linux_dsm_epyc7002/include/linux/sysfs.h

511 lines
14 KiB
C
Raw Normal View History

/*
* sysfs.h - definitions for the device driver filesystem
*
* Copyright (c) 2001,2002 Patrick Mochel
* Copyright (c) 2004 Silicon Graphics, Inc.
* Copyright (c) 2007 SUSE Linux Products GmbH
* Copyright (c) 2007 Tejun Heo <teheo@suse.de>
*
* Please see Documentation/filesystems/sysfs.txt for more information.
*/
#ifndef _SYSFS_H_
#define _SYSFS_H_
#include <linux/kernfs.h>
#include <linux/compiler.h>
#include <linux/errno.h>
#include <linux/list.h>
#include <linux/lockdep.h>
#include <linux/kobject_ns.h>
#include <linux/stat.h>
#include <linux/atomic.h>
struct kobject;
struct module;
struct bin_attribute;
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 - call sysfs_register_ns_types with the type and it's operations - sysfs_exit_ns when an individual tag is no longer valid - Implement mount_ns() which returns the ns of the calling process so we can attach it to a sysfs superblock.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 <ebiederm@xmission.com> Signed-off-by: Benjamin Thery <benjamin.thery@bull.net> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-03-31 01:31:26 +07:00
enum kobj_ns_type;
struct attribute {
const char *name;
umode_t mode;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
2012-05-15 00:30:03 +07:00
bool ignore_lockdep:1;
struct lock_class_key *key;
struct lock_class_key skey;
#endif
};
/**
* sysfs_attr_init - initialize a dynamically allocated sysfs attribute
* @attr: struct attribute to initialize
*
* Initialize a dynamically allocated struct attribute so we can
* make lockdep happy. This is a new requirement for attributes
* and initially this is only needed when lockdep is enabled.
* Lockdep gives a nice error when your attribute is added to
* sysfs if you don't have this.
*/
#ifdef CONFIG_DEBUG_LOCK_ALLOC
#define sysfs_attr_init(attr) \
do { \
static struct lock_class_key __key; \
\
(attr)->key = &__key; \
} while (0)
#else
#define sysfs_attr_init(attr) do {} while (0)
#endif
/**
* struct attribute_group - data structure used to declare an attribute group.
* @name: Optional: Attribute group name
* If specified, the attribute group will be created in
* a new subdirectory with this name.
* @is_visible: Optional: Function to return permissions associated with an
* attribute of the group. Will be called repeatedly for each
* attribute in the group. Only read/write permissions as well as
* SYSFS_PREALLOC are accepted. Must return 0 if an attribute is
* not visible. The returned value will replace static permissions
* defined in struct attribute or struct bin_attribute.
* @attrs: Pointer to NULL terminated list of attributes.
* @bin_attrs: Pointer to NULL terminated list of binary attributes.
* Either attrs or bin_attrs or both must be provided.
*/
struct attribute_group {
const char *name;
umode_t (*is_visible)(struct kobject *,
struct attribute *, int);
struct attribute **attrs;
struct bin_attribute **bin_attrs;
};
/**
* Use these macros to make defining attributes easier. See include/linux/device.h
* for examples..
*/
sysfs/kernfs: allow attributes to request write buffer be pre-allocated. md/raid allows metadata management to be performed in user-space. A various times, particularly on device failure, the metadata needs to be updated before further writes can be permitted. This means that the user-space program which updates metadata much not block on writeout, and so must not allocate memory. mlockall(MCL_CURRENT|MCL_FUTURE) and pre-allocation can avoid all memory allocation issues for user-memory, but that does not help kernel memory. Several kernel objects can be pre-allocated. e.g. files opened before any writes to the array are permitted. However some kernel allocation happens in places that cannot be pre-allocated. In particular, writes to sysfs files (to tell md that it can now allow writes to the array) allocate a buffer using GFP_KERNEL. This patch allows attributes to be marked as "PREALLOC". In that case the maximal buffer is allocated when the file is opened, and then used on each write instead of allocating a new buffer. As the same buffer is now shared for all writes on the same file description, the mutex is extended to cover full use of the buffer including the copy_from_user(). The new __ATTR_PREALLOC() 'or's a new flag in to the 'mode', which is inspected by sysfs_add_file_mode_ns() to determine if the file should be marked as requiring prealloc. Despite the comment, we *do* use ->seq_show together with ->prealloc in this patch. The next patch fixes that. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-13 12:41:28 +07:00
#define SYSFS_PREALLOC 010000
#define __ATTR(_name, _mode, _show, _store) { \
.attr = {.name = __stringify(_name), \
.mode = VERIFY_OCTAL_PERMISSIONS(_mode) }, \
.show = _show, \
.store = _store, \
}
sysfs/kernfs: allow attributes to request write buffer be pre-allocated. md/raid allows metadata management to be performed in user-space. A various times, particularly on device failure, the metadata needs to be updated before further writes can be permitted. This means that the user-space program which updates metadata much not block on writeout, and so must not allocate memory. mlockall(MCL_CURRENT|MCL_FUTURE) and pre-allocation can avoid all memory allocation issues for user-memory, but that does not help kernel memory. Several kernel objects can be pre-allocated. e.g. files opened before any writes to the array are permitted. However some kernel allocation happens in places that cannot be pre-allocated. In particular, writes to sysfs files (to tell md that it can now allow writes to the array) allocate a buffer using GFP_KERNEL. This patch allows attributes to be marked as "PREALLOC". In that case the maximal buffer is allocated when the file is opened, and then used on each write instead of allocating a new buffer. As the same buffer is now shared for all writes on the same file description, the mutex is extended to cover full use of the buffer including the copy_from_user(). The new __ATTR_PREALLOC() 'or's a new flag in to the 'mode', which is inspected by sysfs_add_file_mode_ns() to determine if the file should be marked as requiring prealloc. Despite the comment, we *do* use ->seq_show together with ->prealloc in this patch. The next patch fixes that. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-13 12:41:28 +07:00
#define __ATTR_PREALLOC(_name, _mode, _show, _store) { \
.attr = {.name = __stringify(_name), \
.mode = SYSFS_PREALLOC | VERIFY_OCTAL_PERMISSIONS(_mode) },\
.show = _show, \
.store = _store, \
}
#define __ATTR_RO(_name) { \
.attr = { .name = __stringify(_name), .mode = S_IRUGO }, \
.show = _name##_show, \
}
#define __ATTR_WO(_name) { \
.attr = { .name = __stringify(_name), .mode = S_IWUSR }, \
.store = _name##_store, \
}
#define __ATTR_RW(_name) __ATTR(_name, (S_IWUSR | S_IRUGO), \
_name##_show, _name##_store)
#define __ATTR_NULL { .attr = { .name = NULL } }
2012-05-15 00:30:03 +07:00
#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 __ATTRIBUTE_GROUPS(_name) \
static const struct attribute_group *_name##_groups[] = { \
&_name##_group, \
NULL, \
}
#define ATTRIBUTE_GROUPS(_name) \
static const struct attribute_group _name##_group = { \
.attrs = _name##_attrs, \
}; \
__ATTRIBUTE_GROUPS(_name)
struct file;
struct vm_area_struct;
struct bin_attribute {
struct attribute attr;
size_t size;
void *private;
ssize_t (*read)(struct file *, struct kobject *, struct bin_attribute *,
sysfs: add parameter "struct bin_attribute *" in .read/.write methods for sysfs binary attributes Well, first of all, I don't want to change so many files either. What I do: Adding a new parameter "struct bin_attribute *" in the .read/.write methods for the sysfs binary attributes. In fact, only the four lines change in fs/sysfs/bin.c and include/linux/sysfs.h do the real work. But I have to update all the files that use binary attributes to make them compatible with the new .read and .write methods. I'm not sure if I missed any. :( Why I do this: For a sysfs attribute, we can get a pointer pointing to the struct attribute in the .show/.store method, while we can't do this for the binary attributes. I don't know why this is different, but this does make it not so handy to use the binary attributes as the regular ones. So I think this patch is reasonable. :) Who benefits from it: The patch that exposes ACPI tables in sysfs requires such an improvement. All the table binary attributes share the same .read method. Parameter "struct bin_attribute *" is used to get the table signature and instance number which are used to distinguish different ACPI table binary attributes. Without this parameter, we need to offer different .read methods for different ACPI table binary attributes. This is impossible as there are various ACPI tables on different platforms, and we don't know what they are until they are loaded. Signed-off-by: Zhang Rui <rui.zhang@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-06-09 12:57:22 +07:00
char *, loff_t, size_t);
ssize_t (*write)(struct file *, struct kobject *, struct bin_attribute *,
sysfs: add parameter "struct bin_attribute *" in .read/.write methods for sysfs binary attributes Well, first of all, I don't want to change so many files either. What I do: Adding a new parameter "struct bin_attribute *" in the .read/.write methods for the sysfs binary attributes. In fact, only the four lines change in fs/sysfs/bin.c and include/linux/sysfs.h do the real work. But I have to update all the files that use binary attributes to make them compatible with the new .read and .write methods. I'm not sure if I missed any. :( Why I do this: For a sysfs attribute, we can get a pointer pointing to the struct attribute in the .show/.store method, while we can't do this for the binary attributes. I don't know why this is different, but this does make it not so handy to use the binary attributes as the regular ones. So I think this patch is reasonable. :) Who benefits from it: The patch that exposes ACPI tables in sysfs requires such an improvement. All the table binary attributes share the same .read method. Parameter "struct bin_attribute *" is used to get the table signature and instance number which are used to distinguish different ACPI table binary attributes. Without this parameter, we need to offer different .read methods for different ACPI table binary attributes. This is impossible as there are various ACPI tables on different platforms, and we don't know what they are until they are loaded. Signed-off-by: Zhang Rui <rui.zhang@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2007-06-09 12:57:22 +07:00
char *, loff_t, size_t);
int (*mmap)(struct file *, struct kobject *, struct bin_attribute *attr,
struct vm_area_struct *vma);
};
/**
* sysfs_bin_attr_init - initialize a dynamically allocated bin_attribute
* @attr: struct bin_attribute to initialize
*
* Initialize a dynamically allocated struct bin_attribute so we
* can make lockdep happy. This is a new requirement for
* attributes and initially this is only needed when lockdep is
* enabled. Lockdep gives a nice error when your attribute is
* added to sysfs if you don't have this.
*/
#define sysfs_bin_attr_init(bin_attr) sysfs_attr_init(&(bin_attr)->attr)
/* macros to create static binary attributes easier */
#define __BIN_ATTR(_name, _mode, _read, _write, _size) { \
.attr = { .name = __stringify(_name), .mode = _mode }, \
.read = _read, \
.write = _write, \
.size = _size, \
}
#define __BIN_ATTR_RO(_name, _size) { \
.attr = { .name = __stringify(_name), .mode = S_IRUGO }, \
.read = _name##_read, \
.size = _size, \
}
#define __BIN_ATTR_RW(_name, _size) __BIN_ATTR(_name, \
(S_IWUSR | S_IRUGO), _name##_read, \
_name##_write, _size)
#define __BIN_ATTR_NULL __ATTR_NULL
#define BIN_ATTR(_name, _mode, _read, _write, _size) \
struct bin_attribute bin_attr_##_name = __BIN_ATTR(_name, _mode, _read, \
_write, _size)
#define BIN_ATTR_RO(_name, _size) \
struct bin_attribute bin_attr_##_name = __BIN_ATTR_RO(_name, _size)
#define BIN_ATTR_RW(_name, _size) \
struct bin_attribute bin_attr_##_name = __BIN_ATTR_RW(_name, _size)
struct sysfs_ops {
ssize_t (*show)(struct kobject *, struct attribute *, char *);
ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t);
};
#ifdef CONFIG_SYSFS
2013-09-12 09:29:05 +07:00
int __must_check sysfs_create_dir_ns(struct kobject *kobj, const void *ns);
void sysfs_remove_dir(struct kobject *kobj);
2013-09-12 09:29:05 +07:00
int __must_check sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
const void *new_ns);
int __must_check sysfs_move_dir_ns(struct kobject *kobj,
struct kobject *new_parent_kobj,
const void *new_ns);
int __must_check sysfs_create_mount_point(struct kobject *parent_kobj,
const char *name);
void sysfs_remove_mount_point(struct kobject *parent_kobj,
const char *name);
sysfs: make attr namespace interface less convoluted sysfs ns (namespace) implementation became more convoluted than necessary while trying to hide ns information from visible interface. The relatively recent attr ns support is a good example. * attr ns tag is determined by sysfs_ops->namespace() callback while dir tag is determined by kobj_type->namespace(). The placement is arbitrary. * Instead of performing operations with explicit ns tag, the namespace callback is routed through sysfs_attr_ns(), sysfs_ops->namespace(), class_attr_namespace(), class_attr->namespace(). It's not simpler in any sense. The only thing this convolution does is traversing the whole stack backwards. The namespace callbacks are unncessary because the operations involved are inherently synchronous. The information can be provided in in straight-forward top-down direction and reversing that direction is unnecessary and against basic design principles. This backward interface is unnecessarily convoluted and hinders properly separating out sysfs from driver model / kobject for proper layering. This patch updates attr ns support such that * sysfs_ops->namespace() and class_attr->namespace() are dropped. * sysfs_{create|remove}_file_ns(), which take explicit @ns param, are added and sysfs_{create|remove}_file() are now simple wrappers around the ns aware functions. * ns handling is dropped from sysfs_chmod_file(). Nobody uses it at this point. sysfs_chmod_file_ns() can be added later if necessary. * Explicit @ns is propagated through class_{create|remove}_file_ns() and netdev_class_{create|remove}_file_ns(). * driver/net/bonding which is currently the only user of attr namespace is updated to use netdev_class_{create|remove}_file_ns() with @bh->net as the ns tag instead of using the namespace callback. This patch should be an equivalent conversion without any functional difference. It makes the code easier to follow, reduces lines of code a bit and helps proper separation and layering. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Kay Sievers <kay@vrfy.org> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-09-12 09:29:04 +07:00
int __must_check sysfs_create_file_ns(struct kobject *kobj,
const struct attribute *attr,
const void *ns);
int __must_check sysfs_create_files(struct kobject *kobj,
const struct attribute **attr);
int __must_check sysfs_chmod_file(struct kobject *kobj,
const struct attribute *attr, umode_t mode);
sysfs: make attr namespace interface less convoluted sysfs ns (namespace) implementation became more convoluted than necessary while trying to hide ns information from visible interface. The relatively recent attr ns support is a good example. * attr ns tag is determined by sysfs_ops->namespace() callback while dir tag is determined by kobj_type->namespace(). The placement is arbitrary. * Instead of performing operations with explicit ns tag, the namespace callback is routed through sysfs_attr_ns(), sysfs_ops->namespace(), class_attr_namespace(), class_attr->namespace(). It's not simpler in any sense. The only thing this convolution does is traversing the whole stack backwards. The namespace callbacks are unncessary because the operations involved are inherently synchronous. The information can be provided in in straight-forward top-down direction and reversing that direction is unnecessary and against basic design principles. This backward interface is unnecessarily convoluted and hinders properly separating out sysfs from driver model / kobject for proper layering. This patch updates attr ns support such that * sysfs_ops->namespace() and class_attr->namespace() are dropped. * sysfs_{create|remove}_file_ns(), which take explicit @ns param, are added and sysfs_{create|remove}_file() are now simple wrappers around the ns aware functions. * ns handling is dropped from sysfs_chmod_file(). Nobody uses it at this point. sysfs_chmod_file_ns() can be added later if necessary. * Explicit @ns is propagated through class_{create|remove}_file_ns() and netdev_class_{create|remove}_file_ns(). * driver/net/bonding which is currently the only user of attr namespace is updated to use netdev_class_{create|remove}_file_ns() with @bh->net as the ns tag instead of using the namespace callback. This patch should be an equivalent conversion without any functional difference. It makes the code easier to follow, reduces lines of code a bit and helps proper separation and layering. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Kay Sievers <kay@vrfy.org> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-09-12 09:29:04 +07:00
void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
const void *ns);
kernfs, sysfs, driver-core: implement kernfs_remove_self() and its wrappers Sometimes it's necessary to implement a node which wants to delete nodes including itself. This isn't straightforward because of kernfs active reference. While a file operation is in progress, an active reference is held and kernfs_remove() waits for all such references to drain before completing. For a self-deleting node, this is a deadlock as kernfs_remove() ends up waiting for an active reference that itself is sitting on top of. This currently is worked around in the sysfs layer using sysfs_schedule_callback() which makes such removals asynchronous. While it works, it's rather cumbersome and inherently breaks synchronicity of the operation - the file operation which triggered the operation may complete before the removal is finished (or even started) and the removal may fail asynchronously. If a removal operation is immmediately followed by another operation which expects the specific name to be available (e.g. removal followed by rename onto the same name), there's no way to make the latter operation reliable. The thing is there's no inherent reason for this to be asynchrnous. All that's necessary to do this synchronous is a dedicated operation which drops its own active ref and deactivates self. This patch implements kernfs_remove_self() and its wrappers in sysfs and driver core. kernfs_remove_self() is to be called from one of the file operations, drops the active ref the task is holding, removes the self node, and restores active ref to the dead node so that the ref is balanced afterwards. __kernfs_remove() is updated so that it takes an early exit if the target node is already fully removed so that the active ref restored by kernfs_remove_self() after removal doesn't confuse the deactivation path. This makes implementing self-deleting nodes very easy. The normal removal path doesn't even need to be changed to use kernfs_remove_self() for the self-deleting node. The method can invoke kernfs_remove_self() on itself before proceeding the normal removal path. kernfs_remove() invoked on the node by the normal deletion path will simply be ignored. This will replace sysfs_schedule_callback(). A subtle feature of sysfs_schedule_callback() is that it collapses multiple invocations - even if multiple removals are triggered, the removal callback is run only once. An equivalent effect can be achieved by testing the return value of kernfs_remove_self() - only the one which gets %true return value should proceed with actual deletion. All other instances of kernfs_remove_self() will wait till the enclosing kernfs operation which invoked the winning instance of kernfs_remove_self() finishes and then return %false. This trivially makes all users of kernfs_remove_self() automatically show correct synchronous behavior even when there are multiple concurrent operations - all "echo 1 > delete" instances will finish only after the whole operation is completed by one of the instances. Note that manipulation of active ref is implemented in separate public functions - kernfs_[un]break_active_protection(). kernfs_remove_self() is the only user at the moment but this will be used to cater to more complex cases. v2: For !CONFIG_SYSFS, dummy version kernfs_remove_self() was missing and sysfs_remove_file_self() had incorrect return type. Fix it. Reported by kbuild test bot. v3: kernfs_[un]break_active_protection() separated out from kernfs_remove_self() and exposed as public API. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: kbuild test robot <fengguang.wu@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-02-04 02:03:01 +07:00
bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr);
void sysfs_remove_files(struct kobject *kobj, const struct attribute **attr);
int __must_check sysfs_create_bin_file(struct kobject *kobj,
const struct bin_attribute *attr);
void sysfs_remove_bin_file(struct kobject *kobj,
const struct bin_attribute *attr);
int __must_check sysfs_create_link(struct kobject *kobj, struct kobject *target,
const char *name);
int __must_check sysfs_create_link_nowarn(struct kobject *kobj,
struct kobject *target,
const char *name);
void sysfs_remove_link(struct kobject *kobj, const char *name);
int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *target,
const char *old_name, const char *new_name,
const void *new_ns);
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 __must_check sysfs_create_groups(struct kobject *kobj,
const struct attribute_group **groups);
int sysfs_update_group(struct kobject *kobj,
const struct attribute_group *grp);
void sysfs_remove_group(struct kobject *kobj,
const struct attribute_group *grp);
void sysfs_remove_groups(struct kobject *kobj,
const struct attribute_group **groups);
int sysfs_add_file_to_group(struct kobject *kobj,
const struct attribute *attr, const char *group);
void sysfs_remove_file_from_group(struct kobject *kobj,
const struct attribute *attr, const char *group);
int sysfs_merge_group(struct kobject *kobj,
const struct attribute_group *grp);
void sysfs_unmerge_group(struct kobject *kobj,
const struct attribute_group *grp);
int sysfs_add_link_to_group(struct kobject *kobj, const char *group_name,
struct kobject *target, const char *link_name);
void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name,
const char *link_name);
void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr);
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 <ebiederm@xmission.com> Signed-off-by: Benjamin Thery <benjamin.thery@bull.net> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-03-31 01:31:26 +07:00
int __must_check sysfs_init(void);
static inline void sysfs_enable_ns(struct kernfs_node *kn)
{
return kernfs_enable_ns(kn);
}
#else /* CONFIG_SYSFS */
2013-09-12 09:29:05 +07:00
static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
{
return 0;
}
static inline void sysfs_remove_dir(struct kobject *kobj)
{
}
2013-09-12 09:29:05 +07:00
static inline int sysfs_rename_dir_ns(struct kobject *kobj,
const char *new_name, const void *new_ns)
{
return 0;
}
2013-09-12 09:29:05 +07:00
static inline int sysfs_move_dir_ns(struct kobject *kobj,
struct kobject *new_parent_kobj,
const void *new_ns)
{
return 0;
}
static inline int sysfs_create_mount_point(struct kobject *parent_kobj,
const char *name)
{
return 0;
}
static inline void sysfs_remove_mount_point(struct kobject *parent_kobj,
const char *name)
{
}
sysfs: make attr namespace interface less convoluted sysfs ns (namespace) implementation became more convoluted than necessary while trying to hide ns information from visible interface. The relatively recent attr ns support is a good example. * attr ns tag is determined by sysfs_ops->namespace() callback while dir tag is determined by kobj_type->namespace(). The placement is arbitrary. * Instead of performing operations with explicit ns tag, the namespace callback is routed through sysfs_attr_ns(), sysfs_ops->namespace(), class_attr_namespace(), class_attr->namespace(). It's not simpler in any sense. The only thing this convolution does is traversing the whole stack backwards. The namespace callbacks are unncessary because the operations involved are inherently synchronous. The information can be provided in in straight-forward top-down direction and reversing that direction is unnecessary and against basic design principles. This backward interface is unnecessarily convoluted and hinders properly separating out sysfs from driver model / kobject for proper layering. This patch updates attr ns support such that * sysfs_ops->namespace() and class_attr->namespace() are dropped. * sysfs_{create|remove}_file_ns(), which take explicit @ns param, are added and sysfs_{create|remove}_file() are now simple wrappers around the ns aware functions. * ns handling is dropped from sysfs_chmod_file(). Nobody uses it at this point. sysfs_chmod_file_ns() can be added later if necessary. * Explicit @ns is propagated through class_{create|remove}_file_ns() and netdev_class_{create|remove}_file_ns(). * driver/net/bonding which is currently the only user of attr namespace is updated to use netdev_class_{create|remove}_file_ns() with @bh->net as the ns tag instead of using the namespace callback. This patch should be an equivalent conversion without any functional difference. It makes the code easier to follow, reduces lines of code a bit and helps proper separation and layering. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Kay Sievers <kay@vrfy.org> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-09-12 09:29:04 +07:00
static inline int sysfs_create_file_ns(struct kobject *kobj,
const struct attribute *attr,
const void *ns)
{
return 0;
}
static inline int sysfs_create_files(struct kobject *kobj,
const struct attribute **attr)
{
return 0;
}
static inline int sysfs_chmod_file(struct kobject *kobj,
const struct attribute *attr, umode_t mode)
{
return 0;
}
sysfs: make attr namespace interface less convoluted sysfs ns (namespace) implementation became more convoluted than necessary while trying to hide ns information from visible interface. The relatively recent attr ns support is a good example. * attr ns tag is determined by sysfs_ops->namespace() callback while dir tag is determined by kobj_type->namespace(). The placement is arbitrary. * Instead of performing operations with explicit ns tag, the namespace callback is routed through sysfs_attr_ns(), sysfs_ops->namespace(), class_attr_namespace(), class_attr->namespace(). It's not simpler in any sense. The only thing this convolution does is traversing the whole stack backwards. The namespace callbacks are unncessary because the operations involved are inherently synchronous. The information can be provided in in straight-forward top-down direction and reversing that direction is unnecessary and against basic design principles. This backward interface is unnecessarily convoluted and hinders properly separating out sysfs from driver model / kobject for proper layering. This patch updates attr ns support such that * sysfs_ops->namespace() and class_attr->namespace() are dropped. * sysfs_{create|remove}_file_ns(), which take explicit @ns param, are added and sysfs_{create|remove}_file() are now simple wrappers around the ns aware functions. * ns handling is dropped from sysfs_chmod_file(). Nobody uses it at this point. sysfs_chmod_file_ns() can be added later if necessary. * Explicit @ns is propagated through class_{create|remove}_file_ns() and netdev_class_{create|remove}_file_ns(). * driver/net/bonding which is currently the only user of attr namespace is updated to use netdev_class_{create|remove}_file_ns() with @bh->net as the ns tag instead of using the namespace callback. This patch should be an equivalent conversion without any functional difference. It makes the code easier to follow, reduces lines of code a bit and helps proper separation and layering. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Kay Sievers <kay@vrfy.org> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-09-12 09:29:04 +07:00
static inline void sysfs_remove_file_ns(struct kobject *kobj,
const struct attribute *attr,
const void *ns)
{
}
kernfs, sysfs, driver-core: implement kernfs_remove_self() and its wrappers Sometimes it's necessary to implement a node which wants to delete nodes including itself. This isn't straightforward because of kernfs active reference. While a file operation is in progress, an active reference is held and kernfs_remove() waits for all such references to drain before completing. For a self-deleting node, this is a deadlock as kernfs_remove() ends up waiting for an active reference that itself is sitting on top of. This currently is worked around in the sysfs layer using sysfs_schedule_callback() which makes such removals asynchronous. While it works, it's rather cumbersome and inherently breaks synchronicity of the operation - the file operation which triggered the operation may complete before the removal is finished (or even started) and the removal may fail asynchronously. If a removal operation is immmediately followed by another operation which expects the specific name to be available (e.g. removal followed by rename onto the same name), there's no way to make the latter operation reliable. The thing is there's no inherent reason for this to be asynchrnous. All that's necessary to do this synchronous is a dedicated operation which drops its own active ref and deactivates self. This patch implements kernfs_remove_self() and its wrappers in sysfs and driver core. kernfs_remove_self() is to be called from one of the file operations, drops the active ref the task is holding, removes the self node, and restores active ref to the dead node so that the ref is balanced afterwards. __kernfs_remove() is updated so that it takes an early exit if the target node is already fully removed so that the active ref restored by kernfs_remove_self() after removal doesn't confuse the deactivation path. This makes implementing self-deleting nodes very easy. The normal removal path doesn't even need to be changed to use kernfs_remove_self() for the self-deleting node. The method can invoke kernfs_remove_self() on itself before proceeding the normal removal path. kernfs_remove() invoked on the node by the normal deletion path will simply be ignored. This will replace sysfs_schedule_callback(). A subtle feature of sysfs_schedule_callback() is that it collapses multiple invocations - even if multiple removals are triggered, the removal callback is run only once. An equivalent effect can be achieved by testing the return value of kernfs_remove_self() - only the one which gets %true return value should proceed with actual deletion. All other instances of kernfs_remove_self() will wait till the enclosing kernfs operation which invoked the winning instance of kernfs_remove_self() finishes and then return %false. This trivially makes all users of kernfs_remove_self() automatically show correct synchronous behavior even when there are multiple concurrent operations - all "echo 1 > delete" instances will finish only after the whole operation is completed by one of the instances. Note that manipulation of active ref is implemented in separate public functions - kernfs_[un]break_active_protection(). kernfs_remove_self() is the only user at the moment but this will be used to cater to more complex cases. v2: For !CONFIG_SYSFS, dummy version kernfs_remove_self() was missing and sysfs_remove_file_self() had incorrect return type. Fix it. Reported by kbuild test bot. v3: kernfs_[un]break_active_protection() separated out from kernfs_remove_self() and exposed as public API. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: kbuild test robot <fengguang.wu@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-02-04 02:03:01 +07:00
static inline bool sysfs_remove_file_self(struct kobject *kobj,
const struct attribute *attr)
{
return false;
}
static inline void sysfs_remove_files(struct kobject *kobj,
const struct attribute **attr)
{
}
static inline int sysfs_create_bin_file(struct kobject *kobj,
const struct bin_attribute *attr)
{
return 0;
}
static inline void sysfs_remove_bin_file(struct kobject *kobj,
const struct bin_attribute *attr)
{
}
static inline int sysfs_create_link(struct kobject *kobj,
struct kobject *target, const char *name)
{
return 0;
}
static inline int sysfs_create_link_nowarn(struct kobject *kobj,
struct kobject *target,
const char *name)
{
return 0;
}
static inline void sysfs_remove_link(struct kobject *kobj, const char *name)
{
}
static inline int sysfs_rename_link_ns(struct kobject *k, struct kobject *t,
const char *old_name,
const char *new_name, const void *ns)
{
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)
{
return 0;
}
static inline int sysfs_create_groups(struct kobject *kobj,
const struct attribute_group **groups)
{
return 0;
}
static inline int sysfs_update_group(struct kobject *kobj,
const struct attribute_group *grp)
{
return 0;
}
static inline void sysfs_remove_group(struct kobject *kobj,
const struct attribute_group *grp)
{
}
static inline void sysfs_remove_groups(struct kobject *kobj,
const struct attribute_group **groups)
{
}
static inline int sysfs_add_file_to_group(struct kobject *kobj,
const struct attribute *attr, const char *group)
{
return 0;
}
static inline void sysfs_remove_file_from_group(struct kobject *kobj,
const struct attribute *attr, const char *group)
{
}
static inline int sysfs_merge_group(struct kobject *kobj,
const struct attribute_group *grp)
{
return 0;
}
static inline void sysfs_unmerge_group(struct kobject *kobj,
const struct attribute_group *grp)
{
}
static inline int sysfs_add_link_to_group(struct kobject *kobj,
const char *group_name, struct kobject *target,
const char *link_name)
{
return 0;
}
static inline void sysfs_remove_link_from_group(struct kobject *kobj,
const char *group_name, const char *link_name)
{
}
static inline void sysfs_notify(struct kobject *kobj, const char *dir,
const char *attr)
{
}
static inline int __must_check sysfs_init(void)
{
return 0;
}
static inline void sysfs_enable_ns(struct kernfs_node *kn)
{
}
#endif /* CONFIG_SYSFS */
sysfs: make attr namespace interface less convoluted sysfs ns (namespace) implementation became more convoluted than necessary while trying to hide ns information from visible interface. The relatively recent attr ns support is a good example. * attr ns tag is determined by sysfs_ops->namespace() callback while dir tag is determined by kobj_type->namespace(). The placement is arbitrary. * Instead of performing operations with explicit ns tag, the namespace callback is routed through sysfs_attr_ns(), sysfs_ops->namespace(), class_attr_namespace(), class_attr->namespace(). It's not simpler in any sense. The only thing this convolution does is traversing the whole stack backwards. The namespace callbacks are unncessary because the operations involved are inherently synchronous. The information can be provided in in straight-forward top-down direction and reversing that direction is unnecessary and against basic design principles. This backward interface is unnecessarily convoluted and hinders properly separating out sysfs from driver model / kobject for proper layering. This patch updates attr ns support such that * sysfs_ops->namespace() and class_attr->namespace() are dropped. * sysfs_{create|remove}_file_ns(), which take explicit @ns param, are added and sysfs_{create|remove}_file() are now simple wrappers around the ns aware functions. * ns handling is dropped from sysfs_chmod_file(). Nobody uses it at this point. sysfs_chmod_file_ns() can be added later if necessary. * Explicit @ns is propagated through class_{create|remove}_file_ns() and netdev_class_{create|remove}_file_ns(). * driver/net/bonding which is currently the only user of attr namespace is updated to use netdev_class_{create|remove}_file_ns() with @bh->net as the ns tag instead of using the namespace callback. This patch should be an equivalent conversion without any functional difference. It makes the code easier to follow, reduces lines of code a bit and helps proper separation and layering. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Kay Sievers <kay@vrfy.org> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-09-12 09:29:04 +07:00
static inline int __must_check sysfs_create_file(struct kobject *kobj,
const struct attribute *attr)
{
return sysfs_create_file_ns(kobj, attr, NULL);
}
static inline void sysfs_remove_file(struct kobject *kobj,
const struct attribute *attr)
{
sysfs_remove_file_ns(kobj, attr, NULL);
sysfs: make attr namespace interface less convoluted sysfs ns (namespace) implementation became more convoluted than necessary while trying to hide ns information from visible interface. The relatively recent attr ns support is a good example. * attr ns tag is determined by sysfs_ops->namespace() callback while dir tag is determined by kobj_type->namespace(). The placement is arbitrary. * Instead of performing operations with explicit ns tag, the namespace callback is routed through sysfs_attr_ns(), sysfs_ops->namespace(), class_attr_namespace(), class_attr->namespace(). It's not simpler in any sense. The only thing this convolution does is traversing the whole stack backwards. The namespace callbacks are unncessary because the operations involved are inherently synchronous. The information can be provided in in straight-forward top-down direction and reversing that direction is unnecessary and against basic design principles. This backward interface is unnecessarily convoluted and hinders properly separating out sysfs from driver model / kobject for proper layering. This patch updates attr ns support such that * sysfs_ops->namespace() and class_attr->namespace() are dropped. * sysfs_{create|remove}_file_ns(), which take explicit @ns param, are added and sysfs_{create|remove}_file() are now simple wrappers around the ns aware functions. * ns handling is dropped from sysfs_chmod_file(). Nobody uses it at this point. sysfs_chmod_file_ns() can be added later if necessary. * Explicit @ns is propagated through class_{create|remove}_file_ns() and netdev_class_{create|remove}_file_ns(). * driver/net/bonding which is currently the only user of attr namespace is updated to use netdev_class_{create|remove}_file_ns() with @bh->net as the ns tag instead of using the namespace callback. This patch should be an equivalent conversion without any functional difference. It makes the code easier to follow, reduces lines of code a bit and helps proper separation and layering. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Kay Sievers <kay@vrfy.org> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-09-12 09:29:04 +07:00
}
static inline int sysfs_rename_link(struct kobject *kobj, struct kobject *target,
const char *old_name, const char *new_name)
{
return sysfs_rename_link_ns(kobj, target, old_name, new_name, NULL);
}
static inline void sysfs_notify_dirent(struct kernfs_node *kn)
{
kernfs_notify(kn);
}
static inline struct kernfs_node *sysfs_get_dirent(struct kernfs_node *parent,
const unsigned char *name)
{
return kernfs_find_and_get(parent, name);
}
static inline struct kernfs_node *sysfs_get(struct kernfs_node *kn)
{
kernfs_get(kn);
return kn;
}
static inline void sysfs_put(struct kernfs_node *kn)
{
kernfs_put(kn);
}
#endif /* _SYSFS_H_ */