initial_state.S stopped working...

.gitignore

@@ -6,3 +6,4 @@
 *.o
 *.so
 *.tmp
+tmp.S

Makefile

@@ -1,17 +1,18 @@
 .POSIX:
 
-IN_EXT ?= .S
+ASM_EXT ?= .asm
+S_EXT ?= .S
 LD ?= ld
 LINKER_SCRIPT ?= linker.ld
 # Use gcc so that the preprocessor will run first.
-MYAS ?= gcc
+GAS ?= gcc
 OBJ_EXT ?= .o
 OUT_EXT ?= .img
 QEMU ?= qemu-system-i386
 RUN ?= bios_hello_world
 TMP_EXT ?= .tmp
 
-OUTS := $(patsubst %$(IN_EXT),%$(OUT_EXT),$(wildcard *$(IN_EXT)))
+OUTS := $(foreach IN_EXT,$(ASM_EXT) $(S_EXT),$(patsubst %$(IN_EXT),%$(OUT_EXT),$(wildcard *$(IN_EXT))))
 RUN_FILE := $(RUN)$(OUT_EXT)
 
 .PRECIOUS: %$(OBJ_EXT)
@@ -22,8 +23,11 @@ all: $(OUTS)
 %$(OUT_EXT): %$(OBJ_EXT) $(LINKER_SCRIPT)
 	$(LD) --oformat binary -o '$@' -T '$(LINKER_SCRIPT)' '$<'
 
-%$(OBJ_EXT): %$(IN_EXT)
-	$(MYAS) -c -o '$@' '$<'
+%$(OBJ_EXT): %$(S_EXT)
+	$(GAS) -c -o '$@' '$<'
+
+%$(OUT_EXT): %$(ASM_EXT)
+	nasm -f bin -o '$@' '$<'
 
 clean:
 	rm -fr *$(OBJ_EXT) *$(OUT_EXT) *$(TMP_EXT)
@@ -37,7 +41,8 @@ debug: all
 
 bochs: all
 	# Supposes size is already multiples of 512.
-	# `grub-mkrescue` seems to respect that.
+	# We force that with our linker script,
+	# and `grub-mkrescue` also seems to respect it as well.
 	CYLINDERS="$$(($$(stat -c '%s' '$(RUN_FILE)') / 512))" && \
 	bochs -qf /dev/null \
 		'ata0-master: type=disk, path="$(RUN_FILE)", mode=flat, cylinders='"$$CYLINDERS"', heads=1, spt=1' \

README.md

@@ -22,6 +22,8 @@ Hello world programs that run without an operating system.
         1.  [keyboard](bios_keyboard.S)
             1.  [keyboard loop](bios_keyboard_loop.S)
         1.  [disk load](bios_disk_load.S)
+            1.  [disk load 2](bios_disk_load2.S)
+    1.  [Initial state](initial_state.S)
     1.  [reboot](reboot.S)
     1.  [Not testable in userland](not-testable-in-userland.md)
         1.  [Segment registers real mode](segment_registers_real_mode.S)
@@ -58,7 +60,7 @@ Hello world programs that run without an operating system.
 
 ## Getting started
 
-    sudo apt-get install bochs bochs-sdl build-essential gnu-efi qemu nasm xorriso
+    sudo apt-get install bochs bochs-sdl build-essential gdb gnu-efi qemu nasm xorriso
 
 ### Emulator
 

bios_disk_load.S

@@ -1,9 +1,11 @@
 /*
 Load one more sector from the disk
-besides the first 512 bytes and do something with it..
+besides the first 512 bytes and do something with it.
 
 Expected outcome: `@` gets printed to the screen.
 
+Grub 2.0 makes several calls to it under `grub-core/boot/i386/pc`
+
 TODO: not working on:
 
 - Bochs: `BOUND_GdMa: fails bounds test`.
@@ -11,14 +13,15 @@ TODO: not working on:
 
 Does work on QEMU and Thinkpad T400.
 
-Bibliography:
+## int 13
+
+BIOS call used for disk operations.
+
+## Bibliography
 
 - http://wiki.osdev.org/ATA_in_x86_RealMode_%28BIOS%29
-- https://en.wikipedia.org/wiki/INT_13H
 - https://thiscouldbebetter.wordpress.com/2011/03/15/creating-a-bootable-program-in-assembly-language/
-
-TODO answer:
-
+- https://en.wikipedia.org/wiki/INT_13H
 - http://stackoverflow.com/questions/19381434/cannot-read-disk-sectors-in-assembly-language
 - http://stackoverflow.com/questions/15497842/read-a-sector-from-hard-drive-with-int-13h
 */
@@ -67,13 +70,12 @@ just after the magic bytes.
 */
 .section .stage2
 stage2:
-    PUTC($0x0E40)
+    PUTC($0x40)
     hlt
+
     /*
-    Fill up the second sector to 512 byte.
-
-    This should be on the linker script as well in decent programs,
-    but let's just put it here to keep our other images smaller.
+    We could use `.org` here to fill up the second sector to a multiple of 512 bytes.
+    But the linker does that beautifully with `. = ALIGN(512)` for any size of stage2,
+    so we use that instead.
     */
-    .org 512
-
+    /*.org 512*/

bios_disk_load2.S

@@ -0,0 +1,12 @@
+/* Test loading 2 sectors instead of 1. */
+
+#include "common.h"
+BEGIN
+    CLEAR
+STAGE2
+    PUTC($0x61)
+    jmp sector3
+.org 512
+sector3:
+    PUTC($0x62)
+    hlt

common.h

@@ -89,6 +89,8 @@ end:
 /*
 Print a byte as two hexadecimal digits.
 
+reg: 1 byte register.
+
 Clobbers: ax, dl
 */
 #define PRINT_HEX(reg) \
@@ -127,3 +129,28 @@ loop:
     jmp loop
 end:
 .endm
+
+/*
+Load stage2 from disk to memory, and jump to it.
+
+TODO not working?
+
+To be used when the program does not fit in the 512 bytes.
+
+Sample usage:
+
+    STAGE2
+    Stage 2 code here.
+*/
+#define STAGE2 \
+    mov $2, %ah;\
+    mov __stage2_size, %al;\
+    mov $0x80, %dl;\
+    mov $0, %ch;\
+    mov $0, %dh;\
+    mov $2, %cl;\
+    mov $1f, %bx;\
+    int $0x13;\
+    jmp 1f;\
+    .section .stage2;\
+    1:

initial_state.S

@@ -17,19 +17,39 @@ Could be done with GDB on the emulator, but this will also work on real hardware
     PRINT_HEX(x);\
     PRINT_NEWLINE
 
-BEGIN
-
 INITIAL_STORE(ax)
 INITIAL_STORE(bx)
 INITIAL_STORE(cx)
 INITIAL_STORE(dx)
+/*
 INITIAL_STORE(cs)
+INITIAL_STORE(ds)
+INITIAL_STORE(es)
+INITIAL_STORE(fs)
+INITIAL_STORE(gs)
+INITIAL_STORE(ss)
+*/
+
+BEGIN
+
+STAGE2
 
 INITIAL_PRINT(ax)
 INITIAL_PRINT(bx)
 INITIAL_PRINT(cx)
 INITIAL_PRINT(dx)
+/*
+TODO this breaks if I add more code here.
+Linked to STAGE2 load I imagine.
+*/
+/*
 INITIAL_PRINT(cs)
+INITIAL_PRINT(ds)
+INITIAL_PRINT(es)
+INITIAL_PRINT(fs)
+INITIAL_PRINT(gs)
+INITIAL_PRINT(ss)
+*/
 
 hlt
 
@@ -37,4 +57,11 @@ INITIAL_DATA(ax)
 INITIAL_DATA(bx)
 INITIAL_DATA(cx)
 INITIAL_DATA(dx)
+/*
 INITIAL_DATA(cs)
+INITIAL_DATA(ds)
+INITIAL_DATA(es)
+INITIAL_DATA(fs)
+INITIAL_DATA(gs)
+INITIAL_DATA(ss)
+*/

linker.ld

@@ -29,6 +29,20 @@ SECTIONS
         e.g. by reading more disk than the default 512 bytes with BIOS `int 0x13`.
          */
         *(.stage2)
+
+        /*
+        Number of sectors in stage 2. Used by the `int 13`.
+
+        The value gets put into memory as the very last thing
+        in the `.stage` section if it exists.
+
+        We must put it *before* the final `. = ALIGN(512)`,
+        or else it would fall out of the loaded memory.
+         */
+        __stage2_size = (ALIGN(.) / 512) - 1;
+
+        /* Ensure that the generated image is a multiple of 512. */
+        . = ALIGN(512);
     }
 }
 

nasm/Makefile

@@ -1,29 +0,0 @@
-.POSIX:
-
-RUN ?= bios_hello_world
-IN_EXT ?= .asm
-OUT_EXT ?= .img
-
-OUTS := $(patsubst %$(IN_EXT),%$(OUT_EXT),$(wildcard *$(IN_EXT)))
-RUN_FILE := $(RUN)$(OUT_EXT)
-
-.PHONY: clean run
-
-all: $(OUTS)
-
-%$(OUT_EXT): %$(IN_EXT)
-	nasm -f bin -o '$@' '$<'
-
-clean:
-	rm -f *'$(OUT_EXT)'
-
-run: all
-	qemu-system-i386 '$(RUN_FILE)'
-
-bochs: all
-	CYLINDERS="$$(($$(stat -c '%s' '$(RUN_FILE)') / 512))" && \
-	bochs -qf /dev/null \
-		'ata0-master: type=disk, path="$(RUN_FILE)", mode=flat, cylinders='"$$CYLINDERS"', heads=1, spt=1' \
-		'boot: disk' \
-		'display_library: sdl' \
-		'megs: 128'

nasm/Makefile

@@ -0,0 +1 @@
+../Makefile

protected_mode.S

@@ -1,6 +1,16 @@
 /*
 # Protected mode
 
+Major changes:
+
+-   BIOS cannot be used anymore
+
+-   GDT takes effect immediately so we *have* to deal with it now,
+    and we will later turn on paging
+
+-   we have to encode instructions differently.
+    Note that in 16-bit 32-bit instructions were encodable, but with a prefix.
+
 TODO get working.
 
 - http://wiki.osdev.org/Journey_To_The_Protected_Land

segment_registers_real_mode.S

@@ -9,10 +9,18 @@ On failure, trash is shows.
 
 I think their goal was to implement process virtualization in the past.
 
-FS and GS are general purpose: they don't generate or are affected implicitly by instructions.
-
 The special semantics of other registers will be covered in other files.
 
+## ES
+
+TODO: this does seem to have special properties as used by string instructions.
+
+## FS
+
+## GS
+
+FS and GS are general purpose: they don't generate or are affected implicitly by instructions.
+
 ## Vs protected mode
 
 In protected mode, the segment registers point to entries on the GDT:
@@ -20,7 +28,8 @@ In protected mode, the segment registers point to entries on the GDT:
 - http://reverseengineering.stackexchange.com/questions/2006/how-are-the-segment-registers-fs-gs-cs-ss-ds-es-used-in-linux
 - http://wiki.osdev.org/Segmentation
 
-Those entries still contain an analogous offset to the real mode offset, but also much more data, like segment width and permission.
+Those entries still contain an analogous offset to the real mode offset,
+but also much more data, like segment width and permission.
 
 ## How they work
 
@@ -43,7 +52,6 @@ The command:
 Shows that non ds encodings are achieved through a prefix, except for `ds`:
 
     20:   a0 63 7c                mov    0x7c63,%al
-    29:   a0 63 7c                mov    0x7c63,%al
     34:   26 a0 63 7c             mov    %es:0x7c63,%al
     40:   64 a0 63 7c             mov    %fs:0x7c63,%al
     4c:   65 a0 63 7c             mov    %gs:0x7c63,%al
@@ -67,7 +75,10 @@ BEGIN
     mov %ds:msg, %al
     PUTC(%al)
 
-    /* %ds is the default segment for GAS if we don't write it. */
+    /*
+    %ds is the default segment for GAS memory operations
+    if we don't write it explicitly.
+    */
     mov msg, %al
     PUTC(%al)