From a15d49fd3094cff90e5410ca454a870e0a722fe1 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 16 Apr 2012 15:06:25 +0200 Subject: driver core: check start node in klist_iter_init_node klist_iter_init_node() takes a node as a start argument. However, this node might not be valid anymore. This patch updates the klist_iter_init_node() and dependent functions to return an error if so. All calling functions have been audited to check for a return code here. Signed-off-by: Hannes Reinecke Cc: Greg Kroah-Hartmann Cc: Kay Sievers Cc: Stable Kernel Cc: Linux Kernel Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux/device.h') diff --git a/include/linux/device.h b/include/linux/device.h index 5ad17cccdd71..50429b911b21 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -128,7 +128,7 @@ struct subsys_dev_iter { struct klist_iter ki; const struct device_type *type; }; -void subsys_dev_iter_init(struct subsys_dev_iter *iter, +int subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys, struct device *start, const struct device_type *type); @@ -380,10 +380,10 @@ int class_compat_create_link(struct class_compat *cls, struct device *dev, void class_compat_remove_link(struct class_compat *cls, struct device *dev, struct device *device_link); -extern void class_dev_iter_init(struct class_dev_iter *iter, - struct class *class, - struct device *start, - const struct device_type *type); +extern int class_dev_iter_init(struct class_dev_iter *iter, + struct class *class, + struct device *start, + const struct device_type *type); extern struct device *class_dev_iter_next(struct class_dev_iter *iter); extern void class_dev_iter_exit(struct class_dev_iter *iter); -- cgit v1.2.3 From 7cd9c9bb57476167e83b7780dbc06d1dd601789d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 19 Apr 2012 19:17:30 -0700 Subject: Revert "driver core: check start node in klist_iter_init_node" This reverts commit a15d49fd3094cff90e5410ca454a870e0a722fe1 as that patch broke the build. Cc: Hannes Reinecke Reported-by: Stephen Rothwell Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 46 +++++++++++++++++----------------------------- drivers/base/class.c | 32 ++++++++++++-------------------- drivers/base/driver.c | 18 +++++++----------- include/linux/device.h | 10 +++++----- include/linux/klist.h | 2 +- lib/klist.c | 14 ++++---------- 6 files changed, 46 insertions(+), 76 deletions(-) (limited to 'include/linux/device.h') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 76aed01a8b2c..2bcef657a60c 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -296,13 +296,11 @@ int bus_for_each_dev(struct bus_type *bus, struct device *start, if (!bus) return -EINVAL; - error = klist_iter_init_node(&bus->p->klist_devices, &i, - (start ? &start->p->knode_bus : NULL)); - if (!error) { - while ((dev = next_device(&i)) && !error) - error = fn(dev, data); - klist_iter_exit(&i); - } + klist_iter_init_node(&bus->p->klist_devices, &i, + (start ? &start->p->knode_bus : NULL)); + while ((dev = next_device(&i)) && !error) + error = fn(dev, data); + klist_iter_exit(&i); return error; } EXPORT_SYMBOL_GPL(bus_for_each_dev); @@ -332,10 +330,8 @@ struct device *bus_find_device(struct bus_type *bus, if (!bus) return NULL; - if (klist_iter_init_node(&bus->p->klist_devices, &i, - (start ? &start->p->knode_bus : NULL)) < 0) - 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; @@ -388,9 +384,7 @@ struct device *subsys_find_device_by_id(struct bus_type *subsys, unsigned int id return NULL; if (hint) { - if (klist_iter_init_node(&subsys->p->klist_devices, &i, - &hint->p->knode_bus) < 0) - return NULL; + 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); @@ -452,13 +446,11 @@ int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, if (!bus) return -EINVAL; - error = klist_iter_init_node(&bus->p->klist_drivers, &i, - start ? &start->p->knode_bus : NULL); - if (!error) { - while ((drv = next_driver(&i)) && !error) - error = fn(drv, data); - klist_iter_exit(&i); - } + 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); @@ -1119,19 +1111,15 @@ EXPORT_SYMBOL_GPL(bus_sort_breadthfirst); * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ -int subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys, - struct device *start, const struct device_type *type) +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; - int error; if (start) start_knode = &start->p->knode_bus; - error = klist_iter_init_node(&subsys->p->klist_devices, &iter->ki, - start_knode); - if (!error) - iter->type = type; - return error; + klist_iter_init_node(&subsys->p->klist_devices, &iter->ki, start_knode); + iter->type = type; } EXPORT_SYMBOL_GPL(subsys_dev_iter_init); diff --git a/drivers/base/class.c b/drivers/base/class.c index 23dbc661d4a0..03243d4002fd 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -301,20 +301,15 @@ void class_destroy(struct class *cls) * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ -int class_dev_iter_init(struct class_dev_iter *iter, struct class *class, - struct device *start, const struct device_type *type) +void class_dev_iter_init(struct class_dev_iter *iter, struct class *class, + struct device *start, const struct device_type *type) { struct klist_node *start_knode = NULL; - int error; if (start) start_knode = &start->knode_class; - error = klist_iter_init_node(&class->p->klist_devices, &iter->ki, - start_knode); - if (!error) - iter->type = type; - - return error; + klist_iter_init_node(&class->p->klist_devices, &iter->ki, start_knode); + iter->type = type; } EXPORT_SYMBOL_GPL(class_dev_iter_init); @@ -392,15 +387,14 @@ int class_for_each_device(struct class *class, struct device *start, return -EINVAL; } - error = class_dev_iter_init(&iter, class, start, NULL); - if (!error) { - while ((dev = class_dev_iter_next(&iter))) { - error = fn(dev, data); - if (error) - break; - } - class_dev_iter_exit(&iter); + class_dev_iter_init(&iter, class, start, NULL); + while ((dev = class_dev_iter_next(&iter))) { + error = fn(dev, data); + if (error) + break; } + class_dev_iter_exit(&iter); + return error; } EXPORT_SYMBOL_GPL(class_for_each_device); @@ -440,9 +434,7 @@ struct device *class_find_device(struct class *class, struct device *start, return NULL; } - if (class_dev_iter_init(&iter, class, start, NULL) < 0) - return NULL; - + class_dev_iter_init(&iter, class, start, NULL); while ((dev = class_dev_iter_next(&iter))) { if (match(dev, data)) { get_device(dev); diff --git a/drivers/base/driver.c b/drivers/base/driver.c index 16f6dd2c4403..3ec3896c83a6 100644 --- a/drivers/base/driver.c +++ b/drivers/base/driver.c @@ -49,13 +49,11 @@ int driver_for_each_device(struct device_driver *drv, struct device *start, if (!drv) return -EINVAL; - error = klist_iter_init_node(&drv->p->klist_devices, &i, - start ? &start->p->knode_driver : NULL); - if (!error) { - while ((dev = next_device(&i)) && !error) - error = fn(dev, data); - klist_iter_exit(&i); - } + klist_iter_init_node(&drv->p->klist_devices, &i, + start ? &start->p->knode_driver : NULL); + while ((dev = next_device(&i)) && !error) + error = fn(dev, data); + klist_iter_exit(&i); return error; } EXPORT_SYMBOL_GPL(driver_for_each_device); @@ -85,10 +83,8 @@ struct device *driver_find_device(struct device_driver *drv, if (!drv) return NULL; - if (klist_iter_init_node(&drv->p->klist_devices, &i, - (start ? &start->p->knode_driver : NULL)) < 0) - return NULL; - + klist_iter_init_node(&drv->p->klist_devices, &i, + (start ? &start->p->knode_driver : NULL)); while ((dev = next_device(&i))) if (match(dev, data) && get_device(dev)) break; diff --git a/include/linux/device.h b/include/linux/device.h index 50429b911b21..5ad17cccdd71 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -128,7 +128,7 @@ struct subsys_dev_iter { struct klist_iter ki; const struct device_type *type; }; -int subsys_dev_iter_init(struct subsys_dev_iter *iter, +void subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys, struct device *start, const struct device_type *type); @@ -380,10 +380,10 @@ int class_compat_create_link(struct class_compat *cls, struct device *dev, void class_compat_remove_link(struct class_compat *cls, struct device *dev, struct device *device_link); -extern int class_dev_iter_init(struct class_dev_iter *iter, - struct class *class, - struct device *start, - const struct device_type *type); +extern void class_dev_iter_init(struct class_dev_iter *iter, + struct class *class, + struct device *start, + const struct device_type *type); extern struct device *class_dev_iter_next(struct class_dev_iter *iter); extern void class_dev_iter_exit(struct class_dev_iter *iter); diff --git a/include/linux/klist.h b/include/linux/klist.h index 9f633230f189..a370ce57cf1d 100644 --- a/include/linux/klist.h +++ b/include/linux/klist.h @@ -60,7 +60,7 @@ struct klist_iter { extern void klist_iter_init(struct klist *k, struct klist_iter *i); -extern int klist_iter_init_node(struct klist *k, struct klist_iter *i, +extern void klist_iter_init_node(struct klist *k, struct klist_iter *i, struct klist_node *n); extern void klist_iter_exit(struct klist_iter *i); extern struct klist_node *klist_next(struct klist_iter *i); diff --git a/lib/klist.c b/lib/klist.c index a2741a7d9784..0874e41609a6 100644 --- a/lib/klist.c +++ b/lib/klist.c @@ -278,19 +278,13 @@ EXPORT_SYMBOL_GPL(klist_node_attached); * Similar to klist_iter_init(), but starts the action off with @n, * instead of with the list head. */ -int klist_iter_init_node(struct klist *k, struct klist_iter *i, - struct klist_node *n) +void klist_iter_init_node(struct klist *k, struct klist_iter *i, + struct klist_node *n) { - if (n) { - kref_get(&n->n_ref); - if (!n->n_klist) { - kref_put(&n->n_ref); - return -ENODEV; - } - } i->i_klist = k; i->i_cur = n; - return 0; + if (n) + kref_get(&n->n_ref); } EXPORT_SYMBOL_GPL(klist_iter_init_node); -- cgit v1.2.3 From 94758185689ee96694558d720d44e81b4e0abc3d Mon Sep 17 00:00:00 2001 From: Michael Davidson Date: Thu, 3 May 2012 16:19:02 -0700 Subject: driver-core: fix DEVICE_INT_ATTR to use correct show/store functions DEVICE_INT_ATTR() should use device_show_int() and device_store_int() not device_show_ulong() and device_store_ulong() Signed-off-by: Michael Davidson Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/device.h') diff --git a/include/linux/device.h b/include/linux/device.h index 5ad17cccdd71..3ab4d63609b6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -502,7 +502,7 @@ ssize_t device_store_int(struct device *dev, struct device_attribute *attr, { __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) } #define DEVICE_INT_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ - { __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) } + { __ATTR(_name, _mode, device_show_int, device_store_int), &(_var) } extern int device_create_file(struct device *device, const struct device_attribute *entry); -- cgit v1.2.3 From d926d0e4c74cfcb42a05e91d1cdf698b41e1e118 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 3 May 2012 18:15:13 +0100 Subject: devres: Add devres_release() APIs using devres frequently want to implement a "remove and free the resource" operation so it seems sensible that they should be able to just have devres do the freeing for them since that's a big part of what devres is all about. Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/base/devres.c | 31 +++++++++++++++++++++++++++++++ include/linux/device.h | 2 ++ 2 files changed, 33 insertions(+) (limited to 'include/linux/device.h') diff --git a/drivers/base/devres.c b/drivers/base/devres.c index 1741a60de117..2360adb7a58f 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -330,6 +330,37 @@ int devres_destroy(struct device *dev, dr_release_t release, } EXPORT_SYMBOL_GPL(devres_destroy); + +/** + * devres_release - Find a device resource and destroy it, calling release + * @dev: Device to find resource from + * @release: Look for resources associated with this release function + * @match: Match function (optional) + * @match_data: Data for the match function + * + * Find the latest devres of @dev associated with @release and for + * which @match returns 1. If @match is NULL, it's considered to + * match all. If found, the resource is removed atomically, the + * release function called and the resource freed. + * + * RETURNS: + * 0 if devres is found and freed, -ENOENT if not found. + */ +int devres_release(struct device *dev, dr_release_t release, + dr_match_t match, void *match_data) +{ + void *res; + + res = devres_remove(dev, release, match, match_data); + if (unlikely(!res)) + return -ENOENT; + + (*release)(dev, res); + devres_free(res); + return 0; +} +EXPORT_SYMBOL_GPL(devres_release); + static int remove_nodes(struct device *dev, struct list_head *first, struct list_head *end, struct list_head *todo) diff --git a/include/linux/device.h b/include/linux/device.h index 3ab4d63609b6..863acf8a0dce 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -541,6 +541,8 @@ extern void *devres_remove(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); extern int devres_destroy(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); +extern int devres_release(struct device *dev, dr_release_t release, + dr_match_t match, void *match_data); /* devres group */ extern void * __must_check devres_open_group(struct device *dev, void *id, -- cgit v1.2.3 From 6ca045930338485a8cdef117e74372aa1678009d Mon Sep 17 00:00:00 2001 From: Hiroshi DOYU Date: Mon, 14 May 2012 10:47:57 +0300 Subject: driver core: Add dev_*_ratelimited() family Add dev_*_ratelimited() family, dev_* version of pr_*_ratelimited(). Using Joe Perches's proposal/implementation. Signed-off-by: Hiroshi DOYU Cc: Joe Perches Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux/device.h') diff --git a/include/linux/device.h b/include/linux/device.h index 863acf8a0dce..a8db2cfa2c81 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -23,6 +23,7 @@ #include #include #include +#include #include struct device; @@ -933,6 +934,32 @@ int _dev_info(const struct device *dev, const char *fmt, ...) #endif +#define dev_level_ratelimited(dev_level, dev, fmt, ...) \ +do { \ + static DEFINE_RATELIMIT_STATE(_rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + if (__ratelimit(&_rs)) \ + dev_level(dev, fmt, ##__VA_ARGS__); \ +} while (0) + +#define dev_emerg_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_emerg, dev, fmt, ##__VA_ARGS__) +#define dev_alert_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_alert, dev, fmt, ##__VA_ARGS__) +#define dev_crit_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_crit, dev, fmt, ##__VA_ARGS__) +#define dev_err_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_err, dev, fmt, ##__VA_ARGS__) +#define dev_warn_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_warn, dev, fmt, ##__VA_ARGS__) +#define dev_notice_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_notice, dev, fmt, ##__VA_ARGS__) +#define dev_info_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_info, dev, fmt, ##__VA_ARGS__) +#define dev_dbg_ratelimited(dev, fmt, ...) \ + dev_level_ratelimited(dev_dbg, dev, fmt, ##__VA_ARGS__) + /* * Stupid hackaround for existing uses of non-printk uses dev_info * -- cgit v1.2.3 From 356c05d58af05d582e634b54b40050c73609617b Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 14 May 2012 13:30:03 -0400 Subject: sysfs: get rid of some lockdep false positives This patch (as1554) fixes a lockdep false-positive report. The problem arises because lockdep is unable to deal with the tree-structured locks created by the device core and sysfs. This particular problem involves a sysfs attribute method that unregisters itself, not from the device it was called for, but from a descendant device. Lockdep doesn't understand the distinction and reports a possible deadlock, even though the operation is safe. This is the sort of thing that would normally be handled by using a nested lock annotation; unfortunately it's not feasible to do that here. There's no sensible way to tell sysfs when attribute removal occurs in the context of a parent attribute method. As a workaround, the patch adds a new flag to struct attribute telling sysfs not to inform lockdep when it acquires a readlock on a sysfs_dirent instance for the attribute. The readlock is still acquired, but lockdep doesn't know about it and hence does not complain about impossible deadlock scenarios. Also added are macros for static initialization of attribute structures with the ignore_lockdep flag set. The three offending attributes in the USB subsystem are converted to use the new macros. Signed-off-by: Alan Stern Acked-by: Tejun Heo CC: Eric W. Biederman CC: Peter Zijlstra Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/sysfs.c | 6 +++--- fs/sysfs/dir.c | 31 ++++++++++++++++++++++++++----- include/linux/device.h | 3 +++ include/linux/sysfs.h | 12 ++++++++++++ 4 files changed, 44 insertions(+), 8 deletions(-) (limited to 'include/linux/device.h') diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index 566d9f94f735..9a56e3adf476 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -73,7 +73,7 @@ set_bConfigurationValue(struct device *dev, struct device_attribute *attr, return (value < 0) ? value : count; } -static DEVICE_ATTR(bConfigurationValue, S_IRUGO | S_IWUSR, +static DEVICE_ATTR_IGNORE_LOCKDEP(bConfigurationValue, S_IRUGO | S_IWUSR, show_bConfigurationValue, set_bConfigurationValue); /* String fields */ @@ -595,7 +595,7 @@ static ssize_t usb_dev_authorized_store(struct device *dev, return result < 0? result : size; } -static DEVICE_ATTR(authorized, 0644, +static DEVICE_ATTR_IGNORE_LOCKDEP(authorized, 0644, usb_dev_authorized_show, usb_dev_authorized_store); /* "Safely remove a device" */ @@ -618,7 +618,7 @@ static ssize_t usb_remove_store(struct device *dev, usb_unlock_device(udev); return rc; } -static DEVICE_ATTR(remove, 0200, NULL, usb_remove_store); +static DEVICE_ATTR_IGNORE_LOCKDEP(remove, 0200, NULL, usb_remove_store); static struct attribute *dev_attrs[] = { diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 24fa995f0312..e6bb9b2a4cbe 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -132,6 +132,24 @@ static void sysfs_unlink_sibling(struct sysfs_dirent *sd) rb_erase(&sd->s_rb, &sd->s_parent->s_dir.children); } +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +/* Test for attributes that want to ignore lockdep for read-locking */ +static bool ignore_lockdep(struct sysfs_dirent *sd) +{ + return sysfs_type(sd) == SYSFS_KOBJ_ATTR && + sd->s_attr.attr->ignore_lockdep; +} + +#else + +static inline bool ignore_lockdep(struct sysfs_dirent *sd) +{ + return true; +} + +#endif + /** * sysfs_get_active - get an active reference to sysfs_dirent * @sd: sysfs_dirent to get an active reference to @@ -155,15 +173,17 @@ struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd) return NULL; t = atomic_cmpxchg(&sd->s_active, v, v + 1); - if (likely(t == v)) { - rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_); - return sd; - } + if (likely(t == v)) + break; if (t < 0) return NULL; cpu_relax(); } + + if (likely(!ignore_lockdep(sd))) + rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_); + return sd; } /** @@ -180,7 +200,8 @@ void sysfs_put_active(struct sysfs_dirent *sd) if (unlikely(!sd)) return; - rwsem_release(&sd->dep_map, 1, _RET_IP_); + if (likely(!ignore_lockdep(sd))) + rwsem_release(&sd->dep_map, 1, _RET_IP_); v = atomic_dec_return(&sd->s_active); if (likely(v != SD_DEACTIVATED_BIAS)) return; diff --git a/include/linux/device.h b/include/linux/device.h index a8db2cfa2c81..e04f5776f6d0 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -504,6 +504,9 @@ ssize_t device_store_int(struct device *dev, struct device_attribute *attr, #define DEVICE_INT_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_int, device_store_int), &(_var) } +#define DEVICE_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \ + struct device_attribute dev_attr_##_name = \ + __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) extern int device_create_file(struct device *device, const struct device_attribute *entry); diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 0010009b2f00..381f06db2fe5 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -27,6 +27,7 @@ struct attribute { const char *name; umode_t mode; #ifdef CONFIG_DEBUG_LOCK_ALLOC + bool ignore_lockdep:1; struct lock_class_key *key; struct lock_class_key skey; #endif @@ -80,6 +81,17 @@ struct attribute_group { #define __ATTR_NULL { .attr = { .name = NULL } } +#ifdef CONFIG_DEBUG_LOCK_ALLOC +#define __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) { \ + .attr = {.name = __stringify(_name), .mode = _mode, \ + .ignore_lockdep = true }, \ + .show = _show, \ + .store = _store, \ +} +#else +#define __ATTR_IGNORE_LOCKDEP __ATTR +#endif + #define attr_name(_attr) (_attr).attr.name struct file; -- cgit v1.2.3 From c64be2bb1c6eb43c838b2c6d57b074078be208dd Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Thu, 29 Dec 2011 13:09:51 +0100 Subject: drivers: add Contiguous Memory Allocator The Contiguous Memory Allocator is a set of helper functions for DMA mapping framework that improves allocations of contiguous memory chunks. CMA grabs memory on system boot, marks it with MIGRATE_CMA migrate type and gives back to the system. Kernel is allowed to allocate only movable pages within CMA's managed memory so that it can be used for example for page cache when DMA mapping do not use it. On dma_alloc_from_contiguous() request such pages are migrated out of CMA area to free required contiguous block and fulfill the request. This allows to allocate large contiguous chunks of memory at any time assuming that there is enough free memory available in the system. This code is heavily based on earlier works by Michal Nazarewicz. Signed-off-by: Marek Szyprowski Signed-off-by: Kyungmin Park Signed-off-by: Michal Nazarewicz Acked-by: Arnd Bergmann Tested-by: Rob Clark Tested-by: Ohad Ben-Cohen Tested-by: Benjamin Gaignard Tested-by: Robert Nelson Tested-by: Barry Song --- Documentation/kernel-parameters.txt | 5 + arch/Kconfig | 3 + drivers/base/Kconfig | 89 ++++++++ drivers/base/Makefile | 1 + drivers/base/dma-contiguous.c | 401 +++++++++++++++++++++++++++++++++++ include/asm-generic/dma-contiguous.h | 28 +++ include/linux/device.h | 4 + include/linux/dma-contiguous.h | 110 ++++++++++ 8 files changed, 641 insertions(+) create mode 100644 drivers/base/dma-contiguous.c create mode 100644 include/asm-generic/dma-contiguous.h create mode 100644 include/linux/dma-contiguous.h (limited to 'include/linux/device.h') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index c1601e5a8b71..669e8bb52b94 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -508,6 +508,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Also note the kernel might malfunction if you disable some critical bits. + cma=nn[MG] [ARM,KNL] + Sets the size of kernel global memory area for contiguous + memory allocations. For more information, see + include/linux/dma-contiguous.h + cmo_free_hint= [PPC] Format: { yes | no } Specify whether pages are marked as being inactive when they are freed. This is used in CMO environments diff --git a/arch/Kconfig b/arch/Kconfig index 684eb5af439d..0a3ffe46e567 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -142,6 +142,9 @@ config HAVE_ARCH_TRACEHOOK config HAVE_DMA_ATTRS bool +config HAVE_DMA_CONTIGUOUS + bool + config USE_GENERIC_SMP_HELPERS bool diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 9aa618acfe97..9b21469482ae 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -192,4 +192,93 @@ config DMA_SHARED_BUFFER APIs extension; the file's descriptor can then be passed on to other driver. +config CMA + bool "Contiguous Memory Allocator (EXPERIMENTAL)" + depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK && EXPERIMENTAL + select MIGRATION + help + This enables the Contiguous Memory Allocator which allows drivers + to allocate big physically-contiguous blocks of memory for use with + hardware components that do not support I/O map nor scatter-gather. + + For more information see . + If unsure, say "n". + +if CMA + +config CMA_DEBUG + bool "CMA debug messages (DEVELOPMENT)" + depends on DEBUG_KERNEL + help + Turns on debug messages in CMA. This produces KERN_DEBUG + messages for every CMA call as well as various messages while + processing calls such as dma_alloc_from_contiguous(). + This option does not affect warning and error messages. + +comment "Default contiguous memory area size:" + +config CMA_SIZE_MBYTES + int "Size in Mega Bytes" + depends on !CMA_SIZE_SEL_PERCENTAGE + default 16 + help + Defines the size (in MiB) of the default memory area for Contiguous + Memory Allocator. + +config CMA_SIZE_PERCENTAGE + int "Percentage of total memory" + depends on !CMA_SIZE_SEL_MBYTES + default 10 + help + Defines the size of the default memory area for Contiguous Memory + Allocator as a percentage of the total memory in the system. + +choice + prompt "Selected region size" + default CMA_SIZE_SEL_ABSOLUTE + +config CMA_SIZE_SEL_MBYTES + bool "Use mega bytes value only" + +config CMA_SIZE_SEL_PERCENTAGE + bool "Use percentage value only" + +config CMA_SIZE_SEL_MIN + bool "Use lower value (minimum)" + +config CMA_SIZE_SEL_MAX + bool "Use higher value (maximum)" + +endchoice + +config CMA_ALIGNMENT + int "Maximum PAGE_SIZE order of alignment for contiguous buffers" + range 4 9 + default 8 + help + DMA mapping framework by default aligns all buffers to the smallest + PAGE_SIZE order which is greater than or equal to the requested buffer + size. This works well for buffers up to a few hundreds kilobytes, but + for larger buffers it just a memory waste. With this parameter you can + specify the maximum PAGE_SIZE order for contiguous buffers. Larger + buffers will be aligned only to this specified order. The order is + expressed as a power of two multiplied by the PAGE_SIZE. + + For example, if your system defaults to 4KiB pages, the order value + of 8 means that the buffers will be aligned up to 1MiB only. + + If unsure, leave the default value "8". + +config CMA_AREAS + int "Maximum count of the CMA device-private areas" + default 7 + help + CMA allows to create CMA areas for particular devices. This parameter + sets the maximum number of such device private CMA areas in the + system. + + If unsure, leave the default value "7". + +endif + endmenu diff --git a/drivers/base/Makefile b/drivers/base/Makefile index b6d1b9c4200c..5aa2d703d19f 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -6,6 +6,7 @@ obj-y := core.o bus.o dd.o syscore.o \ attribute_container.o transport_class.o \ topology.o obj-$(CONFIG_DEVTMPFS) += devtmpfs.o +obj-$(CONFIG_CMA) += dma-contiguous.o obj-y += power/ obj-$(CONFIG_HAS_DMA) += dma-mapping.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c new file mode 100644 index 000000000000..78efb0306a44 --- /dev/null +++ b/drivers/base/dma-contiguous.c @@ -0,0 +1,401 @@ +/* + * Contiguous Memory Allocator for DMA mapping framework + * Copyright (c) 2010-2011 by Samsung Electronics. + * Written by: + * Marek Szyprowski + * Michal Nazarewicz + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License or (at your optional) any later version of the license. + */ + +#define pr_fmt(fmt) "cma: " fmt + +#ifdef CONFIG_CMA_DEBUG +#ifndef DEBUG +# define DEBUG +#endif +#endif + +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifndef SZ_1M +#define SZ_1M (1 << 20) +#endif + +struct cma { + unsigned long base_pfn; + unsigned long count; + unsigned long *bitmap; +}; + +struct cma *dma_contiguous_default_area; + +#ifdef CONFIG_CMA_SIZE_MBYTES +#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES +#else +#define CMA_SIZE_MBYTES 0 +#endif + +/* + * Default global CMA area size can be defined in kernel's .config. + * This is usefull mainly for distro maintainers to create a kernel + * that works correctly for most supported systems. + * The size can be set in bytes or as a percentage of the total memory + * in the system. + * + * Users, who want to set the size of global CMA area for their system + * should use cma= kernel parameter. + */ +static const unsigned long size_bytes = CMA_SIZE_MBYTES * SZ_1M; +static long size_cmdline = -1; + +static int __init early_cma(char *p) +{ + pr_debug("%s(%s)\n", __func__, p); + size_cmdline = memparse(p, &p); + return 0; +} +early_param("cma", early_cma); + +#ifdef CONFIG_CMA_SIZE_PERCENTAGE + +static unsigned long __init __maybe_unused cma_early_percent_memory(void) +{ + struct memblock_region *reg; + unsigned long total_pages = 0; + + /* + * We cannot use memblock_phys_mem_size() here, because + * memblock_analyze() has not been called yet. + */ + for_each_memblock(memory, reg) + total_pages += memblock_region_memory_end_pfn(reg) - + memblock_region_memory_base_pfn(reg); + + return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT; +} + +#else + +static inline __maybe_unused unsigned long cma_early_percent_memory(void) +{ + return 0; +} + +#endif + +/** + * dma_contiguous_reserve() - reserve area for contiguous memory handling + * @limit: End address of the reserved memory (optional, 0 for any). + * + * This function reserves memory from early allocator. It should be + * called by arch specific code once the early allocator (memblock or bootmem) + * has been activated and all other subsystems have already allocated/reserved + * memory. + */ +void __init dma_contiguous_reserve(phys_addr_t limit) +{ + unsigned long selected_size = 0; + + pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit); + + if (size_cmdline != -1) { + selected_size = size_cmdline; + } else { +#ifdef CONFIG_CMA_SIZE_SEL_MBYTES + selected_size = size_bytes; +#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE) + selected_size = cma_early_percent_memory(); +#elif defined(CONFIG_CMA_SIZE_SEL_MIN) + selected_size = min(size_bytes, cma_early_percent_memory()); +#elif defined(CONFIG_CMA_SIZE_SEL_MAX) + selected_size = max(size_bytes, cma_early_percent_memory()); +#endif + } + + if (selected_size) { + pr_debug("%s: reserving %ld MiB for global area\n", __func__, + selected_size / SZ_1M); + + dma_declare_contiguous(NULL, selected_size, 0, limit); + } +}; + +static DEFINE_MUTEX(cma_mutex); + +static __init int cma_activate_area(unsigned long base_pfn, unsigned long count) +{ + unsigned long pfn = base_pfn; + unsigned i = count >> pageblock_order; + struct zone *zone; + + WARN_ON_ONCE(!pfn_valid(pfn)); + zone = page_zone(pfn_to_page(pfn)); + + do { + unsigned j; + base_pfn = pfn; + for (j = pageblock_nr_pages; j; --j, pfn++) { + WARN_ON_ONCE(!pfn_valid(pfn)); + if (page_zone(pfn_to_page(pfn)) != zone) + return -EINVAL; + } + init_cma_reserved_pageblock(pfn_to_page(base_pfn)); + } while (--i); + return 0; +} + +static __init struct cma *cma_create_area(unsigned long base_pfn, + unsigned long count) +{ + int bitmap_size = BITS_TO_LONGS(count) * sizeof(long); + struct cma *cma; + int ret = -ENOMEM; + + pr_debug("%s(base %08lx, count %lx)\n", __func__, base_pfn, count); + + cma = kmalloc(sizeof *cma, GFP_KERNEL); + if (!cma) + return ERR_PTR(-ENOMEM); + + cma->base_pfn = base_pfn; + cma->count = count; + cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL); + + if (!cma->bitmap) + goto no_mem; + + ret = cma_activate_area(base_pfn, count); + if (ret) + goto error; + + pr_debug("%s: returned %p\n", __func__, (void *)cma); + return cma; + +error: + kfree(cma->bitmap); +no_mem: + kfree(cma); + return ERR_PTR(ret); +} + +static struct cma_reserved { + phys_addr_t start; + unsigned long size; + struct device *dev; +} cma_reserved[MAX_CMA_AREAS] __initdata; +static unsigned cma_reserved_count __initdata; + +static int __init cma_init_reserved_areas(void) +{ + struct cma_reserved *r = cma_reserved; + unsigned i = cma_reserved_count; + + pr_debug("%s()\n", __func__); + + for (; i; --i, ++r) { + struct cma *cma; + cma = cma_create_area(PFN_DOWN(r->start), + r->size >> PAGE_SHIFT); + if (!IS_ERR(cma)) + dev_set_cma_area(r->dev, cma); + } + return 0; +} +core_initcall(cma_init_reserved_areas); + +/** + * dma_declare_contiguous() - reserve area for contiguous memory handling + * for particular device + * @dev: Pointer to device structure. + * @size: Size of the reserved memory. + * @base: Start address of the reserved memory (optional, 0 for any). + * @limit: End address of the reserved memory (optional, 0 for any). + * + * This function reserves memory for specified device. It should be + * called by board specific code when early allocator (memblock or bootmem) + * is still activate. + */ +int __init dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit) +{ + struct cma_reserved *r = &cma_reserved[cma_reserved_count]; + unsigned long alignment; + + pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__, + (unsigned long)size, (unsigned long)base, + (unsigned long)limit); + + /* Sanity checks */ + if (cma_reserved_count == ARRAY_SIZE(cma_reserved)) { + pr_err("Not enough slots for CMA reserved regions!\n"); + return -ENOSPC; + } + + if (!size) + return -EINVAL; + + /* Sanitise input arguments */ + alignment = PAGE_SIZE << max(MAX_ORDER, pageblock_order); + base = ALIGN(base, alignment); + size = ALIGN(size, alignment); + limit &= ~(alignment - 1); + + /* Reserve memory */ + if (base) { + if (memblock_is_region_reserved(base, size) || + memblock_reserve(base, size) < 0) { + base = -EBUSY; + goto err; + } + } else { + /* + * Use __memblock_alloc_base() since + * memblock_alloc_base() panic()s. + */ + phys_addr_t addr = __memblock_alloc_base(size, alignment, limit); + if (!addr) { + base = -ENOMEM; + goto err; + } else if (addr + size > ~(unsigned long)0) { + memblock_free(addr, size); + base = -EINVAL; + goto err; + } else { + base = addr; + } + } + + /* + * Each reserved area must be initialised later, when more kernel + * subsystems (like slab allocator) are available. + */ + r->start = base; + r->size = size; + r->dev = dev; + cma_reserved_count++; + pr_info("CMA: reserved %ld MiB at %08lx\n", size / SZ_1M, + (unsigned long)base); + + /* Architecture specific contiguous memory fixup. */ + dma_contiguous_early_fixup(base, size); + return 0; +err: + pr_err("CMA: failed to reserve %ld MiB\n", size / SZ_1M); + return base; +} + +/** + * dma_alloc_from_contiguous() - allocate pages from contiguous area + * @dev: Pointer to device for which the allocation is performed. + * @count: Requested number of pages. + * @align: Requested alignment of pages (in PAGE_SIZE order). + * + * This function allocates memory buffer for specified device. It uses + * device specific contiguous memory area if available or the default + * global one. Requires architecture specific get_dev_cma_area() helper + * function. + */ +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int align) +{ + unsigned long mask, pfn, pageno, start = 0; + struct cma *cma = dev_get_cma_area(dev); + int ret; + + if (!cma || !cma->count) + return NULL; + + if (align > CONFIG_CMA_ALIGNMENT) + align = CONFIG_CMA_ALIGNMENT; + + pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma, + count, align); + + if (!count) + return NULL; + + mask = (1 << align) - 1; + + mutex_lock(&cma_mutex); + + for (;;) { + pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count, + start, count, mask); + if (pageno >= cma->count) { + ret = -ENOMEM; + goto error; + } + + pfn = cma->base_pfn + pageno; + ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA); + if (ret == 0) { + bitmap_set(cma->bitmap, pageno, count); + break; + } else if (ret != -EBUSY) { + goto error; + } + pr_debug("%s(): memory range at %p is busy, retrying\n", + __func__, pfn_to_page(pfn)); + /* try again with a bit different memory target */ + start = pageno + mask + 1; + } + + mutex_unlock(&cma_mutex); + + pr_debug("%s(): returned %p\n", __func__, pfn_to_page(pfn)); + return pfn_to_page(pfn); +error: + mutex_unlock(&cma_mutex); + return NULL; +} + +/** + * dma_release_from_contiguous() - release allocated pages + * @dev: Pointer to device for which the pages were allocated. + * @pages: Allocated pages. + * @count: Number of allocated pages. + * + * This function releases memory allocated by dma_alloc_from_contiguous(). + * It returns false when provided pages do not belong to contiguous area and + * true otherwise. + */ +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count) +{ + struct cma *cma = dev_get_cma_area(dev); + unsigned long pfn; + + if (!cma || !pages) + return false; + + pr_debug("%s(page %p)\n", __func__, (void *)pages); + + pfn = page_to_pfn(pages); + + if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) + return false; + + VM_BUG_ON(pfn + count > cma->base_pfn + cma->count); + + mutex_lock(&cma_mutex); + bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count); + free_contig_range(pfn, count); + mutex_unlock(&cma_mutex); + + return true; +} diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h new file mode 100644 index 000000000000..c544356b374b --- /dev/null +++ b/include/asm-generic/dma-contiguous.h @@ -0,0 +1,28 @@ +#ifndef ASM_DMA_CONTIGUOUS_H +#define ASM_DMA_CONTIGUOUS_H + +#ifdef __KERNEL__ +#ifdef CONFIG_CMA + +#include +#include + +static inline struct cma *dev_get_cma_area(struct device *dev) +{ + if (dev && dev->cma_area) + return dev->cma_area; + return dma_contiguous_default_area; +} + +static inline void dev_set_cma_area(struct device *dev, struct cma *cma) +{ + if (dev) + dev->cma_area = cma; + if (!dev || !dma_contiguous_default_area) + dma_contiguous_default_area = cma; +} + +#endif +#endif + +#endif diff --git a/include/linux/device.h b/include/linux/device.h index 5ad17cccdd71..e3399290436e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -661,6 +661,10 @@ struct device { struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ +#ifdef CONFIG_CMA + struct cma *cma_area; /* contiguous memory area for dma + allocations */ +#endif /* arch specific additions */ struct dev_archdata archdata; diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h new file mode 100644 index 000000000000..2f303e4b7ed3 --- /dev/null +++ b/include/linux/dma-contiguous.h @@ -0,0 +1,110 @@ +#ifndef __LINUX_CMA_H +#define __LINUX_CMA_H + +/* + * Contiguous Memory Allocator for DMA mapping framework + * Copyright (c) 2010-2011 by Samsung Electronics. + * Written by: + * Marek Szyprowski + * Michal Nazarewicz + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License or (at your optional) any later version of the license. + */ + +/* + * Contiguous Memory Allocator + * + * The Contiguous Memory Allocator (CMA) makes it possible to + * allocate big contiguous chunks of memory after the system has + * booted. + * + * Why is it needed? + * + * Various devices on embedded systems have no scatter-getter and/or + * IO map support and require contiguous blocks of memory to + * operate. They include devices such as cameras, hardware video + * coders, etc. + * + * Such devices often require big memory buffers (a full HD frame + * is, for instance, more then 2 mega pixels large, i.e. more than 6 + * MB of memory), which makes mechanisms such as kmalloc() or + * alloc_page() ineffective. + * + * At the same time, a solution where a big memory region is + * reserved for a device is suboptimal since often more memory is + * reserved then strictly required and, moreover, the memory is + * inaccessible to page system even if device drivers don't use it. + * + * CMA tries to solve this issue by operating on memory regions + * where only movable pages can be allocated from. This way, kernel + * can use the memory for pagecache and when device driver requests + * it, allocated pages can be migrated. + * + * Driver usage + * + * CMA should not be used by the device drivers directly. It is + * only a helper framework for dma-mapping subsystem. + * + * For more information, see kernel-docs in drivers/base/dma-contiguous.c + */ + +#ifdef __KERNEL__ + +struct cma; +struct page; +struct device; + +#ifdef CONFIG_CMA + +/* + * There is always at least global CMA area and a few optional device + * private areas configured in kernel .config. + */ +#define MAX_CMA_AREAS (1 + CONFIG_CMA_AREAS) + +extern struct cma *dma_contiguous_default_area; + +void dma_contiguous_reserve(phys_addr_t addr_limit); +int dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit); + +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int order); +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count); + +#else + +#define MAX_CMA_AREAS (0) + +static inline void dma_contiguous_reserve(phys_addr_t limit) { } + +static inline +int dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit) +{ + return -ENOSYS; +} + +static inline +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int order) +{ + return NULL; +} + +static inline +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count) +{ + return false; +} + +#endif + +#endif + +#endif -- cgit v1.2.3