word labels are now stored as offsets

also, the various address spaces in use are described better, and there's helper functions to convert between them.

Force-Push: yes
Change-Id: Idb56d2b6299d6e7071c9d42b2eb1138b17b85c69

2 files changed, 57 insertions, 14 deletions

diff --git a/execution.e b/execution.e
index 8410678..bd27f7e 100644
--- a/execution.e
+++ b/execution.e
@@ -481,7 +481,7 @@
   current-offset L!' warm-start
 
   ~ TODO this is tied to the specific example in evoke
-  over L@' happy-path swap - L@' origin + pack64
+  L@' happy-path L@' origin + pack64
 
   ~   Before handing off to us, cold-start pushed a single value onto the
   ~ stack, a pointer to the beginning of the heap. Now, we load our entire
diff --git a/transform.e b/transform.e
index e788836..f8a4ee4 100644
--- a/transform.e
+++ b/transform.e
@@ -163,12 +163,52 @@ allocate-transform-state s" transform-state" variable
   latest @ transform-state transform-state-saved-latest @
   latest ! transform-state transform-state-saved-latest ! ;
 
-~ (address within the output buffer -- address at generated binary's runtime)
-: transform-offset
+~   We deal with a few address spaces. There's the "host" address space, the
+~ space this process performing the compilation is using for itself. There's
+~ the "target" address space, the address space that will exist later, when
+~ the program we've compiled is running.
+~
+~   Then there's "offsets", which are relative to the start of the output
+~ buffer. For clarity's sake, we always refer to these as offsets, rather than
+~ as addresses.
+~
+~   When we define labels for compiled words, we set their values to be
+~ offsets pointing to the generated codeword. This is done by "Lcreate". We
+~ then need to convert them either to the host or the target address space,
+~ depending on how we're using them.
+~
+~   There's no approach here that isn't confusing, but the hope is that by
+~ using offsets, so that we always have to convert them regardless of what
+~ we're doing with them, we won't miss a spot where conversion needs to
+~ happen.
+~
+~ (output offset -- target address)
+: offset-to-target-address-space
+  ~ Don't transform null pointers.
+  dup { swap-transform-variables L@' origin swap-transform-variables + } if ;
+
+~ (target address -- output offset)
+: target-address-space-to-offset
   ~ Don't transform null pointers.
-  dup { transform-state transform-state-output-buffer-start @ -
-        swap-transform-variables L@' origin swap-transform-variables
-        + } if ;
+  dup { swap-transform-variables L@' origin swap-transform-variables - } if ;
+
+~ (output offset -- host address)
+: offset-to-host-address-space
+  ~ Don't transform null pointers
+  dup { transform-state transform-state-output-buffer-start @ + } if ;
+
+~ (host address --output offset)
+: host-address-space-to-offset
+  ~ Don't transform null pointers
+  dup { transform-state transform-state-output-buffer-start @ - } if ;
+
+~ (host address inside the output buffer -- target address)
+: host-address-space-to-target
+  host-address-space-to-offset offset-to-target-address-space ;
+
+~ (target address -- host address)
+: target-address-space-to-host
+  target-address-space-to-offset offset-to-host-address-space ;
 
 
 ~   This is the alternate version of "create" for use with the label
@@ -180,9 +220,11 @@ allocate-transform-state s" transform-state" variable
   here @ 10 + 3unroll memmove
   here @
 
-  ~   This value of "latest" is going into the generated output, so call
-  ~ transform-offset on it first.
-  latest @ transform-offset pack64
+  ~   This value of "latest" is going into the generated output, so we need
+  ~ to map it to the target address space. It's stored in the host address
+  ~ space to make immediate words work as expected, so the appropriate
+  ~ conversion is host-address-space-to-target.
+  latest @ host-address-space-to-target pack64
   0 pack8
   0 pack8
   +
@@ -191,7 +233,8 @@ allocate-transform-state s" transform-state" variable
 
   ~   Now we're immediately after the word header, which is where the codeword
   ~ will be. This is the value the label should taken on, so we set it.
-  dup here @ 10 +
+  dup host-address-space-to-offset
+  here @ 10 +
   swap-transform-variables
   intern-label set-label
   swap-transform-variables
@@ -226,7 +269,7 @@ allocate-transform-state s" transform-state" variable
   swap-transform-variables
   L@' exit
   swap-transform-variables
-  transform-offset ,
+  offset-to-target-address-space ,
 
   latest @ unhide-entry
 
@@ -244,7 +287,7 @@ allocate-transform-state s" transform-state" variable
   here @ pack-next 8 packalign here !
   latest @ dup unhide-entry entry-to-execution-token
   ~ The codeword needs to be transformed to the target address space.
-  dup 8 + transform-offset
+  dup 8 + host-address-space-to-target
   swap !
 
   ~   Since [ is an immediate word, we have to go to extra trouble to compile
@@ -347,7 +390,7 @@ allocate-transform-state s" transform-state" variable
         ~
         ~   Fortunately we don't have to look at it, just append it to the heap
         ~ and clean up.
-        transform-offset , drop dropstring 0 exit
+        offset-to-target-address-space , drop dropstring 0 exit
       } if
     } if
   } if
@@ -380,7 +423,7 @@ allocate-transform-state s" transform-state" variable
 
       ~ We look up "lit" as a label.
       swap-transform-variables L@' lit swap-transform-variables
-      transform-offset
+      offset-to-target-address-space
       , ,
       0 exit
     } if