Make profiling work with multiple capabilities (+RTS -N)

This means that both time and heap profiling work for parallel
programs.  Main internal changes:

  - CCCS is no longer a global variable; it is now another
    pseudo-register in the StgRegTable struct.  Thus every
    Capability has its own CCCS.

  - There is a new built-in CCS called "IDLE", which records ticks for
    Capabilities in the idle state.  If you profile a single-threaded
    program with +RTS -N2, you'll see about 50% of time in "IDLE".

  - There is appropriate locking in rts/Profiling.c to protect the
    shared cost-centre-stack data structures.

This patch does enough to get it working, I have cut one big corner:
the cost-centre-stack data structure is still shared amongst all
Capabilities, which means that multiple Capabilities will race when
updating the "allocations" and "entries" fields of a CCS.  Not only
does this give unpredictable results, but it runs very slowly due to
cache line bouncing.

It is strongly recommended that you use -fno-prof-count-entries to
disable the "entries" count when profiling parallel programs. (I shall
add a note to this effect to the docs).

6 files changed, 16 insertions, 5 deletions

diff --git a/includes/Cmm.h b/includes/Cmm.h
index 641faa216e..11c02b4e3e 100644
--- a/includes/Cmm.h
+++ b/includes/Cmm.h
@@ -372,7 +372,7 @@
    CCCS_ALLOC(bytes);
 
 /* CCS_ALLOC wants the size in words, because ccs->mem_alloc is in words */
-#define CCCS_ALLOC(__alloc) CCS_ALLOC(BYTES_TO_WDS(__alloc), W_[CCCS])
+#define CCCS_ALLOC(__alloc) CCS_ALLOC(BYTES_TO_WDS(__alloc), CCCS)
 
 #define HP_CHK_GEN_TICKY(alloc,liveness,reentry)	\
    HP_CHK_GEN(alloc,liveness,reentry);			\
diff --git a/includes/RtsAPI.h b/includes/RtsAPI.h
index 329b1569ab..8d948f9b49 100644
--- a/includes/RtsAPI.h
+++ b/includes/RtsAPI.h
@@ -37,6 +37,15 @@ typedef struct StgClosure_ *HaskellObj;
  */
 typedef struct Capability_ Capability;
 
+/*
+ * The public view of a Capability: we can be sure it starts with
+ * these two components (but it may have more private fields).
+ */
+typedef struct CapabilityPublic_ {
+    StgFunTable f;
+    StgRegTable r;
+} CapabilityPublic;
+
 /* ----------------------------------------------------------------------------
    RTS configuration settings, for passing to hs_init_ghc()
    ------------------------------------------------------------------------- */
diff --git a/includes/mkDerivedConstants.c b/includes/mkDerivedConstants.c
index b02b6c86f0..a2c9160e95 100644
--- a/includes/mkDerivedConstants.c
+++ b/includes/mkDerivedConstants.c
@@ -222,6 +222,7 @@ main(int argc, char *argv[])
     field_offset(StgRegTable, rSpLim);
     field_offset(StgRegTable, rHp);
     field_offset(StgRegTable, rHpLim);
+    field_offset(StgRegTable, rCCCS);
     field_offset(StgRegTable, rCurrentTSO);
     field_offset(StgRegTable, rCurrentNursery);
     field_offset(StgRegTable, rHpAlloc);
diff --git a/includes/rts/prof/CCS.h b/includes/rts/prof/CCS.h
index 4692d166b5..9737fc9c18 100644
--- a/includes/rts/prof/CCS.h
+++ b/includes/rts/prof/CCS.h
@@ -114,8 +114,6 @@ typedef struct _IndexTable {
    Pre-defined cost centres and cost centre stacks
    -------------------------------------------------------------------------- */
 
-extern CostCentreStack * RTS_VAR(CCCS);	        /* current CCS */
- 
 #if IN_STG_CODE
 
 extern StgWord CC_MAIN[];	
@@ -153,6 +151,9 @@ extern CostCentreStack CCS_DONT_CARE[];  // shouldn't ever get set
 extern CostCentre      CC_PINNED[];
 extern CostCentreStack CCS_PINNED[];     // pinned memory
 
+extern CostCentre      CC_IDLE[];
+extern CostCentreStack CCS_IDLE[];       // capability is idle
+
 #endif /* IN_STG_CODE */
 
 extern unsigned int RTS_VAR(CC_ID);     // global ids
@@ -165,7 +166,7 @@ extern unsigned int RTS_VAR(era);
  * ---------------------------------------------------------------------------*/
 
 CostCentreStack * pushCostCentre (CostCentreStack *, CostCentre *);
-void              enterFunCCS    (CostCentreStack *);
+void              enterFunCCS    (StgRegTable *reg, CostCentreStack *);
 
 /* -----------------------------------------------------------------------------
    Registering CCs and CCSs
diff --git a/includes/stg/MiscClosures.h b/includes/stg/MiscClosures.h
index 45dc8369c7..fcfdede2ff 100644
--- a/includes/stg/MiscClosures.h
+++ b/includes/stg/MiscClosures.h
@@ -488,7 +488,6 @@ extern StgWord RTS_VAR(stable_ptr_table);
 
 // Profiling.c
 extern unsigned int RTS_VAR(era);
-extern StgWord      RTS_VAR(CCCS);	        /* current CCS */
 extern unsigned int RTS_VAR(entering_PAP);
 extern StgWord      RTS_VAR(CC_LIST);               /* registered CC list */
 extern StgWord      RTS_VAR(CCS_LIST);         /* registered CCS list */
diff --git a/includes/stg/Regs.h b/includes/stg/Regs.h
index 1d0c00c491..b7f0abda7d 100644
--- a/includes/stg/Regs.h
+++ b/includes/stg/Regs.h
@@ -80,6 +80,7 @@ typedef struct StgRegTable_ {
   StgPtr 	  rSpLim;
   StgPtr 	  rHp;
   StgPtr 	  rHpLim;
+  struct _CostCentreStack * rCCCS;  // current cost-centre-stack
   struct StgTSO_ *     rCurrentTSO;
   struct nursery_ *    rNursery;
   struct bdescr_ *     rCurrentNursery; /* Hp/HpLim point into this block */