summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorKrzysztof Gogolewski <krzysztof.gogolewski@tweag.io>2023-02-20 19:19:17 +0100
committerKrzysztof Gogolewski <krzysztof.gogolewski@tweag.io>2023-03-30 18:21:40 +0200
commitb6dc079489950741808b12ee4bafbf60e837ffd5 (patch)
treebb758e8ace24b13e9e5124ed457cac73520ce339
parent76bb4c586084d7fdcf0e5ce52623abbfca527c55 (diff)
downloadhaskell-wip/unsafe-coerce-doc.tar.gz
Fixes around unsafeCoerce#wip/unsafe-coerce-doc
1. `unsafeCoerce#` was documented in `GHC.Prim`. But since the overhaul in 74ad75e87317, `unsafeCoerce#` is no longer defined there. I've combined the documentation in `GHC.Prim` with the `Unsafe.Coerce` module. 2. The documentation of `unsafeCoerce#` stated that you should not cast a function to an algebraic type, even if you later cast it back before applying it. But ghci was doing that type of cast, as can be seen with 'ghci -ddump-ds' and typing 'x = not'. I've changed it to use Any following the documentation.
-rw-r--r--compiler/GHC/Builtin/primops.txt.pp44
-rw-r--r--compiler/GHC/Tc/Module.hs26
-rw-r--r--libraries/base/Unsafe/Coerce.hs30
-rw-r--r--testsuite/tests/ghci/should_run/T16096.stdout24
-rw-r--r--testsuite/tests/ghci/should_run/T21052.stdout4
5 files changed, 59 insertions, 69 deletions
diff --git a/compiler/GHC/Builtin/primops.txt.pp b/compiler/GHC/Builtin/primops.txt.pp
index e4283b2dda..e99e5dc3a3 100644
--- a/compiler/GHC/Builtin/primops.txt.pp
+++ b/compiler/GHC/Builtin/primops.txt.pp
@@ -3845,50 +3845,6 @@ pseudoop "seq"
-- This fixity is only the one picked up by Haddock. If you
-- change this, do update 'ghcPrimIface' in 'GHC.Iface.Load'.
-pseudoop "unsafeCoerce#"
- o -> p
- { The function 'unsafeCoerce#' allows you to side-step the typechecker entirely. That
- is, it allows you to coerce any type into any other type. If you use this function,
- you had better get it right, otherwise segmentation faults await. It is generally
- used when you want to write a program that you know is well-typed, but where Haskell's
- type system is not expressive enough to prove that it is well typed.
-
- The following uses of 'unsafeCoerce#' are supposed to work (i.e. not lead to
- spurious compile-time or run-time crashes):
-
- * Casting any lifted type to 'Any'
-
- * Casting 'Any' back to the real type
-
- * Casting an unboxed type to another unboxed type of the same size.
- (Casting between floating-point and integral types does not work.
- See the "GHC.Float" module for functions to do work.)
-
- * Casting between two types that have the same runtime representation. One case is when
- the two types differ only in "phantom" type parameters, for example
- @'Ptr' 'Int'@ to @'Ptr' 'Float'@, or @['Int']@ to @['Float']@ when the list is
- known to be empty. Also, a @newtype@ of a type @T@ has the same representation
- at runtime as @T@.
-
- Other uses of 'unsafeCoerce#' are undefined. In particular, you should not use
- 'unsafeCoerce#' to cast a T to an algebraic data type D, unless T is also
- an algebraic data type. For example, do not cast @'Int'->'Int'@ to 'Bool', even if
- you later cast that 'Bool' back to @'Int'->'Int'@ before applying it. The reasons
- have to do with GHC's internal representation details (for the cognoscenti, data values
- can be entered but function closures cannot). If you want a safe type to cast things
- to, use 'Any', which is not an algebraic data type.
-
- }
- with can_fail = True
-
--- NB. It is tempting to think that casting a value to a type that it doesn't have is safe
--- as long as you don't "do anything" with the value in its cast form, such as seq on it. This
--- isn't the case: the compiler can insert seqs itself, and if these happen at the wrong type,
--- Bad Things Might Happen. See bug #1616: in this case we cast a function of type (a,b) -> (a,b)
--- to () -> () and back again. The strictness analyser saw that the function was strict, but
--- the wrapper had type () -> (), and hence the wrapper de-constructed the (), the worker re-constructed
--- a new (), with the result that the code ended up with "case () of (a,b) -> ...".
-
primop TraceEventOp "traceEvent#" GenPrimOp
Addr# -> State# s -> State# s
{ Emits an event via the RTS tracing framework. The contents
diff --git a/compiler/GHC/Tc/Module.hs b/compiler/GHC/Tc/Module.hs
index f877e006b8..4b2c3969aa 100644
--- a/compiler/GHC/Tc/Module.hs
+++ b/compiler/GHC/Tc/Module.hs
@@ -103,7 +103,7 @@ import GHC.Iface.Env ( externaliseName )
import GHC.Iface.Make ( coAxiomToIfaceDecl )
import GHC.Iface.Load
-import GHC.Builtin.Types ( unitTy, mkListTy )
+import GHC.Builtin.Types ( mkListTy, anyTypeOfKind )
import GHC.Builtin.Names
import GHC.Builtin.Utils
@@ -2172,8 +2172,8 @@ We don't bother with the tcl_th_bndrs environment either.
-- | The returned [Id] is the list of new Ids bound by this statement. It can
-- be used to extend the InteractiveContext via extendInteractiveContext.
--
--- The returned TypecheckedHsExpr is of type IO [ () ], a list of the bound
--- values, coerced to ().
+-- The returned TypecheckedHsExpr is of type IO [ Any ], a list of the bound
+-- values, coerced to Any.
tcRnStmt :: HscEnv -> GhciLStmt GhcPs
-> IO (Messages TcRnMessage, Maybe ([Id], LHsExpr GhcTc, FixityEnv))
tcRnStmt hsc_env rdr_stmt
@@ -2467,13 +2467,16 @@ The reason for -fno-it is explained in #14336. `it` can lead to the repl
leaking memory as it is repeatedly queried.
-}
+any_lifted :: Type
+any_lifted = anyTypeOfKind liftedTypeKind
+
-- | Typecheck the statements given and then return the results of the
--- statement in the form 'IO [()]'.
+-- statement in the form 'IO [Any]'.
tcGhciStmts :: [GhciLStmt GhcRn] -> TcM PlanResult
tcGhciStmts stmts
= do { ioTyCon <- tcLookupTyCon ioTyConName
; ret_id <- tcLookupId returnIOName -- return @ IO
- ; let ret_ty = mkListTy unitTy
+ ; let ret_ty = mkListTy any_lifted
io_ret_ty = mkTyConApp ioTyCon [ret_ty]
tc_io_stmts = tcStmtsAndThen (HsDoStmt GhciStmtCtxt) tcDoStmt stmts
(mkCheckExpType io_ret_ty)
@@ -2496,28 +2499,31 @@ tcGhciStmts stmts
; traceTc "GHC.Tc.Module.tcGhciStmts: done" empty
-- ret_expr is the expression
- -- returnIO @[()] [unsafeCoerce# () x, .., unsafeCoerce# () z]
+ -- returnIO @[Any] [unsafeCoerce# @Any x, .., unsafeCoerce# @Any z]
--
-- Despite the inconvenience of building the type applications etc,
-- this *has* to be done in type-annotated post-typecheck form
-- because we are going to return a list of *polymorphic* values
- -- coerced to type (). If we built a *source* stmt
+ -- coerced to type Any. If we built a *source* stmt
-- return [coerce x, ..., coerce z]
-- then the type checker would instantiate x..z, and we wouldn't
-- get their *polymorphic* values. (And we'd get ambiguity errs
-- if they were overloaded, since they aren't applied to anything.)
+ --
+ -- We use Any rather than a dummy type such as () because of
+ -- the rules of unsafeCoerce#; see Unsafe/Coerce.hs for the details.
; AnId unsafe_coerce_id <- tcLookupGlobal unsafeCoercePrimName
-- We use unsafeCoerce# here because of (U11) in
-- Note [Implementing unsafeCoerce] in base:Unsafe.Coerce
; let ret_expr = nlHsApp (nlHsTyApp ret_id [ret_ty]) $
- noLocA $ ExplicitList unitTy $
+ noLocA $ ExplicitList any_lifted $
map mk_item ids
mk_item id = unsafe_coerce_id `nlHsTyApp` [ getRuntimeRep (idType id)
- , getRuntimeRep unitTy
- , idType id, unitTy]
+ , getRuntimeRep any_lifted
+ , idType id, any_lifted]
`nlHsApp` nlHsVar id
stmts = tc_stmts ++ [noLocA (mkLastStmt ret_expr)]
diff --git a/libraries/base/Unsafe/Coerce.hs b/libraries/base/Unsafe/Coerce.hs
index 76c010a0bf..23820f0f48 100644
--- a/libraries/base/Unsafe/Coerce.hs
+++ b/libraries/base/Unsafe/Coerce.hs
@@ -244,11 +244,11 @@ unsafeEqualityProof = case unsafeEqualityProof @a @b of UnsafeRefl -> UnsafeRefl
-- Why delay inlining to Phase 1? Because of the RULES for map/unsafeCoerce;
-- see (U8) in Note [Implementing unsafeCoerce]
--- | Coerce a value from one type to another, bypassing the type-checker.
+-- | `unsafeCoerce` coerces a value from one type to another, bypassing the type-checker.
--
-- There are several legitimate ways to use 'unsafeCoerce':
--
--- 1. To coerce e.g. @Int@ to @HValue@, put it in a list of @HValue@,
+-- 1. To coerce a lifted type such as @Int@ to @Any@, put it in a list of @Any@,
-- and then later coerce it back to @Int@ before using it.
--
-- 2. To produce e.g. @(a+b) :~: (b+a)@ from @unsafeCoerce Refl@.
@@ -269,15 +269,35 @@ unsafeEqualityProof = case unsafeEqualityProof @a @b of UnsafeRefl -> UnsafeRefl
-- are the same -- but the proof of that relies on the complex, trusted
-- implementation of @Typeable@.
--
--- 4. The "reflection trick", which takes advantage of the fact that in
+-- 4. (superseded) The "reflection trick", which takes advantage of the fact that in
-- @class C a where { op :: ty }@, we can safely coerce between @C a@ and @ty@
-- (which have different kinds!) because it's really just a newtype.
-- Note: there is /no guarantee, at all/ that this behavior will be supported
-- into perpetuity.
+-- It is now preferred to use `withDict` in @GHC.Magic.Dict@, which
+-- is type-safe. See Note [withDict] in GHC.Tc.Instance.Class for details.
--
+-- 5. (superseded) Casting between two types which have exactly the same structure:
+-- between a newtype of T and T, or between types which differ only
+-- in "phantom" type parameters.
+-- It is now preferred to use `coerce` from @Data.Coerce@, which
+-- is type-safe.
--
--- For safe zero-cost coercions you can instead use the 'Data.Coerce.coerce' function from
--- "Data.Coerce".
+-- Other uses of 'unsafeCoerce' are undefined. In particular, you should not use
+-- 'unsafeCoerce' to cast a T to an algebraic data type D, unless T is also
+-- an algebraic data type. For example, do not cast @'Int'->'Int'@ to 'Bool', even if
+-- you later cast that 'Bool' back to @'Int'->'Int'@ before applying it. The reasons
+-- have to do with GHC's internal representation details (for the cognoscenti, data values
+-- can be entered but function closures cannot). If you want a safe type to cast things
+-- to, use 'Any', which is not an algebraic data type.
+
+-- NB. It is tempting to think that casting a value to a type that it doesn't have is safe
+-- as long as you don't "do anything" with the value in its cast form, such as seq on it. This
+-- isn't the case: the compiler can insert seqs itself, and if these happen at the wrong type,
+-- Bad Things Might Happen. See bug #1616: in this case we cast a function of type (a,b) -> (a,b)
+-- to () -> () and back again. The strictness analyser saw that the function was strict, but
+-- the wrapper had type () -> (), and hence the wrapper de-constructed the (), the worker re-constructed
+-- a new (), with the result that the code ended up with "case () of (a,b) -> ...".
unsafeCoerce :: forall (a :: Type) (b :: Type) . a -> b
unsafeCoerce x = case unsafeEqualityProof @a @b of UnsafeRefl -> x
diff --git a/testsuite/tests/ghci/should_run/T16096.stdout b/testsuite/tests/ghci/should_run/T16096.stdout
index 2749f06586..d5c11d696b 100644
--- a/testsuite/tests/ghci/should_run/T16096.stdout
+++ b/testsuite/tests/ghci/should_run/T16096.stdout
@@ -13,12 +13,16 @@ letrec {
x = GHC.Enum.enumFrom @GHC.Types.Int $dEnum (GHC.Types.I# 1#); } in
x; } in
GHC.Base.returnIO
- @[()]
+ @[GHC.Types.Any]
(GHC.Types.:
- @()
+ @GHC.Types.Any
(Unsafe.Coerce.unsafeCoerce#
- @GHC.Types.LiftedRep @GHC.Types.LiftedRep @[GHC.Types.Int] @() x)
- (GHC.Types.[] @()))
+ @GHC.Types.LiftedRep
+ @GHC.Types.LiftedRep
+ @[GHC.Types.Int]
+ @GHC.Types.Any
+ x)
+ (GHC.Types.[] @GHC.Types.Any))
@@ -36,11 +40,15 @@ letrec {
x = GHC.Enum.enumFrom @GHC.Types.Int $dEnum (GHC.Types.I# 1#); } in
x; } in
GHC.Base.returnIO
- @[()]
+ @[GHC.Types.Any]
(GHC.Types.:
- @()
+ @GHC.Types.Any
(Unsafe.Coerce.unsafeCoerce#
- @GHC.Types.LiftedRep @GHC.Types.LiftedRep @[GHC.Types.Int] @() x)
- (GHC.Types.[] @()))
+ @GHC.Types.LiftedRep
+ @GHC.Types.LiftedRep
+ @[GHC.Types.Int]
+ @GHC.Types.Any
+ x)
+ (GHC.Types.[] @GHC.Types.Any))
diff --git a/testsuite/tests/ghci/should_run/T21052.stdout b/testsuite/tests/ghci/should_run/T21052.stdout
index 3822a96b6e..cb1a1a16d4 100644
--- a/testsuite/tests/ghci/should_run/T21052.stdout
+++ b/testsuite/tests/ghci/should_run/T21052.stdout
@@ -1,10 +1,10 @@
==================== CodeGenInput STG: ====================
-BCO_toplevel :: GHC.Types.IO [()]
+BCO_toplevel :: GHC.Types.IO [GHC.Types.Any]
[LclId] =
{} \u []
let {
- sat :: [()]
+ sat :: [GHC.Types.Any]
[LclId] =
:! [GHC.Tuple.Prim.() GHC.Types.[]];
} in GHC.Base.returnIO sat;