[RFC PATCH v2 11/58] KVM: arm64: pkvm: Add pkvm_udelay()

[Mostafa Saleh]

From: Jean-Philippe Brucker <jean-philippe@xxxxxxxxxx>

Add a simple delay loop for drivers.

This could use more work. It should be possible to insert a wfe and save
power, but I haven't studied whether it is safe to do so with the host
in control of the event stream. The SMMU driver will use wfe anyway for
frequent waits (provided the implementation can send command queue
events).

Signed-off-by: Mostafa Saleh <smostafa@xxxxxxxxxx>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@xxxxxxxxxx>
---
 arch/arm64/kvm/hyp/include/nvhe/pkvm.h |  3 ++
 arch/arm64/kvm/hyp/nvhe/setup.c        |  4 +++
 arch/arm64/kvm/hyp/nvhe/timer-sr.c     | 42 ++++++++++++++++++++++++++
 3 files changed, 49 insertions(+)

diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
index 3b515ce4c433..8a5554615e40 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
@@ -143,4 +143,7 @@ int pkvm_load_pvmfw_pages(struct pkvm_hyp_vm *vm, u64 ipa, phys_addr_t phys,
 			  u64 size);
 void pkvm_poison_pvmfw_pages(void);
 
+int pkvm_timer_init(void);
+void pkvm_udelay(unsigned long usecs);
+
 #endif /* __ARM64_KVM_NVHE_PKVM_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 46dd68161979..9d09f5f471b9 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -356,6 +356,10 @@ void __noreturn __pkvm_init_finalise(void)
 	if (ret)
 		goto out;
 
+	ret = pkvm_timer_init();
+	if (ret)
+		goto out;
+
 	ret = fix_host_ownership();
 	if (ret)
 		goto out;
diff --git a/arch/arm64/kvm/hyp/nvhe/timer-sr.c b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
index 3aaab20ae5b4..732beb5fe24b 100644
--- a/arch/arm64/kvm/hyp/nvhe/timer-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
@@ -11,6 +11,10 @@
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 
+#include <nvhe/pkvm.h>
+
+static u32 timer_freq;
+
 void __kvm_timer_set_cntvoff(u64 cntvoff)
 {
 	write_sysreg(cntvoff, cntvoff_el2);
@@ -60,3 +64,41 @@ void __timer_enable_traps(struct kvm_vcpu *vcpu)
 
 	sysreg_clear_set(cnthctl_el2, clr, set);
 }
+
+static u64 pkvm_ticks_get(void)
+{
+	return __arch_counter_get_cntvct();
+}
+
+#define SEC_TO_US 1000000
+
+int pkvm_timer_init(void)
+{
+	timer_freq = read_sysreg(cntfrq_el0);
+	/*
+	 * TODO: The highest privileged level is supposed to initialize this
+	 * register. But on some systems (which?), this information is only
+	 * contained in the device-tree, so we'll need to find it out some other
+	 * way.
+	 */
+	if (!timer_freq || timer_freq < SEC_TO_US)
+		return -ENODEV;
+	return 0;
+}
+
+#define pkvm_time_us_to_ticks(us) ((u64)(us) * timer_freq / SEC_TO_US)
+
+void pkvm_udelay(unsigned long usecs)
+{
+	u64 ticks = pkvm_time_us_to_ticks(usecs);
+	u64 start = pkvm_ticks_get();
+
+	while (true) {
+		u64 cur = pkvm_ticks_get();
+
+		if ((cur - start) >= ticks || cur < start)
+			break;
+		/* TODO wfe */
+		cpu_relax();
+	}
+}
-- 
2.47.0.338.g60cca15819-goog