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

Pull perf changes from Ingo Molnar:
 "Main changes:

  Kernel side changes:

   - Add SNB/IVB/HSW client uncore memory controller support (Stephane
     Eranian)

   - Fix various x86/P4 PMU driver bugs (Don Zickus)

  Tooling, user visible changes:

   - Add several futex 'perf bench' microbenchmarks (Davidlohr Bueso)

   - Speed up thread map generation (Don Zickus)

   - Introduce 'perf kvm --list-cmds' command line option for use by
     scripts (Ramkumar Ramachandra)

   - Print the evsel name in the annotate stdio output, prep to fix
     support outputting annotation for multiple events, not just for the
     first one (Arnaldo Carvalho de Melo)

   - Allow setting preferred callchain method in .perfconfig (Jiri Olsa)

   - Show in what binaries/modules 'perf probe's are set (Masami
     Hiramatsu)

   - Support distro-style debuginfo for uprobe in 'perf probe' (Masami
     Hiramatsu)

  Tooling, internal changes and fixes:

   - Use tid in mmap/mmap2 events to find maps (Don Zickus)

   - Record the reason for filtering an address_location (Namhyung Kim)

   - Apply all filters to an addr_location (Namhyung Kim)

   - Merge al->filtered with hist_entry->filtered in report/hists
     (Namhyung Kim)

   - Fix memory leak when synthesizing thread records (Namhyung Kim)

   - Use ui__has_annotation() in 'report' (Namhyung Kim)

   - hists browser refactorings to reuse code accross UIs (Namhyung Kim)

   - Add support for the new DWARF unwinder library in elfutils (Jiri
     Olsa)

   - Fix build race in the generation of bison files (Jiri Olsa)

   - Further streamline the feature detection display, trimming it a bit
     to show just the libraries detected, using VF=1 gets a more verbose
     output, showing the less interesting feature checks as well (Jiri
     Olsa).

   - Check compatible symtab type before loading dso (Namhyung Kim)

   - Check return value of filename__read_debuglink() (Stephane Eranian)

   - Move some hashing and fs related code from tools/perf/util/ to
     tools/lib/ so that it can be used by more tools/ living utilities
     (Borislav Petkov)

   - Prepare DWARF unwinding code for using an elfutils alternative
     unwinding library (Jiri Olsa)

   - Fix DWARF unwind max_stack processing (Jiri Olsa)

   - Add dwarf unwind 'perf test' entry (Jiri Olsa)

   - 'perf probe' improvements including memory leak fixes, sharing the
     intlist class with other tools, uprobes/kprobes code sharing and
     use of ref_reloc_sym (Masami Hiramatsu)

   - Shorten sample symbol resolving by adding cpumode to struct
     addr_location (Arnaldo Carvalho de Melo)

   - Fix synthesizing mmaps for threads (Don Zickus)

   - Fix invalid output on event group stdio report (Namhyung Kim)

   - Fixup header alignment in 'perf sched latency' output (Ramkumar
     Ramachandra)

   - Fix off-by-one error in 'perf timechart record' argv handling
     (Ramkumar Ramachandra)

  Tooling, cleanups:

   - Remove unused thread__find_map function (Jiri Olsa)

   - Remove unused simple_strtoul() function (Ramkumar Ramachandra)

  Tooling, documentation updates:

   - Update function names in debug messages (Ramkumar Ramachandra)

   - Update some code references in design.txt (Ramkumar Ramachandra)

   - Clarify load-latency information in the 'perf mem' docs (Andi
     Kleen)

   - Clarify x86 register naming in 'perf probe' docs (Andi Kleen)"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (96 commits)
  perf tools: Remove unused simple_strtoul() function
  perf tools: Update some code references in design.txt
  perf evsel: Update function names in debug messages
  perf tools: Remove thread__find_map function
  perf annotate: Print the evsel name in the stdio output
  perf report: Use ui__has_annotation()
  perf tools: Fix memory leak when synthesizing thread records
  perf tools: Use tid in mmap/mmap2 events to find maps
  perf report: Merge al->filtered with hist_entry->filtered
  perf symbols: Apply all filters to an addr_location
  perf symbols: Record the reason for filtering an address_location
  perf sched: Fixup header alignment in 'latency' output
  perf timechart: Fix off-by-one error in 'record' argv handling
  perf machine: Factor machine__find_thread to take tid argument
  perf tools: Speed up thread map generation
  perf kvm: introduce --list-cmds for use by scripts
  perf ui hists: Pass evsel to hpp->header/width functions explicitly
  perf symbols: Introduce thread__find_cpumode_addr_location
  perf session: Change header.misc dump from decimal to hex
  perf ui/tui: Reuse generic __hpp__fmt() code
  ...

6 files changed, 218 insertions, 3 deletions

diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 8801fe02f206..1641542e3636 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -3,7 +3,14 @@ PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
 ifndef NO_LIBUNWIND
-LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
+endif
+ifndef NO_LIBDW_DWARF_UNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libdw.o
+endif
+ifndef NO_DWARF_UNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o
 endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index e84ca76aae77..fc819ca34a7e 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -5,14 +5,20 @@
 #include "../../util/types.h"
 #include <asm/perf_regs.h>
 
+void perf_regs_load(u64 *regs);
+
 #ifndef HAVE_ARCH_X86_64_SUPPORT
 #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
+#define PERF_REGS_MAX PERF_REG_X86_32_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32
 #else
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
 		       (1ULL << PERF_REG_X86_ES) | \
 		       (1ULL << PERF_REG_X86_FS) | \
 		       (1ULL << PERF_REG_X86_GS))
 #define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT)
+#define PERF_REGS_MAX PERF_REG_X86_64_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
 #endif
 #define PERF_REG_IP PERF_REG_X86_IP
 #define PERF_REG_SP PERF_REG_X86_SP
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
new file mode 100644
index 000000000000..b602ad93ce63
--- /dev/null
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -0,0 +1,59 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+			 struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_X86_SP];
+
+	map = map_groups__find(&thread->mg, MAP__FUNCTION, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = malloc(sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S
new file mode 100644
index 000000000000..99167bf644ea
--- /dev/null
+++ b/tools/perf/arch/x86/tests/regs_load.S
@@ -0,0 +1,92 @@
+
+#include <linux/linkage.h>
+
+#define AX	 0
+#define BX	 1 * 8
+#define CX	 2 * 8
+#define DX	 3 * 8
+#define SI	 4 * 8
+#define DI	 5 * 8
+#define BP	 6 * 8
+#define SP	 7 * 8
+#define IP	 8 * 8
+#define FLAGS	 9 * 8
+#define CS	10 * 8
+#define SS	11 * 8
+#define DS	12 * 8
+#define ES	13 * 8
+#define FS	14 * 8
+#define GS	15 * 8
+#define R8	16 * 8
+#define R9	17 * 8
+#define R10	18 * 8
+#define R11	19 * 8
+#define R12	20 * 8
+#define R13	21 * 8
+#define R14	22 * 8
+#define R15	23 * 8
+
+.text
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+ENTRY(perf_regs_load)
+	movq %rax, AX(%rdi)
+	movq %rbx, BX(%rdi)
+	movq %rcx, CX(%rdi)
+	movq %rdx, DX(%rdi)
+	movq %rsi, SI(%rdi)
+	movq %rdi, DI(%rdi)
+	movq %rbp, BP(%rdi)
+
+	leaq 8(%rsp), %rax /* exclude this call.  */
+	movq %rax, SP(%rdi)
+
+	movq 0(%rsp), %rax
+	movq %rax, IP(%rdi)
+
+	movq $0, FLAGS(%rdi)
+	movq $0, CS(%rdi)
+	movq $0, SS(%rdi)
+	movq $0, DS(%rdi)
+	movq $0, ES(%rdi)
+	movq $0, FS(%rdi)
+	movq $0, GS(%rdi)
+
+	movq %r8,  R8(%rdi)
+	movq %r9,  R9(%rdi)
+	movq %r10, R10(%rdi)
+	movq %r11, R11(%rdi)
+	movq %r12, R12(%rdi)
+	movq %r13, R13(%rdi)
+	movq %r14, R14(%rdi)
+	movq %r15, R15(%rdi)
+	ret
+ENDPROC(perf_regs_load)
+#else
+ENTRY(perf_regs_load)
+	push %edi
+	movl 8(%esp), %edi
+	movl %eax, AX(%edi)
+	movl %ebx, BX(%edi)
+	movl %ecx, CX(%edi)
+	movl %edx, DX(%edi)
+	movl %esi, SI(%edi)
+	pop %eax
+	movl %eax, DI(%edi)
+	movl %ebp, BP(%edi)
+
+	leal 4(%esp), %eax /* exclude this call.  */
+	movl %eax, SP(%edi)
+
+	movl 0(%esp), %eax
+	movl %eax, IP(%edi)
+
+	movl $0, FLAGS(%edi)
+	movl $0, CS(%edi)
+	movl $0, SS(%edi)
+	movl $0, DS(%edi)
+	movl $0, ES(%edi)
+	movl $0, FS(%edi)
+	movl $0, GS(%edi)
+	ret
+ENDPROC(perf_regs_load)
+#endif
diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c
new file mode 100644
index 000000000000..c4b72176ca83
--- /dev/null
+++ b/tools/perf/arch/x86/util/unwind-libdw.c
@@ -0,0 +1,51 @@
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[17];
+	unsigned nregs;
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_X86_##r);	\
+	val;							\
+})
+
+	if (user_regs->abi == PERF_SAMPLE_REGS_ABI_32) {
+		dwarf_regs[0] = REG(AX);
+		dwarf_regs[1] = REG(CX);
+		dwarf_regs[2] = REG(DX);
+		dwarf_regs[3] = REG(BX);
+		dwarf_regs[4] = REG(SP);
+		dwarf_regs[5] = REG(BP);
+		dwarf_regs[6] = REG(SI);
+		dwarf_regs[7] = REG(DI);
+		dwarf_regs[8] = REG(IP);
+		nregs = 9;
+	} else {
+		dwarf_regs[0]  = REG(AX);
+		dwarf_regs[1]  = REG(DX);
+		dwarf_regs[2]  = REG(CX);
+		dwarf_regs[3]  = REG(BX);
+		dwarf_regs[4]  = REG(SI);
+		dwarf_regs[5]  = REG(DI);
+		dwarf_regs[6]  = REG(BP);
+		dwarf_regs[7]  = REG(SP);
+		dwarf_regs[8]  = REG(R8);
+		dwarf_regs[9]  = REG(R9);
+		dwarf_regs[10] = REG(R10);
+		dwarf_regs[11] = REG(R11);
+		dwarf_regs[12] = REG(R12);
+		dwarf_regs[13] = REG(R13);
+		dwarf_regs[14] = REG(R14);
+		dwarf_regs[15] = REG(R15);
+		dwarf_regs[16] = REG(IP);
+		nregs = 17;
+	}
+
+	return dwfl_thread_state_registers(thread, 0, nregs, dwarf_regs);
+}
diff --git a/tools/perf/arch/x86/util/unwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index 456a88cf5b37..3261f68c6a7c 100644
--- a/tools/perf/arch/x86/util/unwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -5,7 +5,7 @@
 #include "../../util/unwind.h"
 
 #ifdef HAVE_ARCH_X86_64_SUPPORT
-int unwind__arch_reg_id(int regnum)
+int libunwind__arch_reg_id(int regnum)
 {
 	int id;
 
@@ -69,7 +69,7 @@ int unwind__arch_reg_id(int regnum)
 	return id;
 }
 #else
-int unwind__arch_reg_id(int regnum)
+int libunwind__arch_reg_id(int regnum)
 {
 	int id;