[PATCH 0/1 v6] [GIT PULL] ftrace/x86: Ftrace cleanup and add support for -mfentry on x86_32

[PATCH 0/1 v6] [GIT PULL] ftrace/x86: Ftrace cleanup and add support for -mfentry on x86_32

[Steven Rostedt]

[
 Ingo, Thomas or H.Peter,

 I believe this is all set to go now. I updated those patches that Linus
 commented on and I don't believe there are any more issues. I ran this
 through several tests (although some of my tests are failing due to
 bugs introduced by others in 4.11-rc2). You can take this as a patch
 series, or you can pull from my tree defined below. It's based on 4.11-rc2
 as I noticed that tip/x86/core is rather outdated, and Linus is fine with
 basing off of his tagged releases.
]


With the issues of gcc screwing around with the mcount stack frame causing
function graph tracer to panic on x86_32, and with Linus saying that we
should start deprecating mcount (at least on x86), I figured that x86_32
needs to support fentry.

First, I renamed mcount_64.S to ftrace_64.S. As we want to get away from
mcount, having the ftrace code in a file called mcount seems rather backwards.

Next I moved the ftrace code out of entry_32.S. It's not in entry_64.S
and it does not belong in entry_32.S.

I noticed that the x86_32 code has the same issue as the x86_64 did
in the past with respect to a stack frame. I fixed that just for the main
ftrace_caller. The ftrace_regs_caller is rather special, and so is
function graph tracing.

I realized the ftrace_regs_caller code was complex due to me aggressively
saving flags, even though I could still do push, lea and mov without
changing them. That made the logic a little nicer.

Finally I added the fentry code.

I tested this with an older compiler (for mcount) with and without
FRAME_POINTER set. I also did it with a new compiler (with fentry), with and
without FRAME_POINTER. I tested function tracing, stack tracing, function_graph
tracing, and kprobes (as that uses the ftrace_regs_caller).

Please pull (or take the patch series) from:

  git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
tip/x86/ftrace

Head SHA1: 71a281dd0356fb7cb207e3387c2716b887b646de


[ Note, all is the same from v5 but patch 2, so I'm only posting that one ]

Steven Rostedt (VMware) (6):
      ftrace/x86_64: Rename mcount_64.S to ftrace_64.S
      ftrace/x86_32: Move the ftrace specific code out of entry_32.S
      ftrace/x86_32: Add stack frame pointer to ftrace_caller
      ftrace/x86_32: Clean up ftrace_regs_caller
      ftrace/x86_32: Add -mfentry support to x86_32 with DYNAMIC_FTRACE set
      ftrace/x86: Use Makefile logic instead of #ifdef for compiling ftrace_*.o

----

Changes from v5:

   Removed file name from header comment. (Thomas Gleixner)

 arch/x86/Kconfig                             |   2 +-
 arch/x86/entry/entry_32.S                    | 169 -------------------
 arch/x86/kernel/Makefile                     |   5 +-
 arch/x86/kernel/ftrace_32.S                  | 244 +++++++++++++++++++++++++++
 arch/x86/kernel/{mcount_64.S => ftrace_64.S} |   6 -
 5 files changed, 248 insertions(+), 178 deletions(-)
 create mode 100644 arch/x86/kernel/ftrace_32.S
 rename arch/x86/kernel/{mcount_64.S => ftrace_64.S} (98%)

Diff against v5:

diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index 97ede82aeb8c..07f40359c9ea 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -1,6 +1,4 @@
 /*
- *  linux/arch/x86_64/ftrace_32.S
- *
  *  Copyright (C) 2017  Steven Rostedt, VMware Inc.
  */
 
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index aef2361e7f83..1dfac634bbf7 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -1,6 +1,4 @@
 /*
- *  linux/arch/x86_64/ftrace_64.S
- *
  *  Copyright (C) 2014  Steven Rostedt, Red Hat Inc
  */
 

[PATCH 1/1 v6] ftrace/x86_32: Move the ftrace specific code out of entry_32.S

[Steven Rostedt]

[-- Attachment #1: 0002-ftrace-x86_32-Move-the-ftrace-specific-code-out-of-e.patch --]
[-- Type: text/plain, Size: 10082 bytes --]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

The function tracing hook code for ftrace is not an entry point from
userspace and does not belong in the entry_*.S files. It has already been
moved out of entry_64.S. This moves it out of entry_32.S into its own
ftrace_32.S file.

Also removed the file name from the comment header in ftrace_64.S.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/x86/entry/entry_32.S   | 169 ------------------------------------------
 arch/x86/kernel/Makefile    |   1 +
 arch/x86/kernel/ftrace_32.S | 175 ++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/ftrace_64.S |   2 -
 4 files changed, 176 insertions(+), 171 deletions(-)
 create mode 100644 arch/x86/kernel/ftrace_32.S

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 57f7ec35216e..169b3b0c5ec6 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -35,16 +35,13 @@
 #include <asm/errno.h>
 #include <asm/segment.h>
 #include <asm/smp.h>
-#include <asm/page_types.h>
 #include <asm/percpu.h>
 #include <asm/processor-flags.h>
-#include <asm/ftrace.h>
 #include <asm/irq_vectors.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
-#include <asm/export.h>
 #include <asm/frame.h>
 
 	.section .entry.text, "ax"
@@ -886,172 +883,6 @@ BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
 
 #endif /* CONFIG_HYPERV */
 
-#ifdef CONFIG_FUNCTION_TRACER
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-ENTRY(mcount)
-	ret
-END(mcount)
-
-ENTRY(ftrace_caller)
-	pushl	%eax
-	pushl	%ecx
-	pushl	%edx
-	pushl	$0				/* Pass NULL as regs pointer */
-	movl	4*4(%esp), %eax
-	movl	0x4(%ebp), %edx
-	movl	function_trace_op, %ecx
-	subl	$MCOUNT_INSN_SIZE, %eax
-
-.globl ftrace_call
-ftrace_call:
-	call	ftrace_stub
-
-	addl	$4, %esp			/* skip NULL pointer */
-	popl	%edx
-	popl	%ecx
-	popl	%eax
-.Lftrace_ret:
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
-	jmp	ftrace_stub
-#endif
-
-/* This is weak to keep gas from relaxing the jumps */
-WEAK(ftrace_stub)
-	ret
-END(ftrace_caller)
-
-ENTRY(ftrace_regs_caller)
-	pushf	/* push flags before compare (in cs location) */
-
-	/*
-	 * i386 does not save SS and ESP when coming from kernel.
-	 * Instead, to get sp, &regs->sp is used (see ptrace.h).
-	 * Unfortunately, that means eflags must be at the same location
-	 * as the current return ip is. We move the return ip into the
-	 * ip location, and move flags into the return ip location.
-	 */
-	pushl	4(%esp)				/* save return ip into ip slot */
-
-	pushl	$0				/* Load 0 into orig_ax */
-	pushl	%gs
-	pushl	%fs
-	pushl	%es
-	pushl	%ds
-	pushl	%eax
-	pushl	%ebp
-	pushl	%edi
-	pushl	%esi
-	pushl	%edx
-	pushl	%ecx
-	pushl	%ebx
-
-	movl	13*4(%esp), %eax		/* Get the saved flags */
-	movl	%eax, 14*4(%esp)		/* Move saved flags into regs->flags location */
-						/* clobbering return ip */
-	movl	$__KERNEL_CS, 13*4(%esp)
-
-	movl	12*4(%esp), %eax		/* Load ip (1st parameter) */
-	subl	$MCOUNT_INSN_SIZE, %eax		/* Adjust ip */
-	movl	0x4(%ebp), %edx			/* Load parent ip (2nd parameter) */
-	movl	function_trace_op, %ecx		/* Save ftrace_pos in 3rd parameter */
-	pushl	%esp				/* Save pt_regs as 4th parameter */
-
-GLOBAL(ftrace_regs_call)
-	call	ftrace_stub
-
-	addl	$4, %esp			/* Skip pt_regs */
-	movl	14*4(%esp), %eax		/* Move flags back into cs */
-	movl	%eax, 13*4(%esp)		/* Needed to keep addl	from modifying flags */
-	movl	12*4(%esp), %eax		/* Get return ip from regs->ip */
-	movl	%eax, 14*4(%esp)		/* Put return ip back for ret */
-
-	popl	%ebx
-	popl	%ecx
-	popl	%edx
-	popl	%esi
-	popl	%edi
-	popl	%ebp
-	popl	%eax
-	popl	%ds
-	popl	%es
-	popl	%fs
-	popl	%gs
-	addl	$8, %esp			/* Skip orig_ax and ip */
-	popf					/* Pop flags at end (no addl to corrupt flags) */
-	jmp	.Lftrace_ret
-
-	popf
-	jmp	ftrace_stub
-#else /* ! CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(mcount)
-	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
-
-	call	*ftrace_trace_function
-
-	popl	%edx
-	popl	%ecx
-	popl	%eax
-	jmp	ftrace_stub
-END(mcount)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-EXPORT_SYMBOL(mcount)
-#endif /* CONFIG_FUNCTION_TRACER */
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
-	pushl	%eax
-	pushl	%ecx
-	pushl	%edx
-	movl	0xc(%esp), %eax
-	lea	0x4(%ebp), %edx
-	movl	(%ebp), %ecx
-	subl	$MCOUNT_INSN_SIZE, %eax
-	call	prepare_ftrace_return
-	popl	%edx
-	popl	%ecx
-	popl	%eax
-	ret
-END(ftrace_graph_caller)
-
-.globl return_to_handler
-return_to_handler:
-	pushl	%eax
-	pushl	%edx
-	movl	%ebp, %eax
-	call	ftrace_return_to_handler
-	movl	%eax, %ecx
-	popl	%edx
-	popl	%eax
-	jmp	*%ecx
-#endif
-
 #ifdef CONFIG_TRACING
 ENTRY(trace_page_fault)
 	ASM_CLAC
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index d3743a37e990..55e8902c461f 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -47,6 +47,7 @@ obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
 obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-y			+= probe_roms.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o ftrace_64.o
+obj-$(CONFIG_X86_32)	+= ftrace_32.o
 obj-$(CONFIG_X86_ESPFIX64)	+= espfix_64.o
 obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
new file mode 100644
index 000000000000..2b160f238a42
--- /dev/null
+++ b/arch/x86/kernel/ftrace_32.S
@@ -0,0 +1,175 @@
+/*
+ *  Copyright (C) 2017  Steven Rostedt, VMware Inc.
+ */
+
+#include <linux/linkage.h>
+#include <asm/page_types.h>
+#include <asm/segment.h>
+#include <asm/export.h>
+#include <asm/ftrace.h>
+
+#ifdef CONFIG_FUNCTION_TRACER
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+ENTRY(mcount)
+	ret
+END(mcount)
+
+ENTRY(ftrace_caller)
+	pushl	%eax
+	pushl	%ecx
+	pushl	%edx
+	pushl	$0				/* Pass NULL as regs pointer */
+	movl	4*4(%esp), %eax
+	movl	0x4(%ebp), %edx
+	movl	function_trace_op, %ecx
+	subl	$MCOUNT_INSN_SIZE, %eax
+
+.globl ftrace_call
+ftrace_call:
+	call	ftrace_stub
+
+	addl	$4, %esp			/* skip NULL pointer */
+	popl	%edx
+	popl	%ecx
+	popl	%eax
+.Lftrace_ret:
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+	jmp	ftrace_stub
+#endif
+
+/* This is weak to keep gas from relaxing the jumps */
+WEAK(ftrace_stub)
+	ret
+END(ftrace_caller)
+
+ENTRY(ftrace_regs_caller)
+	pushf	/* push flags before compare (in cs location) */
+
+	/*
+	 * i386 does not save SS and ESP when coming from kernel.
+	 * Instead, to get sp, &regs->sp is used (see ptrace.h).
+	 * Unfortunately, that means eflags must be at the same location
+	 * as the current return ip is. We move the return ip into the
+	 * ip location, and move flags into the return ip location.
+	 */
+	pushl	4(%esp)				/* save return ip into ip slot */
+
+	pushl	$0				/* Load 0 into orig_ax */
+	pushl	%gs
+	pushl	%fs
+	pushl	%es
+	pushl	%ds
+	pushl	%eax
+	pushl	%ebp
+	pushl	%edi
+	pushl	%esi
+	pushl	%edx
+	pushl	%ecx
+	pushl	%ebx
+
+	movl	13*4(%esp), %eax		/* Get the saved flags */
+	movl	%eax, 14*4(%esp)		/* Move saved flags into regs->flags location */
+						/* clobbering return ip */
+	movl	$__KERNEL_CS, 13*4(%esp)
+
+	movl	12*4(%esp), %eax		/* Load ip (1st parameter) */
+	subl	$MCOUNT_INSN_SIZE, %eax		/* Adjust ip */
+	movl	0x4(%ebp), %edx			/* Load parent ip (2nd parameter) */
+	movl	function_trace_op, %ecx		/* Save ftrace_pos in 3rd parameter */
+	pushl	%esp				/* Save pt_regs as 4th parameter */
+
+GLOBAL(ftrace_regs_call)
+	call	ftrace_stub
+
+	addl	$4, %esp			/* Skip pt_regs */
+	movl	14*4(%esp), %eax		/* Move flags back into cs */
+	movl	%eax, 13*4(%esp)		/* Needed to keep addl	from modifying flags */
+	movl	12*4(%esp), %eax		/* Get return ip from regs->ip */
+	movl	%eax, 14*4(%esp)		/* Put return ip back for ret */
+
+	popl	%ebx
+	popl	%ecx
+	popl	%edx
+	popl	%esi
+	popl	%edi
+	popl	%ebp
+	popl	%eax
+	popl	%ds
+	popl	%es
+	popl	%fs
+	popl	%gs
+	addl	$8, %esp			/* Skip orig_ax and ip */
+	popf					/* Pop flags at end (no addl to corrupt flags) */
+	jmp	.Lftrace_ret
+
+	popf
+	jmp	ftrace_stub
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(mcount)
+	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
+
+	call	*ftrace_trace_function
+
+	popl	%edx
+	popl	%ecx
+	popl	%eax
+	jmp	ftrace_stub
+END(mcount)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+EXPORT_SYMBOL(mcount)
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+	pushl	%eax
+	pushl	%ecx
+	pushl	%edx
+	movl	0xc(%esp), %eax
+	lea	0x4(%ebp), %edx
+	movl	(%ebp), %ecx
+	subl	$MCOUNT_INSN_SIZE, %eax
+	call	prepare_ftrace_return
+	popl	%edx
+	popl	%ecx
+	popl	%eax
+	ret
+END(ftrace_graph_caller)
+
+.globl return_to_handler
+return_to_handler:
+	pushl	%eax
+	pushl	%edx
+	movl	%ebp, %eax
+	call	ftrace_return_to_handler
+	movl	%eax, %ecx
+	popl	%edx
+	popl	%eax
+	jmp	*%ecx
+#endif
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 7b0d3da52fb4..d1be3cbe2cd4 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -1,6 +1,4 @@
 /*
- *  linux/arch/x86_64/mcount_64.S
- *
  *  Copyright (C) 2014  Steven Rostedt, Red Hat Inc
  */
 
-- 
2.10.2