Merge branch kvm-arm64/timer-vm-offsets into kvmarm-master/next

* kvm-arm64/timer-vm-offsets: (21 commits)
  : .
  : This series aims at satisfying multiple goals:
  :
  : - allow a VMM to atomically restore a timer offset for a whole VM
  :   instead of updating the offset each time a vcpu get its counter
  :   written
  :
  : - allow a VMM to save/restore the physical timer context, something
  :   that we cannot do at the moment due to the lack of offsetting
  :
  : - provide a framework that is suitable for NV support, where we get
  :   both global and per timer, per vcpu offsetting, and manage
  :   interrupts in a less braindead way.
  :
  : Conflict resolution involves using the new per-vcpu config lock instead
  : of the home-grown timer lock.
  : .
  KVM: arm64: Handle 32bit CNTPCTSS traps
  KVM: arm64: selftests: Augment existing timer test to handle variable offset
  KVM: arm64: selftests: Deal with spurious timer interrupts
  KVM: arm64: selftests: Add physical timer registers to the sysreg list
  KVM: arm64: nv: timers: Support hyp timer emulation
  KVM: arm64: nv: timers: Add a per-timer, per-vcpu offset
  KVM: arm64: Document KVM_ARM_SET_CNT_OFFSETS and co
  KVM: arm64: timers: Abstract the number of valid timers per vcpu
  KVM: arm64: timers: Fast-track CNTPCT_EL0 trap handling
  KVM: arm64: Elide kern_hyp_va() in VHE-specific parts of the hypervisor
  KVM: arm64: timers: Move the timer IRQs into arch_timer_vm_data
  KVM: arm64: timers: Abstract per-timer IRQ access
  KVM: arm64: timers: Rationalise per-vcpu timer init
  KVM: arm64: timers: Allow save/restoring of the physical timer
  KVM: arm64: timers: Allow userspace to set the global counter offset
  KVM: arm64: Expose {un,}lock_all_vcpus() to the rest of KVM
  KVM: arm64: timers: Allow physical offset without CNTPOFF_EL2
  KVM: arm64: timers: Use CNTPOFF_EL2 to offset the physical timer
  arm64: Add HAS_ECV_CNTPOFF capability
  arm64: Add CNTPOFF_EL2 register definition
  ...

Signed-off-by: Marc Zyngier <maz@kernel.org>

Author: Marc Zyngier

Documentation/virt/kvm/api.rst

@@ -6029,6 +6029,44 @@ delivery must be provided via the "reg_aen" struct.
 The "pad" and "reserved" fields may be used for future extensions and should be
 set to 0s by userspace.
 
+4.138 KVM_ARM_SET_COUNTER_OFFSET
+--------------------------------
+
+:Capability: KVM_CAP_COUNTER_OFFSET
+:Architectures: arm64
+:Type: vm ioctl
+:Parameters: struct kvm_arm_counter_offset (in)
+:Returns: 0 on success, < 0 on error
+
+This capability indicates that userspace is able to apply a single VM-wide
+offset to both the virtual and physical counters as viewed by the guest
+using the KVM_ARM_SET_CNT_OFFSET ioctl and the following data structure:
+
+::
+
+	struct kvm_arm_counter_offset {
+		__u64 counter_offset;
+		__u64 reserved;
+	};
+
+The offset describes a number of counter cycles that are subtracted from
+both virtual and physical counter views (similar to the effects of the
+CNTVOFF_EL2 and CNTPOFF_EL2 system registers, but only global). The offset
+always applies to all vcpus (already created or created after this ioctl)
+for this VM.
+
+It is userspace's responsibility to compute the offset based, for example,
+on previous values of the guest counters.
+
+Any value other than 0 for the "reserved" field may result in an error
+(-EINVAL) being returned. This ioctl can also return -EBUSY if any vcpu
+ioctl is issued concurrently.
+
+Note that using this ioctl results in KVM ignoring subsequent userspace
+writes to the CNTVCT_EL0 and CNTPCT_EL0 registers using the SET_ONE_REG
+interface. No error will be returned, but the resulting offset will not be
+applied.
+
 5. The kvm_run structure
 ========================
 

arch/arm64/include/asm/kvm_host.h

@@ -224,6 +224,10 @@ struct kvm_arch {
 #define KVM_ARCH_FLAG_EL1_32BIT				4
 	/* PSCI SYSTEM_SUSPEND enabled for the guest */
 #define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED		5
+	/* VM counter offset */
+#define KVM_ARCH_FLAG_VM_COUNTER_OFFSET			6
+	/* Timer PPIs made immutable */
+#define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE		7
 
 	unsigned long flags;
 
@@ -368,6 +372,10 @@ 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! */
 };
@@ -926,6 +934,9 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu);
 
 int __init kvm_sys_reg_table_init(void);
 
+bool lock_all_vcpus(struct kvm *kvm);
+void unlock_all_vcpus(struct kvm *kvm);
+
 /* MMIO helpers */
 void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
 unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
@@ -1011,6 +1022,8 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
 
 long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
 				struct kvm_arm_copy_mte_tags *copy_tags);
+int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm,
+				    struct kvm_arm_counter_offset *offset);
 
 /* Guest/host FPSIMD coordination helpers */
 int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);

arch/arm64/include/asm/kvm_mmu.h

@@ -63,13 +63,15 @@
  * specific registers encoded in the instructions).
  */
 .macro kern_hyp_va	reg
+#ifndef __KVM_VHE_HYPERVISOR__
 alternative_cb ARM64_ALWAYS_SYSTEM, kvm_update_va_mask
 	and     \reg, \reg, #1		/* mask with va_mask */
 	ror	\reg, \reg, #1		/* rotate to the first tag bit */
 	add	\reg, \reg, #0		/* insert the low 12 bits of the tag */
 	add	\reg, \reg, #0, lsl 12	/* insert the top 12 bits of the tag */
 	ror	\reg, \reg, #63		/* rotate back */
 alternative_cb_end
+#endif
 .endm
 
 /*
@@ -127,6 +129,7 @@ void kvm_apply_hyp_relocations(void);
 
 static __always_inline unsigned long __kern_hyp_va(unsigned long v)
 {
+#ifndef __KVM_VHE_HYPERVISOR__
 	asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n"
 				    "ror %0, %0, #1\n"
 				    "add %0, %0, #0\n"
@@ -135,6 +138,7 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v)
 				    ARM64_ALWAYS_SYSTEM,
 				    kvm_update_va_mask)
 		     : "+r" (v));
+#endif
 	return v;
 }
 

arch/arm64/include/asm/sysreg.h

@@ -388,6 +388,7 @@
 
 #define SYS_CNTFRQ_EL0			sys_reg(3, 3, 14, 0, 0)
 
+#define SYS_CNTPCT_EL0			sys_reg(3, 3, 14, 0, 1)
 #define SYS_CNTPCTSS_EL0		sys_reg(3, 3, 14, 0, 5)
 #define SYS_CNTVCTSS_EL0		sys_reg(3, 3, 14, 0, 6)
 
@@ -400,7 +401,9 @@
 
 #define SYS_AARCH32_CNTP_TVAL		sys_reg(0, 0, 14, 2, 0)
 #define SYS_AARCH32_CNTP_CTL		sys_reg(0, 0, 14, 2, 1)
+#define SYS_AARCH32_CNTPCT		sys_reg(0, 0, 0, 14, 0)
 #define SYS_AARCH32_CNTP_CVAL		sys_reg(0, 2, 0, 14, 0)
+#define SYS_AARCH32_CNTPCTSS		sys_reg(0, 8, 0, 14, 0)
 
 #define __PMEV_op2(n)			((n) & 0x7)
 #define __CNTR_CRm(n)			(0x8 | (((n) >> 3) & 0x3))

arch/arm64/include/uapi/asm/kvm.h

@@ -198,6 +198,15 @@ struct kvm_arm_copy_mte_tags {
 	__u64 reserved[2];
 };
 
+/*
+ * Counter/Timer offset structure. Describe the virtual/physical offset.
+ * To be used with KVM_ARM_SET_COUNTER_OFFSET.
+ */
+struct kvm_arm_counter_offset {
+	__u64 counter_offset;
+	__u64 reserved;
+};
+
 #define KVM_ARM_TAGS_TO_GUEST		0
 #define KVM_ARM_TAGS_FROM_GUEST		1
 
@@ -411,6 +420,8 @@ enum {
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
+#define   KVM_ARM_VCPU_TIMER_IRQ_HVTIMER	2
+#define   KVM_ARM_VCPU_TIMER_IRQ_HPTIMER	3
 #define KVM_ARM_VCPU_PVTIME_CTRL	2
 #define   KVM_ARM_VCPU_PVTIME_IPA	0
 

arch/arm64/kernel/cpufeature.c

@@ -2223,6 +2223,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.sign = FTR_UNSIGNED,
 		.min_field_value = 1,
 	},
+	{
+		.desc = "Enhanced Counter Virtualization (CNTPOFF)",
+		.capability = ARM64_HAS_ECV_CNTPOFF,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64MMFR0_EL1,
+		.field_pos = ID_AA64MMFR0_EL1_ECV_SHIFT,
+		.field_width = 4,
+		.sign = FTR_UNSIGNED,
+		.min_field_value = ID_AA64MMFR0_EL1_ECV_CNTPOFF,
+	},
 #ifdef CONFIG_ARM64_PAN
 	{
 		.desc = "Privileged Access Never",