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

Pull perf updates from Ingo Molnar:
 "The main changes in this cycle were:

  Kernel:

   - kprobes updates: use better W^X patterns for code modifications,
     improve optprobes, remove jprobes. (Masami Hiramatsu, Kees Cook)

   - core fixes: event timekeeping (enabled/running times statistics)
     fixes, perf_event_read() locking fixes and cleanups, etc. (Peter
     Zijlstra)

   - Extend x86 Intel free-running PEBS support and support x86
     user-register sampling in perf record and perf script. (Andi Kleen)

  Tooling:

   - Completely rework the way inline frames are handled. Instead of
     querying for the inline nodes on-demand in the individual tools, we
     now create proper callchain nodes for inlined frames. (Milian
     Wolff)

   - 'perf trace' updates (Arnaldo Carvalho de Melo)

   - Implement a way to print formatted output to per-event files in
     'perf script' to facilitate generate flamegraphs, elliminating the
     need to write scripts to do that separation (yuzhoujian, Arnaldo
     Carvalho de Melo)

   - Update vendor events JSON metrics for Intel's Broadwell, Broadwell
     Server, Haswell, Haswell Server, IvyBridge, IvyTown, JakeTown,
     Sandy Bridge, Skylake, SkyLake Server - and Goldmont Plus V1 (Andi
     Kleen, Kan Liang)

   - Multithread the synthesizing of PERF_RECORD_ events for
     pre-existing threads in 'perf top', speeding up that phase, greatly
     improving the user experience in systems such as Intel's Knights
     Mill (Kan Liang)

   - Introduce the concept of weak groups in 'perf stat': try to set up
     a group, but if it's not schedulable fallback to not using a group.
     That gives us the best of both worlds: groups if they work, but
     still a usable fallback if they don't. E.g: (Andi Kleen)

   - perf sched timehist enhancements (David Ahern)

   - ... various other enhancements, updates, cleanups and fixes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (139 commits)
  kprobes: Don't spam the build log with deprecation warnings
  arm/kprobes: Remove jprobe test case
  arm/kprobes: Fix kretprobe test to check correct counter
  perf srcline: Show correct function name for srcline of callchains
  perf srcline: Fix memory leak in addr2inlines()
  perf trace beauty kcmp: Beautify arguments
  perf trace beauty: Implement pid_fd beautifier
  tools include uapi: Grab a copy of linux/kcmp.h
  perf callchain: Fix double mapping al->addr for children without self period
  perf stat: Make --per-thread update shadow stats to show metrics
  perf stat: Move the shadow stats scale computation in perf_stat__update_shadow_stats
  perf tools: Add perf_data_file__write function
  perf tools: Add struct perf_data_file
  perf tools: Rename struct perf_data_file to perf_data
  perf script: Print information about per-event-dump files
  perf trace beauty prctl: Generate 'option' string table from kernel headers
  tools include uapi: Grab a copy of linux/prctl.h
  perf script: Allow creating per-event dump files
  perf evsel: Restore evsel->priv as a tool private area
  perf script: Use event_format__fprintf()
  ...

1 files changed, 40 insertions, 21 deletions

diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 0742491cbb73..bd36f3c33cd0 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -119,29 +119,29 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = {
 const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist);
 
 static nokprobe_inline void
-__synthesize_relative_insn(void *from, void *to, u8 op)
+__synthesize_relative_insn(void *dest, void *from, void *to, u8 op)
 {
 	struct __arch_relative_insn {
 		u8 op;
 		s32 raddr;
 	} __packed *insn;
 
-	insn = (struct __arch_relative_insn *)from;
+	insn = (struct __arch_relative_insn *)dest;
 	insn->raddr = (s32)((long)(to) - ((long)(from) + 5));
 	insn->op = op;
 }
 
 /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/
-void synthesize_reljump(void *from, void *to)
+void synthesize_reljump(void *dest, void *from, void *to)
 {
-	__synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE);
+	__synthesize_relative_insn(dest, from, to, RELATIVEJUMP_OPCODE);
 }
 NOKPROBE_SYMBOL(synthesize_reljump);
 
 /* Insert a call instruction at address 'from', which calls address 'to'.*/
-void synthesize_relcall(void *from, void *to)
+void synthesize_relcall(void *dest, void *from, void *to)
 {
-	__synthesize_relative_insn(from, to, RELATIVECALL_OPCODE);
+	__synthesize_relative_insn(dest, from, to, RELATIVECALL_OPCODE);
 }
 NOKPROBE_SYMBOL(synthesize_relcall);
 
@@ -346,10 +346,11 @@ static int is_IF_modifier(kprobe_opcode_t *insn)
 /*
  * Copy an instruction with recovering modified instruction by kprobes
  * and adjust the displacement if the instruction uses the %rip-relative
- * addressing mode.
+ * addressing mode. Note that since @real will be the final place of copied
+ * instruction, displacement must be adjust by @real, not @dest.
  * This returns the length of copied instruction, or 0 if it has an error.
  */
-int __copy_instruction(u8 *dest, u8 *src, struct insn *insn)
+int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 {
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
 	unsigned long recovered_insn =
@@ -387,11 +388,11 @@ int __copy_instruction(u8 *dest, u8 *src, struct insn *insn)
 		 * have given.
 		 */
 		newdisp = (u8 *) src + (s64) insn->displacement.value
-			  - (u8 *) dest;
+			  - (u8 *) real;
 		if ((s64) (s32) newdisp != newdisp) {
 			pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
 			pr_err("\tSrc: %p, Dest: %p, old disp: %x\n",
-				src, dest, insn->displacement.value);
+				src, real, insn->displacement.value);
 			return 0;
 		}
 		disp = (u8 *) dest + insn_offset_displacement(insn);
@@ -402,20 +403,38 @@ int __copy_instruction(u8 *dest, u8 *src, struct insn *insn)
 }
 
 /* Prepare reljump right after instruction to boost */
-static void prepare_boost(struct kprobe *p, struct insn *insn)
+static int prepare_boost(kprobe_opcode_t *buf, struct kprobe *p,
+			  struct insn *insn)
 {
+	int len = insn->length;
+
 	if (can_boost(insn, p->addr) &&
-	    MAX_INSN_SIZE - insn->length >= RELATIVEJUMP_SIZE) {
+	    MAX_INSN_SIZE - len >= RELATIVEJUMP_SIZE) {
 		/*
 		 * These instructions can be executed directly if it
 		 * jumps back to correct address.
 		 */
-		synthesize_reljump(p->ainsn.insn + insn->length,
+		synthesize_reljump(buf + len, p->ainsn.insn + len,
 				   p->addr + insn->length);
+		len += RELATIVEJUMP_SIZE;
 		p->ainsn.boostable = true;
 	} else {
 		p->ainsn.boostable = false;
 	}
+
+	return len;
+}
+
+/* Make page to RO mode when allocate it */
+void *alloc_insn_page(void)
+{
+	void *page;
+
+	page = module_alloc(PAGE_SIZE);
+	if (page)
+		set_memory_ro((unsigned long)page & PAGE_MASK, 1);
+
+	return page;
 }
 
 /* Recover page to RW mode before releasing it */
@@ -429,12 +448,11 @@ void free_insn_page(void *page)
 static int arch_copy_kprobe(struct kprobe *p)
 {
 	struct insn insn;
+	kprobe_opcode_t buf[MAX_INSN_SIZE];
 	int len;
 
-	set_memory_rw((unsigned long)p->ainsn.insn & PAGE_MASK, 1);
-
 	/* Copy an instruction with recovering if other optprobe modifies it.*/
-	len = __copy_instruction(p->ainsn.insn, p->addr, &insn);
+	len = __copy_instruction(buf, p->addr, p->ainsn.insn, &insn);
 	if (!len)
 		return -EINVAL;
 
@@ -442,15 +460,16 @@ static int arch_copy_kprobe(struct kprobe *p)
 	 * __copy_instruction can modify the displacement of the instruction,
 	 * but it doesn't affect boostable check.
 	 */
-	prepare_boost(p, &insn);
-
-	set_memory_ro((unsigned long)p->ainsn.insn & PAGE_MASK, 1);
+	len = prepare_boost(buf, p, &insn);
 
 	/* Check whether the instruction modifies Interrupt Flag or not */
-	p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn);
+	p->ainsn.if_modifier = is_IF_modifier(buf);
 
 	/* Also, displacement change doesn't affect the first byte */
-	p->opcode = p->ainsn.insn[0];
+	p->opcode = buf[0];
+
+	/* OK, write back the instruction(s) into ROX insn buffer */
+	text_poke(p->ainsn.insn, buf, len);
 
 	return 0;
 }