From dd336c554d8926c3348a2d5f2a5ef5597f6d1a06 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sun, 2 May 2010 11:21:21 +0300 Subject: firmware_class: fix memory leak - free allocated pages fix memory leak introduced by the patch 6e03a201bbe: firmware: speed up request_firmware() 1. vfree won't release pages there were allocated explicitly and mapped using vmap. The memory has to be vunmap-ed and the pages needs to be freed explicitly 2. page array is moved into the 'struct firmware' so that we can free it from release_firmware() and not only in fw_dev_release() The fix doesn't break the firmware load speed. Cc: Johannes Berg Cc: Ming Lei Cc: Catalin Marinas Singed-off-by: Kay Sievers Signed-off-by: David Woodhouse Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 043811f0d277..53d1e6c4f848 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -12,6 +12,7 @@ struct firmware { size_t size; const u8 *data; + struct page **pages; }; struct device; -- cgit v1.2.3 From db1afffab0b5d9f6d31f8f4bea44c9cb3bc59351 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 16 Mar 2010 15:14:51 +1100 Subject: kref: remove kref_set Of the three uses of kref_set in the kernel: One really should be kref_put as the code is letting go of a reference, Two really should be kref_init because the kref is being initialised. This suggests that making kref_set available encourages bad code. So fix the three uses and remove kref_set completely. Signed-off-by: NeilBrown Acked-by: Mimi Zohar Acked-by: Serge Hallyn Signed-off-by: Greg Kroah-Hartman --- include/linux/kref.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kref.h b/include/linux/kref.h index baf4b9e4b194..6cc38fc07ab7 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -21,7 +21,6 @@ struct kref { atomic_t refcount; }; -void kref_set(struct kref *kref, int num); void kref_init(struct kref *kref); void kref_get(struct kref *kref); int kref_put(struct kref *kref, void (*release) (struct kref *kref)); -- cgit v1.2.3 From da5e4ef7fdb8f2fb0878dee3bd9d4dd10cea8cf1 Mon Sep 17 00:00:00 2001 From: Peter Korsgaard Date: Tue, 16 Mar 2010 21:55:21 +0100 Subject: devtmpfs: support !CONFIG_TMPFS Make devtmpfs available on (embedded) configurations without SHMEM/TMPFS, using ramfs instead. Saves ~15KB. Signed-off-by: Peter Korsgaard Acked-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/ramfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index 4e768dda87b0..8600508c77a6 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -20,4 +20,6 @@ extern const struct file_operations ramfs_file_operations; extern const struct vm_operations_struct generic_file_vm_ops; extern int __init init_rootfs(void); +int ramfs_fill_super(struct super_block *sb, void *data, int silent); + #endif -- cgit v1.2.3 From 3142788b7967ccfd2f1813ee9e11aeb1e1cf7de2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 29 Jan 2010 20:39:02 +0000 Subject: drivers/base: Convert dev->sem to mutex The semaphore is semantically a mutex. Convert it to a real mutex and fix up a few places where code was relying on semaphore.h to be included by device.h, as well as the users of the trylock function, as that value is now reversed. Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 241b96bcd7ad..6f9619190aaf 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -22,7 +22,6 @@ #include #include #include -#include #include #include @@ -404,7 +403,7 @@ struct device { const char *init_name; /* initial name of the device */ struct device_type *type; - struct semaphore sem; /* semaphore to synchronize calls to + struct mutex mutex; /* mutex to synchronize calls to * its driver. */ @@ -514,17 +513,17 @@ static inline bool device_async_suspend_enabled(struct device *dev) static inline void device_lock(struct device *dev) { - down(&dev->sem); + mutex_lock(&dev->mutex); } static inline int device_trylock(struct device *dev) { - return down_trylock(&dev->sem); + return mutex_trylock(&dev->mutex); } static inline void device_unlock(struct device *dev) { - up(&dev->sem); + mutex_unlock(&dev->mutex); } void driver_init(void); -- cgit v1.2.3 From 1704f47b50b5d9e1b825e43e1baaf2c5897baf03 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 19 Mar 2010 01:37:42 +0100 Subject: lockdep: Add novalidate class for dev->mutex conversion The conversion of device->sem to device->mutex resulted in lockdep warnings. Create a novalidate class for now until the driver folks come up with separate classes. That way we have at least the basic mutex debugging coverage. Add a checkpatch error so the usage is reserved for device->mutex. [ tglx: checkpatch and compile fix for LOCKDEP=n ] Signed-off-by: Peter Zijlstra Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- include/linux/lockdep.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index a03977a96d7e..06aed8305bf3 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -44,6 +44,8 @@ struct lock_class_key { struct lockdep_subclass_key subkeys[MAX_LOCKDEP_SUBCLASSES]; }; +extern struct lock_class_key __lockdep_no_validate__; + #define LOCKSTAT_POINTS 4 /* @@ -270,6 +272,9 @@ extern void lockdep_init_map(struct lockdep_map *lock, const char *name, #define lockdep_set_subclass(lock, sub) \ lockdep_init_map(&(lock)->dep_map, #lock, \ (lock)->dep_map.key, sub) + +#define lockdep_set_novalidate_class(lock) \ + lockdep_set_class(lock, &__lockdep_no_validate__) /* * Compare locking classes */ @@ -354,6 +359,9 @@ static inline void lockdep_on(void) #define lockdep_set_class_and_subclass(lock, key, sub) \ do { (void)(key); } while (0) #define lockdep_set_subclass(lock, sub) do { } while (0) + +#define lockdep_set_novalidate_class(lock) do { } while (0) + /* * We don't define lockdep_match_class() and lockdep_match_key() for !LOCKDEP * case since the result is not well defined and the caller should rather -- cgit v1.2.3 From bc451f2058238013e1cdf4acd443c01734d332f0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 30 Mar 2010 11:31:25 -0700 Subject: kobj: Add basic infrastructure for dealing with namespaces. Move complete knowledge of namespaces into the kobject layer so we can use that information when reporting kobjects to userspace. Signed-off-by: Eric W. Biederman Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 3 +++ include/linux/kobject.h | 26 ++++++++++++++++++++++++++ 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 6f9619190aaf..7bb9f426f3e6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -202,6 +202,9 @@ struct class { int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); + const struct kobj_ns_type_operations *ns_type; + const void *(*namespace)(struct device *dev); + const struct dev_pm_ops *pm; struct class_private *p; diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 3950d3c2850d..d9456f69904f 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -108,6 +108,8 @@ struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; struct attribute **default_attrs; + const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); + const void *(*namespace)(struct kobject *kobj); }; struct kobj_uevent_env { @@ -134,6 +136,30 @@ struct kobj_attribute { extern const struct sysfs_ops kobj_sysfs_ops; +enum kobj_ns_type { + KOBJ_NS_TYPE_NONE = 0, + KOBJ_NS_TYPES +}; + +struct sock; +struct kobj_ns_type_operations { + enum kobj_ns_type type; + const void *(*current_ns)(void); + const void *(*netlink_ns)(struct sock *sk); + const void *(*initial_ns)(void); +}; + +int kobj_ns_type_register(const struct kobj_ns_type_operations *ops); +int kobj_ns_type_registered(enum kobj_ns_type type); +const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent); +const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj); + +const void *kobj_ns_current(enum kobj_ns_type type); +const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk); +const void *kobj_ns_initial(enum kobj_ns_type type); +void kobj_ns_exit(enum kobj_ns_type type, const void *ns); + + /** * struct kset - a set of kobjects of a specific type, belonging to a specific subsystem. * -- cgit v1.2.3 From 3ff195b011d7decf501a4d55aeed312731094796 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 30 Mar 2010 11:31:26 -0700 Subject: sysfs: Implement sysfs tagged directory support. The problem. When implementing a network namespace I need to be able to have multiple network devices with the same name. Currently this is a problem for /sys/class/net/*, /sys/devices/virtual/net/*, and potentially a few other directories of the form /sys/ ... /net/*. What this patch does is to add an additional tag field to the sysfs dirent structure. For directories that should show different contents depending on the context such as /sys/class/net/, and /sys/devices/virtual/net/ this tag field is used to specify the context in which those directories should be visible. Effectively this is the same as creating multiple distinct directories with the same name but internally to sysfs the result is nicer. I am calling the concept of a single directory that looks like multiple directories all at the same path in the filesystem tagged directories. For the networking namespace the set of directories whose contents I need to filter with tags can depend on the presence or absence of hotplug hardware or which modules are currently loaded. Which means I need a simple race free way to setup those directories as tagged. To achieve a reace free design all tagged directories are created and managed by sysfs itself. Users of this interface: - define a type in the sysfs_tag_type enumeration. - call sysfs_register_ns_types with the type and it's operations - sysfs_exit_ns when an individual tag is no longer valid - Implement mount_ns() which returns the ns of the calling process so we can attach it to a sysfs superblock. - Implement ktype.namespace() which returns the ns of a syfs kobject. Everything else is left up to sysfs and the driver layer. For the network namespace mount_ns and namespace() are essentially one line functions, and look to remain that. Tags are currently represented a const void * pointers as that is both generic, prevides enough information for equality comparisons, and is trivial to create for current users, as it is just the existing namespace pointer. The work needed in sysfs is more extensive. At each directory or symlink creating I need to check if the directory it is being created in is a tagged directory and if so generate the appropriate tag to place on the sysfs_dirent. Likewise at each symlink or directory removal I need to check if the sysfs directory it is being removed from is a tagged directory and if so figure out which tag goes along with the name I am deleting. Currently only directories which hold kobjects, and symlinks are supported. There is not enough information in the current file attribute interfaces to give us anything to discriminate on which makes it useless, and there are no potential users which makes it an uninteresting problem to solve. Signed-off-by: Eric W. Biederman Signed-off-by: Benjamin Thery Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index f0496b3d1811..1885d21b0c80 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -20,6 +20,7 @@ struct kobject; struct module; +enum kobj_ns_type; /* FIXME * The *owner field is no longer used. @@ -168,10 +169,14 @@ void sysfs_remove_file_from_group(struct kobject *kobj, void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr); void sysfs_notify_dirent(struct sysfs_dirent *sd); struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd, + const void *ns, const unsigned char *name); struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd); void sysfs_put(struct sysfs_dirent *sd); void sysfs_printk_last_file(void); + +void sysfs_exit_ns(enum kobj_ns_type type, const void *tag); + int __must_check sysfs_init(void); #else /* CONFIG_SYSFS */ @@ -301,6 +306,7 @@ static inline void sysfs_notify_dirent(struct sysfs_dirent *sd) } static inline struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd, + const void *ns, const unsigned char *name) { return NULL; @@ -313,6 +319,10 @@ static inline void sysfs_put(struct sysfs_dirent *sd) { } +static inline void sysfs_exit_ns(enum kobj_ns_type type, const void *tag) +{ +} + static inline int __must_check sysfs_init(void) { return 0; -- cgit v1.2.3 From 746edb7ae8a1abdd39be2b28c03aa073183340db Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 30 Mar 2010 11:31:28 -0700 Subject: sysfs: Implement sysfs_delete_link When removing a symlink sysfs_remove_link does not provide enough information to figure out which tagged directory the symlink falls in. So I need sysfs_delete_link which is passed the target of the symlink to delete. sysfs_rename_link is updated to call sysfs_delete_link instead of sysfs_remove_link as we have all of the information necessary and the callers are interesting. Both of these functions now have enough information to find a symlink in a tagged directory. The only restriction is that they must be called before the target kobject is renamed or deleted. If they are called later I loose track of which tag the target kobject was marked with and can no longer find the old symlink to remove it. This patch was split from an earlier patch. Signed-off-by: Eric W. Biederman Signed-off-by: Benjamin Thery Signed-off-by: Daniel Lezcano Acked-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 1885d21b0c80..976c4664b216 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -155,6 +155,9 @@ void sysfs_remove_link(struct kobject *kobj, const char *name); int sysfs_rename_link(struct kobject *kobj, struct kobject *target, const char *old_name, const char *new_name); +void sysfs_delete_link(struct kobject *dir, struct kobject *targ, + const char *name); + int __must_check sysfs_create_group(struct kobject *kobj, const struct attribute_group *grp); int sysfs_update_group(struct kobject *kobj, @@ -269,6 +272,11 @@ static inline int sysfs_rename_link(struct kobject *k, struct kobject *t, return 0; } +static inline void sysfs_delete_link(struct kobject *k, struct kobject *t, + const char *name) +{ +} + static inline int sysfs_create_group(struct kobject *kobj, const struct attribute_group *grp) { -- cgit v1.2.3 From be867b194a3ae3c680c29521287ae49b4d44d420 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 3 May 2010 16:23:15 -0500 Subject: sysfs: Comment sysfs directory tagging logic Add some in-line comments to explain the new infrastructure, which was introduced to support sysfs directory tagging with namespaces. I think an overall description someplace might be good too, but it didn't really seem to fit into Documentation/filesystems/sysfs.txt, which appears more geared toward users, rather than maintainers, of sysfs. (Tejun, please let me know if I can make anything clearer or failed altogether to comment something that should be commented.) Signed-off-by: Serge E. Hallyn Cc: Eric W. Biederman Cc: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 11 +++++++++++ include/linux/sysfs.h | 1 + 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index d9456f69904f..b60d2dfe4e69 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -136,12 +136,23 @@ struct kobj_attribute { extern const struct sysfs_ops kobj_sysfs_ops; +/* + * Namespace types which are used to tag kobjects and sysfs entries. + * Network namespace will likely be the first. + */ enum kobj_ns_type { KOBJ_NS_TYPE_NONE = 0, KOBJ_NS_TYPES }; struct sock; + +/* + * Callbacks so sysfs can determine namespaces + * @current_ns: return calling task's namespace + * @netlink_ns: return namespace to which a sock belongs (right?) + * @initial_ns: return the initial namespace (i.e. init_net_ns) + */ struct kobj_ns_type_operations { enum kobj_ns_type type; const void *(*current_ns)(void); diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 976c4664b216..47f1c95b5298 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -178,6 +178,7 @@ struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd); void sysfs_put(struct sysfs_dirent *sd); void sysfs_printk_last_file(void); +/* Called to clear a ns tag when it is no longer valid */ void sysfs_exit_ns(enum kobj_ns_type type, const void *tag); int __must_check sysfs_init(void); -- cgit v1.2.3 From 27eabc7cb4b357c68e4ce77d0b014f7a23add752 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 5 May 2010 14:54:00 -0700 Subject: sysfs: Don't use enums in inline function declaration. It appears gcc can't cope with using an enum that is only declared in an inline function declaration, that doesn't even use the variable that is so declared. Avoid the silliness and replace the enum with an int, and make gcc happy. Signed-off-by: Eric W. Biederman Acked-by: Randy Dunlap Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 47f1c95b5298..6903e9204032 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -328,7 +328,7 @@ static inline void sysfs_put(struct sysfs_dirent *sd) { } -static inline void sysfs_exit_ns(enum kobj_ns_type type, const void *tag) +static inline void sysfs_exit_ns(int type, const void *tag) { } -- cgit v1.2.3 From 2c3c8bea608866d8bd9dcf92657d57fdcac011c5 Mon Sep 17 00:00:00 2001 From: Chris Wright Date: Wed, 12 May 2010 18:28:57 -0700 Subject: sysfs: add struct file* to bin_attr callbacks This allows bin_attr->read,write,mmap callbacks to check file specific data (such as inode owner) as part of any privilege validation. Signed-off-by: Chris Wright Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 6903e9204032..f2694eb4dd3d 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -87,17 +87,18 @@ struct attribute_group { #define attr_name(_attr) (_attr).attr.name +struct file; struct vm_area_struct; struct bin_attribute { struct attribute attr; size_t size; void *private; - ssize_t (*read)(struct kobject *, struct bin_attribute *, + ssize_t (*read)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); - ssize_t (*write)(struct kobject *, struct bin_attribute *, + ssize_t (*write)(struct file *,struct kobject *, struct bin_attribute *, char *, loff_t, size_t); - int (*mmap)(struct kobject *, struct bin_attribute *attr, + int (*mmap)(struct file *, struct kobject *, struct bin_attribute *attr, struct vm_area_struct *vma); }; -- cgit v1.2.3 From 608b4b9548dedf4185ca47edcaae4bff2ceb62de Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 4 May 2010 17:36:45 -0700 Subject: netns: Teach network device kobjects which namespace they are in. The problem. Network devices show up in sysfs and with the network namespace active multiple devices with the same name can show up in the same directory, ouch! To avoid that problem and allow existing applications in network namespaces to see the same interface that is currently presented in sysfs, this patch enables the tagging directory support in sysfs. By using the network namespace pointers as tags to separate out the the sysfs directory entries we ensure that we don't have conflicts in the directories and applications only see a limited set of the network devices. Signed-off-by: Eric W. Biederman Acked-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index b60d2dfe4e69..cf343a852534 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -142,6 +142,7 @@ extern const struct sysfs_ops kobj_sysfs_ops; */ enum kobj_ns_type { KOBJ_NS_TYPE_NONE = 0, + KOBJ_NS_TYPE_NET, KOBJ_NS_TYPES }; -- cgit v1.2.3 From 910a7e905f36e51a17d6e8bb4ad6dcd5ac5f1d53 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 4 May 2010 17:36:46 -0700 Subject: netlink: Implment netlink_broadcast_filtered When netlink sockets are used to convey data that is in a namespace we need a way to select a subset of the listening sockets to deliver the packet to. For the network namespace we have been doing this by only transmitting packets in the correct network namespace. For data belonging to other namespaces netlink_bradcast_filtered provides a mechanism that allows us to examine the destination socket and to decide if we should transmit the specified packet to it. Signed-off-by: Eric W. Biederman Acked-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/netlink.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 6eaca5e1e8ca..59d066936ab9 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -188,6 +188,10 @@ extern int netlink_has_listeners(struct sock *sk, unsigned int group); extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid, __u32 group, gfp_t allocation); +extern int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, + __u32 pid, __u32 group, gfp_t allocation, + int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data), + void *filter_data); extern int netlink_set_err(struct sock *ssk, __u32 pid, __u32 group, int code); extern int netlink_register_notifier(struct notifier_block *nb); extern int netlink_unregister_notifier(struct notifier_block *nb); -- cgit v1.2.3