Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "s390:

   - More phys_to_virt conversions

   - Improvement of AP management for VSIE (nested virtualization)

  ARM64:

   - Numerous fixes for the pathological lock inversion issue that
     plagued KVM/arm64 since... forever.

   - New framework allowing SMCCC-compliant hypercalls to be forwarded
     to userspace, hopefully paving the way for some more features being
     moved to VMMs rather than be implemented in the kernel.

   - Large rework of the timer code to allow a VM-wide offset to be
     applied to both virtual and physical counters as well as a
     per-timer, per-vcpu offset that complements the global one. This
     last part allows the NV timer code to be implemented on top.

   - A small set of fixes to make sure that we don't change anything
     affecting the EL1&0 translation regime just after having having
     taken an exception to EL2 until we have executed a DSB. This
     ensures that speculative walks started in EL1&0 have completed.

   - The usual selftest fixes and improvements.

  x86:

   - Optimize CR0.WP toggling by avoiding an MMU reload when TDP is
     enabled, and by giving the guest control of CR0.WP when EPT is
     enabled on VMX (VMX-only because SVM doesn't support per-bit
     controls)

   - Add CR0/CR4 helpers to query single bits, and clean up related code
     where KVM was interpreting kvm_read_cr4_bits()'s "unsigned long"
     return as a bool

   - Move AMD_PSFD to cpufeatures.h and purge KVM's definition

   - Avoid unnecessary writes+flushes when the guest is only adding new
     PTEs

   - Overhaul .sync_page() and .invlpg() to utilize .sync_page()'s
     optimizations when emulating invalidations

   - Clean up the range-based flushing APIs

   - Revamp the TDP MMU's reaping of Accessed/Dirty bits to clear a
     single A/D bit using a LOCK AND instead of XCHG, and skip all of
     the "handle changed SPTE" overhead associated with writing the
     entire entry

   - Track the number of "tail" entries in a pte_list_desc to avoid
     having to walk (potentially) all descriptors during insertion and
     deletion, which gets quite expensive if the guest is spamming
     fork()

   - Disallow virtualizing legacy LBRs if architectural LBRs are
     available, the two are mutually exclusive in hardware

   - Disallow writes to immutable feature MSRs (notably
     PERF_CAPABILITIES) after KVM_RUN, similar to CPUID features

   - Overhaul the vmx_pmu_caps selftest to better validate
     PERF_CAPABILITIES

   - Apply PMU filters to emulated events and add test coverage to the
     pmu_event_filter selftest

   - AMD SVM:
       - Add support for virtual NMIs
       - Fixes for edge cases related to virtual interrupts

   - Intel AMX:
       - Don't advertise XTILE_CFG in KVM_GET_SUPPORTED_CPUID if
         XTILE_DATA is not being reported due to userspace not opting in
         via prctl()
       - Fix a bug in emulation of ENCLS in compatibility mode
       - Allow emulation of NOP and PAUSE for L2
       - AMX selftests improvements
       - Misc cleanups

  MIPS:

   - Constify MIPS's internal callbacks (a leftover from the hardware
     enabling rework that landed in 6.3)

  Generic:

   - Drop unnecessary casts from "void *" throughout kvm_main.c

   - Tweak the layout of "struct kvm_mmu_memory_cache" to shrink the
     struct size by 8 bytes on 64-bit kernels by utilizing a padding
     hole

  Documentation:

   - Fix goof introduced by the conversion to rST"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (211 commits)
  KVM: s390: pci: fix virtual-physical confusion on module unload/load
  KVM: s390: vsie: clarifications on setting the APCB
  KVM: s390: interrupt: fix virtual-physical confusion for next alert GISA
  KVM: arm64: Have kvm_psci_vcpu_on() use WRITE_ONCE() to update mp_state
  KVM: arm64: Acquire mp_state_lock in kvm_arch_vcpu_ioctl_vcpu_init()
  KVM: selftests: Test the PMU event "Instructions retired"
  KVM: selftests: Copy full counter values from guest in PMU event filter test
  KVM: selftests: Use error codes to signal errors in PMU event filter test
  KVM: selftests: Print detailed info in PMU event filter asserts
  KVM: selftests: Add helpers for PMC asserts in PMU event filter test
  KVM: selftests: Add a common helper for the PMU event filter guest code
  KVM: selftests: Fix spelling mistake "perrmited" -> "permitted"
  KVM: arm64: vhe: Drop extra isb() on guest exit
  KVM: arm64: vhe: Synchronise with page table walker on MMU update
  KVM: arm64: pkvm: Document the side effects of kvm_flush_dcache_to_poc()
  KVM: arm64: nvhe: Synchronise with page table walker on TLBI
  KVM: arm64: Handle 32bit CNTPCTSS traps
  KVM: arm64: nvhe: Synchronise with page table walker on vcpu run
  KVM: arm64: vgic: Don't acquire its_lock before config_lock
  KVM: selftests: Add test to verify KVM's supported XCR0
  ...

7 files changed, 50 insertions, 15 deletions

diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h
index 057c8964aefb..cbbc9a6dc571 100644
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@@ -21,6 +21,7 @@
 #define CNTHCTL_EVNTEN			(1 << 2)
 #define CNTHCTL_EVNTDIR			(1 << 3)
 #define CNTHCTL_EVNTI			(0xF << 4)
+#define CNTHCTL_ECV			(1 << 12)
 
 enum arch_timer_reg {
 	ARCH_TIMER_REG_CTRL,
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index c52a6e6839da..bb3cb005873e 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -13,6 +13,9 @@
 enum kvm_arch_timers {
 	TIMER_PTIMER,
 	TIMER_VTIMER,
+	NR_KVM_EL0_TIMERS,
+	TIMER_HVTIMER = NR_KVM_EL0_TIMERS,
+	TIMER_HPTIMER,
 	NR_KVM_TIMERS
 };
 
@@ -21,6 +24,7 @@ enum kvm_arch_timer_regs {
 	TIMER_REG_CVAL,
 	TIMER_REG_TVAL,
 	TIMER_REG_CTL,
+	TIMER_REG_VOFF,
 };
 
 struct arch_timer_offset {
@@ -29,21 +33,29 @@ struct arch_timer_offset {
 	 * structure. If NULL, assume a zero offset.
 	 */
 	u64	*vm_offset;
+	/*
+	 * If set, pointer to one of the offsets in the vcpu's sysreg
+	 * array. If NULL, assume a zero offset.
+	 */
+	u64	*vcpu_offset;
 };
 
 struct arch_timer_vm_data {
 	/* Offset applied to the virtual timer/counter */
 	u64	voffset;
+	/* Offset applied to the physical timer/counter */
+	u64	poffset;
+
+	/* The PPI for each timer, global to the VM */
+	u8	ppi[NR_KVM_TIMERS];
 };
 
 struct arch_timer_context {
 	struct kvm_vcpu			*vcpu;
 
-	/* Timer IRQ */
-	struct kvm_irq_level		irq;
-
 	/* Emulated Timer (may be unused) */
 	struct hrtimer			hrtimer;
+	u64				ns_frac;
 
 	/* Offset for this counter/timer */
 	struct arch_timer_offset	offset;
@@ -54,14 +66,19 @@ struct arch_timer_context {
 	 */
 	bool				loaded;
 
+	/* Output level of the timer IRQ */
+	struct {
+		bool			level;
+	} irq;
+
 	/* Duplicated state from arch_timer.c for convenience */
 	u32				host_timer_irq;
-	u32				host_timer_irq_flags;
 };
 
 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;
 };
 
@@ -84,6 +101,8 @@ bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu);
 void kvm_timer_update_run(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu);
 
+void kvm_timer_init_vm(struct kvm *kvm);
+
 u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid);
 int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value);
 
@@ -98,15 +117,18 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu);
 
 void kvm_timer_init_vhe(void);
 
-bool kvm_arch_timer_get_input_level(int vintid);
-
 #define vcpu_timer(v)	(&(v)->arch.timer_cpu)
 #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)
 
+#define timer_vm_data(ctx)		(&(ctx)->vcpu->kvm->arch.timer_data)
+#define timer_irq(ctx)			(timer_vm_data(ctx)->ppi[arch_timer_ctx_index(ctx)])
+
 u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu,
 			      enum kvm_arch_timers tmr,
 			      enum kvm_arch_timer_regs treg);
diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h
index 1188f116cf4e..2df152207ccd 100644
--- a/include/kvm/arm_hypercalls.h
+++ b/include/kvm/arm_hypercalls.h
@@ -6,7 +6,7 @@
 
 #include <asm/kvm_emulate.h>
 
-int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
+int kvm_smccc_call_handler(struct kvm_vcpu *vcpu);
 
 static inline u32 smccc_get_function(struct kvm_vcpu *vcpu)
 {
@@ -43,9 +43,13 @@ static inline void smccc_set_retval(struct kvm_vcpu *vcpu,
 struct kvm_one_reg;
 
 void kvm_arm_init_hypercalls(struct kvm *kvm);
+void kvm_arm_teardown_hypercalls(struct kvm *kvm);
 int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
 int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 
+int kvm_vm_smccc_has_attr(struct kvm *kvm, struct kvm_device_attr *attr);
+int kvm_vm_smccc_set_attr(struct kvm *kvm, struct kvm_device_attr *attr);
+
 #endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index d3ad51fde9db..402b545959af 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -380,6 +380,7 @@ 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, struct irq_ops *ops);
 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);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a9adf75344be..0e571e973bc2 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -58,7 +58,7 @@
 
 /*
  * Bit 63 of the memslot generation number is an "update in-progress flag",
- * e.g. is temporarily set for the duration of install_new_memslots().
+ * e.g. is temporarily set for the duration of kvm_swap_active_memslots().
  * This flag effectively creates a unique generation number that is used to
  * mark cached memslot data, e.g. MMIO accesses, as potentially being stale,
  * i.e. may (or may not) have come from the previous memslots generation.
@@ -713,7 +713,7 @@ struct kvm {
 	 * use by the VM. To be used under the slots_lock (above) or in a
 	 * kvm->srcu critical section where acquiring the slots_lock would
 	 * lead to deadlock with the synchronize_srcu in
-	 * install_new_memslots.
+	 * kvm_swap_active_memslots().
 	 */
 	struct mutex slots_arch_lock;
 	struct mm_struct *mm; /* userspace tied to this vm */
@@ -1398,8 +1398,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 			bool line_status);
 int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 			    struct kvm_enable_cap *cap);
-long kvm_arch_vm_ioctl(struct file *filp,
-		       unsigned int ioctl, unsigned long arg);
+int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg);
 long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
 			      unsigned long arg);
 
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 2728d49bbdf6..6f4737d5046a 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -91,11 +91,11 @@ struct gfn_to_pfn_cache {
  * is topped up (__kvm_mmu_topup_memory_cache()).
  */
 struct kvm_mmu_memory_cache {
-	int nobjs;
 	gfp_t gfp_zero;
 	gfp_t gfp_custom;
 	struct kmem_cache *kmem_cache;
 	int capacity;
+	int nobjs;
 	void **objects;
 };
 #endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index d77aef872a0a..737318b1c1d9 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -341,8 +341,13 @@ struct kvm_run {
 			__u64 nr;
 			__u64 args[6];
 			__u64 ret;
-			__u32 longmode;
-			__u32 pad;
+
+			union {
+#ifndef __KERNEL__
+				__u32 longmode;
+#endif
+				__u64 flags;
+			};
 		} hypercall;
 		/* KVM_EXIT_TPR_ACCESS */
 		struct {
@@ -1184,6 +1189,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224
 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225
 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226
+#define KVM_CAP_COUNTER_OFFSET 227
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1451,7 +1457,7 @@ struct kvm_vfio_spapr_tce {
 #define KVM_CREATE_VCPU           _IO(KVMIO,   0x41)
 #define KVM_GET_DIRTY_LOG         _IOW(KVMIO,  0x42, struct kvm_dirty_log)
 #define KVM_SET_NR_MMU_PAGES      _IO(KVMIO,   0x44)
-#define KVM_GET_NR_MMU_PAGES      _IO(KVMIO,   0x45)
+#define KVM_GET_NR_MMU_PAGES      _IO(KVMIO,   0x45)  /* deprecated */
 #define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
@@ -1543,6 +1549,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_SET_PMU_EVENT_FILTER  _IOW(KVMIO,  0xb2, struct kvm_pmu_event_filter)
 #define KVM_PPC_SVM_OFF		  _IO(KVMIO,  0xb3)
 #define KVM_ARM_MTE_COPY_TAGS	  _IOR(KVMIO,  0xb4, struct kvm_arm_copy_mte_tags)
+/* Available with KVM_CAP_COUNTER_OFFSET */
+#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO,  0xb5, struct kvm_arm_counter_offset)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)