% (c) The GRASP/AQUA Project, Glasgow University, 1992-1998
%
\section{Tidying up Core}
\begin{code}
module TidyPgm (
mkBootModDetailsTc, tidyProgram, globaliseAndTidyId
) where
#include "HsVersions.h"
import TcRnTypes
import DynFlags
import CoreSyn
import CoreUnfold
import CoreFVs
import CoreTidy
import CoreMonad
import CorePrep
import CoreUtils
import Literal
import Rules
import CoreArity ( exprArity, exprBotStrictness_maybe )
import VarEnv
import VarSet
import Var
import Id
import IdInfo
import InstEnv
import FamInstEnv
import Demand
import BasicTypes
import Name hiding (varName)
import NameSet
import NameEnv
import Avail
import PrelNames
import IfaceEnv
import TcEnv
import TcRnMonad
import TcType
import DataCon
import TyCon
import Class
import Module
import Packages( isDllName )
import HscTypes
import Maybes
import UniqSupply
import ErrUtils (Severity(..))
import Outputable
import FastBool hiding ( fastOr )
import SrcLoc
import Util
import FastString
import qualified ErrUtils as Err
import Control.Monad
import Data.Function
import Data.List ( sortBy )
import Data.IORef ( readIORef, writeIORef )
\end{code}
Constructing the TypeEnv, Instances, Rules, VectInfo from which the
ModIface is constructed, and which goes on to subsequent modules in
--make mode.
Most of the interface file is obtained simply by serialising the
TypeEnv. One important consequence is that if the *interface file*
has pragma info if and only if the final TypeEnv does. This is not so
important for *this* module, but it's essential for ghc --make:
subsequent compilations must not see (e.g.) the arity if the interface
file does not contain arity If they do, they'll exploit the arity;
then the arity might change, but the iface file doesn't change =>
recompilation does not happen => disaster.
For data types, the final TypeEnv will have a TyThing for the TyCon,
plus one for each DataCon; the interface file will contain just one
data type declaration, but it is de-serialised back into a collection
of TyThings.
%************************************************************************
%* *
Plan A: simpleTidyPgm
%* *
%************************************************************************
Plan A: mkBootModDetails: omit pragmas, make interfaces small
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
* Ignore the bindings
* Drop all WiredIn things from the TypeEnv
(we never want them in interface files)
* Retain all TyCons and Classes in the TypeEnv, to avoid
having to find which ones are mentioned in the
types of exported Ids
* Trim off the constructors of non-exported TyCons, both
from the TyCon and from the TypeEnv
* Drop non-exported Ids from the TypeEnv
* Tidy the types of the DFunIds of Instances,
make them into GlobalIds, (they already have External Names)
and add them to the TypeEnv
* Tidy the types of the (exported) Ids in the TypeEnv,
make them into GlobalIds (they already have External Names)
* Drop rules altogether
* Tidy the bindings, to ensure that the Caf and Arity
information is correct for each top-level binder; the
code generator needs it. And to ensure that local names have
distinct OccNames in case of object-file splitting
\begin{code}
mkBootModDetailsTc :: HscEnv -> TcGblEnv -> IO ModDetails
mkBootModDetailsTc hsc_env
TcGblEnv{ tcg_exports = exports,
tcg_type_env = type_env,
tcg_tcs = tcs,
tcg_insts = insts,
tcg_fam_insts = fam_insts
}
= do { let dflags = hsc_dflags hsc_env
; showPass dflags CoreTidy
; let { insts' = tidyInstances globaliseAndTidyId insts
; dfun_ids = map instanceDFunId insts'
; type_env1 = mkBootTypeEnv (availsToNameSet exports)
(typeEnvIds type_env) tcs fam_insts
; type_env' = extendTypeEnvWithIds type_env1 dfun_ids
}
; return (ModDetails { md_types = type_env'
, md_insts = insts'
, md_fam_insts = fam_insts
, md_rules = []
, md_anns = []
, md_exports = exports
, md_vect_info = noVectInfo
})
}
where
mkBootTypeEnv :: NameSet -> [Id] -> [TyCon] -> [FamInst] -> TypeEnv
mkBootTypeEnv exports ids tcs fam_insts
= tidyTypeEnv True False exports $
typeEnvFromEntities final_ids tcs fam_insts
where
final_ids = [ if isLocalId id then globaliseAndTidyId id
else id
| id <- ids
, keep_it id ]
keep_it id = isExportedId id || idName id `elemNameSet` exports
globaliseAndTidyId :: Id -> Id
globaliseAndTidyId id
= Id.setIdType (globaliseId id) tidy_type
where
tidy_type = tidyTopType (idType id)
\end{code}
%************************************************************************
%* *
Plan B: tidy bindings, make TypeEnv full of IdInfo
%* *
%************************************************************************
Plan B: include pragmas, make interfaces
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
* Figure out which Ids are externally visible
* Tidy the bindings, externalising appropriate Ids
* Drop all Ids from the TypeEnv, and add all the External Ids from
the bindings. (This adds their IdInfo to the TypeEnv; and adds
floated-out Ids that weren't even in the TypeEnv before.)
Step 1: Figure out external Ids
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Note [choosing external names]
See also the section "Interface stability" in the
RecompilationAvoidance commentary:
http://hackage.haskell.org/trac/ghc/wiki/Commentary/Compiler/RecompilationAvoidance
First we figure out which Ids are "external" Ids. An
"external" Id is one that is visible from outside the compilation
unit. These are
a) the user exported ones
b) ones mentioned in the unfoldings, workers,
rules of externally-visible ones ,
or vectorised versions of externally-visible ones
While figuring out which Ids are external, we pick a "tidy" OccName
for each one. That is, we make its OccName distinct from the other
external OccNames in this module, so that in interface files and
object code we can refer to it unambiguously by its OccName. The
OccName for each binder is prefixed by the name of the exported Id
that references it; e.g. if "f" references "x" in its unfolding, then
"x" is renamed to "f_x". This helps distinguish the different "x"s
from each other, and means that if "f" is later removed, things that
depend on the other "x"s will not need to be recompiled. Of course,
if there are multiple "f_x"s, then we have to disambiguate somehow; we
use "f_x0", "f_x1" etc.
As far as possible we should assign names in a deterministic fashion.
Each time this module is compiled with the same options, we should end
up with the same set of external names with the same types. That is,
the ABI hash in the interface should not change. This turns out to be
quite tricky, since the order of the bindings going into the tidy
phase is already non-deterministic, as it is based on the ordering of
Uniques, which are assigned unpredictably.
To name things in a stable way, we do a depth-first-search of the
bindings, starting from the exports sorted by name. This way, as long
as the bindings themselves are deterministic (they sometimes aren't!),
the order in which they are presented to the tidying phase does not
affect the names we assign.
Step 2: Tidy the program
~~~~~~~~~~~~~~~~~~~~~~~~
Next we traverse the bindings top to bottom. For each *top-level*
binder
1. Make it into a GlobalId; its IdDetails becomes VanillaGlobal,
reflecting the fact that from now on we regard it as a global,
not local, Id
2. Give it a system-wide Unique.
[Even non-exported things need system-wide Uniques because the
byte-code generator builds a single Name->BCO symbol table.]
We use the NameCache kept in the HscEnv as the
source of such system-wide uniques.
For external Ids, use the original-name cache in the NameCache
to ensure that the unique assigned is the same as the Id had
in any previous compilation run.
3. Rename top-level Ids according to the names we chose in step 1.
If it's an external Id, make it have a External Name, otherwise
make it have an Internal Name. This is used by the code generator
to decide whether to make the label externally visible
4. Give it its UTTERLY FINAL IdInfo; in ptic,
* its unfolding, if it should have one
* its arity, computed from the number of visible lambdas
* its CAF info, computed from what is free in its RHS
Finally, substitute these new top-level binders consistently
throughout, including in unfoldings. We also tidy binders in
RHSs, so that they print nicely in interfaces.
\begin{code}
tidyProgram :: HscEnv -> ModGuts -> IO (CgGuts, ModDetails)
tidyProgram hsc_env (ModGuts { mg_module = mod
, mg_exports = exports
, mg_tcs = tcs
, mg_insts = insts
, mg_fam_insts = fam_insts
, mg_binds = binds
, mg_rules = imp_rules
, mg_vect_info = vect_info
, mg_anns = anns
, mg_deps = deps
, mg_foreign = foreign_stubs
, mg_hpc_info = hpc_info
, mg_modBreaks = modBreaks
})
= do { let { dflags = hsc_dflags hsc_env
; omit_prags = dopt Opt_OmitInterfacePragmas dflags
; expose_all = dopt Opt_ExposeAllUnfoldings dflags
; th = xopt Opt_TemplateHaskell dflags
; data_kinds = xopt Opt_DataKinds dflags
; no_trim_types = th || data_kinds
}
; showPass dflags CoreTidy
; let { type_env = typeEnvFromEntities [] tcs fam_insts
; implicit_binds
= concatMap getClassImplicitBinds (typeEnvClasses type_env) ++
concatMap getTyConImplicitBinds (typeEnvTyCons type_env)
}
; (unfold_env, tidy_occ_env)
<- chooseExternalIds hsc_env mod omit_prags expose_all
binds implicit_binds imp_rules (vectInfoVar vect_info)
; let { ext_rules = findExternalRules omit_prags binds imp_rules unfold_env }
; (tidy_env, tidy_binds)
<- tidyTopBinds hsc_env unfold_env tidy_occ_env binds
; let { export_set = availsToNameSet exports
; final_ids = [ id | id <- bindersOfBinds tidy_binds,
isExternalName (idName id)]
; tidy_type_env = tidyTypeEnv omit_prags no_trim_types export_set
(extendTypeEnvWithIds type_env final_ids)
; tidy_insts = tidyInstances (lookup_dfun tidy_type_env) insts
; tidy_rules = tidyRules tidy_env ext_rules
; tidy_vect_info = tidyVectInfo tidy_env vect_info
; all_tidy_binds = implicit_binds ++ tidy_binds
; alg_tycons = filter isAlgTyCon (typeEnvTyCons type_env)
}
; endPass dflags CoreTidy all_tidy_binds tidy_rules
; unless (dopt Opt_D_dump_simpl dflags) $
Err.dumpIfSet_dyn dflags Opt_D_dump_rules
(showSDoc dflags (ppr CoreTidy <+> ptext (sLit "rules")))
(pprRulesForUser tidy_rules)
; let cs = coreBindsStats tidy_binds
; when (dopt Opt_D_dump_core_stats dflags)
(log_action dflags dflags SevDump noSrcSpan defaultDumpStyle
(ptext (sLit "Tidy size (terms,types,coercions)")
<+> ppr (moduleName mod) <> colon
<+> int (cs_tm cs)
<+> int (cs_ty cs)
<+> int (cs_co cs) ))
; return (CgGuts { cg_module = mod,
cg_tycons = alg_tycons,
cg_binds = all_tidy_binds,
cg_foreign = foreign_stubs,
cg_dep_pkgs = map fst $ dep_pkgs deps,
cg_hpc_info = hpc_info,
cg_modBreaks = modBreaks },
ModDetails { md_types = tidy_type_env,
md_rules = tidy_rules,
md_insts = tidy_insts,
md_vect_info = tidy_vect_info,
md_fam_insts = fam_insts,
md_exports = exports,
md_anns = anns
})
}
lookup_dfun :: TypeEnv -> Var -> Id
lookup_dfun type_env dfun_id
= case lookupTypeEnv type_env (idName dfun_id) of
Just (AnId dfun_id') -> dfun_id'
_other -> pprPanic "lookup_dfun" (ppr dfun_id)
tidyTypeEnv :: Bool
-> Bool
-> NameSet -> TypeEnv -> TypeEnv
tidyTypeEnv omit_prags no_trim_types exports type_env
= let
type_env1 = filterNameEnv (not . isWiredInName . getName) type_env
type_env2 | omit_prags = mapNameEnv (trimThing no_trim_types exports) type_env1
| otherwise = type_env1
in
type_env2
trimThing :: Bool -> NameSet -> TyThing -> TyThing
trimThing no_trim_types exports (ATyCon tc)
| not (mustExposeTyCon no_trim_types exports tc)
= ATyCon (makeTyConAbstract tc)
trimThing _th _exports (AnId id)
| not (isImplicitId id)
= AnId (id `setIdInfo` vanillaIdInfo)
trimThing _th _exports other_thing
= other_thing
mustExposeTyCon :: Bool
-> NameSet
-> TyCon
-> Bool
mustExposeTyCon no_trim_types exports tc
| no_trim_types
= True
| not (isAlgTyCon tc)
= True
| isEnumerationTyCon tc
= True
| isFamilyTyCon tc
= True
| null data_cons
= True
| any exported_con data_cons
= True
| isNewTyCon tc && isFFITy (snd (newTyConRhs tc))
= True
| otherwise
= False
where
data_cons = tyConDataCons tc
exported_con con = any (`elemNameSet` exports)
(dataConName con : dataConFieldLabels con)
tidyInstances :: (DFunId -> DFunId) -> [ClsInst] -> [ClsInst]
tidyInstances tidy_dfun ispecs
= map tidy ispecs
where
tidy ispec = setInstanceDFunId ispec $
tidy_dfun (instanceDFunId ispec)
\end{code}
\begin{code}
tidyVectInfo :: TidyEnv -> VectInfo -> VectInfo
tidyVectInfo (_, var_env) info@(VectInfo { vectInfoVar = vars
, vectInfoScalarVars = scalarVars
})
= info { vectInfoVar = tidy_vars
, vectInfoScalarVars = tidy_scalarVars
}
where
tidy_vars = mkVarEnv [ (tidy_var, (tidy_var, tidy_var_v))
| (var, var_v) <- varEnvElts vars
, let tidy_var = lookup_var var
tidy_var_v = lookup_var var_v
, isExportedId tidy_var
, isExportedId tidy_var_v
, isDataConWorkId var || not (isImplicitId var)
]
tidy_scalarVars = mkVarSet [ lookup_var var
| var <- varSetElems scalarVars
, isGlobalId var || isExportedId var]
lookup_var var = lookupWithDefaultVarEnv var_env var var
\end{code}
%************************************************************************
%* *
Implicit bindings
%* *
%************************************************************************
Note [Injecting implicit bindings]
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
We inject the implict bindings right at the end, in CoreTidy.
Some of these bindings, notably record selectors, are not
constructed in an optimised form. E.g. record selector for
data T = MkT { x :: {-# UNPACK #-} !Int }
Then the unfolding looks like
x = \t. case t of MkT x1 -> let x = I# x1 in x
This generates bad code unless it's first simplified a bit. That is
why CoreUnfold.mkImplicitUnfolding uses simleExprOpt to do a bit of
optimisation first. (Only matters when the selector is used curried;
eg map x ys.) See Trac #2070.
[Oct 09: in fact, record selectors are no longer implicit Ids at all,
because we really do want to optimise them properly. They are treated
much like any other Id. But doing "light" optimisation on an implicit
Id still makes sense.]
At one time I tried injecting the implicit bindings *early*, at the
beginning of SimplCore. But that gave rise to real difficulty,
becuase GlobalIds are supposed to have *fixed* IdInfo, but the
simplifier and other core-to-core passes mess with IdInfo all the
time. The straw that broke the camels back was when a class selector
got the wrong arity -- ie the simplifier gave it arity 2, whereas
importing modules were expecting it to have arity 1 (Trac #2844).
It's much safer just to inject them right at the end, after tidying.
Oh: two other reasons for injecting them late:
- If implicit Ids are already in the bindings when we start TidyPgm,
we'd have to be careful not to treat them as external Ids (in
the sense of findExternalIds); else the Ids mentioned in *their*
RHSs will be treated as external and you get an interface file
saying a18 =
but nothing refererring to a18 (because the implicit Id is the
one that does, and implicit Ids don't appear in interface files).
- More seriously, the tidied type-envt will include the implicit
Id replete with a18 in its unfolding; but we won't take account
of a18 when computing a fingerprint for the class; result chaos.
There is one sort of implicit binding that is injected still later,
namely those for data constructor workers. Reason (I think): it's
really just a code generation trick.... binding itself makes no sense.
See CorePrep Note [Data constructor workers].
\begin{code}
getTyConImplicitBinds :: TyCon -> [CoreBind]
getTyConImplicitBinds tc = map get_defn (mapCatMaybes dataConWrapId_maybe (tyConDataCons tc))
getClassImplicitBinds :: Class -> [CoreBind]
getClassImplicitBinds cls = map get_defn (classAllSelIds cls)
get_defn :: Id -> CoreBind
get_defn id = NonRec id (unfoldingTemplate (realIdUnfolding id))
\end{code}
%************************************************************************
%* *
\subsection{Step 1: finding externals}
%* *
%************************************************************************
See Note [Choosing external names].
\begin{code}
type UnfoldEnv = IdEnv (Name, Bool )
chooseExternalIds :: HscEnv
-> Module
-> Bool -> Bool
-> [CoreBind]
-> [CoreBind]
-> [CoreRule]
-> VarEnv (Var, Var)
-> IO (UnfoldEnv, TidyOccEnv)
chooseExternalIds hsc_env mod omit_prags expose_all binds implicit_binds imp_id_rules vect_vars
= do { (unfold_env1,occ_env1) <- search init_work_list emptyVarEnv init_occ_env
; let internal_ids = filter (not . (`elemVarEnv` unfold_env1)) binders
; tidy_internal internal_ids unfold_env1 occ_env1 }
where
nc_var = hsc_NC hsc_env
init_work_list = zip init_ext_ids init_ext_ids
init_ext_ids = sortBy (compare `on` getOccName) $
filter is_external binders
is_external id = isExportedId id || id `elemVarSet` rule_rhs_vars || id `elemVarSet` vect_var_vs
rule_rhs_vars = foldr (unionVarSet . ruleRhsFreeVars) emptyVarSet imp_id_rules
vect_var_vs = mkVarSet [var_v | (var, var_v) <- nameEnvElts vect_vars, isGlobalId var]
binders = bindersOfBinds binds
implicit_binders = bindersOfBinds implicit_binds
binder_set = mkVarSet binders
avoids = [getOccName name | bndr <- binders ++ implicit_binders,
let name = idName bndr,
isExternalName name ]
init_occ_env = initTidyOccEnv avoids
search :: [(Id,Id)]
-> UnfoldEnv
-> TidyOccEnv
-> IO (UnfoldEnv, TidyOccEnv)
search [] unfold_env occ_env = return (unfold_env, occ_env)
search ((idocc,referrer) : rest) unfold_env occ_env
| idocc `elemVarEnv` unfold_env = search rest unfold_env occ_env
| otherwise = do
(occ_env', name') <- tidyTopName mod nc_var (Just referrer) occ_env idocc
let
(new_ids, show_unfold)
| omit_prags = ([], False)
| otherwise = addExternal expose_all refined_id
refined_id = case lookupVarSet binder_set idocc of
Just id -> id
Nothing -> WARN( True, ppr idocc ) idocc
unfold_env' = extendVarEnv unfold_env idocc (name',show_unfold)
referrer' | isExportedId refined_id = refined_id
| otherwise = referrer
search (zip new_ids (repeat referrer') ++ rest) unfold_env' occ_env'
tidy_internal :: [Id] -> UnfoldEnv -> TidyOccEnv
-> IO (UnfoldEnv, TidyOccEnv)
tidy_internal [] unfold_env occ_env = return (unfold_env,occ_env)
tidy_internal (id:ids) unfold_env occ_env = do
(occ_env', name') <- tidyTopName mod nc_var Nothing occ_env id
let unfold_env' = extendVarEnv unfold_env id (name',False)
tidy_internal ids unfold_env' occ_env'
addExternal :: Bool -> Id -> ([Id], Bool)
addExternal expose_all id = (new_needed_ids, show_unfold)
where
new_needed_ids = bndrFvsInOrder show_unfold id
idinfo = idInfo id
show_unfold = show_unfolding (unfoldingInfo idinfo)
never_active = isNeverActive (inlinePragmaActivation (inlinePragInfo idinfo))
loop_breaker = isStrongLoopBreaker (occInfo idinfo)
bottoming_fn = isBottomingSig (strictnessInfo idinfo `orElse` topSig)
show_unfolding (CoreUnfolding { uf_src = src, uf_guidance = guidance })
= expose_all
|| isStableSource src
|| not (bottoming_fn
|| never_active
|| loop_breaker
|| neverUnfoldGuidance guidance)
show_unfolding (DFunUnfolding {}) = True
show_unfolding _ = False
\end{code}
%************************************************************************
%* *
Deterministic free variables
%* *
%************************************************************************
We want a deterministic free-variable list. exprFreeVars gives us
a VarSet, which is in a non-deterministic order when converted to a
list. Hence, here we define a free-variable finder that returns
the free variables in the order that they are encountered.
See Note [Choosing external names]
\begin{code}
bndrFvsInOrder :: Bool -> Id -> [Id]
bndrFvsInOrder show_unfold id
= run (dffvLetBndr show_unfold id)
run :: DFFV () -> [Id]
run (DFFV m) = case m emptyVarSet (emptyVarSet, []) of
((_,ids),_) -> ids
newtype DFFV a
= DFFV (VarSet
-> (VarSet, [Var])
-> ((VarSet,[Var]),a))
instance Monad DFFV where
return a = DFFV $ \_ st -> (st, a)
(DFFV m) >>= k = DFFV $ \env st ->
case m env st of
(st',a) -> case k a of
DFFV f -> f env st'
extendScope :: Var -> DFFV a -> DFFV a
extendScope v (DFFV f) = DFFV (\env st -> f (extendVarSet env v) st)
extendScopeList :: [Var] -> DFFV a -> DFFV a
extendScopeList vs (DFFV f) = DFFV (\env st -> f (extendVarSetList env vs) st)
insert :: Var -> DFFV ()
insert v = DFFV $ \ env (set, ids) ->
let keep_me = isLocalId v &&
not (v `elemVarSet` env) &&
not (v `elemVarSet` set)
in if keep_me
then ((extendVarSet set v, v:ids), ())
else ((set, ids), ())
dffvExpr :: CoreExpr -> DFFV ()
dffvExpr (Var v) = insert v
dffvExpr (App e1 e2) = dffvExpr e1 >> dffvExpr e2
dffvExpr (Lam v e) = extendScope v (dffvExpr e)
dffvExpr (Tick (Breakpoint _ ids) e) = mapM_ insert ids >> dffvExpr e
dffvExpr (Tick _other e) = dffvExpr e
dffvExpr (Cast e _) = dffvExpr e
dffvExpr (Let (NonRec x r) e) = dffvBind (x,r) >> extendScope x (dffvExpr e)
dffvExpr (Let (Rec prs) e) = extendScopeList (map fst prs) $
(mapM_ dffvBind prs >> dffvExpr e)
dffvExpr (Case e b _ as) = dffvExpr e >> extendScope b (mapM_ dffvAlt as)
dffvExpr _other = return ()
dffvAlt :: (t, [Var], CoreExpr) -> DFFV ()
dffvAlt (_,xs,r) = extendScopeList xs (dffvExpr r)
dffvBind :: (Id, CoreExpr) -> DFFV ()
dffvBind(x,r)
| not (isId x) = dffvExpr r
| otherwise = dffvLetBndr False x >> dffvExpr r
dffvLetBndr :: Bool -> Id -> DFFV ()
dffvLetBndr vanilla_unfold id
= do { go_unf (unfoldingInfo idinfo)
; mapM_ go_rule (specInfoRules (specInfo idinfo)) }
where
idinfo = idInfo id
go_unf (CoreUnfolding { uf_tmpl = rhs, uf_src = src })
= case src of
InlineRhs | vanilla_unfold -> dffvExpr rhs
| otherwise -> return ()
InlineWrapper v -> insert v
_ -> dffvExpr rhs
go_unf (DFunUnfolding _ _ args) = mapM_ dffvExpr (dfunArgExprs args)
go_unf _ = return ()
go_rule (BuiltinRule {}) = return ()
go_rule (Rule { ru_bndrs = bndrs, ru_rhs = rhs })
= extendScopeList bndrs (dffvExpr rhs)
\end{code}
%************************************************************************
%* *
tidyTopName
%* *
%************************************************************************
This is where we set names to local/global based on whether they really are
externally visible (see comment at the top of this module). If the name
was previously local, we have to give it a unique occurrence name if
we intend to externalise it.
\begin{code}
tidyTopName :: Module -> IORef NameCache -> Maybe Id -> TidyOccEnv
-> Id -> IO (TidyOccEnv, Name)
tidyTopName mod nc_var maybe_ref occ_env id
| global && internal = return (occ_env, localiseName name)
| global && external = return (occ_env, name)
| local && internal = do { nc <- readIORef nc_var
; let (nc', new_local_name) = mk_new_local nc
; writeIORef nc_var nc'
; return (occ_env', new_local_name) }
| local && external = do { nc <- readIORef nc_var
; let (nc', new_external_name) = mk_new_external nc
; writeIORef nc_var nc'
; return (occ_env', new_external_name) }
| otherwise = panic "tidyTopName"
where
name = idName id
external = isJust maybe_ref
global = isExternalName name
local = not global
internal = not external
loc = nameSrcSpan name
old_occ = nameOccName name
new_occ
| Just ref <- maybe_ref, ref /= id =
mkOccName (occNameSpace old_occ) $
let
ref_str = occNameString (getOccName ref)
occ_str = occNameString old_occ
in
case occ_str of
'$':'w':_ -> occ_str
_other | isSystemName name -> ref_str
| otherwise -> ref_str ++ '_' : occ_str
| otherwise = old_occ
(occ_env', occ') = tidyOccName occ_env new_occ
mk_new_local nc = (nc { nsUniqs = us }, mkInternalName uniq occ' loc)
where
(uniq, us) = takeUniqFromSupply (nsUniqs nc)
mk_new_external nc = allocateGlobalBinder nc mod occ' loc
\end{code}
\begin{code}
findExternalRules :: Bool
-> [CoreBind]
-> [CoreRule]
-> UnfoldEnv
-> [CoreRule]
findExternalRules omit_prags binds imp_id_rules unfold_env
| omit_prags = []
| otherwise = filterOut internal_rule (imp_id_rules ++ local_rules)
where
local_rules = [ rule
| id <- bindersOfBinds binds,
external_id id,
rule <- idCoreRules id
]
internal_rule rule
= any (not . external_id) (varSetElems (ruleLhsFreeIds rule))
external_id id
| Just (name,_) <- lookupVarEnv unfold_env id = isExternalName name
| otherwise = False
\end{code}
Note [Which rules to expose]
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
findExternalRules filters imp_rules to avoid binders that
aren't externally visible; but the externally-visible binders
are computed (by findExternalIds) assuming that all orphan
rules are externalised (see init_ext_ids in function
'search'). So in fact we may export more than we need.
(It's a sort of mutual recursion.)
%************************************************************************
%* *
\subsection{Step 2: top-level tidying}
%* *
%************************************************************************
\begin{code}
tidyTopBinds :: HscEnv
-> UnfoldEnv
-> TidyOccEnv
-> CoreProgram
-> IO (TidyEnv, CoreProgram)
tidyTopBinds hsc_env unfold_env init_occ_env binds
= do mkIntegerId <- liftM tyThingId
$ initTcForLookup hsc_env (tcLookupGlobal mkIntegerName)
return $ tidy mkIntegerId init_env binds
where
init_env = (init_occ_env, emptyVarEnv)
this_pkg = thisPackage (hsc_dflags hsc_env)
tidy _ env [] = (env, [])
tidy mkIntegerId env (b:bs) = let (env1, b') = tidyTopBind this_pkg mkIntegerId unfold_env env b
(env2, bs') = tidy mkIntegerId env1 bs
in
(env2, b':bs')
tidyTopBind :: PackageId
-> Id
-> UnfoldEnv
-> TidyEnv
-> CoreBind
-> (TidyEnv, CoreBind)
tidyTopBind this_pkg mkIntegerId unfold_env (occ_env,subst1) (NonRec bndr rhs)
= (tidy_env2, NonRec bndr' rhs')
where
Just (name',show_unfold) = lookupVarEnv unfold_env bndr
caf_info = hasCafRefs this_pkg (mkIntegerId, subst1) (idArity bndr) rhs
(bndr', rhs') = tidyTopPair show_unfold tidy_env2 caf_info name' (bndr, rhs)
subst2 = extendVarEnv subst1 bndr bndr'
tidy_env2 = (occ_env, subst2)
tidyTopBind this_pkg mkIntegerId unfold_env (occ_env,subst1) (Rec prs)
= (tidy_env2, Rec prs')
where
prs' = [ tidyTopPair show_unfold tidy_env2 caf_info name' (id,rhs)
| (id,rhs) <- prs,
let (name',show_unfold) =
expectJust "tidyTopBind" $ lookupVarEnv unfold_env id
]
subst2 = extendVarEnvList subst1 (bndrs `zip` map fst prs')
tidy_env2 = (occ_env, subst2)
bndrs = map fst prs
caf_info
| or [ mayHaveCafRefs (hasCafRefs this_pkg (mkIntegerId, subst1) (idArity bndr) rhs)
| (bndr,rhs) <- prs ] = MayHaveCafRefs
| otherwise = NoCafRefs
tidyTopPair :: Bool
-> TidyEnv
-> CafInfo
-> Name
-> (Id, CoreExpr)
-> (Id, CoreExpr)
tidyTopPair show_unfold rhs_tidy_env caf_info name' (bndr, rhs)
= (bndr1, rhs1)
where
bndr1 = mkGlobalId details name' ty' idinfo'
details = idDetails bndr
ty' = tidyTopType (idType bndr)
rhs1 = tidyExpr rhs_tidy_env rhs
idinfo' = tidyTopIdInfo rhs_tidy_env name' rhs rhs1 (idInfo bndr)
show_unfold caf_info
tidyTopIdInfo :: TidyEnv -> Name -> CoreExpr -> CoreExpr
-> IdInfo -> Bool -> CafInfo -> IdInfo
tidyTopIdInfo rhs_tidy_env name orig_rhs tidy_rhs idinfo show_unfold caf_info
| not is_external
= vanillaIdInfo
`setCafInfo` caf_info
`setArityInfo` arity
`setStrictnessInfo` final_sig
| otherwise
= vanillaIdInfo
`setCafInfo` caf_info
`setArityInfo` arity
`setStrictnessInfo` final_sig
`setOccInfo` robust_occ_info
`setInlinePragInfo` (inlinePragInfo idinfo)
`setUnfoldingInfo` unfold_info
where
is_external = isExternalName name
robust_occ_info = zapFragileOcc (occInfo idinfo)
final_sig | Just sig <- strictnessInfo idinfo
= WARN( _bottom_hidden sig, ppr name ) Just sig
| Just (_, sig) <- mb_bot_str = Just sig
| otherwise = Nothing
_bottom_hidden id_sig = case mb_bot_str of
Nothing -> False
Just (arity, _) -> not (appIsBottom id_sig arity)
mb_bot_str = exprBotStrictness_maybe orig_rhs
unf_info = unfoldingInfo idinfo
unfold_info | show_unfold = tidyUnfolding rhs_tidy_env unf_info unf_from_rhs
| otherwise = noUnfolding
unf_from_rhs = mkTopUnfolding is_bot tidy_rhs
is_bot = case final_sig of
Just sig -> isBottomingSig sig
Nothing -> False
arity = exprArity orig_rhs
\end{code}
%************************************************************************
%* *
\subsection{Figuring out CafInfo for an expression}
%* *
%************************************************************************
hasCafRefs decides whether a top-level closure can point into the dynamic heap.
We mark such things as `MayHaveCafRefs' because this information is
used to decide whether a particular closure needs to be referenced
in an SRT or not.
There are two reasons for setting MayHaveCafRefs:
a) The RHS is a CAF: a top-level updatable thunk.
b) The RHS refers to something that MayHaveCafRefs
Possible improvement: In an effort to keep the number of CAFs (and
hence the size of the SRTs) down, we could also look at the expression and
decide whether it requires a small bounded amount of heap, so we can ignore
it as a CAF. In these cases however, we would need to use an additional
CAF list to keep track of non-collectable CAFs.
\begin{code}
hasCafRefs :: PackageId -> (Id, VarEnv Var) -> Arity -> CoreExpr -> CafInfo
hasCafRefs this_pkg p arity expr
| is_caf || mentions_cafs = MayHaveCafRefs
| otherwise = NoCafRefs
where
mentions_cafs = isFastTrue (cafRefsE p expr)
is_dynamic_name = isDllName this_pkg
is_caf = not (arity > 0 || rhsIsStatic is_dynamic_name expr)
cafRefsE :: (Id, VarEnv Id) -> Expr a -> FastBool
cafRefsE p (Var id) = cafRefsV p id
cafRefsE p (Lit lit) = cafRefsL p lit
cafRefsE p (App f a) = fastOr (cafRefsE p f) (cafRefsE p) a
cafRefsE p (Lam _ e) = cafRefsE p e
cafRefsE p (Let b e) = fastOr (cafRefsEs p (rhssOfBind b)) (cafRefsE p) e
cafRefsE p (Case e _bndr _ alts) = fastOr (cafRefsE p e) (cafRefsEs p) (rhssOfAlts alts)
cafRefsE p (Tick _n e) = cafRefsE p e
cafRefsE p (Cast e _co) = cafRefsE p e
cafRefsE _ (Type _) = fastBool False
cafRefsE _ (Coercion _) = fastBool False
cafRefsEs :: (Id, VarEnv Id) -> [Expr a] -> FastBool
cafRefsEs _ [] = fastBool False
cafRefsEs p (e:es) = fastOr (cafRefsE p e) (cafRefsEs p) es
cafRefsL :: (Id, VarEnv Id) -> Literal -> FastBool
cafRefsL p@(mk_integer, _) (LitInteger i _) = cafRefsE p (cvtLitInteger mk_integer i)
cafRefsL _ _ = fastBool False
cafRefsV :: (Id, VarEnv Id) -> Id -> FastBool
cafRefsV (_, p) id
| not (isLocalId id) = fastBool (mayHaveCafRefs (idCafInfo id))
| Just id' <- lookupVarEnv p id = fastBool (mayHaveCafRefs (idCafInfo id'))
| otherwise = fastBool False
fastOr :: FastBool -> (a -> FastBool) -> a -> FastBool
fastOr a f x = fastBool (isFastTrue a || isFastTrue (f x))
\end{code}