Merge tag 'kvmarm-7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for 7.1

* New features:

- Add support for tracing in the standalone EL2 hypervisor code,
  which should help both debugging and performance analysis.
  This comes with a full infrastructure for 'remote' trace buffers
  that can be exposed by non-kernel entities such as firmware.

- Add support for GICv5 Per Processor Interrupts (PPIs), as the
  starting point for supporting the new GIC architecture in KVM.

- Finally add support for pKVM protected guests, with anonymous
  memory being used as a backing store. About time!

* Improvements and bug fixes:

- Rework the dreaded user_mem_abort() function to make it more
  maintainable, reducing the amount of state being exposed to
  the various helpers and rendering a substantial amount of
  state immutable.

- Expand the Stage-2 page table dumper to support NV shadow
  page tables on a per-VM basis.

- Tidy up the pKVM PSCI proxy code to be slightly less hard
  to follow.

- Fix both SPE and TRBE in non-VHE configurations so that they
  do not generate spurious, out of context table walks that
  ultimately lead to very bad HW lockups.

- A small set of patches fixing the Stage-2 MMU freeing in error
  cases.

- Tighten-up accepted SMC immediate value to be only #0 for host
  SMCCC calls.

- The usual cleanups and other selftest churn.

13 files changed, 553 insertions, 12 deletions

diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index 7310841f4512..bf8cc9589bd0 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -10,6 +10,8 @@
 #include <linux/clocksource.h>
 #include <linux/hrtimer.h>
 
+#include <linux/irqchip/arm-gic-v5.h>
+
 enum kvm_arch_timers {
 	TIMER_PTIMER,
 	TIMER_VTIMER,
@@ -47,7 +49,7 @@ struct arch_timer_vm_data {
 	u64	poffset;
 
 	/* The PPI for each timer, global to the VM */
-	u8	ppi[NR_KVM_TIMERS];
+	u32	ppi[NR_KVM_TIMERS];
 };
 
 struct arch_timer_context {
@@ -130,6 +132,10 @@ void kvm_timer_init_vhe(void);
 #define timer_vm_data(ctx)		(&(timer_context_to_vcpu(ctx)->kvm->arch.timer_data))
 #define timer_irq(ctx)			(timer_vm_data(ctx)->ppi[arch_timer_ctx_index(ctx)])
 
+#define get_vgic_ppi(k, i) (((k)->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V5) ? \
+			    (i) : (FIELD_PREP(GICV5_HWIRQ_ID, i) |	\
+				   FIELD_PREP(GICV5_HWIRQ_TYPE, GICV5_HWIRQ_TYPE_PPI)))
+
 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_pmu.h b/include/kvm/arm_pmu.h
index 96754b51b411..0a36a3d5c894 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -12,6 +12,9 @@
 
 #define KVM_ARMV8_PMU_MAX_COUNTERS	32
 
+/* PPI #23 - architecturally specified for GICv5 */
+#define KVM_ARMV8_PMU_GICV5_IRQ		0x20000017
+
 #if IS_ENABLED(CONFIG_HW_PERF_EVENTS) && IS_ENABLED(CONFIG_KVM)
 struct kvm_pmc {
 	u8 idx;	/* index into the pmu->pmc array */
@@ -38,7 +41,7 @@ struct arm_pmu_entry {
 };
 
 bool kvm_supports_guest_pmuv3(void);
-#define kvm_arm_pmu_irq_initialized(v)	((v)->arch.pmu.irq_num >= VGIC_NR_SGIS)
+#define kvm_arm_pmu_irq_initialized(v)	((v)->arch.pmu.irq_num != 0)
 u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx);
 void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val);
 void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu, u64 select_idx, u64 val);
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index f2eafc65bbf4..1388dc6028a9 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -19,7 +19,9 @@
 #include <linux/jump_label.h>
 
 #include <linux/irqchip/arm-gic-v4.h>
+#include <linux/irqchip/arm-gic-v5.h>
 
+#define VGIC_V5_MAX_CPUS	512
 #define VGIC_V3_MAX_CPUS	512
 #define VGIC_V2_MAX_CPUS	8
 #define VGIC_NR_IRQS_LEGACY     256
@@ -31,9 +33,96 @@
 #define VGIC_MIN_LPI		8192
 #define KVM_IRQCHIP_NUM_PINS	(1020 - 32)
 
-#define irq_is_ppi(irq) ((irq) >= VGIC_NR_SGIS && (irq) < VGIC_NR_PRIVATE_IRQS)
-#define irq_is_spi(irq) ((irq) >= VGIC_NR_PRIVATE_IRQS && \
-			 (irq) <= VGIC_MAX_SPI)
+/*
+ * GICv5 supports 128 PPIs, but only the first 64 are architected. We only
+ * support the timers and PMU in KVM, both of which are architected. Rather than
+ * handling twice the state, we instead opt to only support the architected set
+ * in KVM for now. At a future stage, this can be bumped up to 128, if required.
+ */
+#define VGIC_V5_NR_PRIVATE_IRQS	64
+
+#define is_v5_type(t, i)	(FIELD_GET(GICV5_HWIRQ_TYPE, (i)) == (t))
+
+#define __irq_is_sgi(t, i)						\
+	({								\
+		bool __ret;						\
+									\
+		switch (t) {						\
+		case KVM_DEV_TYPE_ARM_VGIC_V5:				\
+			__ret = false;					\
+			break;						\
+		default:						\
+			__ret  = (i) < VGIC_NR_SGIS;			\
+		}							\
+									\
+		__ret;							\
+	})
+
+#define __irq_is_ppi(t, i)						\
+	({								\
+		bool __ret;						\
+									\
+		switch (t) {						\
+		case KVM_DEV_TYPE_ARM_VGIC_V5:				\
+			__ret = is_v5_type(GICV5_HWIRQ_TYPE_PPI, (i));	\
+			break;						\
+		default:						\
+			__ret  = (i) >= VGIC_NR_SGIS;			\
+			__ret &= (i) < VGIC_NR_PRIVATE_IRQS;		\
+		}							\
+									\
+		__ret;							\
+	})
+
+#define __irq_is_spi(t, i)						\
+	({								\
+		bool __ret;						\
+									\
+		switch (t) {						\
+		case KVM_DEV_TYPE_ARM_VGIC_V5:				\
+			__ret = is_v5_type(GICV5_HWIRQ_TYPE_SPI, (i));	\
+			break;						\
+		default:						\
+			__ret  = (i) <= VGIC_MAX_SPI;			\
+			__ret &= (i) >= VGIC_NR_PRIVATE_IRQS;		\
+		}							\
+									\
+		__ret;							\
+	})
+
+#define __irq_is_lpi(t, i)						\
+	({								\
+		bool __ret;						\
+									\
+		switch (t) {						\
+		case KVM_DEV_TYPE_ARM_VGIC_V5:				\
+			__ret = is_v5_type(GICV5_HWIRQ_TYPE_LPI, (i));	\
+			break;						\
+		default:						\
+			__ret  = (i) >= 8192;				\
+		}							\
+									\
+		__ret;							\
+	})
+
+#define irq_is_sgi(k, i) __irq_is_sgi((k)->arch.vgic.vgic_model, i)
+#define irq_is_ppi(k, i) __irq_is_ppi((k)->arch.vgic.vgic_model, i)
+#define irq_is_spi(k, i) __irq_is_spi((k)->arch.vgic.vgic_model, i)
+#define irq_is_lpi(k, i) __irq_is_lpi((k)->arch.vgic.vgic_model, i)
+
+#define irq_is_private(k, i) (irq_is_ppi(k, i) || irq_is_sgi(k, i))
+
+#define vgic_v5_get_hwirq_id(x) FIELD_GET(GICV5_HWIRQ_ID, (x))
+#define vgic_v5_set_hwirq_id(x) FIELD_PREP(GICV5_HWIRQ_ID, (x))
+
+#define __vgic_v5_set_type(t) (FIELD_PREP(GICV5_HWIRQ_TYPE, GICV5_HWIRQ_TYPE_##t))
+#define vgic_v5_make_ppi(x) (__vgic_v5_set_type(PPI) | vgic_v5_set_hwirq_id(x))
+#define vgic_v5_make_spi(x) (__vgic_v5_set_type(SPI) | vgic_v5_set_hwirq_id(x))
+#define vgic_v5_make_lpi(x) (__vgic_v5_set_type(LPI) | vgic_v5_set_hwirq_id(x))
+
+#define __vgic_is_v(k, v) ((k)->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V##v)
+#define vgic_is_v3(k) (__vgic_is_v(k, 3))
+#define vgic_is_v5(k) (__vgic_is_v(k, 5))
 
 enum vgic_type {
 	VGIC_V2,		/* Good ol' GICv2 */
@@ -101,6 +190,8 @@ enum vgic_irq_config {
 	VGIC_CONFIG_LEVEL
 };
 
+struct vgic_irq;
+
 /*
  * Per-irq ops overriding some common behavious.
  *
@@ -119,6 +210,19 @@ struct irq_ops {
 	 * peaking into the physical GIC.
 	 */
 	bool (*get_input_level)(int vintid);
+
+	/*
+	 * Function pointer to override the queuing of an IRQ.
+	 */
+	bool (*queue_irq_unlock)(struct kvm *kvm, struct vgic_irq *irq,
+				unsigned long flags) __releases(&irq->irq_lock);
+
+	/*
+	 * Callback function pointer to either enable or disable direct
+	 * injection for a mapped interrupt.
+	 */
+	void (*set_direct_injection)(struct kvm_vcpu *vcpu,
+				     struct vgic_irq *irq, bool direct);
 };
 
 struct vgic_irq {
@@ -238,6 +342,26 @@ struct vgic_redist_region {
 	struct list_head list;
 };
 
+struct vgic_v5_vm {
+	/*
+	 * We only expose a subset of PPIs to the guest. This subset is a
+	 * combination of the PPIs that are actually implemented and what we
+	 * actually choose to expose.
+	 */
+	DECLARE_BITMAP(vgic_ppi_mask, VGIC_V5_NR_PRIVATE_IRQS);
+
+	/* A mask of the PPIs that are exposed for userspace to drive. */
+	DECLARE_BITMAP(userspace_ppis, VGIC_V5_NR_PRIVATE_IRQS);
+
+	/*
+	 * The HMR itself is handled by the hardware, but we still need to have
+	 * a mask that we can use when merging in pending state (only the state
+	 * of Edge PPIs is merged back in from the guest an the HMR provides a
+	 * convenient way to do that).
+	 */
+	DECLARE_BITMAP(vgic_ppi_hmr, VGIC_V5_NR_PRIVATE_IRQS);
+};
+
 struct vgic_dist {
 	bool			in_kernel;
 	bool			ready;
@@ -310,6 +434,11 @@ struct vgic_dist {
 	 * else.
 	 */
 	struct its_vm		its_vm;
+
+	/*
+	 * GICv5 per-VM data.
+	 */
+	struct vgic_v5_vm	gicv5_vm;
 };
 
 struct vgic_v2_cpu_if {
@@ -340,11 +469,40 @@ struct vgic_v3_cpu_if {
 	unsigned int used_lrs;
 };
 
+struct vgic_v5_cpu_if {
+	u64	vgic_apr;
+	u64	vgic_vmcr;
+
+	/* PPI register state */
+	DECLARE_BITMAP(vgic_ppi_dvir, VGIC_V5_NR_PRIVATE_IRQS);
+	DECLARE_BITMAP(vgic_ppi_activer, VGIC_V5_NR_PRIVATE_IRQS);
+	DECLARE_BITMAP(vgic_ppi_enabler, VGIC_V5_NR_PRIVATE_IRQS);
+	/* We have one byte (of which 5 bits are used) per PPI for priority */
+	u64	vgic_ppi_priorityr[VGIC_V5_NR_PRIVATE_IRQS / 8];
+
+	/*
+	 * The ICSR is re-used across host and guest, and hence it needs to be
+	 * saved/restored. Only one copy is required as the host should block
+	 * preemption between executing GIC CDRCFG and acccessing the
+	 * ICC_ICSR_EL1. A guest, of course, can never guarantee this, and hence
+	 * it is the hyp's responsibility to keep the state constistent.
+	 */
+	u64	vgic_icsr;
+
+	struct gicv5_vpe gicv5_vpe;
+};
+
+/* What PPI capabilities does a GICv5 host have */
+struct vgic_v5_ppi_caps {
+	DECLARE_BITMAP(impl_ppi_mask, VGIC_V5_NR_PRIVATE_IRQS);
+};
+
 struct vgic_cpu {
 	/* CPU vif control registers for world switch */
 	union {
 		struct vgic_v2_cpu_if	vgic_v2;
 		struct vgic_v3_cpu_if	vgic_v3;
+		struct vgic_v5_cpu_if	vgic_v5;
 	};
 
 	struct vgic_irq *private_irqs;
@@ -392,13 +550,17 @@ int kvm_vgic_create(struct kvm *kvm, u32 type);
 void kvm_vgic_destroy(struct kvm *kvm);
 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
 int kvm_vgic_map_resources(struct kvm *kvm);
+void kvm_vgic_finalize_idregs(struct kvm *kvm);
 int kvm_vgic_hyp_init(void);
 void kvm_vgic_init_cpu_hardware(void);
 
 int kvm_vgic_inject_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
 			unsigned int intid, bool level, void *owner);
+void kvm_vgic_set_irq_ops(struct kvm_vcpu *vcpu, u32 vintid,
+			  struct irq_ops *ops);
+void kvm_vgic_clear_irq_ops(struct kvm_vcpu *vcpu, u32 vintid);
 int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq,
-			  u32 vintid, struct irq_ops *ops);
+			  u32 vintid);
 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);
@@ -414,8 +576,20 @@ 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_valid_spi(k, i)	(((i) >= VGIC_NR_PRIVATE_IRQS) && \
-			((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS))
+#define vgic_valid_spi(k, i)						\
+	({								\
+		bool __ret = irq_is_spi(k, i);				\
+									\
+		switch ((k)->arch.vgic.vgic_model) {			\
+		case KVM_DEV_TYPE_ARM_VGIC_V5:				\
+			__ret &= FIELD_GET(GICV5_HWIRQ_ID, i) < (k)->arch.vgic.nr_spis; \
+			break;						\
+		default:						\
+			__ret &= (i) < ((k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS); \
+		}							\
+									\
+		__ret;							\
+	})
 
 bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu);
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
@@ -455,6 +629,11 @@ int vgic_v4_load(struct kvm_vcpu *vcpu);
 void vgic_v4_commit(struct kvm_vcpu *vcpu);
 int vgic_v4_put(struct kvm_vcpu *vcpu);
 
+int vgic_v5_finalize_ppi_state(struct kvm *kvm);
+bool vgic_v5_ppi_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq,
+				  unsigned long flags);
+void vgic_v5_set_ppi_dvi(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool dvi);
+
 bool vgic_state_is_nested(struct kvm_vcpu *vcpu);
 
 /* CPU HP callbacks */
diff --git a/include/linux/irqchip/arm-gic-v5.h b/include/linux/irqchip/arm-gic-v5.h
index b78488df6c98..40d2fce68294 100644
--- a/include/linux/irqchip/arm-gic-v5.h
+++ b/include/linux/irqchip/arm-gic-v5.h
@@ -25,6 +25,28 @@
 #define GICV5_HWIRQ_TYPE_SPI		UL(0x3)
 
 /*
+ * Architected PPIs
+ */
+#define GICV5_ARCH_PPI_S_DB_PPI		0x0
+#define GICV5_ARCH_PPI_RL_DB_PPI	0x1
+#define GICV5_ARCH_PPI_NS_DB_PPI	0x2
+#define GICV5_ARCH_PPI_SW_PPI		0x3
+#define GICV5_ARCH_PPI_HACDBSIRQ	0xf
+#define GICV5_ARCH_PPI_CNTHVS		0x13
+#define GICV5_ARCH_PPI_CNTHPS		0x14
+#define GICV5_ARCH_PPI_PMBIRQ		0x15
+#define GICV5_ARCH_PPI_COMMIRQ		0x16
+#define GICV5_ARCH_PPI_PMUIRQ		0x17
+#define GICV5_ARCH_PPI_CTIIRQ		0x18
+#define GICV5_ARCH_PPI_GICMNT		0x19
+#define GICV5_ARCH_PPI_CNTHP		0x1a
+#define GICV5_ARCH_PPI_CNTV		0x1b
+#define GICV5_ARCH_PPI_CNTHV		0x1c
+#define GICV5_ARCH_PPI_CNTPS		0x1d
+#define GICV5_ARCH_PPI_CNTP		0x1e
+#define GICV5_ARCH_PPI_TRBIRQ		0x1f
+
+/*
  * Tables attributes
  */
 #define GICV5_NO_READ_ALLOC		0b0
@@ -365,6 +387,11 @@ int gicv5_spi_irq_set_type(struct irq_data *d, unsigned int type);
 int gicv5_irs_iste_alloc(u32 lpi);
 void gicv5_irs_syncr(void);
 
+/* Embedded in kvm.arch */
+struct gicv5_vpe {
+	bool			resident;
+};
+
 struct gicv5_its_devtab_cfg {
 	union {
 		struct {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 6b76e7a6f4c2..779d9ed85cbf 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2366,6 +2366,7 @@ void kvm_unregister_device_ops(u32 type);
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
 extern struct kvm_device_ops kvm_arm_vgic_v3_ops;
+extern struct kvm_device_ops kvm_arm_vgic_v5_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index d862fa610270..994f52b34344 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -251,4 +251,62 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu);
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu);
 int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu);
+
+struct ring_buffer_desc {
+	int		cpu;
+	unsigned int	nr_page_va; /* excludes the meta page */
+	unsigned long	meta_va;
+	unsigned long	page_va[] __counted_by(nr_page_va);
+};
+
+struct trace_buffer_desc {
+	int		nr_cpus;
+	size_t		struct_len;
+	char		__data[]; /* list of ring_buffer_desc */
+};
+
+static inline struct ring_buffer_desc *__next_ring_buffer_desc(struct ring_buffer_desc *desc)
+{
+	size_t len = struct_size(desc, page_va, desc->nr_page_va);
+
+	return (struct ring_buffer_desc *)((void *)desc + len);
+}
+
+static inline struct ring_buffer_desc *__first_ring_buffer_desc(struct trace_buffer_desc *desc)
+{
+	return (struct ring_buffer_desc *)(&desc->__data[0]);
+}
+
+static inline size_t trace_buffer_desc_size(size_t buffer_size, unsigned int nr_cpus)
+{
+	unsigned int nr_pages = max(DIV_ROUND_UP(buffer_size, PAGE_SIZE), 2UL) + 1;
+	struct ring_buffer_desc *rbdesc;
+
+	return size_add(offsetof(struct trace_buffer_desc, __data),
+			size_mul(nr_cpus, struct_size(rbdesc, page_va, nr_pages)));
+}
+
+#define for_each_ring_buffer_desc(__pdesc, __cpu, __trace_pdesc)		\
+	for (__pdesc = __first_ring_buffer_desc(__trace_pdesc), __cpu = 0;	\
+	     (__cpu) < (__trace_pdesc)->nr_cpus;				\
+	     (__cpu)++, __pdesc = __next_ring_buffer_desc(__pdesc))
+
+struct ring_buffer_remote {
+	struct trace_buffer_desc	*desc;
+	int				(*swap_reader_page)(unsigned int cpu, void *priv);
+	int				(*reset)(unsigned int cpu, void *priv);
+	void				*priv;
+};
+
+int ring_buffer_poll_remote(struct trace_buffer *buffer, int cpu);
+
+struct trace_buffer *
+__ring_buffer_alloc_remote(struct ring_buffer_remote *remote,
+			   struct lock_class_key *key);
+
+#define ring_buffer_alloc_remote(remote)			\
+({								\
+	static struct lock_class_key __key;			\
+	__ring_buffer_alloc_remote(remote, &__key);		\
+})
 #endif /* _LINUX_RING_BUFFER_H */
diff --git a/include/linux/ring_buffer_types.h b/include/linux/ring_buffer_types.h
new file mode 100644
index 000000000000..54577021a49d
--- /dev/null
+++ b/include/linux/ring_buffer_types.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_RING_BUFFER_TYPES_H
+#define _LINUX_RING_BUFFER_TYPES_H
+
+#include <asm/local.h>
+
+#define TS_SHIFT        27
+#define TS_MASK         ((1ULL << TS_SHIFT) - 1)
+#define TS_DELTA_TEST   (~TS_MASK)
+
+/*
+ * We need to fit the time_stamp delta into 27 bits.
+ */
+static inline bool test_time_stamp(u64 delta)
+{
+	return !!(delta & TS_DELTA_TEST);
+}
+
+#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data)
+
+#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
+#define RB_ALIGNMENT		4U
+#define RB_MAX_SMALL_DATA	(RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
+#define RB_EVNT_MIN_SIZE	8U	/* two 32bit words */
+
+#ifndef CONFIG_HAVE_64BIT_ALIGNED_ACCESS
+# define RB_FORCE_8BYTE_ALIGNMENT	0
+# define RB_ARCH_ALIGNMENT		RB_ALIGNMENT
+#else
+# define RB_FORCE_8BYTE_ALIGNMENT	1
+# define RB_ARCH_ALIGNMENT		8U
+#endif
+
+#define RB_ALIGN_DATA		__aligned(RB_ARCH_ALIGNMENT)
+
+struct buffer_data_page {
+	u64		 time_stamp;	/* page time stamp */
+	local_t		 commit;	/* write committed index */
+	unsigned char	 data[] RB_ALIGN_DATA;	/* data of buffer page */
+};
+#endif
diff --git a/include/linux/simple_ring_buffer.h b/include/linux/simple_ring_buffer.h
new file mode 100644
index 000000000000..21aec556293e
--- /dev/null
+++ b/include/linux/simple_ring_buffer.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SIMPLE_RING_BUFFER_H
+#define _LINUX_SIMPLE_RING_BUFFER_H
+
+#include <linux/list.h>
+#include <linux/ring_buffer.h>
+#include <linux/ring_buffer_types.h>
+#include <linux/types.h>
+
+/*
+ * Ideally those struct would stay private but the caller needs to know
+ * the allocation size for simple_ring_buffer_init().
+ */
+struct simple_buffer_page {
+	struct list_head	link;
+	struct buffer_data_page	*page;
+	u64			entries;
+	u32			write;
+	u32			id;
+};
+
+struct simple_rb_per_cpu {
+	struct simple_buffer_page	*tail_page;
+	struct simple_buffer_page	*reader_page;
+	struct simple_buffer_page	*head_page;
+	struct simple_buffer_page	*bpages;
+	struct trace_buffer_meta	*meta;
+	u32				nr_pages;
+
+#define SIMPLE_RB_UNAVAILABLE	0
+#define SIMPLE_RB_READY		1
+#define SIMPLE_RB_WRITING	2
+	u32				status;
+
+	u64				last_overrun;
+	u64				write_stamp;
+
+	struct simple_rb_cbs		*cbs;
+};
+
+int simple_ring_buffer_init(struct simple_rb_per_cpu *cpu_buffer, struct simple_buffer_page *bpages,
+			    const struct ring_buffer_desc *desc);
+
+void simple_ring_buffer_unload(struct simple_rb_per_cpu *cpu_buffer);
+
+void *simple_ring_buffer_reserve(struct simple_rb_per_cpu *cpu_buffer, unsigned long length,
+				 u64 timestamp);
+
+void simple_ring_buffer_commit(struct simple_rb_per_cpu *cpu_buffer);
+
+int simple_ring_buffer_enable_tracing(struct simple_rb_per_cpu *cpu_buffer, bool enable);
+
+int simple_ring_buffer_reset(struct simple_rb_per_cpu *cpu_buffer);
+
+int simple_ring_buffer_swap_reader_page(struct simple_rb_per_cpu *cpu_buffer);
+
+int simple_ring_buffer_init_mm(struct simple_rb_per_cpu *cpu_buffer,
+			       struct simple_buffer_page *bpages,
+			       const struct ring_buffer_desc *desc,
+			       void *(*load_page)(unsigned long va),
+			       void (*unload_page)(void *va));
+
+void simple_ring_buffer_unload_mm(struct simple_rb_per_cpu *cpu_buffer,
+				  void (*unload_page)(void *));
+#endif
diff --git a/include/linux/trace_remote.h b/include/linux/trace_remote.h
new file mode 100644
index 000000000000..fcd1d46ea466
--- /dev/null
+++ b/include/linux/trace_remote.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_TRACE_REMOTE_H
+#define _LINUX_TRACE_REMOTE_H
+
+#include <linux/dcache.h>
+#include <linux/ring_buffer.h>
+#include <linux/trace_remote_event.h>
+
+/**
+ * struct trace_remote_callbacks - Callbacks used by Tracefs to control the remote
+ * @init:		Called once the remote has been registered. Allows the
+ *			caller to extend the Tracefs remote directory
+ * @load_trace_buffer:  Called before Tracefs accesses the trace buffer for the first
+ *			time. Must return a &trace_buffer_desc
+ *			(most likely filled with trace_remote_alloc_buffer())
+ * @unload_trace_buffer:
+ *			Called once Tracefs has no use for the trace buffer
+ *			(most likely call trace_remote_free_buffer())
+ * @enable_tracing:	Called on Tracefs tracing_on. It is expected from the
+ *			remote to allow writing.
+ * @swap_reader_page:	Called when Tracefs consumes a new page from a
+ *			ring-buffer. It is expected from the remote to isolate a
+ * @reset:		Called on `echo 0 > trace`. It is expected from the
+ *			remote to reset all ring-buffer pages.
+ *			new reader-page from the @cpu ring-buffer.
+ * @enable_event:	Called on events/event_name/enable. It is expected from
+ *			the remote to allow the writing event @id.
+ */
+struct trace_remote_callbacks {
+	int	(*init)(struct dentry *d, void *priv);
+	struct trace_buffer_desc *(*load_trace_buffer)(unsigned long size, void *priv);
+	void	(*unload_trace_buffer)(struct trace_buffer_desc *desc, void *priv);
+	int	(*enable_tracing)(bool enable, void *priv);
+	int	(*swap_reader_page)(unsigned int cpu, void *priv);
+	int	(*reset)(unsigned int cpu, void *priv);
+	int	(*enable_event)(unsigned short id, bool enable, void *priv);
+};
+
+int trace_remote_register(const char *name, struct trace_remote_callbacks *cbs, void *priv,
+			  struct remote_event *events, size_t nr_events);
+
+int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size, size_t buffer_size,
+			      const struct cpumask *cpumask);
+
+void trace_remote_free_buffer(struct trace_buffer_desc *desc);
+
+#endif
diff --git a/include/linux/trace_remote_event.h b/include/linux/trace_remote_event.h
new file mode 100644
index 000000000000..c8ae1e1f5e72
--- /dev/null
+++ b/include/linux/trace_remote_event.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_TRACE_REMOTE_EVENTS_H
+#define _LINUX_TRACE_REMOTE_EVENTS_H
+
+struct trace_remote;
+struct trace_event_fields;
+struct trace_seq;
+
+struct remote_event_hdr {
+	unsigned short	id;
+};
+
+#define REMOTE_EVENT_NAME_MAX 30
+struct remote_event {
+	char				name[REMOTE_EVENT_NAME_MAX];
+	unsigned short			id;
+	bool				enabled;
+	struct trace_remote		*remote;
+	struct trace_event_fields	*fields;
+	char				*print_fmt;
+	void				(*print)(void *evt, struct trace_seq *seq);
+};
+
+#define RE_STRUCT(__args...) __args
+#define re_field(__type, __field) __type __field;
+
+#define REMOTE_EVENT_FORMAT(__name, __struct)	\
+	struct remote_event_format_##__name {	\
+		struct remote_event_hdr hdr;	\
+		__struct			\
+	}
+#endif
diff --git a/include/trace/define_remote_events.h b/include/trace/define_remote_events.h
new file mode 100644
index 000000000000..676e803dc144
--- /dev/null
+++ b/include/trace/define_remote_events.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/trace_events.h>
+#include <linux/trace_remote_event.h>
+#include <linux/trace_seq.h>
+#include <linux/stringify.h>
+
+#define REMOTE_EVENT_INCLUDE(__file) __stringify(../../__file)
+
+#ifdef REMOTE_EVENT_SECTION
+# define __REMOTE_EVENT_SECTION(__name) __used __section(REMOTE_EVENT_SECTION"."#__name)
+#else
+# define __REMOTE_EVENT_SECTION(__name)
+#endif
+
+#define REMOTE_PRINTK_COUNT_ARGS(__args...) \
+	__COUNT_ARGS(, ##__args, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 0)
+
+#define __remote_printk0()								\
+	trace_seq_putc(seq, '\n')
+
+#define __remote_printk1(__fmt)								\
+	trace_seq_puts(seq, " " __fmt "\n")						\
+
+#define __remote_printk2(__fmt, __args...)						\
+do {											\
+	trace_seq_putc(seq, ' ');							\
+	trace_seq_printf(seq, __fmt, __args);						\
+	trace_seq_putc(seq, '\n');							\
+} while (0)
+
+/* Apply the appropriate trace_seq sequence according to the number of arguments */
+#define remote_printk(__args...)							\
+	CONCATENATE(__remote_printk, REMOTE_PRINTK_COUNT_ARGS(__args))(__args)
+
+#define RE_PRINTK(__args...) __args
+
+#define REMOTE_EVENT(__name, __id, __struct, __printk)					\
+	REMOTE_EVENT_FORMAT(__name, __struct);						\
+	static void remote_event_print_##__name(void *evt, struct trace_seq *seq)	\
+	{										\
+		struct remote_event_format_##__name __maybe_unused *__entry = evt;	\
+		trace_seq_puts(seq, #__name);						\
+		remote_printk(__printk);						\
+	}
+#include REMOTE_EVENT_INCLUDE(REMOTE_EVENT_INCLUDE_FILE)
+
+#undef REMOTE_EVENT
+#undef RE_PRINTK
+#undef re_field
+#define re_field(__type, __field)							\
+	{										\
+		.type = #__type, .name = #__field,					\
+		.size = sizeof(__type), .align = __alignof__(__type),			\
+		.is_signed = is_signed_type(__type),					\
+	},
+#define __entry REC
+#define RE_PRINTK(__fmt, __args...) "\"" __fmt "\", " __stringify(__args)
+#define REMOTE_EVENT(__name, __id, __struct, __printk)					\
+	static struct trace_event_fields remote_event_fields_##__name[] = {		\
+		__struct								\
+		{}									\
+	};										\
+	static char remote_event_print_fmt_##__name[] = __printk;			\
+	static struct remote_event __REMOTE_EVENT_SECTION(__name)			\
+	remote_event_##__name = {							\
+		.name		= #__name,						\
+		.id		= __id,							\
+		.fields		= remote_event_fields_##__name,				\
+		.print_fmt	= remote_event_print_fmt_##__name,			\
+		.print		= remote_event_print_##__name,				\
+	}
+#include REMOTE_EVENT_INCLUDE(REMOTE_EVENT_INCLUDE_FILE)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 7fb4fea9d38e..1cc0c9463f71 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -704,6 +704,11 @@ struct kvm_enable_cap {
 #define KVM_VM_TYPE_ARM_IPA_SIZE_MASK	0xffULL
 #define KVM_VM_TYPE_ARM_IPA_SIZE(x)		\
 	((x) & KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
+
+#define KVM_VM_TYPE_ARM_PROTECTED	(1UL << 31)
+#define KVM_VM_TYPE_ARM_MASK		(KVM_VM_TYPE_ARM_IPA_SIZE_MASK | \
+					 KVM_VM_TYPE_ARM_PROTECTED)
+
 /*
  * ioctls for /dev/kvm fds:
  */
@@ -1227,6 +1232,8 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_LOONGARCH_PCHPIC	KVM_DEV_TYPE_LOONGARCH_PCHPIC
 	KVM_DEV_TYPE_LOONGARCH_DMSINTC,
 #define KVM_DEV_TYPE_LOONGARCH_DMSINTC	KVM_DEV_TYPE_LOONGARCH_DMSINTC
+	KVM_DEV_TYPE_ARM_VGIC_V5,
+#define KVM_DEV_TYPE_ARM_VGIC_V5	KVM_DEV_TYPE_ARM_VGIC_V5
 
 	KVM_DEV_TYPE_MAX,
 
diff --git a/include/uapi/linux/trace_mmap.h b/include/uapi/linux/trace_mmap.h
index c102ef35d11e..e8185889a1c8 100644
--- a/include/uapi/linux/trace_mmap.h
+++ b/include/uapi/linux/trace_mmap.h
@@ -17,8 +17,8 @@
  * @entries:		Number of entries in the ring-buffer.
  * @overrun:		Number of entries lost in the ring-buffer.
  * @read:		Number of entries that have been read.
- * @Reserved1:		Internal use only.
- * @Reserved2:		Internal use only.
+ * @pages_lost:		Number of pages overwritten by the writer.
+ * @pages_touched:	Number of pages written by the writer.
  */
 struct trace_buffer_meta {
 	__u32		meta_page_size;
@@ -39,8 +39,8 @@ struct trace_buffer_meta {
 	__u64	overrun;
 	__u64	read;
 
-	__u64	Reserved1;
-	__u64	Reserved2;
+	__u64	pages_lost;
+	__u64	pages_touched;
 };
 
 #define TRACE_MMAP_IOCTL_GET_READER		_IO('R', 0x20)