Merge tag 'trace-v5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "The major changes in this tracing update includes:

   - Removal of non-DYNAMIC_FTRACE from 32bit x86

   - Removal of mcount support from x86

   - Emulating a call from int3 on x86_64, fixes live kernel patching

   - Consolidated Tracing Error logs file

  Minor updates:

   - Removal of klp_check_compiler_support()

   - kdb ftrace dumping output changes

   - Accessing and creating ftrace instances from inside the kernel

   - Clean up of #define if macro

   - Introduction of TRACE_EVENT_NOP() to disable trace events based on
     config options

  And other minor fixes and clean ups"

* tag 'trace-v5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (44 commits)
  x86: Hide the int3_emulate_call/jmp functions from UML
  livepatch: Remove klp_check_compiler_support()
  ftrace/x86: Remove mcount support
  ftrace/x86_32: Remove support for non DYNAMIC_FTRACE
  tracing: Simplify "if" macro code
  tracing: Fix documentation about disabling options using trace_options
  tracing: Replace kzalloc with kcalloc
  tracing: Fix partial reading of trace event's id file
  tracing: Allow RCU to run between postponed startup tests
  tracing: Fix white space issues in parse_pred() function
  tracing: Eliminate const char[] auto variables
  ring-buffer: Fix mispelling of Calculate
  tracing: probeevent: Fix to make the type of $comm string
  tracing: probeevent: Do not accumulate on ret variable
  tracing: uprobes: Re-enable $comm support for uprobe events
  ftrace/x86_64: Emulate call function while updating in breakpoint handler
  x86_64: Allow breakpoints to emulate call instructions
  x86_64: Add gap to int3 to allow for call emulation
  tracing: kdb: Allow ftdump to skip all but the last few entries
  tracing: Add trace_total_entries() / trace_total_entries_cpu()
  ...

8 files changed, 93 insertions, 117 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 326b2d5bab9d..21e9f2fac04b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -31,6 +31,17 @@ config X86_64
 	select SWIOTLB
 	select ARCH_HAS_SYSCALL_WRAPPER
 
+config FORCE_DYNAMIC_FTRACE
+	def_bool y
+	depends on X86_32
+	depends on FUNCTION_TRACER
+	select DYNAMIC_FTRACE
+	help
+	 We keep the static function tracing (!DYNAMIC_FTRACE) around
+	 in order to test the non static function tracing in the
+	 generic code, as other architectures still use it. But we
+	 only need to keep it around for x86_64. No need to keep it
+	 for x86_32. For x86_32, force DYNAMIC_FTRACE. 
 #
 # Arch settings
 #
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 20e45d9b4e15..11aa3b2afa4d 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -878,7 +878,7 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
  * @paranoid == 2 is special: the stub will never switch stacks.  This is for
  * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS.
  */
-.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0
+.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 create_gap=0
 ENTRY(\sym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 
@@ -898,6 +898,20 @@ ENTRY(\sym)
 	jnz	.Lfrom_usermode_switch_stack_\@
 	.endif
 
+	.if \create_gap == 1
+	/*
+	 * If coming from kernel space, create a 6-word gap to allow the
+	 * int3 handler to emulate a call instruction.
+	 */
+	testb	$3, CS-ORIG_RAX(%rsp)
+	jnz	.Lfrom_usermode_no_gap_\@
+	.rept	6
+	pushq	5*8(%rsp)
+	.endr
+	UNWIND_HINT_IRET_REGS offset=8
+.Lfrom_usermode_no_gap_\@:
+	.endif
+
 	.if \paranoid
 	call	paranoid_entry
 	.else
@@ -1129,7 +1143,7 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \
 #endif /* CONFIG_HYPERV */
 
 idtentry debug			do_debug		has_error_code=0	paranoid=1 shift_ist=IST_INDEX_DB ist_offset=DB_STACK_OFFSET
-idtentry int3			do_int3			has_error_code=0
+idtentry int3			do_int3			has_error_code=0	create_gap=1
 idtentry stack_segment		do_stack_segment	has_error_code=1
 
 #ifdef CONFIG_XEN_PV
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index cf350639e76d..287f1f7b2e52 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -3,12 +3,10 @@
 #define _ASM_X86_FTRACE_H
 
 #ifdef CONFIG_FUNCTION_TRACER
-#ifdef CC_USING_FENTRY
-# define MCOUNT_ADDR		((unsigned long)(__fentry__))
-#else
-# define MCOUNT_ADDR		((unsigned long)(mcount))
-# define HAVE_FUNCTION_GRAPH_FP_TEST
+#ifndef CC_USING_FENTRY
+# error Compiler does not support fentry?
 #endif
+# define MCOUNT_ADDR		((unsigned long)(__fentry__))
 #define MCOUNT_INSN_SIZE	5 /* sizeof mcount call */
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
index ed80003ce3e2..a66f6706c2de 100644
--- a/arch/x86/include/asm/livepatch.h
+++ b/arch/x86/include/asm/livepatch.h
@@ -24,14 +24,6 @@
 #include <asm/setup.h>
 #include <linux/ftrace.h>
 
-static inline int klp_check_compiler_support(void)
-{
-#ifndef CC_USING_FENTRY
-	return 1;
-#endif
-	return 0;
-}
-
 static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 {
 	regs->ip = ip;
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index c90678fd391a..880b5515b1d6 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -42,4 +42,34 @@ extern int after_bootmem;
 extern __ro_after_init struct mm_struct *poking_mm;
 extern __ro_after_init unsigned long poking_addr;
 
+#ifndef CONFIG_UML_X86
+static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip)
+{
+	regs->ip = ip;
+}
+
+#define INT3_INSN_SIZE 1
+#define CALL_INSN_SIZE 5
+
+#ifdef CONFIG_X86_64
+static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val)
+{
+	/*
+	 * The int3 handler in entry_64.S adds a gap between the
+	 * stack where the break point happened, and the saving of
+	 * pt_regs. We can extend the original stack because of
+	 * this gap. See the idtentry macro's create_gap option.
+	 */
+	regs->sp -= sizeof(unsigned long);
+	*(unsigned long *)regs->sp = val;
+}
+
+static inline void int3_emulate_call(struct pt_regs *regs, unsigned long func)
+{
+	int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + CALL_INSN_SIZE);
+	int3_emulate_jmp(regs, func);
+}
+#endif /* CONFIG_X86_64 */
+#endif /* !CONFIG_UML_X86 */
+
 #endif /* _ASM_X86_TEXT_PATCHING_H */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 0caf8122d680..0927bb158ffc 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -29,6 +29,7 @@
 #include <asm/kprobes.h>
 #include <asm/ftrace.h>
 #include <asm/nops.h>
+#include <asm/text-patching.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
@@ -231,6 +232,7 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 }
 
 static unsigned long ftrace_update_func;
+static unsigned long ftrace_update_func_call;
 
 static int update_ftrace_func(unsigned long ip, void *new)
 {
@@ -259,6 +261,8 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	unsigned char *new;
 	int ret;
 
+	ftrace_update_func_call = (unsigned long)func;
+
 	new = ftrace_call_replace(ip, (unsigned long)func);
 	ret = update_ftrace_func(ip, new);
 
@@ -294,13 +298,28 @@ int ftrace_int3_handler(struct pt_regs *regs)
 	if (WARN_ON_ONCE(!regs))
 		return 0;
 
-	ip = regs->ip - 1;
-	if (!ftrace_location(ip) && !is_ftrace_caller(ip))
-		return 0;
+	ip = regs->ip - INT3_INSN_SIZE;
 
-	regs->ip += MCOUNT_INSN_SIZE - 1;
+#ifdef CONFIG_X86_64
+	if (ftrace_location(ip)) {
+		int3_emulate_call(regs, (unsigned long)ftrace_regs_caller);
+		return 1;
+	} else if (is_ftrace_caller(ip)) {
+		if (!ftrace_update_func_call) {
+			int3_emulate_jmp(regs, ip + CALL_INSN_SIZE);
+			return 1;
+		}
+		int3_emulate_call(regs, ftrace_update_func_call);
+		return 1;
+	}
+#else
+	if (ftrace_location(ip) || is_ftrace_caller(ip)) {
+		int3_emulate_jmp(regs, ip + CALL_INSN_SIZE);
+		return 1;
+	}
+#endif
 
-	return 1;
+	return 0;
 }
 NOKPROBE_SYMBOL(ftrace_int3_handler);
 
@@ -865,6 +884,8 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
 
 	func = ftrace_ops_get_func(ops);
 
+	ftrace_update_func_call = (unsigned long)func;
+
 	/* Do a safe modify in case the trampoline is executing */
 	new = ftrace_call_replace(ip, (unsigned long)func);
 	ret = update_ftrace_func(ip, new);
@@ -966,6 +987,7 @@ static int ftrace_mod_jmp(unsigned long ip, void *func)
 {
 	unsigned char *new;
 
+	ftrace_update_func_call = 0UL;
 	new = ftrace_jmp_replace(ip, (unsigned long)func);
 
 	return update_ftrace_func(ip, new);
diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index 4c8440de3355..2ba914a34b06 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -10,22 +10,10 @@
 #include <asm/ftrace.h>
 #include <asm/nospec-branch.h>
 
-#ifdef CC_USING_FENTRY
 # define function_hook	__fentry__
 EXPORT_SYMBOL(__fentry__)
-#else
-# define function_hook	mcount
-EXPORT_SYMBOL(mcount)
-#endif
-
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-/* mcount uses a frame pointer even if CONFIG_FRAME_POINTER is not set */
-#if !defined(CC_USING_FENTRY) || defined(CONFIG_FRAME_POINTER)
-# define USING_FRAME_POINTER
-#endif
 
-#ifdef USING_FRAME_POINTER
+#ifdef CONFIG_FRAME_POINTER
 # define MCOUNT_FRAME			1	/* using frame = true  */
 #else
 # define MCOUNT_FRAME			0	/* using frame = false */
@@ -37,8 +25,7 @@ END(function_hook)
 
 ENTRY(ftrace_caller)
 
-#ifdef USING_FRAME_POINTER
-# ifdef CC_USING_FENTRY
+#ifdef CONFIG_FRAME_POINTER
 	/*
 	 * Frame pointers are of ip followed by bp.
 	 * Since fentry is an immediate jump, we are left with
@@ -49,7 +36,7 @@ ENTRY(ftrace_caller)
 	pushl	%ebp
 	movl	%esp, %ebp
 	pushl	2*4(%esp)			/* function ip */
-# endif
+
 	/* For mcount, the function ip is directly above */
 	pushl	%ebp
 	movl	%esp, %ebp
@@ -59,7 +46,7 @@ ENTRY(ftrace_caller)
 	pushl	%edx
 	pushl	$0				/* Pass NULL as regs pointer */
 
-#ifdef USING_FRAME_POINTER
+#ifdef CONFIG_FRAME_POINTER
 	/* Load parent ebp into edx */
 	movl	4*4(%esp), %edx
 #else
@@ -82,13 +69,11 @@ ftrace_call:
 	popl	%edx
 	popl	%ecx
 	popl	%eax
-#ifdef USING_FRAME_POINTER
+#ifdef CONFIG_FRAME_POINTER
 	popl	%ebp
-# ifdef CC_USING_FENTRY
 	addl	$4,%esp				/* skip function ip */
 	popl	%ebp				/* this is the orig bp */
 	addl	$4, %esp			/* skip parent ip */
-# endif
 #endif
 .Lftrace_ret:
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -133,11 +118,7 @@ ENTRY(ftrace_regs_caller)
 
 	movl	12*4(%esp), %eax		/* Load ip (1st parameter) */
 	subl	$MCOUNT_INSN_SIZE, %eax		/* Adjust ip */
-#ifdef CC_USING_FENTRY
 	movl	15*4(%esp), %edx		/* Load parent ip (2nd parameter) */
-#else
-	movl	0x4(%ebp), %edx			/* Load parent ip (2nd parameter) */
-#endif
 	movl	function_trace_op, %ecx		/* Save ftrace_pos in 3rd parameter */
 	pushl	%esp				/* Save pt_regs as 4th parameter */
 
@@ -170,43 +151,6 @@ GLOBAL(ftrace_regs_call)
 	lea	3*4(%esp), %esp			/* Skip orig_ax, ip and cs */
 
 	jmp	.Lftrace_ret
-#else /* ! CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(function_hook)
-	cmpl	$__PAGE_OFFSET, %esp
-	jb	ftrace_stub			/* Paging not enabled yet? */
-
-	cmpl	$ftrace_stub, ftrace_trace_function
-	jnz	.Ltrace
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	cmpl	$ftrace_stub, ftrace_graph_return
-	jnz	ftrace_graph_caller
-
-	cmpl	$ftrace_graph_entry_stub, ftrace_graph_entry
-	jnz	ftrace_graph_caller
-#endif
-.globl ftrace_stub
-ftrace_stub:
-	ret
-
-	/* taken from glibc */
-.Ltrace:
-	pushl	%eax
-	pushl	%ecx
-	pushl	%edx
-	movl	0xc(%esp), %eax
-	movl	0x4(%ebp), %edx
-	subl	$MCOUNT_INSN_SIZE, %eax
-
-	movl	ftrace_trace_function, %ecx
-	CALL_NOSPEC %ecx
-
-	popl	%edx
-	popl	%ecx
-	popl	%eax
-	jmp	ftrace_stub
-END(function_hook)
-#endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 ENTRY(ftrace_graph_caller)
@@ -215,13 +159,8 @@ ENTRY(ftrace_graph_caller)
 	pushl	%edx
 	movl	3*4(%esp), %eax
 	/* Even with frame pointers, fentry doesn't have one here */
-#ifdef CC_USING_FENTRY
 	lea	4*4(%esp), %edx
 	movl	$0, %ecx
-#else
-	lea	0x4(%ebp), %edx
-	movl	(%ebp), %ecx
-#endif
 	subl	$MCOUNT_INSN_SIZE, %eax
 	call	prepare_ftrace_return
 	popl	%edx
@@ -234,11 +173,7 @@ END(ftrace_graph_caller)
 return_to_handler:
 	pushl	%eax
 	pushl	%edx
-#ifdef CC_USING_FENTRY
 	movl	$0, %eax
-#else
-	movl	%ebp, %eax
-#endif
 	call	ftrace_return_to_handler
 	movl	%eax, %ecx
 	popl	%edx
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 75f2b36b41a6..10eb2760ef2c 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -13,22 +13,12 @@
 	.code64
 	.section .entry.text, "ax"
 
-#ifdef CC_USING_FENTRY
 # define function_hook	__fentry__
 EXPORT_SYMBOL(__fentry__)
-#else
-# define function_hook	mcount
-EXPORT_SYMBOL(mcount)
-#endif
 
 #ifdef CONFIG_FRAME_POINTER
-# ifdef CC_USING_FENTRY
 /* Save parent and function stack frames (rip and rbp) */
 #  define MCOUNT_FRAME_SIZE	(8+16*2)
-# else
-/* Save just function stack frame (rip and rbp) */
-#  define MCOUNT_FRAME_SIZE	(8+16)
-# endif
 #else
 /* No need to save a stack frame */
 # define MCOUNT_FRAME_SIZE	0
@@ -75,17 +65,13 @@ EXPORT_SYMBOL(mcount)
 	 * fentry is called before the stack frame is set up, where as mcount
 	 * is called afterward.
 	 */
-#ifdef CC_USING_FENTRY
+
 	/* Save the parent pointer (skip orig rbp and our return address) */
 	pushq \added+8*2(%rsp)
 	pushq %rbp
 	movq %rsp, %rbp
 	/* Save the return address (now skip orig rbp, rbp and parent) */
 	pushq \added+8*3(%rsp)
-#else
-	/* Can't assume that rip is before this (unless added was zero) */
-	pushq \added+8(%rsp)
-#endif
 	pushq %rbp
 	movq %rsp, %rbp
 #endif /* CONFIG_FRAME_POINTER */
@@ -113,12 +99,7 @@ EXPORT_SYMBOL(mcount)
 	movq %rdx, RBP(%rsp)
 
 	/* Copy the parent address into %rsi (second parameter) */
-#ifdef CC_USING_FENTRY
 	movq MCOUNT_REG_SIZE+8+\added(%rsp), %rsi
-#else
-	/* %rdx contains original %rbp */
-	movq 8(%rdx), %rsi
-#endif
 
 	 /* Move RIP to its proper location */
 	movq MCOUNT_REG_SIZE+\added(%rsp), %rdi
@@ -303,15 +284,8 @@ ENTRY(ftrace_graph_caller)
 	/* Saves rbp into %rdx and fills first parameter  */
 	save_mcount_regs
 
-#ifdef CC_USING_FENTRY
 	leaq MCOUNT_REG_SIZE+8(%rsp), %rsi
 	movq $0, %rdx	/* No framepointers needed */
-#else
-	/* Save address of the return address of traced function */
-	leaq 8(%rdx), %rsi
-	/* ftrace does sanity checks against frame pointers */
-	movq (%rdx), %rdx
-#endif
 	call	prepare_ftrace_return
 
 	restore_mcount_regs