2006-01-08 17:01:31 +08:00
|
|
|
/*
|
2005-04-17 06:20:36 +08:00
|
|
|
* Copyright (C) 2000, 2002 Jeff Dike (jdike@karaya.com)
|
|
|
|
* Licensed under the GPL
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include "linux/kernel.h"
|
|
|
|
#include "linux/sched.h"
|
|
|
|
#include "linux/notifier.h"
|
|
|
|
#include "linux/mm.h"
|
|
|
|
#include "linux/types.h"
|
|
|
|
#include "linux/tty.h"
|
|
|
|
#include "linux/init.h"
|
|
|
|
#include "linux/bootmem.h"
|
|
|
|
#include "linux/spinlock.h"
|
|
|
|
#include "linux/utsname.h"
|
|
|
|
#include "linux/sysrq.h"
|
|
|
|
#include "linux/seq_file.h"
|
|
|
|
#include "linux/delay.h"
|
|
|
|
#include "linux/module.h"
|
2007-05-07 05:50:59 +08:00
|
|
|
#include "linux/utsname.h"
|
2005-04-17 06:20:36 +08:00
|
|
|
#include "asm/page.h"
|
|
|
|
#include "asm/pgtable.h"
|
|
|
|
#include "asm/ptrace.h"
|
|
|
|
#include "asm/elf.h"
|
|
|
|
#include "asm/user.h"
|
2005-05-07 12:30:45 +08:00
|
|
|
#include "asm/setup.h"
|
2005-04-17 06:20:36 +08:00
|
|
|
#include "ubd_user.h"
|
|
|
|
#include "asm/current.h"
|
|
|
|
#include "kern_util.h"
|
2007-05-07 05:51:08 +08:00
|
|
|
#include "as-layout.h"
|
2007-05-07 05:51:07 +08:00
|
|
|
#include "arch.h"
|
2005-04-17 06:20:36 +08:00
|
|
|
#include "kern.h"
|
|
|
|
#include "mem_user.h"
|
|
|
|
#include "mem.h"
|
|
|
|
#include "initrd.h"
|
|
|
|
#include "init.h"
|
|
|
|
#include "os.h"
|
2005-07-28 02:43:31 +08:00
|
|
|
#include "skas.h"
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#define DEFAULT_COMMAND_LINE "root=98:0"
|
|
|
|
|
2007-05-07 05:51:26 +08:00
|
|
|
/* Changed in add_arg and setup_arch, which run before SMP is started */
|
2007-02-12 16:54:26 +08:00
|
|
|
static char __initdata command_line[COMMAND_LINE_SIZE] = { 0 };
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-02-12 16:54:26 +08:00
|
|
|
static void __init add_arg(char *arg)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
if (strlen(command_line) + strlen(arg) + 1 > COMMAND_LINE_SIZE) {
|
|
|
|
printf("add_arg: Too many command line arguments!\n");
|
|
|
|
exit(1);
|
|
|
|
}
|
|
|
|
if(strlen(command_line) > 0)
|
|
|
|
strcat(command_line, " ");
|
|
|
|
strcat(command_line, arg);
|
|
|
|
}
|
|
|
|
|
2007-05-07 05:51:26 +08:00
|
|
|
/*
|
|
|
|
* These fields are initialized at boot time and not changed.
|
|
|
|
* XXX This structure is used only in the non-SMP case. Maybe this
|
|
|
|
* should be moved to smp.c.
|
|
|
|
*/
|
|
|
|
struct cpuinfo_um boot_cpu_data = {
|
2005-04-17 06:20:36 +08:00
|
|
|
.loops_per_jiffy = 0,
|
|
|
|
.ipi_pipe = { -1, -1 }
|
|
|
|
};
|
|
|
|
|
|
|
|
unsigned long thread_saved_pc(struct task_struct *task)
|
|
|
|
{
|
2007-10-16 16:26:58 +08:00
|
|
|
/* FIXME: Need to look up userspace_pid by cpu */
|
|
|
|
return os_process_pc(userspace_pid[0]);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2007-05-07 05:50:59 +08:00
|
|
|
/* Changed in setup_arch, which is called in early boot */
|
|
|
|
static char host_info[(__NEW_UTS_LEN + 1) * 5];
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
static int show_cpuinfo(struct seq_file *m, void *v)
|
|
|
|
{
|
|
|
|
int index = 0;
|
|
|
|
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
index = (struct cpuinfo_um *) v - cpu_data;
|
|
|
|
if (!cpu_online(index))
|
|
|
|
return 0;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
seq_printf(m, "processor\t: %d\n", index);
|
|
|
|
seq_printf(m, "vendor_id\t: User Mode Linux\n");
|
|
|
|
seq_printf(m, "model name\t: UML\n");
|
2007-10-16 16:26:56 +08:00
|
|
|
seq_printf(m, "mode\t\t: skas\n");
|
2005-04-17 06:20:36 +08:00
|
|
|
seq_printf(m, "host\t\t: %s\n", host_info);
|
|
|
|
seq_printf(m, "bogomips\t: %lu.%02lu\n\n",
|
|
|
|
loops_per_jiffy/(500000/HZ),
|
|
|
|
(loops_per_jiffy/(5000/HZ)) % 100);
|
|
|
|
|
2007-05-07 05:50:58 +08:00
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void *c_start(struct seq_file *m, loff_t *pos)
|
|
|
|
{
|
|
|
|
return *pos < NR_CPUS ? cpu_data + *pos : NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void *c_next(struct seq_file *m, void *v, loff_t *pos)
|
|
|
|
{
|
|
|
|
++*pos;
|
|
|
|
return c_start(m, pos);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void c_stop(struct seq_file *m, void *v)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2006-09-27 16:50:33 +08:00
|
|
|
const struct seq_operations cpuinfo_op = {
|
2005-04-17 06:20:36 +08:00
|
|
|
.start = c_start,
|
|
|
|
.next = c_next,
|
|
|
|
.stop = c_stop,
|
|
|
|
.show = show_cpuinfo,
|
|
|
|
};
|
|
|
|
|
|
|
|
/* Set in linux_main */
|
|
|
|
unsigned long host_task_size;
|
|
|
|
unsigned long task_size;
|
|
|
|
unsigned long uml_physmem;
|
2007-05-07 05:51:26 +08:00
|
|
|
unsigned long uml_reserved; /* Also modified in mem_init */
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned long start_vm;
|
|
|
|
unsigned long end_vm;
|
2007-05-07 05:51:26 +08:00
|
|
|
|
|
|
|
/* Set in uml_ncpus_setup */
|
2005-04-17 06:20:36 +08:00
|
|
|
int ncpus = 1;
|
|
|
|
|
|
|
|
/* Set in early boot */
|
|
|
|
static int have_root __initdata = 0;
|
2007-05-07 05:51:26 +08:00
|
|
|
|
|
|
|
/* Set in uml_mem_setup and modified in linux_main */
|
2005-11-07 16:58:57 +08:00
|
|
|
long long physmem_size = 32 * 1024 * 1024;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
static char *usage_string =
|
|
|
|
"User Mode Linux v%s\n"
|
|
|
|
" available at http://user-mode-linux.sourceforge.net/\n\n";
|
|
|
|
|
|
|
|
static int __init uml_version_setup(char *line, int *add)
|
|
|
|
{
|
2006-10-02 17:18:13 +08:00
|
|
|
printf("%s\n", init_utsname()->release);
|
2005-04-17 06:20:36 +08:00
|
|
|
exit(0);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
__uml_setup("--version", uml_version_setup,
|
|
|
|
"--version\n"
|
|
|
|
" Prints the version number of the kernel.\n\n"
|
|
|
|
);
|
|
|
|
|
|
|
|
static int __init uml_root_setup(char *line, int *add)
|
|
|
|
{
|
|
|
|
have_root = 1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
__uml_setup("root=", uml_root_setup,
|
|
|
|
"root=<file containing the root fs>\n"
|
|
|
|
" This is actually used by the generic kernel in exactly the same\n"
|
|
|
|
" way as in any other kernel. If you configure a number of block\n"
|
|
|
|
" devices and want to boot off something other than ubd0, you \n"
|
|
|
|
" would use something like:\n"
|
|
|
|
" root=/dev/ubd5\n\n"
|
|
|
|
);
|
|
|
|
|
2006-02-08 04:58:40 +08:00
|
|
|
static int __init no_skas_debug_setup(char *line, int *add)
|
|
|
|
{
|
|
|
|
printf("'debug' is not necessary to gdb UML in skas mode - run \n");
|
uml: throw out CONFIG_MODE_TT
This patchset throws out tt mode, which has been non-functional for a while.
This is done in phases, interspersed with code cleanups on the affected files.
The removal is done as follows:
remove all code, config options, and files which depend on
CONFIG_MODE_TT
get rid of the CHOOSE_MODE macro, which decided whether to
call tt-mode or skas-mode code, and replace invocations with their
skas portions
replace all now-trivial procedures with their skas equivalents
There are now a bunch of now-redundant pieces of data structures, including
mode-specific pieces of the thread structure, pt_regs, and mm_context. These
are all replaced with their skas-specific contents.
As part of the ongoing style compliance project, I made a style pass over all
files that were changed. There are three such patches, one for each phase,
covering the files affected by that phase but no later ones.
I noticed that we weren't freeing the LDT state associated with a process when
it exited, so that's fixed in one of the later patches.
The last patch is a tidying patch which I've had for a while, but which caused
inexplicable crashes under tt mode. Since that is no longer a problem, this
can now go in.
This patch:
Start getting rid of tt mode support.
This patch throws out CONFIG_MODE_TT and all config options, code, and files
which depend on it.
CONFIG_MODE_SKAS is gone and everything that depends on it is included
unconditionally.
The few changed lines are in re-written Kconfig help, lines which needed
something skas-related removed from them, and a few more which weren't
strictly deletions.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:26:50 +08:00
|
|
|
printf("'gdb linux'");
|
2006-02-08 04:58:40 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
__uml_setup("debug", no_skas_debug_setup,
|
|
|
|
"debug\n"
|
|
|
|
" this flag is not needed to run gdb on UML in skas mode\n\n"
|
|
|
|
);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
static int __init uml_ncpus_setup(char *line, int *add)
|
|
|
|
{
|
2007-05-07 05:50:58 +08:00
|
|
|
if (!sscanf(line, "%d", &ncpus)) {
|
|
|
|
printf("Couldn't parse [%s]\n", line);
|
|
|
|
return -1;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-05-07 05:50:58 +08:00
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
__uml_setup("ncpus=", uml_ncpus_setup,
|
|
|
|
"ncpus=<# of desired CPUs>\n"
|
|
|
|
" This tells an SMP kernel how many virtual processors to start.\n\n"
|
|
|
|
);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
static int __init Usage(char *line, int *add)
|
|
|
|
{
|
2007-05-07 05:50:58 +08:00
|
|
|
const char **p;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-10-02 17:18:13 +08:00
|
|
|
printf(usage_string, init_utsname()->release);
|
2007-05-07 05:50:58 +08:00
|
|
|
p = &__uml_help_start;
|
|
|
|
while (p < &__uml_help_end) {
|
|
|
|
printf("%s", *p);
|
|
|
|
p++;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
exit(0);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
__uml_setup("--help", Usage,
|
|
|
|
"--help\n"
|
|
|
|
" Prints this message.\n\n"
|
|
|
|
);
|
|
|
|
|
|
|
|
static int __init uml_checksetup(char *line, int *add)
|
|
|
|
{
|
|
|
|
struct uml_param *p;
|
|
|
|
|
|
|
|
p = &__uml_setup_start;
|
|
|
|
while(p < &__uml_setup_end) {
|
|
|
|
int n;
|
|
|
|
|
|
|
|
n = strlen(p->str);
|
|
|
|
if(!strncmp(line, p->str, n)){
|
|
|
|
if (p->setup_func(line + n, add)) return 1;
|
|
|
|
}
|
|
|
|
p++;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __init uml_postsetup(void)
|
|
|
|
{
|
|
|
|
initcall_t *p;
|
|
|
|
|
|
|
|
p = &__uml_postsetup_start;
|
|
|
|
while(p < &__uml_postsetup_end){
|
|
|
|
(*p)();
|
|
|
|
p++;
|
|
|
|
}
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Set during early boot */
|
|
|
|
unsigned long brk_start;
|
|
|
|
unsigned long end_iomem;
|
|
|
|
EXPORT_SYMBOL(end_iomem);
|
|
|
|
|
|
|
|
#define MIN_VMALLOC (32 * 1024 * 1024)
|
|
|
|
|
2006-07-10 19:45:06 +08:00
|
|
|
extern char __binary_start;
|
|
|
|
|
2007-10-16 16:26:58 +08:00
|
|
|
static unsigned long set_task_sizes_skas(unsigned long *task_size_out)
|
|
|
|
{
|
|
|
|
/* Round up to the nearest 4M */
|
|
|
|
unsigned long host_task_size = ROUND_4M((unsigned long)
|
|
|
|
&host_task_size);
|
|
|
|
|
|
|
|
if (!skas_needs_stub)
|
|
|
|
*task_size_out = host_task_size;
|
|
|
|
else *task_size_out = CONFIG_STUB_START & PGDIR_MASK;
|
|
|
|
|
|
|
|
return host_task_size;
|
|
|
|
}
|
|
|
|
|
2007-02-12 16:54:26 +08:00
|
|
|
int __init linux_main(int argc, char **argv)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
unsigned long avail, diff;
|
|
|
|
unsigned long virtmem_size, max_physmem;
|
|
|
|
unsigned int i, add;
|
2005-07-28 02:43:31 +08:00
|
|
|
char * mode;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
for (i = 1; i < argc; i++){
|
|
|
|
if((i == 1) && (argv[i][0] == ' ')) continue;
|
|
|
|
add = 1;
|
|
|
|
uml_checksetup(argv[i], &add);
|
|
|
|
if (add)
|
|
|
|
add_arg(argv[i]);
|
|
|
|
}
|
|
|
|
if(have_root == 0)
|
|
|
|
add_arg(DEFAULT_COMMAND_LINE);
|
|
|
|
|
2005-09-04 06:57:47 +08:00
|
|
|
os_early_checks();
|
2005-07-28 02:43:31 +08:00
|
|
|
|
uml: throw out CONFIG_MODE_TT
This patchset throws out tt mode, which has been non-functional for a while.
This is done in phases, interspersed with code cleanups on the affected files.
The removal is done as follows:
remove all code, config options, and files which depend on
CONFIG_MODE_TT
get rid of the CHOOSE_MODE macro, which decided whether to
call tt-mode or skas-mode code, and replace invocations with their
skas portions
replace all now-trivial procedures with their skas equivalents
There are now a bunch of now-redundant pieces of data structures, including
mode-specific pieces of the thread structure, pt_regs, and mm_context. These
are all replaced with their skas-specific contents.
As part of the ongoing style compliance project, I made a style pass over all
files that were changed. There are three such patches, one for each phase,
covering the files affected by that phase but no later ones.
I noticed that we weren't freeing the LDT state associated with a process when
it exited, so that's fixed in one of the later patches.
The last patch is a tidying patch which I've had for a while, but which caused
inexplicable crashes under tt mode. Since that is no longer a problem, this
can now go in.
This patch:
Start getting rid of tt mode support.
This patch throws out CONFIG_MODE_TT and all config options, code, and files
which depend on it.
CONFIG_MODE_SKAS is gone and everything that depends on it is included
unconditionally.
The few changed lines are in re-written Kconfig help, lines which needed
something skas-related removed from them, and a few more which weren't
strictly deletions.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:26:50 +08:00
|
|
|
can_do_skas();
|
|
|
|
|
|
|
|
if (proc_mm && ptrace_faultinfo)
|
2005-07-28 02:43:31 +08:00
|
|
|
mode = "SKAS3";
|
|
|
|
else
|
|
|
|
mode = "SKAS0";
|
|
|
|
|
|
|
|
printf("UML running in %s mode\n", mode);
|
|
|
|
|
2007-10-16 16:26:56 +08:00
|
|
|
host_task_size = set_task_sizes_skas(&task_size);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-01-08 17:01:31 +08:00
|
|
|
/*
|
2007-05-07 05:50:58 +08:00
|
|
|
* Setting up handlers to 'sig_info' struct
|
|
|
|
*/
|
2006-01-08 17:01:31 +08:00
|
|
|
os_fill_handlinfo(handlinfo_kern);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
brk_start = (unsigned long) sbrk(0);
|
2007-10-16 16:26:58 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Increase physical memory size for exec-shield users
|
|
|
|
so they actually get what they asked for. This should
|
|
|
|
add zero for non-exec shield users */
|
|
|
|
|
|
|
|
diff = UML_ROUND_UP(brk_start) - UML_ROUND_UP(&_end);
|
|
|
|
if(diff > 1024 * 1024){
|
|
|
|
printf("Adding %ld bytes to physical memory to account for "
|
|
|
|
"exec-shield gap\n", diff);
|
|
|
|
physmem_size += UML_ROUND_UP(brk_start) - UML_ROUND_UP(&_end);
|
|
|
|
}
|
|
|
|
|
2007-05-07 05:51:26 +08:00
|
|
|
uml_physmem = (unsigned long) &__binary_start & PAGE_MASK;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* Reserve up to 4M after the current brk */
|
|
|
|
uml_reserved = ROUND_4M(brk_start) + (1 << 22);
|
|
|
|
|
2006-10-02 17:18:13 +08:00
|
|
|
setup_machinename(init_utsname()->machine);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
highmem = 0;
|
|
|
|
iomem_size = (iomem_size + PAGE_SIZE - 1) & PAGE_MASK;
|
|
|
|
max_physmem = get_kmem_end() - uml_physmem - iomem_size - MIN_VMALLOC;
|
|
|
|
|
|
|
|
/* Zones have to begin on a 1 << MAX_ORDER page boundary,
|
|
|
|
* so this makes sure that's true for highmem
|
|
|
|
*/
|
|
|
|
max_physmem &= ~((1 << (PAGE_SHIFT + MAX_ORDER)) - 1);
|
|
|
|
if(physmem_size + iomem_size > max_physmem){
|
|
|
|
highmem = physmem_size + iomem_size - max_physmem;
|
|
|
|
physmem_size -= highmem;
|
|
|
|
#ifndef CONFIG_HIGHMEM
|
|
|
|
highmem = 0;
|
|
|
|
printf("CONFIG_HIGHMEM not enabled - physical memory shrunk "
|
2006-03-27 17:14:29 +08:00
|
|
|
"to %Lu bytes\n", physmem_size);
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
high_physmem = uml_physmem + physmem_size;
|
|
|
|
end_iomem = high_physmem + iomem_size;
|
|
|
|
high_memory = (void *) end_iomem;
|
|
|
|
|
|
|
|
start_vm = VMALLOC_START;
|
|
|
|
|
|
|
|
setup_physmem(uml_physmem, uml_reserved, physmem_size, highmem);
|
|
|
|
if(init_maps(physmem_size, iomem_size, highmem)){
|
2006-03-27 17:14:29 +08:00
|
|
|
printf("Failed to allocate mem_map for %Lu bytes of physical "
|
|
|
|
"memory and %Lu bytes of highmem\n", physmem_size,
|
2005-04-17 06:20:36 +08:00
|
|
|
highmem);
|
|
|
|
exit(1);
|
|
|
|
}
|
|
|
|
|
|
|
|
virtmem_size = physmem_size;
|
|
|
|
avail = get_kmem_end() - start_vm;
|
|
|
|
if(physmem_size > avail) virtmem_size = avail;
|
|
|
|
end_vm = start_vm + virtmem_size;
|
|
|
|
|
|
|
|
if(virtmem_size < physmem_size)
|
2005-11-07 16:58:57 +08:00
|
|
|
printf("Kernel virtual memory size shrunk to %lu bytes\n",
|
2005-04-17 06:20:36 +08:00
|
|
|
virtmem_size);
|
|
|
|
|
2007-05-07 05:50:58 +08:00
|
|
|
uml_postsetup();
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-05-11 13:22:30 +08:00
|
|
|
stack_protections((unsigned long) &init_thread_info);
|
2005-04-17 06:20:36 +08:00
|
|
|
os_flush_stdout();
|
|
|
|
|
2007-10-16 16:26:58 +08:00
|
|
|
return start_uml();
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
extern int uml_exitcode;
|
|
|
|
|
|
|
|
static int panic_exit(struct notifier_block *self, unsigned long unused1,
|
|
|
|
void *unused2)
|
|
|
|
{
|
|
|
|
bust_spinlocks(1);
|
|
|
|
show_regs(&(current->thread.regs));
|
|
|
|
bust_spinlocks(0);
|
|
|
|
uml_exitcode = 1;
|
2007-05-07 05:51:39 +08:00
|
|
|
os_dump_core();
|
2007-05-07 05:50:58 +08:00
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static struct notifier_block panic_exit_notifier = {
|
|
|
|
.notifier_call = panic_exit,
|
|
|
|
.next = NULL,
|
|
|
|
.priority = 0
|
|
|
|
};
|
|
|
|
|
|
|
|
void __init setup_arch(char **cmdline_p)
|
|
|
|
{
|
[PATCH] Notifier chain update: API changes
The kernel's implementation of notifier chains is unsafe. There is no
protection against entries being added to or removed from a chain while the
chain is in use. The issues were discussed in this thread:
http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2
We noticed that notifier chains in the kernel fall into two basic usage
classes:
"Blocking" chains are always called from a process context
and the callout routines are allowed to sleep;
"Atomic" chains can be called from an atomic context and
the callout routines are not allowed to sleep.
We decided to codify this distinction and make it part of the API. Therefore
this set of patches introduces three new, parallel APIs: one for blocking
notifiers, one for atomic notifiers, and one for "raw" notifiers (which is
really just the old API under a new name). New kinds of data structures are
used for the heads of the chains, and new routines are defined for
registration, unregistration, and calling a chain. The three APIs are
explained in include/linux/notifier.h and their implementation is in
kernel/sys.c.
With atomic and blocking chains, the implementation guarantees that the chain
links will not be corrupted and that chain callers will not get messed up by
entries being added or removed. For raw chains the implementation provides no
guarantees at all; users of this API must provide their own protections. (The
idea was that situations may come up where the assumptions of the atomic and
blocking APIs are not appropriate, so it should be possible for users to
handle these things in their own way.)
There are some limitations, which should not be too hard to live with. For
atomic/blocking chains, registration and unregistration must always be done in
a process context since the chain is protected by a mutex/rwsem. Also, a
callout routine for a non-raw chain must not try to register or unregister
entries on its own chain. (This did happen in a couple of places and the code
had to be changed to avoid it.)
Since atomic chains may be called from within an NMI handler, they cannot use
spinlocks for synchronization. Instead we use RCU. The overhead falls almost
entirely in the unregister routine, which is okay since unregistration is much
less frequent that calling a chain.
Here is the list of chains that we adjusted and their classifications. None
of them use the raw API, so for the moment it is only a placeholder.
ATOMIC CHAINS
-------------
arch/i386/kernel/traps.c: i386die_chain
arch/ia64/kernel/traps.c: ia64die_chain
arch/powerpc/kernel/traps.c: powerpc_die_chain
arch/sparc64/kernel/traps.c: sparc64die_chain
arch/x86_64/kernel/traps.c: die_chain
drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list
kernel/panic.c: panic_notifier_list
kernel/profile.c: task_free_notifier
net/bluetooth/hci_core.c: hci_notifier
net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain
net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain
net/ipv6/addrconf.c: inet6addr_chain
net/netfilter/nf_conntrack_core.c: nf_conntrack_chain
net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain
net/netlink/af_netlink.c: netlink_chain
BLOCKING CHAINS
---------------
arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain
arch/s390/kernel/process.c: idle_chain
arch/x86_64/kernel/process.c idle_notifier
drivers/base/memory.c: memory_chain
drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list
drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list
drivers/macintosh/adb.c: adb_client_list
drivers/macintosh/via-pmu.c sleep_notifier_list
drivers/macintosh/via-pmu68k.c sleep_notifier_list
drivers/macintosh/windfarm_core.c wf_client_list
drivers/usb/core/notify.c usb_notifier_list
drivers/video/fbmem.c fb_notifier_list
kernel/cpu.c cpu_chain
kernel/module.c module_notify_list
kernel/profile.c munmap_notifier
kernel/profile.c task_exit_notifier
kernel/sys.c reboot_notifier_list
net/core/dev.c netdev_chain
net/decnet/dn_dev.c: dnaddr_chain
net/ipv4/devinet.c: inetaddr_chain
It's possible that some of these classifications are wrong. If they are,
please let us know or submit a patch to fix them. Note that any chain that
gets called very frequently should be atomic, because the rwsem read-locking
used for blocking chains is very likely to incur cache misses on SMP systems.
(However, if the chain's callout routines may sleep then the chain cannot be
atomic.)
The patch set was written by Alan Stern and Chandra Seetharaman, incorporating
material written by Keith Owens and suggestions from Paul McKenney and Andrew
Morton.
[jes@sgi.com: restructure the notifier chain initialization macros]
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com>
Signed-off-by: Jes Sorensen <jes@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 17:16:30 +08:00
|
|
|
atomic_notifier_chain_register(&panic_notifier_list,
|
|
|
|
&panic_exit_notifier);
|
2005-04-17 06:20:36 +08:00
|
|
|
paging_init();
|
2007-02-12 16:54:23 +08:00
|
|
|
strlcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
|
2007-05-07 05:50:58 +08:00
|
|
|
*cmdline_p = command_line;
|
2007-05-07 05:50:59 +08:00
|
|
|
setup_hostinfo(host_info, sizeof host_info);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
void __init check_bugs(void)
|
|
|
|
{
|
|
|
|
arch_check_bugs();
|
2007-05-07 05:50:58 +08:00
|
|
|
os_check_bugs();
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2006-03-23 18:59:32 +08:00
|
|
|
void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2006-07-03 15:24:09 +08:00
|
|
|
#ifdef CONFIG_SMP
|
2006-03-23 18:59:32 +08:00
|
|
|
void alternatives_smp_module_add(struct module *mod, char *name,
|
|
|
|
void *locks, void *locks_end,
|
|
|
|
void *text, void *text_end)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
void alternatives_smp_module_del(struct module *mod)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
}
|
2006-07-03 15:24:09 +08:00
|
|
|
#endif
|