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 --- lib/kobject.c | 103 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 103 insertions(+) (limited to 'lib/kobject.c') diff --git a/lib/kobject.c b/lib/kobject.c index 8115eb1bbf4d..bbb2bb40ee1f 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -850,6 +850,109 @@ struct kset *kset_create_and_add(const char *name, } EXPORT_SYMBOL_GPL(kset_create_and_add); + +static DEFINE_SPINLOCK(kobj_ns_type_lock); +static const struct kobj_ns_type_operations *kobj_ns_ops_tbl[KOBJ_NS_TYPES]; + +int kobj_ns_type_register(const struct kobj_ns_type_operations *ops) +{ + enum kobj_ns_type type = ops->type; + int error; + + spin_lock(&kobj_ns_type_lock); + + error = -EINVAL; + if (type >= KOBJ_NS_TYPES) + goto out; + + error = -EINVAL; + if (type <= KOBJ_NS_TYPE_NONE) + goto out; + + error = -EBUSY; + if (kobj_ns_ops_tbl[type]) + goto out; + + error = 0; + kobj_ns_ops_tbl[type] = ops; + +out: + spin_unlock(&kobj_ns_type_lock); + return error; +} + +int kobj_ns_type_registered(enum kobj_ns_type type) +{ + int registered = 0; + + spin_lock(&kobj_ns_type_lock); + if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES)) + registered = kobj_ns_ops_tbl[type] != NULL; + spin_unlock(&kobj_ns_type_lock); + + return registered; +} + +const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent) +{ + const struct kobj_ns_type_operations *ops = NULL; + + if (parent && parent->ktype->child_ns_type) + ops = parent->ktype->child_ns_type(parent); + + return ops; +} + +const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj) +{ + return kobj_child_ns_ops(kobj->parent); +} + + +const void *kobj_ns_current(enum kobj_ns_type type) +{ + const void *ns = NULL; + + spin_lock(&kobj_ns_type_lock); + if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) && + kobj_ns_ops_tbl[type]) + ns = kobj_ns_ops_tbl[type]->current_ns(); + spin_unlock(&kobj_ns_type_lock); + + return ns; +} + +const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk) +{ + const void *ns = NULL; + + spin_lock(&kobj_ns_type_lock); + if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) && + kobj_ns_ops_tbl[type]) + ns = kobj_ns_ops_tbl[type]->netlink_ns(sk); + spin_unlock(&kobj_ns_type_lock); + + return ns; +} + +const void *kobj_ns_initial(enum kobj_ns_type type) +{ + const void *ns = NULL; + + spin_lock(&kobj_ns_type_lock); + if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) && + kobj_ns_ops_tbl[type]) + ns = kobj_ns_ops_tbl[type]->initial_ns(); + spin_unlock(&kobj_ns_type_lock); + + return ns; +} + +void kobj_ns_exit(enum kobj_ns_type type, const void *ns) +{ +} + + EXPORT_SYMBOL(kobject_get); EXPORT_SYMBOL(kobject_put); EXPORT_SYMBOL(kobject_del); -- 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 --- lib/kobject.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib/kobject.c') diff --git a/lib/kobject.c b/lib/kobject.c index bbb2bb40ee1f..b2c6d1f56e65 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -950,6 +950,7 @@ const void *kobj_ns_initial(enum kobj_ns_type type) void kobj_ns_exit(enum kobj_ns_type type, const void *ns) { + sysfs_exit_ns(type, ns); } -- 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 --- lib/kobject.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'lib/kobject.c') diff --git a/lib/kobject.c b/lib/kobject.c index b2c6d1f56e65..f07c57252e82 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -948,6 +948,17 @@ const void *kobj_ns_initial(enum kobj_ns_type type) return ns; } +/* + * kobj_ns_exit - invalidate a namespace tag + * + * @type: the namespace type (i.e. KOBJ_NS_TYPE_NET) + * @ns: the actual namespace being invalidated + * + * This is called when a tag is no longer valid. For instance, + * when a network namespace exits, it uses this helper to + * make sure no sb's sysfs_info points to the now-invalidated + * netns. + */ void kobj_ns_exit(enum kobj_ns_type type, const void *ns) { sysfs_exit_ns(type, ns); -- cgit v1.2.3