Merge branch kvm-arm64/hyp-tracing into kvmarm-master/next

* kvm-arm64/hyp-tracing: (40 commits)
  : .
  : EL2 tracing support, adding both 'remote' ring-buffer
  : infrastructure and the tracing itself, courtesy of
  : Vincent Donnefort. From the cover letter:
  :
  : "The growing set of features supported by the hypervisor in protected
  : mode necessitates debugging and profiling tools. Tracefs is the
  : ideal candidate for this task:
  :
  :   * It is simple to use and to script.
  :
  :   * It is supported by various tools, from the trace-cmd CLI to the
  :     Android web-based perfetto.
  :
  :   * The ring-buffer, where are stored trace events consists of linked
  :     pages, making it an ideal structure for sharing between kernel and
  :     hypervisor.
  :
  : This series first introduces a new generic way of creating remote events and
  : remote buffers. Then it adds support to the pKVM hypervisor."
  : .
  tracing: selftests: Extend hotplug testing for trace remotes
  tracing: Non-consuming read for trace remotes with an offline CPU
  tracing: Adjust cmd_check_undefined to show unexpected undefined symbols
  tracing: Restore accidentally removed SPDX tag
  KVM: arm64: avoid unused-variable warning
  tracing: Generate undef symbols allowlist for simple_ring_buffer
  KVM: arm64: tracing: add ftrace dependency
  tracing: add more symbols to whitelist
  tracing: Update undefined symbols allow list for simple_ring_buffer
  KVM: arm64: Fix out-of-tree build for nVHE/pKVM tracing
  tracing: selftests: Add hypervisor trace remote tests
  KVM: arm64: Add selftest event support to nVHE/pKVM hyp
  KVM: arm64: Add hyp_enter/hyp_exit events to nVHE/pKVM hyp
  KVM: arm64: Add event support to the nVHE/pKVM hyp and trace remote
  KVM: arm64: Add trace reset to the nVHE/pKVM hyp
  KVM: arm64: Sync boot clock with the nVHE/pKVM hyp
  KVM: arm64: Add trace remote for the nVHE/pKVM hyp
  KVM: arm64: Add tracing capability for the nVHE/pKVM hyp
  KVM: arm64: Support unaligned fixmap in the pKVM hyp
  KVM: arm64: Initialise hyp_nr_cpus for nVHE hyp
  ...

Signed-off-by: Marc Zyngier <maz@kernel.org>

7 files changed, 322 insertions, 4 deletions

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/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)