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

Pull perf updates and fixes from Ingo Molnar:
 "These are almost all tooling updates: 'perf top', 'perf trace' and
  'perf script' fixes and updates, an UAPI header sync with the merge
  window versions, license marker updates, much improved Sparc support
  from David Miller, and a number of fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (66 commits)
  perf intel-pt/bts: Calculate cpumode for synthesized samples
  perf intel-pt: Insert callchain context into synthesized callchains
  perf tools: Don't clone maps from parent when synthesizing forks
  perf top: Start display thread earlier
  tools headers uapi: Update linux/if_link.h header copy
  tools headers uapi: Update linux/netlink.h header copy
  tools headers: Sync the various kvm.h header copies
  tools include uapi: Update linux/mmap.h copy
  perf trace beauty: Use the mmap flags table generated from headers
  perf beauty: Wire up the mmap flags table generator to the Makefile
  perf beauty: Add a generator for MAP_ mmap's flag constants
  tools include uapi: Update asound.h copy
  tools arch uapi: Update asm-generic/unistd.h and arm64 unistd.h copies
  tools include uapi: Update linux/fs.h copy
  perf callchain: Honour the ordering of PERF_CONTEXT_{USER,KERNEL,etc}
  perf cs-etm: Correct CPU mode for samples
  perf unwind: Take pgoff into account when reporting elf to libdwfl
  perf top: Do not use overwrite mode by default
  perf top: Allow disabling the overwrite mode
  perf trace: Beautify mount's first pathname arg
  ...

1 files changed, 35 insertions, 9 deletions

diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index c091635bf7dc..61a4286a74dc 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -310,20 +310,46 @@ void thread_stack__free(struct thread *thread)
         }
 }
 
+static inline u64 callchain_context(u64 ip, u64 kernel_start)
+{
+        return ip < kernel_start ? PERF_CONTEXT_USER : PERF_CONTEXT_KERNEL;
+}
+
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
-                          size_t sz, u64 ip)
+                          size_t sz, u64 ip, u64 kernel_start)
 {
-        size_t i;
+        u64 context = callchain_context(ip, kernel_start);
+        u64 last_context;
+        size_t i, j;
 
-        if (!thread || !thread->ts)
-                chain->nr = 1;
-        else
-                chain->nr = min(sz, thread->ts->cnt + 1);
+        if (sz < 2) {
+                chain->nr = 0;
+                return;
+        }
 
-        chain->ips[0] = ip;
+        chain->ips[0] = context;
+        chain->ips[1] = ip;
+
+        if (!thread || !thread->ts) {
+                chain->nr = 2;
+                return;
+        }
+
+        last_context = context;
+
+        for (i = 2, j = 1; i < sz && j <= thread->ts->cnt; i++, j++) {
+                ip = thread->ts->stack[thread->ts->cnt - j].ret_addr;
+                context = callchain_context(ip, kernel_start);
+                if (context != last_context) {
+                        if (i >= sz - 1)
+                                break;
+                        chain->ips[i++] = context;
+                        last_context = context;
+                }
+                chain->ips[i] = ip;
+        }
 
-        for (i = 1; i < chain->nr; i++)
-                chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+        chain->nr = i;
 }
 
 struct call_return_processor *