Merge tag 'kvm-4.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Radim Krčmář:
 "First batch of KVM changes for 4.15

  Common:
   - Python 3 support in kvm_stat
   - Accounting of slabs to kmemcg

  ARM:
   - Optimized arch timer handling for KVM/ARM
   - Improvements to the VGIC ITS code and introduction of an ITS reset
     ioctl
   - Unification of the 32-bit fault injection logic
   - More exact external abort matching logic

  PPC:
   - Support for running hashed page table (HPT) MMU mode on a host that
     is using the radix MMU mode; single threaded mode on POWER 9 is
     added as a pre-requisite
   - Resolution of merge conflicts with the last second 4.14 HPT fixes
   - Fixes and cleanups

  s390:
   - Some initial preparation patches for exitless interrupts and crypto
   - New capability for AIS migration
   - Fixes

  x86:
   - Improved emulation of LAPIC timer mode changes, MCi_STATUS MSRs,
     and after-reset state
   - Refined dependencies for VMX features
   - Fixes for nested SMI injection
   - A lot of cleanups"

* tag 'kvm-4.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (89 commits)
  KVM: s390: provide a capability for AIS state migration
  KVM: s390: clear_io_irq() requests are not expected for adapter interrupts
  KVM: s390: abstract conversion between isc and enum irq_types
  KVM: s390: vsie: use common code functions for pinning
  KVM: s390: SIE considerations for AP Queue virtualization
  KVM: s390: document memory ordering for kvm_s390_vcpu_wakeup
  KVM: PPC: Book3S HV: Cosmetic post-merge cleanups
  KVM: arm/arm64: fix the incompatible matching for external abort
  KVM: arm/arm64: Unify 32bit fault injection
  KVM: arm/arm64: vgic-its: Implement KVM_DEV_ARM_ITS_CTRL_RESET
  KVM: arm/arm64: Document KVM_DEV_ARM_ITS_CTRL_RESET
  KVM: arm/arm64: vgic-its: Free caches when GITS_BASER Valid bit is cleared
  KVM: arm/arm64: vgic-its: New helper functions to free the caches
  KVM: arm/arm64: vgic-its: Remove kvm_its_unmap_device
  arm/arm64: KVM: Load the timer state when enabling the timer
  KVM: arm/arm64: Rework kvm_timer_should_fire
  KVM: arm/arm64: Get rid of kvm_timer_flush_hwstate
  KVM: arm/arm64: Avoid phys timer emulation in vcpu entry/exit
  KVM: arm/arm64: Move phys_timer_emulate function
  KVM: arm/arm64: Use kvm_arm_timer_set/get_reg for guest register traps
  ...

9 files changed, 39 insertions, 124 deletions

diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index bdedd8f748d1..f2a234d6516c 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -52,6 +52,7 @@ struct arch_timer_erratum_workaround {
 	const char *desc;
 	u32 (*read_cntp_tval_el0)(void);
 	u32 (*read_cntv_tval_el0)(void);
+	u64 (*read_cntpct_el0)(void);
 	u64 (*read_cntvct_el0)(void);
 	int (*set_next_event_phys)(unsigned long, struct clock_event_device *);
 	int (*set_next_event_virt)(unsigned long, struct clock_event_device *);
@@ -149,11 +150,8 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
 
 static inline u64 arch_counter_get_cntpct(void)
 {
-	/*
-	 * AArch64 kernel and user space mandate the use of CNTVCT.
-	 */
-	BUG();
-	return 0;
+	isb();
+	return arch_timer_reg_read_stable(cntpct_el0);
 }
 
 static inline u64 arch_counter_get_cntvct(void)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 26a64d0f9ab9..ab4d0a926043 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -55,6 +55,8 @@ extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
 
+extern void __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high);
+
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern u64 __vgic_v3_get_ich_vtr_el2(void);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index e5df3fce0008..5f28dfa14cee 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -41,6 +41,9 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu);
 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_inject_undef32(struct kvm_vcpu *vcpu);
+void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr);
+void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr);
 
 static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 {
@@ -237,7 +240,7 @@ static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
 
 static inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
 {
-	switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
+	switch (kvm_vcpu_trap_get_fault(vcpu)) {
 	case FSC_SEA:
 	case FSC_SEA_TTW0:
 	case FSC_SEA_TTW1:
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 4572a9b560fa..08d3bb66c8b7 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -129,8 +129,8 @@ void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
 void __vgic_v3_restore_state(struct kvm_vcpu *vcpu);
 int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu);
 
-void __timer_save_state(struct kvm_vcpu *vcpu);
-void __timer_restore_state(struct kvm_vcpu *vcpu);
+void __timer_enable_traps(struct kvm_vcpu *vcpu);
+void __timer_disable_traps(struct kvm_vcpu *vcpu);
 
 void __sysreg_save_host_state(struct kvm_cpu_context *ctxt);
 void __sysreg_restore_host_state(struct kvm_cpu_context *ctxt);
diff --git a/arch/arm64/include/asm/timex.h b/arch/arm64/include/asm/timex.h
index 81a076eb37fa..9ad60bae5c8d 100644
--- a/arch/arm64/include/asm/timex.h
+++ b/arch/arm64/include/asm/timex.h
@@ -22,7 +22,7 @@
  * Use the current timer as a cycle counter since this is what we use for
  * the delay loop.
  */
-#define get_cycles()	arch_counter_get_cntvct()
+#define get_cycles()	arch_timer_read_counter()
 
 #include <asm-generic/timex.h>
 
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 51149ec75fe4..9abbf3044654 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -196,6 +196,12 @@ struct kvm_arch_memory_slot {
 
 #define ARM64_SYS_REG(...) (__ARM64_SYS_REG(__VA_ARGS__) | KVM_REG_SIZE_U64)
 
+/* Physical Timer EL0 Registers */
+#define KVM_REG_ARM_PTIMER_CTL		ARM64_SYS_REG(3, 3, 14, 2, 1)
+#define KVM_REG_ARM_PTIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 2, 2)
+#define KVM_REG_ARM_PTIMER_CNT		ARM64_SYS_REG(3, 3, 14, 0, 1)
+
+/* EL0 Virtual Timer Registers */
 #define KVM_REG_ARM_TIMER_CTL		ARM64_SYS_REG(3, 3, 14, 3, 1)
 #define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
@@ -228,6 +234,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_ITS_SAVE_TABLES           1
 #define   KVM_DEV_ARM_ITS_RESTORE_TABLES        2
 #define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES	3
+#define   KVM_DEV_ARM_ITS_CTRL_RESET		4
 
 /* Device Control API on vcpu fd */
 #define KVM_ARM_VCPU_PMU_V3_CTRL	0
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 951f3ebaff26..525c01f48867 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -304,7 +304,7 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	__activate_vm(vcpu);
 
 	__vgic_restore_state(vcpu);
-	__timer_restore_state(vcpu);
+	__timer_enable_traps(vcpu);
 
 	/*
 	 * We must restore the 32-bit state before the sysregs, thanks
@@ -374,7 +374,7 @@ again:
 
 	__sysreg_save_guest_state(guest_ctxt);
 	__sysreg32_save_state(vcpu);
-	__timer_save_state(vcpu);
+	__timer_disable_traps(vcpu);
 	__vgic_save_state(vcpu);
 
 	__deactivate_traps(vcpu);
@@ -442,7 +442,7 @@ void __hyp_text __noreturn __hyp_panic(void)
 
 		vcpu = (struct kvm_vcpu *)read_sysreg(tpidr_el2);
 		host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
-		__timer_save_state(vcpu);
+		__timer_disable_traps(vcpu);
 		__deactivate_traps(vcpu);
 		__deactivate_vm(vcpu);
 		__sysreg_restore_host_state(host_ctxt);
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 3556715a774e..8ecbcb40e317 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -33,88 +33,6 @@
 #define LOWER_EL_AArch64_VECTOR		0x400
 #define LOWER_EL_AArch32_VECTOR		0x600
 
-/*
- * Table taken from ARMv8 ARM DDI0487B-B, table G1-10.
- */
-static const u8 return_offsets[8][2] = {
-	[0] = { 0, 0 },		/* Reset, unused */
-	[1] = { 4, 2 },		/* Undefined */
-	[2] = { 0, 0 },		/* SVC, unused */
-	[3] = { 4, 4 },		/* Prefetch abort */
-	[4] = { 8, 8 },		/* Data abort */
-	[5] = { 0, 0 },		/* HVC, unused */
-	[6] = { 4, 4 },		/* IRQ, unused */
-	[7] = { 4, 4 },		/* FIQ, unused */
-};
-
-static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
-{
-	unsigned long cpsr;
-	unsigned long new_spsr_value = *vcpu_cpsr(vcpu);
-	bool is_thumb = (new_spsr_value & COMPAT_PSR_T_BIT);
-	u32 return_offset = return_offsets[vect_offset >> 2][is_thumb];
-	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
-
-	cpsr = mode | COMPAT_PSR_I_BIT;
-
-	if (sctlr & (1 << 30))
-		cpsr |= COMPAT_PSR_T_BIT;
-	if (sctlr & (1 << 25))
-		cpsr |= COMPAT_PSR_E_BIT;
-
-	*vcpu_cpsr(vcpu) = cpsr;
-
-	/* Note: These now point to the banked copies */
-	*vcpu_spsr(vcpu) = new_spsr_value;
-	*vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
-
-	/* Branch to exception vector */
-	if (sctlr & (1 << 13))
-		vect_offset += 0xffff0000;
-	else /* always have security exceptions */
-		vect_offset += vcpu_cp15(vcpu, c12_VBAR);
-
-	*vcpu_pc(vcpu) = vect_offset;
-}
-
-static void inject_undef32(struct kvm_vcpu *vcpu)
-{
-	prepare_fault32(vcpu, COMPAT_PSR_MODE_UND, 4);
-}
-
-/*
- * Modelled after TakeDataAbortException() and TakePrefetchAbortException
- * pseudocode.
- */
-static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
-			 unsigned long addr)
-{
-	u32 vect_offset;
-	u32 *far, *fsr;
-	bool is_lpae;
-
-	if (is_pabt) {
-		vect_offset = 12;
-		far = &vcpu_cp15(vcpu, c6_IFAR);
-		fsr = &vcpu_cp15(vcpu, c5_IFSR);
-	} else { /* !iabt */
-		vect_offset = 16;
-		far = &vcpu_cp15(vcpu, c6_DFAR);
-		fsr = &vcpu_cp15(vcpu, c5_DFSR);
-	}
-
-	prepare_fault32(vcpu, COMPAT_PSR_MODE_ABT | COMPAT_PSR_A_BIT, vect_offset);
-
-	*far = addr;
-
-	/* Give the guest an IMPLEMENTATION DEFINED exception */
-	is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31);
-	if (is_lpae)
-		*fsr = 1 << 9 | 0x34;
-	else
-		*fsr = 0x14;
-}
-
 enum exception_type {
 	except_type_sync	= 0,
 	except_type_irq		= 0x80,
@@ -211,7 +129,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
 {
 	if (!(vcpu->arch.hcr_el2 & HCR_RW))
-		inject_abt32(vcpu, false, addr);
+		kvm_inject_dabt32(vcpu, addr);
 	else
 		inject_abt64(vcpu, false, addr);
 }
@@ -227,7 +145,7 @@ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
 {
 	if (!(vcpu->arch.hcr_el2 & HCR_RW))
-		inject_abt32(vcpu, true, addr);
+		kvm_inject_pabt32(vcpu, addr);
 	else
 		inject_abt64(vcpu, true, addr);
 }
@@ -241,7 +159,7 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
 void kvm_inject_undefined(struct kvm_vcpu *vcpu)
 {
 	if (!(vcpu->arch.hcr_el2 & HCR_RW))
-		inject_undef32(vcpu);
+		kvm_inject_undef32(vcpu);
 	else
 		inject_undef64(vcpu);
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index a0ee9b05e3d4..1830ebc227d1 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -842,13 +842,16 @@ static bool access_cntp_tval(struct kvm_vcpu *vcpu,
 		struct sys_reg_params *p,
 		const struct sys_reg_desc *r)
 {
-	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
 	u64 now = kvm_phys_timer_read();
+	u64 cval;
 
-	if (p->is_write)
-		ptimer->cnt_cval = p->regval + now;
-	else
-		p->regval = ptimer->cnt_cval - now;
+	if (p->is_write) {
+		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL,
+				      p->regval + now);
+	} else {
+		cval = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL);
+		p->regval = cval - now;
+	}
 
 	return true;
 }
@@ -857,24 +860,10 @@ static bool access_cntp_ctl(struct kvm_vcpu *vcpu,
 		struct sys_reg_params *p,
 		const struct sys_reg_desc *r)
 {
-	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
-
-	if (p->is_write) {
-		/* ISTATUS bit is read-only */
-		ptimer->cnt_ctl = p->regval & ~ARCH_TIMER_CTRL_IT_STAT;
-	} else {
-		u64 now = kvm_phys_timer_read();
-
-		p->regval = ptimer->cnt_ctl;
-		/*
-		 * Set ISTATUS bit if it's expired.
-		 * Note that according to ARMv8 ARM Issue A.k, ISTATUS bit is
-		 * UNKNOWN when ENABLE bit is 0, so we chose to set ISTATUS bit
-		 * regardless of ENABLE bit for our implementation convenience.
-		 */
-		if (ptimer->cnt_cval <= now)
-			p->regval |= ARCH_TIMER_CTRL_IT_STAT;
-	}
+	if (p->is_write)
+		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CTL, p->regval);
+	else
+		p->regval = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CTL);
 
 	return true;
 }
@@ -883,12 +872,10 @@ static bool access_cntp_cval(struct kvm_vcpu *vcpu,
 		struct sys_reg_params *p,
 		const struct sys_reg_desc *r)
 {
-	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
-
 	if (p->is_write)
-		ptimer->cnt_cval = p->regval;
+		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL, p->regval);
 	else
-		p->regval = ptimer->cnt_cval;
+		p->regval = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL);
 
 	return true;
 }