Merge tag 'perf-core-for-mingo-20160516' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

- Honour the kernel.perf_event_max_stack knob more precisely by not counting
PERF_CONTEXT_{KERNEL,USER} when deciding when to stop adding entries to
the perf_sample->ip_callchain[] array (Arnaldo Carvalho de Melo)

- Fix identation of 'stalled-backend-cycles' in 'perf stat' (Namhyung Kim)

- Update runtime using 'cpu-clock' event in 'perf stat' (Namhyung Kim)

- Use 'cpu-clock' for cpu targets in 'perf stat' (Namhyung Kim)

- Avoid fractional digits for integer scales in 'perf stat' (Andi Kleen)

- Store vdso buildid unconditionally, as it appears in callchains and
we're not checking those when creating the build-id table, so we
end up not being able to resolve VDSO symbols when doing analysis
on a different machine than the one where recording was done, possibly
of a different arch even (arm -> x86_64) (He Kuang)

Infrastructure changes:

- Generalize max_stack sysctl handler, will be used for configuring
multiple kernel knobs related to callchains (Arnaldo Carvalho de Melo)

Cleanups:

- Introduce DSO__NAME_KALLSYMS and DSO__NAME_KCORE, to stop using
open coded strings (Masami Hiramatsu)

Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>
Signed-off-by: Ingo Molnar <[e-mail]>

Documentation/sysctl/kernel.txt

···
 - perf_cpu_time_max_percent
 - perf_event_paranoid
 - perf_event_max_stack
+- perf_event_max_contexts_per_stack
 - pid_max
 - powersave-nap               [ PPC only ]
 - printk
···
 enabled, otherwise writing to this file will return -EBUSY.
 
 The default value is 127.
+
+==============================================================
+
+perf_event_max_contexts_per_stack:
+
+Controls maximum number of stack frame context entries for
+(attr.sample_type & PERF_SAMPLE_CALLCHAIN) configured events, for
+instance, when using 'perf record -g' or 'perf trace --call-graph fp'.
+
+This can only be done when no events are in use that have callchains
+enabled, otherwise writing to this file will return -EBUSY.
+
+The default value is 8.
 
 ==============================================================
 

arch/arc/kernel/perf_event.c

···
 static int callchain_trace(unsigned int addr, void *data)
 {
 	struct arc_callchain_trace *ctrl = data;
-	struct perf_callchain_entry *entry = ctrl->perf_stuff;
+	struct perf_callchain_entry_ctx *entry = ctrl->perf_stuff;
 	perf_callchain_store(entry, addr);
 
 	if (ctrl->depth++ < 3)
···
 }
 
 void
-perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	struct arc_callchain_trace ctrl = {
 		.depth = 0,
···
 }
 
 void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	/*
 	 * User stack can't be unwound trivially with kernel dwarf unwinder

arch/arm/kernel/perf_callchain.c

···
  */
 static struct frame_tail __user *
 user_backtrace(struct frame_tail __user *tail,
-	       struct perf_callchain_entry *entry)
+	       struct perf_callchain_entry_ctx *entry)
 {
 	struct frame_tail buftail;
 	unsigned long err;
···
 }
 
 void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	struct frame_tail __user *tail;
 
···
 
 	tail = (struct frame_tail __user *)regs->ARM_fp - 1;
 
-	while ((entry->nr < sysctl_perf_event_max_stack) &&
+	while ((entry->nr < entry->max_stack) &&
 	       tail && !((unsigned long)tail & 0x3))
 		tail = user_backtrace(tail, entry);
 }
···
 callchain_trace(struct stackframe *fr,
 		void *data)
 {
-	struct perf_callchain_entry *entry = data;
+	struct perf_callchain_entry_ctx *entry = data;
 	perf_callchain_store(entry, fr->pc);
 	return 0;
 }
 
 void
-perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	struct stackframe fr;
 

arch/arm64/kernel/perf_callchain.c

···
  */
 static struct frame_tail __user *
 user_backtrace(struct frame_tail __user *tail,
-	       struct perf_callchain_entry *entry)
+	       struct perf_callchain_entry_ctx *entry)
 {
 	struct frame_tail buftail;
 	unsigned long err;
···
 
 static struct compat_frame_tail __user *
 compat_user_backtrace(struct compat_frame_tail __user *tail,
-		      struct perf_callchain_entry *entry)
+		      struct perf_callchain_entry_ctx *entry)
 {
 	struct compat_frame_tail buftail;
 	unsigned long err;
···
 }
 #endif /* CONFIG_COMPAT */
 
-void perf_callchain_user(struct perf_callchain_entry *entry,
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 			 struct pt_regs *regs)
 {
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
···
 
 		tail = (struct frame_tail __user *)regs->regs[29];
 
-		while (entry->nr < sysctl_perf_event_max_stack &&
+		while (entry->nr < entry->max_stack &&
 		       tail && !((unsigned long)tail & 0xf))
 			tail = user_backtrace(tail, entry);
 	} else {
···
 
 		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
 
-		while ((entry->nr < sysctl_perf_event_max_stack) &&
+		while ((entry->nr < entry->max_stack) &&
 			tail && !((unsigned long)tail & 0x3))
 			tail = compat_user_backtrace(tail, entry);
 #endif
···
  */
 static int callchain_trace(struct stackframe *frame, void *data)
 {
-	struct perf_callchain_entry *entry = data;
+	struct perf_callchain_entry_ctx *entry = data;
 	perf_callchain_store(entry, frame->pc);
 	return 0;
 }
 
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
 	struct stackframe frame;

arch/metag/kernel/perf_callchain.c

···
 
 static struct metag_frame __user *
 user_backtrace(struct metag_frame __user *user_frame,
-	       struct perf_callchain_entry *entry)
+	       struct perf_callchain_entry_ctx *entry)
 {
 	struct metag_frame frame;
 	unsigned long calladdr;
···
 }
 
 void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	unsigned long sp = regs->ctx.AX[0].U0;
 	struct metag_frame __user *frame;
···
 
 	--frame;
 
-	while ((entry->nr < sysctl_perf_event_max_stack) && frame)
+	while ((entry->nr < entry->max_stack) && frame)
 		frame = user_backtrace(frame, entry);
 }
 
···
 callchain_trace(struct stackframe *fr,
 		void *data)
 {
-	struct perf_callchain_entry *entry = data;
+	struct perf_callchain_entry_ctx *entry = data;
 	perf_callchain_store(entry, fr->pc);
 	return 0;
 }
 
 void
-perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	struct stackframe fr;
 

arch/mips/kernel/perf_event.c

···
  * the user stack callchains, we will add it here.
  */
 
-static void save_raw_perf_callchain(struct perf_callchain_entry *entry,
-	unsigned long reg29)
+static void save_raw_perf_callchain(struct perf_callchain_entry_ctx *entry,
+				    unsigned long reg29)
 {
 	unsigned long *sp = (unsigned long *)reg29;
 	unsigned long addr;
···
 		addr = *sp++;
 		if (__kernel_text_address(addr)) {
 			perf_callchain_store(entry, addr);
-			if (entry->nr >= sysctl_perf_event_max_stack)
+			if (entry->nr >= entry->max_stack)
 				break;
 		}
 	}
 }
 
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
-		      struct pt_regs *regs)
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
+			   struct pt_regs *regs)
 {
 	unsigned long sp = regs->regs[29];
 #ifdef CONFIG_KALLSYMS
···
 	}
 	do {
 		perf_callchain_store(entry, pc);
-		if (entry->nr >= sysctl_perf_event_max_stack)
+		if (entry->nr >= entry->max_stack)
 			break;
 		pc = unwind_stack(current, &sp, pc, &ra);
 	} while (pc);

arch/powerpc/perf/callchain.c

···
 }
 
 void
-perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	unsigned long sp, next_sp;
 	unsigned long next_ip;
···
 			next_ip = regs->nip;
 			lr = regs->link;
 			level = 0;
-			perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
+			perf_callchain_store_context(entry, PERF_CONTEXT_KERNEL);
 
 		} else {
 			if (level == 0)
···
 		puc == (unsigned long) &sf->uc;
 }
 
-static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 				   struct pt_regs *regs)
 {
 	unsigned long sp, next_sp;
···
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
 
-	while (entry->nr < sysctl_perf_event_max_stack) {
+	while (entry->nr < entry->max_stack) {
 		fp = (unsigned long __user *) sp;
 		if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp))
 			return;
···
 			    read_user_stack_64(&uregs[PT_R1], &sp))
 				return;
 			level = 0;
-			perf_callchain_store(entry, PERF_CONTEXT_USER);
+			perf_callchain_store_context(entry, PERF_CONTEXT_USER);
 			perf_callchain_store(entry, next_ip);
 			continue;
 		}
···
 	return rc;
 }
 
-static inline void perf_callchain_user_64(struct perf_callchain_entry *entry,
+static inline void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 					  struct pt_regs *regs)
 {
 }
···
 	return mctx->mc_gregs;
 }
 
-static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
 				   struct pt_regs *regs)
 {
 	unsigned int sp, next_sp;
···
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
 
-	while (entry->nr < sysctl_perf_event_max_stack) {
+	while (entry->nr < entry->max_stack) {
 		fp = (unsigned int __user *) (unsigned long) sp;
 		if (!valid_user_sp(sp, 0) || read_user_stack_32(fp, &next_sp))
 			return;
···
 			    read_user_stack_32(&uregs[PT_R1], &sp))
 				return;
 			level = 0;
-			perf_callchain_store(entry, PERF_CONTEXT_USER);
+			perf_callchain_store_context(entry, PERF_CONTEXT_USER);
 			perf_callchain_store(entry, next_ip);
 			continue;
 		}
···
 }
 
 void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	if (current_is_64bit())
 		perf_callchain_user_64(entry, regs);

arch/s390/kernel/perf_event.c

···
 
 static int __perf_callchain_kernel(void *data, unsigned long address)
 {
-	struct perf_callchain_entry *entry = data;
+	struct perf_callchain_entry_ctx *entry = data;
 
 	perf_callchain_store(entry, address);
 	return 0;
 }
 
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
 	if (user_mode(regs))

arch/sh/kernel/perf_callchain.c

···
 
 static void callchain_address(void *data, unsigned long addr, int reliable)
 {
-	struct perf_callchain_entry *entry = data;
+	struct perf_callchain_entry_ctx *entry = data;
 
 	if (reliable)
 		perf_callchain_store(entry, addr);
···
 };
 
 void
-perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	perf_callchain_store(entry, regs->pc);
 

arch/sparc/kernel/perf_event.c

···
 }
 pure_initcall(init_hw_perf_events);
 
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
 	unsigned long ksp, fp;
···
 			}
 		}
 #endif
-	} while (entry->nr < sysctl_perf_event_max_stack);
+	} while (entry->nr < entry->max_stack);
 }
 
 static inline int
···
 	return (__range_not_ok(fp, size, TASK_SIZE) == 0);
 }
 
-static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 				   struct pt_regs *regs)
 {
 	unsigned long ufp;
···
 		pc = sf.callers_pc;
 		ufp = (unsigned long)sf.fp + STACK_BIAS;
 		perf_callchain_store(entry, pc);
-	} while (entry->nr < sysctl_perf_event_max_stack);
+	} while (entry->nr < entry->max_stack);
 }
 
-static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
 				   struct pt_regs *regs)
 {
 	unsigned long ufp;
···
 			ufp = (unsigned long)sf.fp;
 		}
 		perf_callchain_store(entry, pc);
-	} while (entry->nr < sysctl_perf_event_max_stack);
+	} while (entry->nr < entry->max_stack);
 }
 
 void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	u64 saved_fault_address = current_thread_info()->fault_address;
 	u8 saved_fault_code = get_thread_fault_code();

arch/tile/kernel/perf_event.c

···
 /*
  * Tile specific backtracing code for perf_events.
  */
-static inline void perf_callchain(struct perf_callchain_entry *entry,
+static inline void perf_callchain(struct perf_callchain_entry_ctx *entry,
 		    struct pt_regs *regs)
 {
 	struct KBacktraceIterator kbt;
···
 	}
 }
 
-void perf_callchain_user(struct perf_callchain_entry *entry,
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 		    struct pt_regs *regs)
 {
 	perf_callchain(entry, regs);
 }
 
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 		      struct pt_regs *regs)
 {
 	perf_callchain(entry, regs);

arch/x86/events/core.c

···
 
 static int backtrace_address(void *data, unsigned long addr, int reliable)
 {
-	struct perf_callchain_entry *entry = data;
+	struct perf_callchain_entry_ctx *entry = data;
 
 	return perf_callchain_store(entry, addr);
 }
···
 };
 
 void
-perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
···
 #include <asm/compat.h>
 
 static inline int
-perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry)
 {
 	/* 32-bit process in 64-bit kernel. */
 	unsigned long ss_base, cs_base;
···
 
 	fp = compat_ptr(ss_base + regs->bp);
 	pagefault_disable();
-	while (entry->nr < sysctl_perf_event_max_stack) {
+	while (entry->nr < entry->max_stack) {
 		unsigned long bytes;
 		frame.next_frame     = 0;
 		frame.return_address = 0;
···
 }
 #else
 static inline int
-perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry)
 {
     return 0;
 }
 #endif
 
 void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	struct stack_frame frame;
 	const void __user *fp;
···
 		return;
 
 	pagefault_disable();
-	while (entry->nr < sysctl_perf_event_max_stack) {
+	while (entry->nr < entry->max_stack) {
 		unsigned long bytes;
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;

arch/xtensa/kernel/perf_event.c

···
 
 static int callchain_trace(struct stackframe *frame, void *data)
 {
-	struct perf_callchain_entry *entry = data;
+	struct perf_callchain_entry_ctx *entry = data;
 
 	perf_callchain_store(entry, frame->pc);
 	return 0;
 }
 
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
-	xtensa_backtrace_kernel(regs, sysctl_perf_event_max_stack,
+	xtensa_backtrace_kernel(regs, entry->max_stack,
 				callchain_trace, NULL, entry);
 }
 
-void perf_callchain_user(struct perf_callchain_entry *entry,
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 			 struct pt_regs *regs)
 {
-	xtensa_backtrace_user(regs, sysctl_perf_event_max_stack,
+	xtensa_backtrace_user(regs, entry->max_stack,
 			      callchain_trace, entry);
 }
 

include/linux/perf_event.h

···
 	__u64				ip[0]; /* /proc/sys/kernel/perf_event_max_stack */
 };
 
+struct perf_callchain_entry_ctx {
+	struct perf_callchain_entry *entry;
+	u32			    max_stack;
+	u32			    nr;
+	short			    contexts;
+	bool			    contexts_maxed;
+};
+
 struct perf_raw_record {
 	u32				size;
 	void				*data;
···
 /* Callchains */
 DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
 
-extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs);
-extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs);
+extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
+extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
 extern struct perf_callchain_entry *
 get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
-		   bool crosstask, bool add_mark);
+		   u32 max_stack, bool crosstask, bool add_mark);
 extern int get_callchain_buffers(void);
 extern void put_callchain_buffers(void);
 
 extern int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_contexts_per_stack;
 
-static inline int perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
+static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip)
 {
-	if (entry->nr < sysctl_perf_event_max_stack) {
+	if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) {
+		struct perf_callchain_entry *entry = ctx->entry;
 		entry->ip[entry->nr++] = ip;
+		++ctx->contexts;
+		return 0;
+	} else {
+		ctx->contexts_maxed = true;
+		return -1; /* no more room, stop walking the stack */
+	}
+}
+
+static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip)
+{
+	if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) {
+		struct perf_callchain_entry *entry = ctx->entry;
+		entry->ip[entry->nr++] = ip;
+		++ctx->nr;
 		return 0;
 	} else {
 		return -1; /* no more room, stop walking the stack */

include/uapi/linux/perf_event.h

···
 };
 
 #define PERF_MAX_STACK_DEPTH		127
+#define PERF_MAX_CONTEXTS_PER_STACK	  8
 
 enum perf_callchain_context {
 	PERF_CONTEXT_HV			= (__u64)-32,

kernel/bpf/stackmap.c

···
 			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
 		return -EINVAL;
 
-	trace = get_perf_callchain(regs, init_nr, kernel, user, false, false);
+	trace = get_perf_callchain(regs, init_nr, kernel, user,
+				   sysctl_perf_event_max_stack, false, false);
 
 	if (unlikely(!trace))
 		/* couldn't fetch the stack trace */

kernel/events/callchain.c

···
 };
 
 int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_contexts_per_stack __read_mostly = PERF_MAX_CONTEXTS_PER_STACK;
 
 static inline size_t perf_callchain_entry__sizeof(void)
 {
 	return (sizeof(struct perf_callchain_entry) +
-		sizeof(__u64) * sysctl_perf_event_max_stack);
+		sizeof(__u64) * (sysctl_perf_event_max_stack +
+				 sysctl_perf_event_max_contexts_per_stack));
 }
 
 static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
···
 static struct callchain_cpus_entries *callchain_cpus_entries;
 
 
-__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
+__weak void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 				  struct pt_regs *regs)
 {
 }
 
-__weak void perf_callchain_user(struct perf_callchain_entry *entry,
+__weak void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 				struct pt_regs *regs)
 {
 }
···
 	if (!kernel && !user)
 		return NULL;
 
-	return get_perf_callchain(regs, 0, kernel, user, crosstask, true);
+	return get_perf_callchain(regs, 0, kernel, user, sysctl_perf_event_max_stack, crosstask, true);
 }
 
 struct perf_callchain_entry *
 get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
-		   bool crosstask, bool add_mark)
+		   u32 max_stack, bool crosstask, bool add_mark)
 {
 	struct perf_callchain_entry *entry;
+	struct perf_callchain_entry_ctx ctx;
 	int rctx;
 
 	entry = get_callchain_entry(&rctx);
···
 	if (!entry)
 		goto exit_put;
 
-	entry->nr = init_nr;
+	ctx.entry     = entry;
+	ctx.max_stack = max_stack;
+	ctx.nr	      = entry->nr = init_nr;
+	ctx.contexts       = 0;
+	ctx.contexts_maxed = false;
 
 	if (kernel && !user_mode(regs)) {
 		if (add_mark)
-			perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
-		perf_callchain_kernel(entry, regs);
+			perf_callchain_store_context(&ctx, PERF_CONTEXT_KERNEL);
+		perf_callchain_kernel(&ctx, regs);
 	}
 
 	if (user) {
···
 				goto exit_put;
 
 			if (add_mark)
-				perf_callchain_store(entry, PERF_CONTEXT_USER);
-			perf_callchain_user(entry, regs);
+				perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
+			perf_callchain_user(&ctx, regs);
 		}
 	}
 
···
 	return entry;
 }
 
+/*
+ * Used for sysctl_perf_event_max_stack and
+ * sysctl_perf_event_max_contexts_per_stack.
+ */
 int perf_event_max_stack_handler(struct ctl_table *table, int write,
 				 void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	int new_value = sysctl_perf_event_max_stack, ret;
+	int *value = table->data;
+	int new_value = *value, ret;
 	struct ctl_table new_table = *table;
 
 	new_table.data = &new_value;
···
 	if (atomic_read(&nr_callchain_events))
 		ret = -EBUSY;
 	else
-		sysctl_perf_event_max_stack = new_value;
+		*value = new_value;
 
 	mutex_unlock(&callchain_mutex);
 

kernel/sysctl.c

···
 	},
 	{
 		.procname	= "perf_event_max_stack",
-		.data		= NULL, /* filled in by handler */
+		.data		= &sysctl_perf_event_max_stack,
 		.maxlen		= sizeof(sysctl_perf_event_max_stack),
 		.mode		= 0644,
 		.proc_handler	= perf_event_max_stack_handler,
 		.extra1		= &zero,
 		.extra2		= &six_hundred_forty_kb,
+	},
+	{
+		.procname	= "perf_event_max_contexts_per_stack",
+		.data		= &sysctl_perf_event_max_contexts_per_stack,
+		.maxlen		= sizeof(sysctl_perf_event_max_contexts_per_stack),
+		.mode		= 0644,
+		.proc_handler	= perf_event_max_stack_handler,
+		.extra1		= &zero,
+		.extra2		= &one_thousand,
 	},
 #endif
 #ifdef CONFIG_KMEMCHECK

tools/perf/builtin-buildid-cache.c

···
 	if (build_id_cache__kcore_buildid(from_dir, sbuildid) < 0)
 		return -1;
 
-	scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s",
-		  buildid_dir, sbuildid);
+	scnprintf(to_dir, sizeof(to_dir), "%s/%s/%s",
+		  buildid_dir, DSO__NAME_KCORE, sbuildid);
 
 	if (!force &&
 	    !build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) {
···
 	if (build_id_cache__kcore_dir(dir, sizeof(dir)))
 		return -1;
 
-	scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s/%s",
-		  buildid_dir, sbuildid, dir);
+	scnprintf(to_dir, sizeof(to_dir), "%s/%s/%s/%s",
+		  buildid_dir, DSO__NAME_KCORE, sbuildid, dir);
 
 	if (mkdir_p(to_dir, 0755))
 		return -1;

tools/perf/builtin-stat.c

···
 #include <stdlib.h>
 #include <sys/prctl.h>
 #include <locale.h>
+#include <math.h>
 
 #define DEFAULT_SEPARATOR	" "
 #define CNTR_NOT_SUPPORTED	"<not supported>"
···
 	const char *fmt;
 
 	if (csv_output) {
-		fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
+		fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
 	} else {
 		if (big_num)
-			fmt = sc != 1.0 ? "%'18.2f%s" : "%'18.0f%s";
+			fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
 		else
-			fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
+			fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
 	}
 
 	aggr_printout(evsel, id, nr);
···
 	}
 
 	if (!evsel_list->nr_entries) {
+		if (target__has_cpu(&target))
+			default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;
+
 		if (perf_evlist__add_default_attrs(evsel_list, default_attrs0) < 0)
 			return -1;
 		if (pmu_have_event("cpu", "stalled-cycles-frontend")) {
···
 				    union perf_event *event,
 				    struct perf_session *session)
 {
-	struct stat_round_event *round = &event->stat_round;
+	struct stat_round_event *stat_round = &event->stat_round;
 	struct perf_evsel *counter;
 	struct timespec tsh, *ts = NULL;
 	const char **argv = session->header.env.cmdline_argv;
···
 	evlist__for_each(evsel_list, counter)
 		perf_stat_process_counter(&stat_config, counter);
 
-	if (round->type == PERF_STAT_ROUND_TYPE__FINAL)
-		update_stats(&walltime_nsecs_stats, round->time);
+	if (stat_round->type == PERF_STAT_ROUND_TYPE__FINAL)
+		update_stats(&walltime_nsecs_stats, stat_round->time);
 
-	if (stat_config.interval && round->time) {
-		tsh.tv_sec  = round->time / NSECS_PER_SEC;
-		tsh.tv_nsec = round->time % NSECS_PER_SEC;
+	if (stat_config.interval && stat_round->time) {
+		tsh.tv_sec  = stat_round->time / NSECS_PER_SEC;
+		tsh.tv_nsec = stat_round->time % NSECS_PER_SEC;
 		ts = &tsh;
 	}
 

tools/perf/perf.c

···
 	if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
 		sysctl_perf_event_max_stack = value;
 
+	if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
+		sysctl_perf_event_max_contexts_per_stack = value;
+
 	cmd = extract_argv0_path(argv[0]);
 	if (!cmd)
 		cmd = "perf-help";

tools/perf/util/annotate.c

···
 	} else if (dso__is_kcore(dso)) {
 		goto fallback;
 	} else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
-		   strstr(command, "[kernel.kallsyms]") ||
+		   strstr(command, DSO__NAME_KALLSYMS) ||
 		   access(symfs_filename, R_OK)) {
 		free(filename);
 fallback:

tools/perf/util/build-id.c

···
 		size_t name_len;
 		bool in_kernel = false;
 
-		if (!pos->hit)
+		if (!pos->hit && !dso__is_vdso(pos))
 			continue;
 
 		if (dso__is_vdso(pos)) {

tools/perf/util/dso.c

···
 #include "auxtrace.h"
 #include "util.h"
 #include "debug.h"
+#include "vdso.h"
 
 char dso__symtab_origin(const struct dso *dso)
 {
···
 	struct dso *pos;
 
 	list_for_each_entry(pos, head, node) {
-		if (with_hits && !pos->hit)
+		if (with_hits && !pos->hit && !dso__is_vdso(pos))
 			continue;
 		if (pos->has_build_id) {
 			have_build_id = true;

tools/perf/util/machine.c

···
 	if (machine__is_host(machine)) {
 		vmlinux_name = symbol_conf.vmlinux_name;
 		if (!vmlinux_name)
-			vmlinux_name = "[kernel.kallsyms]";
+			vmlinux_name = DSO__NAME_KALLSYMS;
 
 		kernel = machine__findnew_kernel(machine, vmlinux_name,
 						 "[kernel]", DSO_TYPE_KERNEL);
···
 {
 	struct branch_stack *branch = sample->branch_stack;
 	struct ip_callchain *chain = sample->callchain;
-	int chain_nr = min(max_stack, (int)chain->nr);
+	int chain_nr = chain->nr;
 	u8 cpumode = PERF_RECORD_MISC_USER;
-	int i, j, err;
+	int i, j, err, nr_entries, nr_contexts;
 	int skip_idx = -1;
 	int first_call = 0;
 
···
 	 * Based on DWARF debug information, some architectures skip
 	 * a callchain entry saved by the kernel.
 	 */
-	if (chain->nr < sysctl_perf_event_max_stack)
+	if (chain_nr < sysctl_perf_event_max_stack)
 		skip_idx = arch_skip_callchain_idx(thread, chain);
 
 	/*
···
 	}
 
 check_calls:
-	if (chain->nr > sysctl_perf_event_max_stack && (int)chain->nr > max_stack) {
-		pr_warning("corrupted callchain. skipping...\n");
-		return 0;
-	}
-
-	for (i = first_call; i < chain_nr; i++) {
+	for (i = first_call, nr_entries = 0, nr_contexts = 0;
+	     i < chain_nr && nr_entries < max_stack; i++) {
 		u64 ip;
 
 		if (callchain_param.order == ORDER_CALLEE)
···
 #endif
 		ip = chain->ips[j];
 
+		if (ip >= PERF_CONTEXT_MAX) {
+			if (++nr_contexts > sysctl_perf_event_max_contexts_per_stack)
+				goto out_corrupted_callchain;
+		} else {
+			if (++nr_entries > sysctl_perf_event_max_stack)
+				goto out_corrupted_callchain;
+		}
+
 		err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip);
 
 		if (err)
 			return (err < 0) ? err : 0;
 	}
 
+	return 0;
+
+out_corrupted_callchain:
+	pr_warning("corrupted callchain. skipping...\n");
 	return 0;
 }
 

tools/perf/util/stat-shadow.c

···
 {
 	int ctx = evsel_context(counter);
 
-	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
+	    perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
 		update_stats(&runtime_nsecs_stats[cpu], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
 		update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
···
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio);
+	out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
 }
 
 static void print_branch_misses(int cpu,
···
 			ratio = total / avg;
 
 		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
-	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
+	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) ||
+		   perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
 			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
 				     avg / ratio);

tools/perf/util/symbol.c

···
 
 	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
 
-	scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", buildid_dir,
-		  sbuild_id);
+	scnprintf(path, sizeof(path), "%s/%s/%s", buildid_dir,
+		  DSO__NAME_KCORE, sbuild_id);
 
 	/* Use /proc/kallsyms if possible */
 	if (is_host) {
···
 	if (!find_matching_kcore(map, path, sizeof(path)))
 		return strdup(path);
 
-	scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
-		  buildid_dir, sbuild_id);
+	scnprintf(path, sizeof(path), "%s/%s/%s",
+		  buildid_dir, DSO__NAME_KALLSYMS, sbuild_id);
 
 	if (access(path, F_OK)) {
 		pr_err("No kallsyms or vmlinux with build-id %s was found\n",
···
 
 	if (err > 0 && !dso__is_kcore(dso)) {
 		dso->binary_type = DSO_BINARY_TYPE__KALLSYMS;
-		dso__set_long_name(dso, "[kernel.kallsyms]", false);
+		dso__set_long_name(dso, DSO__NAME_KALLSYMS, false);
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}

tools/perf/util/symbol.h

···
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
 #endif
 
+#define DSO__NAME_KALLSYMS	"[kernel.kallsyms]"
+#define DSO__NAME_KCORE		"[kernel.kcore]"
+
 /** struct symbol - symtab entry
  *
  * @ignore - resolvable but tools ignore it (e.g. idle routines)

tools/perf/util/util.c

···
 unsigned int page_size;
 int cacheline_size;
 
-unsigned int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
 
 bool test_attr__enabled;
 

tools/perf/util/util.h

···
 
 extern unsigned int page_size;
 extern int cacheline_size;
-extern unsigned int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_contexts_per_stack;
 
 struct parse_tag {
 	char tag;