linux/kernel/kmod.c

528 lines
14 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/completion.h>
#include <linux/cred.h>
#include <linux/file.h>
#include <linux/fdtable.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 08:29:28 +02:00
#include <linux/resource.h>
#include <linux/notifier.h>
#include <linux/suspend.h>
#include <asm/uaccess.h>
tracing/events: Add module tracepoints Add trace points to trace module_load, module_free, module_get, module_put and module_request, and use trace_event facility to get the trace output. Here's the sample output: TASK-PID CPU# TIMESTAMP FUNCTION | | | | | <...>-42 [000] 1.758380: module_request: fb0 wait=1 call_site=fb_open ... <...>-60 [000] 3.269403: module_load: scsi_wait_scan <...>-60 [000] 3.269432: module_put: scsi_wait_scan call_site=sys_init_module refcnt=0 <...>-61 [001] 3.273168: module_free: scsi_wait_scan ... <...>-1021 [000] 13.836081: module_load: sunrpc <...>-1021 [000] 13.840589: module_put: sunrpc call_site=sys_init_module refcnt=-1 <...>-1027 [000] 13.848098: module_get: sunrpc call_site=try_module_get refcnt=0 <...>-1027 [000] 13.848308: module_get: sunrpc call_site=get_filesystem refcnt=1 <...>-1027 [000] 13.848692: module_put: sunrpc call_site=put_filesystem refcnt=0 ... modprobe-2587 [001] 1088.437213: module_load: trace_events_sample F modprobe-2587 [001] 1088.437786: module_put: trace_events_sample call_site=sys_init_module refcnt=0 Note: - the taints flag can be 'F', 'C' and/or 'P' if mod->taints != 0 - the module refcnt is percpu, so it can be negative in a specific cpu Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Rusty Russell <rusty@rustcorp.com.au> LKML-Reference: <4A891B3C.5030608@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-17 10:56:28 +02:00
#include <trace/events/module.h>
extern int max_threads;
static struct workqueue_struct *khelper_wq;
#define CAP_BSET (void *)1
#define CAP_PI (void *)2
static kernel_cap_t usermodehelper_bset = CAP_FULL_SET;
static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET;
static DEFINE_SPINLOCK(umh_sysctl_lock);
#ifdef CONFIG_MODULES
/*
modprobe_path is set via /proc/sys.
*/
char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe";
/**
* __request_module - try to load a kernel module
* @wait: wait (or not) for the operation to complete
* @fmt: printf style format string for the name of the module
* @...: arguments 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(bool wait, 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;
ret = security_kernel_module_request(module_name);
if (ret)
return ret;
/* 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;
}
tracing/events: Add module tracepoints Add trace points to trace module_load, module_free, module_get, module_put and module_request, and use trace_event facility to get the trace output. Here's the sample output: TASK-PID CPU# TIMESTAMP FUNCTION | | | | | <...>-42 [000] 1.758380: module_request: fb0 wait=1 call_site=fb_open ... <...>-60 [000] 3.269403: module_load: scsi_wait_scan <...>-60 [000] 3.269432: module_put: scsi_wait_scan call_site=sys_init_module refcnt=0 <...>-61 [001] 3.273168: module_free: scsi_wait_scan ... <...>-1021 [000] 13.836081: module_load: sunrpc <...>-1021 [000] 13.840589: module_put: sunrpc call_site=sys_init_module refcnt=-1 <...>-1027 [000] 13.848098: module_get: sunrpc call_site=try_module_get refcnt=0 <...>-1027 [000] 13.848308: module_get: sunrpc call_site=get_filesystem refcnt=1 <...>-1027 [000] 13.848692: module_put: sunrpc call_site=put_filesystem refcnt=0 ... modprobe-2587 [001] 1088.437213: module_load: trace_events_sample F modprobe-2587 [001] 1088.437786: module_put: trace_events_sample call_site=sys_init_module refcnt=0 Note: - the taints flag can be 'F', 'C' and/or 'P' if mod->taints != 0 - the module refcnt is percpu, so it can be negative in a specific cpu Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Rusty Russell <rusty@rustcorp.com.au> LKML-Reference: <4A891B3C.5030608@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-17 10:56:28 +02:00
trace_module_request(module_name, wait, _RET_IP_);
kmod: add init function to usermodehelper About 6 months ago, I made a set of changes to how the core-dump-to-a-pipe feature in the kernel works. We had reports of several races, including some reports of apps bypassing our recursion check so that a process that was forked as part of a core_pattern setup could infinitely crash and refork until the system crashed. We fixed those by improving our recursion checks. The new check basically refuses to fork a process if its core limit is zero, which works well. Unfortunately, I've been getting grief from maintainer of user space programs that are inserted as the forked process of core_pattern. They contend that in order for their programs (such as abrt and apport) to work, all the running processes in a system must have their core limits set to a non-zero value, to which I say 'yes'. I did this by design, and think thats the right way to do things. But I've been asked to ease this burden on user space enough times that I thought I would take a look at it. The first suggestion was to make the recursion check fail on a non-zero 'special' number, like one. That way the core collector process could set its core size ulimit to 1, and enable the kernel's recursion detection. This isn't a bad idea on the surface, but I don't like it since its opt-in, in that if a program like abrt or apport has a bug and fails to set such a core limit, we're left with a recursively crashing system again. So I've come up with this. What I've done is modify the call_usermodehelper api such that an extra parameter is added, a function pointer which will be called by the user helper task, after it forks, but before it exec's the required process. This will give the caller the opportunity to get a call back in the processes context, allowing it to do whatever it needs to to the process in the kernel prior to exec-ing the user space code. In the case of do_coredump, this callback is ues to set the core ulimit of the helper process to 1. This elimnates the opt-in problem that I had above, as it allows the ulimit for core sizes to be set to the value of 1, which is what the recursion check looks for in do_coredump. This patch: Create new function call_usermodehelper_fns() and allow it to assign both an init and cleanup function, as we'll as arbitrary data. The init function is called from the context of the forked process and allows for customization of the helper process prior to calling exec. Its return code gates the continuation of the process, or causes its exit. Also add an arbitrary data pointer to the subprocess_info struct allowing for data to be passed from the caller to the new process, and the subsequent cleanup process Also, use this patch to cleanup the cleanup function. It currently takes an argp and envp pointer for freeing, which is ugly. Lets instead just make the subprocess_info structure public, and pass that to the cleanup and init routines Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-26 23:42:58 +02:00
ret = call_usermodehelper_fns(modprobe_path, argv, envp,
wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC,
NULL, NULL, NULL);
atomic_dec(&kmod_concurrent);
return ret;
}
EXPORT_SYMBOL(__request_module);
#endif /* CONFIG_MODULES */
/*
* This is the task which runs the usermode application
*/
static int ____call_usermodehelper(void *data)
{
struct subprocess_info *sub_info = data;
struct cred *new;
int retval;
spin_lock_irq(&current->sighand->siglock);
flush_signal_handlers(current, 1);
spin_unlock_irq(&current->sighand->siglock);
/* We can run anywhere, unlike our parent keventd(). */
set_cpus_allowed_ptr(current, cpu_all_mask);
/*
* Our parent is keventd, which runs with elevated scheduling priority.
* Avoid propagating that into the userspace child.
*/
set_user_nice(current, 0);
kmod: add init function to usermodehelper About 6 months ago, I made a set of changes to how the core-dump-to-a-pipe feature in the kernel works. We had reports of several races, including some reports of apps bypassing our recursion check so that a process that was forked as part of a core_pattern setup could infinitely crash and refork until the system crashed. We fixed those by improving our recursion checks. The new check basically refuses to fork a process if its core limit is zero, which works well. Unfortunately, I've been getting grief from maintainer of user space programs that are inserted as the forked process of core_pattern. They contend that in order for their programs (such as abrt and apport) to work, all the running processes in a system must have their core limits set to a non-zero value, to which I say 'yes'. I did this by design, and think thats the right way to do things. But I've been asked to ease this burden on user space enough times that I thought I would take a look at it. The first suggestion was to make the recursion check fail on a non-zero 'special' number, like one. That way the core collector process could set its core size ulimit to 1, and enable the kernel's recursion detection. This isn't a bad idea on the surface, but I don't like it since its opt-in, in that if a program like abrt or apport has a bug and fails to set such a core limit, we're left with a recursively crashing system again. So I've come up with this. What I've done is modify the call_usermodehelper api such that an extra parameter is added, a function pointer which will be called by the user helper task, after it forks, but before it exec's the required process. This will give the caller the opportunity to get a call back in the processes context, allowing it to do whatever it needs to to the process in the kernel prior to exec-ing the user space code. In the case of do_coredump, this callback is ues to set the core ulimit of the helper process to 1. This elimnates the opt-in problem that I had above, as it allows the ulimit for core sizes to be set to the value of 1, which is what the recursion check looks for in do_coredump. This patch: Create new function call_usermodehelper_fns() and allow it to assign both an init and cleanup function, as we'll as arbitrary data. The init function is called from the context of the forked process and allows for customization of the helper process prior to calling exec. Its return code gates the continuation of the process, or causes its exit. Also add an arbitrary data pointer to the subprocess_info struct allowing for data to be passed from the caller to the new process, and the subsequent cleanup process Also, use this patch to cleanup the cleanup function. It currently takes an argp and envp pointer for freeing, which is ugly. Lets instead just make the subprocess_info structure public, and pass that to the cleanup and init routines Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-26 23:42:58 +02:00
if (sub_info->init) {
retval = sub_info->init(sub_info);
if (retval)
goto fail;
}
retval = -ENOMEM;
new = prepare_kernel_cred(current);
if (!new)
goto fail;
spin_lock(&umh_sysctl_lock);
new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset);
new->cap_inheritable = cap_intersect(usermodehelper_inheritable,
new->cap_inheritable);
spin_unlock(&umh_sysctl_lock);
commit_creds(new);
retval = kernel_execve(sub_info->path,
(const char *const *)sub_info->argv,
(const char *const *)sub_info->envp);
/* Exec failed? */
kmod: add init function to usermodehelper About 6 months ago, I made a set of changes to how the core-dump-to-a-pipe feature in the kernel works. We had reports of several races, including some reports of apps bypassing our recursion check so that a process that was forked as part of a core_pattern setup could infinitely crash and refork until the system crashed. We fixed those by improving our recursion checks. The new check basically refuses to fork a process if its core limit is zero, which works well. Unfortunately, I've been getting grief from maintainer of user space programs that are inserted as the forked process of core_pattern. They contend that in order for their programs (such as abrt and apport) to work, all the running processes in a system must have their core limits set to a non-zero value, to which I say 'yes'. I did this by design, and think thats the right way to do things. But I've been asked to ease this burden on user space enough times that I thought I would take a look at it. The first suggestion was to make the recursion check fail on a non-zero 'special' number, like one. That way the core collector process could set its core size ulimit to 1, and enable the kernel's recursion detection. This isn't a bad idea on the surface, but I don't like it since its opt-in, in that if a program like abrt or apport has a bug and fails to set such a core limit, we're left with a recursively crashing system again. So I've come up with this. What I've done is modify the call_usermodehelper api such that an extra parameter is added, a function pointer which will be called by the user helper task, after it forks, but before it exec's the required process. This will give the caller the opportunity to get a call back in the processes context, allowing it to do whatever it needs to to the process in the kernel prior to exec-ing the user space code. In the case of do_coredump, this callback is ues to set the core ulimit of the helper process to 1. This elimnates the opt-in problem that I had above, as it allows the ulimit for core sizes to be set to the value of 1, which is what the recursion check looks for in do_coredump. This patch: Create new function call_usermodehelper_fns() and allow it to assign both an init and cleanup function, as we'll as arbitrary data. The init function is called from the context of the forked process and allows for customization of the helper process prior to calling exec. Its return code gates the continuation of the process, or causes its exit. Also add an arbitrary data pointer to the subprocess_info struct allowing for data to be passed from the caller to the new process, and the subsequent cleanup process Also, use this patch to cleanup the cleanup function. It currently takes an argp and envp pointer for freeing, which is ugly. Lets instead just make the subprocess_info structure public, and pass that to the cleanup and init routines Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-26 23:42:58 +02:00
fail:
sub_info->retval = retval;
do_exit(0);
}
void call_usermodehelper_freeinfo(struct subprocess_info *info)
{
if (info->cleanup)
kmod: add init function to usermodehelper About 6 months ago, I made a set of changes to how the core-dump-to-a-pipe feature in the kernel works. We had reports of several races, including some reports of apps bypassing our recursion check so that a process that was forked as part of a core_pattern setup could infinitely crash and refork until the system crashed. We fixed those by improving our recursion checks. The new check basically refuses to fork a process if its core limit is zero, which works well. Unfortunately, I've been getting grief from maintainer of user space programs that are inserted as the forked process of core_pattern. They contend that in order for their programs (such as abrt and apport) to work, all the running processes in a system must have their core limits set to a non-zero value, to which I say 'yes'. I did this by design, and think thats the right way to do things. But I've been asked to ease this burden on user space enough times that I thought I would take a look at it. The first suggestion was to make the recursion check fail on a non-zero 'special' number, like one. That way the core collector process could set its core size ulimit to 1, and enable the kernel's recursion detection. This isn't a bad idea on the surface, but I don't like it since its opt-in, in that if a program like abrt or apport has a bug and fails to set such a core limit, we're left with a recursively crashing system again. So I've come up with this. What I've done is modify the call_usermodehelper api such that an extra parameter is added, a function pointer which will be called by the user helper task, after it forks, but before it exec's the required process. This will give the caller the opportunity to get a call back in the processes context, allowing it to do whatever it needs to to the process in the kernel prior to exec-ing the user space code. In the case of do_coredump, this callback is ues to set the core ulimit of the helper process to 1. This elimnates the opt-in problem that I had above, as it allows the ulimit for core sizes to be set to the value of 1, which is what the recursion check looks for in do_coredump. This patch: Create new function call_usermodehelper_fns() and allow it to assign both an init and cleanup function, as we'll as arbitrary data. The init function is called from the context of the forked process and allows for customization of the helper process prior to calling exec. Its return code gates the continuation of the process, or causes its exit. Also add an arbitrary data pointer to the subprocess_info struct allowing for data to be passed from the caller to the new process, and the subsequent cleanup process Also, use this patch to cleanup the cleanup function. It currently takes an argp and envp pointer for freeing, which is ugly. Lets instead just make the subprocess_info structure public, and pass that to the cleanup and init routines Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-26 23:42:58 +02:00
(*info->cleanup)(info);
kfree(info);
}
EXPORT_SYMBOL(call_usermodehelper_freeinfo);
/* 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;
/* If SIGCLD is ignored sys_wait4 won't populate the status. */
spin_lock_irq(&current->sighand->siglock);
current->sighand->action[SIGCHLD-1].sa.sa_handler = SIG_DFL;
spin_unlock_irq(&current->sighand->siglock);
pid = kernel_thread(____call_usermodehelper, sub_info, SIGCHLD);
if (pid < 0) {
sub_info->retval = pid;
} else {
int ret = -ECHILD;
/*
* 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;
}
complete(sub_info->complete);
return 0;
}
/* This is run by khelper thread */
2006-11-22 15:55:48 +01:00
static void __call_usermodehelper(struct work_struct *work)
{
2006-11-22 15:55:48 +01:00
struct subprocess_info *sub_info =
container_of(work, struct subprocess_info, work);
enum umh_wait wait = sub_info->wait;
pid_t pid;
/* 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 == UMH_WAIT_PROC)
pid = kernel_thread(wait_for_helper, sub_info,
CLONE_FS | CLONE_FILES | SIGCHLD);
else
pid = kernel_thread(____call_usermodehelper, sub_info,
CLONE_VFORK | SIGCHLD);
switch (wait) {
case UMH_NO_WAIT:
call_usermodehelper_freeinfo(sub_info);
break;
case UMH_WAIT_PROC:
if (pid > 0)
break;
/* FALLTHROUGH */
case UMH_WAIT_EXEC:
if (pid < 0)
sub_info->retval = pid;
complete(sub_info->complete);
}
}
/*
* If set, call_usermodehelper_exec() will exit immediately returning -EBUSY
* (used for preventing user land processes from being created after the user
* land has been frozen during a system-wide hibernation or suspend operation).
*/
static int usermodehelper_disabled;
/* Number of helpers running */
static atomic_t running_helpers = ATOMIC_INIT(0);
/*
* Wait queue head used by usermodehelper_pm_callback() to wait for all running
* helpers to finish.
*/
static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq);
/*
* Time to wait for running_helpers to become zero before the setting of
* usermodehelper_disabled in usermodehelper_pm_callback() fails
*/
#define RUNNING_HELPERS_TIMEOUT (5 * HZ)
/**
* usermodehelper_disable - prevent new helpers from being started
*/
int usermodehelper_disable(void)
{
long retval;
usermodehelper_disabled = 1;
smp_mb();
/*
* From now on call_usermodehelper_exec() won't start any new
* helpers, so it is sufficient if running_helpers turns out to
* be zero at one point (it may be increased later, but that
* doesn't matter).
*/
retval = wait_event_timeout(running_helpers_waitq,
atomic_read(&running_helpers) == 0,
RUNNING_HELPERS_TIMEOUT);
if (retval)
return 0;
usermodehelper_disabled = 0;
return -EAGAIN;
}
/**
* usermodehelper_enable - allow new helpers to be started again
*/
void usermodehelper_enable(void)
{
usermodehelper_disabled = 0;
}
/**
* usermodehelper_is_disabled - check if new helpers are allowed to be started
*/
bool usermodehelper_is_disabled(void)
{
return usermodehelper_disabled;
}
EXPORT_SYMBOL_GPL(usermodehelper_is_disabled);
static void helper_lock(void)
{
atomic_inc(&running_helpers);
smp_mb__after_atomic_inc();
}
static void helper_unlock(void)
{
if (atomic_dec_and_test(&running_helpers))
wake_up(&running_helpers_waitq);
}
/**
* call_usermodehelper_setup - prepare to call a usermode helper
* @path: path to usermode executable
* @argv: arg vector for process
* @envp: environment for process
* @gfp_mask: gfp mask for memory allocation
*
* Returns either %NULL on allocation failure, or a subprocess_info
* structure. This should be passed to call_usermodehelper_exec to
* exec the process and free the structure.
*/
struct subprocess_info *call_usermodehelper_setup(char *path, char **argv,
char **envp, gfp_t gfp_mask)
{
struct subprocess_info *sub_info;
sub_info = kzalloc(sizeof(struct subprocess_info), gfp_mask);
if (!sub_info)
goto out;
INIT_WORK(&sub_info->work, __call_usermodehelper);
sub_info->path = path;
sub_info->argv = argv;
sub_info->envp = envp;
out:
return sub_info;
}
EXPORT_SYMBOL(call_usermodehelper_setup);
/**
kmod: add init function to usermodehelper About 6 months ago, I made a set of changes to how the core-dump-to-a-pipe feature in the kernel works. We had reports of several races, including some reports of apps bypassing our recursion check so that a process that was forked as part of a core_pattern setup could infinitely crash and refork until the system crashed. We fixed those by improving our recursion checks. The new check basically refuses to fork a process if its core limit is zero, which works well. Unfortunately, I've been getting grief from maintainer of user space programs that are inserted as the forked process of core_pattern. They contend that in order for their programs (such as abrt and apport) to work, all the running processes in a system must have their core limits set to a non-zero value, to which I say 'yes'. I did this by design, and think thats the right way to do things. But I've been asked to ease this burden on user space enough times that I thought I would take a look at it. The first suggestion was to make the recursion check fail on a non-zero 'special' number, like one. That way the core collector process could set its core size ulimit to 1, and enable the kernel's recursion detection. This isn't a bad idea on the surface, but I don't like it since its opt-in, in that if a program like abrt or apport has a bug and fails to set such a core limit, we're left with a recursively crashing system again. So I've come up with this. What I've done is modify the call_usermodehelper api such that an extra parameter is added, a function pointer which will be called by the user helper task, after it forks, but before it exec's the required process. This will give the caller the opportunity to get a call back in the processes context, allowing it to do whatever it needs to to the process in the kernel prior to exec-ing the user space code. In the case of do_coredump, this callback is ues to set the core ulimit of the helper process to 1. This elimnates the opt-in problem that I had above, as it allows the ulimit for core sizes to be set to the value of 1, which is what the recursion check looks for in do_coredump. This patch: Create new function call_usermodehelper_fns() and allow it to assign both an init and cleanup function, as we'll as arbitrary data. The init function is called from the context of the forked process and allows for customization of the helper process prior to calling exec. Its return code gates the continuation of the process, or causes its exit. Also add an arbitrary data pointer to the subprocess_info struct allowing for data to be passed from the caller to the new process, and the subsequent cleanup process Also, use this patch to cleanup the cleanup function. It currently takes an argp and envp pointer for freeing, which is ugly. Lets instead just make the subprocess_info structure public, and pass that to the cleanup and init routines Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-26 23:42:58 +02:00
* call_usermodehelper_setfns - set a cleanup/init function
* @info: a subprocess_info returned by call_usermodehelper_setup
* @cleanup: a cleanup function
kmod: add init function to usermodehelper About 6 months ago, I made a set of changes to how the core-dump-to-a-pipe feature in the kernel works. We had reports of several races, including some reports of apps bypassing our recursion check so that a process that was forked as part of a core_pattern setup could infinitely crash and refork until the system crashed. We fixed those by improving our recursion checks. The new check basically refuses to fork a process if its core limit is zero, which works well. Unfortunately, I've been getting grief from maintainer of user space programs that are inserted as the forked process of core_pattern. They contend that in order for their programs (such as abrt and apport) to work, all the running processes in a system must have their core limits set to a non-zero value, to which I say 'yes'. I did this by design, and think thats the right way to do things. But I've been asked to ease this burden on user space enough times that I thought I would take a look at it. The first suggestion was to make the recursion check fail on a non-zero 'special' number, like one. That way the core collector process could set its core size ulimit to 1, and enable the kernel's recursion detection. This isn't a bad idea on the surface, but I don't like it since its opt-in, in that if a program like abrt or apport has a bug and fails to set such a core limit, we're left with a recursively crashing system again. So I've come up with this. What I've done is modify the call_usermodehelper api such that an extra parameter is added, a function pointer which will be called by the user helper task, after it forks, but before it exec's the required process. This will give the caller the opportunity to get a call back in the processes context, allowing it to do whatever it needs to to the process in the kernel prior to exec-ing the user space code. In the case of do_coredump, this callback is ues to set the core ulimit of the helper process to 1. This elimnates the opt-in problem that I had above, as it allows the ulimit for core sizes to be set to the value of 1, which is what the recursion check looks for in do_coredump. This patch: Create new function call_usermodehelper_fns() and allow it to assign both an init and cleanup function, as we'll as arbitrary data. The init function is called from the context of the forked process and allows for customization of the helper process prior to calling exec. Its return code gates the continuation of the process, or causes its exit. Also add an arbitrary data pointer to the subprocess_info struct allowing for data to be passed from the caller to the new process, and the subsequent cleanup process Also, use this patch to cleanup the cleanup function. It currently takes an argp and envp pointer for freeing, which is ugly. Lets instead just make the subprocess_info structure public, and pass that to the cleanup and init routines Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-26 23:42:58 +02:00
* @init: an init function
* @data: arbitrary context sensitive data
*
* The init function is used to customize the helper process prior to
* exec. A non-zero return code causes the process to error out, exit,
* and return the failure to the calling process
*
kmod: add init function to usermodehelper About 6 months ago, I made a set of changes to how the core-dump-to-a-pipe feature in the kernel works. We had reports of several races, including some reports of apps bypassing our recursion check so that a process that was forked as part of a core_pattern setup could infinitely crash and refork until the system crashed. We fixed those by improving our recursion checks. The new check basically refuses to fork a process if its core limit is zero, which works well. Unfortunately, I've been getting grief from maintainer of user space programs that are inserted as the forked process of core_pattern. They contend that in order for their programs (such as abrt and apport) to work, all the running processes in a system must have their core limits set to a non-zero value, to which I say 'yes'. I did this by design, and think thats the right way to do things. But I've been asked to ease this burden on user space enough times that I thought I would take a look at it. The first suggestion was to make the recursion check fail on a non-zero 'special' number, like one. That way the core collector process could set its core size ulimit to 1, and enable the kernel's recursion detection. This isn't a bad idea on the surface, but I don't like it since its opt-in, in that if a program like abrt or apport has a bug and fails to set such a core limit, we're left with a recursively crashing system again. So I've come up with this. What I've done is modify the call_usermodehelper api such that an extra parameter is added, a function pointer which will be called by the user helper task, after it forks, but before it exec's the required process. This will give the caller the opportunity to get a call back in the processes context, allowing it to do whatever it needs to to the process in the kernel prior to exec-ing the user space code. In the case of do_coredump, this callback is ues to set the core ulimit of the helper process to 1. This elimnates the opt-in problem that I had above, as it allows the ulimit for core sizes to be set to the value of 1, which is what the recursion check looks for in do_coredump. This patch: Create new function call_usermodehelper_fns() and allow it to assign both an init and cleanup function, as we'll as arbitrary data. The init function is called from the context of the forked process and allows for customization of the helper process prior to calling exec. Its return code gates the continuation of the process, or causes its exit. Also add an arbitrary data pointer to the subprocess_info struct allowing for data to be passed from the caller to the new process, and the subsequent cleanup process Also, use this patch to cleanup the cleanup function. It currently takes an argp and envp pointer for freeing, which is ugly. Lets instead just make the subprocess_info structure public, and pass that to the cleanup and init routines Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-26 23:42:58 +02:00
* The cleanup function is just before ethe subprocess_info is about to
* be freed. This can be used for freeing the argv and envp. The
* Function must be runnable in either a process context or the
* context in which call_usermodehelper_exec is called.
*/
kmod: add init function to usermodehelper About 6 months ago, I made a set of changes to how the core-dump-to-a-pipe feature in the kernel works. We had reports of several races, including some reports of apps bypassing our recursion check so that a process that was forked as part of a core_pattern setup could infinitely crash and refork until the system crashed. We fixed those by improving our recursion checks. The new check basically refuses to fork a process if its core limit is zero, which works well. Unfortunately, I've been getting grief from maintainer of user space programs that are inserted as the forked process of core_pattern. They contend that in order for their programs (such as abrt and apport) to work, all the running processes in a system must have their core limits set to a non-zero value, to which I say 'yes'. I did this by design, and think thats the right way to do things. But I've been asked to ease this burden on user space enough times that I thought I would take a look at it. The first suggestion was to make the recursion check fail on a non-zero 'special' number, like one. That way the core collector process could set its core size ulimit to 1, and enable the kernel's recursion detection. This isn't a bad idea on the surface, but I don't like it since its opt-in, in that if a program like abrt or apport has a bug and fails to set such a core limit, we're left with a recursively crashing system again. So I've come up with this. What I've done is modify the call_usermodehelper api such that an extra parameter is added, a function pointer which will be called by the user helper task, after it forks, but before it exec's the required process. This will give the caller the opportunity to get a call back in the processes context, allowing it to do whatever it needs to to the process in the kernel prior to exec-ing the user space code. In the case of do_coredump, this callback is ues to set the core ulimit of the helper process to 1. This elimnates the opt-in problem that I had above, as it allows the ulimit for core sizes to be set to the value of 1, which is what the recursion check looks for in do_coredump. This patch: Create new function call_usermodehelper_fns() and allow it to assign both an init and cleanup function, as we'll as arbitrary data. The init function is called from the context of the forked process and allows for customization of the helper process prior to calling exec. Its return code gates the continuation of the process, or causes its exit. Also add an arbitrary data pointer to the subprocess_info struct allowing for data to be passed from the caller to the new process, and the subsequent cleanup process Also, use this patch to cleanup the cleanup function. It currently takes an argp and envp pointer for freeing, which is ugly. Lets instead just make the subprocess_info structure public, and pass that to the cleanup and init routines Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-26 23:42:58 +02:00
void call_usermodehelper_setfns(struct subprocess_info *info,
int (*init)(struct subprocess_info *info),
void (*cleanup)(struct subprocess_info *info),
void *data)
{
info->cleanup = cleanup;
kmod: add init function to usermodehelper About 6 months ago, I made a set of changes to how the core-dump-to-a-pipe feature in the kernel works. We had reports of several races, including some reports of apps bypassing our recursion check so that a process that was forked as part of a core_pattern setup could infinitely crash and refork until the system crashed. We fixed those by improving our recursion checks. The new check basically refuses to fork a process if its core limit is zero, which works well. Unfortunately, I've been getting grief from maintainer of user space programs that are inserted as the forked process of core_pattern. They contend that in order for their programs (such as abrt and apport) to work, all the running processes in a system must have their core limits set to a non-zero value, to which I say 'yes'. I did this by design, and think thats the right way to do things. But I've been asked to ease this burden on user space enough times that I thought I would take a look at it. The first suggestion was to make the recursion check fail on a non-zero 'special' number, like one. That way the core collector process could set its core size ulimit to 1, and enable the kernel's recursion detection. This isn't a bad idea on the surface, but I don't like it since its opt-in, in that if a program like abrt or apport has a bug and fails to set such a core limit, we're left with a recursively crashing system again. So I've come up with this. What I've done is modify the call_usermodehelper api such that an extra parameter is added, a function pointer which will be called by the user helper task, after it forks, but before it exec's the required process. This will give the caller the opportunity to get a call back in the processes context, allowing it to do whatever it needs to to the process in the kernel prior to exec-ing the user space code. In the case of do_coredump, this callback is ues to set the core ulimit of the helper process to 1. This elimnates the opt-in problem that I had above, as it allows the ulimit for core sizes to be set to the value of 1, which is what the recursion check looks for in do_coredump. This patch: Create new function call_usermodehelper_fns() and allow it to assign both an init and cleanup function, as we'll as arbitrary data. The init function is called from the context of the forked process and allows for customization of the helper process prior to calling exec. Its return code gates the continuation of the process, or causes its exit. Also add an arbitrary data pointer to the subprocess_info struct allowing for data to be passed from the caller to the new process, and the subsequent cleanup process Also, use this patch to cleanup the cleanup function. It currently takes an argp and envp pointer for freeing, which is ugly. Lets instead just make the subprocess_info structure public, and pass that to the cleanup and init routines Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-26 23:42:58 +02:00
info->init = init;
info->data = data;
}
kmod: add init function to usermodehelper About 6 months ago, I made a set of changes to how the core-dump-to-a-pipe feature in the kernel works. We had reports of several races, including some reports of apps bypassing our recursion check so that a process that was forked as part of a core_pattern setup could infinitely crash and refork until the system crashed. We fixed those by improving our recursion checks. The new check basically refuses to fork a process if its core limit is zero, which works well. Unfortunately, I've been getting grief from maintainer of user space programs that are inserted as the forked process of core_pattern. They contend that in order for their programs (such as abrt and apport) to work, all the running processes in a system must have their core limits set to a non-zero value, to which I say 'yes'. I did this by design, and think thats the right way to do things. But I've been asked to ease this burden on user space enough times that I thought I would take a look at it. The first suggestion was to make the recursion check fail on a non-zero 'special' number, like one. That way the core collector process could set its core size ulimit to 1, and enable the kernel's recursion detection. This isn't a bad idea on the surface, but I don't like it since its opt-in, in that if a program like abrt or apport has a bug and fails to set such a core limit, we're left with a recursively crashing system again. So I've come up with this. What I've done is modify the call_usermodehelper api such that an extra parameter is added, a function pointer which will be called by the user helper task, after it forks, but before it exec's the required process. This will give the caller the opportunity to get a call back in the processes context, allowing it to do whatever it needs to to the process in the kernel prior to exec-ing the user space code. In the case of do_coredump, this callback is ues to set the core ulimit of the helper process to 1. This elimnates the opt-in problem that I had above, as it allows the ulimit for core sizes to be set to the value of 1, which is what the recursion check looks for in do_coredump. This patch: Create new function call_usermodehelper_fns() and allow it to assign both an init and cleanup function, as we'll as arbitrary data. The init function is called from the context of the forked process and allows for customization of the helper process prior to calling exec. Its return code gates the continuation of the process, or causes its exit. Also add an arbitrary data pointer to the subprocess_info struct allowing for data to be passed from the caller to the new process, and the subsequent cleanup process Also, use this patch to cleanup the cleanup function. It currently takes an argp and envp pointer for freeing, which is ugly. Lets instead just make the subprocess_info structure public, and pass that to the cleanup and init routines Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-26 23:42:58 +02:00
EXPORT_SYMBOL(call_usermodehelper_setfns);
/**
* call_usermodehelper_exec - start a usermode application
* @sub_info: information about the subprocessa
* @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).
*/
int call_usermodehelper_exec(struct subprocess_info *sub_info,
enum umh_wait wait)
{
DECLARE_COMPLETION_ONSTACK(done);
int retval = 0;
helper_lock();
if (sub_info->path[0] == '\0')
goto out;
if (!khelper_wq || usermodehelper_disabled) {
retval = -EBUSY;
goto out;
}
sub_info->complete = &done;
sub_info->wait = wait;
queue_work(khelper_wq, &sub_info->work);
if (wait == UMH_NO_WAIT) /* task has freed sub_info */
goto unlock;
wait_for_completion(&done);
retval = sub_info->retval;
out:
call_usermodehelper_freeinfo(sub_info);
unlock:
helper_unlock();
return retval;
}
EXPORT_SYMBOL(call_usermodehelper_exec);
static int proc_cap_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table t;
unsigned long cap_array[_KERNEL_CAPABILITY_U32S];
kernel_cap_t new_cap;
int err, i;
if (write && (!capable(CAP_SETPCAP) ||
!capable(CAP_SYS_MODULE)))
return -EPERM;
/*
* convert from the global kernel_cap_t to the ulong array to print to
* userspace if this is a read.
*/
spin_lock(&umh_sysctl_lock);
for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) {
if (table->data == CAP_BSET)
cap_array[i] = usermodehelper_bset.cap[i];
else if (table->data == CAP_PI)
cap_array[i] = usermodehelper_inheritable.cap[i];
else
BUG();
}
spin_unlock(&umh_sysctl_lock);
t = *table;
t.data = &cap_array;
/*
* actually read or write and array of ulongs from userspace. Remember
* these are least significant 32 bits first
*/
err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
if (err < 0)
return err;
/*
* convert from the sysctl array of ulongs to the kernel_cap_t
* internal representation
*/
for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++)
new_cap.cap[i] = cap_array[i];
/*
* Drop everything not in the new_cap (but don't add things)
*/
spin_lock(&umh_sysctl_lock);
if (write) {
if (table->data == CAP_BSET)
usermodehelper_bset = cap_intersect(usermodehelper_bset, new_cap);
if (table->data == CAP_PI)
usermodehelper_inheritable = cap_intersect(usermodehelper_inheritable, new_cap);
}
spin_unlock(&umh_sysctl_lock);
return 0;
}
struct ctl_table usermodehelper_table[] = {
{
.procname = "bset",
.data = CAP_BSET,
.maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long),
.mode = 0600,
.proc_handler = proc_cap_handler,
},
{
.procname = "inheritable",
.data = CAP_PI,
.maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long),
.mode = 0600,
.proc_handler = proc_cap_handler,
},
{ }
};
void __init usermodehelper_init(void)
{
khelper_wq = create_singlethread_workqueue("khelper");
BUG_ON(!khelper_wq);
}