linux-sg2042/kernel/kmod.c

351 lines
9.5 KiB
C
Raw Normal View History

/*
kmod, the new module loader (replaces kerneld)
Kirk Petersen
Reorganized not to be a daemon by Adam Richter, with guidance
from Greg Zornetzer.
Modified to avoid chroot and file sharing problems.
Mikael Pettersson
Limit the concurrent number of kmod modprobes to catch loops from
"modprobe needs a service that is in a module".
Keith Owens <kaos@ocs.com.au> December 1999
Unblock all signals when we exec a usermode process.
Shuu Yamaguchi <shuu@wondernetworkresources.com> December 2000
call_usermodehelper wait flag, and remove exec_usermodehelper.
Rusty Russell <rusty@rustcorp.com.au> Jan 2003
*/
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/syscalls.h>
#include <linux/unistd.h>
#include <linux/kmod.h>
#include <linux/slab.h>
#include <linux/mnt_namespace.h>
#include <linux/completion.h>
#include <linux/file.h>
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/kernel.h>
#include <linux/init.h>
[PATCH] Support piping into commands in /proc/sys/kernel/core_pattern Using the infrastructure created in previous patches implement support to pipe core dumps into programs. This is done by overloading the existing core_pattern sysctl with a new syntax: |program When the first character of the pattern is a '|' the kernel will instead threat the rest of the pattern as a command to run. The core dump will be written to the standard input of that program instead of to a file. This is useful for having automatic core dump analysis without filling up disks. The program can do some simple analysis and save only a summary of the core dump. The core dump proces will run with the privileges and in the name space of the process that caused the core dump. I also increased the core pattern size to 128 bytes so that longer command lines fit. Most of the changes comes from allowing core dumps without seeks. They are fairly straight forward though. One small incompatibility is that if someone had a core pattern previously that started with '|' they will get suddenly new behaviour. I think that's unlikely to be a real problem though. Additional background: > Very nice, do you happen to have a program that can accept this kind of > input for crash dumps? I'm guessing that the embedded people will > really want this functionality. I had a cheesy demo/prototype. Basically it wrote the dump to a file again, ran gdb on it to get a backtrace and wrote the summary to a shared directory. Then there was a simple CGI script to generate a "top 10" crashes HTML listing. Unfortunately this still had the disadvantage to needing full disk space for a dump except for deleting it afterwards (in fact it was worse because over the pipe holes didn't work so if you have a holey address map it would require more space). Fortunately gdb seems to be happy to handle /proc/pid/fd/xxx input pipes as cores (at least it worked with zsh's =(cat core) syntax), so it would be likely possible to do it without temporary space with a simple wrapper that calls it in the right way. I ran out of time before doing that though. The demo prototype scripts weren't very good. If there is really interest I can dig them out (they are currently on a laptop disk on the desk with the laptop itself being in service), but I would recommend to rewrite them for any serious application of this and fix the disk space problem. Also to be really useful it should probably find a way to automatically fetch the debuginfos (I cheated and just installed them in advance). If nobody else does it I can probably do the rewrite myself again at some point. My hope at some point was that desktops would support it in their builtin crash reporters, but at least the KDE people I talked too seemed to be happy with their user space only solution. Alan sayeth: I don't believe that piping as such as neccessarily the right model, but the ability to intercept and processes core dumps from user space is asked for by many enterprise users as well. They want to know about, capture, analyse and process core dumps, often centrally and in automated form. [akpm@osdl.org: loff_t != unsigned long] Signed-off-by: Andi Kleen <ak@suse.de> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-01 14:29:28 +08:00
#include <linux/resource.h>
#include <asm/uaccess.h>
extern int max_threads;
static struct workqueue_struct *khelper_wq;
#ifdef CONFIG_KMOD
/*
modprobe_path is set via /proc/sys.
*/
char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe";
/**
* request_module - try to load a kernel module
* @fmt: printf style format string for the name of the module
* @varargs: arguements as specified in the format string
*
* Load a module using the user mode module loader. The function returns
* zero on success or a negative errno code on failure. Note that a
* successful module load does not mean the module did not then unload
* and exit on an error of its own. Callers must check that the service
* they requested is now available not blindly invoke it.
*
* If module auto-loading support is disabled then this function
* becomes a no-operation.
*/
int request_module(const char *fmt, ...)
{
va_list args;
char module_name[MODULE_NAME_LEN];
unsigned int max_modprobes;
int ret;
char *argv[] = { modprobe_path, "-q", "--", module_name, NULL };
static char *envp[] = { "HOME=/",
"TERM=linux",
"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
NULL };
static atomic_t kmod_concurrent = ATOMIC_INIT(0);
#define MAX_KMOD_CONCURRENT 50 /* Completely arbitrary value - KAO */
static int kmod_loop_msg;
va_start(args, fmt);
ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
va_end(args);
if (ret >= MODULE_NAME_LEN)
return -ENAMETOOLONG;
/* If modprobe needs a service that is in a module, we get a recursive
* loop. Limit the number of running kmod threads to max_threads/2 or
* MAX_KMOD_CONCURRENT, whichever is the smaller. A cleaner method
* would be to run the parents of this process, counting how many times
* kmod was invoked. That would mean accessing the internals of the
* process tables to get the command line, proc_pid_cmdline is static
* and it is not worth changing the proc code just to handle this case.
* KAO.
*
* "trace the ppid" is simple, but will fail if someone's
* parent exits. I think this is as good as it gets. --RR
*/
max_modprobes = min(max_threads/2, MAX_KMOD_CONCURRENT);
atomic_inc(&kmod_concurrent);
if (atomic_read(&kmod_concurrent) > max_modprobes) {
/* We may be blaming an innocent here, but unlikely */
if (kmod_loop_msg++ < 5)
printk(KERN_ERR
"request_module: runaway loop modprobe %s\n",
module_name);
atomic_dec(&kmod_concurrent);
return -ENOMEM;
}
ret = call_usermodehelper(modprobe_path, argv, envp, 1);
atomic_dec(&kmod_concurrent);
return ret;
}
EXPORT_SYMBOL(request_module);
#endif /* CONFIG_KMOD */
struct subprocess_info {
2006-11-22 22:55:48 +08:00
struct work_struct work;
struct completion *complete;
char *path;
char **argv;
char **envp;
struct key *ring;
int wait;
int retval;
struct file *stdin;
};
/*
* This is the task which runs the usermode application
*/
static int ____call_usermodehelper(void *data)
{
struct subprocess_info *sub_info = data;
struct key *new_session, *old_session;
int retval;
/* Unblock all signals and set the session keyring. */
new_session = key_get(sub_info->ring);
spin_lock_irq(&current->sighand->siglock);
old_session = __install_session_keyring(current, new_session);
flush_signal_handlers(current, 1);
sigemptyset(&current->blocked);
recalc_sigpending();
spin_unlock_irq(&current->sighand->siglock);
key_put(old_session);
/* Install input pipe when needed */
if (sub_info->stdin) {
struct files_struct *f = current->files;
struct fdtable *fdt;
/* no races because files should be private here */
sys_close(0);
fd_install(0, sub_info->stdin);
spin_lock(&f->file_lock);
fdt = files_fdtable(f);
FD_SET(0, fdt->open_fds);
FD_CLR(0, fdt->close_on_exec);
spin_unlock(&f->file_lock);
[PATCH] Support piping into commands in /proc/sys/kernel/core_pattern Using the infrastructure created in previous patches implement support to pipe core dumps into programs. This is done by overloading the existing core_pattern sysctl with a new syntax: |program When the first character of the pattern is a '|' the kernel will instead threat the rest of the pattern as a command to run. The core dump will be written to the standard input of that program instead of to a file. This is useful for having automatic core dump analysis without filling up disks. The program can do some simple analysis and save only a summary of the core dump. The core dump proces will run with the privileges and in the name space of the process that caused the core dump. I also increased the core pattern size to 128 bytes so that longer command lines fit. Most of the changes comes from allowing core dumps without seeks. They are fairly straight forward though. One small incompatibility is that if someone had a core pattern previously that started with '|' they will get suddenly new behaviour. I think that's unlikely to be a real problem though. Additional background: > Very nice, do you happen to have a program that can accept this kind of > input for crash dumps? I'm guessing that the embedded people will > really want this functionality. I had a cheesy demo/prototype. Basically it wrote the dump to a file again, ran gdb on it to get a backtrace and wrote the summary to a shared directory. Then there was a simple CGI script to generate a "top 10" crashes HTML listing. Unfortunately this still had the disadvantage to needing full disk space for a dump except for deleting it afterwards (in fact it was worse because over the pipe holes didn't work so if you have a holey address map it would require more space). Fortunately gdb seems to be happy to handle /proc/pid/fd/xxx input pipes as cores (at least it worked with zsh's =(cat core) syntax), so it would be likely possible to do it without temporary space with a simple wrapper that calls it in the right way. I ran out of time before doing that though. The demo prototype scripts weren't very good. If there is really interest I can dig them out (they are currently on a laptop disk on the desk with the laptop itself being in service), but I would recommend to rewrite them for any serious application of this and fix the disk space problem. Also to be really useful it should probably find a way to automatically fetch the debuginfos (I cheated and just installed them in advance). If nobody else does it I can probably do the rewrite myself again at some point. My hope at some point was that desktops would support it in their builtin crash reporters, but at least the KDE people I talked too seemed to be happy with their user space only solution. Alan sayeth: I don't believe that piping as such as neccessarily the right model, but the ability to intercept and processes core dumps from user space is asked for by many enterprise users as well. They want to know about, capture, analyse and process core dumps, often centrally and in automated form. [akpm@osdl.org: loff_t != unsigned long] Signed-off-by: Andi Kleen <ak@suse.de> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-01 14:29:28 +08:00
/* and disallow core files too */
current->signal->rlim[RLIMIT_CORE] = (struct rlimit){0, 0};
}
/* We can run anywhere, unlike our parent keventd(). */
set_cpus_allowed(current, CPU_MASK_ALL);
/*
* Our parent is keventd, which runs with elevated scheduling priority.
* Avoid propagating that into the userspace child.
*/
set_user_nice(current, 0);
retval = -EPERM;
if (current->fs->root)
[PATCH] introduce kernel_execve The use of execve() in the kernel is dubious, since it relies on the __KERNEL_SYSCALLS__ mechanism that stores the result in a global errno variable. As a first step of getting rid of this, change all users to a global kernel_execve function that returns a proper error code. This function is a terrible hack, and a later patch removes it again after the kernel syscalls are gone. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Andi Kleen <ak@muc.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Hirokazu Takata <takata.hirokazu@renesas.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-02 17:18:26 +08:00
retval = kernel_execve(sub_info->path,
sub_info->argv, sub_info->envp);
/* Exec failed? */
sub_info->retval = retval;
do_exit(0);
}
/* Keventd can't block, but this (a child) can. */
static int wait_for_helper(void *data)
{
struct subprocess_info *sub_info = data;
pid_t pid;
/* Install a handler: if SIGCLD isn't handled sys_wait4 won't
* populate the status, but will return -ECHILD. */
allow_signal(SIGCHLD);
pid = kernel_thread(____call_usermodehelper, sub_info, SIGCHLD);
if (pid < 0) {
sub_info->retval = pid;
} else {
int ret;
/*
* Normally it is bogus to call wait4() from in-kernel because
* wait4() wants to write the exit code to a userspace address.
* But wait_for_helper() always runs as keventd, and put_user()
* to a kernel address works OK for kernel threads, due to their
* having an mm_segment_t which spans the entire address space.
*
* Thus the __user pointer cast is valid here.
*/
sys_wait4(pid, (int __user *)&ret, 0, NULL);
/*
* If ret is 0, either ____call_usermodehelper failed and the
* real error code is already in sub_info->retval or
* sub_info->retval is 0 anyway, so don't mess with it then.
*/
if (ret)
sub_info->retval = ret;
}
if (sub_info->wait < 0)
kfree(sub_info);
else
complete(sub_info->complete);
return 0;
}
/* This is run by khelper thread */
2006-11-22 22:55:48 +08:00
static void __call_usermodehelper(struct work_struct *work)
{
2006-11-22 22:55:48 +08:00
struct subprocess_info *sub_info =
container_of(work, struct subprocess_info, work);
pid_t pid;
int wait = sub_info->wait;
/* CLONE_VFORK: wait until the usermode helper has execve'd
* successfully We need the data structures to stay around
* until that is done. */
if (wait)
pid = kernel_thread(wait_for_helper, sub_info,
CLONE_FS | CLONE_FILES | SIGCHLD);
else
pid = kernel_thread(____call_usermodehelper, sub_info,
CLONE_VFORK | SIGCHLD);
if (wait < 0)
return;
if (pid < 0) {
sub_info->retval = pid;
complete(sub_info->complete);
} else if (!wait)
complete(sub_info->complete);
}
/**
* call_usermodehelper_keys - start a usermode application
* @path: pathname for the application
* @argv: null-terminated argument list
* @envp: null-terminated environment list
* @session_keyring: session keyring for process (NULL for an empty keyring)
* @wait: wait for the application to finish and return status.
* when -1 don't wait at all, but you get no useful error back when
* the program couldn't be exec'ed. This makes it safe to call
* from interrupt context.
*
* Runs a user-space application. The application is started
* asynchronously if wait is not set, and runs as a child of keventd.
* (ie. it runs with full root capabilities).
*
* Must be called from process context. Returns a negative error code
* if program was not execed successfully, or 0.
*/
int call_usermodehelper_keys(char *path, char **argv, char **envp,
struct key *session_keyring, int wait)
{
DECLARE_COMPLETION_ONSTACK(done);
struct subprocess_info *sub_info;
int retval;
if (!khelper_wq)
return -EBUSY;
if (path[0] == '\0')
return 0;
sub_info = kzalloc(sizeof(struct subprocess_info), GFP_ATOMIC);
if (!sub_info)
return -ENOMEM;
INIT_WORK(&sub_info->work, __call_usermodehelper);
sub_info->complete = &done;
sub_info->path = path;
sub_info->argv = argv;
sub_info->envp = envp;
sub_info->ring = session_keyring;
sub_info->wait = wait;
queue_work(khelper_wq, &sub_info->work);
if (wait < 0) /* task has freed sub_info */
return 0;
wait_for_completion(&done);
retval = sub_info->retval;
kfree(sub_info);
return retval;
}
EXPORT_SYMBOL(call_usermodehelper_keys);
int call_usermodehelper_pipe(char *path, char **argv, char **envp,
struct file **filp)
{
DECLARE_COMPLETION(done);
struct subprocess_info sub_info = {
2006-11-22 22:55:48 +08:00
.work = __WORK_INITIALIZER(sub_info.work,
__call_usermodehelper),
.complete = &done,
.path = path,
.argv = argv,
.envp = envp,
.retval = 0,
};
struct file *f;
if (!khelper_wq)
return -EBUSY;
if (path[0] == '\0')
return 0;
f = create_write_pipe();
if (IS_ERR(f))
return PTR_ERR(f);
*filp = f;
f = create_read_pipe(f);
if (IS_ERR(f)) {
free_write_pipe(*filp);
return PTR_ERR(f);
}
sub_info.stdin = f;
2006-11-22 22:55:48 +08:00
queue_work(khelper_wq, &sub_info.work);
wait_for_completion(&done);
return sub_info.retval;
}
EXPORT_SYMBOL(call_usermodehelper_pipe);
void __init usermodehelper_init(void)
{
khelper_wq = create_singlethread_workqueue("khelper");
BUG_ON(!khelper_wq);
}