2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-29 15:43:59 +08:00
linux-next/drivers/base/bus.c

1183 lines
30 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* bus.c - bus driver management
*
* Copyright (c) 2002-3 Patrick Mochel
* Copyright (c) 2002-3 Open Source Development Labs
* Copyright (c) 2007 Greg Kroah-Hartman <gregkh@suse.de>
* Copyright (c) 2007 Novell Inc.
*/
#include <linux/async.h>
#include <linux/device/bus.h>
#include <linux/device.h>
#include <linux/module.h>
#include <linux/errno.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/mutex.h>
#include <linux/sysfs.h>
#include "base.h"
#include "power/power.h"
/* /sys/devices/system */
static struct kset *system_kset;
#define to_bus_attr(_attr) container_of(_attr, struct bus_attribute, attr)
/*
* sysfs bindings for drivers
*/
#define to_drv_attr(_attr) container_of(_attr, struct driver_attribute, attr)
sysfs: Disable lockdep for driver bind/unbind files This is the much more correct fix for my earlier attempt at: https://lkml.org/lkml/2018/12/10/118 Short recap: - There's not actually a locking issue, it's just lockdep being a bit too eager to complain about a possible deadlock. - Contrary to what I claimed the real problem is recursion on kn->count. Greg pointed me at sysfs_break_active_protection(), used by the scsi subsystem to allow a sysfs file to unbind itself. That would be a real deadlock, which isn't what's happening here. Also, breaking the active protection means we'd need to manually handle all the lifetime fun. - With Rafael we discussed the task_work approach, which kinda works, but has two downsides: It's a functional change for a lockdep annotation issue, and it won't work for the bind file (which needs to get the errno from the driver load function back to userspace). - Greg also asked why this never showed up: To hit this you need to unregister a 2nd driver from the unload code of your first driver. I guess only gpus do that. The bug has always been there, but only with a recent patch series did we add more locks so that lockdep built a chain from unbinding the snd-hda driver to the acpi_video_unregister call. Full lockdep splat: [12301.898799] ============================================ [12301.898805] WARNING: possible recursive locking detected [12301.898811] 4.20.0-rc7+ #84 Not tainted [12301.898815] -------------------------------------------- [12301.898821] bash/5297 is trying to acquire lock: [12301.898826] 00000000f61c6093 (kn->count#39){++++}, at: kernfs_remove_by_name_ns+0x3b/0x80 [12301.898841] but task is already holding lock: [12301.898847] 000000005f634021 (kn->count#39){++++}, at: kernfs_fop_write+0xdc/0x190 [12301.898856] other info that might help us debug this: [12301.898862] Possible unsafe locking scenario: [12301.898867] CPU0 [12301.898870] ---- [12301.898874] lock(kn->count#39); [12301.898879] lock(kn->count#39); [12301.898883] *** DEADLOCK *** [12301.898891] May be due to missing lock nesting notation [12301.898899] 5 locks held by bash/5297: [12301.898903] #0: 00000000cd800e54 (sb_writers#4){.+.+}, at: vfs_write+0x17f/0x1b0 [12301.898915] #1: 000000000465e7c2 (&of->mutex){+.+.}, at: kernfs_fop_write+0xd3/0x190 [12301.898925] #2: 000000005f634021 (kn->count#39){++++}, at: kernfs_fop_write+0xdc/0x190 [12301.898936] #3: 00000000414ef7ac (&dev->mutex){....}, at: device_release_driver_internal+0x34/0x240 [12301.898950] #4: 000000003218fbdf (register_count_mutex){+.+.}, at: acpi_video_unregister+0xe/0x40 [12301.898960] stack backtrace: [12301.898968] CPU: 1 PID: 5297 Comm: bash Not tainted 4.20.0-rc7+ #84 [12301.898974] Hardware name: Hewlett-Packard HP EliteBook 8460p/161C, BIOS 68SCF Ver. F.01 03/11/2011 [12301.898982] Call Trace: [12301.898989] dump_stack+0x67/0x9b [12301.898997] __lock_acquire+0x6ad/0x1410 [12301.899003] ? kernfs_remove_by_name_ns+0x3b/0x80 [12301.899010] ? find_held_lock+0x2d/0x90 [12301.899017] ? mutex_spin_on_owner+0xe4/0x150 [12301.899023] ? find_held_lock+0x2d/0x90 [12301.899030] ? lock_acquire+0x90/0x180 [12301.899036] lock_acquire+0x90/0x180 [12301.899042] ? kernfs_remove_by_name_ns+0x3b/0x80 [12301.899049] __kernfs_remove+0x296/0x310 [12301.899055] ? kernfs_remove_by_name_ns+0x3b/0x80 [12301.899060] ? kernfs_name_hash+0xd/0x80 [12301.899066] ? kernfs_find_ns+0x6c/0x100 [12301.899073] kernfs_remove_by_name_ns+0x3b/0x80 [12301.899080] bus_remove_driver+0x92/0xa0 [12301.899085] acpi_video_unregister+0x24/0x40 [12301.899127] i915_driver_unload+0x42/0x130 [i915] [12301.899160] i915_pci_remove+0x19/0x30 [i915] [12301.899169] pci_device_remove+0x36/0xb0 [12301.899176] device_release_driver_internal+0x185/0x240 [12301.899183] unbind_store+0xaf/0x180 [12301.899189] kernfs_fop_write+0x104/0x190 [12301.899195] __vfs_write+0x31/0x180 [12301.899203] ? rcu_read_lock_sched_held+0x6f/0x80 [12301.899209] ? rcu_sync_lockdep_assert+0x29/0x50 [12301.899216] ? __sb_start_write+0x13c/0x1a0 [12301.899221] ? vfs_write+0x17f/0x1b0 [12301.899227] vfs_write+0xb9/0x1b0 [12301.899233] ksys_write+0x50/0xc0 [12301.899239] do_syscall_64+0x4b/0x180 [12301.899247] entry_SYSCALL_64_after_hwframe+0x49/0xbe [12301.899253] RIP: 0033:0x7f452ac7f7a4 [12301.899259] Code: 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 80 00 00 00 00 8b 05 aa f0 2c 00 48 63 ff 85 c0 75 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 f3 c3 66 90 55 53 48 89 d5 48 89 f3 48 83 [12301.899273] RSP: 002b:00007ffceafa6918 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [12301.899282] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f452ac7f7a4 [12301.899288] RDX: 000000000000000d RSI: 00005612a1abf7c0 RDI: 0000000000000001 [12301.899295] RBP: 00005612a1abf7c0 R08: 000000000000000a R09: 00005612a1c46730 [12301.899301] R10: 000000000000000a R11: 0000000000000246 R12: 000000000000000d [12301.899308] R13: 0000000000000001 R14: 00007f452af4a740 R15: 000000000000000d Looking around I've noticed that usb and i2c already handle similar recursion problems, where a sysfs file can unbind the same type of sysfs somewhere else in the hierarchy. Relevant commits are: commit 356c05d58af05d582e634b54b40050c73609617b Author: Alan Stern <stern@rowland.harvard.edu> Date: Mon May 14 13:30:03 2012 -0400 sysfs: get rid of some lockdep false positives commit e9b526fe704812364bca07edd15eadeba163ebfb Author: Alexander Sverdlin <alexander.sverdlin@nsn.com> Date: Fri May 17 14:56:35 2013 +0200 i2c: suppress lockdep warning on delete_device Implement the same trick for driver bind/unbind. v2: Put the macro into bus.c (Greg). Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Ramalingam C <ramalingam.c@intel.com> Cc: Arend van Spriel <aspriel@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Geert Uytterhoeven <geert+renesas@glider.be> Cc: Bartosz Golaszewski <brgl@bgdev.pl> Cc: Heikki Krogerus <heikki.krogerus@linux.intel.com> Cc: Vivek Gautam <vivek.gautam@codeaurora.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-19 20:39:09 +08:00
#define DRIVER_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \
struct driver_attribute driver_attr_##_name = \
__ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store)
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
static int __must_check bus_rescan_devices_helper(struct device *dev,
void *data);
static struct bus_type *bus_get(struct bus_type *bus)
{
if (bus) {
kset_get(&bus->p->subsys);
return bus;
}
return NULL;
}
static void bus_put(struct bus_type *bus)
{
if (bus)
kset_put(&bus->p->subsys);
}
static ssize_t drv_attr_show(struct kobject *kobj, struct attribute *attr,
char *buf)
{
struct driver_attribute *drv_attr = to_drv_attr(attr);
struct driver_private *drv_priv = to_driver(kobj);
ssize_t ret = -EIO;
if (drv_attr->show)
ret = drv_attr->show(drv_priv->driver, buf);
return ret;
}
static ssize_t drv_attr_store(struct kobject *kobj, struct attribute *attr,
const char *buf, size_t count)
{
struct driver_attribute *drv_attr = to_drv_attr(attr);
struct driver_private *drv_priv = to_driver(kobj);
ssize_t ret = -EIO;
if (drv_attr->store)
ret = drv_attr->store(drv_priv->driver, buf, count);
return ret;
}
static const struct sysfs_ops driver_sysfs_ops = {
.show = drv_attr_show,
.store = drv_attr_store,
};
static void driver_release(struct kobject *kobj)
{
struct driver_private *drv_priv = to_driver(kobj);
pr_debug("driver: '%s': %s\n", kobject_name(kobj), __func__);
kfree(drv_priv);
}
static struct kobj_type driver_ktype = {
.sysfs_ops = &driver_sysfs_ops,
.release = driver_release,
};
/*
* sysfs bindings for buses
*/
static ssize_t bus_attr_show(struct kobject *kobj, struct attribute *attr,
char *buf)
{
struct bus_attribute *bus_attr = to_bus_attr(attr);
struct subsys_private *subsys_priv = to_subsys_private(kobj);
ssize_t ret = 0;
if (bus_attr->show)
ret = bus_attr->show(subsys_priv->bus, buf);
return ret;
}
static ssize_t bus_attr_store(struct kobject *kobj, struct attribute *attr,
const char *buf, size_t count)
{
struct bus_attribute *bus_attr = to_bus_attr(attr);
struct subsys_private *subsys_priv = to_subsys_private(kobj);
ssize_t ret = 0;
if (bus_attr->store)
ret = bus_attr->store(subsys_priv->bus, buf, count);
return ret;
}
static const struct sysfs_ops bus_sysfs_ops = {
.show = bus_attr_show,
.store = bus_attr_store,
};
int bus_create_file(struct bus_type *bus, struct bus_attribute *attr)
{
int error;
if (bus_get(bus)) {
error = sysfs_create_file(&bus->p->subsys.kobj, &attr->attr);
bus_put(bus);
} else
error = -EINVAL;
return error;
}
EXPORT_SYMBOL_GPL(bus_create_file);
void bus_remove_file(struct bus_type *bus, struct bus_attribute *attr)
{
if (bus_get(bus)) {
sysfs_remove_file(&bus->p->subsys.kobj, &attr->attr);
bus_put(bus);
}
}
EXPORT_SYMBOL_GPL(bus_remove_file);
driver-core: Fix use-after-free triggered by bus_unregister() Avoid that bus_unregister() triggers a use-after-free with CONFIG_DEBUG_KOBJECT_RELEASE=y. This patch avoids that the following sequence triggers a kernel crash with memory poisoning enabled: * bus_register() * driver_register() * driver_unregister() * bus_unregister() The above sequence causes the bus private data to be freed from inside the bus_unregister() call although it is not guaranteed in that function that the reference count on the bus private data has dropped to zero. As an example, with CONFIG_DEBUG_KOBJECT_RELEASE=y the ${bus}/drivers kobject is still holding a reference on bus->p->subsys.kobj via its parent pointer at the time the bus private data is freed. Fix this by deferring freeing the bus private data until the last kobject_put() call on bus->p->subsys.kobj. The kernel oops triggered by the above sequence and with memory poisoning enabled and that is fixed by this patch is as follows: general protection fault: 0000 [#1] PREEMPT SMP CPU: 3 PID: 2711 Comm: kworker/3:32 Tainted: G W O 3.13.0-rc4-debug+ #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 Workqueue: events kobject_delayed_cleanup task: ffff880037f866d0 ti: ffff88003b638000 task.ti: ffff88003b638000 Call Trace: [<ffffffff81263105>] ? kobject_get_path+0x25/0x100 [<ffffffff81264354>] kobject_uevent_env+0x134/0x600 [<ffffffff8126482b>] kobject_uevent+0xb/0x10 [<ffffffff81262fa2>] kobject_delayed_cleanup+0xc2/0x1b0 [<ffffffff8106c047>] process_one_work+0x217/0x700 [<ffffffff8106bfdb>] ? process_one_work+0x1ab/0x700 [<ffffffff8106c64b>] worker_thread+0x11b/0x3a0 [<ffffffff8106c530>] ? process_one_work+0x700/0x700 [<ffffffff81074b70>] kthread+0xf0/0x110 [<ffffffff81074a80>] ? insert_kthread_work+0x80/0x80 [<ffffffff815673bc>] ret_from_fork+0x7c/0xb0 [<ffffffff81074a80>] ? insert_kthread_work+0x80/0x80 Code: 89 f8 48 89 e5 f6 82 c0 27 63 81 20 74 15 0f 1f 44 00 00 48 83 c0 01 0f b6 10 f6 82 c0 27 63 81 20 75 f0 5d c3 66 0f 1f 44 00 00 <80> 3f 00 55 48 89 e5 74 15 48 89 f8 0f 1f 40 00 48 83 c0 01 80 RIP [<ffffffff81267ed0>] strlen+0x0/0x30 RSP <ffff88003b639c70> ---[ end trace 210f883ef80376aa ]--- Signed-off-by: Bart Van Assche <bvanassche@acm.org> Acked-by: Ming Lei <ming.lei@canonical.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-01-04 21:21:42 +08:00
static void bus_release(struct kobject *kobj)
{
struct subsys_private *priv = to_subsys_private(kobj);
driver-core: Fix use-after-free triggered by bus_unregister() Avoid that bus_unregister() triggers a use-after-free with CONFIG_DEBUG_KOBJECT_RELEASE=y. This patch avoids that the following sequence triggers a kernel crash with memory poisoning enabled: * bus_register() * driver_register() * driver_unregister() * bus_unregister() The above sequence causes the bus private data to be freed from inside the bus_unregister() call although it is not guaranteed in that function that the reference count on the bus private data has dropped to zero. As an example, with CONFIG_DEBUG_KOBJECT_RELEASE=y the ${bus}/drivers kobject is still holding a reference on bus->p->subsys.kobj via its parent pointer at the time the bus private data is freed. Fix this by deferring freeing the bus private data until the last kobject_put() call on bus->p->subsys.kobj. The kernel oops triggered by the above sequence and with memory poisoning enabled and that is fixed by this patch is as follows: general protection fault: 0000 [#1] PREEMPT SMP CPU: 3 PID: 2711 Comm: kworker/3:32 Tainted: G W O 3.13.0-rc4-debug+ #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 Workqueue: events kobject_delayed_cleanup task: ffff880037f866d0 ti: ffff88003b638000 task.ti: ffff88003b638000 Call Trace: [<ffffffff81263105>] ? kobject_get_path+0x25/0x100 [<ffffffff81264354>] kobject_uevent_env+0x134/0x600 [<ffffffff8126482b>] kobject_uevent+0xb/0x10 [<ffffffff81262fa2>] kobject_delayed_cleanup+0xc2/0x1b0 [<ffffffff8106c047>] process_one_work+0x217/0x700 [<ffffffff8106bfdb>] ? process_one_work+0x1ab/0x700 [<ffffffff8106c64b>] worker_thread+0x11b/0x3a0 [<ffffffff8106c530>] ? process_one_work+0x700/0x700 [<ffffffff81074b70>] kthread+0xf0/0x110 [<ffffffff81074a80>] ? insert_kthread_work+0x80/0x80 [<ffffffff815673bc>] ret_from_fork+0x7c/0xb0 [<ffffffff81074a80>] ? insert_kthread_work+0x80/0x80 Code: 89 f8 48 89 e5 f6 82 c0 27 63 81 20 74 15 0f 1f 44 00 00 48 83 c0 01 0f b6 10 f6 82 c0 27 63 81 20 75 f0 5d c3 66 0f 1f 44 00 00 <80> 3f 00 55 48 89 e5 74 15 48 89 f8 0f 1f 40 00 48 83 c0 01 80 RIP [<ffffffff81267ed0>] strlen+0x0/0x30 RSP <ffff88003b639c70> ---[ end trace 210f883ef80376aa ]--- Signed-off-by: Bart Van Assche <bvanassche@acm.org> Acked-by: Ming Lei <ming.lei@canonical.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-01-04 21:21:42 +08:00
struct bus_type *bus = priv->bus;
kfree(priv);
bus->p = NULL;
}
static struct kobj_type bus_ktype = {
.sysfs_ops = &bus_sysfs_ops,
driver-core: Fix use-after-free triggered by bus_unregister() Avoid that bus_unregister() triggers a use-after-free with CONFIG_DEBUG_KOBJECT_RELEASE=y. This patch avoids that the following sequence triggers a kernel crash with memory poisoning enabled: * bus_register() * driver_register() * driver_unregister() * bus_unregister() The above sequence causes the bus private data to be freed from inside the bus_unregister() call although it is not guaranteed in that function that the reference count on the bus private data has dropped to zero. As an example, with CONFIG_DEBUG_KOBJECT_RELEASE=y the ${bus}/drivers kobject is still holding a reference on bus->p->subsys.kobj via its parent pointer at the time the bus private data is freed. Fix this by deferring freeing the bus private data until the last kobject_put() call on bus->p->subsys.kobj. The kernel oops triggered by the above sequence and with memory poisoning enabled and that is fixed by this patch is as follows: general protection fault: 0000 [#1] PREEMPT SMP CPU: 3 PID: 2711 Comm: kworker/3:32 Tainted: G W O 3.13.0-rc4-debug+ #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 Workqueue: events kobject_delayed_cleanup task: ffff880037f866d0 ti: ffff88003b638000 task.ti: ffff88003b638000 Call Trace: [<ffffffff81263105>] ? kobject_get_path+0x25/0x100 [<ffffffff81264354>] kobject_uevent_env+0x134/0x600 [<ffffffff8126482b>] kobject_uevent+0xb/0x10 [<ffffffff81262fa2>] kobject_delayed_cleanup+0xc2/0x1b0 [<ffffffff8106c047>] process_one_work+0x217/0x700 [<ffffffff8106bfdb>] ? process_one_work+0x1ab/0x700 [<ffffffff8106c64b>] worker_thread+0x11b/0x3a0 [<ffffffff8106c530>] ? process_one_work+0x700/0x700 [<ffffffff81074b70>] kthread+0xf0/0x110 [<ffffffff81074a80>] ? insert_kthread_work+0x80/0x80 [<ffffffff815673bc>] ret_from_fork+0x7c/0xb0 [<ffffffff81074a80>] ? insert_kthread_work+0x80/0x80 Code: 89 f8 48 89 e5 f6 82 c0 27 63 81 20 74 15 0f 1f 44 00 00 48 83 c0 01 0f b6 10 f6 82 c0 27 63 81 20 75 f0 5d c3 66 0f 1f 44 00 00 <80> 3f 00 55 48 89 e5 74 15 48 89 f8 0f 1f 40 00 48 83 c0 01 80 RIP [<ffffffff81267ed0>] strlen+0x0/0x30 RSP <ffff88003b639c70> ---[ end trace 210f883ef80376aa ]--- Signed-off-by: Bart Van Assche <bvanassche@acm.org> Acked-by: Ming Lei <ming.lei@canonical.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-01-04 21:21:42 +08:00
.release = bus_release,
};
static int bus_uevent_filter(struct kset *kset, struct kobject *kobj)
{
struct kobj_type *ktype = get_ktype(kobj);
if (ktype == &bus_ktype)
return 1;
return 0;
}
static const struct kset_uevent_ops bus_uevent_ops = {
.filter = bus_uevent_filter,
};
static struct kset *bus_kset;
/* Manually detach a device from its associated driver. */
static ssize_t unbind_store(struct device_driver *drv, const char *buf,
size_t count)
{
struct bus_type *bus = bus_get(drv->bus);
struct device *dev;
int err = -ENODEV;
dev = bus_find_device_by_name(bus, NULL, buf);
if (dev && dev->driver == drv) {
device_driver_detach(dev);
err = count;
}
put_device(dev);
bus_put(bus);
return err;
}
sysfs: Disable lockdep for driver bind/unbind files This is the much more correct fix for my earlier attempt at: https://lkml.org/lkml/2018/12/10/118 Short recap: - There's not actually a locking issue, it's just lockdep being a bit too eager to complain about a possible deadlock. - Contrary to what I claimed the real problem is recursion on kn->count. Greg pointed me at sysfs_break_active_protection(), used by the scsi subsystem to allow a sysfs file to unbind itself. That would be a real deadlock, which isn't what's happening here. Also, breaking the active protection means we'd need to manually handle all the lifetime fun. - With Rafael we discussed the task_work approach, which kinda works, but has two downsides: It's a functional change for a lockdep annotation issue, and it won't work for the bind file (which needs to get the errno from the driver load function back to userspace). - Greg also asked why this never showed up: To hit this you need to unregister a 2nd driver from the unload code of your first driver. I guess only gpus do that. The bug has always been there, but only with a recent patch series did we add more locks so that lockdep built a chain from unbinding the snd-hda driver to the acpi_video_unregister call. Full lockdep splat: [12301.898799] ============================================ [12301.898805] WARNING: possible recursive locking detected [12301.898811] 4.20.0-rc7+ #84 Not tainted [12301.898815] -------------------------------------------- [12301.898821] bash/5297 is trying to acquire lock: [12301.898826] 00000000f61c6093 (kn->count#39){++++}, at: kernfs_remove_by_name_ns+0x3b/0x80 [12301.898841] but task is already holding lock: [12301.898847] 000000005f634021 (kn->count#39){++++}, at: kernfs_fop_write+0xdc/0x190 [12301.898856] other info that might help us debug this: [12301.898862] Possible unsafe locking scenario: [12301.898867] CPU0 [12301.898870] ---- [12301.898874] lock(kn->count#39); [12301.898879] lock(kn->count#39); [12301.898883] *** DEADLOCK *** [12301.898891] May be due to missing lock nesting notation [12301.898899] 5 locks held by bash/5297: [12301.898903] #0: 00000000cd800e54 (sb_writers#4){.+.+}, at: vfs_write+0x17f/0x1b0 [12301.898915] #1: 000000000465e7c2 (&of->mutex){+.+.}, at: kernfs_fop_write+0xd3/0x190 [12301.898925] #2: 000000005f634021 (kn->count#39){++++}, at: kernfs_fop_write+0xdc/0x190 [12301.898936] #3: 00000000414ef7ac (&dev->mutex){....}, at: device_release_driver_internal+0x34/0x240 [12301.898950] #4: 000000003218fbdf (register_count_mutex){+.+.}, at: acpi_video_unregister+0xe/0x40 [12301.898960] stack backtrace: [12301.898968] CPU: 1 PID: 5297 Comm: bash Not tainted 4.20.0-rc7+ #84 [12301.898974] Hardware name: Hewlett-Packard HP EliteBook 8460p/161C, BIOS 68SCF Ver. F.01 03/11/2011 [12301.898982] Call Trace: [12301.898989] dump_stack+0x67/0x9b [12301.898997] __lock_acquire+0x6ad/0x1410 [12301.899003] ? kernfs_remove_by_name_ns+0x3b/0x80 [12301.899010] ? find_held_lock+0x2d/0x90 [12301.899017] ? mutex_spin_on_owner+0xe4/0x150 [12301.899023] ? find_held_lock+0x2d/0x90 [12301.899030] ? lock_acquire+0x90/0x180 [12301.899036] lock_acquire+0x90/0x180 [12301.899042] ? kernfs_remove_by_name_ns+0x3b/0x80 [12301.899049] __kernfs_remove+0x296/0x310 [12301.899055] ? kernfs_remove_by_name_ns+0x3b/0x80 [12301.899060] ? kernfs_name_hash+0xd/0x80 [12301.899066] ? kernfs_find_ns+0x6c/0x100 [12301.899073] kernfs_remove_by_name_ns+0x3b/0x80 [12301.899080] bus_remove_driver+0x92/0xa0 [12301.899085] acpi_video_unregister+0x24/0x40 [12301.899127] i915_driver_unload+0x42/0x130 [i915] [12301.899160] i915_pci_remove+0x19/0x30 [i915] [12301.899169] pci_device_remove+0x36/0xb0 [12301.899176] device_release_driver_internal+0x185/0x240 [12301.899183] unbind_store+0xaf/0x180 [12301.899189] kernfs_fop_write+0x104/0x190 [12301.899195] __vfs_write+0x31/0x180 [12301.899203] ? rcu_read_lock_sched_held+0x6f/0x80 [12301.899209] ? rcu_sync_lockdep_assert+0x29/0x50 [12301.899216] ? __sb_start_write+0x13c/0x1a0 [12301.899221] ? vfs_write+0x17f/0x1b0 [12301.899227] vfs_write+0xb9/0x1b0 [12301.899233] ksys_write+0x50/0xc0 [12301.899239] do_syscall_64+0x4b/0x180 [12301.899247] entry_SYSCALL_64_after_hwframe+0x49/0xbe [12301.899253] RIP: 0033:0x7f452ac7f7a4 [12301.899259] Code: 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 80 00 00 00 00 8b 05 aa f0 2c 00 48 63 ff 85 c0 75 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 f3 c3 66 90 55 53 48 89 d5 48 89 f3 48 83 [12301.899273] RSP: 002b:00007ffceafa6918 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [12301.899282] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f452ac7f7a4 [12301.899288] RDX: 000000000000000d RSI: 00005612a1abf7c0 RDI: 0000000000000001 [12301.899295] RBP: 00005612a1abf7c0 R08: 000000000000000a R09: 00005612a1c46730 [12301.899301] R10: 000000000000000a R11: 0000000000000246 R12: 000000000000000d [12301.899308] R13: 0000000000000001 R14: 00007f452af4a740 R15: 000000000000000d Looking around I've noticed that usb and i2c already handle similar recursion problems, where a sysfs file can unbind the same type of sysfs somewhere else in the hierarchy. Relevant commits are: commit 356c05d58af05d582e634b54b40050c73609617b Author: Alan Stern <stern@rowland.harvard.edu> Date: Mon May 14 13:30:03 2012 -0400 sysfs: get rid of some lockdep false positives commit e9b526fe704812364bca07edd15eadeba163ebfb Author: Alexander Sverdlin <alexander.sverdlin@nsn.com> Date: Fri May 17 14:56:35 2013 +0200 i2c: suppress lockdep warning on delete_device Implement the same trick for driver bind/unbind. v2: Put the macro into bus.c (Greg). Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Ramalingam C <ramalingam.c@intel.com> Cc: Arend van Spriel <aspriel@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Geert Uytterhoeven <geert+renesas@glider.be> Cc: Bartosz Golaszewski <brgl@bgdev.pl> Cc: Heikki Krogerus <heikki.krogerus@linux.intel.com> Cc: Vivek Gautam <vivek.gautam@codeaurora.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-19 20:39:09 +08:00
static DRIVER_ATTR_IGNORE_LOCKDEP(unbind, S_IWUSR, NULL, unbind_store);
/*
* Manually attach a device to a driver.
* Note: the driver must want to bind to the device,
* it is not possible to override the driver's id table.
*/
static ssize_t bind_store(struct device_driver *drv, const char *buf,
size_t count)
{
struct bus_type *bus = bus_get(drv->bus);
struct device *dev;
int err = -ENODEV;
dev = bus_find_device_by_name(bus, NULL, buf);
if (dev && dev->driver == NULL && driver_match_device(drv, dev)) {
err = device_driver_attach(drv, dev);
if (err > 0) {
/* success */
err = count;
} else if (err == 0) {
/* driver didn't accept device */
err = -ENODEV;
}
}
put_device(dev);
bus_put(bus);
return err;
}
sysfs: Disable lockdep for driver bind/unbind files This is the much more correct fix for my earlier attempt at: https://lkml.org/lkml/2018/12/10/118 Short recap: - There's not actually a locking issue, it's just lockdep being a bit too eager to complain about a possible deadlock. - Contrary to what I claimed the real problem is recursion on kn->count. Greg pointed me at sysfs_break_active_protection(), used by the scsi subsystem to allow a sysfs file to unbind itself. That would be a real deadlock, which isn't what's happening here. Also, breaking the active protection means we'd need to manually handle all the lifetime fun. - With Rafael we discussed the task_work approach, which kinda works, but has two downsides: It's a functional change for a lockdep annotation issue, and it won't work for the bind file (which needs to get the errno from the driver load function back to userspace). - Greg also asked why this never showed up: To hit this you need to unregister a 2nd driver from the unload code of your first driver. I guess only gpus do that. The bug has always been there, but only with a recent patch series did we add more locks so that lockdep built a chain from unbinding the snd-hda driver to the acpi_video_unregister call. Full lockdep splat: [12301.898799] ============================================ [12301.898805] WARNING: possible recursive locking detected [12301.898811] 4.20.0-rc7+ #84 Not tainted [12301.898815] -------------------------------------------- [12301.898821] bash/5297 is trying to acquire lock: [12301.898826] 00000000f61c6093 (kn->count#39){++++}, at: kernfs_remove_by_name_ns+0x3b/0x80 [12301.898841] but task is already holding lock: [12301.898847] 000000005f634021 (kn->count#39){++++}, at: kernfs_fop_write+0xdc/0x190 [12301.898856] other info that might help us debug this: [12301.898862] Possible unsafe locking scenario: [12301.898867] CPU0 [12301.898870] ---- [12301.898874] lock(kn->count#39); [12301.898879] lock(kn->count#39); [12301.898883] *** DEADLOCK *** [12301.898891] May be due to missing lock nesting notation [12301.898899] 5 locks held by bash/5297: [12301.898903] #0: 00000000cd800e54 (sb_writers#4){.+.+}, at: vfs_write+0x17f/0x1b0 [12301.898915] #1: 000000000465e7c2 (&of->mutex){+.+.}, at: kernfs_fop_write+0xd3/0x190 [12301.898925] #2: 000000005f634021 (kn->count#39){++++}, at: kernfs_fop_write+0xdc/0x190 [12301.898936] #3: 00000000414ef7ac (&dev->mutex){....}, at: device_release_driver_internal+0x34/0x240 [12301.898950] #4: 000000003218fbdf (register_count_mutex){+.+.}, at: acpi_video_unregister+0xe/0x40 [12301.898960] stack backtrace: [12301.898968] CPU: 1 PID: 5297 Comm: bash Not tainted 4.20.0-rc7+ #84 [12301.898974] Hardware name: Hewlett-Packard HP EliteBook 8460p/161C, BIOS 68SCF Ver. F.01 03/11/2011 [12301.898982] Call Trace: [12301.898989] dump_stack+0x67/0x9b [12301.898997] __lock_acquire+0x6ad/0x1410 [12301.899003] ? kernfs_remove_by_name_ns+0x3b/0x80 [12301.899010] ? find_held_lock+0x2d/0x90 [12301.899017] ? mutex_spin_on_owner+0xe4/0x150 [12301.899023] ? find_held_lock+0x2d/0x90 [12301.899030] ? lock_acquire+0x90/0x180 [12301.899036] lock_acquire+0x90/0x180 [12301.899042] ? kernfs_remove_by_name_ns+0x3b/0x80 [12301.899049] __kernfs_remove+0x296/0x310 [12301.899055] ? kernfs_remove_by_name_ns+0x3b/0x80 [12301.899060] ? kernfs_name_hash+0xd/0x80 [12301.899066] ? kernfs_find_ns+0x6c/0x100 [12301.899073] kernfs_remove_by_name_ns+0x3b/0x80 [12301.899080] bus_remove_driver+0x92/0xa0 [12301.899085] acpi_video_unregister+0x24/0x40 [12301.899127] i915_driver_unload+0x42/0x130 [i915] [12301.899160] i915_pci_remove+0x19/0x30 [i915] [12301.899169] pci_device_remove+0x36/0xb0 [12301.899176] device_release_driver_internal+0x185/0x240 [12301.899183] unbind_store+0xaf/0x180 [12301.899189] kernfs_fop_write+0x104/0x190 [12301.899195] __vfs_write+0x31/0x180 [12301.899203] ? rcu_read_lock_sched_held+0x6f/0x80 [12301.899209] ? rcu_sync_lockdep_assert+0x29/0x50 [12301.899216] ? __sb_start_write+0x13c/0x1a0 [12301.899221] ? vfs_write+0x17f/0x1b0 [12301.899227] vfs_write+0xb9/0x1b0 [12301.899233] ksys_write+0x50/0xc0 [12301.899239] do_syscall_64+0x4b/0x180 [12301.899247] entry_SYSCALL_64_after_hwframe+0x49/0xbe [12301.899253] RIP: 0033:0x7f452ac7f7a4 [12301.899259] Code: 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 80 00 00 00 00 8b 05 aa f0 2c 00 48 63 ff 85 c0 75 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 f3 c3 66 90 55 53 48 89 d5 48 89 f3 48 83 [12301.899273] RSP: 002b:00007ffceafa6918 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [12301.899282] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f452ac7f7a4 [12301.899288] RDX: 000000000000000d RSI: 00005612a1abf7c0 RDI: 0000000000000001 [12301.899295] RBP: 00005612a1abf7c0 R08: 000000000000000a R09: 00005612a1c46730 [12301.899301] R10: 000000000000000a R11: 0000000000000246 R12: 000000000000000d [12301.899308] R13: 0000000000000001 R14: 00007f452af4a740 R15: 000000000000000d Looking around I've noticed that usb and i2c already handle similar recursion problems, where a sysfs file can unbind the same type of sysfs somewhere else in the hierarchy. Relevant commits are: commit 356c05d58af05d582e634b54b40050c73609617b Author: Alan Stern <stern@rowland.harvard.edu> Date: Mon May 14 13:30:03 2012 -0400 sysfs: get rid of some lockdep false positives commit e9b526fe704812364bca07edd15eadeba163ebfb Author: Alexander Sverdlin <alexander.sverdlin@nsn.com> Date: Fri May 17 14:56:35 2013 +0200 i2c: suppress lockdep warning on delete_device Implement the same trick for driver bind/unbind. v2: Put the macro into bus.c (Greg). Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Ramalingam C <ramalingam.c@intel.com> Cc: Arend van Spriel <aspriel@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Geert Uytterhoeven <geert+renesas@glider.be> Cc: Bartosz Golaszewski <brgl@bgdev.pl> Cc: Heikki Krogerus <heikki.krogerus@linux.intel.com> Cc: Vivek Gautam <vivek.gautam@codeaurora.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-19 20:39:09 +08:00
static DRIVER_ATTR_IGNORE_LOCKDEP(bind, S_IWUSR, NULL, bind_store);
static ssize_t drivers_autoprobe_show(struct bus_type *bus, char *buf)
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
{
return sysfs_emit(buf, "%d\n", bus->p->drivers_autoprobe);
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
}
static ssize_t drivers_autoprobe_store(struct bus_type *bus,
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
const char *buf, size_t count)
{
if (buf[0] == '0')
bus->p->drivers_autoprobe = 0;
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
else
bus->p->drivers_autoprobe = 1;
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
return count;
}
static ssize_t drivers_probe_store(struct bus_type *bus,
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
const char *buf, size_t count)
{
struct device *dev;
driver core: Fix unbalanced device reference in drivers_probe bus_find_device_by_name() acquires a device reference which is never released. This results in an object leak, which on older kernels results in failure to release all resources of PCI devices. libvirt uses drivers_probe to re-attach devices to the host after assignment and is therefore a common trigger for this leak. Example: # cd /sys/bus/pci/ # dmesg -C # echo 1 > devices/0000\:01\:00.0/sriov_numvfs # echo 0 > devices/0000\:01\:00.0/sriov_numvfs # dmesg | grep 01:10 pci 0000:01:10.0: [8086:10ca] type 00 class 0x020000 kobject: '0000:01:10.0' (ffff8801d79cd0a8): kobject_add_internal: parent: '0000:00:01.0', set: 'devices' kobject: '0000:01:10.0' (ffff8801d79cd0a8): kobject_uevent_env kobject: '0000:01:10.0' (ffff8801d79cd0a8): fill_kobj_path: path = '/devices/pci0000:00/0000:00:01.0/0000:01:10.0' kobject: '0000:01:10.0' (ffff8801d79cd0a8): kobject_uevent_env kobject: '0000:01:10.0' (ffff8801d79cd0a8): fill_kobj_path: path = '/devices/pci0000:00/0000:00:01.0/0000:01:10.0' kobject: '0000:01:10.0' (ffff8801d79cd0a8): kobject_uevent_env kobject: '0000:01:10.0' (ffff8801d79cd0a8): fill_kobj_path: path = '/devices/pci0000:00/0000:00:01.0/0000:01:10.0' kobject: '0000:01:10.0' (ffff8801d79cd0a8): kobject_cleanup, parent (null) kobject: '0000:01:10.0' (ffff8801d79cd0a8): calling ktype release kobject: '0000:01:10.0': free name [kobject freed as expected] # dmesg -C # echo 1 > devices/0000\:01\:00.0/sriov_numvfs # echo 0000:01:10.0 > drivers_probe # echo 0 > devices/0000\:01\:00.0/sriov_numvfs # dmesg | grep 01:10 pci 0000:01:10.0: [8086:10ca] type 00 class 0x020000 kobject: '0000:01:10.0' (ffff8801d79ce0a8): kobject_add_internal: parent: '0000:00:01.0', set: 'devices' kobject: '0000:01:10.0' (ffff8801d79ce0a8): kobject_uevent_env kobject: '0000:01:10.0' (ffff8801d79ce0a8): fill_kobj_path: path = '/devices/pci0000:00/0000:00:01.0/0000:01:10.0' kobject: '0000:01:10.0' (ffff8801d79ce0a8): kobject_uevent_env kobject: '0000:01:10.0' (ffff8801d79ce0a8): fill_kobj_path: path = '/devices/pci0000:00/0000:00:01.0/0000:01:10.0' kobject: '0000:01:10.0' (ffff8801d79ce0a8): kobject_uevent_env kobject: '0000:01:10.0' (ffff8801d79ce0a8): fill_kobj_path: path = '/devices/pci0000:00/0000:00:01.0/0000:01:10.0' [no free] Signed-off-by: Alex Williamson <alex.williamson@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-01 01:13:07 +08:00
int err = -EINVAL;
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
dev = bus_find_device_by_name(bus, NULL, buf);
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
if (!dev)
return -ENODEV;
driver core: Fix unbalanced device reference in drivers_probe bus_find_device_by_name() acquires a device reference which is never released. This results in an object leak, which on older kernels results in failure to release all resources of PCI devices. libvirt uses drivers_probe to re-attach devices to the host after assignment and is therefore a common trigger for this leak. Example: # cd /sys/bus/pci/ # dmesg -C # echo 1 > devices/0000\:01\:00.0/sriov_numvfs # echo 0 > devices/0000\:01\:00.0/sriov_numvfs # dmesg | grep 01:10 pci 0000:01:10.0: [8086:10ca] type 00 class 0x020000 kobject: '0000:01:10.0' (ffff8801d79cd0a8): kobject_add_internal: parent: '0000:00:01.0', set: 'devices' kobject: '0000:01:10.0' (ffff8801d79cd0a8): kobject_uevent_env kobject: '0000:01:10.0' (ffff8801d79cd0a8): fill_kobj_path: path = '/devices/pci0000:00/0000:00:01.0/0000:01:10.0' kobject: '0000:01:10.0' (ffff8801d79cd0a8): kobject_uevent_env kobject: '0000:01:10.0' (ffff8801d79cd0a8): fill_kobj_path: path = '/devices/pci0000:00/0000:00:01.0/0000:01:10.0' kobject: '0000:01:10.0' (ffff8801d79cd0a8): kobject_uevent_env kobject: '0000:01:10.0' (ffff8801d79cd0a8): fill_kobj_path: path = '/devices/pci0000:00/0000:00:01.0/0000:01:10.0' kobject: '0000:01:10.0' (ffff8801d79cd0a8): kobject_cleanup, parent (null) kobject: '0000:01:10.0' (ffff8801d79cd0a8): calling ktype release kobject: '0000:01:10.0': free name [kobject freed as expected] # dmesg -C # echo 1 > devices/0000\:01\:00.0/sriov_numvfs # echo 0000:01:10.0 > drivers_probe # echo 0 > devices/0000\:01\:00.0/sriov_numvfs # dmesg | grep 01:10 pci 0000:01:10.0: [8086:10ca] type 00 class 0x020000 kobject: '0000:01:10.0' (ffff8801d79ce0a8): kobject_add_internal: parent: '0000:00:01.0', set: 'devices' kobject: '0000:01:10.0' (ffff8801d79ce0a8): kobject_uevent_env kobject: '0000:01:10.0' (ffff8801d79ce0a8): fill_kobj_path: path = '/devices/pci0000:00/0000:00:01.0/0000:01:10.0' kobject: '0000:01:10.0' (ffff8801d79ce0a8): kobject_uevent_env kobject: '0000:01:10.0' (ffff8801d79ce0a8): fill_kobj_path: path = '/devices/pci0000:00/0000:00:01.0/0000:01:10.0' kobject: '0000:01:10.0' (ffff8801d79ce0a8): kobject_uevent_env kobject: '0000:01:10.0' (ffff8801d79ce0a8): fill_kobj_path: path = '/devices/pci0000:00/0000:00:01.0/0000:01:10.0' [no free] Signed-off-by: Alex Williamson <alex.williamson@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-01 01:13:07 +08:00
if (bus_rescan_devices_helper(dev, NULL) == 0)
err = count;
put_device(dev);
return err;
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
}
static struct device *next_device(struct klist_iter *i)
{
struct klist_node *n = klist_next(i);
struct device *dev = NULL;
struct device_private *dev_prv;
if (n) {
dev_prv = to_device_private_bus(n);
dev = dev_prv->device;
}
return dev;
}
/**
* bus_for_each_dev - device iterator.
* @bus: bus type.
* @start: device to start iterating from.
* @data: data for the callback.
* @fn: function to be called for each device.
*
* Iterate over @bus's list of devices, and call @fn for each,
* passing it @data. If @start is not NULL, we use that device to
* begin iterating from.
*
* We check the return of @fn each time. If it returns anything
* other than 0, we break out and return that value.
*
* NOTE: The device that returns a non-zero value is not retained
* in any way, nor is its refcount incremented. If the caller needs
* to retain this data, it should do so, and increment the reference
* count in the supplied callback.
*/
int bus_for_each_dev(struct bus_type *bus, struct device *start,
void *data, int (*fn)(struct device *, void *))
{
struct klist_iter i;
struct device *dev;
int error = 0;
if (!bus || !bus->p)
return -EINVAL;
klist_iter_init_node(&bus->p->klist_devices, &i,
(start ? &start->p->knode_bus : NULL));
while (!error && (dev = next_device(&i)))
error = fn(dev, data);
klist_iter_exit(&i);
return error;
}
EXPORT_SYMBOL_GPL(bus_for_each_dev);
/**
* bus_find_device - device iterator for locating a particular device.
* @bus: bus type
* @start: Device to begin with
* @data: Data to pass to match function
* @match: Callback function to check device
*
* This is similar to the bus_for_each_dev() function above, but it
* returns a reference to a device that is 'found' for later use, as
* determined by the @match callback.
*
* The callback should return 0 if the device doesn't match and non-zero
* if it does. If the callback returns non-zero, this function will
* return to the caller and not iterate over any more devices.
*/
struct device *bus_find_device(struct bus_type *bus,
bus_find_device: Unify the match callback with class_find_device There is an arbitrary difference between the prototypes of bus_find_device() and class_find_device() preventing their callers from passing the same pair of data and match() arguments to both of them, which is the const qualifier used in the prototype of class_find_device(). If that qualifier is also used in the bus_find_device() prototype, it will be possible to pass the same match() callback function to both bus_find_device() and class_find_device(), which will allow some optimizations to be made in order to avoid code duplication going forward. Also with that, constify the "data" parameter as it is passed as a const to the match function. For this reason, change the prototype of bus_find_device() to match the prototype of class_find_device() and adjust its callers to use the const qualifier in accordance with the new prototype of it. Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andrew Lunn <andrew@lunn.ch> Cc: Andreas Noever <andreas.noever@gmail.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Corey Minyard <minyard@acm.org> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: David Kershner <david.kershner@unisys.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: David Airlie <airlied@linux.ie> Cc: Felipe Balbi <balbi@kernel.org> Cc: Frank Rowand <frowand.list@gmail.com> Cc: Grygorii Strashko <grygorii.strashko@ti.com> Cc: Harald Freudenberger <freude@linux.ibm.com> Cc: Hartmut Knaack <knaack.h@gmx.de> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jonathan Cameron <jic23@kernel.org> Cc: "James E.J. Bottomley" <jejb@linux.ibm.com> Cc: Len Brown <lenb@kernel.org> Cc: Mark Brown <broonie@kernel.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michael Jamet <michael.jamet@intel.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Peter Oberparleiter <oberpar@linux.ibm.com> Cc: Sebastian Ott <sebott@linux.ibm.com> Cc: Srinivas Kandagatla <srinivas.kandagatla@linaro.org> Cc: Yehezkel Bernat <YehezkelShB@gmail.com> Cc: rafael@kernel.org Acked-by: Corey Minyard <minyard@acm.org> Acked-by: David Kershner <david.kershner@unisys.com> Acked-by: Mark Brown <broonie@kernel.org> Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org> Acked-by: Wolfram Sang <wsa@the-dreams.de> # for the I2C parts Acked-by: Rob Herring <robh@kernel.org> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-06-15 01:53:59 +08:00
struct device *start, const void *data,
int (*match)(struct device *dev, const void *data))
{
struct klist_iter i;
struct device *dev;
if (!bus || !bus->p)
return NULL;
klist_iter_init_node(&bus->p->klist_devices, &i,
(start ? &start->p->knode_bus : NULL));
while ((dev = next_device(&i)))
if (match(dev, data) && get_device(dev))
break;
klist_iter_exit(&i);
return dev;
}
EXPORT_SYMBOL_GPL(bus_find_device);
/**
* subsys_find_device_by_id - find a device with a specific enumeration number
* @subsys: subsystem
* @id: index 'id' in struct device
* @hint: device to check first
*
* Check the hint's next object and if it is a match return it directly,
* otherwise, fall back to a full list search. Either way a reference for
* the returned object is taken.
*/
struct device *subsys_find_device_by_id(struct bus_type *subsys, unsigned int id,
struct device *hint)
{
struct klist_iter i;
struct device *dev;
if (!subsys)
return NULL;
if (hint) {
klist_iter_init_node(&subsys->p->klist_devices, &i, &hint->p->knode_bus);
dev = next_device(&i);
if (dev && dev->id == id && get_device(dev)) {
klist_iter_exit(&i);
return dev;
}
klist_iter_exit(&i);
}
klist_iter_init_node(&subsys->p->klist_devices, &i, NULL);
while ((dev = next_device(&i))) {
if (dev->id == id && get_device(dev)) {
klist_iter_exit(&i);
return dev;
}
}
klist_iter_exit(&i);
return NULL;
}
EXPORT_SYMBOL_GPL(subsys_find_device_by_id);
static struct device_driver *next_driver(struct klist_iter *i)
{
struct klist_node *n = klist_next(i);
struct driver_private *drv_priv;
if (n) {
drv_priv = container_of(n, struct driver_private, knode_bus);
return drv_priv->driver;
}
return NULL;
}
/**
* bus_for_each_drv - driver iterator
* @bus: bus we're dealing with.
* @start: driver to start iterating on.
* @data: data to pass to the callback.
* @fn: function to call for each driver.
*
* This is nearly identical to the device iterator above.
* We iterate over each driver that belongs to @bus, and call
* @fn for each. If @fn returns anything but 0, we break out
* and return it. If @start is not NULL, we use it as the head
* of the list.
*
* NOTE: we don't return the driver that returns a non-zero
* value, nor do we leave the reference count incremented for that
* driver. If the caller needs to know that info, it must set it
* in the callback. It must also be sure to increment the refcount
* so it doesn't disappear before returning to the caller.
*/
int bus_for_each_drv(struct bus_type *bus, struct device_driver *start,
void *data, int (*fn)(struct device_driver *, void *))
{
struct klist_iter i;
struct device_driver *drv;
int error = 0;
if (!bus)
return -EINVAL;
klist_iter_init_node(&bus->p->klist_drivers, &i,
start ? &start->p->knode_bus : NULL);
while ((drv = next_driver(&i)) && !error)
error = fn(drv, data);
klist_iter_exit(&i);
return error;
}
EXPORT_SYMBOL_GPL(bus_for_each_drv);
/**
* bus_add_device - add device to bus
* @dev: device being added
*
* - Add device's bus attributes.
* - Create links to device's bus.
* - Add the device to its bus's list of devices.
*/
int bus_add_device(struct device *dev)
{
struct bus_type *bus = bus_get(dev->bus);
int error = 0;
if (bus) {
pr_debug("bus: '%s': add device %s\n", bus->name, dev_name(dev));
error = device_add_groups(dev, bus->dev_groups);
if (error)
goto out_put;
error = sysfs_create_link(&bus->p->devices_kset->kobj,
&dev->kobj, dev_name(dev));
if (error)
goto out_groups;
error = sysfs_create_link(&dev->kobj,
&dev->bus->p->subsys.kobj, "subsystem");
if (error)
goto out_subsys;
klist_add_tail(&dev->p->knode_bus, &bus->p->klist_devices);
}
return 0;
out_subsys:
sysfs_remove_link(&bus->p->devices_kset->kobj, dev_name(dev));
out_groups:
device_remove_groups(dev, bus->dev_groups);
out_put:
bus_put(dev->bus);
return error;
}
/**
* bus_probe_device - probe drivers for a new device
* @dev: device to probe
*
* - Automatically probe for a driver if the bus allows it.
*/
void bus_probe_device(struct device *dev)
{
struct bus_type *bus = dev->bus;
struct subsys_interface *sif;
if (!bus)
return;
if (bus->p->drivers_autoprobe)
device_initial_probe(dev);
mutex_lock(&bus->p->mutex);
list_for_each_entry(sif, &bus->p->interfaces, node)
if (sif->add_dev)
sif->add_dev(dev, sif);
mutex_unlock(&bus->p->mutex);
}
/**
* bus_remove_device - remove device from bus
* @dev: device to be removed
*
* - Remove device from all interfaces.
* - Remove symlink from bus' directory.
* - Delete device from bus's list.
* - Detach from its driver.
* - Drop reference taken in bus_add_device().
*/
void bus_remove_device(struct device *dev)
{
struct bus_type *bus = dev->bus;
struct subsys_interface *sif;
if (!bus)
return;
mutex_lock(&bus->p->mutex);
list_for_each_entry(sif, &bus->p->interfaces, node)
if (sif->remove_dev)
sif->remove_dev(dev, sif);
mutex_unlock(&bus->p->mutex);
sysfs_remove_link(&dev->kobj, "subsystem");
sysfs_remove_link(&dev->bus->p->devices_kset->kobj,
dev_name(dev));
device_remove_groups(dev, dev->bus->dev_groups);
if (klist_node_attached(&dev->p->knode_bus))
klist_del(&dev->p->knode_bus);
pr_debug("bus: '%s': remove device %s\n",
dev->bus->name, dev_name(dev));
device_release_driver(dev);
bus_put(dev->bus);
}
static int __must_check add_bind_files(struct device_driver *drv)
{
int ret;
ret = driver_create_file(drv, &driver_attr_unbind);
if (ret == 0) {
ret = driver_create_file(drv, &driver_attr_bind);
if (ret)
driver_remove_file(drv, &driver_attr_unbind);
}
return ret;
}
static void remove_bind_files(struct device_driver *drv)
{
driver_remove_file(drv, &driver_attr_bind);
driver_remove_file(drv, &driver_attr_unbind);
}
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
static BUS_ATTR_WO(drivers_probe);
static BUS_ATTR_RW(drivers_autoprobe);
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
static int add_probe_files(struct bus_type *bus)
{
int retval;
retval = bus_create_file(bus, &bus_attr_drivers_probe);
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
if (retval)
goto out;
retval = bus_create_file(bus, &bus_attr_drivers_autoprobe);
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
if (retval)
bus_remove_file(bus, &bus_attr_drivers_probe);
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
out:
return retval;
}
static void remove_probe_files(struct bus_type *bus)
{
bus_remove_file(bus, &bus_attr_drivers_autoprobe);
bus_remove_file(bus, &bus_attr_drivers_probe);
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
}
static ssize_t uevent_store(struct device_driver *drv, const char *buf,
size_t count)
{
int rc;
rc = kobject_synth_uevent(&drv->p->kobj, buf, count);
return rc ? rc : count;
}
static DRIVER_ATTR_WO(uevent);
/**
* bus_add_driver - Add a driver to the bus.
* @drv: driver.
*/
int bus_add_driver(struct device_driver *drv)
{
struct bus_type *bus;
struct driver_private *priv;
int error = 0;
bus = bus_get(drv->bus);
if (!bus)
return -EINVAL;
pr_debug("bus: '%s': add driver %s\n", bus->name, drv->name);
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (!priv) {
error = -ENOMEM;
goto out_put_bus;
}
klist_init(&priv->klist_devices, NULL, NULL);
priv->driver = drv;
drv->p = priv;
priv->kobj.kset = bus->p->drivers_kset;
error = kobject_init_and_add(&priv->kobj, &driver_ktype, NULL,
"%s", drv->name);
if (error)
goto out_unregister;
klist_add_tail(&priv->knode_bus, &bus->p->klist_drivers);
if (drv->bus->p->drivers_autoprobe) {
error = driver_attach(drv);
if (error)
goto out_unregister;
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
}
module_add_driver(drv->owner, drv);
error = driver_create_file(drv, &driver_attr_uevent);
if (error) {
printk(KERN_ERR "%s: uevent attr (%s) failed\n",
__func__, drv->name);
}
error = driver_add_groups(drv, bus->drv_groups);
if (error) {
/* How the hell do we get out of this pickle? Give up */
printk(KERN_ERR "%s: driver_add_groups(%s) failed\n",
__func__, drv->name);
}
if (!drv->suppress_bind_attrs) {
error = add_bind_files(drv);
if (error) {
/* Ditto */
printk(KERN_ERR "%s: add_bind_files(%s) failed\n",
__func__, drv->name);
}
}
return 0;
out_unregister:
kobject_put(&priv->kobj);
/* drv->p is freed in driver_release() */
drv->p = NULL;
out_put_bus:
bus_put(bus);
return error;
}
/**
* bus_remove_driver - delete driver from bus's knowledge.
* @drv: driver.
*
* Detach the driver from the devices it controls, and remove
* it from its bus's list of drivers. Finally, we drop the reference
* to the bus we took in bus_add_driver().
*/
void bus_remove_driver(struct device_driver *drv)
{
if (!drv->bus)
return;
if (!drv->suppress_bind_attrs)
remove_bind_files(drv);
driver_remove_groups(drv, drv->bus->drv_groups);
driver_remove_file(drv, &driver_attr_uevent);
klist_remove(&drv->p->knode_bus);
pr_debug("bus: '%s': remove driver %s\n", drv->bus->name, drv->name);
driver_detach(drv);
module_remove_driver(drv);
kobject_put(&drv->p->kobj);
bus_put(drv->bus);
}
/* Helper for bus_rescan_devices's iter */
static int __must_check bus_rescan_devices_helper(struct device *dev,
void *data)
{
int ret = 0;
[PATCH] Hold the device's parent's lock during probe and remove This patch (as604) makes the driver core hold a device's parent's lock as well as the device's lock during calls to the probe and remove methods in a driver. This facility is needed by USB device drivers, owing to the peculiar way USB devices work: A device provides multiple interfaces, and drivers are bound to interfaces rather than to devices; Nevertheless a reset, reset-configuration, suspend, or resume affects the entire device and requires the caller to hold the lock for the device, not just a lock for one of the interfaces. Since a USB driver's probe method is always called with the interface lock held, the locking order rules (always lock parent before child) prevent these methods from acquiring the device lock. The solution provided here is to call all probe and remove methods, for all devices (not just USB), with the parent lock already acquired. Although currently only the USB subsystem requires these changes, people have mentioned in prior discussion that the overhead of acquiring an extra semaphore in all the prove/remove sequences is not overly large. Up to now, the USB core has been using its own set of private semaphores. A followup patch will remove them, relying entirely on the device semaphores provided by the driver core. The code paths affected by this patch are: device_add and device_del: The USB core already holds the parent lock, so no actual change is needed. driver_register and driver_unregister: The driver core will now lock both the parent and the device before probing or removing. driver_bind and driver_unbind (in sysfs): These routines will now lock both the parent and the device before binding or unbinding. bus_rescan_devices: The helper routine will lock the parent before probing a device. I have not tested this patch for conflicts with other subsystems. As far as I can see, the only possibility of conflict would lie in the bus_rescan_devices pathway, and it seems pretty remote. Nevertheless, it would be good for this to get a lot of testing in -mm. Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2005-11-18 05:54:12 +08:00
if (!dev->driver) {
if (dev->parent && dev->bus->need_parent_lock)
Driver core: create lock/unlock functions for struct device In the future, we are going to be changing the lock type for struct device (once we get the lockdep infrastructure properly worked out) To make that changeover easier, and to possibly burry the lock in a different part of struct device, let's create some functions to lock and unlock a device so that no out-of-core code needs to be changed in the future. This patch creates the device_lock/unlock/trylock() functions, and converts all in-tree users to them. Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Jean Delvare <khali@linux-fr.org> Cc: Dave Young <hidave.darkstar@gmail.com> Cc: Ming Lei <tom.leiming@gmail.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Phil Carmody <ext-phil.2.carmody@nokia.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Cornelia Huck <cornelia.huck@de.ibm.com> Cc: Rafael J. Wysocki <rjw@sisk.pl> Cc: Pavel Machek <pavel@ucw.cz> Cc: Len Brown <len.brown@intel.com> Cc: Magnus Damm <damm@igel.co.jp> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: Randy Dunlap <randy.dunlap@oracle.com> Cc: Stefan Richter <stefanr@s5r6.in-berlin.de> Cc: David Brownell <dbrownell@users.sourceforge.net> Cc: Vegard Nossum <vegard.nossum@gmail.com> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Cc: Alex Chiang <achiang@hp.com> Cc: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andrew Patterson <andrew.patterson@hp.com> Cc: Yu Zhao <yu.zhao@intel.com> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Samuel Ortiz <sameo@linux.intel.com> Cc: Wolfram Sang <w.sang@pengutronix.de> Cc: CHENG Renquan <rqcheng@smu.edu.sg> Cc: Oliver Neukum <oliver@neukum.org> Cc: Frans Pop <elendil@planet.nl> Cc: David Vrabel <david.vrabel@csr.com> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-02-18 02:57:05 +08:00
device_lock(dev->parent);
ret = device_attach(dev);
if (dev->parent && dev->bus->need_parent_lock)
Driver core: create lock/unlock functions for struct device In the future, we are going to be changing the lock type for struct device (once we get the lockdep infrastructure properly worked out) To make that changeover easier, and to possibly burry the lock in a different part of struct device, let's create some functions to lock and unlock a device so that no out-of-core code needs to be changed in the future. This patch creates the device_lock/unlock/trylock() functions, and converts all in-tree users to them. Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Jean Delvare <khali@linux-fr.org> Cc: Dave Young <hidave.darkstar@gmail.com> Cc: Ming Lei <tom.leiming@gmail.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Phil Carmody <ext-phil.2.carmody@nokia.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Cornelia Huck <cornelia.huck@de.ibm.com> Cc: Rafael J. Wysocki <rjw@sisk.pl> Cc: Pavel Machek <pavel@ucw.cz> Cc: Len Brown <len.brown@intel.com> Cc: Magnus Damm <damm@igel.co.jp> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: Randy Dunlap <randy.dunlap@oracle.com> Cc: Stefan Richter <stefanr@s5r6.in-berlin.de> Cc: David Brownell <dbrownell@users.sourceforge.net> Cc: Vegard Nossum <vegard.nossum@gmail.com> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Cc: Alex Chiang <achiang@hp.com> Cc: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andrew Patterson <andrew.patterson@hp.com> Cc: Yu Zhao <yu.zhao@intel.com> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Samuel Ortiz <sameo@linux.intel.com> Cc: Wolfram Sang <w.sang@pengutronix.de> Cc: CHENG Renquan <rqcheng@smu.edu.sg> Cc: Oliver Neukum <oliver@neukum.org> Cc: Frans Pop <elendil@planet.nl> Cc: David Vrabel <david.vrabel@csr.com> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-02-18 02:57:05 +08:00
device_unlock(dev->parent);
[PATCH] Hold the device's parent's lock during probe and remove This patch (as604) makes the driver core hold a device's parent's lock as well as the device's lock during calls to the probe and remove methods in a driver. This facility is needed by USB device drivers, owing to the peculiar way USB devices work: A device provides multiple interfaces, and drivers are bound to interfaces rather than to devices; Nevertheless a reset, reset-configuration, suspend, or resume affects the entire device and requires the caller to hold the lock for the device, not just a lock for one of the interfaces. Since a USB driver's probe method is always called with the interface lock held, the locking order rules (always lock parent before child) prevent these methods from acquiring the device lock. The solution provided here is to call all probe and remove methods, for all devices (not just USB), with the parent lock already acquired. Although currently only the USB subsystem requires these changes, people have mentioned in prior discussion that the overhead of acquiring an extra semaphore in all the prove/remove sequences is not overly large. Up to now, the USB core has been using its own set of private semaphores. A followup patch will remove them, relying entirely on the device semaphores provided by the driver core. The code paths affected by this patch are: device_add and device_del: The USB core already holds the parent lock, so no actual change is needed. driver_register and driver_unregister: The driver core will now lock both the parent and the device before probing or removing. driver_bind and driver_unbind (in sysfs): These routines will now lock both the parent and the device before binding or unbinding. bus_rescan_devices: The helper routine will lock the parent before probing a device. I have not tested this patch for conflicts with other subsystems. As far as I can see, the only possibility of conflict would lie in the bus_rescan_devices pathway, and it seems pretty remote. Nevertheless, it would be good for this to get a lot of testing in -mm. Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2005-11-18 05:54:12 +08:00
}
return ret < 0 ? ret : 0;
}
/**
* bus_rescan_devices - rescan devices on the bus for possible drivers
* @bus: the bus to scan.
*
* This function will look for devices on the bus with no driver
* attached and rescan it against existing drivers to see if it matches
* any by calling device_attach() for the unbound devices.
*/
int bus_rescan_devices(struct bus_type *bus)
{
return bus_for_each_dev(bus, NULL, NULL, bus_rescan_devices_helper);
}
EXPORT_SYMBOL_GPL(bus_rescan_devices);
/**
* device_reprobe - remove driver for a device and probe for a new driver
* @dev: the device to reprobe
*
* This function detaches the attached driver (if any) for the given
* device and restarts the driver probing process. It is intended
* to use if probing criteria changed during a devices lifetime and
* driver attachment should change accordingly.
*/
int device_reprobe(struct device *dev)
{
if (dev->driver)
device_driver_detach(dev);
return bus_rescan_devices_helper(dev, NULL);
}
EXPORT_SYMBOL_GPL(device_reprobe);
static int bus_add_groups(struct bus_type *bus,
const struct attribute_group **groups)
{
return sysfs_create_groups(&bus->p->subsys.kobj, groups);
}
static void bus_remove_groups(struct bus_type *bus,
const struct attribute_group **groups)
{
sysfs_remove_groups(&bus->p->subsys.kobj, groups);
}
static void klist_devices_get(struct klist_node *n)
{
struct device_private *dev_prv = to_device_private_bus(n);
struct device *dev = dev_prv->device;
get_device(dev);
}
static void klist_devices_put(struct klist_node *n)
{
struct device_private *dev_prv = to_device_private_bus(n);
struct device *dev = dev_prv->device;
put_device(dev);
}
static ssize_t bus_uevent_store(struct bus_type *bus,
const char *buf, size_t count)
{
int rc;
rc = kobject_synth_uevent(&bus->p->subsys.kobj, buf, count);
return rc ? rc : count;
}
/*
* "open code" the old BUS_ATTR() macro here. We want to use BUS_ATTR_WO()
* here, but can not use it as earlier in the file we have
* DEVICE_ATTR_WO(uevent), which would cause a clash with the with the store
* function name.
*/
static struct bus_attribute bus_attr_uevent = __ATTR(uevent, S_IWUSR, NULL,
bus_uevent_store);
/**
device: separate all subsys mutexes ca22e56d (driver-core: implement 'sysdev' functionality for regular devices and buses) has introduced bus_register macro with a static key to distinguish different subsys mutex classes. This however doesn't work for different subsys which use a common registering function. One example is subsys_system_register (and mce_device and cpu_device). In the end this leads to the following lockdep splat: [ 207.271924] ====================================================== [ 207.271932] [ INFO: possible circular locking dependency detected ] [ 207.271942] 3.9.0-rc1-0.7-default+ #34 Not tainted [ 207.271948] ------------------------------------------------------- [ 207.271957] bash/10493 is trying to acquire lock: [ 207.271963] (subsys mutex){+.+.+.}, at: [<ffffffff8134af27>] bus_remove_device+0x37/0x1c0 [ 207.271987] [ 207.271987] but task is already holding lock: [ 207.271995] (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff81046ccf>] cpu_hotplug_begin+0x2f/0x60 [ 207.272012] [ 207.272012] which lock already depends on the new lock. [ 207.272012] [ 207.272023] [ 207.272023] the existing dependency chain (in reverse order) is: [ 207.272033] [ 207.272033] -> #4 (cpu_hotplug.lock){+.+.+.}: [ 207.272044] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272056] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.272069] [<ffffffff81046ba9>] get_online_cpus+0x29/0x40 [ 207.272082] [<ffffffff81185210>] drain_all_stock+0x30/0x150 [ 207.272094] [<ffffffff811853da>] mem_cgroup_reclaim+0xaa/0xe0 [ 207.272104] [<ffffffff8118775e>] __mem_cgroup_try_charge+0x51e/0xcf0 [ 207.272114] [<ffffffff81188486>] mem_cgroup_charge_common+0x36/0x60 [ 207.272125] [<ffffffff811884da>] mem_cgroup_newpage_charge+0x2a/0x30 [ 207.272135] [<ffffffff81150531>] do_wp_page+0x231/0x830 [ 207.272147] [<ffffffff8115151e>] handle_pte_fault+0x19e/0x8d0 [ 207.272157] [<ffffffff81151da8>] handle_mm_fault+0x158/0x1e0 [ 207.272166] [<ffffffff814b6153>] do_page_fault+0x2a3/0x4e0 [ 207.272178] [<ffffffff814b2578>] page_fault+0x28/0x30 [ 207.272189] [ 207.272189] -> #3 (&mm->mmap_sem){++++++}: [ 207.272199] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272208] [<ffffffff8114c5ad>] might_fault+0x6d/0x90 [ 207.272218] [<ffffffff811a11e3>] filldir64+0xb3/0x120 [ 207.272229] [<ffffffffa013fc19>] call_filldir+0x89/0x130 [ext3] [ 207.272248] [<ffffffffa0140377>] ext3_readdir+0x6b7/0x7e0 [ext3] [ 207.272263] [<ffffffff811a1519>] vfs_readdir+0xa9/0xc0 [ 207.272273] [<ffffffff811a15cb>] sys_getdents64+0x9b/0x110 [ 207.272284] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272296] [ 207.272296] -> #2 (&type->i_mutex_dir_key#3){+.+.+.}: [ 207.272309] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272319] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.272329] [<ffffffff8119c254>] link_path_walk+0x6f4/0x9a0 [ 207.272339] [<ffffffff8119e7fa>] path_openat+0xba/0x470 [ 207.272349] [<ffffffff8119ecf8>] do_filp_open+0x48/0xa0 [ 207.272358] [<ffffffff8118d81c>] file_open_name+0xdc/0x110 [ 207.272369] [<ffffffff8118d885>] filp_open+0x35/0x40 [ 207.272378] [<ffffffff8135c76e>] _request_firmware+0x52e/0xb20 [ 207.272389] [<ffffffff8135cdd6>] request_firmware+0x16/0x20 [ 207.272399] [<ffffffffa03bdb91>] request_microcode_fw+0x61/0xd0 [microcode] [ 207.272416] [<ffffffffa03bd554>] microcode_init_cpu+0x104/0x150 [microcode] [ 207.272431] [<ffffffffa03bd61c>] mc_device_add+0x7c/0xb0 [microcode] [ 207.272444] [<ffffffff8134a419>] subsys_interface_register+0xc9/0x100 [ 207.272457] [<ffffffffa04fc0f4>] 0xffffffffa04fc0f4 [ 207.272472] [<ffffffff81000202>] do_one_initcall+0x42/0x180 [ 207.272485] [<ffffffff810bbeff>] load_module+0x19df/0x1b70 [ 207.272499] [<ffffffff810bc376>] sys_init_module+0xe6/0x130 [ 207.272511] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272523] [ 207.272523] -> #1 (umhelper_sem){++++.+}: [ 207.272537] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272548] [<ffffffff814ae9c4>] down_read+0x34/0x50 [ 207.272559] [<ffffffff81062bff>] usermodehelper_read_trylock+0x4f/0x100 [ 207.272575] [<ffffffff8135c7dd>] _request_firmware+0x59d/0xb20 [ 207.272587] [<ffffffff8135cdd6>] request_firmware+0x16/0x20 [ 207.272599] [<ffffffffa03bdb91>] request_microcode_fw+0x61/0xd0 [microcode] [ 207.272613] [<ffffffffa03bd554>] microcode_init_cpu+0x104/0x150 [microcode] [ 207.272627] [<ffffffffa03bd61c>] mc_device_add+0x7c/0xb0 [microcode] [ 207.272641] [<ffffffff8134a419>] subsys_interface_register+0xc9/0x100 [ 207.272654] [<ffffffffa04fc0f4>] 0xffffffffa04fc0f4 [ 207.272666] [<ffffffff81000202>] do_one_initcall+0x42/0x180 [ 207.272678] [<ffffffff810bbeff>] load_module+0x19df/0x1b70 [ 207.272690] [<ffffffff810bc376>] sys_init_module+0xe6/0x130 [ 207.272702] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272715] [ 207.272715] -> #0 (subsys mutex){+.+.+.}: [ 207.272729] [<ffffffff810ae002>] __lock_acquire+0x13b2/0x15f0 [ 207.272740] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272751] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.272763] [<ffffffff8134af27>] bus_remove_device+0x37/0x1c0 [ 207.272775] [<ffffffff81349114>] device_del+0x134/0x1f0 [ 207.272786] [<ffffffff813491f2>] device_unregister+0x22/0x60 [ 207.272798] [<ffffffff814a24ea>] mce_cpu_callback+0x15e/0x1ad [ 207.272812] [<ffffffff814b6402>] notifier_call_chain+0x72/0x130 [ 207.272824] [<ffffffff81073d6e>] __raw_notifier_call_chain+0xe/0x10 [ 207.272839] [<ffffffff81498f76>] _cpu_down+0x1d6/0x350 [ 207.272851] [<ffffffff81499130>] cpu_down+0x40/0x60 [ 207.272862] [<ffffffff8149cc55>] store_online+0x75/0xe0 [ 207.272874] [<ffffffff813474a0>] dev_attr_store+0x20/0x30 [ 207.272886] [<ffffffff812090d9>] sysfs_write_file+0xd9/0x150 [ 207.272900] [<ffffffff8118e10b>] vfs_write+0xcb/0x130 [ 207.272911] [<ffffffff8118e924>] sys_write+0x64/0xa0 [ 207.272923] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272936] [ 207.272936] other info that might help us debug this: [ 207.272936] [ 207.272952] Chain exists of: [ 207.272952] subsys mutex --> &mm->mmap_sem --> cpu_hotplug.lock [ 207.272952] [ 207.272973] Possible unsafe locking scenario: [ 207.272973] [ 207.272984] CPU0 CPU1 [ 207.272992] ---- ---- [ 207.273000] lock(cpu_hotplug.lock); [ 207.273009] lock(&mm->mmap_sem); [ 207.273020] lock(cpu_hotplug.lock); [ 207.273031] lock(subsys mutex); [ 207.273040] [ 207.273040] *** DEADLOCK *** [ 207.273040] [ 207.273055] 5 locks held by bash/10493: [ 207.273062] #0: (&buffer->mutex){+.+.+.}, at: [<ffffffff81209049>] sysfs_write_file+0x49/0x150 [ 207.273080] #1: (s_active#150){.+.+.+}, at: [<ffffffff812090c2>] sysfs_write_file+0xc2/0x150 [ 207.273099] #2: (x86_cpu_hotplug_driver_mutex){+.+.+.}, at: [<ffffffff81027557>] cpu_hotplug_driver_lock+0x17/0x20 [ 207.273121] #3: (cpu_add_remove_lock){+.+.+.}, at: [<ffffffff8149911c>] cpu_down+0x2c/0x60 [ 207.273140] #4: (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff81046ccf>] cpu_hotplug_begin+0x2f/0x60 [ 207.273158] [ 207.273158] stack backtrace: [ 207.273170] Pid: 10493, comm: bash Not tainted 3.9.0-rc1-0.7-default+ #34 [ 207.273180] Call Trace: [ 207.273192] [<ffffffff810ab373>] print_circular_bug+0x223/0x310 [ 207.273204] [<ffffffff810ae002>] __lock_acquire+0x13b2/0x15f0 [ 207.273216] [<ffffffff812086b0>] ? sysfs_hash_and_remove+0x60/0xc0 [ 207.273227] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.273239] [<ffffffff8134af27>] ? bus_remove_device+0x37/0x1c0 [ 207.273251] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.273263] [<ffffffff8134af27>] ? bus_remove_device+0x37/0x1c0 [ 207.273274] [<ffffffff812086b0>] ? sysfs_hash_and_remove+0x60/0xc0 [ 207.273286] [<ffffffff8134af27>] bus_remove_device+0x37/0x1c0 [ 207.273298] [<ffffffff81349114>] device_del+0x134/0x1f0 [ 207.273309] [<ffffffff813491f2>] device_unregister+0x22/0x60 [ 207.273321] [<ffffffff814a24ea>] mce_cpu_callback+0x15e/0x1ad [ 207.273332] [<ffffffff814b6402>] notifier_call_chain+0x72/0x130 [ 207.273344] [<ffffffff81073d6e>] __raw_notifier_call_chain+0xe/0x10 [ 207.273356] [<ffffffff81498f76>] _cpu_down+0x1d6/0x350 [ 207.273368] [<ffffffff81027557>] ? cpu_hotplug_driver_lock+0x17/0x20 [ 207.273380] [<ffffffff81499130>] cpu_down+0x40/0x60 [ 207.273391] [<ffffffff8149cc55>] store_online+0x75/0xe0 [ 207.273402] [<ffffffff813474a0>] dev_attr_store+0x20/0x30 [ 207.273413] [<ffffffff812090d9>] sysfs_write_file+0xd9/0x150 [ 207.273425] [<ffffffff8118e10b>] vfs_write+0xcb/0x130 [ 207.273436] [<ffffffff8118e924>] sys_write+0x64/0xa0 [ 207.273447] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b Which reports a false possitive deadlock because it sees: 1) load_module -> subsys_interface_register -> mc_deveice_add (*) -> subsys->p->mutex -> link_path_walk -> lookup_slow -> i_mutex 2) sys_write -> _cpu_down -> cpu_hotplug_begin -> cpu_hotplug.lock -> mce_cpu_callback -> mce_device_remove(**) -> device_unregister -> bus_remove_device -> subsys mutex 3) vfs_readdir -> i_mutex -> filldir64 -> might_fault -> might_lock_read(mmap_sem) -> page_fault -> mmap_sem -> drain_all_stock -> cpu_hotplug.lock but 1) takes cpu_subsys subsys (*) but 2) takes mce_device subsys (**) so the deadlock is not possible AFAICS. The fix is quite simple. We can pull the key inside bus_type structure because they are defined per device so the pointer will be unique as well. bus_register doesn't need to be a macro anymore so change it to the inline. We could get rid of __bus_register as there is no other caller but maybe somebody will want to use a different key so keep it around for now. Reported-by: Li Zefan <lizefan@huawei.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-03-13 00:21:19 +08:00
* bus_register - register a driver-core subsystem
* @bus: bus to register
*
* Once we have that, we register the bus with the kobject
* infrastructure, then register the children subsystems it has:
* the devices and drivers that belong to the subsystem.
*/
device: separate all subsys mutexes ca22e56d (driver-core: implement 'sysdev' functionality for regular devices and buses) has introduced bus_register macro with a static key to distinguish different subsys mutex classes. This however doesn't work for different subsys which use a common registering function. One example is subsys_system_register (and mce_device and cpu_device). In the end this leads to the following lockdep splat: [ 207.271924] ====================================================== [ 207.271932] [ INFO: possible circular locking dependency detected ] [ 207.271942] 3.9.0-rc1-0.7-default+ #34 Not tainted [ 207.271948] ------------------------------------------------------- [ 207.271957] bash/10493 is trying to acquire lock: [ 207.271963] (subsys mutex){+.+.+.}, at: [<ffffffff8134af27>] bus_remove_device+0x37/0x1c0 [ 207.271987] [ 207.271987] but task is already holding lock: [ 207.271995] (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff81046ccf>] cpu_hotplug_begin+0x2f/0x60 [ 207.272012] [ 207.272012] which lock already depends on the new lock. [ 207.272012] [ 207.272023] [ 207.272023] the existing dependency chain (in reverse order) is: [ 207.272033] [ 207.272033] -> #4 (cpu_hotplug.lock){+.+.+.}: [ 207.272044] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272056] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.272069] [<ffffffff81046ba9>] get_online_cpus+0x29/0x40 [ 207.272082] [<ffffffff81185210>] drain_all_stock+0x30/0x150 [ 207.272094] [<ffffffff811853da>] mem_cgroup_reclaim+0xaa/0xe0 [ 207.272104] [<ffffffff8118775e>] __mem_cgroup_try_charge+0x51e/0xcf0 [ 207.272114] [<ffffffff81188486>] mem_cgroup_charge_common+0x36/0x60 [ 207.272125] [<ffffffff811884da>] mem_cgroup_newpage_charge+0x2a/0x30 [ 207.272135] [<ffffffff81150531>] do_wp_page+0x231/0x830 [ 207.272147] [<ffffffff8115151e>] handle_pte_fault+0x19e/0x8d0 [ 207.272157] [<ffffffff81151da8>] handle_mm_fault+0x158/0x1e0 [ 207.272166] [<ffffffff814b6153>] do_page_fault+0x2a3/0x4e0 [ 207.272178] [<ffffffff814b2578>] page_fault+0x28/0x30 [ 207.272189] [ 207.272189] -> #3 (&mm->mmap_sem){++++++}: [ 207.272199] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272208] [<ffffffff8114c5ad>] might_fault+0x6d/0x90 [ 207.272218] [<ffffffff811a11e3>] filldir64+0xb3/0x120 [ 207.272229] [<ffffffffa013fc19>] call_filldir+0x89/0x130 [ext3] [ 207.272248] [<ffffffffa0140377>] ext3_readdir+0x6b7/0x7e0 [ext3] [ 207.272263] [<ffffffff811a1519>] vfs_readdir+0xa9/0xc0 [ 207.272273] [<ffffffff811a15cb>] sys_getdents64+0x9b/0x110 [ 207.272284] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272296] [ 207.272296] -> #2 (&type->i_mutex_dir_key#3){+.+.+.}: [ 207.272309] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272319] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.272329] [<ffffffff8119c254>] link_path_walk+0x6f4/0x9a0 [ 207.272339] [<ffffffff8119e7fa>] path_openat+0xba/0x470 [ 207.272349] [<ffffffff8119ecf8>] do_filp_open+0x48/0xa0 [ 207.272358] [<ffffffff8118d81c>] file_open_name+0xdc/0x110 [ 207.272369] [<ffffffff8118d885>] filp_open+0x35/0x40 [ 207.272378] [<ffffffff8135c76e>] _request_firmware+0x52e/0xb20 [ 207.272389] [<ffffffff8135cdd6>] request_firmware+0x16/0x20 [ 207.272399] [<ffffffffa03bdb91>] request_microcode_fw+0x61/0xd0 [microcode] [ 207.272416] [<ffffffffa03bd554>] microcode_init_cpu+0x104/0x150 [microcode] [ 207.272431] [<ffffffffa03bd61c>] mc_device_add+0x7c/0xb0 [microcode] [ 207.272444] [<ffffffff8134a419>] subsys_interface_register+0xc9/0x100 [ 207.272457] [<ffffffffa04fc0f4>] 0xffffffffa04fc0f4 [ 207.272472] [<ffffffff81000202>] do_one_initcall+0x42/0x180 [ 207.272485] [<ffffffff810bbeff>] load_module+0x19df/0x1b70 [ 207.272499] [<ffffffff810bc376>] sys_init_module+0xe6/0x130 [ 207.272511] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272523] [ 207.272523] -> #1 (umhelper_sem){++++.+}: [ 207.272537] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272548] [<ffffffff814ae9c4>] down_read+0x34/0x50 [ 207.272559] [<ffffffff81062bff>] usermodehelper_read_trylock+0x4f/0x100 [ 207.272575] [<ffffffff8135c7dd>] _request_firmware+0x59d/0xb20 [ 207.272587] [<ffffffff8135cdd6>] request_firmware+0x16/0x20 [ 207.272599] [<ffffffffa03bdb91>] request_microcode_fw+0x61/0xd0 [microcode] [ 207.272613] [<ffffffffa03bd554>] microcode_init_cpu+0x104/0x150 [microcode] [ 207.272627] [<ffffffffa03bd61c>] mc_device_add+0x7c/0xb0 [microcode] [ 207.272641] [<ffffffff8134a419>] subsys_interface_register+0xc9/0x100 [ 207.272654] [<ffffffffa04fc0f4>] 0xffffffffa04fc0f4 [ 207.272666] [<ffffffff81000202>] do_one_initcall+0x42/0x180 [ 207.272678] [<ffffffff810bbeff>] load_module+0x19df/0x1b70 [ 207.272690] [<ffffffff810bc376>] sys_init_module+0xe6/0x130 [ 207.272702] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272715] [ 207.272715] -> #0 (subsys mutex){+.+.+.}: [ 207.272729] [<ffffffff810ae002>] __lock_acquire+0x13b2/0x15f0 [ 207.272740] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272751] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.272763] [<ffffffff8134af27>] bus_remove_device+0x37/0x1c0 [ 207.272775] [<ffffffff81349114>] device_del+0x134/0x1f0 [ 207.272786] [<ffffffff813491f2>] device_unregister+0x22/0x60 [ 207.272798] [<ffffffff814a24ea>] mce_cpu_callback+0x15e/0x1ad [ 207.272812] [<ffffffff814b6402>] notifier_call_chain+0x72/0x130 [ 207.272824] [<ffffffff81073d6e>] __raw_notifier_call_chain+0xe/0x10 [ 207.272839] [<ffffffff81498f76>] _cpu_down+0x1d6/0x350 [ 207.272851] [<ffffffff81499130>] cpu_down+0x40/0x60 [ 207.272862] [<ffffffff8149cc55>] store_online+0x75/0xe0 [ 207.272874] [<ffffffff813474a0>] dev_attr_store+0x20/0x30 [ 207.272886] [<ffffffff812090d9>] sysfs_write_file+0xd9/0x150 [ 207.272900] [<ffffffff8118e10b>] vfs_write+0xcb/0x130 [ 207.272911] [<ffffffff8118e924>] sys_write+0x64/0xa0 [ 207.272923] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272936] [ 207.272936] other info that might help us debug this: [ 207.272936] [ 207.272952] Chain exists of: [ 207.272952] subsys mutex --> &mm->mmap_sem --> cpu_hotplug.lock [ 207.272952] [ 207.272973] Possible unsafe locking scenario: [ 207.272973] [ 207.272984] CPU0 CPU1 [ 207.272992] ---- ---- [ 207.273000] lock(cpu_hotplug.lock); [ 207.273009] lock(&mm->mmap_sem); [ 207.273020] lock(cpu_hotplug.lock); [ 207.273031] lock(subsys mutex); [ 207.273040] [ 207.273040] *** DEADLOCK *** [ 207.273040] [ 207.273055] 5 locks held by bash/10493: [ 207.273062] #0: (&buffer->mutex){+.+.+.}, at: [<ffffffff81209049>] sysfs_write_file+0x49/0x150 [ 207.273080] #1: (s_active#150){.+.+.+}, at: [<ffffffff812090c2>] sysfs_write_file+0xc2/0x150 [ 207.273099] #2: (x86_cpu_hotplug_driver_mutex){+.+.+.}, at: [<ffffffff81027557>] cpu_hotplug_driver_lock+0x17/0x20 [ 207.273121] #3: (cpu_add_remove_lock){+.+.+.}, at: [<ffffffff8149911c>] cpu_down+0x2c/0x60 [ 207.273140] #4: (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff81046ccf>] cpu_hotplug_begin+0x2f/0x60 [ 207.273158] [ 207.273158] stack backtrace: [ 207.273170] Pid: 10493, comm: bash Not tainted 3.9.0-rc1-0.7-default+ #34 [ 207.273180] Call Trace: [ 207.273192] [<ffffffff810ab373>] print_circular_bug+0x223/0x310 [ 207.273204] [<ffffffff810ae002>] __lock_acquire+0x13b2/0x15f0 [ 207.273216] [<ffffffff812086b0>] ? sysfs_hash_and_remove+0x60/0xc0 [ 207.273227] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.273239] [<ffffffff8134af27>] ? bus_remove_device+0x37/0x1c0 [ 207.273251] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.273263] [<ffffffff8134af27>] ? bus_remove_device+0x37/0x1c0 [ 207.273274] [<ffffffff812086b0>] ? sysfs_hash_and_remove+0x60/0xc0 [ 207.273286] [<ffffffff8134af27>] bus_remove_device+0x37/0x1c0 [ 207.273298] [<ffffffff81349114>] device_del+0x134/0x1f0 [ 207.273309] [<ffffffff813491f2>] device_unregister+0x22/0x60 [ 207.273321] [<ffffffff814a24ea>] mce_cpu_callback+0x15e/0x1ad [ 207.273332] [<ffffffff814b6402>] notifier_call_chain+0x72/0x130 [ 207.273344] [<ffffffff81073d6e>] __raw_notifier_call_chain+0xe/0x10 [ 207.273356] [<ffffffff81498f76>] _cpu_down+0x1d6/0x350 [ 207.273368] [<ffffffff81027557>] ? cpu_hotplug_driver_lock+0x17/0x20 [ 207.273380] [<ffffffff81499130>] cpu_down+0x40/0x60 [ 207.273391] [<ffffffff8149cc55>] store_online+0x75/0xe0 [ 207.273402] [<ffffffff813474a0>] dev_attr_store+0x20/0x30 [ 207.273413] [<ffffffff812090d9>] sysfs_write_file+0xd9/0x150 [ 207.273425] [<ffffffff8118e10b>] vfs_write+0xcb/0x130 [ 207.273436] [<ffffffff8118e924>] sys_write+0x64/0xa0 [ 207.273447] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b Which reports a false possitive deadlock because it sees: 1) load_module -> subsys_interface_register -> mc_deveice_add (*) -> subsys->p->mutex -> link_path_walk -> lookup_slow -> i_mutex 2) sys_write -> _cpu_down -> cpu_hotplug_begin -> cpu_hotplug.lock -> mce_cpu_callback -> mce_device_remove(**) -> device_unregister -> bus_remove_device -> subsys mutex 3) vfs_readdir -> i_mutex -> filldir64 -> might_fault -> might_lock_read(mmap_sem) -> page_fault -> mmap_sem -> drain_all_stock -> cpu_hotplug.lock but 1) takes cpu_subsys subsys (*) but 2) takes mce_device subsys (**) so the deadlock is not possible AFAICS. The fix is quite simple. We can pull the key inside bus_type structure because they are defined per device so the pointer will be unique as well. bus_register doesn't need to be a macro anymore so change it to the inline. We could get rid of __bus_register as there is no other caller but maybe somebody will want to use a different key so keep it around for now. Reported-by: Li Zefan <lizefan@huawei.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-03-13 00:21:19 +08:00
int bus_register(struct bus_type *bus)
{
int retval;
struct subsys_private *priv;
device: separate all subsys mutexes ca22e56d (driver-core: implement 'sysdev' functionality for regular devices and buses) has introduced bus_register macro with a static key to distinguish different subsys mutex classes. This however doesn't work for different subsys which use a common registering function. One example is subsys_system_register (and mce_device and cpu_device). In the end this leads to the following lockdep splat: [ 207.271924] ====================================================== [ 207.271932] [ INFO: possible circular locking dependency detected ] [ 207.271942] 3.9.0-rc1-0.7-default+ #34 Not tainted [ 207.271948] ------------------------------------------------------- [ 207.271957] bash/10493 is trying to acquire lock: [ 207.271963] (subsys mutex){+.+.+.}, at: [<ffffffff8134af27>] bus_remove_device+0x37/0x1c0 [ 207.271987] [ 207.271987] but task is already holding lock: [ 207.271995] (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff81046ccf>] cpu_hotplug_begin+0x2f/0x60 [ 207.272012] [ 207.272012] which lock already depends on the new lock. [ 207.272012] [ 207.272023] [ 207.272023] the existing dependency chain (in reverse order) is: [ 207.272033] [ 207.272033] -> #4 (cpu_hotplug.lock){+.+.+.}: [ 207.272044] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272056] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.272069] [<ffffffff81046ba9>] get_online_cpus+0x29/0x40 [ 207.272082] [<ffffffff81185210>] drain_all_stock+0x30/0x150 [ 207.272094] [<ffffffff811853da>] mem_cgroup_reclaim+0xaa/0xe0 [ 207.272104] [<ffffffff8118775e>] __mem_cgroup_try_charge+0x51e/0xcf0 [ 207.272114] [<ffffffff81188486>] mem_cgroup_charge_common+0x36/0x60 [ 207.272125] [<ffffffff811884da>] mem_cgroup_newpage_charge+0x2a/0x30 [ 207.272135] [<ffffffff81150531>] do_wp_page+0x231/0x830 [ 207.272147] [<ffffffff8115151e>] handle_pte_fault+0x19e/0x8d0 [ 207.272157] [<ffffffff81151da8>] handle_mm_fault+0x158/0x1e0 [ 207.272166] [<ffffffff814b6153>] do_page_fault+0x2a3/0x4e0 [ 207.272178] [<ffffffff814b2578>] page_fault+0x28/0x30 [ 207.272189] [ 207.272189] -> #3 (&mm->mmap_sem){++++++}: [ 207.272199] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272208] [<ffffffff8114c5ad>] might_fault+0x6d/0x90 [ 207.272218] [<ffffffff811a11e3>] filldir64+0xb3/0x120 [ 207.272229] [<ffffffffa013fc19>] call_filldir+0x89/0x130 [ext3] [ 207.272248] [<ffffffffa0140377>] ext3_readdir+0x6b7/0x7e0 [ext3] [ 207.272263] [<ffffffff811a1519>] vfs_readdir+0xa9/0xc0 [ 207.272273] [<ffffffff811a15cb>] sys_getdents64+0x9b/0x110 [ 207.272284] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272296] [ 207.272296] -> #2 (&type->i_mutex_dir_key#3){+.+.+.}: [ 207.272309] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272319] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.272329] [<ffffffff8119c254>] link_path_walk+0x6f4/0x9a0 [ 207.272339] [<ffffffff8119e7fa>] path_openat+0xba/0x470 [ 207.272349] [<ffffffff8119ecf8>] do_filp_open+0x48/0xa0 [ 207.272358] [<ffffffff8118d81c>] file_open_name+0xdc/0x110 [ 207.272369] [<ffffffff8118d885>] filp_open+0x35/0x40 [ 207.272378] [<ffffffff8135c76e>] _request_firmware+0x52e/0xb20 [ 207.272389] [<ffffffff8135cdd6>] request_firmware+0x16/0x20 [ 207.272399] [<ffffffffa03bdb91>] request_microcode_fw+0x61/0xd0 [microcode] [ 207.272416] [<ffffffffa03bd554>] microcode_init_cpu+0x104/0x150 [microcode] [ 207.272431] [<ffffffffa03bd61c>] mc_device_add+0x7c/0xb0 [microcode] [ 207.272444] [<ffffffff8134a419>] subsys_interface_register+0xc9/0x100 [ 207.272457] [<ffffffffa04fc0f4>] 0xffffffffa04fc0f4 [ 207.272472] [<ffffffff81000202>] do_one_initcall+0x42/0x180 [ 207.272485] [<ffffffff810bbeff>] load_module+0x19df/0x1b70 [ 207.272499] [<ffffffff810bc376>] sys_init_module+0xe6/0x130 [ 207.272511] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272523] [ 207.272523] -> #1 (umhelper_sem){++++.+}: [ 207.272537] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272548] [<ffffffff814ae9c4>] down_read+0x34/0x50 [ 207.272559] [<ffffffff81062bff>] usermodehelper_read_trylock+0x4f/0x100 [ 207.272575] [<ffffffff8135c7dd>] _request_firmware+0x59d/0xb20 [ 207.272587] [<ffffffff8135cdd6>] request_firmware+0x16/0x20 [ 207.272599] [<ffffffffa03bdb91>] request_microcode_fw+0x61/0xd0 [microcode] [ 207.272613] [<ffffffffa03bd554>] microcode_init_cpu+0x104/0x150 [microcode] [ 207.272627] [<ffffffffa03bd61c>] mc_device_add+0x7c/0xb0 [microcode] [ 207.272641] [<ffffffff8134a419>] subsys_interface_register+0xc9/0x100 [ 207.272654] [<ffffffffa04fc0f4>] 0xffffffffa04fc0f4 [ 207.272666] [<ffffffff81000202>] do_one_initcall+0x42/0x180 [ 207.272678] [<ffffffff810bbeff>] load_module+0x19df/0x1b70 [ 207.272690] [<ffffffff810bc376>] sys_init_module+0xe6/0x130 [ 207.272702] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272715] [ 207.272715] -> #0 (subsys mutex){+.+.+.}: [ 207.272729] [<ffffffff810ae002>] __lock_acquire+0x13b2/0x15f0 [ 207.272740] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272751] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.272763] [<ffffffff8134af27>] bus_remove_device+0x37/0x1c0 [ 207.272775] [<ffffffff81349114>] device_del+0x134/0x1f0 [ 207.272786] [<ffffffff813491f2>] device_unregister+0x22/0x60 [ 207.272798] [<ffffffff814a24ea>] mce_cpu_callback+0x15e/0x1ad [ 207.272812] [<ffffffff814b6402>] notifier_call_chain+0x72/0x130 [ 207.272824] [<ffffffff81073d6e>] __raw_notifier_call_chain+0xe/0x10 [ 207.272839] [<ffffffff81498f76>] _cpu_down+0x1d6/0x350 [ 207.272851] [<ffffffff81499130>] cpu_down+0x40/0x60 [ 207.272862] [<ffffffff8149cc55>] store_online+0x75/0xe0 [ 207.272874] [<ffffffff813474a0>] dev_attr_store+0x20/0x30 [ 207.272886] [<ffffffff812090d9>] sysfs_write_file+0xd9/0x150 [ 207.272900] [<ffffffff8118e10b>] vfs_write+0xcb/0x130 [ 207.272911] [<ffffffff8118e924>] sys_write+0x64/0xa0 [ 207.272923] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272936] [ 207.272936] other info that might help us debug this: [ 207.272936] [ 207.272952] Chain exists of: [ 207.272952] subsys mutex --> &mm->mmap_sem --> cpu_hotplug.lock [ 207.272952] [ 207.272973] Possible unsafe locking scenario: [ 207.272973] [ 207.272984] CPU0 CPU1 [ 207.272992] ---- ---- [ 207.273000] lock(cpu_hotplug.lock); [ 207.273009] lock(&mm->mmap_sem); [ 207.273020] lock(cpu_hotplug.lock); [ 207.273031] lock(subsys mutex); [ 207.273040] [ 207.273040] *** DEADLOCK *** [ 207.273040] [ 207.273055] 5 locks held by bash/10493: [ 207.273062] #0: (&buffer->mutex){+.+.+.}, at: [<ffffffff81209049>] sysfs_write_file+0x49/0x150 [ 207.273080] #1: (s_active#150){.+.+.+}, at: [<ffffffff812090c2>] sysfs_write_file+0xc2/0x150 [ 207.273099] #2: (x86_cpu_hotplug_driver_mutex){+.+.+.}, at: [<ffffffff81027557>] cpu_hotplug_driver_lock+0x17/0x20 [ 207.273121] #3: (cpu_add_remove_lock){+.+.+.}, at: [<ffffffff8149911c>] cpu_down+0x2c/0x60 [ 207.273140] #4: (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff81046ccf>] cpu_hotplug_begin+0x2f/0x60 [ 207.273158] [ 207.273158] stack backtrace: [ 207.273170] Pid: 10493, comm: bash Not tainted 3.9.0-rc1-0.7-default+ #34 [ 207.273180] Call Trace: [ 207.273192] [<ffffffff810ab373>] print_circular_bug+0x223/0x310 [ 207.273204] [<ffffffff810ae002>] __lock_acquire+0x13b2/0x15f0 [ 207.273216] [<ffffffff812086b0>] ? sysfs_hash_and_remove+0x60/0xc0 [ 207.273227] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.273239] [<ffffffff8134af27>] ? bus_remove_device+0x37/0x1c0 [ 207.273251] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.273263] [<ffffffff8134af27>] ? bus_remove_device+0x37/0x1c0 [ 207.273274] [<ffffffff812086b0>] ? sysfs_hash_and_remove+0x60/0xc0 [ 207.273286] [<ffffffff8134af27>] bus_remove_device+0x37/0x1c0 [ 207.273298] [<ffffffff81349114>] device_del+0x134/0x1f0 [ 207.273309] [<ffffffff813491f2>] device_unregister+0x22/0x60 [ 207.273321] [<ffffffff814a24ea>] mce_cpu_callback+0x15e/0x1ad [ 207.273332] [<ffffffff814b6402>] notifier_call_chain+0x72/0x130 [ 207.273344] [<ffffffff81073d6e>] __raw_notifier_call_chain+0xe/0x10 [ 207.273356] [<ffffffff81498f76>] _cpu_down+0x1d6/0x350 [ 207.273368] [<ffffffff81027557>] ? cpu_hotplug_driver_lock+0x17/0x20 [ 207.273380] [<ffffffff81499130>] cpu_down+0x40/0x60 [ 207.273391] [<ffffffff8149cc55>] store_online+0x75/0xe0 [ 207.273402] [<ffffffff813474a0>] dev_attr_store+0x20/0x30 [ 207.273413] [<ffffffff812090d9>] sysfs_write_file+0xd9/0x150 [ 207.273425] [<ffffffff8118e10b>] vfs_write+0xcb/0x130 [ 207.273436] [<ffffffff8118e924>] sys_write+0x64/0xa0 [ 207.273447] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b Which reports a false possitive deadlock because it sees: 1) load_module -> subsys_interface_register -> mc_deveice_add (*) -> subsys->p->mutex -> link_path_walk -> lookup_slow -> i_mutex 2) sys_write -> _cpu_down -> cpu_hotplug_begin -> cpu_hotplug.lock -> mce_cpu_callback -> mce_device_remove(**) -> device_unregister -> bus_remove_device -> subsys mutex 3) vfs_readdir -> i_mutex -> filldir64 -> might_fault -> might_lock_read(mmap_sem) -> page_fault -> mmap_sem -> drain_all_stock -> cpu_hotplug.lock but 1) takes cpu_subsys subsys (*) but 2) takes mce_device subsys (**) so the deadlock is not possible AFAICS. The fix is quite simple. We can pull the key inside bus_type structure because they are defined per device so the pointer will be unique as well. bus_register doesn't need to be a macro anymore so change it to the inline. We could get rid of __bus_register as there is no other caller but maybe somebody will want to use a different key so keep it around for now. Reported-by: Li Zefan <lizefan@huawei.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-03-13 00:21:19 +08:00
struct lock_class_key *key = &bus->lock_key;
priv = kzalloc(sizeof(struct subsys_private), GFP_KERNEL);
if (!priv)
return -ENOMEM;
priv->bus = bus;
bus->p = priv;
BLOCKING_INIT_NOTIFIER_HEAD(&priv->bus_notifier);
Driver core: add notification of bus events I finally did as you suggested and added the notifier to the struct bus_type itself. There are still problems to be expected is something attaches to a bus type where the code can hook in different struct device sub-classes (which is imho a big bogosity but I won't even try to argue that case now) but it will solve nicely a number of issues I've had so far. That also means that clients interested in registering for such notifications have to do it before devices are added and after bus types are registered. Fortunately, most bus types that matter for the various usage scenarios I have in mind are registerd at postcore_initcall time, which means I have a really nice spot at arch_initcall time to add my notifiers. There are 4 notifications provided. Device being added (before hooked to the bus) and removed (failure of previous case or after being unhooked from the bus), along with driver being bound to a device and about to be unbound. The usage I have for these are: - The 2 first ones are used to maintain a struct device_ext that is hooked to struct device.firmware_data. This structure contains for now a pointer to the Open Firmware node related to the device (if any), the NUMA node ID (for quick access to it) and the DMA operations pointers & iommu table instance for DMA to/from this device. For bus types I own (like IBM VIO or EBUS), I just maintain that structure directly from the bus code when creating the devices. But for bus types managed by generic code like PCI or platform (actually, of_platform which is a variation of platform linked to Open Firmware device-tree), I need this notifier. - The other two ones have a completely different usage scenario. I have cases where multiple devices and their drivers depend on each other. For example, the IBM EMAC network driver needs to attach to a MAL DMA engine which is a separate device, and a PHY interface which is also a separate device. They are all of_platform_device's (well, about to be with my upcoming patches) but there is no say in what precise order the core will "probe" them and instanciate the various modules. The solution I found for that is to have the drivers for emac to use multithread_probe, and wait for a driver to be bound to the target MAL and PHY control devices (the device-tree contains reference to the MAL and PHY interface nodes, which I can then match to of_platform_devices). Right now, I've been polling, but with that notifier, I can more cleanly wait (with a timeout of course). Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-10-25 11:44:59 +08:00
retval = kobject_set_name(&priv->subsys.kobj, "%s", bus->name);
if (retval)
goto out;
priv->subsys.kobj.kset = bus_kset;
priv->subsys.kobj.ktype = &bus_ktype;
priv->drivers_autoprobe = 1;
retval = kset_register(&priv->subsys);
if (retval)
goto out;
retval = bus_create_file(bus, &bus_attr_uevent);
if (retval)
goto bus_uevent_fail;
priv->devices_kset = kset_create_and_add("devices", NULL,
&priv->subsys.kobj);
if (!priv->devices_kset) {
retval = -ENOMEM;
goto bus_devices_fail;
}
priv->drivers_kset = kset_create_and_add("drivers", NULL,
&priv->subsys.kobj);
if (!priv->drivers_kset) {
retval = -ENOMEM;
goto bus_drivers_fail;
}
INIT_LIST_HEAD(&priv->interfaces);
__mutex_init(&priv->mutex, "subsys mutex", key);
klist_init(&priv->klist_devices, klist_devices_get, klist_devices_put);
klist_init(&priv->klist_drivers, NULL, NULL);
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
retval = add_probe_files(bus);
if (retval)
goto bus_probe_files_fail;
retval = bus_add_groups(bus, bus->bus_groups);
if (retval)
goto bus_groups_fail;
pr_debug("bus: '%s': registered\n", bus->name);
return 0;
bus_groups_fail:
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
remove_probe_files(bus);
bus_probe_files_fail:
kset_unregister(bus->p->drivers_kset);
bus_drivers_fail:
kset_unregister(bus->p->devices_kset);
bus_devices_fail:
bus_remove_file(bus, &bus_attr_uevent);
bus_uevent_fail:
kset_unregister(&bus->p->subsys);
out:
kfree(bus->p);
bus->p = NULL;
return retval;
}
device: separate all subsys mutexes ca22e56d (driver-core: implement 'sysdev' functionality for regular devices and buses) has introduced bus_register macro with a static key to distinguish different subsys mutex classes. This however doesn't work for different subsys which use a common registering function. One example is subsys_system_register (and mce_device and cpu_device). In the end this leads to the following lockdep splat: [ 207.271924] ====================================================== [ 207.271932] [ INFO: possible circular locking dependency detected ] [ 207.271942] 3.9.0-rc1-0.7-default+ #34 Not tainted [ 207.271948] ------------------------------------------------------- [ 207.271957] bash/10493 is trying to acquire lock: [ 207.271963] (subsys mutex){+.+.+.}, at: [<ffffffff8134af27>] bus_remove_device+0x37/0x1c0 [ 207.271987] [ 207.271987] but task is already holding lock: [ 207.271995] (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff81046ccf>] cpu_hotplug_begin+0x2f/0x60 [ 207.272012] [ 207.272012] which lock already depends on the new lock. [ 207.272012] [ 207.272023] [ 207.272023] the existing dependency chain (in reverse order) is: [ 207.272033] [ 207.272033] -> #4 (cpu_hotplug.lock){+.+.+.}: [ 207.272044] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272056] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.272069] [<ffffffff81046ba9>] get_online_cpus+0x29/0x40 [ 207.272082] [<ffffffff81185210>] drain_all_stock+0x30/0x150 [ 207.272094] [<ffffffff811853da>] mem_cgroup_reclaim+0xaa/0xe0 [ 207.272104] [<ffffffff8118775e>] __mem_cgroup_try_charge+0x51e/0xcf0 [ 207.272114] [<ffffffff81188486>] mem_cgroup_charge_common+0x36/0x60 [ 207.272125] [<ffffffff811884da>] mem_cgroup_newpage_charge+0x2a/0x30 [ 207.272135] [<ffffffff81150531>] do_wp_page+0x231/0x830 [ 207.272147] [<ffffffff8115151e>] handle_pte_fault+0x19e/0x8d0 [ 207.272157] [<ffffffff81151da8>] handle_mm_fault+0x158/0x1e0 [ 207.272166] [<ffffffff814b6153>] do_page_fault+0x2a3/0x4e0 [ 207.272178] [<ffffffff814b2578>] page_fault+0x28/0x30 [ 207.272189] [ 207.272189] -> #3 (&mm->mmap_sem){++++++}: [ 207.272199] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272208] [<ffffffff8114c5ad>] might_fault+0x6d/0x90 [ 207.272218] [<ffffffff811a11e3>] filldir64+0xb3/0x120 [ 207.272229] [<ffffffffa013fc19>] call_filldir+0x89/0x130 [ext3] [ 207.272248] [<ffffffffa0140377>] ext3_readdir+0x6b7/0x7e0 [ext3] [ 207.272263] [<ffffffff811a1519>] vfs_readdir+0xa9/0xc0 [ 207.272273] [<ffffffff811a15cb>] sys_getdents64+0x9b/0x110 [ 207.272284] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272296] [ 207.272296] -> #2 (&type->i_mutex_dir_key#3){+.+.+.}: [ 207.272309] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272319] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.272329] [<ffffffff8119c254>] link_path_walk+0x6f4/0x9a0 [ 207.272339] [<ffffffff8119e7fa>] path_openat+0xba/0x470 [ 207.272349] [<ffffffff8119ecf8>] do_filp_open+0x48/0xa0 [ 207.272358] [<ffffffff8118d81c>] file_open_name+0xdc/0x110 [ 207.272369] [<ffffffff8118d885>] filp_open+0x35/0x40 [ 207.272378] [<ffffffff8135c76e>] _request_firmware+0x52e/0xb20 [ 207.272389] [<ffffffff8135cdd6>] request_firmware+0x16/0x20 [ 207.272399] [<ffffffffa03bdb91>] request_microcode_fw+0x61/0xd0 [microcode] [ 207.272416] [<ffffffffa03bd554>] microcode_init_cpu+0x104/0x150 [microcode] [ 207.272431] [<ffffffffa03bd61c>] mc_device_add+0x7c/0xb0 [microcode] [ 207.272444] [<ffffffff8134a419>] subsys_interface_register+0xc9/0x100 [ 207.272457] [<ffffffffa04fc0f4>] 0xffffffffa04fc0f4 [ 207.272472] [<ffffffff81000202>] do_one_initcall+0x42/0x180 [ 207.272485] [<ffffffff810bbeff>] load_module+0x19df/0x1b70 [ 207.272499] [<ffffffff810bc376>] sys_init_module+0xe6/0x130 [ 207.272511] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272523] [ 207.272523] -> #1 (umhelper_sem){++++.+}: [ 207.272537] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272548] [<ffffffff814ae9c4>] down_read+0x34/0x50 [ 207.272559] [<ffffffff81062bff>] usermodehelper_read_trylock+0x4f/0x100 [ 207.272575] [<ffffffff8135c7dd>] _request_firmware+0x59d/0xb20 [ 207.272587] [<ffffffff8135cdd6>] request_firmware+0x16/0x20 [ 207.272599] [<ffffffffa03bdb91>] request_microcode_fw+0x61/0xd0 [microcode] [ 207.272613] [<ffffffffa03bd554>] microcode_init_cpu+0x104/0x150 [microcode] [ 207.272627] [<ffffffffa03bd61c>] mc_device_add+0x7c/0xb0 [microcode] [ 207.272641] [<ffffffff8134a419>] subsys_interface_register+0xc9/0x100 [ 207.272654] [<ffffffffa04fc0f4>] 0xffffffffa04fc0f4 [ 207.272666] [<ffffffff81000202>] do_one_initcall+0x42/0x180 [ 207.272678] [<ffffffff810bbeff>] load_module+0x19df/0x1b70 [ 207.272690] [<ffffffff810bc376>] sys_init_module+0xe6/0x130 [ 207.272702] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272715] [ 207.272715] -> #0 (subsys mutex){+.+.+.}: [ 207.272729] [<ffffffff810ae002>] __lock_acquire+0x13b2/0x15f0 [ 207.272740] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.272751] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.272763] [<ffffffff8134af27>] bus_remove_device+0x37/0x1c0 [ 207.272775] [<ffffffff81349114>] device_del+0x134/0x1f0 [ 207.272786] [<ffffffff813491f2>] device_unregister+0x22/0x60 [ 207.272798] [<ffffffff814a24ea>] mce_cpu_callback+0x15e/0x1ad [ 207.272812] [<ffffffff814b6402>] notifier_call_chain+0x72/0x130 [ 207.272824] [<ffffffff81073d6e>] __raw_notifier_call_chain+0xe/0x10 [ 207.272839] [<ffffffff81498f76>] _cpu_down+0x1d6/0x350 [ 207.272851] [<ffffffff81499130>] cpu_down+0x40/0x60 [ 207.272862] [<ffffffff8149cc55>] store_online+0x75/0xe0 [ 207.272874] [<ffffffff813474a0>] dev_attr_store+0x20/0x30 [ 207.272886] [<ffffffff812090d9>] sysfs_write_file+0xd9/0x150 [ 207.272900] [<ffffffff8118e10b>] vfs_write+0xcb/0x130 [ 207.272911] [<ffffffff8118e924>] sys_write+0x64/0xa0 [ 207.272923] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b [ 207.272936] [ 207.272936] other info that might help us debug this: [ 207.272936] [ 207.272952] Chain exists of: [ 207.272952] subsys mutex --> &mm->mmap_sem --> cpu_hotplug.lock [ 207.272952] [ 207.272973] Possible unsafe locking scenario: [ 207.272973] [ 207.272984] CPU0 CPU1 [ 207.272992] ---- ---- [ 207.273000] lock(cpu_hotplug.lock); [ 207.273009] lock(&mm->mmap_sem); [ 207.273020] lock(cpu_hotplug.lock); [ 207.273031] lock(subsys mutex); [ 207.273040] [ 207.273040] *** DEADLOCK *** [ 207.273040] [ 207.273055] 5 locks held by bash/10493: [ 207.273062] #0: (&buffer->mutex){+.+.+.}, at: [<ffffffff81209049>] sysfs_write_file+0x49/0x150 [ 207.273080] #1: (s_active#150){.+.+.+}, at: [<ffffffff812090c2>] sysfs_write_file+0xc2/0x150 [ 207.273099] #2: (x86_cpu_hotplug_driver_mutex){+.+.+.}, at: [<ffffffff81027557>] cpu_hotplug_driver_lock+0x17/0x20 [ 207.273121] #3: (cpu_add_remove_lock){+.+.+.}, at: [<ffffffff8149911c>] cpu_down+0x2c/0x60 [ 207.273140] #4: (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff81046ccf>] cpu_hotplug_begin+0x2f/0x60 [ 207.273158] [ 207.273158] stack backtrace: [ 207.273170] Pid: 10493, comm: bash Not tainted 3.9.0-rc1-0.7-default+ #34 [ 207.273180] Call Trace: [ 207.273192] [<ffffffff810ab373>] print_circular_bug+0x223/0x310 [ 207.273204] [<ffffffff810ae002>] __lock_acquire+0x13b2/0x15f0 [ 207.273216] [<ffffffff812086b0>] ? sysfs_hash_and_remove+0x60/0xc0 [ 207.273227] [<ffffffff810ae329>] lock_acquire+0xe9/0x120 [ 207.273239] [<ffffffff8134af27>] ? bus_remove_device+0x37/0x1c0 [ 207.273251] [<ffffffff814ad807>] mutex_lock_nested+0x37/0x360 [ 207.273263] [<ffffffff8134af27>] ? bus_remove_device+0x37/0x1c0 [ 207.273274] [<ffffffff812086b0>] ? sysfs_hash_and_remove+0x60/0xc0 [ 207.273286] [<ffffffff8134af27>] bus_remove_device+0x37/0x1c0 [ 207.273298] [<ffffffff81349114>] device_del+0x134/0x1f0 [ 207.273309] [<ffffffff813491f2>] device_unregister+0x22/0x60 [ 207.273321] [<ffffffff814a24ea>] mce_cpu_callback+0x15e/0x1ad [ 207.273332] [<ffffffff814b6402>] notifier_call_chain+0x72/0x130 [ 207.273344] [<ffffffff81073d6e>] __raw_notifier_call_chain+0xe/0x10 [ 207.273356] [<ffffffff81498f76>] _cpu_down+0x1d6/0x350 [ 207.273368] [<ffffffff81027557>] ? cpu_hotplug_driver_lock+0x17/0x20 [ 207.273380] [<ffffffff81499130>] cpu_down+0x40/0x60 [ 207.273391] [<ffffffff8149cc55>] store_online+0x75/0xe0 [ 207.273402] [<ffffffff813474a0>] dev_attr_store+0x20/0x30 [ 207.273413] [<ffffffff812090d9>] sysfs_write_file+0xd9/0x150 [ 207.273425] [<ffffffff8118e10b>] vfs_write+0xcb/0x130 [ 207.273436] [<ffffffff8118e924>] sys_write+0x64/0xa0 [ 207.273447] [<ffffffff814bb599>] system_call_fastpath+0x16/0x1b Which reports a false possitive deadlock because it sees: 1) load_module -> subsys_interface_register -> mc_deveice_add (*) -> subsys->p->mutex -> link_path_walk -> lookup_slow -> i_mutex 2) sys_write -> _cpu_down -> cpu_hotplug_begin -> cpu_hotplug.lock -> mce_cpu_callback -> mce_device_remove(**) -> device_unregister -> bus_remove_device -> subsys mutex 3) vfs_readdir -> i_mutex -> filldir64 -> might_fault -> might_lock_read(mmap_sem) -> page_fault -> mmap_sem -> drain_all_stock -> cpu_hotplug.lock but 1) takes cpu_subsys subsys (*) but 2) takes mce_device subsys (**) so the deadlock is not possible AFAICS. The fix is quite simple. We can pull the key inside bus_type structure because they are defined per device so the pointer will be unique as well. bus_register doesn't need to be a macro anymore so change it to the inline. We could get rid of __bus_register as there is no other caller but maybe somebody will want to use a different key so keep it around for now. Reported-by: Li Zefan <lizefan@huawei.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-03-13 00:21:19 +08:00
EXPORT_SYMBOL_GPL(bus_register);
/**
* bus_unregister - remove a bus from the system
* @bus: bus.
*
* Unregister the child subsystems and the bus itself.
* Finally, we call bus_put() to release the refcount
*/
void bus_unregister(struct bus_type *bus)
{
pr_debug("bus: '%s': unregistering\n", bus->name);
if (bus->dev_root)
device_unregister(bus->dev_root);
bus_remove_groups(bus, bus->bus_groups);
Driver core: udev triggered device-<>driver binding We get two per-bus sysfs files: ls-l /sys/subsystem/usb drwxr-xr-x 2 root root 0 2007-02-16 16:42 devices drwxr-xr-x 7 root root 0 2007-02-16 14:55 drivers -rw-r--r-- 1 root root 4096 2007-02-16 16:42 drivers_autoprobe --w------- 1 root root 4096 2007-02-16 16:42 drivers_probe The flag "drivers_autoprobe" controls the behavior of the bus to bind devices by default, or just initialize the device and leave it alone. The command "drivers_probe" accepts a bus_id and the bus tries to bind a driver to this device. Systems who want to control the driver binding with udev, switch off the bus initiated probing: echo 0 > /sys/subsystem/usb/drivers_autoprobe echo 0 > /sys/subsystem/pcmcia/drivers_autoprobe ... and initiate the probing with udev rules like: ACTION=="add", SUBSYSTEM=="usb", ATTR{subsystem/drivers_probe}="$kernel" ACTION=="add", SUBSYSTEM=="pcmcia", ATTR{subsystem/drivers_probe}="$kernel" ... Custom driver binding can happen in earlier rules by something like: ACTION=="add", SUBSYSTEM=="usb", \ ATTRS{idVendor}=="1234", ATTRS{idProduct}=="5678" \ ATTR{subsystem/drivers/<custom-driver>/bind}="$kernel" This is intended to solve the modprobe.conf mess with "install-rules", custom bind/unbind-scripts and all the weird things people invented over the years. It should also provide the functionality "libusual" was supposed to do. With udev, one can just write a udev rule to drive all USB-disks at the third port of USB-hub by the "ub" driver, and everything else by usb-storage. One can also instruct udev to bind different wireless drivers to identical cards - just selected by the pcmcia slot-number, and whatever ... To use the mentioned rules, it needs udev version 106, to be able to write ATTR{}="$kernel" to sysfs files. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-02-17 00:33:36 +08:00
remove_probe_files(bus);
kset_unregister(bus->p->drivers_kset);
kset_unregister(bus->p->devices_kset);
bus_remove_file(bus, &bus_attr_uevent);
kset_unregister(&bus->p->subsys);
}
EXPORT_SYMBOL_GPL(bus_unregister);
Driver core: add notification of bus events I finally did as you suggested and added the notifier to the struct bus_type itself. There are still problems to be expected is something attaches to a bus type where the code can hook in different struct device sub-classes (which is imho a big bogosity but I won't even try to argue that case now) but it will solve nicely a number of issues I've had so far. That also means that clients interested in registering for such notifications have to do it before devices are added and after bus types are registered. Fortunately, most bus types that matter for the various usage scenarios I have in mind are registerd at postcore_initcall time, which means I have a really nice spot at arch_initcall time to add my notifiers. There are 4 notifications provided. Device being added (before hooked to the bus) and removed (failure of previous case or after being unhooked from the bus), along with driver being bound to a device and about to be unbound. The usage I have for these are: - The 2 first ones are used to maintain a struct device_ext that is hooked to struct device.firmware_data. This structure contains for now a pointer to the Open Firmware node related to the device (if any), the NUMA node ID (for quick access to it) and the DMA operations pointers & iommu table instance for DMA to/from this device. For bus types I own (like IBM VIO or EBUS), I just maintain that structure directly from the bus code when creating the devices. But for bus types managed by generic code like PCI or platform (actually, of_platform which is a variation of platform linked to Open Firmware device-tree), I need this notifier. - The other two ones have a completely different usage scenario. I have cases where multiple devices and their drivers depend on each other. For example, the IBM EMAC network driver needs to attach to a MAL DMA engine which is a separate device, and a PHY interface which is also a separate device. They are all of_platform_device's (well, about to be with my upcoming patches) but there is no say in what precise order the core will "probe" them and instanciate the various modules. The solution I found for that is to have the drivers for emac to use multithread_probe, and wait for a driver to be bound to the target MAL and PHY control devices (the device-tree contains reference to the MAL and PHY interface nodes, which I can then match to of_platform_devices). Right now, I've been polling, but with that notifier, I can more cleanly wait (with a timeout of course). Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-10-25 11:44:59 +08:00
int bus_register_notifier(struct bus_type *bus, struct notifier_block *nb)
{
return blocking_notifier_chain_register(&bus->p->bus_notifier, nb);
Driver core: add notification of bus events I finally did as you suggested and added the notifier to the struct bus_type itself. There are still problems to be expected is something attaches to a bus type where the code can hook in different struct device sub-classes (which is imho a big bogosity but I won't even try to argue that case now) but it will solve nicely a number of issues I've had so far. That also means that clients interested in registering for such notifications have to do it before devices are added and after bus types are registered. Fortunately, most bus types that matter for the various usage scenarios I have in mind are registerd at postcore_initcall time, which means I have a really nice spot at arch_initcall time to add my notifiers. There are 4 notifications provided. Device being added (before hooked to the bus) and removed (failure of previous case or after being unhooked from the bus), along with driver being bound to a device and about to be unbound. The usage I have for these are: - The 2 first ones are used to maintain a struct device_ext that is hooked to struct device.firmware_data. This structure contains for now a pointer to the Open Firmware node related to the device (if any), the NUMA node ID (for quick access to it) and the DMA operations pointers & iommu table instance for DMA to/from this device. For bus types I own (like IBM VIO or EBUS), I just maintain that structure directly from the bus code when creating the devices. But for bus types managed by generic code like PCI or platform (actually, of_platform which is a variation of platform linked to Open Firmware device-tree), I need this notifier. - The other two ones have a completely different usage scenario. I have cases where multiple devices and their drivers depend on each other. For example, the IBM EMAC network driver needs to attach to a MAL DMA engine which is a separate device, and a PHY interface which is also a separate device. They are all of_platform_device's (well, about to be with my upcoming patches) but there is no say in what precise order the core will "probe" them and instanciate the various modules. The solution I found for that is to have the drivers for emac to use multithread_probe, and wait for a driver to be bound to the target MAL and PHY control devices (the device-tree contains reference to the MAL and PHY interface nodes, which I can then match to of_platform_devices). Right now, I've been polling, but with that notifier, I can more cleanly wait (with a timeout of course). Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-10-25 11:44:59 +08:00
}
EXPORT_SYMBOL_GPL(bus_register_notifier);
int bus_unregister_notifier(struct bus_type *bus, struct notifier_block *nb)
{
return blocking_notifier_chain_unregister(&bus->p->bus_notifier, nb);
Driver core: add notification of bus events I finally did as you suggested and added the notifier to the struct bus_type itself. There are still problems to be expected is something attaches to a bus type where the code can hook in different struct device sub-classes (which is imho a big bogosity but I won't even try to argue that case now) but it will solve nicely a number of issues I've had so far. That also means that clients interested in registering for such notifications have to do it before devices are added and after bus types are registered. Fortunately, most bus types that matter for the various usage scenarios I have in mind are registerd at postcore_initcall time, which means I have a really nice spot at arch_initcall time to add my notifiers. There are 4 notifications provided. Device being added (before hooked to the bus) and removed (failure of previous case or after being unhooked from the bus), along with driver being bound to a device and about to be unbound. The usage I have for these are: - The 2 first ones are used to maintain a struct device_ext that is hooked to struct device.firmware_data. This structure contains for now a pointer to the Open Firmware node related to the device (if any), the NUMA node ID (for quick access to it) and the DMA operations pointers & iommu table instance for DMA to/from this device. For bus types I own (like IBM VIO or EBUS), I just maintain that structure directly from the bus code when creating the devices. But for bus types managed by generic code like PCI or platform (actually, of_platform which is a variation of platform linked to Open Firmware device-tree), I need this notifier. - The other two ones have a completely different usage scenario. I have cases where multiple devices and their drivers depend on each other. For example, the IBM EMAC network driver needs to attach to a MAL DMA engine which is a separate device, and a PHY interface which is also a separate device. They are all of_platform_device's (well, about to be with my upcoming patches) but there is no say in what precise order the core will "probe" them and instanciate the various modules. The solution I found for that is to have the drivers for emac to use multithread_probe, and wait for a driver to be bound to the target MAL and PHY control devices (the device-tree contains reference to the MAL and PHY interface nodes, which I can then match to of_platform_devices). Right now, I've been polling, but with that notifier, I can more cleanly wait (with a timeout of course). Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-10-25 11:44:59 +08:00
}
EXPORT_SYMBOL_GPL(bus_unregister_notifier);
struct kset *bus_get_kset(struct bus_type *bus)
{
return &bus->p->subsys;
}
EXPORT_SYMBOL_GPL(bus_get_kset);
struct klist *bus_get_device_klist(struct bus_type *bus)
{
return &bus->p->klist_devices;
}
EXPORT_SYMBOL_GPL(bus_get_device_klist);
/*
* Yes, this forcibly breaks the klist abstraction temporarily. It
* just wants to sort the klist, not change reference counts and
* take/drop locks rapidly in the process. It does all this while
* holding the lock for the list, so objects can't otherwise be
* added/removed while we're swizzling.
*/
static void device_insertion_sort_klist(struct device *a, struct list_head *list,
int (*compare)(const struct device *a,
const struct device *b))
{
struct klist_node *n;
struct device_private *dev_prv;
struct device *b;
list_for_each_entry(n, list, n_node) {
dev_prv = to_device_private_bus(n);
b = dev_prv->device;
if (compare(a, b) <= 0) {
list_move_tail(&a->p->knode_bus.n_node,
&b->p->knode_bus.n_node);
return;
}
}
list_move_tail(&a->p->knode_bus.n_node, list);
}
void bus_sort_breadthfirst(struct bus_type *bus,
int (*compare)(const struct device *a,
const struct device *b))
{
LIST_HEAD(sorted_devices);
struct klist_node *n, *tmp;
struct device_private *dev_prv;
struct device *dev;
struct klist *device_klist;
device_klist = bus_get_device_klist(bus);
spin_lock(&device_klist->k_lock);
list_for_each_entry_safe(n, tmp, &device_klist->k_list, n_node) {
dev_prv = to_device_private_bus(n);
dev = dev_prv->device;
device_insertion_sort_klist(dev, &sorted_devices, compare);
}
list_splice(&sorted_devices, &device_klist->k_list);
spin_unlock(&device_klist->k_lock);
}
EXPORT_SYMBOL_GPL(bus_sort_breadthfirst);
/**
* subsys_dev_iter_init - initialize subsys device iterator
* @iter: subsys iterator to initialize
* @subsys: the subsys we wanna iterate over
* @start: the device to start iterating from, if any
* @type: device_type of the devices to iterate over, NULL for all
*
* Initialize subsys iterator @iter such that it iterates over devices
* of @subsys. If @start is set, the list iteration will start there,
* otherwise if it is NULL, the iteration starts at the beginning of
* the list.
*/
void subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys,
struct device *start, const struct device_type *type)
{
struct klist_node *start_knode = NULL;
if (start)
start_knode = &start->p->knode_bus;
klist_iter_init_node(&subsys->p->klist_devices, &iter->ki, start_knode);
iter->type = type;
}
EXPORT_SYMBOL_GPL(subsys_dev_iter_init);
/**
* subsys_dev_iter_next - iterate to the next device
* @iter: subsys iterator to proceed
*
* Proceed @iter to the next device and return it. Returns NULL if
* iteration is complete.
*
* The returned device is referenced and won't be released till
* iterator is proceed to the next device or exited. The caller is
* free to do whatever it wants to do with the device including
* calling back into subsys code.
*/
struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter)
{
struct klist_node *knode;
struct device *dev;
for (;;) {
knode = klist_next(&iter->ki);
if (!knode)
return NULL;
dev = to_device_private_bus(knode)->device;
if (!iter->type || iter->type == dev->type)
return dev;
}
}
EXPORT_SYMBOL_GPL(subsys_dev_iter_next);
/**
* subsys_dev_iter_exit - finish iteration
* @iter: subsys iterator to finish
*
* Finish an iteration. Always call this function after iteration is
* complete whether the iteration ran till the end or not.
*/
void subsys_dev_iter_exit(struct subsys_dev_iter *iter)
{
klist_iter_exit(&iter->ki);
}
EXPORT_SYMBOL_GPL(subsys_dev_iter_exit);
int subsys_interface_register(struct subsys_interface *sif)
{
struct bus_type *subsys;
struct subsys_dev_iter iter;
struct device *dev;
if (!sif || !sif->subsys)
return -ENODEV;
subsys = bus_get(sif->subsys);
if (!subsys)
return -EINVAL;
mutex_lock(&subsys->p->mutex);
list_add_tail(&sif->node, &subsys->p->interfaces);
if (sif->add_dev) {
subsys_dev_iter_init(&iter, subsys, NULL, NULL);
while ((dev = subsys_dev_iter_next(&iter)))
sif->add_dev(dev, sif);
subsys_dev_iter_exit(&iter);
}
mutex_unlock(&subsys->p->mutex);
return 0;
}
EXPORT_SYMBOL_GPL(subsys_interface_register);
void subsys_interface_unregister(struct subsys_interface *sif)
{
struct bus_type *subsys;
struct subsys_dev_iter iter;
struct device *dev;
if (!sif || !sif->subsys)
return;
subsys = sif->subsys;
mutex_lock(&subsys->p->mutex);
list_del_init(&sif->node);
if (sif->remove_dev) {
subsys_dev_iter_init(&iter, subsys, NULL, NULL);
while ((dev = subsys_dev_iter_next(&iter)))
sif->remove_dev(dev, sif);
subsys_dev_iter_exit(&iter);
}
mutex_unlock(&subsys->p->mutex);
bus_put(subsys);
}
EXPORT_SYMBOL_GPL(subsys_interface_unregister);
static void system_root_device_release(struct device *dev)
{
kfree(dev);
}
static int subsys_register(struct bus_type *subsys,
const struct attribute_group **groups,
struct kobject *parent_of_root)
{
struct device *dev;
int err;
err = bus_register(subsys);
if (err < 0)
return err;
dev = kzalloc(sizeof(struct device), GFP_KERNEL);
if (!dev) {
err = -ENOMEM;
goto err_dev;
}
err = dev_set_name(dev, "%s", subsys->name);
if (err < 0)
goto err_name;
dev->kobj.parent = parent_of_root;
dev->groups = groups;
dev->release = system_root_device_release;
err = device_register(dev);
if (err < 0)
goto err_dev_reg;
subsys->dev_root = dev;
return 0;
err_dev_reg:
put_device(dev);
dev = NULL;
err_name:
kfree(dev);
err_dev:
bus_unregister(subsys);
return err;
}
/**
* subsys_system_register - register a subsystem at /sys/devices/system/
* @subsys: system subsystem
* @groups: default attributes for the root device
*
* All 'system' subsystems have a /sys/devices/system/<name> root device
* with the name of the subsystem. The root device can carry subsystem-
* wide attributes. All registered devices are below this single root
* device and are named after the subsystem with a simple enumeration
* number appended. The registered devices are not explicitly named;
* only 'id' in the device needs to be set.
*
* Do not use this interface for anything new, it exists for compatibility
* with bad ideas only. New subsystems should use plain subsystems; and
* add the subsystem-wide attributes should be added to the subsystem
* directory itself and not some create fake root-device placed in
* /sys/devices/system/<name>.
*/
int subsys_system_register(struct bus_type *subsys,
const struct attribute_group **groups)
{
return subsys_register(subsys, groups, &system_kset->kobj);
}
EXPORT_SYMBOL_GPL(subsys_system_register);
/**
* subsys_virtual_register - register a subsystem at /sys/devices/virtual/
* @subsys: virtual subsystem
* @groups: default attributes for the root device
*
* All 'virtual' subsystems have a /sys/devices/system/<name> root device
* with the name of the subystem. The root device can carry subsystem-wide
* attributes. All registered devices are below this single root device.
* There's no restriction on device naming. This is for kernel software
* constructs which need sysfs interface.
*/
int subsys_virtual_register(struct bus_type *subsys,
const struct attribute_group **groups)
{
struct kobject *virtual_dir;
virtual_dir = virtual_device_parent(NULL);
if (!virtual_dir)
return -ENOMEM;
return subsys_register(subsys, groups, virtual_dir);
}
EXPORT_SYMBOL_GPL(subsys_virtual_register);
int __init buses_init(void)
{
bus_kset = kset_create_and_add("bus", &bus_uevent_ops, NULL);
if (!bus_kset)
return -ENOMEM;
system_kset = kset_create_and_add("system", NULL, &devices_kset->kobj);
if (!system_kset)
return -ENOMEM;
return 0;
}