Merge tag 'trace-v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "The major update to this release is that there's a new arch config
  option called CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS.

  Currently, only x86_64 enables it. All the ftrace callbacks now take a
  struct ftrace_regs instead of a struct pt_regs. If the architecture
  has HAVE_DYNAMIC_FTRACE_WITH_ARGS enabled, then the ftrace_regs will
  have enough information to read the arguments of the function being
  traced, as well as access to the stack pointer.

  This way, if a user (like live kernel patching) only cares about the
  arguments, then it can avoid using the heavier weight "regs" callback,
  that puts in enough information in the struct ftrace_regs to simulate
  a breakpoint exception (needed for kprobes).

  A new config option that audits the timestamps of the ftrace ring
  buffer at most every event recorded.

  Ftrace recursion protection has been cleaned up to move the protection
  to the callback itself (this saves on an extra function call for those
  callbacks).

  Perf now handles its own RCU protection and does not depend on ftrace
  to do it for it (saving on that extra function call).

  New debug option to add "recursed_functions" file to tracefs that
  lists all the places that triggered the recursion protection of the
  function tracer. This will show where things need to be fixed as
  recursion slows down the function tracer.

  The eval enum mapping updates done at boot up are now offloaded to a
  work queue, as it caused a noticeable pause on slow embedded boards.

  Various clean ups and last minute fixes"

* tag 'trace-v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (33 commits)
  tracing: Offload eval map updates to a work queue
  Revert: "ring-buffer: Remove HAVE_64BIT_ALIGNED_ACCESS"
  ring-buffer: Add rb_check_bpage in __rb_allocate_pages
  ring-buffer: Fix two typos in comments
  tracing: Drop unneeded assignment in ring_buffer_resize()
  tracing: Disable ftrace selftests when any tracer is running
  seq_buf: Avoid type mismatch for seq_buf_init
  ring-buffer: Fix a typo in function description
  ring-buffer: Remove obsolete rb_event_is_commit()
  ring-buffer: Add test to validate the time stamp deltas
  ftrace/documentation: Fix RST C code blocks
  tracing: Clean up after filter logic rewriting
  tracing: Remove the useless value assignment in test_create_synth_event()
  livepatch: Use the default ftrace_ops instead of REGS when ARGS is available
  ftrace/x86: Allow for arguments to be passed in to ftrace_regs by default
  ftrace: Have the callbacks receive a struct ftrace_regs instead of pt_regs
  MAINTAINERS: assign ./fs/tracefs to TRACING
  tracing: Fix some typos in comments
  ftrace: Remove unused varible 'ret'
  ring-buffer: Add recording of ring buffer recursion into recursed_functions
  ...

5 files changed, 271 insertions, 14 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 1bd3a0356ae4..9a8ce28e4485 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -7,6 +7,7 @@
 #ifndef _LINUX_FTRACE_H
 #define _LINUX_FTRACE_H
 
+#include <linux/trace_recursion.h>
 #include <linux/trace_clock.h>
 #include <linux/kallsyms.h>
 #include <linux/linkage.h>
@@ -89,15 +90,39 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 struct ftrace_ops;
 
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+
+struct ftrace_regs {
+	struct pt_regs		regs;
+};
+#define arch_ftrace_get_regs(fregs) (&(fregs)->regs)
+
+/*
+ * ftrace_instruction_pointer_set() is to be defined by the architecture
+ * if to allow setting of the instruction pointer from the ftrace_regs
+ * when HAVE_DYNAMIC_FTRACE_WITH_ARGS is set and it supports
+ * live kernel patching.
+ */
+#define ftrace_instruction_pointer_set(fregs, ip) do { } while (0)
+#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
+
+static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs)
+{
+	if (!fregs)
+		return NULL;
+
+	return arch_ftrace_get_regs(fregs);
+}
+
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
-			      struct ftrace_ops *op, struct pt_regs *regs);
+			      struct ftrace_ops *op, struct ftrace_regs *fregs);
 
 ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
 
 /*
  * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are
  * set in the flags member.
- * CONTROL, SAVE_REGS, SAVE_REGS_IF_SUPPORTED, RECURSION_SAFE, STUB and
+ * CONTROL, SAVE_REGS, SAVE_REGS_IF_SUPPORTED, RECURSION, STUB and
  * IPMODIFY are a kind of attribute flags which can be set only before
  * registering the ftrace_ops, and can not be modified while registered.
  * Changing those attribute flags after registering ftrace_ops will
@@ -120,10 +145,10 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
  *            passing regs to the handler.
  *            Note, if this flag is set, the SAVE_REGS flag will automatically
  *            get set upon registering the ftrace_ops, if the arch supports it.
- * RECURSION_SAFE - The ftrace_ops can set this to tell the ftrace infrastructure
- *            that the call back has its own recursion protection. If it does
- *            not set this, then the ftrace infrastructure will add recursion
- *            protection for the caller.
+ * RECURSION - The ftrace_ops can set this to tell the ftrace infrastructure
+ *            that the call back needs recursion protection. If it does
+ *            not set this, then the ftrace infrastructure will assume
+ *            that the callback can handle recursion on its own.
  * STUB   - The ftrace_ops is just a place holder.
  * INITIALIZED - The ftrace_ops has already been initialized (first use time
  *            register_ftrace_function() is called, it will initialized the ops)
@@ -155,7 +180,7 @@ enum {
 	FTRACE_OPS_FL_DYNAMIC			= BIT(1),
 	FTRACE_OPS_FL_SAVE_REGS			= BIT(2),
 	FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED	= BIT(3),
-	FTRACE_OPS_FL_RECURSION_SAFE		= BIT(4),
+	FTRACE_OPS_FL_RECURSION			= BIT(4),
 	FTRACE_OPS_FL_STUB			= BIT(5),
 	FTRACE_OPS_FL_INITIALIZED		= BIT(6),
 	FTRACE_OPS_FL_DELETED			= BIT(7),
@@ -258,7 +283,7 @@ int register_ftrace_function(struct ftrace_ops *ops);
 int unregister_ftrace_function(struct ftrace_ops *ops);
 
 extern void ftrace_stub(unsigned long a0, unsigned long a1,
-			struct ftrace_ops *op, struct pt_regs *regs);
+			struct ftrace_ops *op, struct ftrace_regs *fregs);
 
 #else /* !CONFIG_FUNCTION_TRACER */
 /*
@@ -863,11 +888,11 @@ struct ftrace_graph_ent {
  */
 struct ftrace_graph_ret {
 	unsigned long func; /* Current function */
+	int depth;
 	/* Number of functions that overran the depth limit for current task */
-	unsigned long overrun;
+	unsigned int overrun;
 	unsigned long long calltime;
 	unsigned long long rettime;
-	int depth;
 } __packed;
 
 /* Type of the callback handlers for tracing function graph*/
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index a79404433812..b3a36b0cfc81 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -360,7 +360,7 @@ static inline void wait_for_kprobe_optimizer(void) { }
 #endif /* CONFIG_OPTPROBES */
 #ifdef CONFIG_KPROBES_ON_FTRACE
 extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-				  struct ftrace_ops *ops, struct pt_regs *regs);
+				  struct ftrace_ops *ops, struct ftrace_regs *fregs);
 extern int arch_prepare_kprobe_ftrace(struct kprobe *p);
 #endif
 
diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index fb0205d87d3c..9d6c28cc4d8f 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -30,7 +30,7 @@ static inline void seq_buf_clear(struct seq_buf *s)
 }
 
 static inline void
-seq_buf_init(struct seq_buf *s, unsigned char *buf, unsigned int size)
+seq_buf_init(struct seq_buf *s, char *buf, unsigned int size)
 {
 	s->buffer = buf;
 	s->size = size;
diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
new file mode 100644
index 000000000000..a9f9c5714e65
--- /dev/null
+++ b/include/linux/trace_recursion.h
@@ -0,0 +1,232 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_TRACE_RECURSION_H
+#define _LINUX_TRACE_RECURSION_H
+
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+
+#ifdef CONFIG_TRACING
+
+/* Only current can touch trace_recursion */
+
+/*
+ * For function tracing recursion:
+ *  The order of these bits are important.
+ *
+ *  When function tracing occurs, the following steps are made:
+ *   If arch does not support a ftrace feature:
+ *    call internal function (uses INTERNAL bits) which calls...
+ *   If callback is registered to the "global" list, the list
+ *    function is called and recursion checks the GLOBAL bits.
+ *    then this function calls...
+ *   The function callback, which can use the FTRACE bits to
+ *    check for recursion.
+ *
+ * Now if the arch does not support a feature, and it calls
+ * the global list function which calls the ftrace callback
+ * all three of these steps will do a recursion protection.
+ * There's no reason to do one if the previous caller already
+ * did. The recursion that we are protecting against will
+ * go through the same steps again.
+ *
+ * To prevent the multiple recursion checks, if a recursion
+ * bit is set that is higher than the MAX bit of the current
+ * check, then we know that the check was made by the previous
+ * caller, and we can skip the current check.
+ */
+enum {
+	/* Function recursion bits */
+	TRACE_FTRACE_BIT,
+	TRACE_FTRACE_NMI_BIT,
+	TRACE_FTRACE_IRQ_BIT,
+	TRACE_FTRACE_SIRQ_BIT,
+
+	/* INTERNAL_BITs must be greater than FTRACE_BITs */
+	TRACE_INTERNAL_BIT,
+	TRACE_INTERNAL_NMI_BIT,
+	TRACE_INTERNAL_IRQ_BIT,
+	TRACE_INTERNAL_SIRQ_BIT,
+
+	TRACE_BRANCH_BIT,
+/*
+ * Abuse of the trace_recursion.
+ * As we need a way to maintain state if we are tracing the function
+ * graph in irq because we want to trace a particular function that
+ * was called in irq context but we have irq tracing off. Since this
+ * can only be modified by current, we can reuse trace_recursion.
+ */
+	TRACE_IRQ_BIT,
+
+	/* Set if the function is in the set_graph_function file */
+	TRACE_GRAPH_BIT,
+
+	/*
+	 * In the very unlikely case that an interrupt came in
+	 * at a start of graph tracing, and we want to trace
+	 * the function in that interrupt, the depth can be greater
+	 * than zero, because of the preempted start of a previous
+	 * trace. In an even more unlikely case, depth could be 2
+	 * if a softirq interrupted the start of graph tracing,
+	 * followed by an interrupt preempting a start of graph
+	 * tracing in the softirq, and depth can even be 3
+	 * if an NMI came in at the start of an interrupt function
+	 * that preempted a softirq start of a function that
+	 * preempted normal context!!!! Luckily, it can't be
+	 * greater than 3, so the next two bits are a mask
+	 * of what the depth is when we set TRACE_GRAPH_BIT
+	 */
+
+	TRACE_GRAPH_DEPTH_START_BIT,
+	TRACE_GRAPH_DEPTH_END_BIT,
+
+	/*
+	 * To implement set_graph_notrace, if this bit is set, we ignore
+	 * function graph tracing of called functions, until the return
+	 * function is called to clear it.
+	 */
+	TRACE_GRAPH_NOTRACE_BIT,
+
+	/*
+	 * When transitioning between context, the preempt_count() may
+	 * not be correct. Allow for a single recursion to cover this case.
+	 */
+	TRACE_TRANSITION_BIT,
+
+	/* Used to prevent recursion recording from recursing. */
+	TRACE_RECORD_RECURSION_BIT,
+};
+
+#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (1<<(bit)); } while (0)
+#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(1<<(bit)); } while (0)
+#define trace_recursion_test(bit)	((current)->trace_recursion & (1<<(bit)))
+
+#define trace_recursion_depth() \
+	(((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3)
+#define trace_recursion_set_depth(depth) \
+	do {								\
+		current->trace_recursion &=				\
+			~(3 << TRACE_GRAPH_DEPTH_START_BIT);		\
+		current->trace_recursion |=				\
+			((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT;	\
+	} while (0)
+
+#define TRACE_CONTEXT_BITS	4
+
+#define TRACE_FTRACE_START	TRACE_FTRACE_BIT
+#define TRACE_FTRACE_MAX	((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1)
+
+#define TRACE_LIST_START	TRACE_INTERNAL_BIT
+#define TRACE_LIST_MAX		((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1)
+
+#define TRACE_CONTEXT_MASK	TRACE_LIST_MAX
+
+/*
+ * Used for setting context
+ *  NMI     = 0
+ *  IRQ     = 1
+ *  SOFTIRQ = 2
+ *  NORMAL  = 3
+ */
+enum {
+	TRACE_CTX_NMI,
+	TRACE_CTX_IRQ,
+	TRACE_CTX_SOFTIRQ,
+	TRACE_CTX_NORMAL,
+};
+
+static __always_inline int trace_get_context_bit(void)
+{
+	unsigned long pc = preempt_count();
+
+	if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
+		return TRACE_CTX_NORMAL;
+	else
+		return pc & NMI_MASK ? TRACE_CTX_NMI :
+			pc & HARDIRQ_MASK ? TRACE_CTX_IRQ : TRACE_CTX_SOFTIRQ;
+}
+
+#ifdef CONFIG_FTRACE_RECORD_RECURSION
+extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip);
+# define do_ftrace_record_recursion(ip, pip)				\
+	do {								\
+		if (!trace_recursion_test(TRACE_RECORD_RECURSION_BIT)) { \
+			trace_recursion_set(TRACE_RECORD_RECURSION_BIT); \
+			ftrace_record_recursion(ip, pip);		\
+			trace_recursion_clear(TRACE_RECORD_RECURSION_BIT); \
+		}							\
+	} while (0)
+#else
+# define do_ftrace_record_recursion(ip, pip)	do { } while (0)
+#endif
+
+static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsigned long pip,
+							int start, int max)
+{
+	unsigned int val = READ_ONCE(current->trace_recursion);
+	int bit;
+
+	/* A previous recursion check was made */
+	if ((val & TRACE_CONTEXT_MASK) > max)
+		return 0;
+
+	bit = trace_get_context_bit() + start;
+	if (unlikely(val & (1 << bit))) {
+		/*
+		 * It could be that preempt_count has not been updated during
+		 * a switch between contexts. Allow for a single recursion.
+		 */
+		bit = TRACE_TRANSITION_BIT;
+		if (val & (1 << bit)) {
+			do_ftrace_record_recursion(ip, pip);
+			return -1;
+		}
+	} else {
+		/* Normal check passed, clear the transition to allow it again */
+		val &= ~(1 << TRACE_TRANSITION_BIT);
+	}
+
+	val |= 1 << bit;
+	current->trace_recursion = val;
+	barrier();
+
+	return bit + 1;
+}
+
+static __always_inline void trace_clear_recursion(int bit)
+{
+	if (!bit)
+		return;
+
+	barrier();
+	bit--;
+	trace_recursion_clear(bit);
+}
+
+/**
+ * ftrace_test_recursion_trylock - tests for recursion in same context
+ *
+ * Use this for ftrace callbacks. This will detect if the function
+ * tracing recursed in the same context (normal vs interrupt),
+ *
+ * Returns: -1 if a recursion happened.
+ *           >= 0 if no recursion
+ */
+static __always_inline int ftrace_test_recursion_trylock(unsigned long ip,
+							 unsigned long parent_ip)
+{
+	return trace_test_and_set_recursion(ip, parent_ip, TRACE_FTRACE_START, TRACE_FTRACE_MAX);
+}
+
+/**
+ * ftrace_test_recursion_unlock - called when function callback is complete
+ * @bit: The return of a successful ftrace_test_recursion_trylock()
+ *
+ * This is used at the end of a ftrace callback.
+ */
+static __always_inline void ftrace_test_recursion_unlock(int bit)
+{
+	trace_clear_recursion(bit);
+}
+
+#endif /* CONFIG_TRACING */
+#endif /* _LINUX_TRACE_RECURSION_H */
diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
index 6c30508fca19..5a2c650d9e1c 100644
--- a/include/linux/trace_seq.h
+++ b/include/linux/trace_seq.h
@@ -12,7 +12,7 @@
  */
 
 struct trace_seq {
-	unsigned char		buffer[PAGE_SIZE];
+	char			buffer[PAGE_SIZE];
 	struct seq_buf		seq;
 	int			full;
 };
@@ -51,7 +51,7 @@ static inline int trace_seq_used(struct trace_seq *s)
  * that is about to be written to and then return the result
  * of that write.
  */
-static inline unsigned char *
+static inline char *
 trace_seq_buffer_ptr(struct trace_seq *s)
 {
 	return s->buffer + seq_buf_used(&s->seq);