pureboot: a 512-byte slot on every chip, the 1284s included

The word-addressed 1284s were the one family deploying in a 1 KiB slot,
because the far-flash machinery (ELPM reads, RAMPZ page commands, a
word-addressed wire) did not fit 512 B. It does now: 478 B stock, 494 B in
the heaviest configuration the build can produce. They take the 644s'
geometry, where the smallest boot section holds the resident slot and its
staging slot together.

Most of the saving is one restructure. The info block and a flash read are
the same act, so giving all four streamed commands one address-and-count
path leaves exactly one call site for the flash streamer: it inlines into
the never-returning command loop and its 24-bit cursor stops being saved
and restored around every transmit. Around it, the ack byte moved out of
line, the wire's byte pair is bit_cast into the word it already is, the
fuse loop ends on its count, the info block's in-slot offset is taken as
the one-byte relocation it is, and -fno-expensive-optimizations gives way
to -fno-move-loop-invariants -fno-tree-ter. Every chip shrank 14-18 B.

The size matrix grew the axes it was missing: the USART1 instance across
the whole clock ladder, and the shape a slow baud gives a software UART —
past 255 delay iterations libavr takes the 16-bit delay loop, which the
ladder default never selects and which was 4 B over the 1284's slot the
first time it was built.

The protocol fixture stopped deriving the loader entry from the flash
size; on the 1284s it had been jumping a slot low and reaching the loader
only because erased flash walked it up.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

pureboot/pureboot.py

@@ -43,7 +43,7 @@ VERSION = 2  # this tool's own version — free to drift from a loader's
 # becomes the new floor here.
 OLDEST_LOADER = 1
 NEWEST_LOADER = 2
-SLOT = 512  # the loader slot on byte-addressed chips; word-addressed ones (>64 KiB) use 1 KiB — their own smallest boot sector
+SLOT = 512  # the loader slot, on every chip
 RETRIES = 3  # rewrites of a page that reads back wrong, before the run stops
 
 VERBOSE = False
@@ -336,9 +336,8 @@ class Info:
         scale = 2 if self.word_flash else 1
         self.base = (raw[7] | (raw[8] << 8)) * scale
         self.eeprom_size = raw[9] | (raw[10] << 8)
-        self.slot = 1024 if self.word_flash else SLOT
-        self.flash_size = self.base + self.slot
-        self.stage = self.base - self.slot  # where a staging copy of the loader goes
+        self.flash_size = self.base + SLOT
+        self.stage = self.base - SLOT  # where a staging copy of the loader goes
         # The hand-over target, as the word address 'J' takes: the trampoline
         # below the loader (tinies), or word 0 (mega — the application's own
         # reset vector; BOOTRST re-vectors a reset into the loader instead).
@@ -365,7 +364,7 @@ class Info:
             f"flash        {self.flash_size} B, {self.page} B pages"
             + (", word-addressed wire" if self.word_flash else ""),
             f"application  0x0000..{self.base - 1:#06x} ({self.base} B)",
-            f"loader       {self.base:#06x} ({self.slot} B slot)",
+            f"loader       {self.base:#06x} ({SLOT} B slot)",
             f"staging      {self.stage:#06x}",
             f"EEPROM       {self.eeprom_size} B",
             f"hand-over    {hand_over}",
@@ -681,13 +680,13 @@ def staging_content(image, info):
     that word, which for a staging copy is the slot's own last word: an rjmp
     to the resident base. The staging copy's fall-through and 'J'-free exit
     both land in a loader instead of garbage."""
-    slot = info.slot
-    if len(image) > (slot - 2 if info.patch_vector else slot):
-        raise Error(f"loader image is {len(image)} B, the slot holds {slot - 2 if info.patch_vector else slot}")
-    content = bytearray(image) + bytearray([0xFF] * (slot - len(image)))
+    budget = SLOT - 2 if info.patch_vector else SLOT
+    if len(image) > budget:
+        raise Error(f"loader image is {len(image)} B, the slot holds {budget}")
+    content = bytearray(image) + bytearray([0xFF] * (SLOT - len(image)))
     if info.patch_vector:
         through = rjmp_to((info.base - 2) // 2, info.base // 2, info.flash_size // 2)
-        content[slot - 2], content[slot - 1] = through & 0xFF, through >> 8
+        content[SLOT - 2], content[SLOT - 1] = through & 0xFF, through >> 8
     return bytes(content)
 
 
@@ -713,7 +712,7 @@ def update_preflight(image, info, fuse_bytes):
             raise Error(
                 f"cannot self-update: the staging slot {info.stage:#06x} lies below the "
                 f"boot section ({bls_start:#06x}) where SPM is disabled "
-                f"— a boot section of at least two slots ({2 * info.slot} B, BOOTSZ) is "
+                f"— a boot section of at least two slots ({2 * SLOT} B, BOOTSZ) is "
                 f"required, and only an external programmer can change fuses"
             )
         if not bootrst:
@@ -755,7 +754,7 @@ class UpdateState:
         self.data = {
             "signature": info.signature.hex(),
             "base": info.base,
-            "staging": loader.read_flash(info.stage, info.slot).hex(),
+            "staging": loader.read_flash(info.stage, SLOT).hex(),
             "page0": loader.read_flash(0, info.page).hex() if info.patch_vector else "",
         }
         with open(self.path, "w") as f:
@@ -835,7 +834,7 @@ def op_update_loader(loader, wait, path, state_path, fuse_bytes):
     update = image_info(image)  # the preflight proved it is there
     verbose(f"installing pureboot {update.version} over pureboot {info.version}")
     staged = staging_content(image, info)
-    resident = bytes(image) + bytes([0xFF] * (info.slot - len(image)))
+    resident = bytes(image) + bytes([0xFF] * (SLOT - len(image)))
     page = info.page
 
     state = UpdateState(state_path)
@@ -858,7 +857,7 @@ def op_update_loader(loader, wait, path, state_path, fuse_bytes):
     # state file's snapshot) — a resumed, half-written install differs
     # from its snapshot and takes the install path below, which completes
     # it page by page.
-    current = loader.read_flash(info.stage, info.slot)
+    current = loader.read_flash(info.stage, SLOT)
     staged_loader = image_info(current[:268])
     if staged_loader is not None and staged_loader.raw == info.raw and current == state.staging:
         print("staging slot already holds a loader — left in place")
@@ -867,7 +866,7 @@ def op_update_loader(loader, wait, path, state_path, fuse_bytes):
         # tiny13s), its first page carries the reset vector: written last,
         # so any earlier interruption still resets into the old resident,
         # and from then on resets enter the staging copy.
-        order = list(range(0, info.slot, page))
+        order = list(range(0, SLOT, page))
         if info.stage == 0:
             order = order[1:] + [0]
         if write_differing(loader, info.stage, staged, order, label="staging copy"):
@@ -894,7 +893,7 @@ def op_update_loader(loader, wait, path, state_path, fuse_bytes):
     if redirect:
         verbose("word 0 restored")
         write_differing(loader, 0, state.page0)
-    order = list(range(0, info.slot, page))
+    order = list(range(0, SLOT, page))
     if info.stage == 0:
         order = [0] + order[1:]
     write_differing(loader, info.stage, state.staging, order, label="staging restore")