Merge branch 'kvmarm-master/master' into HEAD

22 files changed, 280 insertions, 104 deletions

diff --git a/arch/arm/include/asm/kvm_coproc.h b/arch/arm/include/asm/kvm_coproc.h
index 4917c2f7e459..e74ab0fbab79 100644
--- a/arch/arm/include/asm/kvm_coproc.h
+++ b/arch/arm/include/asm/kvm_coproc.h
@@ -31,7 +31,8 @@ void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table);
 int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp_0_13_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
 
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 2c14b69511e9..6d1d2e26dfe5 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -32,6 +32,7 @@
 #include <asm/vfp.h>
 #include "../vfp/vfpinstr.h"
 
+#define CREATE_TRACE_POINTS
 #include "trace.h"
 #include "coproc.h"
 
@@ -111,12 +112,6 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	kvm_inject_undefined(vcpu);
-	return 1;
-}
-
 static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
 {
 	/*
@@ -284,7 +279,7 @@ static bool access_gic_sre(struct kvm_vcpu *vcpu,
  * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
  * all PM registers, which doesn't crash the guest kernel at least.
  */
-static bool pm_fake(struct kvm_vcpu *vcpu,
+static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 		    const struct coproc_params *p,
 		    const struct coproc_reg *r)
 {
@@ -294,19 +289,19 @@ static bool pm_fake(struct kvm_vcpu *vcpu,
 		return read_zero(vcpu, p);
 }
 
-#define access_pmcr pm_fake
-#define access_pmcntenset pm_fake
-#define access_pmcntenclr pm_fake
-#define access_pmovsr pm_fake
-#define access_pmselr pm_fake
-#define access_pmceid0 pm_fake
-#define access_pmceid1 pm_fake
-#define access_pmccntr pm_fake
-#define access_pmxevtyper pm_fake
-#define access_pmxevcntr pm_fake
-#define access_pmuserenr pm_fake
-#define access_pmintenset pm_fake
-#define access_pmintenclr pm_fake
+#define access_pmcr trap_raz_wi
+#define access_pmcntenset trap_raz_wi
+#define access_pmcntenclr trap_raz_wi
+#define access_pmovsr trap_raz_wi
+#define access_pmselr trap_raz_wi
+#define access_pmceid0 trap_raz_wi
+#define access_pmceid1 trap_raz_wi
+#define access_pmccntr trap_raz_wi
+#define access_pmxevtyper trap_raz_wi
+#define access_pmxevcntr trap_raz_wi
+#define access_pmuserenr trap_raz_wi
+#define access_pmintenset trap_raz_wi
+#define access_pmintenclr trap_raz_wi
 
 /* Architected CP15 registers.
  * CRn denotes the primary register number, but is copied to the CRm in the
@@ -532,12 +527,7 @@ static int emulate_cp15(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
-/**
- * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access
- * @vcpu: The VCPU pointer
- * @run:  The kvm_run struct
- */
-int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static struct coproc_params decode_64bit_hsr(struct kvm_vcpu *vcpu)
 {
 	struct coproc_params params;
 
@@ -551,9 +541,38 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf;
 	params.CRm = 0;
 
+	return params;
+}
+
+/**
+ * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct coproc_params params = decode_64bit_hsr(vcpu);
+
 	return emulate_cp15(vcpu, &params);
 }
 
+/**
+ * kvm_handle_cp14_64 -- handles a mrrc/mcrr trap on a guest CP14 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct coproc_params params = decode_64bit_hsr(vcpu);
+
+	/* raz_wi cp14 */
+	trap_raz_wi(vcpu, &params, NULL);
+
+	/* handled */
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+	return 1;
+}
+
 static void reset_coproc_regs(struct kvm_vcpu *vcpu,
 			      const struct coproc_reg *table, size_t num)
 {
@@ -564,12 +583,7 @@ static void reset_coproc_regs(struct kvm_vcpu *vcpu,
 			table[i].reset(vcpu, &table[i]);
 }
 
-/**
- * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access
- * @vcpu: The VCPU pointer
- * @run:  The kvm_run struct
- */
-int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static struct coproc_params decode_32bit_hsr(struct kvm_vcpu *vcpu)
 {
 	struct coproc_params params;
 
@@ -583,9 +597,37 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	params.Op2 = (kvm_vcpu_get_hsr(vcpu) >> 17) & 0x7;
 	params.Rt2 = 0;
 
+	return params;
+}
+
+/**
+ * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct coproc_params params = decode_32bit_hsr(vcpu);
 	return emulate_cp15(vcpu, &params);
 }
 
+/**
+ * kvm_handle_cp14_32 -- handles a mrc/mcr trap on a guest CP14 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct coproc_params params = decode_32bit_hsr(vcpu);
+
+	/* raz_wi cp14 */
+	trap_raz_wi(vcpu, &params, NULL);
+
+	/* handled */
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+	return 1;
+}
+
 /******************************************************************************
  * Userspace API
  *****************************************************************************/
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index a2b4f7b82356..54442e375354 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -96,9 +96,9 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[HSR_EC_WFI]		= kvm_handle_wfx,
 	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
 	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
-	[HSR_EC_CP14_MR]	= kvm_handle_cp14_access,
+	[HSR_EC_CP14_MR]	= kvm_handle_cp14_32,
 	[HSR_EC_CP14_LS]	= kvm_handle_cp14_load_store,
-	[HSR_EC_CP14_64]	= kvm_handle_cp14_access,
+	[HSR_EC_CP14_64]	= kvm_handle_cp14_64,
 	[HSR_EC_CP_0_13]	= kvm_handle_cp_0_13_access,
 	[HSR_EC_CP10_ID]	= kvm_handle_cp10_id,
 	[HSR_EC_HVC]		= handle_hvc,
diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile
index 3023bb530edf..8679405b0b2b 100644
--- a/arch/arm/kvm/hyp/Makefile
+++ b/arch/arm/kvm/hyp/Makefile
@@ -2,6 +2,8 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
+ccflags-y += -fno-stack-protector
+
 KVM=../../../../virt/kvm
 
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
diff --git a/arch/arm/kvm/hyp/switch.c b/arch/arm/kvm/hyp/switch.c
index c8f15bb5c8b3..ebd2dd46adf7 100644
--- a/arch/arm/kvm/hyp/switch.c
+++ b/arch/arm/kvm/hyp/switch.c
@@ -48,7 +48,9 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu, u32 *fpexc_host)
 	write_sysreg(HSTR_T(15), HSTR);
 	write_sysreg(HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11), HCPTR);
 	val = read_sysreg(HDCR);
-	write_sysreg(val | HDCR_TPM | HDCR_TPMCR, HDCR);
+	val |= HDCR_TPM | HDCR_TPMCR; /* trap performance monitors */
+	val |= HDCR_TDRA | HDCR_TDOSA | HDCR_TDA; /* trap debug regs */
+	write_sysreg(val, HDCR);
 }
 
 static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 570ed4a9c261..5386528665b5 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -104,7 +104,6 @@ __do_hyp_init:
 	@  - Write permission implies XN: disabled
 	@  - Instruction cache: enabled
 	@  - Data/Unified cache: enabled
-	@  - Memory alignment checks: enabled
 	@  - MMU: enabled (this code must be run from an identity mapping)
 	mrc	p15, 4, r0, c1, c0, 0	@ HSCR
 	ldr	r2, =HSCTLR_MASK
@@ -112,8 +111,8 @@ __do_hyp_init:
 	mrc	p15, 0, r1, c1, c0, 0	@ SCTLR
 	ldr	r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C)
 	and	r1, r1, r2
- ARM(	ldr	r2, =(HSCTLR_M | HSCTLR_A)			)
- THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE)		)
+ ARM(	ldr	r2, =(HSCTLR_M)					)
+ THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_TE)			)
 	orr	r1, r1, r2
 	orr	r0, r0, r1
 	mcr	p15, 4, r0, c1, c0, 0	@ HSCR
diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h
index fc0943776db2..b0d10648c486 100644
--- a/arch/arm/kvm/trace.h
+++ b/arch/arm/kvm/trace.h
@@ -1,5 +1,5 @@
-#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_KVM_H
+#if !defined(_TRACE_ARM_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_ARM_KVM_H
 
 #include <linux/tracepoint.h>
 
@@ -74,10 +74,10 @@ TRACE_EVENT(kvm_hvc,
 		  __entry->vcpu_pc, __entry->r0, __entry->imm)
 );
 
-#endif /* _TRACE_KVM_H */
+#endif /* _TRACE_ARM_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH arch/arm/kvm
+#define TRACE_INCLUDE_PATH .
 #undef TRACE_INCLUDE_FILE
 #define TRACE_INCLUDE_FILE trace
 
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 15c142ce991c..b4d13d9267ff 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -286,6 +286,10 @@
 #define SCTLR_ELx_A	(1 << 1)
 #define SCTLR_ELx_M	1
 
+#define SCTLR_EL2_RES1	((1 << 4)  | (1 << 5)  | (1 << 11) | (1 << 16) | \
+			 (1 << 16) | (1 << 18) | (1 << 22) | (1 << 23) | \
+			 (1 << 28) | (1 << 29))
+
 #define SCTLR_ELx_FLAGS	(SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
 			 SCTLR_ELx_SA | SCTLR_ELx_I)
 
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 839425c24b1c..3f9615582377 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -106,10 +106,13 @@ __do_hyp_init:
 	tlbi	alle2
 	dsb	sy
 
-	mrs	x4, sctlr_el2
-	and	x4, x4, #SCTLR_ELx_EE	// preserve endianness of EL2
-	ldr	x5, =SCTLR_ELx_FLAGS
-	orr	x4, x4, x5
+	/*
+	 * Preserve all the RES1 bits while setting the default flags,
+	 * as well as the EE bit on BE. Drop the A flag since the compiler
+	 * is allowed to generate unaligned accesses.
+	 */
+	ldr	x4, =(SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
+CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
 	msr	sctlr_el2, x4
 	isb
 
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index aaf42ae8d8c3..14c4e3b14bcb 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -2,6 +2,8 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
+ccflags-y += -fno-stack-protector
+
 KVM=../../../../virt/kvm
 
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
diff --git a/arch/arm64/kvm/vgic-sys-reg-v3.c b/arch/arm64/kvm/vgic-sys-reg-v3.c
index 79f37e37d367..6260b69e5622 100644
--- a/arch/arm64/kvm/vgic-sys-reg-v3.c
+++ b/arch/arm64/kvm/vgic-sys-reg-v3.c
@@ -65,8 +65,8 @@ static bool access_gic_ctlr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		 * Here set VMCR.CTLR in ICC_CTLR_EL1 layout.
 		 * The vgic_set_vmcr() will convert to ICH_VMCR layout.
 		 */
-		vmcr.ctlr = val & ICC_CTLR_EL1_CBPR_MASK;
-		vmcr.ctlr |= val & ICC_CTLR_EL1_EOImode_MASK;
+		vmcr.cbpr = (val & ICC_CTLR_EL1_CBPR_MASK) >> ICC_CTLR_EL1_CBPR_SHIFT;
+		vmcr.eoim = (val & ICC_CTLR_EL1_EOImode_MASK) >> ICC_CTLR_EL1_EOImode_SHIFT;
 		vgic_set_vmcr(vcpu, &vmcr);
 	} else {
 		val = 0;
@@ -83,8 +83,8 @@ static bool access_gic_ctlr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		 * The VMCR.CTLR value is in ICC_CTLR_EL1 layout.
 		 * Extract it directly using ICC_CTLR_EL1 reg definitions.
 		 */
-		val |= vmcr.ctlr & ICC_CTLR_EL1_CBPR_MASK;
-		val |= vmcr.ctlr & ICC_CTLR_EL1_EOImode_MASK;
+		val |= (vmcr.cbpr << ICC_CTLR_EL1_CBPR_SHIFT) & ICC_CTLR_EL1_CBPR_MASK;
+		val |= (vmcr.eoim << ICC_CTLR_EL1_EOImode_SHIFT) & ICC_CTLR_EL1_EOImode_MASK;
 
 		p->regval = val;
 	}
@@ -135,7 +135,7 @@ static bool access_gic_bpr1(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		p->regval = 0;
 
 	vgic_get_vmcr(vcpu, &vmcr);
-	if (!((vmcr.ctlr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT)) {
+	if (!vmcr.cbpr) {
 		if (p->is_write) {
 			vmcr.abpr = (p->regval & ICC_BPR1_EL1_MASK) >>
 				     ICC_BPR1_EL1_SHIFT;
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index a2ae9d2de21f..2d923a6b2175 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -202,7 +202,10 @@ struct vgic_dist {
 		/* either a GICv2 CPU interface */
 		gpa_t			vgic_cpu_base;
 		/* or a number of GICv3 redistributor regions */
-		gpa_t			vgic_redist_base;
+		struct {
+			gpa_t		vgic_redist_base;
+			gpa_t		vgic_redist_free_offset;
+		};
 	};
 
 	/* distributor enabled */
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index fffb91202bc9..1fa293a37f4a 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -417,6 +417,10 @@
 #define ICH_HCR_EN			(1 << 0)
 #define ICH_HCR_UIE			(1 << 1)
 
+#define ICH_VMCR_ACK_CTL_SHIFT		2
+#define ICH_VMCR_ACK_CTL_MASK		(1 << ICH_VMCR_ACK_CTL_SHIFT)
+#define ICH_VMCR_FIQ_EN_SHIFT		3
+#define ICH_VMCR_FIQ_EN_MASK		(1 << ICH_VMCR_FIQ_EN_SHIFT)
 #define ICH_VMCR_CBPR_SHIFT		4
 #define ICH_VMCR_CBPR_MASK		(1 << ICH_VMCR_CBPR_SHIFT)
 #define ICH_VMCR_EOIM_SHIFT		9
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index dc30f3d057eb..d3453ee072fc 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -25,7 +25,18 @@
 #define GICC_ENABLE			0x1
 #define GICC_INT_PRI_THRESHOLD		0xf0
 
-#define GIC_CPU_CTRL_EOImodeNS		(1 << 9)
+#define GIC_CPU_CTRL_EnableGrp0_SHIFT	0
+#define GIC_CPU_CTRL_EnableGrp0		(1 << GIC_CPU_CTRL_EnableGrp0_SHIFT)
+#define GIC_CPU_CTRL_EnableGrp1_SHIFT	1
+#define GIC_CPU_CTRL_EnableGrp1		(1 << GIC_CPU_CTRL_EnableGrp1_SHIFT)
+#define GIC_CPU_CTRL_AckCtl_SHIFT	2
+#define GIC_CPU_CTRL_AckCtl		(1 << GIC_CPU_CTRL_AckCtl_SHIFT)
+#define GIC_CPU_CTRL_FIQEn_SHIFT	3
+#define GIC_CPU_CTRL_FIQEn		(1 << GIC_CPU_CTRL_FIQEn_SHIFT)
+#define GIC_CPU_CTRL_CBPR_SHIFT		4
+#define GIC_CPU_CTRL_CBPR		(1 << GIC_CPU_CTRL_CBPR_SHIFT)
+#define GIC_CPU_CTRL_EOImodeNS_SHIFT	9
+#define GIC_CPU_CTRL_EOImodeNS		(1 << GIC_CPU_CTRL_EOImodeNS_SHIFT)
 
 #define GICC_IAR_INT_ID_MASK		0x3ff
 #define GICC_INT_SPURIOUS		1023
@@ -84,8 +95,19 @@
 #define GICH_LR_EOI			(1 << 19)
 #define GICH_LR_HW			(1 << 31)
 
-#define GICH_VMCR_CTRL_SHIFT		0
-#define GICH_VMCR_CTRL_MASK		(0x21f << GICH_VMCR_CTRL_SHIFT)
+#define GICH_VMCR_ENABLE_GRP0_SHIFT	0
+#define GICH_VMCR_ENABLE_GRP0_MASK	(1 << GICH_VMCR_ENABLE_GRP0_SHIFT)
+#define GICH_VMCR_ENABLE_GRP1_SHIFT	1
+#define GICH_VMCR_ENABLE_GRP1_MASK	(1 << GICH_VMCR_ENABLE_GRP1_SHIFT)
+#define GICH_VMCR_ACK_CTL_SHIFT		2
+#define GICH_VMCR_ACK_CTL_MASK		(1 << GICH_VMCR_ACK_CTL_SHIFT)
+#define GICH_VMCR_FIQ_EN_SHIFT		3
+#define GICH_VMCR_FIQ_EN_MASK		(1 << GICH_VMCR_FIQ_EN_SHIFT)
+#define GICH_VMCR_CBPR_SHIFT		4
+#define GICH_VMCR_CBPR_MASK		(1 << GICH_VMCR_CBPR_SHIFT)
+#define GICH_VMCR_EOI_MODE_SHIFT	9
+#define GICH_VMCR_EOI_MODE_MASK		(1 << GICH_VMCR_EOI_MODE_SHIFT)
+
 #define GICH_VMCR_PRIMASK_SHIFT		27
 #define GICH_VMCR_PRIMASK_MASK		(0x1f << GICH_VMCR_PRIMASK_SHIFT)
 #define GICH_VMCR_BINPOINT_SHIFT	21
diff --git a/virt/kvm/arm/hyp/vgic-v3-sr.c b/virt/kvm/arm/hyp/vgic-v3-sr.c
index bce6037cf01d..87940364570b 100644
--- a/virt/kvm/arm/hyp/vgic-v3-sr.c
+++ b/virt/kvm/arm/hyp/vgic-v3-sr.c
@@ -22,7 +22,7 @@
 #include <asm/kvm_hyp.h>
 
 #define vtr_to_max_lr_idx(v)		((v) & 0xf)
-#define vtr_to_nr_pri_bits(v)		(((u32)(v) >> 29) + 1)
+#define vtr_to_nr_pre_bits(v)		((((u32)(v) >> 26) & 7) + 1)
 
 static u64 __hyp_text __gic_v3_get_lr(unsigned int lr)
 {
@@ -135,13 +135,13 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 
 	if (used_lrs) {
 		int i;
-		u32 nr_pri_bits;
+		u32 nr_pre_bits;
 
 		cpu_if->vgic_elrsr = read_gicreg(ICH_ELSR_EL2);
 
 		write_gicreg(0, ICH_HCR_EL2);
 		val = read_gicreg(ICH_VTR_EL2);
-		nr_pri_bits = vtr_to_nr_pri_bits(val);
+		nr_pre_bits = vtr_to_nr_pre_bits(val);
 
 		for (i = 0; i < used_lrs; i++) {
 			if (cpu_if->vgic_elrsr & (1 << i))
@@ -152,7 +152,7 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 			__gic_v3_set_lr(0, i);
 		}
 
-		switch (nr_pri_bits) {
+		switch (nr_pre_bits) {
 		case 7:
 			cpu_if->vgic_ap0r[3] = read_gicreg(ICH_AP0R3_EL2);
 			cpu_if->vgic_ap0r[2] = read_gicreg(ICH_AP0R2_EL2);
@@ -162,7 +162,7 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 			cpu_if->vgic_ap0r[0] = read_gicreg(ICH_AP0R0_EL2);
 		}
 
-		switch (nr_pri_bits) {
+		switch (nr_pre_bits) {
 		case 7:
 			cpu_if->vgic_ap1r[3] = read_gicreg(ICH_AP1R3_EL2);
 			cpu_if->vgic_ap1r[2] = read_gicreg(ICH_AP1R2_EL2);
@@ -198,7 +198,7 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 	u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
 	u64 val;
-	u32 nr_pri_bits;
+	u32 nr_pre_bits;
 	int i;
 
 	/*
@@ -217,12 +217,12 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	}
 
 	val = read_gicreg(ICH_VTR_EL2);
-	nr_pri_bits = vtr_to_nr_pri_bits(val);
+	nr_pre_bits = vtr_to_nr_pre_bits(val);
 
 	if (used_lrs) {
 		write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
 
-		switch (nr_pri_bits) {
+		switch (nr_pre_bits) {
 		case 7:
 			write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2);
 			write_gicreg(cpu_if->vgic_ap0r[2], ICH_AP0R2_EL2);
@@ -232,7 +232,7 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 			write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2);
 		}
 
-		switch (nr_pri_bits) {
+		switch (nr_pre_bits) {
 		case 7:
 			write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2);
 			write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2);
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 313ee646480f..e2e5effba2a9 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -295,6 +295,13 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 	assert_spin_locked(&kvm->mmu_lock);
 	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
 	do {
+		/*
+		 * Make sure the page table is still active, as another thread
+		 * could have possibly freed the page table, while we released
+		 * the lock.
+		 */
+		if (!READ_ONCE(kvm->arch.pgd))
+			break;
 		next = stage2_pgd_addr_end(addr, end);
 		if (!stage2_pgd_none(*pgd))
 			unmap_stage2_puds(kvm, pgd, addr, next);
@@ -829,22 +836,22 @@ void stage2_unmap_vm(struct kvm *kvm)
  * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all
  * underlying level-2 and level-3 tables before freeing the actual level-1 table
  * and setting the struct pointer to NULL.
- *
- * Note we don't need locking here as this is only called when the VM is
- * destroyed, which can only be done once.
  */
 void kvm_free_stage2_pgd(struct kvm *kvm)
 {
-	if (kvm->arch.pgd == NULL)
-		return;
+	void *pgd = NULL;
 
 	spin_lock(&kvm->mmu_lock);
-	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+	if (kvm->arch.pgd) {
+		unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+		pgd = READ_ONCE(kvm->arch.pgd);
+		kvm->arch.pgd = NULL;
+	}
 	spin_unlock(&kvm->mmu_lock);
 
 	/* Free the HW pgd, one page at a time */
-	free_pages_exact(kvm->arch.pgd, S2_PGD_SIZE);
-	kvm->arch.pgd = NULL;
+	if (pgd)
+		free_pages_exact(pgd, S2_PGD_SIZE);
 }
 
 static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
@@ -872,6 +879,9 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	pmd_t *pmd;
 
 	pud = stage2_get_pud(kvm, cache, addr);
+	if (!pud)
+		return NULL;
+
 	if (stage2_pud_none(*pud)) {
 		if (!cache)
 			return NULL;
@@ -1170,11 +1180,13 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 		 * large. Otherwise, we may see kernel panics with
 		 * CONFIG_DETECT_HUNG_TASK, CONFIG_LOCKUP_DETECTOR,
 		 * CONFIG_LOCKDEP. Additionally, holding the lock too long
-		 * will also starve other vCPUs.
+		 * will also starve other vCPUs. We have to also make sure
+		 * that the page tables are not freed while we released
+		 * the lock.
 		 */
-		if (need_resched() || spin_needbreak(&kvm->mmu_lock))
-			cond_resched_lock(&kvm->mmu_lock);
-
+		cond_resched_lock(&kvm->mmu_lock);
+		if (!READ_ONCE(kvm->arch.pgd))
+			break;
 		next = stage2_pgd_addr_end(addr, end);
 		if (stage2_pgd_present(*pgd))
 			stage2_wp_puds(pgd, addr, next);
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index dc68e2e424ab..3a0b8999f011 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -242,8 +242,11 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	 * 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.
 	 */
-	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
+		mutex_lock(&vcpu->kvm->lock);
 		ret = vgic_register_redist_iodev(vcpu);
+		mutex_unlock(&vcpu->kvm->lock);
+	}
 	return ret;
 }
 
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c
index 8bafe9af3205..37522e65eb53 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v2.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c
@@ -226,7 +226,13 @@ static unsigned long vgic_mmio_read_vcpuif(struct kvm_vcpu *vcpu,
 
 	switch (addr & 0xff) {
 	case GIC_CPU_CTRL:
-		val = vmcr.ctlr;
+		val = vmcr.grpen0 << GIC_CPU_CTRL_EnableGrp0_SHIFT;
+		val |= vmcr.grpen1 << GIC_CPU_CTRL_EnableGrp1_SHIFT;
+		val |= vmcr.ackctl << GIC_CPU_CTRL_AckCtl_SHIFT;
+		val |= vmcr.fiqen << GIC_CPU_CTRL_FIQEn_SHIFT;
+		val |= vmcr.cbpr << GIC_CPU_CTRL_CBPR_SHIFT;
+		val |= vmcr.eoim << GIC_CPU_CTRL_EOImodeNS_SHIFT;
+
 		break;
 	case GIC_CPU_PRIMASK:
 		/*
@@ -267,7 +273,13 @@ static void vgic_mmio_write_vcpuif(struct kvm_vcpu *vcpu,
 
 	switch (addr & 0xff) {
 	case GIC_CPU_CTRL:
-		vmcr.ctlr = val;
+		vmcr.grpen0 = !!(val & GIC_CPU_CTRL_EnableGrp0);
+		vmcr.grpen1 = !!(val & GIC_CPU_CTRL_EnableGrp1);
+		vmcr.ackctl = !!(val & GIC_CPU_CTRL_AckCtl);
+		vmcr.fiqen = !!(val & GIC_CPU_CTRL_FIQEn);
+		vmcr.cbpr = !!(val & GIC_CPU_CTRL_CBPR);
+		vmcr.eoim = !!(val & GIC_CPU_CTRL_EOImodeNS);
+
 		break;
 	case GIC_CPU_PRIMASK:
 		/*
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index e25567a93dd5..714fa3933546 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -590,7 +590,7 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu)
 	if (!vgic_v3_check_base(kvm))
 		return -EINVAL;
 
-	rd_base = vgic->vgic_redist_base + kvm_vcpu_get_idx(vcpu) * SZ_64K * 2;
+	rd_base = vgic->vgic_redist_base + vgic->vgic_redist_free_offset;
 	sgi_base = rd_base + SZ_64K;
 
 	kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops);
@@ -618,11 +618,15 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu)
 	mutex_lock(&kvm->slots_lock);
 	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, sgi_base,
 				      SZ_64K, &sgi_dev->dev);
-	mutex_unlock(&kvm->slots_lock);
-	if (ret)
+	if (ret) {
 		kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
 					  &rd_dev->dev);
+		goto out;
+	}
 
+	vgic->vgic_redist_free_offset += 2 * SZ_64K;
+out:
+	mutex_unlock(&kvm->slots_lock);
 	return ret;
 }
 
@@ -648,10 +652,12 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm)
 
 	if (ret) {
 		/* The current c failed, so we start with the previous one. */
+		mutex_lock(&kvm->slots_lock);
 		for (c--; c >= 0; c--) {
 			vcpu = kvm_get_vcpu(kvm, c);
 			vgic_unregister_redist_iodev(vcpu);
 		}
+		mutex_unlock(&kvm->slots_lock);
 	}
 
 	return ret;
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index a65757aab6d3..e4187e52bb26 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -149,6 +149,13 @@ void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 	if (irq->hw) {
 		val |= GICH_LR_HW;
 		val |= irq->hwintid << GICH_LR_PHYSID_CPUID_SHIFT;
+		/*
+		 * Never set pending+active on a HW interrupt, as the
+		 * pending state is kept at the physical distributor
+		 * level.
+		 */
+		if (irq->active && irq_is_pending(irq))
+			val &= ~GICH_LR_PENDING_BIT;
 	} else {
 		if (irq->config == VGIC_CONFIG_LEVEL)
 			val |= GICH_LR_EOI;
@@ -170,7 +177,18 @@ void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
 	u32 vmcr;
 
-	vmcr  = (vmcrp->ctlr << GICH_VMCR_CTRL_SHIFT) & GICH_VMCR_CTRL_MASK;
+	vmcr = (vmcrp->grpen0 << GICH_VMCR_ENABLE_GRP0_SHIFT) &
+		GICH_VMCR_ENABLE_GRP0_MASK;
+	vmcr |= (vmcrp->grpen1 << GICH_VMCR_ENABLE_GRP1_SHIFT) &
+		GICH_VMCR_ENABLE_GRP1_MASK;
+	vmcr |= (vmcrp->ackctl << GICH_VMCR_ACK_CTL_SHIFT) &
+		GICH_VMCR_ACK_CTL_MASK;
+	vmcr |= (vmcrp->fiqen << GICH_VMCR_FIQ_EN_SHIFT) &
+		GICH_VMCR_FIQ_EN_MASK;
+	vmcr |= (vmcrp->cbpr << GICH_VMCR_CBPR_SHIFT) &
+		GICH_VMCR_CBPR_MASK;
+	vmcr |= (vmcrp->eoim << GICH_VMCR_EOI_MODE_SHIFT) &
+		GICH_VMCR_EOI_MODE_MASK;
 	vmcr |= (vmcrp->abpr << GICH_VMCR_ALIAS_BINPOINT_SHIFT) &
 		GICH_VMCR_ALIAS_BINPOINT_MASK;
 	vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) &
@@ -188,8 +206,19 @@ void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 
 	vmcr = cpu_if->vgic_vmcr;
 
-	vmcrp->ctlr = (vmcr & GICH_VMCR_CTRL_MASK) >>
-			GICH_VMCR_CTRL_SHIFT;
+	vmcrp->grpen0 = (vmcr & GICH_VMCR_ENABLE_GRP0_MASK) >>
+		GICH_VMCR_ENABLE_GRP0_SHIFT;
+	vmcrp->grpen1 = (vmcr & GICH_VMCR_ENABLE_GRP1_MASK) >>
+		GICH_VMCR_ENABLE_GRP1_SHIFT;
+	vmcrp->ackctl = (vmcr & GICH_VMCR_ACK_CTL_MASK) >>
+		GICH_VMCR_ACK_CTL_SHIFT;
+	vmcrp->fiqen = (vmcr & GICH_VMCR_FIQ_EN_MASK) >>
+		GICH_VMCR_FIQ_EN_SHIFT;
+	vmcrp->cbpr = (vmcr & GICH_VMCR_CBPR_MASK) >>
+		GICH_VMCR_CBPR_SHIFT;
+	vmcrp->eoim = (vmcr & GICH_VMCR_EOI_MODE_MASK) >>
+		GICH_VMCR_EOI_MODE_SHIFT;
+
 	vmcrp->abpr = (vmcr & GICH_VMCR_ALIAS_BINPOINT_MASK) >>
 			GICH_VMCR_ALIAS_BINPOINT_SHIFT;
 	vmcrp->bpr  = (vmcr & GICH_VMCR_BINPOINT_MASK) >>
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index 8fa737edde6f..030248e669f6 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -127,6 +127,13 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 	if (irq->hw) {
 		val |= ICH_LR_HW;
 		val |= ((u64)irq->hwintid) << ICH_LR_PHYS_ID_SHIFT;
+		/*
+		 * Never set pending+active on a HW interrupt, as the
+		 * pending state is kept at the physical distributor
+		 * level.
+		 */
+		if (irq->active && irq_is_pending(irq))
+			val &= ~ICH_LR_PENDING_BIT;
 	} else {
 		if (irq->config == VGIC_CONFIG_LEVEL)
 			val |= ICH_LR_EOI;
@@ -152,15 +159,24 @@ void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr)
 void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u32 model = vcpu->kvm->arch.vgic.vgic_model;
 	u32 vmcr;
 
-	/*
-	 * Ignore the FIQen bit, because GIC emulation always implies
-	 * SRE=1 which means the vFIQEn bit is also RES1.
-	 */
-	vmcr = ((vmcrp->ctlr >> ICC_CTLR_EL1_EOImode_SHIFT) <<
-		 ICH_VMCR_EOIM_SHIFT) & ICH_VMCR_EOIM_MASK;
-	vmcr |= (vmcrp->ctlr << ICH_VMCR_CBPR_SHIFT) & ICH_VMCR_CBPR_MASK;
+	if (model == KVM_DEV_TYPE_ARM_VGIC_V2) {
+		vmcr = (vmcrp->ackctl << ICH_VMCR_ACK_CTL_SHIFT) &
+			ICH_VMCR_ACK_CTL_MASK;
+		vmcr |= (vmcrp->fiqen << ICH_VMCR_FIQ_EN_SHIFT) &
+			ICH_VMCR_FIQ_EN_MASK;
+	} else {
+		/*
+		 * When emulating GICv3 on GICv3 with SRE=1 on the
+		 * VFIQEn bit is RES1 and the VAckCtl bit is RES0.
+		 */
+		vmcr = ICH_VMCR_FIQ_EN_MASK;
+	}
+
+	vmcr |= (vmcrp->cbpr << ICH_VMCR_CBPR_SHIFT) & ICH_VMCR_CBPR_MASK;
+	vmcr |= (vmcrp->eoim << ICH_VMCR_EOIM_SHIFT) & ICH_VMCR_EOIM_MASK;
 	vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK;
 	vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK;
 	vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK;
@@ -173,17 +189,27 @@ void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u32 model = vcpu->kvm->arch.vgic.vgic_model;
 	u32 vmcr;
 
 	vmcr = cpu_if->vgic_vmcr;
 
-	/*
-	 * Ignore the FIQen bit, because GIC emulation always implies
-	 * SRE=1 which means the vFIQEn bit is also RES1.
-	 */
-	vmcrp->ctlr = ((vmcr >> ICH_VMCR_EOIM_SHIFT) <<
-			ICC_CTLR_EL1_EOImode_SHIFT) & ICC_CTLR_EL1_EOImode_MASK;
-	vmcrp->ctlr |= (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT;
+	if (model == KVM_DEV_TYPE_ARM_VGIC_V2) {
+		vmcrp->ackctl = (vmcr & ICH_VMCR_ACK_CTL_MASK) >>
+			ICH_VMCR_ACK_CTL_SHIFT;
+		vmcrp->fiqen = (vmcr & ICH_VMCR_FIQ_EN_MASK) >>
+			ICH_VMCR_FIQ_EN_SHIFT;
+	} else {
+		/*
+		 * When emulating GICv3 on GICv3 with SRE=1 on the
+		 * VFIQEn bit is RES1 and the VAckCtl bit is RES0.
+		 */
+		vmcrp->fiqen = 1;
+		vmcrp->ackctl = 0;
+	}
+
+	vmcrp->cbpr = (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT;
+	vmcrp->eoim = (vmcr & ICH_VMCR_EOIM_MASK) >> ICH_VMCR_EOIM_SHIFT;
 	vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT;
 	vmcrp->bpr  = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT;
 	vmcrp->pmr  = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT;
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index da83e4caa272..bba7fa22a7f7 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -111,14 +111,18 @@ static inline bool irq_is_pending(struct vgic_irq *irq)
  * registers regardless of the hardware backed GIC used.
  */
 struct vgic_vmcr {
-	u32	ctlr;
+	u32	grpen0;
+	u32	grpen1;
+
+	u32	ackctl;
+	u32	fiqen;
+	u32	cbpr;
+	u32	eoim;
+
 	u32	abpr;
 	u32	bpr;
 	u32	pmr;  /* Priority mask field in the GICC_PMR and
 		       * ICC_PMR_EL1 priority field format */
-	/* Below member variable are valid only for GICv3 */
-	u32	grpen0;
-	u32	grpen1;
 };
 
 struct vgic_reg_attr {