Merge branch 'perf/urgent' into perf/core, to pick up latest fixes and refresh the...

Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --combined arch/x86/events/intel/lbr.c
index 0edda489cf3663350b5f50d006fdacb2a38ce61a,955457a30197e8be224f0304ec83f14365b3fba9..8a6bbacd17dcfb077e2a910b5b532c1d24a4a623
--- 1/arch/x86/events/intel/lbr.c
--- 2/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@@ -109,9 -109,6 +109,9 @@@ enum 
        X86_BR_ZERO_CALL        = 1 << 15,/* zero length call */
        X86_BR_CALL_STACK       = 1 << 16,/* call stack */
        X86_BR_IND_JMP          = 1 << 17,/* indirect jump */
 +
 +      X86_BR_TYPE_SAVE        = 1 << 18,/* indicate to save branch type */
 +
  };
  
  #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
@@@ -383,8 -380,12 +383,12 @@@ static void __intel_pmu_lbr_save(struc
  
  void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
  {
+       struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
        struct x86_perf_task_context *task_ctx;
  
+       if (!cpuc->lbr_users)
+               return;
+ 
        /*
         * If LBR callstack feature is enabled and the stack was saved when
         * the task was scheduled out, restore the stack. Otherwise flush
@@@ -513,7 -514,6 +517,7 @@@ static void intel_pmu_lbr_read_32(struc
                cpuc->lbr_entries[i].in_tx      = 0;
                cpuc->lbr_entries[i].abort      = 0;
                cpuc->lbr_entries[i].cycles     = 0;
 +              cpuc->lbr_entries[i].type       = 0;
                cpuc->lbr_entries[i].reserved   = 0;
        }
        cpuc->lbr_stack.nr = i;
@@@ -600,7 -600,6 +604,7 @@@ static void intel_pmu_lbr_read_64(struc
                cpuc->lbr_entries[out].in_tx     = in_tx;
                cpuc->lbr_entries[out].abort     = abort;
                cpuc->lbr_entries[out].cycles    = cycles;
 +              cpuc->lbr_entries[out].type      = 0;
                cpuc->lbr_entries[out].reserved  = 0;
                out++;
        }
@@@ -678,10 -677,6 +682,10 @@@ static int intel_pmu_setup_sw_lbr_filte
  
        if (br_type & PERF_SAMPLE_BRANCH_CALL)
                mask |= X86_BR_CALL | X86_BR_ZERO_CALL;
 +
 +      if (br_type & PERF_SAMPLE_BRANCH_TYPE_SAVE)
 +              mask |= X86_BR_TYPE_SAVE;
 +
        /*
         * stash actual user request into reg, it may
         * be used by fixup code for some CPU
@@@ -935,43 -930,6 +939,43 @@@ static int branch_type(unsigned long fr
        return ret;
  }
  
 +#define X86_BR_TYPE_MAP_MAX   16
 +
 +static int branch_map[X86_BR_TYPE_MAP_MAX] = {
 +      PERF_BR_CALL,           /* X86_BR_CALL */
 +      PERF_BR_RET,            /* X86_BR_RET */
 +      PERF_BR_SYSCALL,        /* X86_BR_SYSCALL */
 +      PERF_BR_SYSRET,         /* X86_BR_SYSRET */
 +      PERF_BR_UNKNOWN,        /* X86_BR_INT */
 +      PERF_BR_UNKNOWN,        /* X86_BR_IRET */
 +      PERF_BR_COND,           /* X86_BR_JCC */
 +      PERF_BR_UNCOND,         /* X86_BR_JMP */
 +      PERF_BR_UNKNOWN,        /* X86_BR_IRQ */
 +      PERF_BR_IND_CALL,       /* X86_BR_IND_CALL */
 +      PERF_BR_UNKNOWN,        /* X86_BR_ABORT */
 +      PERF_BR_UNKNOWN,        /* X86_BR_IN_TX */
 +      PERF_BR_UNKNOWN,        /* X86_BR_NO_TX */
 +      PERF_BR_CALL,           /* X86_BR_ZERO_CALL */
 +      PERF_BR_UNKNOWN,        /* X86_BR_CALL_STACK */
 +      PERF_BR_IND,            /* X86_BR_IND_JMP */
 +};
 +
 +static int
 +common_branch_type(int type)
 +{
 +      int i;
 +
 +      type >>= 2; /* skip X86_BR_USER and X86_BR_KERNEL */
 +
 +      if (type) {
 +              i = __ffs(type);
 +              if (i < X86_BR_TYPE_MAP_MAX)
 +                      return branch_map[i];
 +      }
 +
 +      return PERF_BR_UNKNOWN;
 +}
 +
  /*
   * implement actual branch filter based on user demand.
   * Hardware may not exactly satisfy that request, thus
@@@ -988,8 -946,7 +992,8 @@@ intel_pmu_lbr_filter(struct cpu_hw_even
        bool compress = false;
  
        /* if sampling all branches, then nothing to filter */
 -      if ((br_sel & X86_BR_ALL) == X86_BR_ALL)
 +      if (((br_sel & X86_BR_ALL) == X86_BR_ALL) &&
 +          ((br_sel & X86_BR_TYPE_SAVE) != X86_BR_TYPE_SAVE))
                return;
  
        for (i = 0; i < cpuc->lbr_stack.nr; i++) {
@@@ -1010,9 -967,6 +1014,9 @@@
                        cpuc->lbr_entries[i].from = 0;
                        compress = true;
                }
 +
 +              if ((br_sel & X86_BR_TYPE_SAVE) == X86_BR_TYPE_SAVE)
 +                      cpuc->lbr_entries[i].type = common_branch_type(type);
        }
  
        if (!compress)