 	}
 
 	return fixup_guest_exit(vcpu, exit_code);
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index 52fda1d61308..6dd7f224e0f3 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -200,7 +200,8 @@ void __kvm_tlb_el1_instr(struct kvm_s2_mmu *mmu, u64 val, u64 sys_encoding)
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt);
+	if (mmu)
+		__tlb_switch_to_guest(mmu, &cxt);
 
 	/*
 	 * Execute the same instruction as the guest hypervisor did,
@@ -239,5 +240,6 @@ void __kvm_tlb_el1_instr(struct kvm_s2_mmu *mmu, u64 val, u64 sys_encoding)
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	if (mmu)
+		__tlb_switch_to_host(&cxt);
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index c7b004982ea9..cf03281f06a3 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2684,6 +2684,8 @@ static bool handle_tlbi_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			    const struct sys_reg_desc *r)
 {
 	u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+	u64 virtual_vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+	struct kvm_s2_mmu *mmu;
 
 	/*
 	 * If we're here, this is because we've trapped on a EL1 TLBI
@@ -2702,24 +2704,13 @@ static bool handle_tlbi_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 	mutex_lock(&vcpu->kvm->lock);
 
-	if ((__vcpu_sys_reg(vcpu, HCR_EL2) & (HCR_E2H | HCR_TGE)) != (HCR_E2H | HCR_TGE)) {
-		u64 virtual_vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
-		struct kvm_s2_mmu *mmu;
-
-		mmu = lookup_s2_mmu(vcpu->kvm, virtual_vttbr, HCR_VM);
-		if (mmu)
-			__kvm_tlb_el1_instr(mmu, p->regval, sys_encoding);
+	mmu = lookup_s2_mmu(vcpu->kvm, virtual_vttbr, HCR_VM);
+	if (mmu)
+		__kvm_tlb_el1_instr(mmu, p->regval, sys_encoding);
 
-		mmu = lookup_s2_mmu(vcpu->kvm, virtual_vttbr, 0);
-		if (mmu)
-			__kvm_tlb_el1_instr(mmu, p->regval, sys_encoding);
-	} else {
-		/*
-		 * ARMv8.4-NV allows the guest to change TGE behind
-		 * our back, so we always trap EL1 TLBIs from vEL2...
-		 */
-		__kvm_tlb_el1_instr(&vcpu->kvm->arch.mmu, p->regval, sys_encoding);
-	}
+	mmu = lookup_s2_mmu(vcpu->kvm, virtual_vttbr, 0);
+	if (mmu)
+		__kvm_tlb_el1_instr(mmu, p->regval, sys_encoding);
 
 	mutex_unlock(&vcpu->kvm->lock);
 
-- 
2.29.2

Re: [PATCH v3 00/66] KVM: arm64: ARMv8.3/8.4 Nested Virtualization support

[Marc Zyngier]

Hi Haibo,

On 2021-01-11 07:20, Haibo Xu wrote:
> On Fri, 11 Dec 2020 at 00:00, Marc Zyngier <maz@kernel.org> wrote:
>> 
>> This is a rework of the NV series that I posted 10 months ago[1], as a
>> lot of the KVM code has changed since, and the series apply anymore
>> (not that anybody really cares as the the HW is, as usual, made of
>> unobtainium...).
>> 
>> From the previous version:
>> 
>> - Integration with the new page-table code
>> - New exception injection code
>> - No more messing with the nVHE code
>> - No AArch32!!!!
>> - Rebased on v5.10-rc4 + kvmarm/next for 5.11
>> 
>> From a functionality perspective, you can expect a L2 guest to work,
>> but don't even think of L3, as we only partially emulate the
>> ARMv8.{3,4}-NV extensions themselves. Same thing for vgic, debug, PMU,
>> as well as anything that would require a Stage-1 PTW. What we want to
>> achieve is that with NV disabled, there is no performance overhead and
>> no regression.
>> 
>> The series is roughly divided in 5 parts: exception handling, memory
>> virtualization, interrupts and timers for ARMv8.3, followed by the
>> ARMv8.4 support. There are of course some dependencies, but you'll
>> hopefully get the gist of it.
>> 
>> For the most courageous of you, I've put out a branch[2]. Of course,
>> you'll need some userspace. Andre maintains a hacked version of
>> kvmtool[3] that takes a --nested option, allowing the guest to be
>> started at EL2. You can run the whole stack in the Foundation
>> model. Don't be in a hurry ;-).
>> 
> 
> Hi Marc,
> 
> I got a kernel BUG message when booting the L2 guest kernel with the
> kvmtool on a FVP setup.
> Could you help have a look about the BUG message as well as my
> environment configuration?
> I think It probably caused by some local configurations of the FVP 
> setup.

No, this is likely a bug in your L1 guest, which was fixed in -rc3:

2a5f1b67ec57 ("KVM: arm64: Don't access PMCR_EL0 when no PMU is 
available")

and was found in the exact same circumstances. Alternatively, and if
you don't want to change your L1 guest, you can just pass the --pmu
option to kvmtool when starting the L1 guest.

Hope this helps,

         M.
-- 
Jazz is not dead. It just smells funny...

Re: [PATCH v3 00/66] KVM: arm64: ARMv8.3/8.4 Nested Virtualization support

[Haibo Xu]

On Mon, 11 Jan 2021 at 16:59, Marc Zyngier <maz@kernel.org> wrote:
>
> Hi Haibo,
>
> On 2021-01-11 07:20, Haibo Xu wrote:
> > On Fri, 11 Dec 2020 at 00:00, Marc Zyngier <maz@kernel.org> wrote:
> >>
> >> This is a rework of the NV series that I posted 10 months ago[1], as a
> >> lot of the KVM code has changed since, and the series apply anymore
> >> (not that anybody really cares as the the HW is, as usual, made of
> >> unobtainium...).
> >>
> >> From the previous version:
> >>
> >> - Integration with the new page-table code
> >> - New exception injection code
> >> - No more messing with the nVHE code
> >> - No AArch32!!!!
> >> - Rebased on v5.10-rc4 + kvmarm/next for 5.11
> >>
> >> From a functionality perspective, you can expect a L2 guest to work,
> >> but don't even think of L3, as we only partially emulate the
> >> ARMv8.{3,4}-NV extensions themselves. Same thing for vgic, debug, PMU,
> >> as well as anything that would require a Stage-1 PTW. What we want to
> >> achieve is that with NV disabled, there is no performance overhead and
> >> no regression.
> >>
> >> The series is roughly divided in 5 parts: exception handling, memory
> >> virtualization, interrupts and timers for ARMv8.3, followed by the
> >> ARMv8.4 support. There are of course some dependencies, but you'll
> >> hopefully get the gist of it.
> >>
> >> For the most courageous of you, I've put out a branch[2]. Of course,
> >> you'll need some userspace. Andre maintains a hacked version of
> >> kvmtool[3] that takes a --nested option, allowing the guest to be
> >> started at EL2. You can run the whole stack in the Foundation
> >> model. Don't be in a hurry ;-).
> >>
> >
> > Hi Marc,
> >
> > I got a kernel BUG message when booting the L2 guest kernel with the
> > kvmtool on a FVP setup.
> > Could you help have a look about the BUG message as well as my
> > environment configuration?
> > I think It probably caused by some local configurations of the FVP
> > setup.
>
> No, this is likely a bug in your L1 guest, which was fixed in -rc3:
>
> 2a5f1b67ec57 ("KVM: arm64: Don't access PMCR_EL0 when no PMU is
> available")
>
> and was found in the exact same circumstances. Alternatively, and if
> you don't want to change your L1 guest, you can just pass the --pmu
> option to kvmtool when starting the L1 guest.

After passing --pmu when starting a L1 guest, I can successfully run a
L2 guest now!
Thanks so much for the help!

Haibo

>
> Hope this helps,
>
>          M.
> --
> Jazz is not dead. It just smells funny...

Re: [PATCH v3 00/66] KVM: arm64: ARMv8.3/8.4 Nested Virtualization support

[André Przywara]

On 10/12/2020 15:58, Marc Zyngier wrote:

Hi,

> This is a rework of the NV series that I posted 10 months ago[1], as a

....

> For the most courageous of you, I've put out a branch[2]. Of course,
> you'll need some userspace. Andre maintains a hacked version of
> kvmtool[3] that takes a --nested option, allowing the guest to be
> started at EL2.
I have updated the branch, as the headers changed as well:
https://gitlab.arm.com/linux-arm/kvmtool/-/commits/nv-5.11-WIP/

Cheers,
Andre

Re: [PATCH v3 63/66] KVM: arm64: nv: Allocate VNCR page when required

[Haibo Xu]

On Fri, 11 Dec 2020 at 00:04, Marc Zyngier <maz@kernel.org> wrote:
>
> If running a NV guest on an ARMv8.4-NV capable system, let's
> allocate an additional page that will be used by the hypervisor
> to fulfill system register accesses.
>
> Signed-off-by: Marc Zyngier <maz@kernel.org>
> ---
>  arch/arm64/include/asm/kvm_host.h | 3 ++-
>  arch/arm64/kvm/nested.c           | 8 ++++++++
>  arch/arm64/kvm/reset.c            | 1 +
>  3 files changed, 11 insertions(+), 1 deletion(-)
>
> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
> index 78630bd5124d..dada0678c28e 100644
> --- a/arch/arm64/include/asm/kvm_host.h
> +++ b/arch/arm64/include/asm/kvm_host.h
> @@ -523,7 +523,8 @@ struct kvm_vcpu_arch {
>   */
>  static inline u64 *__ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
>  {
> -       if (unlikely(r >= __VNCR_START__ && ctxt->vncr_array))
> +       if (unlikely(cpus_have_final_cap(ARM64_HAS_ENHANCED_NESTED_VIRT) &&
> +                    r >= __VNCR_START__ && ctxt->vncr_array))
>                 return &ctxt->vncr_array[r - __VNCR_START__];
>
>         return (u64 *)&ctxt->sys_regs[r];
> diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
> index eef8f9873814..88147ec99755 100644
> --- a/arch/arm64/kvm/nested.c
> +++ b/arch/arm64/kvm/nested.c
> @@ -47,6 +47,12 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
>         if (!cpus_have_final_cap(ARM64_HAS_NESTED_VIRT))
>                 return -EINVAL;
>
> +       if (cpus_have_final_cap(ARM64_HAS_ENHANCED_NESTED_VIRT)) {
> +               vcpu->arch.ctxt.vncr_array = (u64 *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
> +               if (!vcpu->arch.ctxt.vncr_array)
> +                       return -ENOMEM;
> +       }
> +

If KVM_ARM_VCPU_INIT was called multiple times, the above codes would
try to allocate a new page
without free-ing the previous one. Besides that, the following
kvm_free_stage2_pgd() call would fail in the
second call with the error message "kvm_arch already initialized?".
I think a possible fix is to add a new flag to indicate whether the NV
related meta data have been initialized,
and only initialize them for the first call.

>         mutex_lock(&kvm->lock);
>
>         /*
> @@ -64,6 +70,8 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
>                     kvm_init_stage2_mmu(kvm, &tmp[num_mmus - 2])) {
>                         kvm_free_stage2_pgd(&tmp[num_mmus - 1]);
>                         kvm_free_stage2_pgd(&tmp[num_mmus - 2]);
> +                       free_page((unsigned long)vcpu->arch.ctxt.vncr_array);
> +                       vcpu->arch.ctxt.vncr_array = NULL;
>                 } else {
>                         kvm->arch.nested_mmus_size = num_mmus;
>                         ret = 0;
> diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
> index 2d2c780e6c69..d281eb39036f 100644
> --- a/arch/arm64/kvm/reset.c
> +++ b/arch/arm64/kvm/reset.c
> @@ -150,6 +150,7 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu)
>  void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu)
>  {
>         kfree(vcpu->arch.sve_state);
> +       free_page((unsigned long)vcpu->arch.ctxt.vncr_array);
>  }
>
>  static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
> --
> 2.29.2
>
> _______________________________________________
> kvmarm mailing list
> kvmarm@lists.cs.columbia.edu
> https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

Re: [PATCH v3 33/66] KVM: arm64: nv: Support multiple nested Stage-2 mmu structures

[Haibo Xu]

On Fri, 11 Dec 2020 at 00:04, Marc Zyngier <maz@kernel.org> wrote:
>
> Add Stage-2 mmu data structures for virtual EL2 and for nested guests.
> We don't yet populate shadow Stage-2 page tables, but we now have a
> framework for getting to a shadow Stage-2 pgd.
>
> We allocate twice the number of vcpus as Stage-2 mmu structures because
> that's sufficient for each vcpu running two translation regimes without
> having to flush the Stage-2 page tables.
>
> Co-developed-by: Christoffer Dall <christoffer.dall@arm.com>
> Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
> Signed-off-by: Marc Zyngier <maz@kernel.org>
> ---
>  arch/arm64/include/asm/kvm_host.h   |  29 +++++
>  arch/arm64/include/asm/kvm_mmu.h    |   8 ++
>  arch/arm64/include/asm/kvm_nested.h |   7 ++
>  arch/arm64/kvm/arm.c                |  16 ++-
>  arch/arm64/kvm/mmu.c                |  18 ++-
>  arch/arm64/kvm/nested.c             | 183 ++++++++++++++++++++++++++++
>  6 files changed, 250 insertions(+), 11 deletions(-)
>
> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
> index d731cf7a56cb..d99e51e7cbee 100644
> --- a/arch/arm64/include/asm/kvm_host.h
> +++ b/arch/arm64/include/asm/kvm_host.h
> @@ -95,14 +95,43 @@ struct kvm_s2_mmu {
>         int __percpu *last_vcpu_ran;
>
>         struct kvm *kvm;
> +
> +       /*
> +        * For a shadow stage-2 MMU, the virtual vttbr programmed by the guest
> +        * hypervisor.  Unused for kvm_arch->mmu. Set to 1 when the structure
> +        * contains no valid information.
> +        */
> +       u64     vttbr;
> +
> +       /* true when this represents a nested context where virtual HCR_EL2.VM == 1 */
> +       bool    nested_stage2_enabled;
> +
> +       /*
> +        *  0: Nobody is currently using this, check vttbr for validity
> +        * >0: Somebody is actively using this.
> +        */
> +       atomic_t refcnt;
>  };
>
> +static inline bool kvm_s2_mmu_valid(struct kvm_s2_mmu *mmu)
> +{
> +       return !(mmu->vttbr & 1);
> +}
> +
>  struct kvm_arch_memory_slot {
>  };
>
>  struct kvm_arch {
>         struct kvm_s2_mmu mmu;
>
> +       /*
> +        * Stage 2 paging stage for VMs with nested virtual using a virtual
> +        * VMID.
> +        */
> +       struct kvm_s2_mmu *nested_mmus;
> +       size_t nested_mmus_size;
> +       int nested_mmus_next;
> +
>         /* VTCR_EL2 value for this VM */
>         u64    vtcr;
>
> diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
> index 76a8a0ca45b8..ec39015bb2a6 100644
> --- a/arch/arm64/include/asm/kvm_mmu.h
> +++ b/arch/arm64/include/asm/kvm_mmu.h
> @@ -126,6 +126,7 @@ alternative_cb_end
>  #include <asm/cacheflush.h>
>  #include <asm/mmu_context.h>
>  #include <asm/kvm_emulate.h>
> +#include <asm/kvm_nested.h>
>
>  void kvm_update_va_mask(struct alt_instr *alt,
>                         __le32 *origptr, __le32 *updptr, int nr_inst);
> @@ -184,6 +185,7 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
>                              void **haddr);
>  void free_hyp_pgds(void);
>
> +void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
>  void stage2_unmap_vm(struct kvm *kvm);
>  int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu);
>  void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
> @@ -306,5 +308,11 @@ static __always_inline void __load_guest_stage2(struct kvm_s2_mmu *mmu)
>         asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
>  }
>
> +static inline u64 get_vmid(u64 vttbr)
> +{
> +       return (vttbr & VTTBR_VMID_MASK(kvm_get_vmid_bits())) >>
> +               VTTBR_VMID_SHIFT;
> +}
> +
>  #endif /* __ASSEMBLY__ */
>  #endif /* __ARM64_KVM_MMU_H__ */
> diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
> index 026ddaad972c..473ecd1d60d0 100644
> --- a/arch/arm64/include/asm/kvm_nested.h
> +++ b/arch/arm64/include/asm/kvm_nested.h
> @@ -61,6 +61,13 @@ static inline u64 translate_cnthctl_el2_to_cntkctl_el1(u64 cnthctl)
>                 (cnthctl & (CNTHCTL_EVNTI | CNTHCTL_EVNTDIR | CNTHCTL_EVNTEN)));
>  }
>
> +extern void kvm_init_nested(struct kvm *kvm);
> +extern int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu);
> +extern void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu);
> +extern struct kvm_s2_mmu *lookup_s2_mmu(struct kvm *kvm, u64 vttbr, u64 hcr);
> +extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
> +extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
> +
>  int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe);
>  extern bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg,
>                             u64 control_bit);
> diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
> index 6e637d2b4cfb..1656dd80bbc4 100644
> --- a/arch/arm64/kvm/arm.c
> +++ b/arch/arm64/kvm/arm.c
> @@ -35,6 +35,7 @@
>  #include <asm/kvm_arm.h>
>  #include <asm/kvm_asm.h>
>  #include <asm/kvm_mmu.h>
> +#include <asm/kvm_nested.h>
>  #include <asm/kvm_emulate.h>
>  #include <asm/sections.h>
>
> @@ -142,6 +143,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
>         if (ret)
>                 return ret;
>
> +       kvm_init_nested(kvm);
> +
>         ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP);
>         if (ret)
>                 goto out_free_stage2_pgd;
> @@ -385,6 +388,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
>         struct kvm_s2_mmu *mmu;
>         int *last_ran;
>
> +       if (nested_virt_in_use(vcpu))
> +               kvm_vcpu_load_hw_mmu(vcpu);
> +
>         mmu = vcpu->arch.hw_mmu;
>         last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
>
> @@ -426,6 +432,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
>         kvm_vgic_put(vcpu);
>         kvm_vcpu_pmu_restore_host(vcpu);
>
> +       if (nested_virt_in_use(vcpu))
> +               kvm_vcpu_put_hw_mmu(vcpu);
> +
>         vcpu->cpu = -1;
>  }
>
> @@ -1026,8 +1035,13 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
>
>         vcpu->arch.target = phys_target;
>
> +       /* Prepare for nested if required */
> +       ret = kvm_vcpu_init_nested(vcpu);
> +
>         /* Now we know what it is, we can reset it. */
> -       ret = kvm_reset_vcpu(vcpu);
> +       if (!ret)
> +               ret = kvm_reset_vcpu(vcpu);
> +
>         if (ret) {
>                 vcpu->arch.target = -1;
>                 bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
> diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
> index 1f41173e6149..2f0302211af3 100644
> --- a/arch/arm64/kvm/mmu.c
> +++ b/arch/arm64/kvm/mmu.c
> @@ -113,7 +113,7 @@ static bool kvm_is_device_pfn(unsigned long pfn)
>   * does.
>   */
>  /**
> - * unmap_stage2_range -- Clear stage2 page table entries to unmap a range
> + * kvm_unmap_stage2_range -- Clear stage2 page table entries to unmap a range
>   * @mmu:   The KVM stage-2 MMU pointer
>   * @start: The intermediate physical base address of the range to unmap
>   * @size:  The size of the area to unmap
> @@ -136,7 +136,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
>                                    may_block));
>  }
>
> -static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
> +void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
>  {
>         __unmap_stage2_range(mmu, start, size, true);
>  }
> @@ -391,6 +391,9 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
>         mmu->pgt = pgt;
>         mmu->pgd_phys = __pa(pgt->pgd);
>         mmu->vmid.vmid_gen = 0;
> +
> +       kvm_init_nested_s2_mmu(mmu);
> +
>         return 0;
>
>  out_destroy_pgtable:
> @@ -435,7 +438,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
>
>                 if (!(vma->vm_flags & VM_PFNMAP)) {
>                         gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
> -                       unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
> +                       kvm_unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
>                 }
>                 hva = vm_end;
>         } while (hva < reg_end);
> @@ -1360,7 +1363,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
>
>         spin_lock(&kvm->mmu_lock);
>         if (ret)
> -               unmap_stage2_range(&kvm->arch.mmu, mem->guest_phys_addr, mem->memory_size);
> +               kvm_unmap_stage2_range(&kvm->arch.mmu, mem->guest_phys_addr, mem->memory_size);
>         else if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
>                 stage2_flush_memslot(kvm, memslot);
>         spin_unlock(&kvm->mmu_lock);
> @@ -1377,11 +1380,6 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
>  {
>  }
>
> -void kvm_arch_flush_shadow_all(struct kvm *kvm)
> -{
> -       kvm_free_stage2_pgd(&kvm->arch.mmu);
> -}
> -
>  void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
>                                    struct kvm_memory_slot *slot)
>  {
> @@ -1389,7 +1387,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
>         phys_addr_t size = slot->npages << PAGE_SHIFT;
>
>         spin_lock(&kvm->mmu_lock);
> -       unmap_stage2_range(&kvm->arch.mmu, gpa, size);
> +       kvm_unmap_stage2_range(&kvm->arch.mmu, gpa, size);
>         spin_unlock(&kvm->mmu_lock);
>  }
>
> diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
> index 9fb44bc7db3f..8e85d2ef24d9 100644
> --- a/arch/arm64/kvm/nested.c
> +++ b/arch/arm64/kvm/nested.c
> @@ -19,12 +19,177 @@
>  #include <linux/kvm.h>
>  #include <linux/kvm_host.h>
>
> +#include <asm/kvm_arm.h>
>  #include <asm/kvm_emulate.h>
> +#include <asm/kvm_mmu.h>
>  #include <asm/kvm_nested.h>
>  #include <asm/sysreg.h>
>
>  #include "sys_regs.h"
>
> +void kvm_init_nested(struct kvm *kvm)
> +{
> +       kvm->arch.nested_mmus = NULL;
> +       kvm->arch.nested_mmus_size = 0;
> +}
> +
> +int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
> +{
> +       struct kvm *kvm = vcpu->kvm;
> +       struct kvm_s2_mmu *tmp;
> +       int num_mmus;
> +       int ret = -ENOMEM;
> +
> +       if (!test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features))
> +               return 0;
> +
> +       if (!cpus_have_final_cap(ARM64_HAS_NESTED_VIRT))
> +               return -EINVAL;

nit: returning a "not supported" kind of errno?

> +
> +       mutex_lock(&kvm->lock);
> +
> +       /*
> +        * Let's treat memory allocation failures as benign: If we fail to
> +        * allocate anything, return an error and keep the allocated array
> +        * alive. Userspace may try to recover by intializing the vcpu
> +        * again, and there is no reason to affect the whole VM for this.
> +        */
> +       num_mmus = atomic_read(&kvm->online_vcpus) * 2;
> +       tmp = krealloc(kvm->arch.nested_mmus,
> +                      num_mmus * sizeof(*kvm->arch.nested_mmus),
> +                      GFP_KERNEL | __GFP_ZERO);
> +       if (tmp) {
> +               if (kvm_init_stage2_mmu(kvm, &tmp[num_mmus - 1]) ||
> +                   kvm_init_stage2_mmu(kvm, &tmp[num_mmus - 2])) {
> +                       kvm_free_stage2_pgd(&tmp[num_mmus - 1]);
> +                       kvm_free_stage2_pgd(&tmp[num_mmus - 2]);
> +               } else {
> +                       kvm->arch.nested_mmus_size = num_mmus;
> +                       ret = 0;
> +               }
> +
> +               kvm->arch.nested_mmus = tmp;
> +       }
> +
> +       mutex_unlock(&kvm->lock);
> +       return ret;
> +}
> +
> +/* Must be called with kvm->lock held */
> +struct kvm_s2_mmu *lookup_s2_mmu(struct kvm *kvm, u64 vttbr, u64 hcr)
> +{
> +       bool nested_stage2_enabled = hcr & HCR_VM;
> +       int i;
> +
> +       /* Don't consider the CnP bit for the vttbr match */
> +       vttbr = vttbr & ~VTTBR_CNP_BIT;
> +
> +       /*
> +        * Two possibilities when looking up a S2 MMU context:
> +        *
> +        * - either S2 is enabled in the guest, and we need a context that
> +         *   is S2-enabled and matches the full VTTBR (VMID+BADDR), which
> +         *   makes it safe from a TLB conflict perspective (a broken guest
> +         *   won't be able to generate them),
> +        *
> +        * - or S2 is disabled, and we need a context that is S2-disabled
> +         *   and matches the VMID only, as all TLBs are tagged by VMID even
> +         *   if S2 translation is enabled.
> +        */
> +       for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
> +               struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
> +
> +               if (!kvm_s2_mmu_valid(mmu))
> +                       continue;
> +
> +               if (nested_stage2_enabled &&
> +                   mmu->nested_stage2_enabled &&
> +                   vttbr == mmu->vttbr)
> +                       return mmu;
> +
> +               if (!nested_stage2_enabled &&
> +                   !mmu->nested_stage2_enabled &&
> +                   get_vmid(vttbr) == get_vmid(mmu->vttbr))
> +                       return mmu;
> +       }
> +       return NULL;
> +}
> +
> +static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
> +{
> +       struct kvm *kvm = vcpu->kvm;
> +       u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
> +       u64 hcr= vcpu_read_sys_reg(vcpu, HCR_EL2);
> +       struct kvm_s2_mmu *s2_mmu;
> +       int i;
> +
> +       s2_mmu = lookup_s2_mmu(kvm, vttbr, hcr);
> +       if (s2_mmu)
> +               goto out;
> +
> +       /*
> +        * Make sure we don't always search from the same point, or we
> +        * will always reuse a potentially active context, leaving
> +        * free contexts unused.
> +        */
> +       for (i = kvm->arch.nested_mmus_next;
> +            i < (kvm->arch.nested_mmus_size + kvm->arch.nested_mmus_next);
> +            i++) {
> +               s2_mmu = &kvm->arch.nested_mmus[i % kvm->arch.nested_mmus_size];
> +
> +               if (atomic_read(&s2_mmu->refcnt) == 0)
> +                       break;
> +       }
> +       BUG_ON(atomic_read(&s2_mmu->refcnt)); /* We have struct MMUs to spare */
> +
> +       /* Set the scene for the next search */
> +       kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size;
> +
> +       if (kvm_s2_mmu_valid(s2_mmu)) {
> +               /* Clear the old state */
> +               kvm_unmap_stage2_range(s2_mmu, 0, kvm_phys_size(kvm));
> +               if (s2_mmu->vmid.vmid_gen)
> +                       kvm_call_hyp(__kvm_tlb_flush_vmid, s2_mmu);
> +       }
> +
> +       /*
> +        * The virtual VMID (modulo CnP) will be used as a key when matching
> +        * an existing kvm_s2_mmu.
> +        */
> +       s2_mmu->vttbr = vttbr & ~VTTBR_CNP_BIT;
> +       s2_mmu->nested_stage2_enabled = hcr & HCR_VM;
> +
> +out:
> +       atomic_inc(&s2_mmu->refcnt);
> +       return s2_mmu;
> +}
> +
> +void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu)
> +{
> +       mmu->vttbr = 1;
> +       mmu->nested_stage2_enabled = false;
> +       atomic_set(&mmu->refcnt, 0);
> +}
> +
> +void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
> +{
> +       if (is_hyp_ctxt(vcpu)) {
> +               vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
> +       } else {
> +               spin_lock(&vcpu->kvm->mmu_lock);
> +               vcpu->arch.hw_mmu = get_s2_mmu_nested(vcpu);
> +               spin_unlock(&vcpu->kvm->mmu_lock);
> +       }
> +}
> +
> +void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
> +{
> +       if (vcpu->arch.hw_mmu != &vcpu->kvm->arch.mmu) {
> +               atomic_dec(&vcpu->arch.hw_mmu->refcnt);
> +               vcpu->arch.hw_mmu = NULL;
> +       }
> +}
> +
>  /*
>   * Inject wfx to the virtual EL2 if this is not from the virtual EL2 and
>   * the virtual HCR_EL2.TWX is set. Otherwise, let the host hypervisor
> @@ -43,6 +208,24 @@ int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe)
>         return -EINVAL;
>  }
>
> +void kvm_arch_flush_shadow_all(struct kvm *kvm)
> +{
> +       int i;
> +
> +       for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
> +               struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
> +
> +               WARN_ON(atomic_read(&mmu->refcnt));
> +
> +               if (!atomic_read(&mmu->refcnt))
> +                       kvm_free_stage2_pgd(mmu);
> +       }
> +       kfree(kvm->arch.nested_mmus);
> +       kvm->arch.nested_mmus = NULL;
> +       kvm->arch.nested_mmus_size = 0;
> +       kvm_free_stage2_pgd(&kvm->arch.mmu);
> +}
> +
>  #define FEATURE(x)     (GENMASK_ULL(x##_SHIFT + 3, x##_SHIFT))
>
>  /*
> --
> 2.29.2
>
> _______________________________________________
> kvmarm mailing list
> kvmarm@lists.cs.columbia.edu
> https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

Re: [PATCH v3 00/66] KVM: arm64: ARMv8.3/8.4 Nested Virtualization support

[Haibo Xu]

Re-send in case the previous email was blocked for the inlined hyper-link.

Hi Marc,

I have tried to enable the NV support in Qemu, and now I can
successfully boot a L2 guest
in Qemu KVM mode.

This patch series looks good from the Qemu side except for two minor
requirements:
(1) Qemu will check whether a feature was supported by the KVM cap
when the user tries
     to enable it in the command line, so a new capability was
prefered for the NV(KVM_CAP_ARM_NV?).
(2) According to the Documentation/virt/kvm/api.rst, userspace can
call KVM_ARM_VCPU_INIT
     multiple times for a given vcpu, but the kvm_vcpu_init_nested()
do have some issue when
     called multiple times(please refer to the detailed comments in patch 63)

Regards,
Haibo

On Fri, 11 Dec 2020 at 00:00, Marc Zyngier <maz@kernel.org> wrote:
>
> This is a rework of the NV series that I posted 10 months ago[1], as a
> lot of the KVM code has changed since, and the series apply anymore
> (not that anybody really cares as the the HW is, as usual, made of
> unobtainium...).
>
> From the previous version:
>
> - Integration with the new page-table code
> - New exception injection code
> - No more messing with the nVHE code
> - No AArch32!!!!
> - Rebased on v5.10-rc4 + kvmarm/next for 5.11
>
> From a functionality perspective, you can expect a L2 guest to work,
> but don't even think of L3, as we only partially emulate the
> ARMv8.{3,4}-NV extensions themselves. Same thing for vgic, debug, PMU,
> as well as anything that would require a Stage-1 PTW. What we want to
> achieve is that with NV disabled, there is no performance overhead and
> no regression.
>
> The series is roughly divided in 5 parts: exception handling, memory
> virtualization, interrupts and timers for ARMv8.3, followed by the
> ARMv8.4 support. There are of course some dependencies, but you'll
> hopefully get the gist of it.
>
> For the most courageous of you, I've put out a branch[2]. Of course,
> you'll need some userspace. Andre maintains a hacked version of
> kvmtool[3] that takes a --nested option, allowing the guest to be
> started at EL2. You can run the whole stack in the Foundation
> model. Don't be in a hurry ;-).
>
> And to be clear: although Jintack and Christoffer have written tons of
> the stuff originaly, I'm the one responsible for breaking it!
>
> [1] https://lore.kernel.org/r/20200211174938.27809-1-maz@kernel.org
> [2] git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms.git kvm-arm64/nv-5.11.-WIP
> [3] git://linux-arm.org/kvmtool.git nv/nv-wip-5.2-rc5
>
> Andre Przywara (1):
>   KVM: arm64: nv: vgic: Allow userland to set VGIC maintenance IRQ
>
> Christoffer Dall (15):
>   KVM: arm64: nv: Introduce nested virtualization VCPU feature
>   KVM: arm64: nv: Reset VCPU to EL2 registers if VCPU nested virt is set
>   KVM: arm64: nv: Allow userspace to set PSR_MODE_EL2x
>   KVM: arm64: nv: Add nested virt VCPU primitives for vEL2 VCPU state
>   KVM: arm64: nv: Reset VMPIDR_EL2 and VPIDR_EL2 to sane values
>   KVM: arm64: nv: Handle trapped ERET from virtual EL2
>   KVM: arm64: nv: Emulate PSTATE.M for a guest hypervisor
>   KVM: arm64: nv: Trap EL1 VM register accesses in virtual EL2
>   KVM: arm64: nv: Only toggle cache for virtual EL2 when SCTLR_EL2
>     changes
>   KVM: arm64: nv: Implement nested Stage-2 page table walk logic
>   KVM: arm64: nv: Unmap/flush shadow stage 2 page tables
>   KVM: arm64: nv: arch_timer: Support hyp timer emulation
>   KVM: arm64: nv: vgic: Emulate the HW bit in software
>   KVM: arm64: nv: Add nested GICv3 tracepoints
>   KVM: arm64: nv: Sync nested timer state with ARMv8.4
>
> Jintack Lim (19):
>   arm64: Add ARM64_HAS_NESTED_VIRT cpufeature
>   KVM: arm64: nv: Handle HCR_EL2.NV system register traps
>   KVM: arm64: nv: Support virtual EL2 exceptions
>   KVM: arm64: nv: Inject HVC exceptions to the virtual EL2
>   KVM: arm64: nv: Trap SPSR_EL1, ELR_EL1 and VBAR_EL1 from virtual EL2
>   KVM: arm64: nv: Trap CPACR_EL1 access in virtual EL2
>   KVM: arm64: nv: Handle PSCI call via smc from the guest
>   KVM: arm64: nv: Respect virtual HCR_EL2.TWX setting
>   KVM: arm64: nv: Respect virtual CPTR_EL2.{TFP,FPEN} settings
>   KVM: arm64: nv: Respect the virtual HCR_EL2.NV bit setting
>   KVM: arm64: nv: Respect virtual HCR_EL2.TVM and TRVM settings
>   KVM: arm64: nv: Respect the virtual HCR_EL2.NV1 bit setting
>   KVM: arm64: nv: Emulate EL12 register accesses from the virtual EL2
>   KVM: arm64: nv: Configure HCR_EL2 for nested virtualization
>   KVM: arm64: nv: Introduce sys_reg_desc.forward_trap
>   KVM: arm64: nv: Set a handler for the system instruction traps
>   KVM: arm64: nv: Trap and emulate AT instructions from virtual EL2
>   KVM: arm64: nv: Trap and emulate TLBI instructions from virtual EL2
>   KVM: arm64: nv: Nested GICv3 Support
>
> Marc Zyngier (31):
>   KVM: arm64: nv: Add EL2 system registers to vcpu context
>   KVM: arm64: nv: Add non-VHE-EL2->EL1 translation helpers
>   KVM: arm64: nv: Handle virtual EL2 registers in
>     vcpu_read/write_sys_reg()
>   KVM: arm64: nv: Handle SPSR_EL2 specially
>   KVM: arm64: nv: Handle HCR_EL2.E2H specially
>   KVM: arm64: nv: Save/Restore vEL2 sysregs
>   KVM: arm64: nv: Forward debug traps to the nested guest
>   KVM: arm64: nv: Filter out unsupported features from ID regs
>   KVM: arm64: nv: Hide RAS from nested guests
>   KVM: arm64: nv: Support multiple nested Stage-2 mmu structures
>   KVM: arm64: nv: Handle shadow stage 2 page faults
>   KVM: arm64: nv: Restrict S2 RD/WR permissions to match the guest's
>   KVM: arm64: nv: Fold guest's HCR_EL2 configuration into the host's
>   KVM: arm64: nv: Add handling of EL2-specific timer registers
>   KVM: arm64: nv: Load timer before the GIC
>   KVM: arm64: nv: Don't load the GICv4 context on entering a nested
>     guest
>   KVM: arm64: nv: Implement maintenance interrupt forwarding
>   KVM: arm64: nv: Allow userspace to request KVM_ARM_VCPU_NESTED_VIRT
>   KVM: arm64: nv: Add handling of ARMv8.4-TTL TLB invalidation
>   KVM: arm64: nv: Invalidate TLBs based on shadow S2 TTL-like
>     information
>   KVM: arm64: Allow populating S2 SW bits
>   KVM: arm64: nv: Tag shadow S2 entries with nested level
>   KVM: arm64: nv: Add include containing the VNCR_EL2 offsets
>   KVM: arm64: Map VNCR-capable registers to a separate page
>   KVM: arm64: nv: Move nested vgic state into the sysreg file
>   KVM: arm64: Add ARMv8.4 Enhanced Nested Virt cpufeature
>   KVM: arm64: nv: Synchronize PSTATE early on exit
>   KVM: arm64: nv: Allocate VNCR page when required
>   KVM: arm64: nv: Enable ARMv8.4-NV support
>   KVM: arm64: nv: Fast-track 'InHost' exception returns
>   KVM: arm64: nv: Fast-track EL1 TLBIs for VHE guests
>
>  .../admin-guide/kernel-parameters.txt         |    4 +
>  .../virt/kvm/devices/arm-vgic-v3.rst          |   12 +-
>  arch/arm64/include/asm/cpucaps.h              |    2 +
>  arch/arm64/include/asm/esr.h                  |    6 +
>  arch/arm64/include/asm/kvm_arm.h              |   28 +-
>  arch/arm64/include/asm/kvm_asm.h              |    4 +
>  arch/arm64/include/asm/kvm_emulate.h          |  145 +-
>  arch/arm64/include/asm/kvm_host.h             |  175 ++-
>  arch/arm64/include/asm/kvm_hyp.h              |    2 +
>  arch/arm64/include/asm/kvm_mmu.h              |   17 +-
>  arch/arm64/include/asm/kvm_nested.h           |  152 ++
>  arch/arm64/include/asm/kvm_pgtable.h          |   10 +
>  arch/arm64/include/asm/sysreg.h               |  104 +-
>  arch/arm64/include/asm/vncr_mapping.h         |   73 +
>  arch/arm64/include/uapi/asm/kvm.h             |    2 +
>  arch/arm64/kernel/cpufeature.c                |   35 +
>  arch/arm64/kvm/Makefile                       |    4 +-
>  arch/arm64/kvm/arch_timer.c                   |  189 ++-
>  arch/arm64/kvm/arm.c                          |   34 +-
>  arch/arm64/kvm/at.c                           |  231 ++++
>  arch/arm64/kvm/emulate-nested.c               |  186 +++
>  arch/arm64/kvm/guest.c                        |    6 +
>  arch/arm64/kvm/handle_exit.c                  |   81 +-
>  arch/arm64/kvm/hyp/exception.c                |   44 +-
>  arch/arm64/kvm/hyp/include/hyp/switch.h       |   31 +-
>  arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h    |   28 +-
>  arch/arm64/kvm/hyp/nvhe/switch.c              |   10 +-
>  arch/arm64/kvm/hyp/nvhe/sysreg-sr.c           |    2 +-
>  arch/arm64/kvm/hyp/pgtable.c                  |    6 +
>  arch/arm64/kvm/hyp/vgic-v3-sr.c               |    2 +-
>  arch/arm64/kvm/hyp/vhe/switch.c               |  207 ++-
>  arch/arm64/kvm/hyp/vhe/sysreg-sr.c            |  125 +-
>  arch/arm64/kvm/hyp/vhe/tlb.c                  |   83 ++
>  arch/arm64/kvm/inject_fault.c                 |   62 +-
>  arch/arm64/kvm/mmu.c                          |  183 ++-
>  arch/arm64/kvm/nested.c                       |  908 ++++++++++++
>  arch/arm64/kvm/reset.c                        |   14 +-
>  arch/arm64/kvm/sys_regs.c                     | 1226 ++++++++++++++++-
>  arch/arm64/kvm/sys_regs.h                     |    6 +
>  arch/arm64/kvm/trace_arm.h                    |   65 +-
>  arch/arm64/kvm/vgic/vgic-init.c               |   30 +
>  arch/arm64/kvm/vgic/vgic-kvm-device.c         |   22 +
>  arch/arm64/kvm/vgic/vgic-nested-trace.h       |  137 ++
>  arch/arm64/kvm/vgic/vgic-v3-nested.c          |  240 ++++
>  arch/arm64/kvm/vgic/vgic-v3.c                 |   39 +-
>  arch/arm64/kvm/vgic/vgic.c                    |   44 +
>  arch/arm64/kvm/vgic/vgic.h                    |   10 +
>  include/kvm/arm_arch_timer.h                  |    7 +
>  include/kvm/arm_vgic.h                        |   16 +
>  tools/arch/arm/include/uapi/asm/kvm.h         |    1 +
>  50 files changed, 4890 insertions(+), 160 deletions(-)
>  create mode 100644 arch/arm64/include/asm/kvm_nested.h
>  create mode 100644 arch/arm64/include/asm/vncr_mapping.h
>  create mode 100644 arch/arm64/kvm/at.c
>  create mode 100644 arch/arm64/kvm/emulate-nested.c
>  create mode 100644 arch/arm64/kvm/nested.c
>  create mode 100644 arch/arm64/kvm/vgic/vgic-nested-trace.h
>  create mode 100644 arch/arm64/kvm/vgic/vgic-v3-nested.c
>
> --
> 2.29.2
>
> _______________________________________________
> kvmarm mailing list
> kvmarm@lists.cs.columbia.edu
> https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

Re: [PATCH v3 05/66] KVM: arm64: nv: Add EL2 system registers to vcpu context

[Andre Przywara]

On Thu, 10 Dec 2020 15:59:01 +0000
Marc Zyngier <maz@kernel.org> wrote:

Hi,

> Add the minimal set of EL2 system registers to the vcpu context.
> Nothing uses them just yet.
> 
> Signed-off-by: Marc Zyngier <maz@kernel.org>

Checked against the ARM ARM that this list contains the _EL2 registers
available in ARMv8.1, minus timer and GIC registers.

Reviewed-by: Andre Przywara <andre.przywara@arm.com>

Cheers,
Andre 

> ---
>  arch/arm64/include/asm/kvm_host.h | 34 ++++++++++++++++++++++++++++++-
>  1 file changed, 33 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
> index 11beda85ee7e..d731cf7a56cb 100644
> --- a/arch/arm64/include/asm/kvm_host.h
> +++ b/arch/arm64/include/asm/kvm_host.h
> @@ -206,12 +206,44 @@ enum vcpu_sysreg {
>  	CNTP_CVAL_EL0,
>  	CNTP_CTL_EL0,
>  
> -	/* 32bit specific registers. Keep them at the end of the range */
> +	/* 32bit specific registers. */
>  	DACR32_EL2,	/* Domain Access Control Register */
>  	IFSR32_EL2,	/* Instruction Fault Status Register */
>  	FPEXC32_EL2,	/* Floating-Point Exception Control Register */
>  	DBGVCR32_EL2,	/* Debug Vector Catch Register */
>  
> +	/* EL2 registers */
> +	VPIDR_EL2,	/* Virtualization Processor ID Register */
> +	VMPIDR_EL2,	/* Virtualization Multiprocessor ID Register */
> +	SCTLR_EL2,	/* System Control Register (EL2) */
> +	ACTLR_EL2,	/* Auxiliary Control Register (EL2) */
> +	HCR_EL2,	/* Hypervisor Configuration Register */
> +	MDCR_EL2,	/* Monitor Debug Configuration Register (EL2) */
> +	CPTR_EL2,	/* Architectural Feature Trap Register (EL2) */
> +	HSTR_EL2,	/* Hypervisor System Trap Register */
> +	HACR_EL2,	/* Hypervisor Auxiliary Control Register */
> +	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
> +	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
> +	TCR_EL2,	/* Translation Control Register (EL2) */
> +	VTTBR_EL2,	/* Virtualization Translation Table Base Register */
> +	VTCR_EL2,	/* Virtualization Translation Control Register */
> +	SPSR_EL2,	/* EL2 saved program status register */
> +	ELR_EL2,	/* EL2 exception link register */
> +	AFSR0_EL2,	/* Auxiliary Fault Status Register 0 (EL2) */
> +	AFSR1_EL2,	/* Auxiliary Fault Status Register 1 (EL2) */
> +	ESR_EL2,	/* Exception Syndrome Register (EL2) */
> +	FAR_EL2,	/* Hypervisor IPA Fault Address Register */
> +	HPFAR_EL2,	/* Hypervisor IPA Fault Address Register */
> +	MAIR_EL2,	/* Memory Attribute Indirection Register (EL2) */
> +	AMAIR_EL2,	/* Auxiliary Memory Attribute Indirection Register (EL2) */
> +	VBAR_EL2,	/* Vector Base Address Register (EL2) */
> +	RVBAR_EL2,	/* Reset Vector Base Address Register */
> +	RMR_EL2,	/* Reset Management Register */
> +	CONTEXTIDR_EL2,	/* Context ID Register (EL2) */
> +	TPIDR_EL2,	/* EL2 Software Thread ID Register */
> +	CNTHCTL_EL2,	/* Counter-timer Hypervisor Control register */
> +	SP_EL2,		/* EL2 Stack Pointer */
> +
>  	NR_SYS_REGS	/* Nothing after this line! */
>  };
>  

Re: [PATCH v3 07/66] KVM: arm64: nv: Handle HCR_EL2.NV system register traps

[Andre Przywara]

On Thu, 10 Dec 2020 15:59:03 +0000
Marc Zyngier <maz@kernel.org> wrote:

Hi,

> From: Jintack Lim <jintack.lim@linaro.org>
> 
> ARM v8.3 introduces a new bit in the HCR_EL2, which is the NV bit. When
> this bit is set, accessing EL2 registers in EL1 traps to EL2. In
> addition, executing the following instructions in EL1 will trap to EL2:
> tlbi, at, eret, and msr/mrs instructions to access SP_EL1. Most of the
> instructions that trap to EL2 with the NV bit were undef at EL1 prior to
> ARM v8.3. The only instruction that was not undef is eret.
> 
> This patch sets up a handler for EL2 registers and SP_EL1 register
> accesses at EL1. The host hypervisor keeps those register values in
> memory, and will emulate their behavior.
> 
> This patch doesn't set the NV bit yet. It will be set in a later patch
> once nested virtualization support is completed.
> 
> Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
> [maz: added SCTLR_EL2 RES0/RES1 handling]
> Signed-off-by: Marc Zyngier <maz@kernel.org>

I compared the system register encodings in the first hunk against the
ARMv8 ARM, they are all fine.
I also checked the last hunk for (copy&paste) typos, all good as well.

Some comments below:

> ---
>  arch/arm64/include/asm/sysreg.h |  44 ++++++++++++-
>  arch/arm64/kvm/sys_regs.c       | 112 ++++++++++++++++++++++++++++++--
>  2 files changed, 150 insertions(+), 6 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
> index 82521cdbfc1c..05b49eafbb49 100644
> --- a/arch/arm64/include/asm/sysreg.h
> +++ b/arch/arm64/include/asm/sysreg.h
> @@ -469,19 +469,50 @@
>  
>  #define SYS_PMCCFILTR_EL0		sys_reg(3, 3, 14, 15, 7)
>  
> +#define SYS_VPIDR_EL2			sys_reg(3, 4, 0, 0, 0)
> +#define SYS_VMPIDR_EL2			sys_reg(3, 4, 0, 0, 5)
> +
>  #define SYS_SCTLR_EL2			sys_reg(3, 4, 1, 0, 0)
> +#define SYS_ACTLR_EL2			sys_reg(3, 4, 1, 0, 1)
> +#define SYS_HCR_EL2			sys_reg(3, 4, 1, 1, 0)
> +#define SYS_MDCR_EL2			sys_reg(3, 4, 1, 1, 1)
> +#define SYS_CPTR_EL2			sys_reg(3, 4, 1, 1, 2)
> +#define SYS_HSTR_EL2			sys_reg(3, 4, 1, 1, 3)
> +#define SYS_HACR_EL2			sys_reg(3, 4, 1, 1, 7)
> +
>  #define SYS_ZCR_EL2			sys_reg(3, 4, 1, 2, 0)
> +
> +#define SYS_TTBR0_EL2			sys_reg(3, 4, 2, 0, 0)
> +#define SYS_TTBR1_EL2			sys_reg(3, 4, 2, 0, 1)
> +#define SYS_TCR_EL2			sys_reg(3, 4, 2, 0, 2)
> +#define SYS_VTTBR_EL2			sys_reg(3, 4, 2, 1, 0)
> +#define SYS_VTCR_EL2			sys_reg(3, 4, 2, 1, 2)
> +
>  #define SYS_DACR32_EL2			sys_reg(3, 4, 3, 0, 0)
> +
>  #define SYS_SPSR_EL2			sys_reg(3, 4, 4, 0, 0)
>  #define SYS_ELR_EL2			sys_reg(3, 4, 4, 0, 1)
> +#define SYS_SP_EL1			sys_reg(3, 4, 4, 1, 0)
> +
>  #define SYS_IFSR32_EL2			sys_reg(3, 4, 5, 0, 1)
> +#define SYS_AFSR0_EL2			sys_reg(3, 4, 5, 1, 0)
> +#define SYS_AFSR1_EL2			sys_reg(3, 4, 5, 1, 1)
>  #define SYS_ESR_EL2			sys_reg(3, 4, 5, 2, 0)
>  #define SYS_VSESR_EL2			sys_reg(3, 4, 5, 2, 3)
>  #define SYS_FPEXC32_EL2			sys_reg(3, 4, 5, 3, 0)
>  #define SYS_TFSR_EL2			sys_reg(3, 4, 5, 6, 0)
>  #define SYS_FAR_EL2			sys_reg(3, 4, 6, 0, 0)
>  
> -#define SYS_VDISR_EL2			sys_reg(3, 4, 12, 1,  1)
> +#define SYS_FAR_EL2			sys_reg(3, 4, 6, 0, 0)
> +#define SYS_HPFAR_EL2			sys_reg(3, 4, 6, 0, 4)
> +
> +#define SYS_MAIR_EL2			sys_reg(3, 4, 10, 2, 0)
> +#define SYS_AMAIR_EL2			sys_reg(3, 4, 10, 3, 0)
> +
> +#define SYS_VBAR_EL2			sys_reg(3, 4, 12, 0, 0)
> +#define SYS_RVBAR_EL2			sys_reg(3, 4, 12, 0, 1)
> +#define SYS_RMR_EL2			sys_reg(3, 4, 12, 0, 2)
> +#define SYS_VDISR_EL2			sys_reg(3, 4, 12, 1, 1)
>  #define __SYS__AP0Rx_EL2(x)		sys_reg(3, 4, 12, 8, x)
>  #define SYS_ICH_AP0R0_EL2		__SYS__AP0Rx_EL2(0)
>  #define SYS_ICH_AP0R1_EL2		__SYS__AP0Rx_EL2(1)
> @@ -523,15 +554,24 @@
>  #define SYS_ICH_LR14_EL2		__SYS__LR8_EL2(6)
>  #define SYS_ICH_LR15_EL2		__SYS__LR8_EL2(7)
>  
> +#define SYS_CONTEXTIDR_EL2		sys_reg(3, 4, 13, 0, 1)
> +#define SYS_TPIDR_EL2			sys_reg(3, 4, 13, 0, 2)
> +
> +#define SYS_CNTVOFF_EL2			sys_reg(3, 4, 14, 0, 3)
> +#define SYS_CNTHCTL_EL2			sys_reg(3, 4, 14, 1, 0)
> +
>  /* VHE encodings for architectural EL0/1 system registers */
>  #define SYS_SCTLR_EL12			sys_reg(3, 5, 1, 0, 0)
>  #define SYS_CPACR_EL12			sys_reg(3, 5, 1, 0, 2)
>  #define SYS_ZCR_EL12			sys_reg(3, 5, 1, 2, 0)
> +
>  #define SYS_TTBR0_EL12			sys_reg(3, 5, 2, 0, 0)
>  #define SYS_TTBR1_EL12			sys_reg(3, 5, 2, 0, 1)
>  #define SYS_TCR_EL12			sys_reg(3, 5, 2, 0, 2)
> +
>  #define SYS_SPSR_EL12			sys_reg(3, 5, 4, 0, 0)
>  #define SYS_ELR_EL12			sys_reg(3, 5, 4, 0, 1)
> +
>  #define SYS_AFSR0_EL12			sys_reg(3, 5, 5, 1, 0)
>  #define SYS_AFSR1_EL12			sys_reg(3, 5, 5, 1, 1)
>  #define SYS_ESR_EL12			sys_reg(3, 5, 5, 2, 0)
> @@ -549,6 +589,8 @@
>  #define SYS_CNTV_CTL_EL02		sys_reg(3, 5, 14, 3, 1)
>  #define SYS_CNTV_CVAL_EL02		sys_reg(3, 5, 14, 3, 2)
>  
> +#define SYS_SP_EL2			sys_reg(3, 6,  4, 1, 0)
> +
>  /* Common SCTLR_ELx flags. */
>  #define SCTLR_ELx_DSSBS	(BIT(44))
>  #define SCTLR_ELx_ATA	(BIT(43))
> diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
> index 3313dedfa505..c049867a39bc 100644
> --- a/arch/arm64/kvm/sys_regs.c
> +++ b/arch/arm64/kvm/sys_regs.c
> @@ -104,6 +104,57 @@ static u32 get_ccsidr(u32 csselr)
>  	return ccsidr;
>  }
>  
> +static bool access_rw(struct kvm_vcpu *vcpu,
> +		      struct sys_reg_params *p,
> +		      const struct sys_reg_desc *r)
> +{
> +	if (p->is_write)
> +		vcpu_write_sys_reg(vcpu, p->regval, r->reg);
> +	else
> +		p->regval = vcpu_read_sys_reg(vcpu, r->reg);
> +
> +	return true;
> +}
> +
> +static bool access_wi(struct kvm_vcpu *vcpu,
> +		      struct sys_reg_params *p,
> +		      const struct sys_reg_desc *r)
> +{
> +	if (p->is_write)
> +		return ignore_write(vcpu, p);
> +
> +	p->regval = vcpu_read_sys_reg(vcpu, r->reg);
> +	return true;
> +}
> +
> +static bool access_sctlr_el2(struct kvm_vcpu *vcpu,
> +			     struct sys_reg_params *p,
> +			     const struct sys_reg_desc *r)
> +{
> +	if (p->is_write) {
> +		u64 val = p->regval;
> +
> +		if (vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)) {
> +			val &= ~(GENMASK_ULL(63,45) | GENMASK_ULL(34, 32) |

In ARMv8 ARM F.c bits 49-45 are used for the TWE delay value. The
manual says it's RES0 when FEAT_TWED is not implemented, but this is
true for a lot of other feature bits we don't implement? So shall we
let a guest set them, reducing the mask to (63,50)?

> +				 BIT_ULL(17));

The ARMv8 ARM F.c lists bit 9 as RES0 as well for (E2H,TGE)=(1,1).

> +			val |=  SCTLR_EL1_RES1;
> +		} else {
> +			val &= ~(GENMASK_ULL(63,45) | BIT_ULL(42) |
> +				 GENMASK_ULL(39, 38) | GENMASK_ULL(35, 32) |
> +				 BIT_ULL(26) | BIT_ULL(24) | BIT_ULL(20) |
> +				 BIT_ULL(17) | GENMASK_ULL(15, 14) |
> +				 GENMASK(10, 7));
> +			val |=  SCTLR_EL2_RES1;
> +		}
> +
> +		vcpu_write_sys_reg(vcpu, val, r->reg);
> +	} else {
> +		p->regval = vcpu_read_sys_reg(vcpu, r->reg);
> +	}
> +
> +	return true;
> +}
> +
>  /*
>   * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
>   */
> @@ -342,12 +393,9 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu,
>  			    struct sys_reg_params *p,
>  			    const struct sys_reg_desc *r)
>  {
> -	if (p->is_write) {
> -		vcpu_write_sys_reg(vcpu, p->regval, r->reg);
> +	access_rw(vcpu, p, r);
> +	if (p->is_write)
>  		vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
> -	} else {
> -		p->regval = vcpu_read_sys_reg(vcpu, r->reg);
> -	}
>  
>  	trace_trap_reg(__func__, r->reg, p->is_write, p->regval);
>  
> @@ -1314,6 +1362,18 @@ static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
>  	.set_user = set_raz_id_reg,		\
>  }
>  
> +static bool access_sp_el1(struct kvm_vcpu *vcpu,
> +			  struct sys_reg_params *p,
> +			  const struct sys_reg_desc *r)
> +{
> +	if (p->is_write)
> +		__vcpu_sys_reg(vcpu, SP_EL1) = p->regval;
> +	else
> +		p->regval = __vcpu_sys_reg(vcpu, SP_EL1);
> +
> +	return true;
> +}
> +
>  /*
>   * Architected system registers.
>   * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
> @@ -1692,9 +1752,51 @@ static const struct sys_reg_desc sys_reg_descs[] = {
>  	 */
>  	{ SYS_DESC(SYS_PMCCFILTR_EL0), access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 },
>  
> +	{ SYS_DESC(SYS_VPIDR_EL2), access_rw, reset_val, VPIDR_EL2, 0 },
> +	{ SYS_DESC(SYS_VMPIDR_EL2), access_rw, reset_val, VMPIDR_EL2, 0 },
> +
> +	{ SYS_DESC(SYS_SCTLR_EL2), access_sctlr_el2, reset_val, SCTLR_EL2, SCTLR_EL2_RES1 },
> +	{ SYS_DESC(SYS_ACTLR_EL2), access_rw, reset_val, ACTLR_EL2, 0 },
> +	{ SYS_DESC(SYS_HCR_EL2), access_rw, reset_val, HCR_EL2, 0 },
> +	{ SYS_DESC(SYS_MDCR_EL2), access_rw, reset_val, MDCR_EL2, 0 },
> +	{ SYS_DESC(SYS_CPTR_EL2), access_rw, reset_val, CPTR_EL2, CPTR_EL2_RES1 },
> +	{ SYS_DESC(SYS_HSTR_EL2), access_rw, reset_val, HSTR_EL2, 0 },
> +	{ SYS_DESC(SYS_HACR_EL2), access_rw, reset_val, HACR_EL2, 0 },
> +
> +	{ SYS_DESC(SYS_TTBR0_EL2), access_rw, reset_val, TTBR0_EL2, 0 },
> +	{ SYS_DESC(SYS_TTBR1_EL2), access_rw, reset_val, TTBR1_EL2, 0 },
> +	{ SYS_DESC(SYS_TCR_EL2), access_rw, reset_val, TCR_EL2, TCR_EL2_RES1 },
> +	{ SYS_DESC(SYS_VTTBR_EL2), access_rw, reset_val, VTTBR_EL2, 0 },
> +	{ SYS_DESC(SYS_VTCR_EL2), access_rw, reset_val, VTCR_EL2, 0 },
> +
>  	{ SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 },
> +	{ SYS_DESC(SYS_SPSR_EL2), access_rw, reset_val, SPSR_EL2, 0 },
> +	{ SYS_DESC(SYS_ELR_EL2), access_rw, reset_val, ELR_EL2, 0 },
> +	{ SYS_DESC(SYS_SP_EL1), access_sp_el1},
> +
>  	{ SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 },
> +	{ SYS_DESC(SYS_AFSR0_EL2), access_rw, reset_val, AFSR0_EL2, 0 },
> +	{ SYS_DESC(SYS_AFSR1_EL2), access_rw, reset_val, AFSR1_EL2, 0 },
> +	{ SYS_DESC(SYS_ESR_EL2), access_rw, reset_val, ESR_EL2, 0 },
>  	{ SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x700 },
> +
> +	{ SYS_DESC(SYS_FAR_EL2), access_rw, reset_val, FAR_EL2, 0 },
> +	{ SYS_DESC(SYS_HPFAR_EL2), access_rw, reset_val, HPFAR_EL2, 0 },
> +
> +	{ SYS_DESC(SYS_MAIR_EL2), access_rw, reset_val, MAIR_EL2, 0 },
> +	{ SYS_DESC(SYS_AMAIR_EL2), access_rw, reset_val, AMAIR_EL2, 0 },
> +
> +	{ SYS_DESC(SYS_VBAR_EL2), access_rw, reset_val, VBAR_EL2, 0 },
> +	{ SYS_DESC(SYS_RVBAR_EL2), access_rw, reset_val, RVBAR_EL2, 0 },
> +	{ SYS_DESC(SYS_RMR_EL2), access_wi, reset_val, RMR_EL2, 1 },


Why is this WI, exactly? Isn't EL2 the highest implemented EL from a
guest's point of view, and thus a write to RMR_EL2 with bit 1 set should
trigger a reset (to AArch64)?
I see that we don't NEED to implement this register (as we don't
support AArch32), but that should look differently here then?

The rest looks alright to me.

Cheers,
Andre

> +
> +	{ SYS_DESC(SYS_CONTEXTIDR_EL2), access_rw, reset_val, CONTEXTIDR_EL2, 0 },
> +	{ SYS_DESC(SYS_TPIDR_EL2), access_rw, reset_val, TPIDR_EL2, 0 },
> +
> +	{ SYS_DESC(SYS_CNTVOFF_EL2), access_rw, reset_val, CNTVOFF_EL2, 0 },
> +	{ SYS_DESC(SYS_CNTHCTL_EL2), access_rw, reset_val, CNTHCTL_EL2, 0 },
> +
> +	{ SYS_DESC(SYS_SP_EL2), NULL, reset_unknown, SP_EL2 },
>  };
>  
>  static bool trap_dbgidr(struct kvm_vcpu *vcpu,

Re: [PATCH v3 09/66] KVM: arm64: nv: Support virtual EL2 exceptions

[Andre Przywara]

On Thu, 10 Dec 2020 15:59:05 +0000
Marc Zyngier <maz@kernel.org> wrote:

Hi,

> From: Jintack Lim <jintack.lim@linaro.org>
> 
> Support injecting exceptions and performing exception returns to and
> from virtual EL2.  This must be done entirely in software except when
> taking an exception from vEL0 to vEL2 when the virtual HCR_EL2.{E2H,TGE}
> == {1,1}  (a VHE guest hypervisor).
> 
> Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
> Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
> [maz: switch to common exception injection framework]
> Signed-off-by: Marc Zyngier <maz@kernel.org>
> ---
>  arch/arm64/include/asm/kvm_arm.h     |  17 +++
>  arch/arm64/include/asm/kvm_emulate.h |  10 ++
>  arch/arm64/kvm/Makefile              |   2 +-
>  arch/arm64/kvm/emulate-nested.c      | 176 +++++++++++++++++++++++++++
>  arch/arm64/kvm/hyp/exception.c       |  44 +++++--
>  arch/arm64/kvm/inject_fault.c        |  62 ++++++++--
>  arch/arm64/kvm/trace_arm.h           |  59 +++++++++
>  7 files changed, 352 insertions(+), 18 deletions(-)
>  create mode 100644 arch/arm64/kvm/emulate-nested.c
> 
> diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
> index 4e90c2debf70..e9e10e498785 100644
> --- a/arch/arm64/include/asm/kvm_arm.h
> +++ b/arch/arm64/include/asm/kvm_arm.h
> @@ -332,4 +332,21 @@
>  #define CPACR_EL1_TTA		(1 << 28)
>  #define CPACR_EL1_DEFAULT	(CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN)
>  
> +#define kvm_mode_names				\
> +	{ PSR_MODE_EL0t,	"EL0t" },	\
> +	{ PSR_MODE_EL1t,	"EL1t" },	\
> +	{ PSR_MODE_EL1h,	"EL1h" },	\
> +	{ PSR_MODE_EL2t,	"EL2t" },	\
> +	{ PSR_MODE_EL2h,	"EL2h" },	\
> +	{ PSR_MODE_EL3t,	"EL3t" },	\
> +	{ PSR_MODE_EL3h,	"EL3h" },	\
> +	{ PSR_AA32_MODE_USR,	"32-bit USR" },	\
> +	{ PSR_AA32_MODE_FIQ,	"32-bit FIQ" },	\
> +	{ PSR_AA32_MODE_IRQ,	"32-bit IRQ" },	\
> +	{ PSR_AA32_MODE_SVC,	"32-bit SVC" },	\
> +	{ PSR_AA32_MODE_ABT,	"32-bit ABT" },	\
> +	{ PSR_AA32_MODE_HYP,	"32-bit HYP" },	\
> +	{ PSR_AA32_MODE_UND,	"32-bit UND" },	\
> +	{ PSR_AA32_MODE_SYS,	"32-bit SYS" }
> +
>  #endif /* __ARM64_KVM_ARM_H__ */
> diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
> index e3e22d364dc9..deffd3cc4443 100644
> --- a/arch/arm64/include/asm/kvm_emulate.h
> +++ b/arch/arm64/include/asm/kvm_emulate.h
> @@ -33,6 +33,12 @@ enum exception_type {
>  	except_type_serror	= 0x180,
>  };
>  
> +#define kvm_exception_type_names		\
> +	{ except_type_sync,	"SYNC"   },	\
> +	{ except_type_irq,	"IRQ"    },	\
> +	{ except_type_fiq,	"FIQ"    },	\
> +	{ except_type_serror,	"SERROR" }
> +
>  bool kvm_condition_valid32(const struct kvm_vcpu *vcpu);
>  void kvm_skip_instr32(struct kvm_vcpu *vcpu);
>  
> @@ -41,6 +47,10 @@ void kvm_inject_vabt(struct kvm_vcpu *vcpu);
>  void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
>  void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
>  
> +void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu);
> +int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2);
> +int kvm_inject_nested_irq(struct kvm_vcpu *vcpu);
> +
>  static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
>  {
>  	return !(vcpu->arch.hcr_el2 & HCR_RW);
> diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
> index 60fd181df624..672acdf1e993 100644
> --- a/arch/arm64/kvm/Makefile
> +++ b/arch/arm64/kvm/Makefile
> @@ -17,11 +17,11 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
>  	 guest.o debug.o reset.o sys_regs.o \
>  	 vgic-sys-reg-v3.o fpsimd.o pmu.o \
>  	 arch_timer.o \
> +	 emulate-nested.o \
>  	 vgic/vgic.o vgic/vgic-init.o \
>  	 vgic/vgic-irqfd.o vgic/vgic-v2.o \
>  	 vgic/vgic-v3.o vgic/vgic-v4.o \
>  	 vgic/vgic-mmio.o vgic/vgic-mmio-v2.o \
>  	 vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \
>  	 vgic/vgic-its.o vgic/vgic-debug.o
> -
>  kvm-$(CONFIG_KVM_ARM_PMU)  += pmu-emul.o
> diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
> new file mode 100644
> index 000000000000..ee91bcd925d8
> --- /dev/null
> +++ b/arch/arm64/kvm/emulate-nested.c
> @@ -0,0 +1,176 @@
> +/*
> + * Copyright (C) 2016 - Linaro and Columbia University
> + * Author: Jintack Lim <jintack.lim@linaro.org>
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 as
> + * published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
> + * GNU General Public License for more details.
> + *
> + * You should have received a copy of the GNU General Public License
> + * along with this program.  If not, see <http://www.gnu.org/licenses/>.
> + */
> +
> +#include <linux/kvm.h>
> +#include <linux/kvm_host.h>
> +
> +#include <asm/kvm_emulate.h>
> +#include <asm/kvm_nested.h>
> +
> +#include "hyp/include/hyp/adjust_pc.h"
> +
> +#include "trace.h"
> +
> +void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
> +{
> +	u64 spsr, elr, mode;
> +	bool direct_eret;
> +
> +	/*
> +	 * Going through the whole put/load motions is a waste of time
> +	 * if this is a VHE guest hypervisor returning to its own
> +	 * userspace, or the hypervisor performing a local exception
> +	 * return. No need to save/restore registers, no need to
> +	 * switch S2 MMU. Just do the canonical ERET.
> +	 */
> +	spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2);
> +	mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT);
> +
> +	direct_eret  = (mode == PSR_MODE_EL0t &&
> +			vcpu_el2_e2h_is_set(vcpu) &&
> +			vcpu_el2_tge_is_set(vcpu));
> +	direct_eret |= (mode == PSR_MODE_EL2h || mode == PSR_MODE_EL2t);
> +
> +	if (direct_eret) {
> +		*vcpu_pc(vcpu) = vcpu_read_sys_reg(vcpu, ELR_EL2);
> +		*vcpu_cpsr(vcpu) = spsr;
> +		trace_kvm_nested_eret(vcpu, *vcpu_pc(vcpu), spsr);
> +		return;
> +	}
> +
> +	preempt_disable();
> +	kvm_arch_vcpu_put(vcpu);
> +
> +	elr = __vcpu_sys_reg(vcpu, ELR_EL2);
> +
> +	trace_kvm_nested_eret(vcpu, elr, spsr);
> +
> +	/*
> +	 * Note that the current exception level is always the virtual EL2,
> +	 * since we set HCR_EL2.NV bit only when entering the virtual EL2.
> +	 */
> +	*vcpu_pc(vcpu) = elr;
> +	*vcpu_cpsr(vcpu) = spsr;
> +
> +	kvm_arch_vcpu_load(vcpu, smp_processor_id());
> +	preempt_enable();
> +}
> +
> +static void kvm_inject_el2_exception(struct kvm_vcpu *vcpu, u64 esr_el2,
> +				     enum exception_type type)
> +{
> +	trace_kvm_inject_nested_exception(vcpu, esr_el2, type);
> +
> +	switch (type) {
> +	case except_type_sync:
> +		vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_ELx_SYNC;
> +		break;
> +	case except_type_irq:
> +		vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_ELx_IRQ;
> +		break;
> +	default:
> +		WARN_ONCE(1, "Unsupported EL2 exception injection %d\n", type);
> +	}
> +
> +	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL2		|
> +			     KVM_ARM64_PENDING_EXCEPTION);
> +
> +	vcpu_write_sys_reg(vcpu, esr_el2, ESR_EL2);
> +}
> +
> +/*
> + * Emulate taking an exception to EL2.
> + * See ARM ARM J8.1.2 AArch64.TakeException()
> + */
> +static int kvm_inject_nested(struct kvm_vcpu *vcpu, u64 esr_el2,
> +			     enum exception_type type)
> +{
> +	u64 pstate, mode;
> +	bool direct_inject;
> +
> +	if (!nested_virt_in_use(vcpu)) {
> +		kvm_err("Unexpected call to %s for the non-nesting configuration\n",
> +				__func__);
> +		return -EINVAL;
> +	}
> +
> +	/*
> +	 * As for ERET, we can avoid doing too much on the injection path by
> +	 * checking that we either took the exception from a VHE host
> +	 * userspace or from vEL2. In these cases, there is no change in
> +	 * translation regime (or anything else), so let's do as little as
> +	 * possible.
> +	 */
> +	pstate = *vcpu_cpsr(vcpu);
> +	mode = pstate & (PSR_MODE_MASK | PSR_MODE32_BIT);
> +
> +	direct_inject  = (mode == PSR_MODE_EL0t &&
> +			  vcpu_el2_e2h_is_set(vcpu) &&
> +			  vcpu_el2_tge_is_set(vcpu));
> +	direct_inject |= (mode == PSR_MODE_EL2h || mode == PSR_MODE_EL2t);
> +
> +	if (direct_inject) {
> +		kvm_inject_el2_exception(vcpu, esr_el2, type);
> +		return 1;
> +	}
> +
> +	preempt_disable();
> +	kvm_arch_vcpu_put(vcpu);
> +
> +	kvm_inject_el2_exception(vcpu, esr_el2, type);
> +
> +	/*
> +	 * A hard requirement is that a switch between EL1 and EL2
> +	 * contexts has to happen between a put/load, so that we can
> +	 * pick the correct timer and interrupt configuration, among
> +	 * other things.
> +	 *
> +	 * Make sure the exception actually took place before we load
> +	 * the new context.
> +	 */
> +	__adjust_pc(vcpu);
> +
> +	kvm_arch_vcpu_load(vcpu, smp_processor_id());
> +	preempt_enable();
> +
> +	return 1;
> +}
> +
> +int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2)
> +{
> +	return kvm_inject_nested(vcpu, esr_el2, except_type_sync);
> +}
> +
> +int kvm_inject_nested_irq(struct kvm_vcpu *vcpu)
> +{
> +	/*
> +	 * Do not inject an irq if the:
> +	 *  - Current exception level is EL2, and
> +	 *  - virtual HCR_EL2.TGE == 0
> +	 *  - virtual HCR_EL2.IMO == 0
> +	 *
> +	 * See Table D1-17 "Physical interrupt target and masking when EL3 is
> +	 * not implemented and EL2 is implemented" in ARM DDI 0487C.a.
> +	 */
> +
> +	if (vcpu_mode_el2(vcpu) && !vcpu_el2_tge_is_set(vcpu) &&
> +	    !(__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_IMO))
> +		return 1;
> +
> +	/* esr_el2 value doesn't matter for exits due to irqs. */
> +	return kvm_inject_nested(vcpu, 0, except_type_irq);
> +}
> diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
> index 73629094f903..7c8b3681dafd 100644
> --- a/arch/arm64/kvm/hyp/exception.c
> +++ b/arch/arm64/kvm/hyp/
> @@ -22,7 +22,9 @@ static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
>  {
>  	u64 val;
>  
> -	if (__vcpu_read_sys_reg_from_cpu(reg, &val))
> +	if (unlikely(nested_virt_in_use(vcpu)))
> +		return vcpu_read_sys_reg(vcpu, reg);
> +	else if (__vcpu_read_sys_reg_from_cpu(reg, &val))
>  		return val;
>  
>  	return __vcpu_sys_reg(vcpu, reg);
> @@ -30,14 +32,26 @@ static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
>  
>  static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
>  {
> -	if (__vcpu_write_sys_reg_to_cpu(val, reg))
> +	if (unlikely(nested_virt_in_use(vcpu)))
> +		vcpu_write_sys_reg(vcpu, val, reg);
> +	else if (__vcpu_write_sys_reg_to_cpu(val, reg))
>  		return;
>  
>  	 __vcpu_sys_reg(vcpu, reg) = val;
>  }
>  
> -static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, u64 val)
> +static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
> +			      u64 val)
>  {
> +	if (unlikely(nested_virt_in_use(vcpu))) {
> +		if (target_mode == PSR_MODE_EL1h)
> +			vcpu_write_sys_reg(vcpu, val, SPSR_EL1);
> +		else
> +			vcpu_write_sys_reg(vcpu, val, SPSR_EL2);
> +
> +		return;
> +	}
> +
>  	write_sysreg_el1(val, SYS_SPSR);
>  }
>  
> @@ -97,6 +111,11 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
>  		sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1);
>  		__vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1);
>  		break;
> +	case PSR_MODE_EL2h:
> +		vbar = __vcpu_read_sys_reg(vcpu, VBAR_EL2);
> +		sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL2);
> +		__vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL2);
> +		break;
>  	default:
>  		/* Don't do that */
>  		BUG();
> @@ -148,7 +167,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
>  	new |= target_mode;
>  
>  	*vcpu_cpsr(vcpu) = new;
> -	__vcpu_write_spsr(vcpu, old);
> +	__vcpu_write_spsr(vcpu, target_mode, old);
>  }
>  
>  /*
> @@ -319,11 +338,22 @@ void kvm_inject_exception(struct kvm_vcpu *vcpu)
>  		      KVM_ARM64_EXCEPT_AA64_EL1):
>  			enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync);
>  			break;
> +
> +		case (KVM_ARM64_EXCEPT_AA64_ELx_SYNC |
> +		      KVM_ARM64_EXCEPT_AA64_EL2):
> +			enter_exception64(vcpu, PSR_MODE_EL2h, except_type_sync);
> +			break;
> +
> +		case (KVM_ARM64_EXCEPT_AA64_ELx_IRQ |
> +		      KVM_ARM64_EXCEPT_AA64_EL2):
> +			enter_exception64(vcpu, PSR_MODE_EL2h, except_type_irq);
> +			break;
> +
>  		default:
>  			/*
> -			 * Only EL1_SYNC makes sense so far, EL2_{SYNC,IRQ}
> -			 * will be implemented at some point. Everything
> -			 * else gets silently ignored.
> +			 * Only EL1_SYNC and EL2_{SYNC,IRQ} makes
> +			 * sense so far. Everything else gets silently
> +			 * ignored.
>  			 */
>  			break;
>  		}
> diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
> index b47df73e98d7..530562eb09fd 100644
> --- a/arch/arm64/kvm/inject_fault.c
> +++ b/arch/arm64/kvm/inject_fault.c
> @@ -14,17 +14,50 @@
>  #include <asm/kvm_emulate.h>
>  #include <asm/esr.h>
>  
> +static void pend_sync_exception(struct kvm_vcpu *vcpu)
> +{
> +	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_ELx_SYNC	|
> +			     KVM_ARM64_PENDING_EXCEPTION);
> +
> +	/* If not nesting, EL1 is the only possible exception target */
> +	if (likely(!nested_virt_in_use(vcpu))) {

This breaks compilation for the next 14 patches, because
nested_virt_in_use() is unknown here. Patch 23/66 fixes this by adding
kvm_nested.h to kvm_emulate.h.
Shall we do this already in this patch here, or pull in kvm_nested.h in
every C file we use nested_virt_in_use(), like exception.c above?

Cheers,
Andre

> +		vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_EL1;
> +		return;
> +	}
> +
> +	/*
> +	 * With NV, we need to pick between EL1 and EL2. Note that we
> +	 * never deal with a nesting exception here, hence never
> +	 * changing context, and the exception itself can be delayed
> +	 * until the next entry.
> +	 */
> +	switch(*vcpu_cpsr(vcpu) & PSR_MODE_MASK) {
> +	case PSR_MODE_EL2h:
> +	case PSR_MODE_EL2t:
> +		vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_EL2;
> +		break;
> +	case PSR_MODE_EL1h:
> +	case PSR_MODE_EL1t:
> +		vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_EL1;
> +		break;
> +	case PSR_MODE_EL0t:
> +		if (vcpu_el2_tge_is_set(vcpu) & HCR_TGE)
> +			vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_EL2;
> +		else
> +			vcpu->arch.flags |= KVM_ARM64_EXCEPT_AA64_EL1;
> +		break;
> +	default:
> +		BUG();
> +	}
> +}
> +
>  static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
>  {
>  	unsigned long cpsr = *vcpu_cpsr(vcpu);
>  	bool is_aarch32 = vcpu_mode_is_32bit(vcpu);
>  	u32 esr = 0;
>  
> -	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1		|
> -			     KVM_ARM64_EXCEPT_AA64_ELx_SYNC	|
> -			     KVM_ARM64_PENDING_EXCEPTION);
> -
> -	vcpu_write_sys_reg(vcpu, addr, FAR_EL1);
> +	pend_sync_exception(vcpu);
>  
>  	/*
>  	 * Build an {i,d}abort, depending on the level and the
> @@ -45,16 +78,22 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
>  	if (!is_iabt)
>  		esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT;
>  
> -	vcpu_write_sys_reg(vcpu, esr | ESR_ELx_FSC_EXTABT, ESR_EL1);
> +	esr |= ESR_ELx_FSC_EXTABT;
> +
> +	if (vcpu->arch.flags & KVM_ARM64_EXCEPT_AA64_EL1) {
> +		vcpu_write_sys_reg(vcpu, addr, FAR_EL1);
> +		vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
> +	} else {
> +		vcpu_write_sys_reg(vcpu, addr, FAR_EL2);
> +		vcpu_write_sys_reg(vcpu, esr, ESR_EL2);
> +	}
>  }
>  
>  static void inject_undef64(struct kvm_vcpu *vcpu)
>  {
>  	u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
>  
> -	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1		|
> -			     KVM_ARM64_EXCEPT_AA64_ELx_SYNC	|
> -			     KVM_ARM64_PENDING_EXCEPTION);
> +	pend_sync_exception(vcpu);
>  
>  	/*
>  	 * Build an unknown exception, depending on the instruction
> @@ -63,7 +102,10 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
>  	if (kvm_vcpu_trap_il_is32bit(vcpu))
>  		esr |= ESR_ELx_IL;
>  
> -	vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
> +	if (vcpu->arch.flags & KVM_ARM64_EXCEPT_AA64_EL1)
> +		vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
> +	else
> +		vcpu_write_sys_reg(vcpu, esr, ESR_EL2);
>  }
>  
>  #define DFSR_FSC_EXTABT_LPAE	0x10
> diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h
> index ff0444352bba..5707011c4f47 100644
> --- a/arch/arm64/kvm/trace_arm.h
> +++ b/arch/arm64/kvm/trace_arm.h
> @@ -2,6 +2,7 @@
>  #if !defined(_TRACE_ARM_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
>  #define _TRACE_ARM_ARM64_KVM_H
>  
> +#include <asm/kvm_emulate.h>
>  #include <kvm/arm_arch_timer.h>
>  #include <linux/tracepoint.h>
>  
> @@ -367,6 +368,64 @@ TRACE_EVENT(kvm_timer_emulate,
>  		  __entry->timer_idx, __entry->should_fire)
>  );
>  
> +TRACE_EVENT(kvm_nested_eret,
> +	TP_PROTO(struct kvm_vcpu *vcpu, unsigned long elr_el2,
> +		 unsigned long spsr_el2),
> +	TP_ARGS(vcpu, elr_el2, spsr_el2),
> +
> +	TP_STRUCT__entry(
> +		__field(struct kvm_vcpu *,	vcpu)
> +		__field(unsigned long,		elr_el2)
> +		__field(unsigned long,		spsr_el2)
> +		__field(unsigned long,		target_mode)
> +		__field(unsigned long,		hcr_el2)
> +	),
> +
> +	TP_fast_assign(
> +		__entry->vcpu = vcpu;
> +		__entry->elr_el2 = elr_el2;
> +		__entry->spsr_el2 = spsr_el2;
> +		__entry->target_mode = spsr_el2 & (PSR_MODE_MASK | PSR_MODE32_BIT);
> +		__entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2);
> +	),
> +
> +	TP_printk("elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx",
> +		  __entry->elr_el2, __entry->spsr_el2,
> +		  __print_symbolic(__entry->target_mode, kvm_mode_names),
> +		  __entry->hcr_el2)
> +);
> +
> +TRACE_EVENT(kvm_inject_nested_exception,
> +	TP_PROTO(struct kvm_vcpu *vcpu, u64 esr_el2, int type),
> +	TP_ARGS(vcpu, esr_el2, type),
> +
> +	TP_STRUCT__entry(
> +		__field(struct kvm_vcpu *,		vcpu)
> +		__field(unsigned long,			esr_el2)
> +		__field(int,				type)
> +		__field(unsigned long,			spsr_el2)
> +		__field(unsigned long,			pc)
> +		__field(unsigned long,			source_mode)
> +		__field(unsigned long,			hcr_el2)
> +	),
> +
> +	TP_fast_assign(
> +		__entry->vcpu = vcpu;
> +		__entry->esr_el2 = esr_el2;
> +		__entry->type = type;
> +		__entry->spsr_el2 = *vcpu_cpsr(vcpu);
> +		__entry->pc = *vcpu_pc(vcpu);
> +		__entry->source_mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
> +		__entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2);
> +	),
> +
> +	TP_printk("%s: esr_el2 0x%lx elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx",
> +		  __print_symbolic(__entry->type, kvm_exception_type_names),
> +		  __entry->esr_el2, __entry->pc, __entry->spsr_el2,
> +		  __print_symbolic(__entry->source_mode, kvm_mode_names),
> +		  __entry->hcr_el2)
> +);
> +
>  #endif /* _TRACE_ARM_ARM64_KVM_H */
>  
>  #undef TRACE_INCLUDE_PATH

Re: [PATCH v3 00/66] KVM: arm64: ARMv8.3/8.4 Nested Virtualization support

[Haibo Xu]

Kindly ping!

On Thu, 21 Jan 2021 at 11:03, Haibo Xu <haibo.xu@linaro.org> wrote:
>
> Re-send in case the previous email was blocked for the inlined hyper-link.
>
> Hi Marc,
>
> I have tried to enable the NV support in Qemu, and now I can
> successfully boot a L2 guest
> in Qemu KVM mode.
>
> This patch series looks good from the Qemu side except for two minor
> requirements:
> (1) Qemu will check whether a feature was supported by the KVM cap
> when the user tries
>      to enable it in the command line, so a new capability was
> prefered for the NV(KVM_CAP_ARM_NV?).
> (2) According to the Documentation/virt/kvm/api.rst, userspace can
> call KVM_ARM_VCPU_INIT
>      multiple times for a given vcpu, but the kvm_vcpu_init_nested()
> do have some issue when
>      called multiple times(please refer to the detailed comments in patch 63)
>
> Regards,
> Haibo
>
> On Fri, 11 Dec 2020 at 00:00, Marc Zyngier <maz@kernel.org> wrote:
> >
> > This is a rework of the NV series that I posted 10 months ago[1], as a
> > lot of the KVM code has changed since, and the series apply anymore
> > (not that anybody really cares as the the HW is, as usual, made of
> > unobtainium...).
> >
> > From the previous version:
> >
> > - Integration with the new page-table code
> > - New exception injection code
> > - No more messing with the nVHE code
> > - No AArch32!!!!
> > - Rebased on v5.10-rc4 + kvmarm/next for 5.11
> >
> > From a functionality perspective, you can expect a L2 guest to work,
> > but don't even think of L3, as we only partially emulate the
> > ARMv8.{3,4}-NV extensions themselves. Same thing for vgic, debug, PMU,
> > as well as anything that would require a Stage-1 PTW. What we want to
> > achieve is that with NV disabled, there is no performance overhead and
> > no regression.
> >
> > The series is roughly divided in 5 parts: exception handling, memory
> > virtualization, interrupts and timers for ARMv8.3, followed by the
> > ARMv8.4 support. There are of course some dependencies, but you'll
> > hopefully get the gist of it.
> >
> > For the most courageous of you, I've put out a branch[2]. Of course,
> > you'll need some userspace. Andre maintains a hacked version of
> > kvmtool[3] that takes a --nested option, allowing the guest to be
> > started at EL2. You can run the whole stack in the Foundation
> > model. Don't be in a hurry ;-).
> >
> > And to be clear: although Jintack and Christoffer have written tons of
> > the stuff originaly, I'm the one responsible for breaking it!
> >
> > [1] https://lore.kernel.org/r/20200211174938.27809-1-maz@kernel.org
> > [2] git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms.git kvm-arm64/nv-5.11.-WIP
> > [3] git://linux-arm.org/kvmtool.git nv/nv-wip-5.2-rc5
> >
> > Andre Przywara (1):
> >   KVM: arm64: nv: vgic: Allow userland to set VGIC maintenance IRQ
> >
> > Christoffer Dall (15):
> >   KVM: arm64: nv: Introduce nested virtualization VCPU feature
> >   KVM: arm64: nv: Reset VCPU to EL2 registers if VCPU nested virt is set
> >   KVM: arm64: nv: Allow userspace to set PSR_MODE_EL2x
> >   KVM: arm64: nv: Add nested virt VCPU primitives for vEL2 VCPU state
> >   KVM: arm64: nv: Reset VMPIDR_EL2 and VPIDR_EL2 to sane values
> >   KVM: arm64: nv: Handle trapped ERET from virtual EL2
> >   KVM: arm64: nv: Emulate PSTATE.M for a guest hypervisor
> >   KVM: arm64: nv: Trap EL1 VM register accesses in virtual EL2
> >   KVM: arm64: nv: Only toggle cache for virtual EL2 when SCTLR_EL2
> >     changes
> >   KVM: arm64: nv: Implement nested Stage-2 page table walk logic
> >   KVM: arm64: nv: Unmap/flush shadow stage 2 page tables
> >   KVM: arm64: nv: arch_timer: Support hyp timer emulation
> >   KVM: arm64: nv: vgic: Emulate the HW bit in software
> >   KVM: arm64: nv: Add nested GICv3 tracepoints
> >   KVM: arm64: nv: Sync nested timer state with ARMv8.4
> >
> > Jintack Lim (19):
> >   arm64: Add ARM64_HAS_NESTED_VIRT cpufeature
> >   KVM: arm64: nv: Handle HCR_EL2.NV system register traps
> >   KVM: arm64: nv: Support virtual EL2 exceptions
> >   KVM: arm64: nv: Inject HVC exceptions to the virtual EL2
> >   KVM: arm64: nv: Trap SPSR_EL1, ELR_EL1 and VBAR_EL1 from virtual EL2
> >   KVM: arm64: nv: Trap CPACR_EL1 access in virtual EL2
> >   KVM: arm64: nv: Handle PSCI call via smc from the guest
> >   KVM: arm64: nv: Respect virtual HCR_EL2.TWX setting
> >   KVM: arm64: nv: Respect virtual CPTR_EL2.{TFP,FPEN} settings
> >   KVM: arm64: nv: Respect the virtual HCR_EL2.NV bit setting
> >   KVM: arm64: nv: Respect virtual HCR_EL2.TVM and TRVM settings
> >   KVM: arm64: nv: Respect the virtual HCR_EL2.NV1 bit setting
> >   KVM: arm64: nv: Emulate EL12 register accesses from the virtual EL2
> >   KVM: arm64: nv: Configure HCR_EL2 for nested virtualization
> >   KVM: arm64: nv: Introduce sys_reg_desc.forward_trap
> >   KVM: arm64: nv: Set a handler for the system instruction traps
> >   KVM: arm64: nv: Trap and emulate AT instructions from virtual EL2
> >   KVM: arm64: nv: Trap and emulate TLBI instructions from virtual EL2
> >   KVM: arm64: nv: Nested GICv3 Support
> >
> > Marc Zyngier (31):
> >   KVM: arm64: nv: Add EL2 system registers to vcpu context
> >   KVM: arm64: nv: Add non-VHE-EL2->EL1 translation helpers
> >   KVM: arm64: nv: Handle virtual EL2 registers in
> >     vcpu_read/write_sys_reg()
> >   KVM: arm64: nv: Handle SPSR_EL2 specially
> >   KVM: arm64: nv: Handle HCR_EL2.E2H specially
> >   KVM: arm64: nv: Save/Restore vEL2 sysregs
> >   KVM: arm64: nv: Forward debug traps to the nested guest
> >   KVM: arm64: nv: Filter out unsupported features from ID regs
> >   KVM: arm64: nv: Hide RAS from nested guests
> >   KVM: arm64: nv: Support multiple nested Stage-2 mmu structures
> >   KVM: arm64: nv: Handle shadow stage 2 page faults
> >   KVM: arm64: nv: Restrict S2 RD/WR permissions to match the guest's
> >   KVM: arm64: nv: Fold guest's HCR_EL2 configuration into the host's
> >   KVM: arm64: nv: Add handling of EL2-specific timer registers
> >   KVM: arm64: nv: Load timer before the GIC
> >   KVM: arm64: nv: Don't load the GICv4 context on entering a nested
> >     guest
> >   KVM: arm64: nv: Implement maintenance interrupt forwarding
> >   KVM: arm64: nv: Allow userspace to request KVM_ARM_VCPU_NESTED_VIRT
> >   KVM: arm64: nv: Add handling of ARMv8.4-TTL TLB invalidation
> >   KVM: arm64: nv: Invalidate TLBs based on shadow S2 TTL-like
> >     information
> >   KVM: arm64: Allow populating S2 SW bits
> >   KVM: arm64: nv: Tag shadow S2 entries with nested level
> >   KVM: arm64: nv: Add include containing the VNCR_EL2 offsets
> >   KVM: arm64: Map VNCR-capable registers to a separate page
> >   KVM: arm64: nv: Move nested vgic state into the sysreg file
> >   KVM: arm64: Add ARMv8.4 Enhanced Nested Virt cpufeature
> >   KVM: arm64: nv: Synchronize PSTATE early on exit
> >   KVM: arm64: nv: Allocate VNCR page when required
> >   KVM: arm64: nv: Enable ARMv8.4-NV support
> >   KVM: arm64: nv: Fast-track 'InHost' exception returns
> >   KVM: arm64: nv: Fast-track EL1 TLBIs for VHE guests
> >
> >  .../admin-guide/kernel-parameters.txt         |    4 +
> >  .../virt/kvm/devices/arm-vgic-v3.rst          |   12 +-
> >  arch/arm64/include/asm/cpucaps.h              |    2 +
> >  arch/arm64/include/asm/esr.h                  |    6 +
> >  arch/arm64/include/asm/kvm_arm.h              |   28 +-
> >  arch/arm64/include/asm/kvm_asm.h              |    4 +
> >  arch/arm64/include/asm/kvm_emulate.h          |  145 +-
> >  arch/arm64/include/asm/kvm_host.h             |  175 ++-
> >  arch/arm64/include/asm/kvm_hyp.h              |    2 +
> >  arch/arm64/include/asm/kvm_mmu.h              |   17 +-
> >  arch/arm64/include/asm/kvm_nested.h           |  152 ++
> >  arch/arm64/include/asm/kvm_pgtable.h          |   10 +
> >  arch/arm64/include/asm/sysreg.h               |  104 +-
> >  arch/arm64/include/asm/vncr_mapping.h         |   73 +
> >  arch/arm64/include/uapi/asm/kvm.h             |    2 +
> >  arch/arm64/kernel/cpufeature.c                |   35 +
> >  arch/arm64/kvm/Makefile                       |    4 +-
> >  arch/arm64/kvm/arch_timer.c                   |  189 ++-
> >  arch/arm64/kvm/arm.c                          |   34 +-
> >  arch/arm64/kvm/at.c                           |  231 ++++
> >  arch/arm64/kvm/emulate-nested.c               |  186 +++
> >  arch/arm64/kvm/guest.c                        |    6 +
> >  arch/arm64/kvm/handle_exit.c                  |   81 +-
> >  arch/arm64/kvm/hyp/exception.c                |   44 +-
> >  arch/arm64/kvm/hyp/include/hyp/switch.h       |   31 +-
> >  arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h    |   28 +-
> >  arch/arm64/kvm/hyp/nvhe/switch.c              |   10 +-
> >  arch/arm64/kvm/hyp/nvhe/sysreg-sr.c           |    2 +-
> >  arch/arm64/kvm/hyp/pgtable.c                  |    6 +
> >  arch/arm64/kvm/hyp/vgic-v3-sr.c               |    2 +-
> >  arch/arm64/kvm/hyp/vhe/switch.c               |  207 ++-
> >  arch/arm64/kvm/hyp/vhe/sysreg-sr.c            |  125 +-
> >  arch/arm64/kvm/hyp/vhe/tlb.c                  |   83 ++
> >  arch/arm64/kvm/inject_fault.c                 |   62 +-
> >  arch/arm64/kvm/mmu.c                          |  183 ++-
> >  arch/arm64/kvm/nested.c                       |  908 ++++++++++++
> >  arch/arm64/kvm/reset.c                        |   14 +-
> >  arch/arm64/kvm/sys_regs.c                     | 1226 ++++++++++++++++-
> >  arch/arm64/kvm/sys_regs.h                     |    6 +
> >  arch/arm64/kvm/trace_arm.h                    |   65 +-
> >  arch/arm64/kvm/vgic/vgic-init.c               |   30 +
> >  arch/arm64/kvm/vgic/vgic-kvm-device.c         |   22 +
> >  arch/arm64/kvm/vgic/vgic-nested-trace.h       |  137 ++
> >  arch/arm64/kvm/vgic/vgic-v3-nested.c          |  240 ++++
> >  arch/arm64/kvm/vgic/vgic-v3.c                 |   39 +-
> >  arch/arm64/kvm/vgic/vgic.c                    |   44 +
> >  arch/arm64/kvm/vgic/vgic.h                    |   10 +
> >  include/kvm/arm_arch_timer.h                  |    7 +
> >  include/kvm/arm_vgic.h                        |   16 +
> >  tools/arch/arm/include/uapi/asm/kvm.h         |    1 +
> >  50 files changed, 4890 insertions(+), 160 deletions(-)
> >  create mode 100644 arch/arm64/include/asm/kvm_nested.h
> >  create mode 100644 arch/arm64/include/asm/vncr_mapping.h
> >  create mode 100644 arch/arm64/kvm/at.c
> >  create mode 100644 arch/arm64/kvm/emulate-nested.c
> >  create mode 100644 arch/arm64/kvm/nested.c
> >  create mode 100644 arch/arm64/kvm/vgic/vgic-nested-trace.h
> >  create mode 100644 arch/arm64/kvm/vgic/vgic-v3-nested.c
> >
> > --
> > 2.29.2
> >
> > _______________________________________________
> > kvmarm mailing list
> > kvmarm@lists.cs.columbia.edu
> > https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

Re: [PATCH v3 33/66] KVM: arm64: nv: Support multiple nested Stage-2 mmu structures

[Marc Zyngier]

On Thu, 21 Jan 2021 02:59:13 +0000,
Haibo Xu <haibo.xu@linaro.org> wrote:
> 
> On Fri, 11 Dec 2020 at 00:04, Marc Zyngier <maz@kernel.org> wrote:

[...]

> > diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
> > index 9fb44bc7db3f..8e85d2ef24d9 100644
> > --- a/arch/arm64/kvm/nested.c
> > +++ b/arch/arm64/kvm/nested.c
> > @@ -19,12 +19,177 @@
> >  #include <linux/kvm.h>
> >  #include <linux/kvm_host.h>
> >
> > +#include <asm/kvm_arm.h>
> >  #include <asm/kvm_emulate.h>
> > +#include <asm/kvm_mmu.h>
> >  #include <asm/kvm_nested.h>
> >  #include <asm/sysreg.h>
> >
> >  #include "sys_regs.h"
> >
> > +void kvm_init_nested(struct kvm *kvm)
> > +{
> > +       kvm->arch.nested_mmus = NULL;
> > +       kvm->arch.nested_mmus_size = 0;
> > +}
> > +
> > +int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
> > +{
> > +       struct kvm *kvm = vcpu->kvm;
> > +       struct kvm_s2_mmu *tmp;
> > +       int num_mmus;
> > +       int ret = -ENOMEM;
> > +
> > +       if (!test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features))
> > +               return 0;
> > +
> > +       if (!cpus_have_final_cap(ARM64_HAS_NESTED_VIRT))
> > +               return -EINVAL;
> 
> nit: returning a "not supported" kind of errno?

I think this is consistent with what we otherwise return when there is
a mismatch between requested features from userspace and host
capabilities (such as asking for a 32bit guest on a 64bit only CPU).

What seems to be missing though is a way to *advertise* the feature to
userspace as such:

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 97d377265d8e..0225b81d3434 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -243,6 +243,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ARM_EL1_32BIT:
 		r = cpus_have_const_cap(ARM64_HAS_32BIT_EL1);
 		break;
+	case KVM_CAP_ARM_EL2:
+		r = cpus_have_const_cap(ARM64_HAS_NESTED_VIRT);
+		break;
 	case KVM_CAP_GUEST_DEBUG_HW_BPS:
 		r = get_num_brps();
 		break;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 374c67875cdb..555a60ac00d8 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1058,6 +1058,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
 #define KVM_CAP_SYS_HYPERV_CPUID 191
 #define KVM_CAP_DIRTY_LOG_RING 192
+#define KVM_CAP_ARM_EL2 193
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

Thanks,

	M.

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

Re: [PATCH v3 63/66] KVM: arm64: nv: Allocate VNCR page when required

[Marc Zyngier]

On Thu, 21 Jan 2021 02:47:45 +0000,
Haibo Xu <haibo.xu@linaro.org> wrote:
> 
> On Fri, 11 Dec 2020 at 00:04, Marc Zyngier <maz@kernel.org> wrote:
> >
> > If running a NV guest on an ARMv8.4-NV capable system, let's
> > allocate an additional page that will be used by the hypervisor
> > to fulfill system register accesses.
> >
> > Signed-off-by: Marc Zyngier <maz@kernel.org>
> > ---
> >  arch/arm64/include/asm/kvm_host.h | 3 ++-
> >  arch/arm64/kvm/nested.c           | 8 ++++++++
> >  arch/arm64/kvm/reset.c            | 1 +
> >  3 files changed, 11 insertions(+), 1 deletion(-)
> >
> > diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
> > index 78630bd5124d..dada0678c28e 100644
> > --- a/arch/arm64/include/asm/kvm_host.h
> > +++ b/arch/arm64/include/asm/kvm_host.h
> > @@ -523,7 +523,8 @@ struct kvm_vcpu_arch {
> >   */
> >  static inline u64 *__ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
> >  {
> > -       if (unlikely(r >= __VNCR_START__ && ctxt->vncr_array))
> > +       if (unlikely(cpus_have_final_cap(ARM64_HAS_ENHANCED_NESTED_VIRT) &&
> > +                    r >= __VNCR_START__ && ctxt->vncr_array))
> >                 return &ctxt->vncr_array[r - __VNCR_START__];
> >
> >         return (u64 *)&ctxt->sys_regs[r];
> > diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
> > index eef8f9873814..88147ec99755 100644
> > --- a/arch/arm64/kvm/nested.c
> > +++ b/arch/arm64/kvm/nested.c
> > @@ -47,6 +47,12 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
> >         if (!cpus_have_final_cap(ARM64_HAS_NESTED_VIRT))
> >                 return -EINVAL;
> >
> > +       if (cpus_have_final_cap(ARM64_HAS_ENHANCED_NESTED_VIRT)) {
> > +               vcpu->arch.ctxt.vncr_array = (u64 *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
> > +               if (!vcpu->arch.ctxt.vncr_array)
> > +                       return -ENOMEM;
> > +       }
> > +
> 
> If KVM_ARM_VCPU_INIT was called multiple times, the above codes
> would try to allocate a new page without free-ing the previous
> one. Besides that, the following kvm_free_stage2_pgd() call would

I assume you mean kvm_init_stage2_mmu() here.

> fail in the second call with the error message "kvm_arch already
> initialized?".  I think a possible fix is to add a new flag to
> indicate whether the NV related meta data have been initialized, and
> only initialize them for the first call.

Good catch. But I think we have all the data we need at this stage to
avoid this issue:

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index abb0669bdd4c..baff7373863f 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -390,7 +390,20 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
 	int cpu, err;
 	struct kvm_pgtable *pgt;
 
+	/*
+	 * If we already have our page tables in place, and that the
+	 * MMU context is the canonical one, we have a bug somewhere,
+	 * as this is only supposed to ever happen once per VM.
+	 *
+	 * Otherwise, we're building nested page tables, and that's
+	 * probably because userspace called KVM_ARM_VCPU_INIT more
+	 * than once on the same vcpu. Since that's actually legal,
+	 * don't kick a fuss and leave gracefully.
+	 */
 	if (mmu->pgt != NULL) {
+		if (&kvm->arch.mmu != mmu)
+			return 0;
+
 		kvm_err("kvm_arch already initialized?\n");
 		return -EINVAL;
 	}
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 88147ec99755..3b21ea57fbce 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -48,7 +48,9 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
 		return -EINVAL;
 
 	if (cpus_have_final_cap(ARM64_HAS_ENHANCED_NESTED_VIRT)) {
-		vcpu->arch.ctxt.vncr_array = (u64 *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+		if (!vcpu->arch.ctxt.vncr_array)
+			vcpu->arch.ctxt.vncr_array = (u64 *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+
 		if (!vcpu->arch.ctxt.vncr_array)
 			return -ENOMEM;
 	}

Thanks,

	M.

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

Re: [PATCH v3 09/66] KVM: arm64: nv: Support virtual EL2 exceptions

[Marc Zyngier]

On Fri, 29 Jan 2021 18:05:39 +0000,
Andre Przywara <andre.przywara@arm.com> wrote:
> 
> On Thu, 10 Dec 2020 15:59:05 +0000
> Marc Zyngier <maz@kernel.org> wrote:

[...]

> > diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
> > index b47df73e98d7..530562eb09fd 100644
> > --- a/arch/arm64/kvm/inject_fault.c
> > +++ b/arch/arm64/kvm/inject_fault.c
> > @@ -14,17 +14,50 @@
> >  #include <asm/kvm_emulate.h>
> >  #include <asm/esr.h>
> >  
> > +static void pend_sync_exception(struct kvm_vcpu *vcpu)
> > +{
> > +	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_ELx_SYNC	|
> > +			     KVM_ARM64_PENDING_EXCEPTION);
> > +
> > +	/* If not nesting, EL1 is the only possible exception target */
> > +	if (likely(!nested_virt_in_use(vcpu))) {
> 
> This breaks compilation for the next 14 patches, because
> nested_virt_in_use() is unknown here. Patch 23/66 fixes this by adding
> kvm_nested.h to kvm_emulate.h.

Indeed, well caught.

> Shall we do this already in this patch here, or pull in kvm_nested.h in
> every C file we use nested_virt_in_use(), like exception.c above?

I've just added kvm_nested.h in the two places that were required at
this stage (and verified that it all bisects correctly now).

Thanks,

	M.

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

Re: [PATCH v3 00/66] KVM: arm64: ARMv8.3/8.4 Nested Virtualization support

[Marc Zyngier]

On Thu, 04 Feb 2021 07:51:37 +0000,
Haibo Xu <haibo.xu@linaro.org> wrote:
> 
> Kindly ping!
> 
> On Thu, 21 Jan 2021 at 11:03, Haibo Xu <haibo.xu@linaro.org> wrote:
> >
> > Re-send in case the previous email was blocked for the inlined hyper-link.
> >
> > Hi Marc,
> >
> > I have tried to enable the NV support in Qemu, and now I can
> > successfully boot a L2 guest
> > in Qemu KVM mode.
> >
> > This patch series looks good from the Qemu side except for two minor
> > requirements:
> > (1) Qemu will check whether a feature was supported by the KVM cap
> > when the user tries to enable it in the command line, so a new
> > capability was prefered for the NV(KVM_CAP_ARM_NV?).

I have added KVM_CAP_ARM_EL2 (rather than NV) to that effect.

> > (2) According to the Documentation/virt/kvm/api.rst, userspace can
> > call KVM_ARM_VCPU_INIT multiple times for a given vcpu, but the
> > kvm_vcpu_init_nested() do have some issue when called multiple
> > times(please refer to the detailed comments in patch 63)

This is now fixed, I believe.

I have pushed out a branch [1] that addresses all the reported
issues, though it currently lack some testing. Please let me know if
it works for you.

Thanks,

	M.

[1] https://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms.git/log/?h=kvm-arm64/nv-5.12-WIP

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

Re: [PATCH v3 00/66] KVM: arm64: ARMv8.3/8.4 Nested Virtualization support

[Haibo Xu]

On Thu, 18 Feb 2021 at 06:10, Marc Zyngier <maz@kernel.org> wrote:
>
> On Thu, 04 Feb 2021 07:51:37 +0000,
> Haibo Xu <haibo.xu@linaro.org> wrote:
> >
> > Kindly ping!
> >
> > On Thu, 21 Jan 2021 at 11:03, Haibo Xu <haibo.xu@linaro.org> wrote:
> > >
> > > Re-send in case the previous email was blocked for the inlined hyper-link.
> > >
> > > Hi Marc,
> > >
> > > I have tried to enable the NV support in Qemu, and now I can
> > > successfully boot a L2 guest
> > > in Qemu KVM mode.
> > >
> > > This patch series looks good from the Qemu side except for two minor
> > > requirements:
> > > (1) Qemu will check whether a feature was supported by the KVM cap
> > > when the user tries to enable it in the command line, so a new
> > > capability was prefered for the NV(KVM_CAP_ARM_NV?).
>
> I have added KVM_CAP_ARM_EL2 (rather than NV) to that effect.
>
> > > (2) According to the Documentation/virt/kvm/api.rst, userspace can
> > > call KVM_ARM_VCPU_INIT multiple times for a given vcpu, but the
> > > kvm_vcpu_init_nested() do have some issue when called multiple
> > > times(please refer to the detailed comments in patch 63)
>
> This is now fixed, I believe.
>
> I have pushed out a branch [1] that addresses all the reported
> issues, though it currently lack some testing. Please let me know if
> it works for you.
>

Hi Marc,

I have verified the fix, and it works well with Qemu.

thanks,
Haibo

> Thanks,
>
>         M.
>
> [1] https://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms.git/log/?h=kvm-arm64/nv-5.12-WIP
>
> --
> Without deviation from the norm, progress is not possible.