How to read a NASM Assembly program .lst listing file
I wrote a NASM program and created a listing file from it using nasm -f elf -l rs.lst rs.asm.
The program, which works perfectly, takes in a key input value, and outputs whether the value is a control key or printable key, and if it is a number, lowercase, or uppercase letter.
I need help understanding what I am reading in the .lst file.
Are the numbers on the left addresses? Instructions? DO they represent memory?
Here's the .lst.
1 segment .data
//Removed my student ID info
8 ;Program Output Strings
9
10 00000023 5072657373204B6579- askForKey: db 'Press Key and Enter: ', 10 ; ;10 is the newline value
11 0000002C 20616E6420456E7465-
12 00000035 723A200A
13 askLen: equ $-askForKey
14
15 00000039 436F6E74726F6C204B- controlKey: db 'Control Key ', 10
16 00000042 6579200A
17 controlLen: equ $-controlKey
18
19 00000046 5072696E7461626C65- printableKey: db 'Printable Key ', 10
20 0000004F 204B6579200A
21 printableLen: equ $-printableKey
22
23 00000055 446563696D616C204B- decimalKey: db 'Decimal Key ', 10
24 0000005E 6579200A
25 decimalLen: equ $-decimalKey
26
27 00000062 55707065722D636173- upperKey: db 'Upper-case Key ', 10
28 0000006B 65204B6579200A
29 upperLen: equ $-upperKey
30
31 00000072 4C6F7765722D636173- lowerKey: db 'Lower-case Key ', 10
32 0000007B 65204B6579200A
33 lowerLen: equ $-lowerKey
34
35 00000082 0A blankLine: db '', 10
36 blankLen: equ $-blankLine
37
38 segment .bss
39
40 00000000 <res 00000002> key resb 2
41
42 segment .text
43
44 global main
45 main:
46
47
48 00000000 B804000000 mov eax, 4 ; system call 4
49 00000005 BB01000000 mov ebx, 1 ; standard output
50 0000000A B9[00000000] mov ecx, studentInfo ; 'Program by Raphael Stein'
51 0000000F BA23000000 mov edx, infoLen
52 00000014 CD80 int 0x80
53
54 ;Program Begins
55
56 ; Ask for key input
57 00000016 B804000000 mov eax, 4 ; system call 4
58 0000001B BB01000000 mov ebx, 1 ; standard output
59 00000020 B9[23000000] mov ecx, askForKey ; 'Press key and Enter: '
60 00000025 BA16000000 mov edx, askLen
61 0000002A CD80 int 0x80
62 ; Take input
63 0000002C B803000000 mov eax, 3 ; system call 3 to get input
64 00000031 BB00000000 mov ebx, 0 ; standart input device
65 00000036 B9[00000000] mov ecx, key ; pointer to id
66 0000003B BA02000000 mov edx, 2 ; take in this many bytes
67 00000040 CD80 int 0x80
68
69
70
71 control: ; check if it's a control key
72 00000042 B120 mov cl, 32 ; space bar (32) is the first key after control keys
73 00000044 BB[00000000] mov ebx, key ;move the first 8bits of ebx for comparison
74 00000049 380B cmp byte [ebx], cl ; compare 32 and the value of key
75 0000004B 7D1B jge printable ; If the key is >=, it's a printable
76 0000004D B804000000 mov eax, 4
77 00000052 BB01000000 mov ebx, 1
78 00000057 B9[39000000] mov ecx, controlKey
79 0000005C BA0D000000 mov edx, controlLen
80 00000061 CD80 int 0x80
81 00000063 E9A0000000 jmp exit ; It's obviously not any of the other categories
82
83
84 printable: ; Tell that it's a printable symbol
85 00000068 B804000000 mov eax, 4
86 0000006D BB01000000 mov ebx, 1
87 00000072 B9[46000000] mov ecx, printableKey
88 00000077 BA0F000000 mov edx, printableLen
89 0000007C CD80 int 0x80
90
91 decimal:
92 0000007E B130 mov cl, 48 ; 0 (48) is the smallest decimal
93 00000080 BB[00000000] mov ebx, key ;move the first 8bits of ebx for comparison
94 00000085 380B cmp byte [ebx], cl
95 00000087 7C7F jl exit
96 00000089 B139 mov cl, 57 ; 9 (57) is the largest decimal
97 0000008B BB[00000000] mov ebx, key ;move the first 8bits of ebx for comparison
98 00000090 380B cmp byte [ebx], cl
99 00000092 7F18 jg uppercase ; if key is greater, jump to check if it's uppercase.
100 00000094 B804000000 mov eax, 4
101 00000099 BB01000000 mov ebx, 1
102 0000009E B9[55000000] mov ecx, decimalKey
103 000000A3 BA0D000000 mov edx, decimalLen
104 000000A8 CD80 int 0x80
105 000000AA EB5C jmp exit
106
107 uppercase:
108 000000AC B141 mov cl, 65 ; A (65) is the smallest smallest uppercase
109 000000AE BB[00000000] mov ebx, key ;move the first 8bits of ebx for comparison
110 000000B3 380B cmp byte [ebx], cl
111 000000B5 7C51 jl exit
112 000000B7 B15A mov cl, 90 ; Z (90) is the largest upper case
113 000000B9 BB[00000000] mov ebx, key ;move the first 8bits of ebx for comparison
114 000000BE 380B cmp byte [ebx], cl
115 000000C0 7F18 jg lowercase
116 000000C2 B804000000 mov eax, 4 ; If it IS an upper case key, print and then exit
117 000000C7 BB01000000 mov ebx, 1
118 000000CC B9[62000000] mov ecx, upperKey
119 000000D1 BA10000000 mov edx, upperLen
120 000000D6 CD80 int 0x80
121 000000D8 EB2E jmp exit
122
123
124 lowercase:
125 000000DA B161 mov cl, 97 ; a (97) is the smallest smallest uppercase
126 000000DC BB[00000000] mov ebx, key ;move the first 8bits of ebx for comparison
127 000000E1 380B cmp byte [ebx], cl
128 000000E3 7C23 jl exit ; If the key is less than 97 exit.
129 000000E5 B17A mov cl, 122 ; Z (90) is the largest upper case
130 000000E7 BB[00000000] mov ebx, key ;move the first 8bits of ebx for comparison
131 000000EC 380B cmp byte [ebx], cl
132 000000EE 7FEA jg lowercase
133 000000F0 B804000000 mov eax, 4 ; If it IS an upper case key, print and then exit
134 000000F5 BB01000000 mov ebx, 1
135 000000FA B9[72000000] mov ecx, lowerKey
136 000000FF BA10000000 mov edx, lowerLen
137 00000104 CD80 int 0x80
138 00000106 EB00 jmp exit
139
140 exit:
141 00000108 B804000000 mov eax, 4 ; system call 4
142 0000010D BB01000000 mov ebx, 1 ; standard output
143 00000112 B9[82000000] mov ecx, blankLine ; Print blank line before exiting
144 00000117 BA01000000 mov edx, blankLen
145 0000011C CD80 int 0x80
146
147 0000011E B801000000 mov eax, 1
148 00000123 31DB xor ebx, ebx
149 00000125 CD80 int 0x80
150
Answer
The numbers on the left are the binary output of the assembler, related to your source code lines.
First column is source code line
The second column is address or offset. For example 00000023 is the address where your prompt label askForKey: is.
Third column is binary value. For example if you look at your prompt text Press it translates directly to hex values 5072657373
52 00000014 CD80 int 0x80
reads like this:
source code line 52, offset 00000014 contains binary value CD80, compiled from instruction INT 0x80.
You can also see that the next line that has an address next to it is 57 00000016, where the 16 came to be from the 14 before + 2 bytes for CD80