Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - Ftrace is one of the last W^X violators (after this only KLP is
     left). These patches move it over to the generic text_poke()
     interface and thereby get rid of this oddity. This requires a
     surprising amount of surgery, by Peter Zijlstra.

   - x86/AMD PMUs: add support for 'Large Increment per Cycle Events' to
     count certain types of events that have a special, quirky hw ABI
     (by Kim Phillips)

   - kprobes fixes by Masami Hiramatsu

  Lots of tooling updates as well, the following subcommands were
  updated: annotate/report/top, c2c, clang, record, report/top TUI,
  sched timehist, tests; plus updates were done to the gtk ui, libperf,
  headers and the parser"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (57 commits)
  perf/x86/amd: Add support for Large Increment per Cycle Events
  perf/x86/amd: Constrain Large Increment per Cycle events
  perf/x86/intel/rapl: Add Comet Lake support
  tracing: Initialize ret in syscall_enter_define_fields()
  perf header: Use last modification time for timestamp
  perf c2c: Fix return type for histogram sorting comparision functions
  perf beauty sockaddr: Fix augmented syscall format warning
  perf/ui/gtk: Fix gtk2 build
  perf ui gtk: Add missing zalloc object
  perf tools: Use %define api.pure full instead of %pure-parser
  libperf: Setup initial evlist::all_cpus value
  perf report: Fix no libunwind compiled warning break s390 issue
  perf tools: Support --prefix/--prefix-strip
  perf report: Clarify in help that --children is default
  tools build: Fix test-clang.cpp with Clang 8+
  perf clang: Fix build with Clang 9
  kprobes: Fix optimize_kprobe()/unoptimize_kprobe() cancellation logic
  tools lib: Fix builds when glibc contains strlcpy()
  perf report/top: Make 'e' visible in the help and make it toggle showing callchains
  perf report/top: Do not offer annotation for symbols without samples
  ...

4 files changed, 72 insertions, 32 deletions

diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index c2a7458f912c..85be2f506272 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -47,8 +47,6 @@ struct dyn_arch_ftrace {
 	/* No extra data needed for x86 */
 };
 
-int ftrace_int3_handler(struct pt_regs *regs);
-
 #define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR
 
 #endif /*  CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 5dc909d9ad81..95b1f053bd96 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -11,12 +11,11 @@
 
 #include <asm-generic/kprobes.h>
 
-#define BREAKPOINT_INSTRUCTION	0xcc
-
 #ifdef CONFIG_KPROBES
 #include <linux/types.h>
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
+#include <asm/text-patching.h>
 #include <asm/insn.h>
 
 #define  __ARCH_WANT_KPROBES_INSN_SLOT
@@ -25,10 +24,7 @@ struct pt_regs;
 struct kprobe;
 
 typedef u8 kprobe_opcode_t;
-#define RELATIVEJUMP_OPCODE 0xe9
-#define RELATIVEJUMP_SIZE 5
-#define RELATIVECALL_OPCODE 0xe8
-#define RELATIVE_ADDR_SIZE 4
+
 #define MAX_STACK_SIZE 64
 #define CUR_STACK_SIZE(ADDR) \
 	(current_top_of_stack() - (unsigned long)(ADDR))
@@ -43,11 +39,11 @@ extern __visible kprobe_opcode_t optprobe_template_entry[];
 extern __visible kprobe_opcode_t optprobe_template_val[];
 extern __visible kprobe_opcode_t optprobe_template_call[];
 extern __visible kprobe_opcode_t optprobe_template_end[];
-#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE)
+#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + DISP32_SIZE)
 #define MAX_OPTINSN_SIZE 				\
 	(((unsigned long)optprobe_template_end -	\
 	  (unsigned long)optprobe_template_entry) +	\
-	 MAX_OPTIMIZED_LENGTH + RELATIVEJUMP_SIZE)
+	 MAX_OPTIMIZED_LENGTH + JMP32_INSN_SIZE)
 
 extern const int kretprobe_blacklist_size;
 
@@ -73,7 +69,7 @@ struct arch_specific_insn {
 
 struct arch_optimized_insn {
 	/* copy of the original instructions */
-	kprobe_opcode_t copied_insn[RELATIVE_ADDR_SIZE];
+	kprobe_opcode_t copied_insn[DISP32_SIZE];
 	/* detour code buffer */
 	kprobe_opcode_t *insn;
 	/* the size of instructions copied to detour code buffer */
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 2ee8e469dcf5..64c3dce374e5 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -81,8 +81,6 @@ int set_direct_map_invalid_noflush(struct page *page);
 int set_direct_map_default_noflush(struct page *page);
 
 extern int kernel_set_to_readonly;
-void set_kernel_text_rw(void);
-void set_kernel_text_ro(void);
 
 #ifdef CONFIG_X86_64
 static inline int set_mce_nospec(unsigned long pfn)
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 23c626a742e8..67315fa3956a 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -25,14 +25,6 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
  */
 #define POKE_MAX_OPCODE_SIZE	5
 
-struct text_poke_loc {
-	void *addr;
-	int len;
-	s32 rel32;
-	u8 opcode;
-	const u8 text[POKE_MAX_OPCODE_SIZE];
-};
-
 extern void text_poke_early(void *addr, const void *opcode, size_t len);
 
 /*
@@ -50,21 +42,13 @@ extern void text_poke_early(void *addr, const void *opcode, size_t len);
  * an inconsistent instruction while you patch.
  */
 extern void *text_poke(void *addr, const void *opcode, size_t len);
+extern void text_poke_sync(void);
 extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
 extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate);
-extern void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries);
-extern void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
-			       const void *opcode, size_t len, const void *emulate);
-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;
-}
+extern void text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate);
+extern void text_poke_finish(void);
 
 #define INT3_INSN_SIZE		1
 #define INT3_INSN_OPCODE	0xCC
@@ -78,6 +62,67 @@ static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip)
 #define JMP8_INSN_SIZE		2
 #define JMP8_INSN_OPCODE	0xEB
 
+#define DISP32_SIZE		4
+
+static inline int text_opcode_size(u8 opcode)
+{
+	int size = 0;
+
+#define __CASE(insn)	\
+	case insn##_INSN_OPCODE: size = insn##_INSN_SIZE; break
+
+	switch(opcode) {
+	__CASE(INT3);
+	__CASE(CALL);
+	__CASE(JMP32);
+	__CASE(JMP8);
+	}
+
+#undef __CASE
+
+	return size;
+}
+
+union text_poke_insn {
+	u8 text[POKE_MAX_OPCODE_SIZE];
+	struct {
+		u8 opcode;
+		s32 disp;
+	} __attribute__((packed));
+};
+
+static __always_inline
+void *text_gen_insn(u8 opcode, const void *addr, const void *dest)
+{
+	static union text_poke_insn insn; /* per instance */
+	int size = text_opcode_size(opcode);
+
+	insn.opcode = opcode;
+
+	if (size > 1) {
+		insn.disp = (long)dest - (long)(addr + size);
+		if (size == 2) {
+			/*
+			 * Ensure that for JMP9 the displacement
+			 * actually fits the signed byte.
+			 */
+			BUG_ON((insn.disp >> 31) != (insn.disp >> 7));
+		}
+	}
+
+	return &insn.text;
+}
+
+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;
+}
+
 static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val)
 {
 	/*
@@ -85,6 +130,9 @@ static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val)
 	 * 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.
+	 *
+	 * Similarly entry_32.S will have a gap on the stack for (any) hardware
+	 * exception and pt_regs; see FIXUP_FRAME.
 	 */
 	regs->sp -= sizeof(unsigned long);
 	*(unsigned long *)regs->sp = val;