Merge tag 'trace-v6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing updates from Steven Rostedt:

 - User events are finally ready!

   After lots of collaboration between various parties, we finally
   locked down on a stable interface for user events that can also work
   with user space only tracing.

   This is implemented by telling the kernel (or user space library, but
   that part is user space only and not part of this patch set), where
   the variable is that the application uses to know if something is
   listening to the trace.

   There's also an interface to tell the kernel about these events,
   which will show up in the /sys/kernel/tracing/events/user_events/
   directory, where it can be enabled.

   When it's enabled, the kernel will update the variable, to tell the
   application to start writing to the kernel.

   See https://lwn.net/Articles/927595/

 - Cleaned up the direct trampolines code to simplify arm64 addition of
   direct trampolines.

   Direct trampolines use the ftrace interface but instead of jumping to
   the ftrace trampoline, applications (mostly BPF) can register their
   own trampoline for performance reasons.

 - Some updates to the fprobe infrastructure. fprobes are more efficient
   than kprobes, as it does not need to save all the registers that
   kprobes on ftrace do. More work needs to be done before the fprobes
   will be exposed as dynamic events.

 - More updates to references to the obsolete path of
   /sys/kernel/debug/tracing for the new /sys/kernel/tracing path.

 - Add a seq_buf_do_printk() helper to seq_bufs, to print a large buffer
   line by line instead of all at once.

   There are users in production kernels that have a large data dump
   that originally used printk() directly, but the data dump was larger
   than what printk() allowed as a single print.

   Using seq_buf() to do the printing fixes that.

 - Add /sys/kernel/tracing/touched_functions that shows all functions
   that was every traced by ftrace or a direct trampoline. This is used
   for debugging issues where a traced function could have caused a
   crash by a bpf program or live patching.

 - Add a "fields" option that is similar to "raw" but outputs the fields
   of the events. It's easier to read by humans.

 - Some minor fixes and clean ups.

* tag 'trace-v6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (41 commits)
  ring-buffer: Sync IRQ works before buffer destruction
  tracing: Add missing spaces in trace_print_hex_seq()
  ring-buffer: Ensure proper resetting of atomic variables in ring_buffer_reset_online_cpus
  recordmcount: Fix memory leaks in the uwrite function
  tracing/user_events: Limit max fault-in attempts
  tracing/user_events: Prevent same address and bit per process
  tracing/user_events: Ensure bit is cleared on unregister
  tracing/user_events: Ensure write index cannot be negative
  seq_buf: Add seq_buf_do_printk() helper
  tracing: Fix print_fields() for __dyn_loc/__rel_loc
  tracing/user_events: Set event filter_type from type
  ring-buffer: Clearly check null ptr returned by rb_set_head_page()
  tracing: Unbreak user events
  tracing/user_events: Use print_format_fields() for trace output
  tracing/user_events: Align structs with tabs for readability
  tracing/user_events: Limit global user_event count
  tracing/user_events: Charge event allocs to cgroups
  tracing/user_events: Update documentation for ABI
  tracing/user_events: Use write ABI in example
  tracing/user_events: Add ABI self-test
  ...

5 files changed, 84 insertions, 39 deletions

diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h
index 1c2bde0ead73..47fefc7f363b 100644
--- a/include/linux/fprobe.h
+++ b/include/linux/fprobe.h
@@ -13,6 +13,8 @@
  * @nmissed: The counter for missing events.
  * @flags: The status flag.
  * @rethook: The rethook data structure. (internal data)
+ * @entry_data_size: The private data storage size.
+ * @nr_maxactive: The max number of active functions.
  * @entry_handler: The callback function for function entry.
  * @exit_handler: The callback function for function exit.
  */
@@ -29,9 +31,13 @@ struct fprobe {
 	unsigned long		nmissed;
 	unsigned int		flags;
 	struct rethook		*rethook;
+	size_t			entry_data_size;
+	int			nr_maxactive;
 
-	void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs);
-	void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs);
+	int (*entry_handler)(struct fprobe *fp, unsigned long entry_ip,
+			     struct pt_regs *regs, void *entry_data);
+	void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip,
+			     struct pt_regs *regs, void *entry_data);
 };
 
 /* This fprobe is soft-disabled. */
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 3e56cb6f40d1..6954e4ed5bbf 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -548,6 +548,7 @@ bool is_ftrace_trampoline(unsigned long addr);
  *  DIRECT   - there is a direct function to call
  *  CALL_OPS - the record can use callsite-specific ops
  *  CALL_OPS_EN - the function is set up to use callsite-specific ops
+ *  TOUCHED  - A callback was added since boot up
  *
  * When a new ftrace_ops is registered and wants a function to save
  * pt_regs, the rec->flags REGS is set. When the function has been
@@ -567,9 +568,10 @@ enum {
 	FTRACE_FL_DIRECT_EN	= (1UL << 23),
 	FTRACE_FL_CALL_OPS	= (1UL << 22),
 	FTRACE_FL_CALL_OPS_EN	= (1UL << 21),
+	FTRACE_FL_TOUCHED	= (1UL << 20),
 };
 
-#define FTRACE_REF_MAX_SHIFT	21
+#define FTRACE_REF_MAX_SHIFT	20
 #define FTRACE_REF_MAX		((1UL << FTRACE_REF_MAX_SHIFT) - 1)
 
 #define ftrace_rec_count(rec)	((rec)->flags & FTRACE_REF_MAX)
@@ -628,6 +630,7 @@ enum {
 	FTRACE_ITER_PROBE	= (1 << 4),
 	FTRACE_ITER_MOD		= (1 << 5),
 	FTRACE_ITER_ENABLED	= (1 << 6),
+	FTRACE_ITER_TOUCHED	= (1 << 7),
 };
 
 void arch_ftrace_update_code(int command);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dc4ad4c58fae..eed5d65b8d1f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -70,6 +70,7 @@ struct sighand_struct;
 struct signal_struct;
 struct task_delay_info;
 struct task_group;
+struct user_event_mm;
 
 /*
  * Task state bitmask. NOTE! These bits are also
@@ -1529,6 +1530,10 @@ struct task_struct {
 	union rv_task_monitor		rv[RV_PER_TASK_MONITORS];
 #endif
 
+#ifdef CONFIG_USER_EVENTS
+	struct user_event_mm		*user_event_mm;
+#endif
+
 	/*
 	 * New fields for task_struct should be added above here, so that
 	 * they are included in the randomized portion of task_struct.
diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index 5b31c5147969..515d7fcb9634 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -159,4 +159,6 @@ extern int
 seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary);
 #endif
 
+void seq_buf_do_printk(struct seq_buf *s, const char *lvl);
+
 #endif /* _LINUX_SEQ_BUF_H */
diff --git a/include/linux/user_events.h b/include/linux/user_events.h
index 592a3fbed98e..2847f5a18a86 100644
--- a/include/linux/user_events.h
+++ b/include/linux/user_events.h
@@ -1,54 +1,83 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (c) 2021, Microsoft Corporation.
+ * Copyright (c) 2022, Microsoft Corporation.
  *
  * Authors:
  *   Beau Belgrave <beaub@linux.microsoft.com>
  */
-#ifndef _UAPI_LINUX_USER_EVENTS_H
-#define _UAPI_LINUX_USER_EVENTS_H
 
-#include <linux/types.h>
-#include <linux/ioctl.h>
+#ifndef _LINUX_USER_EVENTS_H
+#define _LINUX_USER_EVENTS_H
 
-#ifdef __KERNEL__
-#include <linux/uio.h>
-#else
-#include <sys/uio.h>
-#endif
+#include <linux/list.h>
+#include <linux/refcount.h>
+#include <linux/mm_types.h>
+#include <linux/workqueue.h>
+#include <uapi/linux/user_events.h>
 
-#define USER_EVENTS_SYSTEM "user_events"
-#define USER_EVENTS_PREFIX "u:"
+#ifdef CONFIG_USER_EVENTS
+struct user_event_mm {
+	struct list_head	link;
+	struct list_head	enablers;
+	struct mm_struct	*mm;
+	struct user_event_mm	*next;
+	refcount_t		refcnt;
+	refcount_t		tasks;
+	struct rcu_work		put_rwork;
+};
 
-/* Create dynamic location entry within a 32-bit value */
-#define DYN_LOC(offset, size) ((size) << 16 | (offset))
+extern void user_event_mm_dup(struct task_struct *t,
+			      struct user_event_mm *old_mm);
 
-/*
- * Describes an event registration and stores the results of the registration.
- * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum
- * must set the size and name_args before invocation.
- */
-struct user_reg {
+extern void user_event_mm_remove(struct task_struct *t);
+
+static inline void user_events_fork(struct task_struct *t,
+				    unsigned long clone_flags)
+{
+	struct user_event_mm *old_mm;
 
-	/* Input: Size of the user_reg structure being used */
-	__u32 size;
+	if (!t || !current->user_event_mm)
+		return;
 
-	/* Input: Pointer to string with event name, description and flags */
-	__u64 name_args;
+	old_mm = current->user_event_mm;
 
-	/* Output: Bitwise index of the event within the status page */
-	__u32 status_bit;
+	if (clone_flags & CLONE_VM) {
+		t->user_event_mm = old_mm;
+		refcount_inc(&old_mm->tasks);
+		return;
+	}
 
-	/* Output: Index of the event to use when writing data */
-	__u32 write_index;
-} __attribute__((__packed__));
+	user_event_mm_dup(t, old_mm);
+}
 
-#define DIAG_IOC_MAGIC '*'
+static inline void user_events_execve(struct task_struct *t)
+{
+	if (!t || !t->user_event_mm)
+		return;
+
+	user_event_mm_remove(t);
+}
+
+static inline void user_events_exit(struct task_struct *t)
+{
+	if (!t || !t->user_event_mm)
+		return;
+
+	user_event_mm_remove(t);
+}
+#else
+static inline void user_events_fork(struct task_struct *t,
+				    unsigned long clone_flags)
+{
+}
 
-/* Requests to register a user_event */
-#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg*)
+static inline void user_events_execve(struct task_struct *t)
+{
+}
 
-/* Requests to delete a user_event */
-#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*)
+static inline void user_events_exit(struct task_struct *t)
+{
+}
+#endif /* CONFIG_USER_EVENTS */
 
-#endif /* _UAPI_LINUX_USER_EVENTS_H */
+#endif /* _LINUX_USER_EVENTS_H */