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

Pull perf updates from Ingo Molnar:
 "Mostly tooling and PMU driver fixes, but also a number of late updates
  such as the reworking of the call-chain size limiting logic to make
  call-graph recording more robust, plus tooling side changes for the
  new 'backwards ring-buffer' extension to the perf ring-buffer"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
  perf record: Read from backward ring buffer
  perf record: Rename variable to make code clear
  perf record: Prevent reading invalid data in record__mmap_read
  perf evlist: Add API to pause/resume
  perf trace: Use the ptr->name beautifier as default for "filename" args
  perf trace: Use the fd->name beautifier as default for "fd" args
  perf report: Add srcline_from/to branch sort keys
  perf evsel: Record fd into perf_mmap
  perf evsel: Add overwrite attribute and check write_backward
  perf tools: Set buildid dir under symfs when --symfs is provided
  perf trace: Only auto set call-graph to "dwarf" when syscalls are being traced
  perf annotate: Sort list of recognised instructions
  perf annotate: Fix identification of ARM blt and bls instructions
  perf tools: Fix usage of max_stack sysctl
  perf callchain: Stop validating callchains by the max_stack sysctl
  perf trace: Fix exit_group() formatting
  perf top: Use machine->kptr_restrict_warned
  perf trace: Warn when trying to resolve kernel addresses with kptr_restrict=1
  perf machine: Do not bail out if not managing to read ref reloc symbol
  perf/x86/intel/p4: Trival indentation fix, remove space
  ...

56 files changed, 618 insertions, 330 deletions

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index daabdd7ee543..a3683ce2a2f3 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -61,6 +61,7 @@ show up in /proc/sys/kernel:
 - 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
@@ -668,6 +669,19 @@ 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.
+
+==============================================================
+
 pid_max:
 
 PID allocation wrap value.  When the kernel's next PID value
diff --git a/MAINTAINERS b/MAINTAINERS
index 7fb2603e3a95..ab7e05d328c1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8881,6 +8881,7 @@ F:	arch/*/kernel/*/perf_event*.c
 F:	arch/*/kernel/*/*/perf_event*.c
 F:	arch/*/include/asm/perf_event.h
 F:	arch/*/kernel/perf_callchain.c
+F:	arch/*/events/*
 F:	tools/perf/
 
 PERSONALITY HANDLING
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 8b134cfe5e1f..6fd48021324b 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -48,7 +48,7 @@ struct arc_callchain_trace {
 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)
@@ -58,7 +58,7 @@ static int callchain_trace(unsigned int addr, void *data)
 }
 
 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,
@@ -69,7 +69,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 }
 
 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
diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c
index 27563befa8a2..22bf1f64d99a 100644
--- a/arch/arm/kernel/perf_callchain.c
+++ b/arch/arm/kernel/perf_callchain.c
@@ -31,7 +31,7 @@ struct frame_tail {
  */
 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;
@@ -59,7 +59,7 @@ user_backtrace(struct frame_tail __user *tail,
 }
 
 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;
 
@@ -75,7 +75,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
 	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);
 }
@@ -89,13 +89,13 @@ static int
 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;
 
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index 32c3c6e70119..713ca824f266 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -31,7 +31,7 @@ struct frame_tail {
  */
 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;
@@ -76,7 +76,7 @@ struct compat_frame_tail {
 
 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;
@@ -106,7 +106,7 @@ compat_user_backtrace(struct compat_frame_tail __user *tail,
 }
 #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()) {
@@ -122,7 +122,7 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
 
 		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 {
@@ -132,7 +132,7 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
 
 		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
@@ -146,12 +146,12 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
  */
 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;
diff --git a/arch/metag/kernel/perf_callchain.c b/arch/metag/kernel/perf_callchain.c
index 252abc12a5a3..3e8e048040df 100644
--- a/arch/metag/kernel/perf_callchain.c
+++ b/arch/metag/kernel/perf_callchain.c
@@ -29,7 +29,7 @@ static bool is_valid_call(unsigned long calladdr)
 
 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;
@@ -56,7 +56,7 @@ user_backtrace(struct metag_frame __user *user_frame,
 }
 
 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;
@@ -65,7 +65,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
 	--frame;
 
-	while ((entry->nr < sysctl_perf_event_max_stack) && frame)
+	while ((entry->nr < entry->max_stack) && frame)
 		frame = user_backtrace(frame, entry);
 }
 
@@ -78,13 +78,13 @@ static int
 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;
 
diff --git a/arch/mips/kernel/perf_event.c b/arch/mips/kernel/perf_event.c
index 5021c546ad07..d64056e0bb56 100644
--- a/arch/mips/kernel/perf_event.c
+++ b/arch/mips/kernel/perf_event.c
@@ -25,8 +25,8 @@
  * 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;
@@ -35,14 +35,14 @@ static void save_raw_perf_callchain(struct perf_callchain_entry *entry,
 		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
@@ -59,7 +59,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 	}
 	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);
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 26d37e6f924e..0fc26714780a 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -47,7 +47,7 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
 }
 
 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;
@@ -76,7 +76,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 			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)
@@ -232,7 +232,7 @@ static int sane_signal_64_frame(unsigned long sp)
 		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;
@@ -247,7 +247,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
 	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;
@@ -274,7 +274,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
 			    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;
 		}
@@ -319,7 +319,7 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 	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)
 {
 }
@@ -439,7 +439,7 @@ static unsigned int __user *signal_frame_32_regs(unsigned int sp,
 	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;
@@ -453,7 +453,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 	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;
@@ -473,7 +473,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 			    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;
 		}
@@ -487,7 +487,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 }
 
 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);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index c3e4099b60a5..87035fa58bbe 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -224,13 +224,13 @@ arch_initcall(service_level_perf_register);
 
 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))
diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c
index cc80b614b5fa..fa2c0cd23eaa 100644
--- a/arch/sh/kernel/perf_callchain.c
+++ b/arch/sh/kernel/perf_callchain.c
@@ -21,7 +21,7 @@ static int callchain_stack(void *data, char *name)
 
 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);
@@ -33,7 +33,7 @@ static const struct stacktrace_ops callchain_ops = {
 };
 
 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);
 
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index a4b8b5aed21c..710f3278d448 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1711,7 +1711,7 @@ static int __init init_hw_perf_events(void)
 }
 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;
@@ -1756,7 +1756,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 			}
 		}
 #endif
-	} while (entry->nr < sysctl_perf_event_max_stack);
+	} while (entry->nr < entry->max_stack);
 }
 
 static inline int
@@ -1769,7 +1769,7 @@ valid_user_frame(const void __user *fp, unsigned long size)
 	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;
@@ -1790,10 +1790,10 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
 		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;
@@ -1822,11 +1822,11 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 			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();
diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c
index 8767060d70fb..6394c1ccb68e 100644
--- a/arch/tile/kernel/perf_event.c
+++ b/arch/tile/kernel/perf_event.c
@@ -941,7 +941,7 @@ arch_initcall(init_hw_perf_events);
 /*
  * 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;
@@ -992,13 +992,13 @@ static inline void perf_callchain(struct perf_callchain_entry *entry,
 	}
 }
 
-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);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 73a75aa5a66d..33787ee817f0 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2202,7 +2202,7 @@ static int backtrace_stack(void *data, char *name)
 
 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);
 }
@@ -2214,7 +2214,7 @@ static const struct stacktrace_ops backtrace_ops = {
 };
 
 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 */
@@ -2268,7 +2268,7 @@ static unsigned long get_segment_base(unsigned int segment)
 #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;
@@ -2283,7 +2283,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 
 	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;
@@ -2309,14 +2309,14 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 }
 #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;
@@ -2343,7 +2343,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		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;
diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
index 0a5ede187d9c..eb0533558c2b 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -826,7 +826,7 @@ static int p4_hw_config(struct perf_event *event)
 		 * Clear bits we reserve to be managed by kernel itself
 		 * and never allowed from a user space
 		 */
-		 event->attr.config &= P4_CONFIG_MASK;
+		event->attr.config &= P4_CONFIG_MASK;
 
 		rc = p4_validate_raw_event(event);
 		if (rc)
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 16c178916412..fce74062d981 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -891,7 +891,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 		return -ENODEV;
 
 	pkg = topology_phys_to_logical_pkg(phys_id);
-	if (WARN_ON_ONCE(pkg < 0))
+	if (pkg < 0)
 		return -EINVAL;
 
 	if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index a6b00b3af429..ef90479e0397 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -323,23 +323,23 @@ static void xtensa_pmu_read(struct perf_event *event)
 
 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);
 }
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 44f33834ad78..1a827cecd62f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -61,6 +61,14 @@ struct perf_callchain_entry {
 	__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;
@@ -1061,20 +1069,36 @@ extern void perf_event_fork(struct task_struct *tsk);
 /* 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_context(struct perf_callchain_entry_ctx *ctx, u64 ip)
+{
+	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 *entry, u64 ip)
+static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip)
 {
-	if (entry->nr < sysctl_perf_event_max_stack) {
+	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 */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 43fc8d213472..36ce552cf6a9 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -862,6 +862,7 @@ enum perf_event_type {
 };
 
 #define PERF_MAX_STACK_DEPTH		127
+#define PERF_MAX_CONTEXTS_PER_STACK	  8
 
 enum perf_callchain_context {
 	PERF_CONTEXT_HV			= (__u64)-32,
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index c8ee35287bfe..080a2dfb5800 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -136,7 +136,8 @@ u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
 			       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 */
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index b9325e7dcba1..179ef4640964 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -19,11 +19,13 @@ struct callchain_cpus_entries {
 };
 
 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]);
@@ -32,12 +34,12 @@ static DEFINE_MUTEX(callchain_mutex);
 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)
 {
 }
@@ -176,14 +178,15 @@ perf_callchain(struct perf_event *event, 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);
@@ -193,12 +196,16 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 	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) {
@@ -214,8 +221,8 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool 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);
 		}
 	}
 
@@ -225,10 +232,15 @@ exit_put:
 	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;
@@ -240,7 +252,7 @@ int perf_event_max_stack_handler(struct ctl_table *table, int write,
 	if (atomic_read(&nr_callchain_events))
 		ret = -EBUSY;
 	else
-		sysctl_perf_event_max_stack = new_value;
+		*value = new_value;
 
 	mutex_unlock(&callchain_mutex);
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2effd84d83e3..87b2fc38398b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1149,13 +1149,22 @@ static struct ctl_table kern_table[] = {
 	},
 	{
 		.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
 	{
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index ebaf849e30ef..9cbddc290aff 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -103,12 +103,13 @@ OPTIONS
 
 	If --branch-stack option is used, following sort keys are also
 	available:
-	dso_from, dso_to, symbol_from, symbol_to, mispredict.
 
 	- dso_from: name of library or module branched from
 	- dso_to: name of library or module branched to
 	- symbol_from: name of function branched from
 	- symbol_to: name of function branched to
+	- srcline_from: source file and line branched from
+	- srcline_to: source file and line branched to
 	- mispredict: "N" for predicted branch, "Y" for mispredicted branch
 	- in_tx: branch in TSX transaction
 	- abort: TSX transaction abort.
@@ -248,7 +249,7 @@ OPTIONS
 	Note that when using the --itrace option the synthesized callchain size
 	will override this value if the synthesized callchain size is bigger.
 
-	Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
+	Default: 127
 
 -G::
 --inverted::
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index a856a1095893..4fc44c75263f 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -267,7 +267,7 @@ include::itrace.txt[]
         Note that when using the --itrace option the synthesized callchain size
         will override this value if the synthesized callchain size is bigger.
 
-        Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
+        Default: 127
 
 --ns::
 	Use 9 decimal places when displaying time (i.e. show the nanoseconds)
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 6afe20121bc0..1ab0782369b1 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -143,7 +143,8 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
         Implies '--call-graph dwarf' when --call-graph not present on the
         command line, on systems where DWARF unwinding was built in.
 
-        Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
+        Default: /proc/sys/kernel/perf_event_max_stack when present for
+                 live sessions (without --input/-i), 127 otherwise.
 
 --min-stack::
         Set the stack depth limit when parsing the callchain, anything
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 814158393656..25c81734a950 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -324,8 +324,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
 		    "Skip symbols that cannot be annotated"),
 	OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		   "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
 		    "Interleave source code with assembly code (default)"),
 	OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 632efc6b79a0..d75bded21fe0 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -119,8 +119,8 @@ static int build_id_cache__add_kcore(const char *filename, bool force)
 	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))) {
@@ -131,8 +131,8 @@ static int build_id_cache__add_kcore(const char *filename, bool force)
 	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;
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9ce354f469dc..f7645a42708e 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -812,8 +812,9 @@ static const struct option options[] = {
 	OPT_STRING_NOEMPTY('t', "field-separator", &symbol_conf.field_sep, "separator",
 		   "separator for columns, no spaces will be added between "
 		   "columns '.' is reserved."),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		    "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_UINTEGER('o', "order", &sort_compute, "Specify compute sorting."),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "How to display percentage of filtered entries", parse_filter_percentage),
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f3679c44d3f3..dc3fcb597e4c 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -40,6 +40,7 @@
 #include <unistd.h>
 #include <sched.h>
 #include <sys/mman.h>
+#include <asm/bug.h>
 
 
 struct record {
@@ -82,27 +83,87 @@ static int process_synthesized_event(struct perf_tool *tool,
 	return record__write(rec, event, event->header.size);
 }
 
+static int
+backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
+{
+	struct perf_event_header *pheader;
+	u64 evt_head = head;
+	int size = mask + 1;
+
+	pr_debug2("backward_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
+	pheader = (struct perf_event_header *)(buf + (head & mask));
+	*start = head;
+	while (true) {
+		if (evt_head - head >= (unsigned int)size) {
+			pr_debug("Finshed reading backward ring buffer: rewind\n");
+			if (evt_head - head > (unsigned int)size)
+				evt_head -= pheader->size;
+			*end = evt_head;
+			return 0;
+		}
+
+		pheader = (struct perf_event_header *)(buf + (evt_head & mask));
+
+		if (pheader->size == 0) {
+			pr_debug("Finshed reading backward ring buffer: get start\n");
+			*end = evt_head;
+			return 0;
+		}
+
+		evt_head += pheader->size;
+		pr_debug3("move evt_head: %"PRIx64"\n", evt_head);
+	}
+	WARN_ONCE(1, "Shouldn't get here\n");
+	return -1;
+}
+
+static int
+rb_find_range(struct perf_evlist *evlist,
+	      void *data, int mask, u64 head, u64 old,
+	      u64 *start, u64 *end)
+{
+	if (!evlist->backward) {
+		*start = old;
+		*end = head;
+		return 0;
+	}
+
+	return backward_rb_find_range(data, mask, head, start, end);
+}
+
 static int record__mmap_read(struct record *rec, int idx)
 {
 	struct perf_mmap *md = &rec->evlist->mmap[idx];
 	u64 head = perf_mmap__read_head(md);
 	u64 old = md->prev;
+	u64 end = head, start = old;
 	unsigned char *data = md->base + page_size;
 	unsigned long size;
 	void *buf;
 	int rc = 0;
 
-	if (old == head)
+	if (rb_find_range(rec->evlist, data, md->mask, head,
+			  old, &start, &end))
+		return -1;
+
+	if (start == end)
 		return 0;
 
 	rec->samples++;
 
-	size = head - old;
+	size = end - start;
+	if (size > (unsigned long)(md->mask) + 1) {
+		WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
+
+		md->prev = head;
+		perf_evlist__mmap_consume(rec->evlist, idx);
+		return 0;
+	}
 
-	if ((old & md->mask) + size != (head & md->mask)) {
-		buf = &data[old & md->mask];
-		size = md->mask + 1 - (old & md->mask);
-		old += size;
+	if ((start & md->mask) + size != (end & md->mask)) {
+		buf = &data[start & md->mask];
+		size = md->mask + 1 - (start & md->mask);
+		start += size;
 
 		if (record__write(rec, buf, size) < 0) {
 			rc = -1;
@@ -110,16 +171,16 @@ static int record__mmap_read(struct record *rec, int idx)
 		}
 	}
 
-	buf = &data[old & md->mask];
-	size = head - old;
-	old += size;
+	buf = &data[start & md->mask];
+	size = end - start;
+	start += size;
 
 	if (record__write(rec, buf, size) < 0) {
 		rc = -1;
 		goto out;
 	}
 
-	md->prev = old;
+	md->prev = head;
 	perf_evlist__mmap_consume(rec->evlist, idx);
 out:
 	return rc;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 87d40e3c4078..a87cb338bdf1 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -691,7 +691,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
-		.max_stack		 = sysctl_perf_event_max_stack,
+		.max_stack		 = PERF_MAX_STACK_DEPTH,
 		.pretty_printing_style	 = "normal",
 		.socket_filter		 = -1,
 	};
@@ -770,8 +770,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "columns '.' is reserved."),
 	OPT_BOOLEAN('U', "hide-unresolved", &symbol_conf.hide_unresolved,
 		    "Only display entries resolved to a symbol"),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		    "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_STRING('C', "cpu", &report.cpu_list, "cpu",
 		   "list of cpus to profile"),
 	OPT_BOOLEAN('I', "show-info", &report.show_full_info,
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index efca81679bb3..e3ce2f34d3ad 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2010,8 +2010,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "file", "kallsyms pathname"),
 	OPT_BOOLEAN('G', "hide-call-graph", &no_callchain,
 		    "When printing symbols do not display call chain"),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		    "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_CALLBACK('F', "fields", NULL, "str",
 		     "comma separated output fields prepend with 'type:'. "
 		     "Valid types: hw,sw,trace,raw. "
@@ -2067,8 +2068,6 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 
-	scripting_max_stack = sysctl_perf_event_max_stack;
-
 	setup_scripting();
 
 	argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e459b685a4e9..ee7ada78d86f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -66,6 +66,7 @@
 #include <stdlib.h>
 #include <sys/prctl.h>
 #include <locale.h>
+#include <math.h>
 
 #define DEFAULT_SEPARATOR	" "
 #define CNTR_NOT_SUPPORTED	"<not supported>"
@@ -991,12 +992,12 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	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);
@@ -1909,6 +1910,9 @@ static int add_default_attributes(void)
 	}
 
 	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")) {
@@ -2000,7 +2004,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 				    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;
@@ -2009,12 +2013,12 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 	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;
 	}
 
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 40cc9bb3506c..733a55422d03 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1945,8 +1945,9 @@ int cmd_timechart(int argc, const char **argv,
 	OPT_CALLBACK('p', "process", NULL, "process",
 		      "process selector. Pass a pid or process name.",
 		       parse_process),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		    "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_INTEGER('n', "proc-num", &tchart.proc_num,
 		    "min. number of tasks to print"),
 	OPT_BOOLEAN('t', "topology", &tchart.topology,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1793da585676..2a6cc254ad0c 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -732,7 +732,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (machine__resolve(machine, &al, sample) < 0)
 		return;
 
-	if (!top->kptr_restrict_warned &&
+	if (!machine->kptr_restrict_warned &&
 	    symbol_conf.kptr_restrict &&
 	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
 		ui__warning(
@@ -743,7 +743,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 			  " modules" : "");
 		if (use_browser <= 0)
 			sleep(5);
-		top->kptr_restrict_warned = true;
+		machine->kptr_restrict_warned = true;
 	}
 
 	if (al.sym == NULL) {
@@ -759,7 +759,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		 * --hide-kernel-symbols, even if the user specifies an
 		 * invalid --vmlinux ;-)
 		 */
-		if (!top->kptr_restrict_warned && !top->vmlinux_warned &&
+		if (!machine->kptr_restrict_warned && !top->vmlinux_warned &&
 		    al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
 		    RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
 			if (symbol_conf.vmlinux_name) {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6e5c325148e4..5c50fe70d6b3 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -576,84 +576,54 @@ static struct syscall_fmt {
 	bool	   hexret;
 } syscall_fmts[] = {
 	{ .name	    = "access",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */
-			     [1] = SCA_ACCMODE,  /* mode */ }, },
+	  .arg_scnprintf = { [1] = SCA_ACCMODE,  /* mode */ }, },
 	{ .name	    = "arch_prctl", .errmsg = true, .alias = "prctl", },
 	{ .name	    = "bpf",	    .errmsg = true, STRARRAY(0, cmd, bpf_cmd), },
 	{ .name	    = "brk",	    .hexret = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
-	{ .name	    = "chdir",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "chmod",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "chroot",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
+	{ .name	    = "chdir",	    .errmsg = true, },
+	{ .name	    = "chmod",	    .errmsg = true, },
+	{ .name	    = "chroot",	    .errmsg = true, },
 	{ .name     = "clock_gettime",  .errmsg = true, STRARRAY(0, clk_id, clockid), },
 	{ .name	    = "clone",	    .errpid = true, },
 	{ .name	    = "close",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, },
 	{ .name	    = "connect",    .errmsg = true, },
-	{ .name	    = "creat",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "dup",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "dup2",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "dup3",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	{ .name	    = "creat",	    .errmsg = true, },
+	{ .name	    = "dup",	    .errmsg = true, },
+	{ .name	    = "dup2",	    .errmsg = true, },
+	{ .name	    = "dup3",	    .errmsg = true, },
 	{ .name	    = "epoll_ctl",  .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
 	{ .name	    = "eventfd2",   .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
-	{ .name	    = "faccessat",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "fadvise64",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "fallocate",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "fchdir",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "fchmod",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	{ .name	    = "faccessat",  .errmsg = true, },
+	{ .name	    = "fadvise64",  .errmsg = true, },
+	{ .name	    = "fallocate",  .errmsg = true, },
+	{ .name	    = "fchdir",	    .errmsg = true, },
+	{ .name	    = "fchmod",	    .errmsg = true, },
 	{ .name	    = "fchmodat",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "fchown",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+	{ .name	    = "fchown",	    .errmsg = true, },
 	{ .name	    = "fchownat",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
 	{ .name	    = "fcntl",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [1] = SCA_STRARRAY, /* cmd */ },
+	  .arg_scnprintf = { [1] = SCA_STRARRAY, /* cmd */ },
 	  .arg_parm	 = { [1] = &strarray__fcntl_cmds, /* cmd */ }, },
-	{ .name	    = "fdatasync",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	{ .name	    = "fdatasync",  .errmsg = true, },
 	{ .name	    = "flock",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [1] = SCA_FLOCK, /* cmd */ }, },
-	{ .name	    = "fsetxattr",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "fstat",	    .errmsg = true, .alias = "newfstat",
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "fstatat",    .errmsg = true, .alias = "newfstatat",
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "fstatfs",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "fsync",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "ftruncate", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	  .arg_scnprintf = { [1] = SCA_FLOCK, /* cmd */ }, },
+	{ .name	    = "fsetxattr",  .errmsg = true, },
+	{ .name	    = "fstat",	    .errmsg = true, .alias = "newfstat", },
+	{ .name	    = "fstatat",    .errmsg = true, .alias = "newfstatat", },
+	{ .name	    = "fstatfs",    .errmsg = true, },
+	{ .name	    = "fsync",    .errmsg = true, },
+	{ .name	    = "ftruncate", .errmsg = true, },
 	{ .name	    = "futex",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
 	{ .name	    = "futimesat", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "getdents",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "getdents64", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+	{ .name	    = "getdents",   .errmsg = true, },
+	{ .name	    = "getdents64", .errmsg = true, },
 	{ .name	    = "getitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
 	{ .name	    = "getpid",	    .errpid = true, },
 	{ .name	    = "getpgid",    .errpid = true, },
@@ -661,12 +631,10 @@ static struct syscall_fmt {
 	{ .name	    = "getrandom",  .errmsg = true,
 	  .arg_scnprintf = { [2] = SCA_GETRANDOM_FLAGS, /* flags */ }, },
 	{ .name	    = "getrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
-	{ .name	    = "getxattr",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "inotify_add_watch",	    .errmsg = true,
-	  .arg_scnprintf = { [1] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "getxattr",   .errmsg = true, },
+	{ .name	    = "inotify_add_watch",	    .errmsg = true, },
 	{ .name	    = "ioctl",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
+	  .arg_scnprintf = {
 #if defined(__i386__) || defined(__x86_64__)
 /*
  * FIXME: Make this available to all arches.
@@ -680,41 +648,28 @@ static struct syscall_fmt {
 	{ .name	    = "keyctl",	    .errmsg = true, STRARRAY(0, option, keyctl_options), },
 	{ .name	    = "kill",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
-	{ .name	    = "lchown",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "lgetxattr",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "lchown",    .errmsg = true, },
+	{ .name	    = "lgetxattr",  .errmsg = true, },
 	{ .name	    = "linkat",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-	{ .name	    = "listxattr",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "llistxattr", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "lremovexattr",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "listxattr",  .errmsg = true, },
+	{ .name	    = "llistxattr", .errmsg = true, },
+	{ .name	    = "lremovexattr",  .errmsg = true, },
 	{ .name	    = "lseek",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [2] = SCA_STRARRAY, /* whence */ },
+	  .arg_scnprintf = { [2] = SCA_STRARRAY, /* whence */ },
 	  .arg_parm	 = { [2] = &strarray__whences, /* whence */ }, },
-	{ .name	    = "lsetxattr",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "lstat",	    .errmsg = true, .alias = "newlstat",
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "lsxattr",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "lsetxattr",  .errmsg = true, },
+	{ .name	    = "lstat",	    .errmsg = true, .alias = "newlstat", },
+	{ .name	    = "lsxattr",    .errmsg = true, },
 	{ .name     = "madvise",    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX,	 /* start */
 			     [2] = SCA_MADV_BHV, /* behavior */ }, },
-	{ .name	    = "mkdir",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "mkdir",    .errmsg = true, },
 	{ .name	    = "mkdirat",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
-			     [1] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "mknod",      .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
+	{ .name	    = "mknod",      .errmsg = true, },
 	{ .name	    = "mknodat",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
 	{ .name	    = "mlock",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
 	{ .name	    = "mlockall",   .errmsg = true,
@@ -722,8 +677,7 @@ static struct syscall_fmt {
 	{ .name	    = "mmap",	    .hexret = true,
 	  .arg_scnprintf = { [0] = SCA_HEX,	  /* addr */
 			     [2] = SCA_MMAP_PROT, /* prot */
-			     [3] = SCA_MMAP_FLAGS, /* flags */
-			     [4] = SCA_FD, 	  /* fd */ }, },
+			     [3] = SCA_MMAP_FLAGS, /* flags */ }, },
 	{ .name	    = "mprotect",   .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* start */
 			     [2] = SCA_MMAP_PROT, /* prot */ }, },
@@ -740,17 +694,14 @@ static struct syscall_fmt {
 	{ .name	    = "name_to_handle_at", .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
 	{ .name	    = "newfstatat", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
 	{ .name	    = "open",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME,   /* filename */
-			     [1] = SCA_OPEN_FLAGS, /* flags */ }, },
+	  .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
 	{ .name	    = "open_by_handle_at", .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
 			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
 	{ .name	    = "openat",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-			     [1] = SCA_FILENAME, /* filename */
 			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
 	{ .name	    = "perf_event_open", .errmsg = true,
 	  .arg_scnprintf = { [2] = SCA_INT, /* cpu */
@@ -760,39 +711,26 @@ static struct syscall_fmt {
 	  .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
 	{ .name	    = "poll",	    .errmsg = true, .timeout = true, },
 	{ .name	    = "ppoll",	    .errmsg = true, .timeout = true, },
-	{ .name	    = "pread",	    .errmsg = true, .alias = "pread64",
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "preadv",	    .errmsg = true, .alias = "pread",
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	{ .name	    = "pread",	    .errmsg = true, .alias = "pread64", },
+	{ .name	    = "preadv",	    .errmsg = true, .alias = "pread", },
 	{ .name	    = "prlimit64",  .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
-	{ .name	    = "pwrite",	    .errmsg = true, .alias = "pwrite64",
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "pwritev",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "read",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "readlink",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* path */ }, },
+	{ .name	    = "pwrite",	    .errmsg = true, .alias = "pwrite64", },
+	{ .name	    = "pwritev",    .errmsg = true, },
+	{ .name	    = "read",	    .errmsg = true, },
+	{ .name	    = "readlink",   .errmsg = true, },
 	{ .name	    = "readlinkat", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-			     [1] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "readv",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+	{ .name	    = "readv",	    .errmsg = true, },
 	{ .name	    = "recvfrom",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [3] = SCA_MSG_FLAGS, /* flags */ }, },
+	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
 	{ .name	    = "recvmmsg",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [3] = SCA_MSG_FLAGS, /* flags */ }, },
+	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
 	{ .name	    = "recvmsg",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [2] = SCA_MSG_FLAGS, /* flags */ }, },
-	{ .name	    = "removexattr", .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	  .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
+	{ .name	    = "removexattr", .errmsg = true, },
 	{ .name	    = "renameat",   .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-	{ .name	    = "rmdir",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "rmdir",    .errmsg = true, },
 	{ .name	    = "rt_sigaction", .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
 	{ .name	    = "rt_sigprocmask",  .errmsg = true, STRARRAY(0, how, sighow), },
@@ -807,22 +745,17 @@ static struct syscall_fmt {
 			     [1] = SCA_SECCOMP_FLAGS, /* flags */ }, },
 	{ .name	    = "select",	    .errmsg = true, .timeout = true, },
 	{ .name	    = "sendmmsg",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [3] = SCA_MSG_FLAGS, /* flags */ }, },
+	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
 	{ .name	    = "sendmsg",    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [2] = SCA_MSG_FLAGS, /* flags */ }, },
+	  .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
 	{ .name	    = "sendto",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
-			     [3] = SCA_MSG_FLAGS, /* flags */ }, },
+	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
 	{ .name	    = "set_tid_address", .errpid = true, },
 	{ .name	    = "setitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
 	{ .name	    = "setpgid",    .errmsg = true, },
 	{ .name	    = "setrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
-	{ .name	    = "setxattr",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "shutdown",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	{ .name	    = "setxattr",   .errmsg = true, },
+	{ .name	    = "shutdown",   .errmsg = true, },
 	{ .name	    = "socket",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
 			     [1] = SCA_SK_TYPE, /* type */ },
@@ -831,10 +764,8 @@ static struct syscall_fmt {
 	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
 			     [1] = SCA_SK_TYPE, /* type */ },
 	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
-	{ .name	    = "stat",	    .errmsg = true, .alias = "newstat",
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "statfs",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
+	{ .name	    = "stat",	    .errmsg = true, .alias = "newstat", },
+	{ .name	    = "statfs",	    .errmsg = true, },
 	{ .name	    = "swapoff",    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, },
 	{ .name	    = "swapon",	    .errmsg = true,
@@ -845,29 +776,21 @@ static struct syscall_fmt {
 	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
 	{ .name	    = "tkill",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
-	{ .name	    = "truncate",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* path */ }, },
+	{ .name	    = "truncate",   .errmsg = true, },
 	{ .name	    = "uname",	    .errmsg = true, .alias = "newuname", },
 	{ .name	    = "unlinkat",   .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-			     [1] = SCA_FILENAME, /* pathname */ }, },
-	{ .name	    = "utime",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+	{ .name	    = "utime",  .errmsg = true, },
 	{ .name	    = "utimensat",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */
-			     [1] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "utimes",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
-	{ .name	    = "vmsplice",  .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, },
+	{ .name	    = "utimes",  .errmsg = true, },
+	{ .name	    = "vmsplice",  .errmsg = true, },
 	{ .name	    = "wait4",	    .errpid = true,
 	  .arg_scnprintf = { [2] = SCA_WAITID_OPTIONS, /* options */ }, },
 	{ .name	    = "waitid",	    .errpid = true,
 	  .arg_scnprintf = { [3] = SCA_WAITID_OPTIONS, /* options */ }, },
-	{ .name	    = "write",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
-	{ .name	    = "writev",	    .errmsg = true,
-	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+	{ .name	    = "write",	    .errmsg = true, },
+	{ .name	    = "writev",	    .errmsg = true, },
 };
 
 static int syscall_fmt__cmp(const void *name, const void *fmtp)
@@ -1160,6 +1083,24 @@ static int trace__tool_process(struct perf_tool *tool,
 	return trace__process_event(trace, machine, event, sample);
 }
 
+static char *trace__machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp)
+{
+	struct machine *machine = vmachine;
+
+	if (machine->kptr_restrict_warned)
+		return NULL;
+
+	if (symbol_conf.kptr_restrict) {
+		pr_warning("Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
+			   "Check /proc/sys/kernel/kptr_restrict.\n\n"
+			   "Kernel samples will not be resolved.\n");
+		machine->kptr_restrict_warned = true;
+		return NULL;
+	}
+
+	return machine__resolve_kernel_addr(vmachine, addrp, modp);
+}
+
 static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 {
 	int err = symbol__init(NULL);
@@ -1171,7 +1112,7 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 	if (trace->host == NULL)
 		return -ENOMEM;
 
-	if (trace_event__register_resolver(trace->host, machine__resolve_kernel_addr) < 0)
+	if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0)
 		return -errno;
 
 	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
@@ -1186,7 +1127,7 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 static int syscall__set_arg_fmts(struct syscall *sc)
 {
 	struct format_field *field;
-	int idx = 0;
+	int idx = 0, len;
 
 	sc->arg_scnprintf = calloc(sc->nr_args, sizeof(void *));
 	if (sc->arg_scnprintf == NULL)
@@ -1198,12 +1139,31 @@ static int syscall__set_arg_fmts(struct syscall *sc)
 	for (field = sc->args; field; field = field->next) {
 		if (sc->fmt && sc->fmt->arg_scnprintf[idx])
 			sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
+		else if (strcmp(field->type, "const char *") == 0 &&
+			 (strcmp(field->name, "filename") == 0 ||
+			  strcmp(field->name, "path") == 0 ||
+			  strcmp(field->name, "pathname") == 0))
+			sc->arg_scnprintf[idx] = SCA_FILENAME;
 		else if (field->flags & FIELD_IS_POINTER)
 			sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
 		else if (strcmp(field->type, "pid_t") == 0)
 			sc->arg_scnprintf[idx] = SCA_PID;
 		else if (strcmp(field->type, "umode_t") == 0)
 			sc->arg_scnprintf[idx] = SCA_MODE_T;
+		else if ((strcmp(field->type, "int") == 0 ||
+			  strcmp(field->type, "unsigned int") == 0 ||
+			  strcmp(field->type, "long") == 0) &&
+			 (len = strlen(field->name)) >= 2 &&
+			 strcmp(field->name + len - 2, "fd") == 0) {
+			/*
+			 * /sys/kernel/tracing/events/syscalls/sys_enter*
+			 * egrep 'field:.*fd;' .../format|sed -r 's/.*field:([a-z ]+) [a-z_]*fd.+/\1/g'|sort|uniq -c
+			 * 65 int
+			 * 23 unsigned int
+			 * 7 unsigned long
+			 */
+			sc->arg_scnprintf[idx] = SCA_FD;
+		}
 		++idx;
 	}
 
@@ -1534,7 +1494,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	if (sc->is_exit) {
 		if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
 			trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
-			fprintf(trace->output, "%-70s\n", ttrace->entry_str);
+			fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
 		}
 	} else {
 		ttrace->entry_pending = true;
@@ -2887,12 +2847,12 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		mmap_pages_user_set = false;
 
 	if (trace.max_stack == UINT_MAX) {
-		trace.max_stack = sysctl_perf_event_max_stack;
+		trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl_perf_event_max_stack;
 		max_stack_user_set = false;
 	}
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
-	if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled)
+	if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled && trace.trace_syscalls)
 		record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false);
 #endif
 
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 797000842d40..15982cee5ef3 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -549,6 +549,9 @@ int main(int argc, const char **argv)
 	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";
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4db73d5a0dbc..7e5a1e8874ce 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -354,9 +354,6 @@ static struct ins_ops nop_ops = {
 	.scnprintf = nop__scnprintf,
 };
 
-/*
- * Must be sorted by name!
- */
 static struct ins instructions[] = {
 	{ .name = "add",   .ops  = &mov_ops, },
 	{ .name = "addl",  .ops  = &mov_ops, },
@@ -372,8 +369,8 @@ static struct ins instructions[] = {
 	{ .name = "bgt",   .ops  = &jump_ops, },
 	{ .name = "bhi",   .ops  = &jump_ops, },
 	{ .name = "bl",    .ops  = &call_ops, },
-	{ .name = "blt",   .ops  = &jump_ops, },
 	{ .name = "bls",   .ops  = &jump_ops, },
+	{ .name = "blt",   .ops  = &jump_ops, },
 	{ .name = "blx",   .ops  = &call_ops, },
 	{ .name = "bne",   .ops  = &jump_ops, },
 #endif
@@ -449,18 +446,39 @@ static struct ins instructions[] = {
 	{ .name = "xbeginq", .ops  = &jump_ops, },
 };
 
-static int ins__cmp(const void *name, const void *insp)
+static int ins__key_cmp(const void *name, const void *insp)
 {
 	const struct ins *ins = insp;
 
 	return strcmp(name, ins->name);
 }
 
+static int ins__cmp(const void *a, const void *b)
+{
+	const struct ins *ia = a;
+	const struct ins *ib = b;
+
+	return strcmp(ia->name, ib->name);
+}
+
+static void ins__sort(void)
+{
+	const int nmemb = ARRAY_SIZE(instructions);
+
+	qsort(instructions, nmemb, sizeof(struct ins), ins__cmp);
+}
+
 static struct ins *ins__find(const char *name)
 {
 	const int nmemb = ARRAY_SIZE(instructions);
+	static bool sorted;
+
+	if (!sorted) {
+		ins__sort();
+		sorted = true;
+	}
 
-	return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__cmp);
+	return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__key_cmp);
 }
 
 int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym)
@@ -1122,7 +1140,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 	} 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:
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index bff425e1232c..67e5966503b2 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -256,7 +256,7 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 		size_t name_len;
 		bool in_kernel = false;
 
-		if (!pos->hit)
+		if (!pos->hit && !dso__is_vdso(pos))
 			continue;
 
 		if (dso__is_vdso(pos)) {
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 8d96c80cc67e..c9a6dc173e74 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -298,8 +298,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 	 */
 	callchain_param.order = ORDER_CALLER;
 	err = thread__resolve_callchain(thread, &callchain_cursor, evsel,
-					sample, NULL, NULL,
-					sysctl_perf_event_max_stack);
+					sample, NULL, NULL, PERF_MAX_STACK_DEPTH);
 	if (err) {
 		callchain_param.order = saved_order;
 		return NULL;
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 3357479082ca..5d286f5d7906 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -7,6 +7,7 @@
 #include "auxtrace.h"
 #include "util.h"
 #include "debug.h"
+#include "vdso.h"
 
 char dso__symtab_origin(const struct dso *dso)
 {
@@ -62,9 +63,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		}
 		break;
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
-		/* skip the locally configured cache if a symfs is given */
-		if (symbol_conf.symfs[0] ||
-		    (dso__build_id_filename(dso, filename, size) == NULL))
+		if (dso__build_id_filename(dso, filename, size) == NULL)
 			ret = -1;
 		break;
 
@@ -1169,7 +1168,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 	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;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c4bfe11479a0..e82ba90cc969 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -44,6 +44,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 	perf_evlist__set_maps(evlist, cpus, threads);
 	fdarray__init(&evlist->pollfd, 64);
 	evlist->workload.pid = -1;
+	evlist->backward = false;
 }
 
 struct perf_evlist *perf_evlist__new(void)
@@ -679,6 +680,33 @@ static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 	return NULL;
 }
 
+static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
+{
+	int i;
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		int fd = evlist->mmap[i].fd;
+		int err;
+
+		if (fd < 0)
+			continue;
+		err = ioctl(fd, PERF_EVENT_IOC_PAUSE_OUTPUT, value ? 1 : 0);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+int perf_evlist__pause(struct perf_evlist *evlist)
+{
+	return perf_evlist__set_paused(evlist, true);
+}
+
+int perf_evlist__resume(struct perf_evlist *evlist)
+{
+	return perf_evlist__set_paused(evlist, false);
+}
+
 /* When check_messup is true, 'end' must points to a good entry */
 static union perf_event *
 perf_mmap__read(struct perf_mmap *md, bool check_messup, u64 start,
@@ -881,6 +909,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
 	if (evlist->mmap[idx].base != NULL) {
 		munmap(evlist->mmap[idx].base, evlist->mmap_len);
 		evlist->mmap[idx].base = NULL;
+		evlist->mmap[idx].fd = -1;
 		atomic_set(&evlist->mmap[idx].refcnt, 0);
 	}
 	auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
@@ -901,10 +930,14 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
 
 static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
+	int i;
+
 	evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
 	if (cpu_map__empty(evlist->cpus))
 		evlist->nr_mmaps = thread_map__nr(evlist->threads);
 	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
+	for (i = 0; i < evlist->nr_mmaps; i++)
+		evlist->mmap[i].fd = -1;
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
@@ -941,6 +974,7 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 		evlist->mmap[idx].base = NULL;
 		return -1;
 	}
+	evlist->mmap[idx].fd = fd;
 
 	if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
 				&mp->auxtrace_mp, evlist->mmap[idx].base, fd))
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 85d1b59802e8..d740fb877ab6 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -28,6 +28,7 @@ struct record_opts;
 struct perf_mmap {
 	void		 *base;
 	int		 mask;
+	int		 fd;
 	atomic_t	 refcnt;
 	u64		 prev;
 	struct auxtrace_mmap auxtrace_mmap;
@@ -43,6 +44,7 @@ struct perf_evlist {
 	bool		 overwrite;
 	bool		 enabled;
 	bool		 has_user_cpus;
+	bool		 backward;
 	size_t		 mmap_len;
 	int		 id_pos;
 	int		 is_pos;
@@ -135,6 +137,8 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx);
 
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
 
+int perf_evlist__pause(struct perf_evlist *evlist);
+int perf_evlist__resume(struct perf_evlist *evlist);
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 52c7d8884741..5d7037ef7d3b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -37,6 +37,7 @@ static struct {
 	bool clockid;
 	bool clockid_wrong;
 	bool lbr_flags;
+	bool write_backward;
 } perf_missing_features;
 
 static clockid_t clockid;
@@ -1376,6 +1377,8 @@ fallback_missing_features:
 	if (perf_missing_features.lbr_flags)
 		evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
 				     PERF_SAMPLE_BRANCH_NO_CYCLES);
+	if (perf_missing_features.write_backward)
+		evsel->attr.write_backward = false;
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
@@ -1438,6 +1441,12 @@ retry_open:
 				err = -EINVAL;
 				goto out_close;
 			}
+
+			if (evsel->overwrite &&
+			    perf_missing_features.write_backward) {
+				err = -EINVAL;
+				goto out_close;
+			}
 		}
 	}
 
@@ -1500,6 +1509,10 @@ try_fallback:
 			  PERF_SAMPLE_BRANCH_NO_FLAGS))) {
 		perf_missing_features.lbr_flags = true;
 		goto fallback_missing_features;
+	} else if (!perf_missing_features.write_backward &&
+			evsel->attr.write_backward) {
+		perf_missing_features.write_backward = true;
+		goto fallback_missing_features;
 	}
 
 out_close:
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 8a644fef452c..c1f10159804c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -112,6 +112,7 @@ struct perf_evsel {
 	bool			tracking;
 	bool			per_pkg;
 	bool			precise_max;
+	bool			overwrite;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index cfab531437c7..d1f19e0012d4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -117,6 +117,13 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
 			hists__set_unres_dso_col_len(hists, HISTC_DSO_TO);
 		}
+
+		if (h->branch_info->srcline_from)
+			hists__new_col_len(hists, HISTC_SRCLINE_FROM,
+					strlen(h->branch_info->srcline_from));
+		if (h->branch_info->srcline_to)
+			hists__new_col_len(hists, HISTC_SRCLINE_TO,
+					strlen(h->branch_info->srcline_to));
 	}
 
 	if (h->mem_info) {
@@ -1042,6 +1049,8 @@ void hist_entry__delete(struct hist_entry *he)
 	if (he->branch_info) {
 		map__zput(he->branch_info->from.map);
 		map__zput(he->branch_info->to.map);
+		free_srcline(he->branch_info->srcline_from);
+		free_srcline(he->branch_info->srcline_to);
 		zfree(&he->branch_info);
 	}
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 0f84bfb42bb1..7b54ccf1b737 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -52,6 +52,8 @@ enum hist_column {
 	HISTC_MEM_IADDR_SYMBOL,
 	HISTC_TRANSACTION,
 	HISTC_CYCLES,
+	HISTC_SRCLINE_FROM,
+	HISTC_SRCLINE_TO,
 	HISTC_TRACE,
 	HISTC_NR_COLS, /* Last entry */
 };
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index f9644f79686c..b1772180c820 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -43,6 +43,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->symbol_filter = NULL;
 	machine->id_hdr_size = 0;
+	machine->kptr_restrict_warned = false;
 	machine->comm_exec = false;
 	machine->kernel_start = 0;
 
@@ -709,7 +710,7 @@ static struct dso *machine__get_kernel(struct machine *machine)
 	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);
@@ -1135,10 +1136,10 @@ int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
 	const char *name;
-	u64 addr = machine__get_running_kernel_start(machine, &name);
+	u64 addr;
 	int ret;
 
-	if (!addr || kernel == NULL)
+	if (kernel == NULL)
 		return -1;
 
 	ret = __machine__create_kernel_maps(machine, kernel);
@@ -1160,8 +1161,9 @@ int machine__create_kernel_maps(struct machine *machine)
 	 */
 	map_groups__fixup_end(&machine->kmaps);
 
-	if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name,
-					     addr)) {
+	addr = machine__get_running_kernel_start(machine, &name);
+	if (!addr) {
+	} else if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) {
 		machine__destroy_kernel_maps(machine);
 		return -1;
 	}
@@ -1769,11 +1771,6 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 		 */
 		int mix_chain_nr = i + 1 + lbr_nr + 1;
 
-		if (mix_chain_nr > (int)sysctl_perf_event_max_stack + PERF_MAX_BRANCH_DEPTH) {
-			pr_warning("corrupted callchain. skipping...\n");
-			return 0;
-		}
-
 		for (j = 0; j < mix_chain_nr; j++) {
 			if (callchain_param.order == ORDER_CALLEE) {
 				if (j < i + 1)
@@ -1811,9 +1808,9 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 {
 	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;
 	int skip_idx = -1;
 	int first_call = 0;
 
@@ -1828,8 +1825,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	 * Based on DWARF debug information, some architectures skip
 	 * a callchain entry saved by the kernel.
 	 */
-	if (chain->nr < sysctl_perf_event_max_stack)
-		skip_idx = arch_skip_callchain_idx(thread, chain);
+	skip_idx = arch_skip_callchain_idx(thread, chain);
 
 	/*
 	 * Add branches to call stack for easier browsing. This gives
@@ -1889,12 +1885,8 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 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;
+	     i < chain_nr && nr_entries < max_stack; i++) {
 		u64 ip;
 
 		if (callchain_param.order == ORDER_CALLEE)
@@ -1908,6 +1900,9 @@ check_calls:
 #endif
 		ip = chain->ips[j];
 
+		if (ip < PERF_CONTEXT_MAX)
+                       ++nr_entries;
+
 		err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip);
 
 		if (err)
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 83f46790c52f..41ac9cfd416b 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -28,6 +28,7 @@ struct machine {
 	pid_t		  pid;
 	u16		  id_hdr_size;
 	bool		  comm_exec;
+	bool		  kptr_restrict_warned;
 	char		  *root_dir;
 	struct rb_root	  threads;
 	pthread_rwlock_t  threads_lock;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 62c7f6988e0e..5d1eb1ccd96c 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -264,8 +264,7 @@ static SV *perl_process_callchain(struct perf_sample *sample,
 		goto exit;
 
 	if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
-				      sample, NULL, NULL,
-				      sysctl_perf_event_max_stack) != 0) {
+				      sample, NULL, NULL, scripting_max_stack) != 0) {
 		pr_err("Failed to resolve callchain. Skipping\n");
 		goto exit;
 	}
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 20e69edd5006..c4e9bd70723c 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -353,6 +353,88 @@ struct sort_entry sort_srcline = {
 	.se_width_idx	= HISTC_SRCLINE,
 };
 
+/* --sort srcline_from */
+
+static int64_t
+sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	if (!left->branch_info->srcline_from) {
+		struct map *map = left->branch_info->from.map;
+		if (!map)
+			left->branch_info->srcline_from = SRCLINE_UNKNOWN;
+		else
+			left->branch_info->srcline_from = get_srcline(map->dso,
+					   map__rip_2objdump(map,
+							     left->branch_info->from.al_addr),
+							 left->branch_info->from.sym, true);
+	}
+	if (!right->branch_info->srcline_from) {
+		struct map *map = right->branch_info->from.map;
+		if (!map)
+			right->branch_info->srcline_from = SRCLINE_UNKNOWN;
+		else
+			right->branch_info->srcline_from = get_srcline(map->dso,
+					     map__rip_2objdump(map,
+							       right->branch_info->from.al_addr),
+						     right->branch_info->from.sym, true);
+	}
+	return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from);
+}
+
+static int hist_entry__srcline_from_snprintf(struct hist_entry *he, char *bf,
+					size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->branch_info->srcline_from);
+}
+
+struct sort_entry sort_srcline_from = {
+	.se_header	= "From Source:Line",
+	.se_cmp		= sort__srcline_from_cmp,
+	.se_snprintf	= hist_entry__srcline_from_snprintf,
+	.se_width_idx	= HISTC_SRCLINE_FROM,
+};
+
+/* --sort srcline_to */
+
+static int64_t
+sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	if (!left->branch_info->srcline_to) {
+		struct map *map = left->branch_info->to.map;
+		if (!map)
+			left->branch_info->srcline_to = SRCLINE_UNKNOWN;
+		else
+			left->branch_info->srcline_to = get_srcline(map->dso,
+					   map__rip_2objdump(map,
+							     left->branch_info->to.al_addr),
+							 left->branch_info->from.sym, true);
+	}
+	if (!right->branch_info->srcline_to) {
+		struct map *map = right->branch_info->to.map;
+		if (!map)
+			right->branch_info->srcline_to = SRCLINE_UNKNOWN;
+		else
+			right->branch_info->srcline_to = get_srcline(map->dso,
+					     map__rip_2objdump(map,
+							       right->branch_info->to.al_addr),
+						     right->branch_info->to.sym, true);
+	}
+	return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to);
+}
+
+static int hist_entry__srcline_to_snprintf(struct hist_entry *he, char *bf,
+					size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->branch_info->srcline_to);
+}
+
+struct sort_entry sort_srcline_to = {
+	.se_header	= "To Source:Line",
+	.se_cmp		= sort__srcline_to_cmp,
+	.se_snprintf	= hist_entry__srcline_to_snprintf,
+	.se_width_idx	= HISTC_SRCLINE_TO,
+};
+
 /* --sort srcfile */
 
 static char no_srcfile[1];
@@ -1347,6 +1429,8 @@ static struct sort_dimension bstack_sort_dimensions[] = {
 	DIM(SORT_IN_TX, "in_tx", sort_in_tx),
 	DIM(SORT_ABORT, "abort", sort_abort),
 	DIM(SORT_CYCLES, "cycles", sort_cycles),
+	DIM(SORT_SRCLINE_FROM, "srcline_from", sort_srcline_from),
+	DIM(SORT_SRCLINE_TO, "srcline_to", sort_srcline_to),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 42927f448bcb..ebb59cacd092 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -215,6 +215,8 @@ enum sort_type {
 	SORT_ABORT,
 	SORT_IN_TX,
 	SORT_CYCLES,
+	SORT_SRCLINE_FROM,
+	SORT_SRCLINE_TO,
 
 	/* memory mode specific sort keys */
 	__SORT_MEMORY_MODE,
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index fdb71961143e..aa9efe08762b 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -94,7 +94,8 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 {
 	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]);
@@ -188,7 +189,7 @@ static void print_stalled_cycles_backend(int cpu,
 
 	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,
@@ -444,7 +445,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			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);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 7fb33304fb4e..20f9cb32b703 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1662,8 +1662,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 
 	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) {
@@ -1699,8 +1699,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 	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",
@@ -1769,7 +1769,7 @@ do_kallsyms:
 
 	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);
 	}
@@ -2033,3 +2033,26 @@ void symbol__exit(void)
 	symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL;
 	symbol_conf.initialized = false;
 }
+
+int symbol__config_symfs(const struct option *opt __maybe_unused,
+			 const char *dir, int unset __maybe_unused)
+{
+	char *bf = NULL;
+	int ret;
+
+	symbol_conf.symfs = strdup(dir);
+	if (symbol_conf.symfs == NULL)
+		return -ENOMEM;
+
+	/* skip the locally configured cache if a symfs is given, and
+	 * config buildid dir to symfs/.debug
+	 */
+	ret = asprintf(&bf, "%s/%s", dir, ".debug");
+	if (ret < 0)
+		return -ENOMEM;
+
+	set_buildid_dir(bf);
+
+	free(bf);
+	return 0;
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 2b5e4ed76fcb..b10d558a8803 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -44,6 +44,9 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 #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)
@@ -183,6 +186,8 @@ struct branch_info {
 	struct addr_map_symbol from;
 	struct addr_map_symbol to;
 	struct branch_flags flags;
+	char			*srcline_from;
+	char			*srcline_to;
 };
 
 struct mem_info {
@@ -287,6 +292,8 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 bool symbol__restricted_filename(const char *filename,
 				 const char *restricted_filename);
 bool symbol__is_idle(struct symbol *sym);
+int symbol__config_symfs(const struct option *opt __maybe_unused,
+			 const char *dir, int unset __maybe_unused);
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, symbol_filter_t filter,
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index f92c37abb0a8..b2940c88734a 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -27,7 +27,6 @@ struct perf_top {
 	int		   max_stack;
 	bool		   hide_kernel_symbols, hide_user_symbols, zero;
 	bool		   use_tui, use_stdio;
-	bool		   kptr_restrict_warned;
 	bool		   vmlinux_warned;
 	bool		   dump_symtab;
 	struct hist_entry  *sym_filter_entry;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index eab077ad6ca9..23504ad5d6dd 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -33,7 +33,8 @@ struct callchain_param	callchain_param = {
 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;
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 7651633a8dc7..1e8c3167b9fb 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -261,7 +261,8 @@ void sighandler_dump_stack(int sig);
 
 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;