Merge tag 'perf-core-for-mingo-4.11-20170306' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

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

New features:

- Allow sorting by symbol_size in 'perf report' and 'perf top' (Charles Baylis)

  E.g.:

  # perf report -s symbol_size,symbol

  Samples: 9K of event 'cycles:k', Event count (approx.): 2870461623
  Overhead  Symbol size  Symbol
    14.55%          326  [k] flush_tlb_mm_range
     7.20%         1045  [k] filemap_map_pages
     5.82%          124  [k] vma_interval_tree_insert
     5.18%         2430  [k] unmap_page_range
     2.57%          571  [k] vma_interval_tree_remove
     1.94%          494  [k] page_add_file_rmap
     1.82%          740  [k] page_remove_rmap
     1.66%         1017  [k] release_pages
     1.57%         1636  [k] update_blocked_averages
     1.57%           76  [k] unlock_page

- Add support for -p/--pid, -a/--all-cpus and -C/--cpu in 'perf ftrace' (Namhyung Kim)

Change in behaviour:

- Make system wide (-a) the default option if no target was specified and one
  of following conditions is met:

  - No workload specified (current behaviour)

  - A workload is specified but all requested events are system wide ones,
    like uncore ones. (Jiri Olsa)

Fixes:

- Add missing initialization to the instruction decoder used in the
  intel PT/BTS code, which was causing lots of failures in 'perf test',
  looking for a value when there was none (Adrian Hunter)

Infrastructure changes:

- Add arch code needed to adopt the kernel's refcount_t to aid in
  catching bugs when using atomic_t as a reference counter, basically
  cmpxchg related functions (Arnaldo Carvalho de Melo)

- Convert the code using atomic_t as reference counts to refcount_t
  (Elena Rashetova)

- Add feature test for sched_getcpu() to more easily check for its
  presence in the many libc implementations and accross different
  versions of such C libraries (Arnaldo Carvalho de Melo)

- Issue a HW watchdog disable hint in 'perf stat' for when some of the
  requested events can't get counted because a PMU counter is taken by that
  watchdog (Borislav Petkov).

- Add mapping for Intel's KnightsMill PMU events (Karol Wachowski)

Documentation changes:

- Clarify the term 'convergence' in:

   perf bench numa numa-mem -h --show_convergence (Jiri Olsa)

Kernel code changes:

- Ensure probe location is at function entry in kretprobes (Naveen N. Rao)

- Allow return probes with offsets and absolute addresses (Naveen N. Rao)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

6 files changed, 177 insertions, 0 deletions

diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h
index 2ba78c9f5701..5e9738f97bf3 100644
--- a/tools/include/asm-generic/atomic-gcc.h
+++ b/tools/include/asm-generic/atomic-gcc.h
@@ -60,4 +60,12 @@ static inline int atomic_dec_and_test(atomic_t *v)
 	return __sync_sub_and_fetch(&v->counter, 1) == 0;
 }
 
+#define cmpxchg(ptr, oldval, newval) \
+	__sync_val_compare_and_swap(ptr, oldval, newval)
+
+static inline int atomic_cmpxchg(atomic_t *v, int oldval, int newval)
+{
+	return cmpxchg(&(v)->counter, oldval, newval);
+}
+
 #endif /* __TOOLS_ASM_GENERIC_ATOMIC_H */
diff --git a/tools/include/linux/atomic.h b/tools/include/linux/atomic.h
index 4e3d3d18ebab..9f21fc2b092b 100644
--- a/tools/include/linux/atomic.h
+++ b/tools/include/linux/atomic.h
@@ -3,4 +3,10 @@
 
 #include <asm/atomic.h>
 
+/* atomic_cmpxchg_relaxed */
+#ifndef atomic_cmpxchg_relaxed
+#define  atomic_cmpxchg_relaxed		atomic_cmpxchg
+#define  atomic_cmpxchg_release         atomic_cmpxchg
+#endif /* atomic_cmpxchg_relaxed */
+
 #endif /* __TOOLS_LINUX_ATOMIC_H */
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index 48af2f10a42d..616935f1ff56 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -12,3 +12,7 @@
 #if GCC_VERSION >= 70000 && !defined(__CHECKER__)
 # define __fallthrough __attribute__ ((fallthrough))
 #endif
+
+#if GCC_VERSION >= 40300
+# define __compiletime_error(message) __attribute__((error(message)))
+#endif /* GCC_VERSION >= 40300 */
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 8de163b17c0d..c9e65e8faacd 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -5,6 +5,10 @@
 #include <linux/compiler-gcc.h>
 #endif
 
+#ifndef __compiletime_error
+# define __compiletime_error(message)
+#endif
+
 /* Optimization barrier */
 /* The "volatile" is due to gcc bugs */
 #define barrier() __asm__ __volatile__("": : :"memory")
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 28607db02bd3..adb4d0147755 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -5,6 +5,10 @@
 #include <stddef.h>
 #include <assert.h>
 
+#ifndef UINT_MAX
+#define UINT_MAX	(~0U)
+#endif
+
 #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
 
 #define PERF_ALIGN(x, a)	__PERF_ALIGN_MASK(x, (typeof(x))(a)-1)
diff --git a/tools/include/linux/refcount.h b/tools/include/linux/refcount.h
new file mode 100644
index 000000000000..a0177c1f55b1
--- /dev/null
+++ b/tools/include/linux/refcount.h
@@ -0,0 +1,151 @@
+#ifndef _TOOLS_LINUX_REFCOUNT_H
+#define _TOOLS_LINUX_REFCOUNT_H
+
+/*
+ * Variant of atomic_t specialized for reference counts.
+ *
+ * The interface matches the atomic_t interface (to aid in porting) but only
+ * provides the few functions one should use for reference counting.
+ *
+ * It differs in that the counter saturates at UINT_MAX and will not move once
+ * there. This avoids wrapping the counter and causing 'spurious'
+ * use-after-free issues.
+ *
+ * Memory ordering rules are slightly relaxed wrt regular atomic_t functions
+ * and provide only what is strictly required for refcounts.
+ *
+ * The increments are fully relaxed; these will not provide ordering. The
+ * rationale is that whatever is used to obtain the object we're increasing the
+ * reference count on will provide the ordering. For locked data structures,
+ * its the lock acquire, for RCU/lockless data structures its the dependent
+ * load.
+ *
+ * Do note that inc_not_zero() provides a control dependency which will order
+ * future stores against the inc, this ensures we'll never modify the object
+ * if we did not in fact acquire a reference.
+ *
+ * The decrements will provide release order, such that all the prior loads and
+ * stores will be issued before, it also provides a control dependency, which
+ * will order us against the subsequent free().
+ *
+ * The control dependency is against the load of the cmpxchg (ll/sc) that
+ * succeeded. This means the stores aren't fully ordered, but this is fine
+ * because the 1->0 transition indicates no concurrency.
+ *
+ * Note that the allocator is responsible for ordering things between free()
+ * and alloc().
+ *
+ */
+
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+
+#ifdef NDEBUG
+#define REFCOUNT_WARN(cond, str) (void)(cond)
+#define __refcount_check
+#else
+#define REFCOUNT_WARN(cond, str) BUG_ON(cond)
+#define __refcount_check	__must_check
+#endif
+
+typedef struct refcount_struct {
+	atomic_t refs;
+} refcount_t;
+
+#define REFCOUNT_INIT(n)	{ .refs = ATOMIC_INIT(n), }
+
+static inline void refcount_set(refcount_t *r, unsigned int n)
+{
+	atomic_set(&r->refs, n);
+}
+
+static inline unsigned int refcount_read(const refcount_t *r)
+{
+	return atomic_read(&r->refs);
+}
+
+/*
+ * Similar to atomic_inc_not_zero(), will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_inc_not_zero(refcount_t *r)
+{
+	unsigned int old, new, val = atomic_read(&r->refs);
+
+	for (;;) {
+		new = val + 1;
+
+		if (!val)
+			return false;
+
+		if (unlikely(!new))
+			return true;
+
+		old = atomic_cmpxchg_relaxed(&r->refs, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+
+	REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+
+	return true;
+}
+
+/*
+ * Similar to atomic_inc(), will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller already has a
+ * reference on the object, will WARN when this is not so.
+ */
+static inline void refcount_inc(refcount_t *r)
+{
+	REFCOUNT_WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+}
+
+/*
+ * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
+ * decrement when saturated at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides a control dependency such that free() must come after.
+ * See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+{
+	unsigned int old, new, val = atomic_read(&r->refs);
+
+	for (;;) {
+		if (unlikely(val == UINT_MAX))
+			return false;
+
+		new = val - i;
+		if (new > val) {
+			REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+			return false;
+		}
+
+		old = atomic_cmpxchg_release(&r->refs, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+
+	return !new;
+}
+
+static inline __refcount_check
+bool refcount_dec_and_test(refcount_t *r)
+{
+	return refcount_sub_and_test(1, r);
+}
+
+
+#endif /* _ATOMIC_LINUX_REFCOUNT_H */