[PATCH v5 20/25] KVM: arm64: Sync boot clock with the pKVM hyp

@@ -87,6 +87,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_load,
 	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_put,
 	__KVM_HOST_SMCCC_FUNC___pkvm_tlb_flush_vmid,
+	__KVM_HOST_SMCCC_FUNC___pkvm_update_clock_tracing,
 	__KVM_HOST_SMCCC_FUNC___pkvm_load_tracing,
 	__KVM_HOST_SMCCC_FUNC___pkvm_unload_tracing,
 	__KVM_HOST_SMCCC_FUNC___pkvm_enable_tracing,

@@ -7,6 +7,7 @@
 void *tracing_reserve_entry(unsigned long length);
 void tracing_commit_entry(void);
 
+void __pkvm_update_clock_tracing(u32 mult, u32 shift, u64 epoch_ns, u64 epoch_cyc);
 int __pkvm_load_tracing(unsigned long desc_va, size_t desc_size);
 void __pkvm_unload_tracing(void);
 int __pkvm_enable_tracing(bool enable);

@@ -15,6 +16,8 @@ int __pkvm_swap_reader_tracing(unsigned int cpu);
 static inline void *tracing_reserve_entry(unsigned long length) { return NULL; }
 static inline void tracing_commit_entry(void) { }
 
+static inline
+void __pkvm_update_clock_tracing(u32 mult, u32 shift, u64 epoch_ns, u64 epoch_cyc) { }
 static inline int __pkvm_load_tracing(unsigned long desc_va, size_t desc_size) { return -ENODEV; }
 static inline void __pkvm_unload_tracing(void) { }
 static inline int __pkvm_enable_tracing(bool enable) { return -ENODEV; }

@@ -571,6 +571,18 @@ static void handle___pkvm_teardown_vm(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) = __pkvm_teardown_vm(handle);
 }
 
+static void handle___pkvm_update_clock_tracing(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(u32, mult, host_ctxt, 1);
+	DECLARE_REG(u32, shift, host_ctxt, 2);
+	DECLARE_REG(u64, epoch_ns, host_ctxt, 3);
+	DECLARE_REG(u64, epoch_cyc, host_ctxt, 4);
+
+	__pkvm_update_clock_tracing(mult, shift, epoch_ns, epoch_cyc);
+
+	cpu_reg(host_ctxt, 1) = 0;
+}
+
 static void handle___pkvm_load_tracing(struct kvm_cpu_context *host_ctxt)
 {
 	 DECLARE_REG(unsigned long, desc_hva, host_ctxt, 1);

@@ -639,6 +651,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_vcpu_load),
 	HANDLE_FUNC(__pkvm_vcpu_put),
 	HANDLE_FUNC(__pkvm_tlb_flush_vmid),
+	HANDLE_FUNC(__pkvm_update_clock_tracing),
 	HANDLE_FUNC(__pkvm_load_tracing),
 	HANDLE_FUNC(__pkvm_unload_tracing),
 	HANDLE_FUNC(__pkvm_enable_tracing),

@@ -249,3 +249,19 @@ int __pkvm_swap_reader_tracing(unsigned int cpu)
 
 	return ret;
 }
+
+void __pkvm_update_clock_tracing(u32 mult, u32 shift, u64 epoch_ns, u64 epoch_cyc)
+{
+	int cpu;
+
+	/* After this loop, all CPUs are observing the new bank... */
+	for (cpu = 0; cpu < hyp_nr_cpus; cpu++) {
+		struct simple_rb_per_cpu *simple_rb = per_cpu_ptr(trace_buffer.simple_rbs, cpu);
+
+		while (READ_ONCE(simple_rb->status) == SIMPLE_RB_WRITING)
+			;
+	}
+
+	/* ...we can now override the old one and swap. */
+	trace_clock_update(mult, shift, epoch_ns, epoch_cyc);
+}

@@ -5,6 +5,7 @@
  */
 
 #include <linux/trace_remote.h>
+#include <linux/tracefs.h>
 #include <linux/simple_ring_buffer.h>
 
 #include <asm/kvm_host.h>

@@ -12,6 +13,121 @@
 
 #include "hyp_trace.h"
 
+/* Same 10min used by clocksource when width is more than 32-bits */
+#define CLOCK_MAX_CONVERSION_S	600
+/*
+ * Time to give for the clock init. Long enough to get a good mult/shift
+ * estimation. Short enough to not delay the tracing start too much.
+ */
+#define CLOCK_INIT_MS		100
+/*
+ * Time between clock checks. Must be small enough to catch clock deviation when
+ * it is still tiny.
+ */
+#define CLOCK_UPDATE_MS		500
+
+static struct hyp_trace_clock {
+	u64			cycles;
+	u64			cyc_overflow64;
+	u64			boot;
+	u32			mult;
+	u32			shift;
+	struct delayed_work	work;
+	struct completion	ready;
+	struct mutex		lock;
+	bool			running;
+} hyp_clock;
+
+static void __hyp_clock_work(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct hyp_trace_clock *hyp_clock;
+	struct system_time_snapshot snap;
+	u64 rate, delta_cycles;
+	u64 boot, delta_boot;
+
+	hyp_clock = container_of(dwork, struct hyp_trace_clock, work);
+
+	ktime_get_snapshot(&snap);
+	boot = ktime_to_ns(snap.boot);
+
+	delta_boot = boot - hyp_clock->boot;
+	delta_cycles = snap.cycles - hyp_clock->cycles;
+
+	/* Compare hyp clock with the kernel boot clock */
+	if (hyp_clock->mult) {
+		u64 err, cur = delta_cycles;
+
+		if (WARN_ON_ONCE(cur >= hyp_clock->cyc_overflow64)) {
+			__uint128_t tmp = (__uint128_t)cur * hyp_clock->mult;
+
+			cur = tmp >> hyp_clock->shift;
+		} else {
+			cur *= hyp_clock->mult;
+			cur >>= hyp_clock->shift;
+		}
+		cur += hyp_clock->boot;
+
+		err = abs_diff(cur, boot);
+		/* No deviation, only update epoch if necessary */
+		if (!err) {
+			if (delta_cycles >= (hyp_clock->cyc_overflow64 >> 1))
+				goto fast_forward;
+
+			goto resched;
+		}
+
+		/* Warn if the error is above tracing precision (1us) */
+		if (err > NSEC_PER_USEC)
+			pr_warn_ratelimited("hyp trace clock off by %lluus\n",
+					    err / NSEC_PER_USEC);
+	}
+
+	rate = div64_u64(delta_cycles * NSEC_PER_SEC, delta_boot);
+
+	clocks_calc_mult_shift(&hyp_clock->mult, &hyp_clock->shift,
+			       rate, NSEC_PER_SEC, CLOCK_MAX_CONVERSION_S);
+
+	/* Add a comfortable 50% margin */
+	hyp_clock->cyc_overflow64 = (U64_MAX / hyp_clock->mult) >> 1;
+
+fast_forward:
+	hyp_clock->cycles = snap.cycles;
+	hyp_clock->boot = boot;
+	kvm_call_hyp_nvhe(__pkvm_update_clock_tracing, hyp_clock->mult,
+			  hyp_clock->shift, hyp_clock->boot, hyp_clock->cycles);
+	complete(&hyp_clock->ready);
+
+resched:
+	schedule_delayed_work(&hyp_clock->work,
+			      msecs_to_jiffies(CLOCK_UPDATE_MS));
+}
+
+static void hyp_trace_clock_enable(struct hyp_trace_clock *hyp_clock, bool enable)
+{
+	struct system_time_snapshot snap;
+
+	if (hyp_clock->running == enable)
+		return;
+
+	if (!enable) {
+		cancel_delayed_work_sync(&hyp_clock->work);
+		hyp_clock->running = false;
+	}
+
+	ktime_get_snapshot(&snap);
+
+	hyp_clock->boot = ktime_to_ns(snap.boot);
+	hyp_clock->cycles = snap.cycles;
+	hyp_clock->mult = 0;
+
+	init_completion(&hyp_clock->ready);
+	INIT_DELAYED_WORK(&hyp_clock->work, __hyp_clock_work);
+	schedule_delayed_work(&hyp_clock->work, msecs_to_jiffies(CLOCK_INIT_MS));
+	wait_for_completion(&hyp_clock->ready);
+	hyp_clock->running = true;
+}
+
 /* Access to this struct within the trace_remote_callbacks are protected by the trace_remote lock */
 struct hyp_trace_buffer {
 	struct hyp_trace_desc	*desc;

@@ -173,6 +289,8 @@ static void hyp_trace_unload(struct trace_buffer_desc *desc, void *priv)
 
 static int hyp_trace_enable_tracing(bool enable, void *priv)
 {
+	hyp_trace_clock_enable(&hyp_clock, enable);
+
 	return kvm_call_hyp_nvhe(__pkvm_enable_tracing, enable);
 }
 

@@ -191,7 +309,22 @@ static int hyp_trace_enable_event(unsigned short id, bool enable, void *priv)
 	return 0;
 }
 
+static int hyp_trace_clock_show(struct seq_file *m, void *v)
+{
+	seq_puts(m, "[boot]\n");
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(hyp_trace_clock);
+
+static int hyp_trace_init_tracefs(struct dentry *d, void *priv)
+{
+	return tracefs_create_file("trace_clock", 0440, d, NULL, &hyp_trace_clock_fops) ?
+		0 : -ENOMEM;
+}
+
 static struct trace_remote_callbacks trace_remote_callbacks = {
+	.init			= hyp_trace_init_tracefs,
 	.load_trace_buffer	= hyp_trace_load,
 	.unload_trace_buffer	= hyp_trace_unload,
 	.enable_tracing		= hyp_trace_enable_tracing,