Compare commits

...

2 Commits

539
exec.c

@ -0,0 +1,539 @@
/*
* linux/fs/exec.c
*
* (C) 1991 Linus Torvalds
*/
/*
* #!-checking implemented by tytso.
*/
/*
* Demand-loading implemented 01.12.91 - no need to read anything but
* the header into memory. The inode of the executable is put into
* "current->executable", and page faults do the actual loading. Clean.
*
* Once more I can proudly say that linux stood up to being changed: it
* was less than 2 hours work to get demand-loading completely implemented.
*/
#include <errno.h>
#include <string.h>
#include <sys/stat.h>
#include <a.out.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <asm/segment.h>
extern int sys_exit(int exit_code);
extern int sys_close(int fd);
/*
* MAX_ARG_PAGES defines the number of pages allocated for arguments
* and envelope for the new program. 32 should suffice, this gives
* a maximum env+arg of 128kB !
*/
#define MAX_ARG_PAGES 32
int sys_uselib()
{
return -ENOSYS;
}
/*
* create_tables() parses the env- and arg-strings in new user
* memory and creates the pointer tables from them, and puts their
* addresses on the "stack", returning the new stack pointer value.
*/
static unsigned long * create_tables(char * p,int argc,int envc)
{
unsigned long *argv,*envp;
unsigned long * sp;
sp = (unsigned long *) (0xfffffffc & (unsigned long) p);
sp -= envc+1;
envp = sp;
sp -= argc+1;
argv = sp;
put_fs_long((unsigned long)envp,--sp);
put_fs_long((unsigned long)argv,--sp);
put_fs_long((unsigned long)argc,--sp);
while (argc-->0) {
put_fs_long((unsigned long) p,argv++);
while (get_fs_byte(p++)) /* nothing */ ;
}
put_fs_long(0,argv);
while (envc-->0) {
put_fs_long((unsigned long) p,envp++);
while (get_fs_byte(p++)) /* nothing */ ;
}
put_fs_long(0,envp);
return sp;
}
/*
* count() counts the number of arguments/envelopes
*/
static int count(char ** argv)
{
int i=0;
char ** tmp;
if (tmp = argv)
while (get_fs_long((unsigned long *) (tmp++)))
i++;
return i;
}
/*
* 'copy_string()' copies argument/envelope strings from user
* memory to free pages in kernel mem. These are in a format ready
* to be put directly into the top of new user memory.
*
* Modified by TYT, 11/24/91 to add the from_kmem argument, which specifies
* whether the string and the string array are from user or kernel segments:
*
* from_kmem argv * argv **
* 0 user space user space
* 1 kernel space user space
* 2 kernel space kernel space
*
* We do this by playing games with the fs segment register. Since it
* it is expensive to load a segment register, we try to avoid calling
* set_fs() unless we absolutely have to.
*/
static unsigned long copy_strings(int argc,char ** argv,unsigned long *page,
unsigned long p, int from_kmem)
{
char *tmp, *pag;
int len, offset = 0;
unsigned long old_fs, new_fs;
if (!p)
return 0; /* bullet-proofing */
new_fs = get_ds();
old_fs = get_fs();
if (from_kmem==2)
set_fs(new_fs);
while (argc-- > 0) {
if (from_kmem == 1)
set_fs(new_fs);
if (!(tmp = (char *)get_fs_long(((unsigned long *)argv)+argc)))
panic("argc is wrong");
if (from_kmem == 1)
set_fs(old_fs);
len=0; /* remember zero-padding */
do {
len++;
} while (get_fs_byte(tmp++));
if (p-len < 0) { /* this shouldn't happen - 128kB */
set_fs(old_fs);
return 0;
}
while (len) {
--p; --tmp; --len;
if (--offset < 0) {
offset = p % PAGE_SIZE;
if (from_kmem==2)
set_fs(old_fs);
if (!(pag = (char *) page[p/PAGE_SIZE]) &&
!(pag = (char *) (page[p/PAGE_SIZE] =
(unsigned long *) get_free_page())))
return 0;
if (from_kmem==2)
set_fs(new_fs);
}
*(pag + offset) = get_fs_byte(tmp);
}
}
if (from_kmem==2)
set_fs(old_fs);
return p;
}
static unsigned long change_ldt(unsigned long text_size,unsigned long * page)
{
unsigned long code_limit,data_limit,code_base,data_base;
int i;
code_limit = text_size+PAGE_SIZE -1;
code_limit &= 0xFFFFF000;
data_limit = 0x4000000;
code_base = get_base(current->ldt[1]);
data_base = code_base;
set_base(current->ldt[1],code_base);
set_limit(current->ldt[1],code_limit);
set_base(current->ldt[2],data_base);
set_limit(current->ldt[2],data_limit);
/* make sure fs points to the NEW data segment */
__asm__("pushl $0x17\n\tpop %%fs"::);
data_base += data_limit;
for (i=MAX_ARG_PAGES-1 ; i>=0 ; i--) {
data_base -= PAGE_SIZE;
if (page[i])
put_page(page[i],data_base);
}
return data_limit;
}
/*
* 'do_execve()' executes a new program.
*/
int do_execve(unsigned long * eip,long tmp,char * filename,
char ** argv, char ** envp)
{
struct m_inode * inode;
struct buffer_head * bh;
struct exec ex;
unsigned long page[MAX_ARG_PAGES];
int i,argc,envc;
int e_uid, e_gid;
int retval;
int sh_bang = 0;
unsigned long p=PAGE_SIZE*MAX_ARG_PAGES-4;
if ((0xffff & eip[1]) != 0x000f)
panic("execve called from supervisor mode");
for (i=0 ; i<MAX_ARG_PAGES ; i++) /* clear page-table */
page[i]=0;
if (!(inode=namei(filename))) /* get executables inode */
return -ENOENT;
argc = count(argv);
envc = count(envp);
restart_interp:
if (!S_ISREG(inode->i_mode)) { /* must be regular file */
retval = -EACCES;
goto exec_error2;
}
i = inode->i_mode;
e_uid = (i & S_ISUID) ? inode->i_uid : current->euid;
e_gid = (i & S_ISGID) ? inode->i_gid : current->egid;
if (current->euid == inode->i_uid)
i >>= 6;
else if (current->egid == inode->i_gid)
i >>= 3;
if (!(i & 1) &&
!((inode->i_mode & 0111) && suser())) {
retval = -ENOEXEC;
goto exec_error2;
}
if (!(bh = bread(inode->i_dev,inode->i_zone[0]))) {
retval = -EACCES;
goto exec_error2;
}
ex = *((struct exec *) bh->b_data); /* read exec-header */
if ((bh->b_data[0] == '#') && (bh->b_data[1] == '!') && (!sh_bang)) {
/*
* This section does the #! interpretation.
* Sorta complicated, but hopefully it will work. -TYT
*/
char buf[1023], *cp, *interp, *i_name, *i_arg;
unsigned long old_fs;
strncpy(buf, bh->b_data+2, 1022);
brelse(bh);
iput(inode);
buf[1022] = '\0';
if (cp = strchr(buf, '\n')) {
*cp = '\0';
for (cp = buf; (*cp == ' ') || (*cp == '\t'); cp++);
}
if (!cp || *cp == '\0') {
retval = -ENOEXEC; /* No interpreter name found */
goto exec_error1;
}
interp = i_name = cp;
i_arg = 0;
for ( ; *cp && (*cp != ' ') && (*cp != '\t'); cp++) {
if (*cp == '/')
i_name = cp+1;
}
if (*cp) {
*cp++ = '\0';
i_arg = cp;
}
/*
* OK, we've parsed out the interpreter name and
* (optional) argument.
*/
if (sh_bang++ == 0) {
p = copy_strings(envc, envp, page, p, 0);
p = copy_strings(--argc, argv+1, page, p, 0);
}
/*
* Splice in (1) the interpreter's name for argv[0]
* (2) (optional) argument to interpreter
* (3) filename of shell script
*
* This is done in reverse order, because of how the
* user environment and arguments are stored.
*/
p = copy_strings(1, &filename, page, p, 1);
argc++;
if (i_arg) {
p = copy_strings(1, &i_arg, page, p, 2);
argc++;
}
p = copy_strings(1, &i_name, page, p, 2);
argc++;
if (!p) {
retval = -ENOMEM;
goto exec_error1;
}
/*
* OK, now restart the process with the interpreter's inode.
*/
old_fs = get_fs();
set_fs(get_ds());
if (!(inode=namei(interp))) { /* get executables inode */
set_fs(old_fs);
retval = -ENOENT;
goto exec_error1;
}
set_fs(old_fs);
goto restart_interp;
}
brelse(bh);
if (N_MAGIC(ex) != ZMAGIC || ex.a_trsize || ex.a_drsize ||
ex.a_text+ex.a_data+ex.a_bss>0x3000000 ||
inode->i_size < ex.a_text+ex.a_data+ex.a_syms+N_TXTOFF(ex)) {
retval = -ENOEXEC;
goto exec_error2;
}
if (N_TXTOFF(ex) != BLOCK_SIZE) {
printk("%s: N_TXTOFF != BLOCK_SIZE. See a.out.h.", filename);
retval = -ENOEXEC;
goto exec_error2;
}
if (!sh_bang) {
p = copy_strings(envc,envp,page,p,0);
p = copy_strings(argc,argv,page,p,0);
if (!p) {
retval = -ENOMEM;
goto exec_error2;
}
}
/* OK, This is the point of no return */
if (current->executable)
iput(current->executable);
current->executable = inode;
for (i=0 ; i<32 ; i++)
current->sigaction[i].sa_handler = NULL;
for (i=0 ; i<NR_OPEN ; i++)
if ((current->close_on_exec>>i)&1)
sys_close(i);
current->close_on_exec = 0;
free_page_tables(get_base(current->ldt[1]),get_limit(0x0f));
free_page_tables(get_base(current->ldt[2]),get_limit(0x17));
if (last_task_used_math == current)
last_task_used_math = NULL;
current->used_math = 0;
p += change_ldt(ex.a_text,page)-MAX_ARG_PAGES*PAGE_SIZE;
p = (unsigned long) create_tables((char *)p,argc,envc);
current->brk = ex.a_bss +
(current->end_data = ex.a_data +
(current->end_code = ex.a_text));
current->start_stack = p & 0xfffff000;
current->euid = e_uid;
current->egid = e_gid;
i = ex.a_text+ex.a_data;
while (i&0xfff)
put_fs_byte(0,(char *) (i++));
eip[0] = ex.a_entry; /* eip, magic happens :-) */
eip[3] = p; /* stack pointer */
return 0;
exec_error2:
iput(inode);
exec_error1:
for (i=0 ; i<MAX_ARG_PAGES ; i++)
free_page(page[i]);
return(retval);
}
int do_execve2(unsigned long * eip,long tmp,char * filename,
char ** argv, char ** envp)
{
struct m_inode * inode;
struct buffer_head * bh;
struct exec ex;
unsigned long page[MAX_ARG_PAGES];
int i,argc,envc;
int e_uid, e_gid;
int retval;
int sh_bang = 0;
unsigned long p=PAGE_SIZE*MAX_ARG_PAGES-4;
if ((0xffff & eip[1]) != 0x000f)
panic("execve2 called from supervisor mode");
for (i=0 ; i<MAX_ARG_PAGES ; i++) /* clear page-table */
page[i]=0;
if (!(inode=namei(filename))) /* get executables inode */
return -ENOENT;
argc = count(argv);
envc = count(envp);
restart_interp:
if (!S_ISREG(inode->i_mode)) { /* must be regular file */
retval = -EACCES;
goto exec_error2;
}
i = inode->i_mode;
e_uid = (i & S_ISUID) ? inode->i_uid : current->euid;
e_gid = (i & S_ISGID) ? inode->i_gid : current->egid;
if (current->euid == inode->i_uid)
i >>= 6;
else if (current->egid == inode->i_gid)
i >>= 3;
if (!(i & 1) &&
!((inode->i_mode & 0111) && suser())) {
retval = -ENOEXEC;
goto exec_error2;
}
if (!(bh = bread(inode->i_dev,inode->i_zone[0]))) {
retval = -EACCES;
goto exec_error2;
}
ex = *((struct exec *) bh->b_data); /* read exec-header */
if ((bh->b_data[0] == '#') && (bh->b_data[1] == '!') && (!sh_bang)) {
/*
* This section does the #! interpretation.
* Sorta complicated, but hopefully it will work. -TYT
*/
char buf[1023], *cp, *interp, *i_name, *i_arg;
unsigned long old_fs;
strncpy(buf, bh->b_data+2, 1022);
brelse(bh);
iput(inode);
buf[1022] = '\0';
if (cp = strchr(buf, '\n')) {
*cp = '\0';
for (cp = buf; (*cp == ' ') || (*cp == '\t'); cp++);
}
if (!cp || *cp == '\0') {
retval = -ENOEXEC; /* No interpreter name found */
goto exec_error1;
}
interp = i_name = cp;
i_arg = 0;
for ( ; *cp && (*cp != ' ') && (*cp != '\t'); cp++) {
if (*cp == '/')
i_name = cp+1;
}
if (*cp) {
*cp++ = '\0';
i_arg = cp;
}
/*
* OK, we've parsed out the interpreter name and
* (optional) argument.
*/
if (sh_bang++ == 0) {
p = copy_strings(envc, envp, page, p, 0);
p = copy_strings(--argc, argv+1, page, p, 0);
}
/*
* Splice in (1) the interpreter's name for argv[0]
* (2) (optional) argument to interpreter
* (3) filename of shell script
*
* This is done in reverse order, because of how the
* user environment and arguments are stored.
*/
p = copy_strings(1, &filename, page, p, 1);
argc++;
if (i_arg) {
p = copy_strings(1, &i_arg, page, p, 2);
argc++;
}
p = copy_strings(1, &i_name, page, p, 2);
argc++;
if (!p) {
retval = -ENOMEM;
goto exec_error1;
}
/*
* OK, now restart the process with the interpreter's inode.
*/
old_fs = get_fs();
set_fs(get_ds());
if (!(inode=namei(interp))) { /* get executables inode */
set_fs(old_fs);
retval = -ENOENT;
goto exec_error1;
}
set_fs(old_fs);
goto restart_interp;
}
brelse(bh);
if (N_MAGIC(ex) != ZMAGIC || ex.a_trsize || ex.a_drsize ||
ex.a_text+ex.a_data+ex.a_bss>0x3000000 ||
inode->i_size < ex.a_text+ex.a_data+ex.a_syms+N_TXTOFF(ex)) {
retval = -ENOEXEC;
goto exec_error2;
}
if (N_TXTOFF(ex) != BLOCK_SIZE) {
printk("%s: N_TXTOFF != BLOCK_SIZE. See a.out.h.", filename);
retval = -ENOEXEC;
goto exec_error2;
}
if (!sh_bang) {
p = copy_strings(envc,envp,page,p,0);
p = copy_strings(argc,argv,page,p,0);
if (!p) {
retval = -ENOMEM;
goto exec_error2;
}
}
/* OK, This is the point of no return */
if (current->executable)
iput(current->executable);
current->executable = inode;
for (i=0 ; i<32 ; i++)
current->sigaction[i].sa_handler = NULL;
for (i=0 ; i<NR_OPEN ; i++)
if ((current->close_on_exec>>i)&1)
sys_close(i);
current->close_on_exec = 0;
free_page_tables(get_base(current->ldt[1]),get_limit(0x0f));
free_page_tables(get_base(current->ldt[2]),get_limit(0x17));
if (last_task_used_math == current)
last_task_used_math = NULL;
current->used_math = 0;
p += change_ldt(ex.a_text,page)-MAX_ARG_PAGES*PAGE_SIZE;
p = (unsigned long) create_tables((char *)p,argc,envc);
current->brk = ex.a_bss +
(current->end_data = ex.a_data +
(current->end_code = ex.a_text));
current->start_stack = p & 0xfffff000;
current->euid = e_uid;
current->egid = e_gid;
i = ex.a_text+ex.a_data;
while (i&0xfff)
put_fs_byte(0,(char *) (i++));
eip[0] = ex.a_entry; /* eip, magic happens :-) */
eip[3] = p; /* stack pointer */
char* tmp_buf;
for(tmp_buf=0;tmp_buf<=current->brk;tmp_buf+=4096)
do_no_page(4, current->start_code+tmp_buf);
return 0;
exec_error2:
iput(inode);
exec_error1:
for (i=0 ; i<MAX_ARG_PAGES ; i++)
free_page(page[i]);
return(retval);
}

@ -0,0 +1,298 @@
/*
* linux/kernel/system_call.s
*
* (C) 1991 Linus Torvalds
*/
/*
* system_call.s contains the system-call low-level handling routines.
* This also contains the timer-interrupt handler, as some of the code is
* the same. The hd- and flopppy-interrupts are also here.
*
* NOTE: This code handles signal-recognition, which happens every time
* after a timer-interrupt and after each system call. Ordinary interrupts
* don't handle signal-recognition, as that would clutter them up totally
* unnecessarily.
*
* Stack layout in 'ret_from_system_call':
*
* 0(%esp) - %eax
* 4(%esp) - %ebx
* 8(%esp) - %ecx
* C(%esp) - %edx
* 10(%esp) - %fs
* 14(%esp) - %es
* 18(%esp) - %ds
* 1C(%esp) - %eip
* 20(%esp) - %cs
* 24(%esp) - %eflags
* 28(%esp) - %oldesp
* 2C(%esp) - %oldss
*/
SIG_CHLD = 17
EAX = 0x00
EBX = 0x04
ECX = 0x08
EDX = 0x0C
FS = 0x10
ES = 0x14
DS = 0x18
EIP = 0x1C
CS = 0x20
EFLAGS = 0x24
OLDESP = 0x28
OLDSS = 0x2C
state = 0 # these are offsets into the task-struct.
counter = 4
priority = 8
signal = 12
sigaction = 16 # MUST be 16 (=len of sigaction)
blocked = (33*16)
# offsets within sigaction
sa_handler = 0
sa_mask = 4
sa_flags = 8
sa_restorer = 12
nr_system_calls = 100 /* 72 */
/*
* Ok, I get parallel printer interrupts while using the floppy for some
* strange reason. Urgel. Now I just ignore them.
*/
.globl system_call,sys_fork,timer_interrupt,sys_execve,sys_execve2
.globl hd_interrupt,floppy_interrupt,parallel_interrupt
.globl device_not_available, coprocessor_error
.align 4
bad_sys_call:
movl $-1,%eax
iret
.align 4
reschedule:
pushl $ret_from_sys_call
jmp schedule
.align 4
system_call:
cmpl $nr_system_calls-1,%eax
ja bad_sys_call
push %ds
push %es
push %fs
pushl %edx
pushl %ecx # push %ebx,%ecx,%edx as parameters
pushl %ebx # to the system call
movl $0x10,%edx # set up ds,es to kernel space
mov %dx,%ds
mov %dx,%es
movl $0x17,%edx # fs points to local data space
mov %dx,%fs
pushl %eax #by wyj
call print_nr
popl %eax
call sys_call_table(,%eax,4)
pushl %eax
movl current,%eax
cmpl $0,state(%eax) # state
jne reschedule
cmpl $0,counter(%eax) # counter
je reschedule
ret_from_sys_call:
movl current,%eax # task[0] cannot have signals
cmpl task,%eax
je 3f
cmpw $0x0f,CS(%esp) # was old code segment supervisor ?
jne 3f
cmpw $0x17,OLDSS(%esp) # was stack segment = 0x17 ?
jne 3f
movl signal(%eax),%ebx
movl blocked(%eax),%ecx
notl %ecx
andl %ebx,%ecx
bsfl %ecx,%ecx
je 3f
btrl %ecx,%ebx
movl %ebx,signal(%eax)
incl %ecx
pushl %ecx
call do_signal
popl %eax
3: popl %eax
popl %ebx
popl %ecx
popl %edx
pop %fs
pop %es
pop %ds
iret
.align 4
coprocessor_error:
push %ds
push %es
push %fs
pushl %edx
pushl %ecx
pushl %ebx
pushl %eax
movl $0x10,%eax
mov %ax,%ds
mov %ax,%es
movl $0x17,%eax
mov %ax,%fs
pushl $ret_from_sys_call
jmp math_error
.align 2
device_not_available:
push %ds
push %es
push %fs
pushl %edx
pushl %ecx
pushl %ebx
pushl %eax
movl $0x10,%eax
mov %ax,%ds
mov %ax,%es
movl $0x17,%eax
mov %ax,%fs
pushl $ret_from_sys_call
clts # clear TS so that we can use math
movl %cr0,%eax
testl $0x4,%eax # EM (math emulation bit)
je math_state_restore
pushl %ebp
pushl %esi
pushl %edi
call math_emulate
popl %edi
popl %esi
popl %ebp
ret
.align 4
timer_interrupt:
push %ds # save ds,es and put kernel data space
push %es # into them. %fs is used by _system_call
push %fs
pushl %edx # we save %eax,%ecx,%edx as gcc doesn't
pushl %ecx # save those across function calls. %ebx
pushl %ebx # is saved as we use that in ret_sys_call
pushl %eax
movl $0x10,%eax
mov %ax,%ds
mov %ax,%es
movl $0x17,%eax
mov %ax,%fs
incl jiffies
movb $0x20,%al # EOI to interrupt controller #1
outb %al,$0x20
movl CS(%esp),%eax
andl $3,%eax # %eax is CPL (0 or 3, 0=supervisor)
pushl %eax
call do_timer # 'do_timer(long CPL)' does everything from
addl $4,%esp # task switching to accounting ...
jmp ret_from_sys_call
.align 4
sys_execve:
lea EIP(%esp),%eax
pushl %eax
call do_execve
addl $4,%esp
ret
.align 4
sys_execve2:
lea EIP(%esp),%eax
pushl %eax
call do_execve2
addl $4,%esp
ret
.align 4
sys_fork:
call find_empty_process
testl %eax,%eax
js 1f
push %gs
pushl %esi
pushl %edi
pushl %ebp
pushl %eax
call copy_process
addl $20,%esp
1: ret
hd_interrupt:
pushl %eax
pushl %ecx
pushl %edx
push %ds
push %es
push %fs
movl $0x10,%eax
mov %ax,%ds
mov %ax,%es
movl $0x17,%eax
mov %ax,%fs
movb $0x20,%al
outb %al,$0xA0 # EOI to interrupt controller #1
jmp 1f # give port chance to breathe
1: jmp 1f
1: xorl %edx,%edx
xchgl do_hd,%edx
testl %edx,%edx
jne 1f
movl $unexpected_hd_interrupt,%edx
1: outb %al,$0x20
call *%edx # "interesting" way of handling intr.
pop %fs
pop %es
pop %ds
popl %edx
popl %ecx
popl %eax
iret
floppy_interrupt:
pushl %eax
pushl %ecx
pushl %edx
push %ds
push %es
push %fs
movl $0x10,%eax
mov %ax,%ds
mov %ax,%es
movl $0x17,%eax
mov %ax,%fs
movb $0x20,%al
outb %al,$0x20 # EOI to interrupt controller #1
xorl %eax,%eax
xchgl do_floppy,%eax
testl %eax,%eax
jne 1f
movl $unexpected_floppy_interrupt,%eax
1: call *%eax # "interesting" way of handling intr.
pop %fs
pop %es
pop %ds
popl %edx
popl %ecx
popl %eax
iret
parallel_interrupt:
pushl %eax
movb $0x20,%al
outb %al,$0x20
popl %eax
iret
Loading…
Cancel
Save