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

Pull perf fixes from Ingo Molnar:
 "A bit larger than what I'd wish for - half of it is due to hw driver
  updates to Intel Ivy-Bridge which info got recently released,
  cycles:pp should work there now too, amongst other things.  (but we
  are generally making exceptions for hardware enablement of this type.)

  There are also callchain fixes in it - responding to mostly
  theoretical (but valid) concerns.  The tooling side sports perf.data
  endianness/portability fixes which did not make it for the merge
  window - and various other fixes as well."

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (26 commits)
  perf/x86: Check user address explicitly in copy_from_user_nmi()
  perf/x86: Check if user fp is valid
  perf: Limit callchains to 127
  perf/x86: Allow multiple stacks
  perf/x86: Update SNB PEBS constraints
  perf/x86: Enable/Add IvyBridge hardware support
  perf/x86: Implement cycles:p for SNB/IVB
  perf/x86: Fix Intel shared extra MSR allocation
  x86/decoder: Fix bsr/bsf/jmpe decoding with operand-size prefix
  perf: Remove duplicate invocation on perf_event_for_each
  perf uprobes: Remove unnecessary check before strlist__delete
  perf symbols: Check for valid dso before creating map
  perf evsel: Fix 32 bit values endianity swap for sample_id_all header
  perf session: Handle endianity swap on sample_id_all header data
  perf symbols: Handle different endians properly during symbol load
  perf evlist: Pass third argument to ioctl explicitly
  perf tools: Update ioctl documentation for PERF_IOC_FLAG_GROUP
  perf tools: Make --version show kernel version instead of pull req tag
  perf tools: Check if callchain is corrupted
  perf callchain: Make callchain cursors TLS
  ...

4 files changed, 120 insertions, 47 deletions

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e049d6da0183..c4706cf9c011 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1496,6 +1496,7 @@ static struct cpu_hw_events *allocate_fake_cpuc(void)
                 if (!cpuc->shared_regs)
                         goto error;
         }
+        cpuc->is_fake = 1;
         return cpuc;
 error:
         free_fake_cpuc(cpuc);
@@ -1756,6 +1757,12 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
         dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
 }
 
+static inline int
+valid_user_frame(const void __user *fp, unsigned long size)
+{
+        return (__range_not_ok(fp, size, TASK_SIZE) == 0);
+}
+
 #ifdef CONFIG_COMPAT
 
 #include <asm/compat.h>
@@ -1780,7 +1787,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
                 if (bytes != sizeof(frame))
                         break;
 
-                if (fp < compat_ptr(regs->sp))
+                if (!valid_user_frame(fp, sizeof(frame)))
                         break;
 
                 perf_callchain_store(entry, frame.return_address);
@@ -1826,7 +1833,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
                 if (bytes != sizeof(frame))
                         break;
 
-                if ((unsigned long)fp < regs->sp)
+                if (!valid_user_frame(fp, sizeof(frame)))
                         break;
 
                 perf_callchain_store(entry, frame.return_address);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6638aaf54493..7241e2fc3c17 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -117,6 +117,7 @@ struct cpu_hw_events {
         struct perf_event       *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
 
         unsigned int            group_flag;
+        int                     is_fake;
 
         /*
          * Intel DebugStore bits
@@ -364,6 +365,7 @@ struct x86_pmu {
         int             pebs_record_size;
         void            (*drain_pebs)(struct pt_regs *regs);
         struct event_constraint *pebs_constraints;
+        void            (*pebs_aliases)(struct perf_event *event);
 
         /*
          * Intel LBR
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 166546ec6aef..187c294bc658 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1119,27 +1119,33 @@ intel_bts_constraints(struct perf_event *event)
         return NULL;
 }
 
-static bool intel_try_alt_er(struct perf_event *event, int orig_idx)
+static int intel_alt_er(int idx)
 {
         if (!(x86_pmu.er_flags & ERF_HAS_RSP_1))
-                return false;
+                return idx;
 
-        if (event->hw.extra_reg.idx == EXTRA_REG_RSP_0) {
-                event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
-                event->hw.config |= 0x01bb;
-                event->hw.extra_reg.idx = EXTRA_REG_RSP_1;
-                event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
-        } else if (event->hw.extra_reg.idx == EXTRA_REG_RSP_1) {
+        if (idx == EXTRA_REG_RSP_0)
+                return EXTRA_REG_RSP_1;
+
+        if (idx == EXTRA_REG_RSP_1)
+                return EXTRA_REG_RSP_0;
+
+        return idx;
+}
+
+static void intel_fixup_er(struct perf_event *event, int idx)
+{
+        event->hw.extra_reg.idx = idx;
+
+        if (idx == EXTRA_REG_RSP_0) {
                 event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
                 event->hw.config |= 0x01b7;
-                event->hw.extra_reg.idx = EXTRA_REG_RSP_0;
                 event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
+        } else if (idx == EXTRA_REG_RSP_1) {
+                event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
+                event->hw.config |= 0x01bb;
+                event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
         }
-
-        if (event->hw.extra_reg.idx == orig_idx)
-                return false;
-
-        return true;
 }
 
 /*
@@ -1157,14 +1163,18 @@ __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
         struct event_constraint *c = &emptyconstraint;
         struct er_account *era;
         unsigned long flags;
-        int orig_idx = reg->idx;
+        int idx = reg->idx;
 
-        /* already allocated shared msr */
-        if (reg->alloc)
+        /*
+         * reg->alloc can be set due to existing state, so for fake cpuc we
+         * need to ignore this, otherwise we might fail to allocate proper fake
+         * state for this extra reg constraint. Also see the comment below.
+         */
+        if (reg->alloc && !cpuc->is_fake)
                 return NULL; /* call x86_get_event_constraint() */
 
 again:
-        era = &cpuc->shared_regs->regs[reg->idx];
+        era = &cpuc->shared_regs->regs[idx];
         /*
          * we use spin_lock_irqsave() to avoid lockdep issues when
          * passing a fake cpuc
@@ -1173,6 +1183,29 @@ again:
 
         if (!atomic_read(&era->ref) || era->config == reg->config) {
 
+                /*
+                 * If its a fake cpuc -- as per validate_{group,event}() we
+                 * shouldn't touch event state and we can avoid doing so
+                 * since both will only call get_event_constraints() once
+                 * on each event, this avoids the need for reg->alloc.
+                 *
+                 * Not doing the ER fixup will only result in era->reg being
+                 * wrong, but since we won't actually try and program hardware
+                 * this isn't a problem either.
+                 */
+                if (!cpuc->is_fake) {