Merge tag 'trace-v5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:

 - kprobes: Restructured stack unwinder to show properly on x86 when a
   stack dump happens from a kretprobe callback.

 - Fix to bootconfig parsing

 - Have tracefs allow owner and group permissions by default (only
   denying others). There's been pressure to allow non root to tracefs
   in a controlled fashion, and using groups is probably the safest.

 - Bootconfig memory managament updates.

 - Bootconfig clean up to have the tools directory be less dependent on
   changes in the kernel tree.

 - Allow perf to be traced by function tracer.

 - Rewrite of function graph tracer to be a callback from the function
   tracer instead of having its own trampoline (this change will happen
   on an arch by arch basis, and currently only x86_64 implements it).

 - Allow multiple direct trampolines (bpf hooks to functions) be batched
   together in one synchronization.

 - Allow histogram triggers to add variables that can perform
   calculations against the event's fields.

 - Use the linker to determine architecture callbacks from the ftrace
   trampoline to allow for proper parameter prototypes and prevent
   warnings from the compiler.

 - Extend histogram triggers to key off of variables.

 - Have trace recursion use bit magic to determine preempt context over
   if branches.

 - Have trace recursion disable preemption as all use cases do anyway.

 - Added testing for verification of tracing utilities.

 - Various small clean ups and fixes.

* tag 'trace-v5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (101 commits)
  tracing/histogram: Fix semicolon.cocci warnings
  tracing/histogram: Fix documentation inline emphasis warning
  tracing: Increase PERF_MAX_TRACE_SIZE to handle Sentinel1 and docker together
  tracing: Show size of requested perf buffer
  bootconfig: Initialize ret in xbc_parse_tree()
  ftrace: do CPU checking after preemption disabled
  ftrace: disable preemption when recursion locked
  tracing/histogram: Document expression arithmetic and constants
  tracing/histogram: Optimize division by a power of 2
  tracing/histogram: Covert expr to const if both operands are constants
  tracing/histogram: Simplify handling of .sym-offset in expressions
  tracing: Fix operator precedence for hist triggers expression
  tracing: Add division and multiplication support for hist triggers
  tracing: Add support for creating hist trigger variables from literal
  selftests/ftrace: Stop tracing while reading the trace file by default
  MAINTAINERS: Update KPROBES and TRACING entries
  test_kprobes: Move it from kernel/ to lib/
  docs, kprobes: Remove invalid URL and add new reference
  samples/kretprobes: Fix return value if register_kretprobe() failed
  lib/bootconfig: Fix the xbc_get_info kerneldoc
  ...

8 files changed, 187 insertions, 67 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index f2984af2b85b..8771c435f34b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -164,16 +164,22 @@
  * Need to also make ftrace_stub_graph point to ftrace_stub
  * so that the same stub location may have different protocols
  * and not mess up with C verifiers.
+ *
+ * ftrace_ops_list_func will be defined as arch_ftrace_ops_list_func
+ * as some archs will have a different prototype for that function
+ * but ftrace_ops_list_func() will have a single prototype.
  */
 #define MCOUNT_REC()	. = ALIGN(8);				\
 			__start_mcount_loc = .;			\
 			KEEP(*(__mcount_loc))			\
 			KEEP(*(__patchable_function_entries))	\
 			__stop_mcount_loc = .;			\
-			ftrace_stub_graph = ftrace_stub;
+			ftrace_stub_graph = ftrace_stub;	\
+			ftrace_ops_list_func = arch_ftrace_ops_list_func;
 #else
 # ifdef CONFIG_FUNCTION_TRACER
-#  define MCOUNT_REC()	ftrace_stub_graph = ftrace_stub;
+#  define MCOUNT_REC()	ftrace_stub_graph = ftrace_stub;	\
+			ftrace_ops_list_func = arch_ftrace_ops_list_func;
 # else
 #  define MCOUNT_REC()
 # endif
diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index 537e1b991f11..a4665c7ab07c 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -7,8 +7,18 @@
  * Author: Masami Hiramatsu <mhiramat@kernel.org>
  */
 
+#ifdef __KERNEL__
 #include <linux/kernel.h>
 #include <linux/types.h>
+#else /* !__KERNEL__ */
+/*
+ * NOTE: This is only for tools/bootconfig, because tools/bootconfig will
+ * run the parser sanity test.
+ * This does NOT mean linux/bootconfig.h is available in the user space.
+ * However, if you change this file, please make sure the tools/bootconfig
+ * has no issue on building and running.
+ */
+#endif
 
 #define BOOTCONFIG_MAGIC	"#BOOTCONFIG\n"
 #define BOOTCONFIG_MAGIC_LEN	12
@@ -25,10 +35,10 @@
  * The checksum will be used with the BOOTCONFIG_MAGIC and the size for
  * embedding the bootconfig in the initrd image.
  */
-static inline __init u32 xbc_calc_checksum(void *data, u32 size)
+static inline __init uint32_t xbc_calc_checksum(void *data, uint32_t size)
 {
 	unsigned char *p = data;
-	u32 ret = 0;
+	uint32_t ret = 0;
 
 	while (size--)
 		ret += *p++;
@@ -38,10 +48,10 @@ static inline __init u32 xbc_calc_checksum(void *data, u32 size)
 
 /* XBC tree node */
 struct xbc_node {
-	u16 next;
-	u16 child;
-	u16 parent;
-	u16 data;
+	uint16_t next;
+	uint16_t child;
+	uint16_t parent;
+	uint16_t data;
 } __attribute__ ((__packed__));
 
 #define XBC_KEY		0
@@ -271,13 +281,12 @@ static inline int __init xbc_node_compose_key(struct xbc_node *node,
 }
 
 /* XBC node initializer */
-int __init xbc_init(char *buf, const char **emsg, int *epos);
+int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos);
 
+/* XBC node and size information */
+int __init xbc_get_info(int *node_size, size_t *data_size);
 
 /* XBC cleanup data structures */
-void __init xbc_destroy_all(void);
-
-/* Debug dump functions */
-void __init xbc_debug_dump(void);
+void __init xbc_exit(void);
 
 #endif
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 832e65f06754..9999e29187de 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -30,16 +30,26 @@
 #define ARCH_SUPPORTS_FTRACE_OPS 0
 #endif
 
+#ifdef CONFIG_FUNCTION_TRACER
+struct ftrace_ops;
+struct ftrace_regs;
 /*
  * If the arch's mcount caller does not support all of ftrace's
  * features, then it must call an indirect function that
  * does. Or at least does enough to prevent any unwelcome side effects.
+ *
+ * Also define the function prototype that these architectures use
+ * to call the ftrace_ops_list_func().
  */
 #if !ARCH_SUPPORTS_FTRACE_OPS
 # define FTRACE_FORCE_LIST_FUNC 1
+void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
 #else
 # define FTRACE_FORCE_LIST_FUNC 0
+void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+			       struct ftrace_ops *op, struct ftrace_regs *fregs);
 #endif
+#endif /* CONFIG_FUNCTION_TRACER */
 
 /* Main tracing buffer and events set up */
 #ifdef CONFIG_TRACING
@@ -88,8 +98,6 @@ extern int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
 		     void *buffer, size_t *lenp, loff_t *ppos);
 
-struct ftrace_ops;
-
 #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
 
 struct ftrace_regs {
@@ -316,7 +324,12 @@ int ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
 				unsigned long old_addr,
 				unsigned long new_addr);
 unsigned long ftrace_find_rec_direct(unsigned long ip);
+int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
+int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
+int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
+
 #else
+struct ftrace_ops;
 # define ftrace_direct_func_count 0
 static inline int register_ftrace_direct(unsigned long ip, unsigned long addr)
 {
@@ -346,6 +359,18 @@ static inline unsigned long ftrace_find_rec_direct(unsigned long ip)
 {
 	return 0;
 }
+static inline int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	return -ENODEV;
+}
+static inline int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	return -ENODEV;
+}
+static inline int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	return -ENODEV;
+}
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
@@ -795,6 +820,15 @@ static inline bool is_ftrace_trampoline(unsigned long addr)
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#ifndef ftrace_graph_func
+#define ftrace_graph_func ftrace_stub
+#define FTRACE_OPS_GRAPH_STUB FTRACE_OPS_FL_STUB
+#else
+#define FTRACE_OPS_GRAPH_STUB 0
+#endif
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 /* totally disable ftrace - can not re-enable after this */
 void ftrace_kill(void);
 
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index e4f3bfe08757..e974caf39d3e 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -3,7 +3,6 @@
 #define _LINUX_KPROBES_H
 /*
  *  Kernel Probes (KProbes)
- *  include/linux/kprobes.h
  *
  * Copyright (C) IBM Corporation, 2002, 2004
  *
@@ -39,7 +38,7 @@
 #define KPROBE_REENTER		0x00000004
 #define KPROBE_HIT_SSDONE	0x00000008
 
-#else /* CONFIG_KPROBES */
+#else /* !CONFIG_KPROBES */
 #include <asm-generic/kprobes.h>
 typedef int kprobe_opcode_t;
 struct arch_specific_insn {
@@ -105,25 +104,25 @@ struct kprobe {
 #define KPROBE_FLAG_FTRACE	8 /* probe is using ftrace */
 
 /* Has this kprobe gone ? */
-static inline int kprobe_gone(struct kprobe *p)
+static inline bool kprobe_gone(struct kprobe *p)
 {
 	return p->flags & KPROBE_FLAG_GONE;
 }
 
 /* Is this kprobe disabled ? */
-static inline int kprobe_disabled(struct kprobe *p)
+static inline bool kprobe_disabled(struct kprobe *p)
 {
 	return p->flags & (KPROBE_FLAG_DISABLED | KPROBE_FLAG_GONE);
 }
 
 /* Is this kprobe really running optimized path ? */
-static inline int kprobe_optimized(struct kprobe *p)
+static inline bool kprobe_optimized(struct kprobe *p)
 {
 	return p->flags & KPROBE_FLAG_OPTIMIZED;
 }
 
 /* Is this kprobe uses ftrace ? */
-static inline int kprobe_ftrace(struct kprobe *p)
+static inline bool kprobe_ftrace(struct kprobe *p)
 {
 	return p->flags & KPROBE_FLAG_FTRACE;
 }
@@ -181,14 +180,6 @@ struct kprobe_blacklist_entry {
 DECLARE_PER_CPU(struct kprobe *, current_kprobe);
 DECLARE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
-/*
- * For #ifdef avoidance:
- */
-static inline int kprobes_built_in(void)
-{
-	return 1;
-}
-
 extern void kprobe_busy_begin(void);
 extern void kprobe_busy_end(void);
 
@@ -197,15 +188,26 @@ extern void arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				   struct pt_regs *regs);
 extern int arch_trampoline_kprobe(struct kprobe *p);
 
+void arch_kretprobe_fixup_return(struct pt_regs *regs,
+				 kprobe_opcode_t *correct_ret_addr);
+
+void __kretprobe_trampoline(void);
+/*
+ * Since some architecture uses structured function pointer,
+ * use dereference_function_descriptor() to get real function address.
+ */
+static nokprobe_inline void *kretprobe_trampoline_addr(void)
+{
+	return dereference_kernel_function_descriptor(__kretprobe_trampoline);
+}
+
 /* If the trampoline handler called from a kprobe, use this version */
 unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
-				void *trampoline_address,
-				void *frame_pointer);
+					     void *frame_pointer);
 
 static nokprobe_inline
 unsigned long kretprobe_trampoline_handler(struct pt_regs *regs,
-				void *trampoline_address,
-				void *frame_pointer)
+					   void *frame_pointer)
 {
 	unsigned long ret;
 	/*
@@ -214,7 +216,7 @@ unsigned long kretprobe_trampoline_handler(struct pt_regs *regs,
 	 * be running at this point.
 	 */
 	kprobe_busy_begin();
-	ret = __kretprobe_trampoline_handler(regs, trampoline_address, frame_pointer);
+	ret = __kretprobe_trampoline_handler(regs, frame_pointer);
 	kprobe_busy_end();
 
 	return ret;
@@ -228,7 +230,7 @@ static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance
 	return READ_ONCE(ri->rph->rp);
 }
 
-#else /* CONFIG_KRETPROBES */
+#else /* !CONFIG_KRETPROBES */
 static inline void arch_prepare_kretprobe(struct kretprobe *rp,
 					struct pt_regs *regs)
 {
@@ -239,11 +241,15 @@ static inline int arch_trampoline_kprobe(struct kprobe *p)
 }
 #endif /* CONFIG_KRETPROBES */
 
+/* Markers of '_kprobe_blacklist' section */
+extern unsigned long __start_kprobe_blacklist[];
+extern unsigned long __stop_kprobe_blacklist[];
+
 extern struct kretprobe_blackpoint kretprobe_blacklist[];
 
 #ifdef CONFIG_KPROBES_SANITY_TEST
 extern int init_test_probes(void);
-#else
+#else /* !CONFIG_KPROBES_SANITY_TEST */
 static inline int init_test_probes(void)
 {
 	return 0;
@@ -303,7 +309,7 @@ static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
 #define KPROBE_OPTINSN_PAGE_SYM		"kprobe_optinsn_page"
 int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
 			     unsigned long *value, char *type, char *sym);
-#else /* __ARCH_WANT_KPROBES_INSN_SLOT */
+#else /* !__ARCH_WANT_KPROBES_INSN_SLOT */
 #define DEFINE_INSN_CACHE_OPS(__name)					\
 static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
 {									\
@@ -334,7 +340,7 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist,
 				    struct list_head *done_list);
 extern void arch_unoptimize_kprobe(struct optimized_kprobe *op);
 extern int arch_within_optimized_kprobe(struct optimized_kprobe *op,
-					unsigned long addr);
+					kprobe_opcode_t *addr);
 
 extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs);
 
@@ -345,18 +351,22 @@ extern int sysctl_kprobes_optimization;
 extern int proc_kprobes_optimization_handler(struct ctl_table *table,
 					     int write, void *buffer,
 					     size_t *length, loff_t *ppos);
-#endif
+#endif /* CONFIG_SYSCTL */
 extern void wait_for_kprobe_optimizer(void);
-#else
+#else /* !CONFIG_OPTPROBES */
 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 ftrace_regs *fregs);
 extern int arch_prepare_kprobe_ftrace(struct kprobe *p);
-#endif
-
-int arch_check_ftrace_location(struct kprobe *p);
+#else
+static inline int arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_KPROBES_ON_FTRACE */
 
 /* Get the kprobe at this addr (if any) - called with preemption disabled */
 struct kprobe *get_kprobe(void *addr);
@@ -364,7 +374,7 @@ struct kprobe *get_kprobe(void *addr);
 /* kprobe_running() will just return the current_kprobe on this CPU */
 static inline struct kprobe *kprobe_running(void)
 {
-	return (__this_cpu_read(current_kprobe));
+	return __this_cpu_read(current_kprobe);
 }
 
 static inline void reset_current_kprobe(void)
@@ -382,7 +392,6 @@ int register_kprobe(struct kprobe *p);
 void unregister_kprobe(struct kprobe *p);
 int register_kprobes(struct kprobe **kps, int num);
 void unregister_kprobes(struct kprobe **kps, int num);
-unsigned long arch_deref_entry_point(void *);
 
 int register_kretprobe(struct kretprobe *rp);
 void unregister_kretprobe(struct kretprobe *rp);
@@ -410,10 +419,6 @@ int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
 			    char *type, char *sym);
 #else /* !CONFIG_KPROBES: */
 
-static inline int kprobes_built_in(void)
-{
-	return 0;
-}
 static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 {
 	return 0;
@@ -428,11 +433,11 @@ static inline struct kprobe *kprobe_running(void)
 }
 static inline int register_kprobe(struct kprobe *p)
 {
-	return -ENOSYS;
+	return -EOPNOTSUPP;
 }
 static inline int register_kprobes(struct kprobe **kps, int num)
 {
-	return -ENOSYS;
+	return -EOPNOTSUPP;
 }
 static inline void unregister_kprobe(struct kprobe *p)
 {
@@ -442,11 +447,11 @@ static inline void unregister_kprobes(struct kprobe **kps, int num)
 }
 static inline int register_kretprobe(struct kretprobe *rp)
 {
-	return -ENOSYS;
+	return -EOPNOTSUPP;
 }
 static inline int register_kretprobes(struct kretprobe **rps, int num)
 {
-	return -ENOSYS;
+	return -EOPNOTSUPP;
 }
 static inline void unregister_kretprobe(struct kretprobe *rp)
 {
@@ -462,11 +467,11 @@ static inline void kprobe_free_init_mem(void)
 }
 static inline int disable_kprobe(struct kprobe *kp)
 {
-	return -ENOSYS;
+	return -EOPNOTSUPP;
 }
 static inline int enable_kprobe(struct kprobe *kp)
 {
-	return -ENOSYS;
+	return -EOPNOTSUPP;
 }
 
 static inline bool within_kprobe_blacklist(unsigned long addr)
@@ -479,6 +484,7 @@ static inline int kprobe_get_kallsym(unsigned int symnum, unsigned long *value,
 	return -ERANGE;
 }
 #endif /* CONFIG_KPROBES */
+
 static inline int disable_kretprobe(struct kretprobe *rp)
 {
 	return disable_kprobe(&rp->kp);
@@ -493,19 +499,42 @@ static inline bool is_kprobe_insn_slot(unsigned long addr)
 {
 	return false;
 }
-#endif
+#endif /* !CONFIG_KPROBES */
+
 #ifndef CONFIG_OPTPROBES
 static inline bool is_kprobe_optinsn_slot(unsigned long addr)
 {
 	return false;
 }
+#endif /* !CONFIG_OPTPROBES */
+
+#ifdef CONFIG_KRETPROBES
+static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr)
+{
+	return (void *)addr == kretprobe_trampoline_addr();
+}
+
+unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp,
+				      struct llist_node **cur);
+#else
+static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr)
+{
+	return false;
+}
+
+static nokprobe_inline
+unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp,
+				      struct llist_node **cur)
+{
+	return 0;
+}
 #endif
 
 /* Returns true if kprobes handled the fault */
 static nokprobe_inline bool kprobe_page_fault(struct pt_regs *regs,
 					      unsigned int trap)
 {
-	if (!kprobes_built_in())
+	if (!IS_ENABLED(CONFIG_KPROBES))
 		return false;
 	if (user_mode(regs))
 		return false;
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index 7e72d975cb76..aca52db2f3f3 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -66,6 +66,17 @@ struct unwind_hint {
 	static void __used __section(".discard.func_stack_frame_non_standard") \
 		*__func_stack_frame_non_standard_##func = func
 
+/*
+ * STACK_FRAME_NON_STANDARD_FP() is a frame-pointer-specific function ignore
+ * for the case where a function is intentionally missing frame pointer setup,
+ * but otherwise needs objtool/ORC coverage when frame pointers are disabled.
+ */
+#ifdef CONFIG_FRAME_POINTER
+#define STACK_FRAME_NON_STANDARD_FP(func) STACK_FRAME_NON_STANDARD(func)
+#else
+#define STACK_FRAME_NON_STANDARD_FP(func)
+#endif
+
 #else /* __ASSEMBLY__ */
 
 /*
@@ -127,6 +138,7 @@ struct unwind_hint {
 #define UNWIND_HINT(sp_reg, sp_offset, type, end)	\
 	"\n\t"
 #define STACK_FRAME_NON_STANDARD(func)
+#define STACK_FRAME_NON_STANDARD_FP(func)
 #else
 #define ANNOTATE_INTRA_FUNCTION_CALL
 .macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 031898b38d06..b4381f255a5c 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -77,6 +77,27 @@
 /* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */
 #include <asm/preempt.h>
 
+/**
+ * interrupt_context_level - return interrupt context level
+ *
+ * Returns the current interrupt context level.
+ *  0 - normal context
+ *  1 - softirq context
+ *  2 - hardirq context
+ *  3 - NMI context
+ */
+static __always_inline unsigned char interrupt_context_level(void)
+{
+	unsigned long pc = preempt_count();
+	unsigned char level = 0;
+
+	level += !!(pc & (NMI_MASK));
+	level += !!(pc & (NMI_MASK | HARDIRQ_MASK));
+	level += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
+
+	return level;
+}
+
 #define nmi_count()	(preempt_count() & NMI_MASK)
 #define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
 #ifdef CONFIG_PREEMPT_RT
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 3e475eeb5a99..50453b287615 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -671,7 +671,7 @@ struct trace_event_file {
 	}								\
 	early_initcall(trace_init_perf_perm_##name);
 
-#define PERF_MAX_TRACE_SIZE	2048
+#define PERF_MAX_TRACE_SIZE	8192
 
 #define MAX_FILTER_STR_VAL	256	/* Should handle KSYM_SYMBOL_LEN */
 
diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index fe95f0922526..c303f7a114e9 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -116,13 +116,9 @@ enum {
 
 static __always_inline int trace_get_context_bit(void)
 {
-	unsigned long pc = preempt_count();
+	unsigned char bit = interrupt_context_level();
 
-	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;
+	return TRACE_CTX_NORMAL - bit;
 }
 
 #ifdef CONFIG_FTRACE_RECORD_RECURSION
@@ -139,6 +135,9 @@ extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip);
 # define do_ftrace_record_recursion(ip, pip)	do { } while (0)
 #endif
 
+/*
+ * Preemption is promised to be disabled when return bit >= 0.
+ */
 static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsigned long pip,
 							int start)
 {
@@ -148,8 +147,12 @@ static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsign
 	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.
+		 * If an interrupt occurs during a trace, and another trace
+		 * happens in that interrupt but before the preempt_count is
+		 * updated to reflect the new interrupt context, then this
+		 * will think a recursion occurred, and the event will be dropped.
+		 * Let a single instance happen via the TRANSITION_BIT to
+		 * not drop those events.
 		 */
 		bit = TRACE_CTX_TRANSITION + start;
 		if (val & (1 << bit)) {
@@ -162,11 +165,17 @@ static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsign
 	current->trace_recursion = val;
 	barrier();
 
+	preempt_disable_notrace();
+
 	return bit;
 }
 
+/*
+ * Preemption will be enabled (if it was previously enabled).
+ */
 static __always_inline void trace_clear_recursion(int bit)
 {
+	preempt_enable_notrace();
 	barrier();
 	trace_recursion_clear(bit);
 }
@@ -178,7 +187,7 @@ static __always_inline void trace_clear_recursion(int bit)
  * tracing recursed in the same context (normal vs interrupt),
  *
  * Returns: -1 if a recursion happened.
- *           >= 0 if no recursion
+ *           >= 0 if no recursion.
  */
 static __always_inline int ftrace_test_recursion_trylock(unsigned long ip,
 							 unsigned long parent_ip)