When running with KVM protected mode, the hypervisor is able to generate
events into tracefs compatible ring-buffers. Create a trace remote so
the kernel can read those buffers.
This currently doesn't provide any event support which will come later.
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 580426cdbe77..64db254f0448 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -87,6 +87,7 @@ config PKVM_TRACING
bool
depends on KVM
depends on TRACING
+ select TRACE_REMOTE
select SIMPLE_RING_BUFFER
default y
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 3ebc0570345c..2c184e3abd8e 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -30,6 +30,8 @@ kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o pmu.o
kvm-$(CONFIG_ARM64_PTR_AUTH) += pauth.o
kvm-$(CONFIG_PTDUMP_STAGE2_DEBUGFS) += ptdump.o
+kvm-$(CONFIG_PKVM_TRACING) += hyp_trace.o
+
always-y := hyp_constants.h hyp-constants.s
define rule_gen_hyp_constants
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 870953b4a8a7..c485e54417e2 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -24,6 +24,7 @@
#define CREATE_TRACE_POINTS
#include "trace_arm.h"
+#include "hyp_trace.h"
#include <linux/uaccess.h>
#include <asm/ptrace.h>
@@ -2345,6 +2346,9 @@ static int __init init_subsystems(void)
kvm_register_perf_callbacks(NULL);
+ err = hyp_trace_init();
+ if (err)
+ kvm_err("Failed to initialize Hyp tracing\n");
out:
if (err)
hyp_cpu_pm_exit();
diff --git a/arch/arm64/kvm/hyp_trace.c b/arch/arm64/kvm/hyp_trace.c
new file mode 100644
index 000000000000..98051c3fb0c2
--- /dev/null
+++ b/arch/arm64/kvm/hyp_trace.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 Google LLC
+ * Author: Vincent Donnefort <vdonnefort@google.com>
+ */
+
+#include <linux/trace_remote.h>
+#include <linux/simple_ring_buffer.h>
+
+#include <asm/kvm_host.h>
+#include <asm/kvm_hyptrace.h>
+
+#include "hyp_trace.h"
+
+/* Access to this struct within the trace_remote_callbacks are protected by the trace_remote lock */
+static struct hyp_trace_buffer {
+ struct hyp_trace_desc *desc;
+ size_t desc_size;
+} trace_buffer;
+
+static int hyp_trace_buffer_alloc_bpages_backing(struct hyp_trace_buffer *trace_buffer, size_t size)
+{
+ int nr_bpages = (PAGE_ALIGN(size) / PAGE_SIZE) + 1;
+ size_t backing_size;
+ void *start;
+
+ backing_size = PAGE_ALIGN(sizeof(struct simple_buffer_page) * nr_bpages *
+ num_possible_cpus());
+
+ start = alloc_pages_exact(backing_size, GFP_KERNEL_ACCOUNT);
+ if (!start)
+ return -ENOMEM;
+
+ trace_buffer->desc->bpages_backing_start = (unsigned long)start;
+ trace_buffer->desc->bpages_backing_size = backing_size;
+
+ return 0;
+}
+
+static void hyp_trace_buffer_free_bpages_backing(struct hyp_trace_buffer *trace_buffer)
+{
+ free_pages_exact((void *)trace_buffer->desc->bpages_backing_start,
+ trace_buffer->desc->bpages_backing_size);
+}
+
+static int __load_page(unsigned long va)
+{
+ return kvm_call_hyp_nvhe(__pkvm_host_share_hyp, virt_to_pfn((void *)va), 1);
+}
+
+static void __unload_page(unsigned long va)
+{
+ WARN_ON(kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, virt_to_pfn((void *)va), 1));
+}
+
+static void hyp_trace_buffer_unload_pages(struct hyp_trace_buffer *trace_buffer, int last_cpu)
+{
+ struct ring_buffer_desc *rb_desc;
+ int cpu, p;
+
+ for_each_ring_buffer_desc(rb_desc, cpu, &trace_buffer->desc->trace_buffer_desc) {
+ if (cpu > last_cpu)
+ break;
+
+ __unload_page(rb_desc->meta_va);
+ for (p = 0; p < rb_desc->nr_page_va; p++)
+ __unload_page(rb_desc->page_va[p]);
+ }
+}
+
+static int hyp_trace_buffer_load_pages(struct hyp_trace_buffer *trace_buffer)
+{
+ struct ring_buffer_desc *rb_desc;
+ int cpu, p, ret = 0;
+
+ for_each_ring_buffer_desc(rb_desc, cpu, &trace_buffer->desc->trace_buffer_desc) {
+ ret = __load_page(rb_desc->meta_va);
+ if (ret)
+ break;
+
+ for (p = 0; p < rb_desc->nr_page_va; p++) {
+ ret = __load_page(rb_desc->page_va[p]);
+ if (ret)
+ break;
+ }
+
+ if (ret) {
+ for (p--; p >= 0; p--)
+ __unload_page(rb_desc->page_va[p]);
+ break;
+ }
+ }
+
+ if (ret)
+ hyp_trace_buffer_unload_pages(trace_buffer, cpu--);
+
+ return ret;
+}
+
+static struct trace_buffer_desc *hyp_trace_load(unsigned long size, void *priv)
+{
+ struct hyp_trace_buffer *trace_buffer = priv;
+ struct hyp_trace_desc *desc;
+ size_t desc_size;
+ int ret;
+
+ if (WARN_ON(trace_buffer->desc))
+ return ERR_PTR(-EINVAL);
+
+ desc_size = trace_buffer_desc_size(size, num_possible_cpus());
+ if (desc_size == SIZE_MAX)
+ return ERR_PTR(-E2BIG);
+
+ /*
+ * The hypervisor will unmap the descriptor from the host to protect the reading. Page
+ * granularity for the allocation ensures no other useful data will be unmapped.
+ */
+ desc_size = PAGE_ALIGN(desc_size);
+ desc = (struct hyp_trace_desc *)alloc_pages_exact(desc_size, GFP_KERNEL);
+ if (!desc)
+ return ERR_PTR(-ENOMEM);
+
+ trace_buffer->desc = desc;
+
+ ret = hyp_trace_buffer_alloc_bpages_backing(trace_buffer, size);
+ if (ret)
+ goto err_free_desc;
+
+ ret = trace_remote_alloc_buffer(&desc->trace_buffer_desc, desc_size, size,
+ cpu_possible_mask);
+ if (ret)
+ goto err_free_backing;
+
+ ret = hyp_trace_buffer_load_pages(trace_buffer);
+ if (ret)
+ goto err_free_buffer;
+
+ ret = kvm_call_hyp_nvhe(__pkvm_load_tracing, (unsigned long)desc, desc_size);
+ if (ret)
+ goto err_unload_pages;
+
+ return &desc->trace_buffer_desc;
+
+err_unload_pages:
+ hyp_trace_buffer_unload_pages(trace_buffer, INT_MAX);
+
+err_free_buffer:
+ trace_remote_free_buffer(&desc->trace_buffer_desc);
+
+err_free_backing:
+ hyp_trace_buffer_free_bpages_backing(trace_buffer);
+
+err_free_desc:
+ free_pages_exact(desc, desc_size);
+ trace_buffer->desc = NULL;
+
+ return ERR_PTR(ret);
+}
+
+static void hyp_trace_unload(struct trace_buffer_desc *desc, void *priv)
+{
+ struct hyp_trace_buffer *trace_buffer = priv;
+
+ if (WARN_ON(desc != &trace_buffer->desc->trace_buffer_desc))
+ return;
+
+ kvm_call_hyp_nvhe(__pkvm_unload_tracing);
+ hyp_trace_buffer_unload_pages(trace_buffer, INT_MAX);
+ trace_remote_free_buffer(desc);
+ hyp_trace_buffer_free_bpages_backing(trace_buffer);
+ free_pages_exact(trace_buffer->desc, trace_buffer->desc_size);
+ trace_buffer->desc = NULL;
+}
+
+static int hyp_trace_enable_tracing(bool enable, void *priv)
+{
+ return kvm_call_hyp_nvhe(__pkvm_enable_tracing, enable);
+}
+
+static int hyp_trace_swap_reader_page(unsigned int cpu, void *priv)
+{
+ return kvm_call_hyp_nvhe(__pkvm_swap_reader_tracing, cpu);
+}
+
+static int hyp_trace_reset(unsigned int cpu, void *priv)
+{
+ return 0;
+}
+
+static int hyp_trace_enable_event(unsigned short id, bool enable, void *priv)
+{
+ return 0;
+}
+
+static struct trace_remote_callbacks trace_remote_callbacks = {
+ .load_trace_buffer = hyp_trace_load,
+ .unload_trace_buffer = hyp_trace_unload,
+ .enable_tracing = hyp_trace_enable_tracing,
+ .swap_reader_page = hyp_trace_swap_reader_page,
+ .reset = hyp_trace_reset,
+ .enable_event = hyp_trace_enable_event,
+};
+
+int hyp_trace_init(void)
+{
+ if (!is_protected_kvm_enabled())
+ return 0;
+
+ return trace_remote_register("hypervisor", &trace_remote_callbacks, &trace_buffer, NULL, 0);
+}
diff --git a/arch/arm64/kvm/hyp_trace.h b/arch/arm64/kvm/hyp_trace.h
new file mode 100644
index 000000000000..54d8b1f44ca5
--- /dev/null
+++ b/arch/arm64/kvm/hyp_trace.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ARM64_KVM_HYP_TRACE_H__
+#define __ARM64_KVM_HYP_TRACE_H__
+
+#ifdef CONFIG_PKVM_TRACING
+int hyp_trace_init(void);
+#else
+static inline int hyp_trace_init(void) { return 0; }
+#endif
+#endif
--
2.51.2.1041.gc1ab5b90ca-goog