Why is my video memory offset calculation off by one?

Question

I have been reading and following a tutorial on writing an operating system from scratch by Nick Blundell which can be found at https://www.cs.bham.ac.uk/~exr/lectures/opsys/10_11/lectures/os-dev.pdf

I have successfully written a boot loader that can call C code, and so I have started writing my kernel in C. I am now trying to write functions that can print characters and strings on screen. By the time I start executing C code, I am in 32-bit protected mode, so I am trying to correctly calculate memory offsets from video memory address 0xb8000.

My problem starts when I try to access specific regions of video memory using a calculated offset. Since the text area is 25 rows by 80 columns, I use the formula ((row * 80) + column) * 2 since I have to have a character byte and an attribute byte. When I set row = 0 and column = 0, the X I'm trying to print is absent. Setting row = 0 and column = 1, an X appears at the upper left hand corner.

Starting with char* video_memory = 0xb8000 and repeatedly issuing video_memory++ allows me to correctly visit each byte and print a space on a black background.

This is my main code:

#include "../drivers/screen.h"

void main() {

   //clear_screen();
   //print_character('X', 0, 0, 0);

   // Helper variables.
   int row;
   int column;

   // We need to point at 0xB8000, where video memory resides.
   unsigned char* video_memory = (unsigned char*)0xB8000;
   for(row = 0; row < 25; row++) {
      for(column = 0; column < 80; column++) {
         // Clear the screen by printing a space on a black background.
         *video_memory = ' ';
         video_memory += 1;
         *video_memory = 0x0F;
         video_memory += 1;
      }
   }

   // Test the offset calculation by printing at row 0, column 0 (the upper 
   // left corner of the screen).
   row = 0;
   column = 0;

   // For an 80 by 25 grid. Multiply by 2 to account for the need of two bytes 
   // to display a character with given attributes.
   int offset = ((row * 80) + column) * 2;

   // Reset memory location after the loop.
   video_memory = (unsigned char*)0xB8000;

   // Add the offset to get the desired cell.
   // THIS IS WHERE THE PROBLEM IS! Setting column = 1 prints in the first cell
   // of video memory instead of the second.
   video_memory += offset;

   // Set character and its attributes.
   *video_memory = 'X';
   video_memory++;
   *video_memory = 0x0F;
}

This is the console displayed when row = 0 and column = 0: The console when row and column are 0. No X appears.

This is the console when row = 0 and column = 1: The console when row is 0 and column is 1. An X appears.

This is an objdump of my kernel.c file above:

kernel.o:     file format elf64-x86-64


Disassembly of section .text:

0000000000000000 <main>:
#include "../drivers/screen.h"

void main() {
   0:   55                      push   rbp
   1:   48 89 e5                mov    rbp,rsp
   // Helper variables.
   int row;
   int column;

   // We need to point at 0xB8000, where video memory resides.
   unsigned char* video_memory = (unsigned char*)0xB8000;
   4:   48 c7 45 f8 00 80 0b    mov    QWORD PTR [rbp-0x8],0xb8000
   b:   00 
   for(row = 0; row < 25; row++) {
   c:   c7 45 ec 00 00 00 00    mov    DWORD PTR [rbp-0x14],0x0
  13:   eb 2f                   jmp    44 <main+0x44>
      for(column = 0; column < 80; column++) {
  15:   c7 45 f0 00 00 00 00    mov    DWORD PTR [rbp-0x10],0x0
  1c:   eb 1c                   jmp    3a <main+0x3a>
         // Clear the screen by printing a space on a black background.
         *video_memory = ' ';
  1e:   48 8b 45 f8             mov    rax,QWORD PTR [rbp-0x8]
  22:   c6 00 20                mov    BYTE PTR [rax],0x20
         video_memory += 1;
  25:   48 83 45 f8 01          add    QWORD PTR [rbp-0x8],0x1
         *video_memory = 0x0F;
  2a:   48 8b 45 f8             mov    rax,QWORD PTR [rbp-0x8]
  2e:   c6 00 0f                mov    BYTE PTR [rax],0xf
         video_memory += 1;
  31:   48 83 45 f8 01          add    QWORD PTR [rbp-0x8],0x1
   int column;

   // We need to point at 0xB8000, where video memory resides.
   unsigned char* video_memory = (unsigned char*)0xB8000;
   for(row = 0; row < 25; row++) {
      for(column = 0; column < 80; column++) {
  36:   83 45 f0 01             add    DWORD PTR [rbp-0x10],0x1
  3a:   83 7d f0 4f             cmp    DWORD PTR [rbp-0x10],0x4f
  3e:   7e de                   jle    1e <main+0x1e>
   int row;
   int column;

   // We need to point at 0xB8000, where video memory resides.
   unsigned char* video_memory = (unsigned char*)0xB8000;
   for(row = 0; row < 25; row++) {
  40:   83 45 ec 01             add    DWORD PTR [rbp-0x14],0x1
  44:   83 7d ec 18             cmp    DWORD PTR [rbp-0x14],0x18
  48:   7e cb                   jle    15 <main+0x15>
      }
   }

   // Test the offset calculation by printing at row 0, column 0 (the upper 
   // left corner of the screen).
   row = 0;
  4a:   c7 45 ec 00 00 00 00    mov    DWORD PTR [rbp-0x14],0x0
   column = 0;
  51:   c7 45 f0 00 00 00 00    mov    DWORD PTR [rbp-0x10],0x0

   // For an 80 by 25 grid. Multiply by 2 to account for the need of two bytes 
   // to display a character with given attributes.
   int offset = ((row * 80) + column) * 2;
  58:   8b 55 ec                mov    edx,DWORD PTR [rbp-0x14]
  5b:   89 d0                   mov    eax,edx
  5d:   c1 e0 02                shl    eax,0x2
  60:   01 d0                   add    eax,edx
  62:   c1 e0 04                shl    eax,0x4
  65:   89 c2                   mov    edx,eax
  67:   8b 45 f0                mov    eax,DWORD PTR [rbp-0x10]
  6a:   01 d0                   add    eax,edx
  6c:   01 c0                   add    eax,eax
  6e:   89 45 f4                mov    DWORD PTR [rbp-0xc],eax

   // Reset memory location after the loop.
   video_memory = (unsigned char*)0xB8000;
  71:   48 c7 45 f8 00 80 0b    mov    QWORD PTR [rbp-0x8],0xb8000
  78:   00 

   // Add the offset to get the desired cell.
   // THIS IS WHERE THE PROBLEM IS! Setting column = 1 prints in the first cell
   // of video memory instead of the second.
   video_memory += offset;
  79:   8b 45 f4                mov    eax,DWORD PTR [rbp-0xc]
  7c:   48 98                   cdqe   
  7e:   48 01 45 f8             add    QWORD PTR [rbp-0x8],rax

   // Set character and its attributes.
   *video_memory = 'X';
  82:   48 8b 45 f8             mov    rax,QWORD PTR [rbp-0x8]
  86:   c6 00 58                mov    BYTE PTR [rax],0x58
   video_memory++;
  89:   48 83 45 f8 01          add    QWORD PTR [rbp-0x8],0x1
   *video_memory = 0x0F;
  8e:   48 8b 45 f8             mov    rax,QWORD PTR [rbp-0x8]
  92:   c6 00 0f                mov    BYTE PTR [rax],0xf
}
  95:   90                      nop
  96:   5d                      pop    rbp
  97:   c3                      ret    

I have traced over and hand checked the actual assembly instructions for my offset calculation, and they appear to be correct. I suspect the issue arises when I try to add my offset (type int) to my video memory address (type unsigned char*), but again I'm not entirely sure.

Also, I tried hard coding specific numbers for offsets. Using video_memory += 0 instead of video_memory += offset works as desired.

Answer 1

After more searching, I found an article on the ARM Information Center describing the use of C pointers to access specific addresses for memory mapped I/O devices.

Declaring my video_memory pointer variable as 'volatile' ensures that "the compiler always carries out the memory-accesses, rather than optimizing them out...". Apparently, according to this answer on Quora, compilers can generate instructions that overwrite data in a write buffer before that data is flushed to memory, which is where my problem occurs.

So declaring my variable as volatile unsigned char* video_memory = 0xB8000; produces the expected results.