Rodrigo Mesquita pushed to branch wip/romes/27461 at Glasgow Haskell Compiler / GHC Commits: 2ca68dd2 by Rodrigo Mesquita at 2026-07-10T11:26:30+01:00 WIP - - - - - 37b51e9b by Rodrigo Mesquita at 2026-07-10T11:42:23+01:00 Revert "WIP" This reverts commit 2ca68dd2d60cf70726b396be53f42b4d52408c9c. - - - - - a9357c77 by Rodrigo Mesquita at 2026-07-10T11:48:58+01:00 Reapply "WIP" This reverts commit 37b51e9b188d35ce88051744170c0c1c1c0ef9a8. - - - - - 1 changed file: - compiler/GHC/Driver/Downsweep.hs Changes: ===================================== compiler/GHC/Driver/Downsweep.hs ===================================== @@ -5,6 +5,8 @@ {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE BlockArguments #-} {-# LANGUAGE ViewPatterns #-} +{-# LANGUAGE TypeFamilies #-} +{-# LANGUAGE FunctionalDependencies #-} module GHC.Driver.Downsweep ( downsweep , downsweepThunk @@ -109,6 +111,7 @@ import Control.Monad.Trans.Reader import qualified Data.Map.Strict as M import Control.Monad.Trans.Class import System.IO.Unsafe (unsafeInterleaveIO) +import Data.IORef {- Note [Downsweep and the ModuleGraph] @@ -143,6 +146,7 @@ The result is having a uniform graph available for the whole compilation pipelin -- This caches the answer to the question, if we are in this unit, what does -- an import of this module mean. type DownsweepCache = M.Map (UnitId, PkgQual, ModuleNameWithIsBoot) [Either DriverMessages ModuleNodeInfo] +-- TODO: kill this type alias and see what can be removed moduleGraphNodeMap :: ModuleGraph -> M.Map NodeKey ModuleGraphNode moduleGraphNodeMap graph @@ -193,8 +197,10 @@ downsweep :: HscEnv -- (Modules, IsBoot) identifiers, unless the Bool is true in -- which case there can be repeats downsweep hsc_env diag_wrapper msg old_summaries maybe_base_graph excl_mods allow_dup_roots = do - n_jobs <- mkWorkerLimit (hsc_dflags hsc_env) - (root_errs, root_summaries) <- rootSummariesParallel n_jobs hsc_env diag_wrapper msg summary + n_jobs <- mkWorkerLimit (hsc_dflags hsc_env) + summ_cache <- newIORef (mkModSummaryCache old_summaries) + (root_errs, root_summaries) <- rootSummariesParallel n_jobs hsc_env diag_wrapper msg + (getRootSummary excl_mods summ_cache) let closure_errs = checkHomeUnitsClosed unit_env unit_env = hsc_unit_env hsc_env @@ -202,7 +208,7 @@ downsweep hsc_env diag_wrapper msg old_summaries maybe_base_graph excl_mods allo case all_errs of [] -> do - (downsweep_errs, downsweep_nodes) <- downsweepFromRootNodes hsc_env old_summary_map maybe_base_graph excl_mods allow_dup_roots DownsweepUseCompile (map ModuleNodeCompile root_summaries) [] + (downsweep_errs, downsweep_nodes) <- downsweepFromRootNodes hsc_env old_summaries maybe_base_graph excl_mods allow_dup_roots DownsweepUseCompile (map ModuleNodeCompile root_summaries) [] let (other_errs, unit_nodes) = partitionEithers $ HUG.unitEnv_foldWithKey (\nodes uid hue -> nodes ++ unitModuleNodes downsweep_nodes uid hue) [] (hsc_HUG hsc_env) @@ -220,17 +226,6 @@ downsweep hsc_env diag_wrapper msg old_summaries maybe_base_graph excl_mods allo return (all_errs, th_configured_nodes) _ -> return (all_errs, emptyMG) where - summary = getRootSummary excl_mods old_summary_map - - -- A cache from file paths to the already summarised modules. The same file - -- can be used in multiple units so the map is also keyed by which unit the - -- file was used in. - -- Reuse these if we can because the most expensive part of downsweep is - -- reading the headers. - old_summary_map :: M.Map (UnitId, OsPath) ModSummary - old_summary_map = - M.fromList [((ms_unitid ms, msHsFileOsPath ms), ms) | ms <- old_summaries] - -- Dependencies arising on a unit (backpack and module linking deps) unitModuleNodes :: [ModuleGraphNode] -> UnitId -> HomeUnitEnv -> [Either (Messages DriverMessage) ModuleGraphNode] unitModuleNodes summaries uid hue = @@ -313,8 +308,9 @@ loopFromInteractive :: HscEnv -> [Either ModuleNodeEdge (UnitId, ImportLevel, PkgQual, GenWithIsBoot (Located ModuleName))] -> M.Map NodeKey ModuleGraphNode -> IO ([ModuleNodeEdge],M.Map NodeKey ModuleGraphNode) -loopFromInteractive _ [] cached_nodes = return ([], cached_nodes) -loopFromInteractive hsc_env (edge:edges) cached_nodes = +loopFromInteractive = error "TODO" +{- +loopFromInteractive = return ([], cached_nodes) case edge of Left edge -> do (edges, cached_nodes') <- loopFromInteractive hsc_env edges cached_nodes @@ -342,7 +338,7 @@ loopFromInteractive hsc_env (edge:edges) cached_nodes = return (edge : edges, cached_nodes') -- And if it's not found.. just carry on and hope. _ -> loopFromInteractive hsc_env edges cached_nodes - +-} -- | Create a module graph from a list of installed modules. -- This is used by the loader when we need to load modules but there @@ -395,7 +391,7 @@ data DownsweepMode = DownsweepUseCompile | DownsweepUseFixed -- This function will start at the given roots, and traverse downwards to find -- all the dependencies, all the way to the leaf units. downsweepFromRootNodes :: HscEnv - -> M.Map (UnitId, OsPath) ModSummary + -> [ModSummary] -> Maybe ModuleGraph -> [ModuleName] -> Bool @@ -407,17 +403,16 @@ downsweepFromRootNodes hsc_env old_summaries maybe_base_graph excl_mods allow_du = do let root_map = mkRootMap root_nodes checkDuplicates root_map - let env = DownsweepEnv hsc_env mode old_summaries excl_mods - (deps', map0) <- runDownsweepM env $ do - let base_nodes = maybe M.empty moduleGraphNodeMap maybe_base_graph - (module_deps, map0) <- loopModuleNodeInfos root_nodes (base_nodes, root_map) - let all_deps = loopUnit hsc_env module_deps root_uids - let all_instantiations = getHomeUnitInstantiations hsc_env - deps' <- loopInstantiations all_instantiations all_deps - return (deps', map0) - - - let downsweep_errs = lefts $ concat $ M.elems map0 + summ_cache <- newIORef (foldr insertRoot (mkModSummaryCache old_summaries) root_nodes) + let env = DownsweepEnv hsc_env mode summ_cache excl_mods + deps' <- runDownsweepM env $ do + let base_nodes = maybe M.empty moduleGraphNodeMap maybe_base_graph + module_deps <- loopModuleNodeInfos base_nodes root_nodes + all_deps <- loopUnits module_deps (hscActiveUnitId hsc_env) root_uids + deps' <- loopInstantiations all_deps (getHomeUnitInstantiations hsc_env) + return deps' + (m_cache, f_cache) <- readIORef summ_cache + let downsweep_errs = lefts (moduleEnvElts m_cache) ++ lefts (M.elems f_cache) downsweep_nodes = M.elems deps' return (downsweep_errs, downsweep_nodes) @@ -441,6 +436,8 @@ downsweepFromRootNodes hsc_env old_summaries maybe_base_graph excl_mods allow_du dup_roots :: [[ModuleNodeInfo]] -- Each at least of length 2 dup_roots = filterOut isSingleton $ map rights (M.elems root_map) + insertRoot (ModuleNodeCompile ms) = addModSummaryCache ms + insertRoot (ModuleNodeFixed _ _) = id calcDeps :: ModSummary -> [(ImportLevel, PkgQual, GenWithIsBoot (Located ModuleName))] calcDeps ms = @@ -455,104 +452,186 @@ type DownsweepM a = ReaderT DownsweepEnv IO a data DownsweepEnv = DownsweepEnv { downsweep_hsc_env :: HscEnv , _downsweep_mode :: DownsweepMode - , _downsweep_old_summaries :: M.Map (UnitId, OsPath) ModSummary + , _downsweep_summaries_cache :: ModSummaryCache , _downsweep_excl_mods :: [ModuleName] } -runDownsweepM :: DownsweepEnv -> DownsweepM a -> IO a -runDownsweepM env act = runReaderT act env +type ModSummaryCache = IORef ModSummaryCacheMap + +-- | A cache both from 'Module' or file paths to the already summarised +-- modules. The same file can be used in multiple units so the file-path map is +-- actually also keyed by which unit the file was used in. +-- +-- We want to reuse ModSummaries as far as possible because the most expensive +-- part of downsweep is reading the headers. +type ModSummaryCacheMap + = ( ModuleEnv (Either DriverMessages ModSummary) + , M.Map (UnitId, OsPath) (Either DriverMessages ModSummary) ) +mkModSummaryCache :: [ModSummary] -> ModSummaryCacheMap +mkModSummaryCache summs = foldr addModSummaryCache (emptyModuleEnv, M.empty) summs -loopInstantiations :: [(UnitId, InstantiatedUnit)] - -> M.Map NodeKey ModuleGraphNode - -> DownsweepM (M.Map NodeKey ModuleGraphNode) -loopInstantiations [] done = pure done -loopInstantiations ((home_uid, iud) :xs) done = do - hsc_env <- asks downsweep_hsc_env - let home_unit = ue_unitHomeUnit home_uid (hsc_unit_env hsc_env) - let hsc_env' = hscSetActiveHomeUnit home_unit hsc_env - done' = loopUnit hsc_env' done [instUnitInstanceOf iud] - payload = InstantiationNode home_uid iud - loopInstantiations xs (M.insert (mkNodeKey payload) payload done') - - --- This loops over all the mod summaries in the dependency graph, accumulates the actual dependencies for each module/unit -loopSummaries :: [ModSummary] - -> (M.Map NodeKey ModuleGraphNode, - DownsweepCache) - -> DownsweepM ((M.Map NodeKey ModuleGraphNode), DownsweepCache) -loopSummaries [] done = pure done -loopSummaries (ms:next) (done, summarised) - | Just {} <- M.lookup k done - = loopSummaries next (done, summarised) - -- Didn't work out what the imports mean yet, now do that. - | otherwise = do - (final_deps, done', summarised') <- loopImports (ms_unitid ms) (calcDeps ms) done summarised - -- This has the effect of finding a .hs file if we are looking at the .hs-boot file. - (_, done'', summarised'') <- loopImports (ms_unitid ms) (maybeToList hs_file_for_boot) done' summarised' - loopSummaries next (M.insert k (ModuleNode final_deps (ModuleNodeCompile ms)) done'', summarised'') +addModSummaryCache :: ModSummary -> ModSummaryCacheMap -> ModSummaryCacheMap +addModSummaryCache ms (me, fe) = (upd_me me, upd_fe fe) where - k = NodeKey_Module (msKey ms) + upd_me me = extendModuleEnv me (ms_mod ms) (Right ms) + upd_fe fe + | Just src_fn_os <- ml_hs_file_ospath (ms_location ms) + = M.insert (ms_unitid ms, src_fn_os) (Right ms) fe + | otherwise = fe - hs_file_for_boot - | HsBootFile <- ms_hsc_src ms - = Just (NormalLevel, NoPkgQual, (GWIB (noLoc $ ms_mod_name ms) NotBoot)) - | otherwise - = Nothing - -loopModuleNodeInfos :: [ModuleNodeInfo] -> (M.Map NodeKey ModuleGraphNode, DownsweepCache) -> DownsweepM (M.Map NodeKey ModuleGraphNode, DownsweepCache) -loopModuleNodeInfos is cache = foldM (flip loopModuleNodeInfo) cache is - -loopModuleNodeInfo :: ModuleNodeInfo -> (M.Map NodeKey ModuleGraphNode, DownsweepCache) -> DownsweepM (M.Map NodeKey ModuleGraphNode, DownsweepCache) -loopModuleNodeInfo mod_node_info (done, summarised) = do - case mod_node_info of - ModuleNodeCompile ms -> do - loopSummaries [ms] (done, summarised) - ModuleNodeFixed mod ml -> do - done' <- loopFixedModule mod ml done - return (done', summarised) - --- NB: loopFixedModule does not take a downsweep cache, because if you --- ever reach a Fixed node, everything under that also must be fixed. -loopFixedModule :: ModNodeKeyWithUid -> ModLocation - -> M.Map NodeKey ModuleGraphNode - -> DownsweepM (M.Map NodeKey ModuleGraphNode) -loopFixedModule key loc done = do - let nk = NodeKey_Module key - hsc_env <- asks downsweep_hsc_env - case M.lookup nk done of - Just {} -> return done - Nothing -> do - -- MP: TODO, we should just read the dependency info from the interface rather than either - -- a. Loading the whole thing into the EPS (this might never nececssary and causes lots of things to be permanently loaded into memory) - -- b. Loading the whole interface into a buffer before discarding it. (wasted allocation and deserialisation) - read_result <- liftIO $ - -- 1. Check if the interface is already loaded into the EPS by some other - -- part of the compiler. - lookupIfaceByModuleHsc hsc_env (mnkToModule key) >>= \case - Just iface -> return (M.Succeeded iface) - Nothing -> readIface (hsc_hooks hsc_env) (hsc_logger hsc_env) (hsc_dflags hsc_env) (hsc_NC hsc_env) (mnkToModule key) (ml_hi_file loc) +runDownsweepM :: DownsweepEnv -> DownsweepM a -> IO a +runDownsweepM env act = runReaderT act env + +loopDownsweepNodes :: M.Map NodeKey ModuleGraphNode -> [DownsweepNode] -> DownsweepM (M.Map NodeKey ModuleGraphNode) +loopModuleNodeInfos :: M.Map NodeKey ModuleGraphNode -> [ModuleNodeInfo] -> DownsweepM (M.Map NodeKey ModuleGraphNode) +loopUnits :: M.Map NodeKey ModuleGraphNode -> UnitId -> [UnitId] -> DownsweepM (M.Map NodeKey ModuleGraphNode) +loopInstantiations :: M.Map NodeKey ModuleGraphNode -> [(UnitId, InstantiatedUnit)] -> DownsweepM (M.Map NodeKey ModuleGraphNode) +loopDownsweepNodes base_map nodes = dfsBuild (Just base_map) nodes dsNodeInfoKey dsNodeExpand +loopModuleNodeInfos base_map = loopDownsweepNodes base_map . map DSMod +loopUnits base_map homud = loopDownsweepNodes base_map . map (DSUnit homud) +loopInstantiations base_map = loopDownsweepNodes base_map . map (uncurry DSInst) + +-------------------------------------------------------------------------------- + +-- | A 'DownsweepNode' is the basic block of the downsweep algorithm which +-- encompasses the types of nodes we can iteratively expand to construct the +-- full module graph. See 'loopDownsweepNodes'. +data DownsweepNode + = DSMod ModuleNodeInfo + -- ^ A module node to expand + | DSUnit + { home_context_uid :: UnitId + -- ^ The home unit which introduced the dependency on this 'node_uid'. This + -- 'node_uid' can only be expanded in the context ('HscEnv') where + -- 'home_context_uid' is the active home unit, to make sure the package flags + -- are the ones attributed to the home package that introduced this node. + , node_uid :: UnitId + -- ^ The unit node to expand + } + | DSInst + { home_context_uid :: UnitId + , instantiated_ud :: InstantiatedUnit + } + +-- | They key by which to cache previously visited 'DownsweepNode's +dsNodeInfoKey :: DownsweepNode -> NodeKey +dsNodeInfoKey = \case + DSMod (ModuleNodeCompile ms) -> NodeKey_Module (msKey ms) + DSMod (ModuleNodeFixed mod _) -> NodeKey_Module mod + DSUnit uid _ctx_uid -> NodeKey_ExternalUnit uid + DSInst{instantiated_ud} -> NodeKey_Unit instantiated_ud + +dsNodeExpand :: DownsweepNode -> DownsweepM (Maybe (ModuleGraphNode, [DownsweepNode])) +dsNodeExpand = \case + DSMod (ModuleNodeCompile ms) -> expandModuleSummary ms + DSMod (ModuleNodeFixed key loc) -> expandFixedModuleNode key loc + DSUnit{ node_uid, home_context_uid } -> expandUnitNode node_uid home_context_uid + DSInst{ instantiated_ud + , home_context_uid } -> expandInstantiatedUnit instantiated_ud home_context_uid + +expandModuleSummary :: ModSummary -> DownsweepM (Maybe (ModuleGraphNode, [DownsweepNode])) +expandModuleSummary ms = do -- Didn't work out what the imports mean yet, now do that. + hsc_env <- asks downsweep_hsc_env + let home_uid = ms_unitid ms + home_unit = ue_unitHomeUnit home_uid (hsc_unit_env hsc_env) + (final_deps, todo) <- fmap unzip $ forM (calcDeps ms) $ \(imp,mb_pkg,gwib) -> do + let GWIB { gwib_mod = L loc mod, gwib_isBoot = is_boot } = gwib + wanted_mod = L loc mod + mb_s <- downsweepSummarise home_unit is_boot wanted_mod mb_pkg Nothing + case mb_s of + NotThere -> return + ( Nothing, [] ) + External uid -> return + ( Just $ mkModuleEdge imp (NodeKey_ExternalUnit uid) + -- Specify home unit, as each unit might have a different visible package database. + , [DSUnit{node_uid = uid, home_context_uid = home_uid}] ) + FoundInstantiation iud -> return + ( Just (mkModuleEdge imp (NodeKey_Unit iud)), [] ) + FoundHomeWithError (_uid, _e) -> return + ( Nothing, [] ) + -- the error @e@ is already stored in the summarisation cache, + -- (the IORef in DownsweepM) and will get reported at the end. + FoundHome s -> return + -- MP: This assumes that we can only instantiate non home units, which is probably fair enough for now. + ( Just $ mkModuleEdge imp (NodeKey_Module (mnKey s)) + , [DSMod s] ) + -- TODO: if this FoundHome was already in the cache, we shouldn't + -- return any dependencies right? or will it all work out? + + -- This has the effect of finding a .hs file if we are looking at the .hs-boot file. + if | HsBootFile <- ms_hsc_src ms + -> void $ + downsweepSummarise home_unit NotBoot (noLoc $ ms_mod_name ms) NoPkgQual Nothing + | otherwise + -> pure () + + return $ Just + ( ModuleNode (catMaybes final_deps) (ModuleNodeCompile ms) + , concat todo ) + +-- | Expand a 'ModuleNodeFixed' node +-- NB: If you ever reach a Fixed node, everything under that also must be fixed. +expandFixedModuleNode :: ModNodeKeyWithUid -> ModLocation -> DownsweepM (Maybe (ModuleGraphNode, [DownsweepNode])) +expandFixedModuleNode key loc = do + hsc_env <- asks downsweep_hsc_env + -- MP: TODO, we should just read the dependency info from the interface rather than either + -- a. Loading the whole thing into the EPS (this might never nececssary and causes lots of things to be permanently loaded into memory) + -- b. Loading the whole interface into a buffer before discarding it. (wasted allocation and deserialisation) + read_result <- liftIO $ + -- 1. Check if the interface is already loaded into the EPS by some other + -- part of the compiler. + lookupIfaceByModuleHsc hsc_env (mnkToModule key) >>= \case + Just iface -> return (M.Succeeded iface) + Nothing -> readIface (hsc_hooks hsc_env) (hsc_logger hsc_env) (hsc_dflags hsc_env) (hsc_NC hsc_env) (mnkToModule key) (ml_hi_file loc) + case read_result of + M.Succeeded iface -> do + -- Computer information about this node + let node_deps = ifaceDeps (mi_deps iface) + edges = map mkFixedEdge node_deps + node = ModuleNode edges (ModuleNodeFixed key loc) + deps' <- catMaybes <$> mapM (mk_dep hsc_env) (bimap snd snd <$> node_deps) + pure $ Just (node, deps') + + -- Ignore any failure, we might try to read a .hi-boot file for + -- example, even if there is not one. + M.Failed {} -> + pure Nothing + where + mk_dep hsc_env (Left key) = do + -- Like expandImports, but we already know exactly which module we are looking for. + read_result <- liftIO $ findExactModule hsc_env (mnkToInstalledModule key) (mnkIsBoot key) case read_result of - M.Succeeded iface -> do - -- Computer information about this node - let node_deps = ifaceDeps (mi_deps iface) - edges = map mkFixedEdge node_deps - node = ModuleNode edges (ModuleNodeFixed key loc) - foldM (loopFixedNodeKey (mnkUnitId key)) (M.insert nk node done) (bimap snd snd <$> node_deps) - -- Ignore any failure, we might try to read a .hi-boot file for - -- example, even if there is not one. - M.Failed {} -> - return done - -loopFixedNodeKey :: UnitId -> M.Map NodeKey ModuleGraphNode -> Either ModNodeKeyWithUid UnitId -> DownsweepM (M.Map NodeKey ModuleGraphNode) -loopFixedNodeKey _ done (Left key) = do - loopFixedImports [key] done -loopFixedNodeKey home_uid done (Right uid) = do - -- Set active unit so that looking loopUnit finds the correct - -- -package flags in the unit state. - hsc_env <- asks downsweep_hsc_env - let hsc_env' = hscSetActiveUnitId home_uid hsc_env - return $ loopUnit hsc_env' done [uid] + InstalledFound loc -> do + pure $ Just $ DSMod (ModuleNodeFixed key loc) + _otherwise -> + -- If the finder fails, just keep going, there will be another + -- error later. + pure Nothing + mk_dep _ (Right uid_dep) = do + -- Set active unit so that looking loopUnit finds the correct + -- -package flags in the unit state. + let home_uid = mnkUnitId key + pure (Just DSUnit{node_uid=uid_dep, home_context_uid=home_uid}) + +-- | Expand a unit id under the context of a certain home unit +expandUnitNode :: UnitId {-^ @node_uid@ -} -> UnitId {-^ Home unit from where @node_uid@ was introduced -} + -> DownsweepM (Maybe (ModuleGraphNode, [DownsweepNode])) +expandUnitNode node_uid home_context_uid = do + -- Set active unit so that looking loopUnit finds the correct + -- -package flags in the unit state. + hsc_env <- asks downsweep_hsc_env + let lcl_hsc_env = hscSetActiveUnitId home_context_uid hsc_env + case unitDepends <$> lookupUnitId (hsc_units lcl_hsc_env) node_uid of + Just us -> pure $ Just ((UnitNode us node_uid), map (\u -> DSUnit{node_uid=u, home_context_uid{-inherit-}}) us) + Nothing -> pprPanic "loopUnit" (text "Malformed package database, missing " <+> ppr node_uid) + +expandInstantiatedUnit :: InstantiatedUnit -> UnitId {-^ Home unit -} -> DownsweepM (Maybe (ModuleGraphNode, [DownsweepNode])) +expandInstantiatedUnit iud home_uid = pure $ Just + ( InstantiationNode home_uid iud + , [DSUnit{node_uid=instUnitInstanceOf iud, home_context_uid=home_uid}] ) + +-------------------------------------------------------------------------------- mkFixedEdge :: Either (ImportLevel, ModNodeKeyWithUid) (ImportLevel, UnitId) -> ModuleNodeEdge mkFixedEdge (Left (lvl, key)) = mkModuleEdge lvl (NodeKey_Module key) @@ -567,27 +646,6 @@ ifaceDeps deps = | (lvl, uid) <- Set.toList (dep_direct_pkgs deps) ] --- Like loopImports, but we already know exactly which module we are looking for. -loopFixedImports :: [ModNodeKeyWithUid] - -> M.Map NodeKey ModuleGraphNode - -> DownsweepM (M.Map NodeKey ModuleGraphNode) -loopFixedImports [] done = pure done -loopFixedImports (key:keys) done = do - let nk = NodeKey_Module key - hsc_env <- asks downsweep_hsc_env - case M.lookup nk done of - Just {} -> loopFixedImports keys done - Nothing -> do - read_result <- liftIO $ findExactModule hsc_env (mnkToInstalledModule key) (mnkIsBoot key) - case read_result of - InstalledFound loc -> do - done' <- loopFixedModule key loc done - loopFixedImports keys done' - _otherwise -> - -- If the finder fails, just keep going, there will be another - -- error later. - loopFixedImports keys done - downsweepSummarise :: HomeUnit -> IsBootInterface -> Located ModuleName @@ -595,82 +653,11 @@ downsweepSummarise :: HomeUnit -> Maybe (StringBuffer, UTCTime) -> DownsweepM SummariseResult downsweepSummarise home_unit is_boot wanted_mod mb_pkg maybe_buf = do - DownsweepEnv hsc_env mode old_summaries excl_mods <- ask + DownsweepEnv hsc_env mode summaries_cache_ref excl_mods <- ask case mode of - DownsweepUseCompile -> liftIO $ summariseModule hsc_env home_unit old_summaries is_boot wanted_mod mb_pkg maybe_buf excl_mods + DownsweepUseCompile -> liftIO $ summariseModule hsc_env home_unit summaries_cache_ref is_boot wanted_mod mb_pkg maybe_buf excl_mods DownsweepUseFixed -> liftIO $ summariseModuleInterface hsc_env home_unit is_boot wanted_mod mb_pkg excl_mods - --- This loops over each import in each summary. It is mutually recursive with --- loopSummaries if we discover a new module by doing this. -loopImports - :: UnitId - -- ^ UnitId of home unit of summary whose imports are being processed - -> [(ImportLevel, PkgQual, GenWithIsBoot (Located ModuleName))] - -- ^ Work list: process these modules - -> M.Map NodeKey ModuleGraphNode - -> DownsweepCache - -- ^ Visited set; the range is a list because - -- the roots can have the same module names - -- if allow_dup_roots is True - -> DownsweepM ([ModuleNodeEdge], - M.Map NodeKey ModuleGraphNode, DownsweepCache) - -- ^ The result is the completed NodeMap -loopImports _ [] done summarised = return ([], done, summarised) -loopImports home_uid ((imp, mb_pkg, gwib) : ss) done summarised - | Just summs <- M.lookup cache_key summarised - = case summs of - [Right ms] -> do - let nk = mkModuleEdge imp (NodeKey_Module (mnKey ms)) - (rest, summarised', done') <- loopImportsNext done summarised - return (nk: rest, summarised', done') - [Left _err] -> - loopImportsNext done summarised - _errs -> do - loopImportsNext done summarised - | otherwise - = do - hsc_env <- asks downsweep_hsc_env - let home_unit = ue_unitHomeUnit home_uid (hsc_unit_env hsc_env) - mb_s <- downsweepSummarise home_unit - is_boot wanted_mod mb_pkg - Nothing - case mb_s of - NotThere -> loopImportsNext done summarised - External uid -> do - -- Pass an updated hsc_env to loopUnit, as each unit might - -- have a different visible package database. - let hsc_env' = hscSetActiveHomeUnit home_unit hsc_env - let done' = loopUnit hsc_env' done [uid] - (other_deps, done'', summarised') <- loopImportsNext done' summarised - return (mkModuleEdge imp (NodeKey_ExternalUnit uid) : other_deps, done'', summarised') - FoundInstantiation iud -> do - (other_deps, done', summarised') <- loopImportsNext done summarised - return (mkModuleEdge imp (NodeKey_Unit iud) : other_deps, done', summarised') - FoundHomeWithError (_uid, e) -> loopImportsNext done (Map.insert cache_key [(Left e)] summarised) - FoundHome s -> do - (done', summarised') <- - loopModuleNodeInfo s (done, Map.insert cache_key [Right s] summarised) - (other_deps, final_done, final_summarised) <- loopImportsNext done' summarised' - - -- MP: This assumes that we can only instantiate non home units, which is probably fair enough for now. - return (mkModuleEdge imp (NodeKey_Module (mnKey s)) : other_deps, final_done, final_summarised) - where - loopImportsNext = loopImports home_uid ss - cache_key = (home_uid, mb_pkg, unLoc <$> gwib) - GWIB { gwib_mod = L loc mod, gwib_isBoot = is_boot } = gwib - wanted_mod = L loc mod - -loopUnit :: HscEnv -> Map.Map NodeKey ModuleGraphNode -> [UnitId] -> Map.Map NodeKey ModuleGraphNode -loopUnit _ cache [] = cache -loopUnit lcl_hsc_env cache (u:uxs) = do - let nk = (NodeKey_ExternalUnit u) - case Map.lookup nk cache of - Just {} -> loopUnit lcl_hsc_env cache uxs - Nothing -> case unitDepends <$> lookupUnitId (hsc_units lcl_hsc_env) u of - Just us -> loopUnit lcl_hsc_env (loopUnit lcl_hsc_env (Map.insert nk (UnitNode us u) cache) us) uxs - Nothing -> pprPanic "loopUnit" (text "Malformed package database, missing " <+> ppr u) - multiRootsErr :: SourceErrorContext -> [ModuleNodeInfo] -> IO () multiRootsErr _ [] = panic "multiRootsErr" multiRootsErr sec summs@(summ1:_) @@ -732,24 +719,24 @@ linkNodes summaries uid hue = getRootSummary :: [ModuleName] -> - M.Map (UnitId, OsPath) ModSummary -> + ModSummaryCache -> HscEnv -> Target -> IO (Either DriverMessages ModSummary) -getRootSummary excl_mods old_summary_map hsc_env target +getRootSummary excl_mods summ_cache hsc_env target | TargetFile file mb_phase <- targetId = do let offset_file = augmentByWorkingDirectory dflags file exists <- liftIO $ doesFileExist offset_file if exists || isJust maybe_buf - then summariseFile hsc_env home_unit old_summary_map offset_file mb_phase + then summariseFile hsc_env home_unit summ_cache offset_file mb_phase maybe_buf else return $ Left $ singleMessage $ mkPlainErrorMsgEnvelope noSrcSpan (DriverFileNotFound offset_file) | TargetModule modl <- targetId = do - maybe_summary <- summariseModule hsc_env home_unit old_summary_map NotBoot + maybe_summary <- summariseModule hsc_env home_unit summ_cache NotBoot (L rootLoc modl) (ThisPkg (homeUnitId home_unit)) maybe_buf excl_mods pure case maybe_summary of @@ -1178,9 +1165,7 @@ Potential TODOS: -} -- | Populate the Downsweep cache with the root modules. -mkRootMap - :: [ModuleNodeInfo] - -> DownsweepCache +mkRootMap :: [ModuleNodeInfo] -> DownsweepCache mkRootMap summaries = Map.fromListWith (flip (++)) [ ((moduleNodeInfoUnitId s, NoPkgQual, moduleNodeInfoMnwib s), [Right s]) | s <- summaries ] @@ -1200,33 +1185,32 @@ mkRootMap summaries = Map.fromListWith (flip (++)) summariseFile :: HscEnv -> HomeUnit - -> M.Map (UnitId, OsPath) ModSummary -- old summaries + -> ModSummaryCache -> FilePath -- source file name -> Maybe Phase -- start phase -> Maybe (StringBuffer,UTCTime) -> IO (Either DriverMessages ModSummary) -summariseFile hsc_env' home_unit old_summaries src_fn mb_phase maybe_buf - -- we can use a cached summary if one is available and the - -- source file hasn't changed, - | Just old_summary <- M.lookup (homeUnitId home_unit, src_fn_os) old_summaries - = do - let location = ms_location $ old_summary - - src_hash <- get_src_hash - -- The file exists; we checked in getRootSummary above. - -- If it gets removed subsequently, then this - -- getFileHash may fail, but that's the right - -- behaviour. - - -- return the cached summary if the source didn't change - checkSummaryHash - hsc_env (new_summary src_fn) - old_summary location src_hash - - | otherwise - = do src_hash <- get_src_hash - new_summary src_fn src_hash +summariseFile hsc_env' home_unit summ_cache_ref src_fn mb_phase maybe_buf + = do (_, file_summ_cache) <- readIORef summ_cache_ref + case M.lookup (homeUnitId home_unit, src_fn_os) file_summ_cache of + Just (Right old_summary) -> do + -- we can use a cached summary if one is available and the + -- source file hasn't changed, + let location = ms_location $ old_summary + + src_hash <- get_src_hash + -- The file exists; we checked in getRootSummary above. + -- If it gets removed subsequently, then this + -- getFileHash may fail, but that's the right + -- behaviour. + + -- return the cached summary if the source didn't change + checkSummaryHash + hsc_env (new_summary src_fn) + old_summary location src_hash + _ -> do src_hash <- get_src_hash + new_summary src_fn src_hash where -- change the main active unit so all operations happen relative to the given unit hsc_env = hscSetActiveHomeUnit home_unit hsc_env' @@ -1237,7 +1221,8 @@ summariseFile hsc_env' home_unit old_summaries src_fn mb_phase maybe_buf Just (buf,_) -> return $ fingerprintStringBuffer buf Nothing -> liftIO $ getFileHash src_fn - new_summary src_fn src_hash = runExceptT $ do + new_summary src_fn src_hash = do + res <- runExceptT $ do preimps@PreprocessedImports {..} <- getPreprocessedImports hsc_env src_fn mb_phase maybe_buf @@ -1268,6 +1253,11 @@ summariseFile hsc_env' home_unit old_summaries src_fn mb_phase maybe_buf , nms_mod = mod , nms_preimps = preimps } + case res of + Left e -> modifyIORef' summ_cache_ref + (\(me, fe) -> (me, M.insert (homeUnitId home_unit, src_fn_os) (Left e) fe)) + Right ms -> modifyIORef' summ_cache_ref (addModSummaryCache ms) + return res checkSummaryHash :: HscEnv @@ -1320,7 +1310,7 @@ data SummariseResult = -- --make mode. summariseModule :: HscEnv -> HomeUnit - -> M.Map (UnitId, OsPath) ModSummary + -> ModSummaryCache -> IsBootInterface -> Located ModuleName -> PkgQual @@ -1400,15 +1390,15 @@ summariseModuleDispatch k hsc_env' home_unit is_boot (L _ wanted_mod) mb_pkg exc -- for it and potentially compile it. summariseModuleWithSource :: HomeUnit - -> M.Map (UnitId, OsPath) ModSummary - -- ^ Map of old summaries + -> ModSummaryCache + -- ^ Cache of constructed summaries -> IsBootInterface -- True <=> a {-# SOURCE #-} import -> Maybe (StringBuffer, UTCTime) -> HscEnv -> ModLocation -> Module -> IO SummariseResult -summariseModuleWithSource home_unit old_summary_map is_boot maybe_buf hsc_env location mod = do +summariseModuleWithSource home_unit summ_cache_ref is_boot maybe_buf hsc_env location mod = do -- Adjust location to point to the hs-boot source file, -- hi file, object file, when is_boot says so let src_fn = expectJust (ml_hs_file location) @@ -1428,20 +1418,19 @@ summariseModuleWithSource home_unit old_summary_map is_boot maybe_buf hsc_env lo where dflags = hsc_dflags hsc_env - new_summary_cache_check loc mod src_fn h - | Just old_summary <- Map.lookup ((toUnitId (moduleUnit mod), src_fn_os)) old_summary_map = - - -- check the hash on the source file, and - -- return the cached summary if it hasn't changed. If the - -- file has changed then need to resummarise. - case maybe_buf of - Just (buf,_) -> - checkSummaryHash hsc_env (new_summary loc mod src_fn) old_summary loc (fingerprintStringBuffer buf) - Nothing -> - checkSummaryHash hsc_env (new_summary loc mod src_fn) old_summary loc h - | otherwise = new_summary loc mod src_fn h - where - src_fn_os = unsafeEncodeUtf src_fn + new_summary_cache_check loc mod src_fn h = do + (summ_cache, _) <- readIORef summ_cache_ref + case lookupModuleEnv summ_cache mod of + Just (Right old_summary) -> do + -- check the hash on the source file, and + -- return the cached summary if it hasn't changed. If the + -- file has changed then need to resummarise. + case maybe_buf of + Just (buf,_) -> + checkSummaryHash hsc_env (new_summary loc mod src_fn) old_summary loc (fingerprintStringBuffer buf) + Nothing -> + checkSummaryHash hsc_env (new_summary loc mod src_fn) old_summary loc h + _ -> new_summary loc mod src_fn h new_summary :: ModLocation -> Module @@ -1449,41 +1438,48 @@ summariseModuleWithSource home_unit old_summary_map is_boot maybe_buf hsc_env lo -> Fingerprint -> IO (Either DriverMessages ModSummary) new_summary location mod src_fn src_hash - = runExceptT $ do - preimps@PreprocessedImports {..} - -- Remember to set the active unit here, otherwise the wrong include paths are passed to CPP - -- See multiHomeUnits_cpp2 test - <- getPreprocessedImports (hscSetActiveUnitId (moduleUnitId mod) hsc_env) src_fn Nothing maybe_buf - - -- NB: Despite the fact that is_boot is a top-level parameter, we - -- don't actually know coming into this function what the HscSource - -- of the module in question is. This is because we may be processing - -- this module because another module in the graph imported it: in this - -- case, we know if it's a boot or not because of the {-# SOURCE #-} - -- annotation, but we don't know if it's a signature or a regular - -- module until we actually look it up on the filesystem. - let hsc_src - | is_boot == IsBoot = HsBootFile - | isHaskellSigFilename src_fn = HsigFile - | otherwise = HsSrcFile - - when (pi_mod_name /= moduleName mod) $ - throwE $ singleMessage $ mkPlainErrorMsgEnvelope pi_mod_name_loc - $ DriverFileModuleNameMismatch pi_mod_name (moduleName mod) - - let instantiations = homeUnitInstantiations home_unit - when (hsc_src == HsigFile && isNothing (lookup pi_mod_name instantiations)) $ - throwE $ singleMessage $ mkPlainErrorMsgEnvelope pi_mod_name_loc - $ DriverUnexpectedSignature pi_mod_name (checkBuildingCabalPackage dflags) instantiations + = pprTrace "new_summary" (ppr mod) $ do + res <- runExceptT $ do + preimps@PreprocessedImports {..} + -- Remember to set the active unit here, otherwise the wrong include paths are passed to CPP + -- See multiHomeUnits_cpp2 test + <- getPreprocessedImports (hscSetActiveUnitId (moduleUnitId mod) hsc_env) src_fn Nothing maybe_buf + + -- NB: Despite the fact that is_boot is a top-level parameter, we + -- don't actually know coming into this function what the HscSource + -- of the module in question is. This is because we may be processing + -- this module because another module in the graph imported it: in this + -- case, we know if it's a boot or not because of the {-# SOURCE #-} + -- annotation, but we don't know if it's a signature or a regular + -- module until we actually look it up on the filesystem. + let hsc_src + | is_boot == IsBoot = HsBootFile + | isHaskellSigFilename src_fn = HsigFile + | otherwise = HsSrcFile + + when (pi_mod_name /= moduleName mod) $ + throwE $ singleMessage $ mkPlainErrorMsgEnvelope pi_mod_name_loc + $ DriverFileModuleNameMismatch pi_mod_name (moduleName mod) + + let instantiations = homeUnitInstantiations home_unit + when (hsc_src == HsigFile && isNothing (lookup pi_mod_name instantiations)) $ + throwE $ singleMessage $ mkPlainErrorMsgEnvelope pi_mod_name_loc + $ DriverUnexpectedSignature pi_mod_name (checkBuildingCabalPackage dflags) instantiations + + liftIO $ makeNewModSummary hsc_env $ MakeNewModSummary + { nms_src_fn = src_fn + , nms_src_hash = src_hash + , nms_hsc_src = hsc_src + , nms_location = location + , nms_mod = mod + , nms_preimps = preimps + } + case res of + Left e -> modifyIORef' summ_cache_ref + (\(me, fe) -> (extendModuleEnv me mod (Left e), fe)) + Right ms -> modifyIORef' summ_cache_ref (addModSummaryCache ms) + return res - liftIO $ makeNewModSummary hsc_env $ MakeNewModSummary - { nms_src_fn = src_fn - , nms_src_hash = src_hash - , nms_hsc_src = hsc_src - , nms_location = location - , nms_mod = mod - , nms_preimps = preimps - } -- | Convenience named arguments for 'makeNewModSummary' only used to make -- code more readable, not exported. @@ -1563,3 +1559,37 @@ getPreprocessedImports hsc_env src_fn mb_phase maybe_buf = do let pi_srcimps = pi_srcimps' let pi_theimps = rn_imps pi_theimps' return PreprocessedImports {..} + +-------------------------------------------------------------------------------- + +-- ToDo: MiniQuickCheck me that I don't ever expand the same node twice (by key) +-- ToDo: Docs +-- base, roots, node to key, expand +-- +-- @n@: a graph node, from which you can recover the key and dependencies +-- @k@: a key from which you can compute the graph node (thus, transitively, the dependencies of that key too) +-- +-- @n@ instanced by @ModuleGraphNode@ +-- @k@ instanced by @NodeKey@ +-- +-- Returning 'Nothing' in the @expand@ function means that node couldn't be +-- expanded yet, and we should continue without failure. Do NOT cache a +-- "negative" result for the 'Nothing', because we may yet discover new +-- information and try to expand that node in the future again, then +-- successfully. +dfsBuild :: (Ord k, Monad m) => Maybe (Map.Map k v) -> [n] -> (n -> k) -> (n -> m (Maybe (v,[n]))) -> m (Map.Map k v) +dfsBuild base_map roots key expand = go roots (fromMaybe Map.empty base_map) + where + go [] visited = pure visited + go (s:ss) visited + | k `Map.member` visited + = go ss visited + | otherwise + = do r <- expand s + case r of + Nothing -> go ss visited -- Skip! + Just (v,ns) -> + go (ns ++ ss {- todo: not use ++ here? -}) + (Map.insert k v visited) + where + k = key s View it on GitLab: https://gitlab.haskell.org/ghc/ghc/-/compare/dfe34135622aad8352d191a3d13352f... -- View it on GitLab: https://gitlab.haskell.org/ghc/ghc/-/compare/dfe34135622aad8352d191a3d13352f... You're receiving this email because of your account on gitlab.haskell.org.