linux/fs/sysfs/file.c
NeilBrown 2b75869bba 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>
2014-11-07 10:53:25 -08:00

474 lines
11 KiB
C

/*
* fs/sysfs/file.c - sysfs regular (text) file implementation
*
* Copyright (c) 2001-3 Patrick Mochel
* Copyright (c) 2007 SUSE Linux Products GmbH
* Copyright (c) 2007 Tejun Heo <teheo@suse.de>
*
* This file is released under the GPLv2.
*
* Please see Documentation/filesystems/sysfs.txt for more information.
*/
#include <linux/module.h>
#include <linux/kobject.h>
#include <linux/kallsyms.h>
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/seq_file.h>
#include "sysfs.h"
#include "../kernfs/kernfs-internal.h"
/*
* Determine ktype->sysfs_ops for the given kernfs_node. This function
* must be called while holding an active reference.
*/
static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn)
{
struct kobject *kobj = kn->parent->priv;
if (kn->flags & KERNFS_LOCKDEP)
lockdep_assert_held(kn);
return kobj->ktype ? kobj->ktype->sysfs_ops : NULL;
}
/*
* Reads on sysfs are handled through seq_file, which takes care of hairy
* details like buffering and seeking. The following function pipes
* sysfs_ops->show() result through seq_file.
*/
static int sysfs_kf_seq_show(struct seq_file *sf, void *v)
{
struct kernfs_open_file *of = sf->private;
struct kobject *kobj = of->kn->parent->priv;
const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
ssize_t count;
char *buf;
/* acquire buffer and ensure that it's >= PAGE_SIZE and clear */
count = seq_get_buf(sf, &buf);
if (count < PAGE_SIZE) {
seq_commit(sf, -1);
return 0;
}
memset(buf, 0, PAGE_SIZE);
/*
* Invoke show(). Control may reach here via seq file lseek even
* if @ops->show() isn't implemented.
*/
if (ops->show) {
count = ops->show(kobj, of->kn->priv, buf);
if (count < 0)
return count;
}
/*
* The code works fine with PAGE_SIZE return but it's likely to
* indicate truncated result or overflow in normal use cases.
*/
if (count >= (ssize_t)PAGE_SIZE) {
print_symbol("fill_read_buffer: %s returned bad count\n",
(unsigned long)ops->show);
/* Try to struggle along */
count = PAGE_SIZE - 1;
}
seq_commit(sf, count);
return 0;
}
static ssize_t sysfs_kf_bin_read(struct kernfs_open_file *of, char *buf,
size_t count, loff_t pos)
{
struct bin_attribute *battr = of->kn->priv;
struct kobject *kobj = of->kn->parent->priv;
loff_t size = file_inode(of->file)->i_size;
if (!count)
return 0;
if (size) {
if (pos > size)
return 0;
if (pos + count > size)
count = size - pos;
}
if (!battr->read)
return -EIO;
return battr->read(of->file, kobj, battr, buf, pos, count);
}
/* kernfs write callback for regular sysfs files */
static ssize_t sysfs_kf_write(struct kernfs_open_file *of, char *buf,
size_t count, loff_t pos)
{
const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
struct kobject *kobj = of->kn->parent->priv;
if (!count)
return 0;
return ops->store(kobj, of->kn->priv, buf, count);
}
/* kernfs write callback for bin sysfs files */
static ssize_t sysfs_kf_bin_write(struct kernfs_open_file *of, char *buf,
size_t count, loff_t pos)
{
struct bin_attribute *battr = of->kn->priv;
struct kobject *kobj = of->kn->parent->priv;
loff_t size = file_inode(of->file)->i_size;
if (size) {
if (size <= pos)
return -EFBIG;
count = min_t(ssize_t, count, size - pos);
}
if (!count)
return 0;
if (!battr->write)
return -EIO;
return battr->write(of->file, kobj, battr, buf, pos, count);
}
static int sysfs_kf_bin_mmap(struct kernfs_open_file *of,
struct vm_area_struct *vma)
{
struct bin_attribute *battr = of->kn->priv;
struct kobject *kobj = of->kn->parent->priv;
return battr->mmap(of->file, kobj, battr, vma);
}
void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr)
{
struct kernfs_node *kn = kobj->sd, *tmp;
if (kn && dir)
kn = kernfs_find_and_get(kn, dir);
else
kernfs_get(kn);
if (kn && attr) {
tmp = kernfs_find_and_get(kn, attr);
kernfs_put(kn);
kn = tmp;
}
if (kn) {
kernfs_notify(kn);
kernfs_put(kn);
}
}
EXPORT_SYMBOL_GPL(sysfs_notify);
static const struct kernfs_ops sysfs_file_kfops_empty = {
};
static const struct kernfs_ops sysfs_file_kfops_ro = {
.seq_show = sysfs_kf_seq_show,
};
static const struct kernfs_ops sysfs_file_kfops_wo = {
.write = sysfs_kf_write,
};
static const struct kernfs_ops sysfs_file_kfops_rw = {
.seq_show = sysfs_kf_seq_show,
.write = sysfs_kf_write,
};
static const struct kernfs_ops sysfs_prealloc_kfops_wo = {
.write = sysfs_kf_write,
.prealloc = true,
};
static const struct kernfs_ops sysfs_prealloc_kfops_rw = {
.seq_show = sysfs_kf_seq_show,
.write = sysfs_kf_write,
.prealloc = true,
};
static const struct kernfs_ops sysfs_bin_kfops_ro = {
.read = sysfs_kf_bin_read,
};
static const struct kernfs_ops sysfs_bin_kfops_wo = {
.write = sysfs_kf_bin_write,
};
static const struct kernfs_ops sysfs_bin_kfops_rw = {
.read = sysfs_kf_bin_read,
.write = sysfs_kf_bin_write,
};
static const struct kernfs_ops sysfs_bin_kfops_mmap = {
.read = sysfs_kf_bin_read,
.write = sysfs_kf_bin_write,
.mmap = sysfs_kf_bin_mmap,
};
int sysfs_add_file_mode_ns(struct kernfs_node *parent,
const struct attribute *attr, bool is_bin,
umode_t mode, const void *ns)
{
struct lock_class_key *key = NULL;
const struct kernfs_ops *ops;
struct kernfs_node *kn;
loff_t size;
if (!is_bin) {
struct kobject *kobj = parent->priv;
const struct sysfs_ops *sysfs_ops = kobj->ktype->sysfs_ops;
/* every kobject with an attribute needs a ktype assigned */
if (WARN(!sysfs_ops, KERN_ERR
"missing sysfs attribute operations for kobject: %s\n",
kobject_name(kobj)))
return -EINVAL;
if (sysfs_ops->show && sysfs_ops->store) {
if (mode & SYSFS_PREALLOC)
ops = &sysfs_prealloc_kfops_rw;
else
ops = &sysfs_file_kfops_rw;
} else if (sysfs_ops->show)
ops = &sysfs_file_kfops_ro;
else if (sysfs_ops->store) {
if (mode & SYSFS_PREALLOC)
ops = &sysfs_prealloc_kfops_wo;
else
ops = &sysfs_file_kfops_wo;
} else
ops = &sysfs_file_kfops_empty;
size = PAGE_SIZE;
} else {
struct bin_attribute *battr = (void *)attr;
if (battr->mmap)
ops = &sysfs_bin_kfops_mmap;
else if (battr->read && battr->write)
ops = &sysfs_bin_kfops_rw;
else if (battr->read)
ops = &sysfs_bin_kfops_ro;
else if (battr->write)
ops = &sysfs_bin_kfops_wo;
else
ops = &sysfs_file_kfops_empty;
size = battr->size;
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
if (!attr->ignore_lockdep)
key = attr->key ?: (struct lock_class_key *)&attr->skey;
#endif
kn = __kernfs_create_file(parent, attr->name, mode & 0777, size, ops,
(void *)attr, ns, true, key);
if (IS_ERR(kn)) {
if (PTR_ERR(kn) == -EEXIST)
sysfs_warn_dup(parent, attr->name);
return PTR_ERR(kn);
}
return 0;
}
int sysfs_add_file(struct kernfs_node *parent, const struct attribute *attr,
bool is_bin)
{
return sysfs_add_file_mode_ns(parent, attr, is_bin, attr->mode, NULL);
}
/**
* sysfs_create_file_ns - create an attribute file for an object with custom ns
* @kobj: object we're creating for
* @attr: attribute descriptor
* @ns: namespace the new file should belong to
*/
int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr,
const void *ns)
{
BUG_ON(!kobj || !kobj->sd || !attr);
return sysfs_add_file_mode_ns(kobj->sd, attr, false, attr->mode, ns);
}
EXPORT_SYMBOL_GPL(sysfs_create_file_ns);
int sysfs_create_files(struct kobject *kobj, const struct attribute **ptr)
{
int err = 0;
int i;
for (i = 0; ptr[i] && !err; i++)
err = sysfs_create_file(kobj, ptr[i]);
if (err)
while (--i >= 0)
sysfs_remove_file(kobj, ptr[i]);
return err;
}
EXPORT_SYMBOL_GPL(sysfs_create_files);
/**
* sysfs_add_file_to_group - add an attribute file to a pre-existing group.
* @kobj: object we're acting for.
* @attr: attribute descriptor.
* @group: group name.
*/
int sysfs_add_file_to_group(struct kobject *kobj,
const struct attribute *attr, const char *group)
{
struct kernfs_node *parent;
int error;
if (group) {
parent = kernfs_find_and_get(kobj->sd, group);
} else {
parent = kobj->sd;
kernfs_get(parent);
}
if (!parent)
return -ENOENT;
error = sysfs_add_file(parent, attr, false);
kernfs_put(parent);
return error;
}
EXPORT_SYMBOL_GPL(sysfs_add_file_to_group);
/**
* sysfs_chmod_file - update the modified mode value on an object attribute.
* @kobj: object we're acting for.
* @attr: attribute descriptor.
* @mode: file permissions.
*
*/
int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr,
umode_t mode)
{
struct kernfs_node *kn;
struct iattr newattrs;
int rc;
kn = kernfs_find_and_get(kobj->sd, attr->name);
if (!kn)
return -ENOENT;
newattrs.ia_mode = (mode & S_IALLUGO) | (kn->mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE;
rc = kernfs_setattr(kn, &newattrs);
kernfs_put(kn);
return rc;
}
EXPORT_SYMBOL_GPL(sysfs_chmod_file);
/**
* sysfs_remove_file_ns - remove an object attribute with a custom ns tag
* @kobj: object we're acting for
* @attr: attribute descriptor
* @ns: namespace tag of the file to remove
*
* Hash the attribute name and namespace tag and kill the victim.
*/
void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
const void *ns)
{
struct kernfs_node *parent = kobj->sd;
kernfs_remove_by_name_ns(parent, attr->name, ns);
}
EXPORT_SYMBOL_GPL(sysfs_remove_file_ns);
/**
* sysfs_remove_file_self - remove an object attribute from its own method
* @kobj: object we're acting for
* @attr: attribute descriptor
*
* See kernfs_remove_self() for details.
*/
bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr)
{
struct kernfs_node *parent = kobj->sd;
struct kernfs_node *kn;
bool ret;
kn = kernfs_find_and_get(parent, attr->name);
if (WARN_ON_ONCE(!kn))
return false;
ret = kernfs_remove_self(kn);
kernfs_put(kn);
return ret;
}
void sysfs_remove_files(struct kobject *kobj, const struct attribute **ptr)
{
int i;
for (i = 0; ptr[i]; i++)
sysfs_remove_file(kobj, ptr[i]);
}
EXPORT_SYMBOL_GPL(sysfs_remove_files);
/**
* sysfs_remove_file_from_group - remove an attribute file from a group.
* @kobj: object we're acting for.
* @attr: attribute descriptor.
* @group: group name.
*/
void sysfs_remove_file_from_group(struct kobject *kobj,
const struct attribute *attr, const char *group)
{
struct kernfs_node *parent;
if (group) {
parent = kernfs_find_and_get(kobj->sd, group);
} else {
parent = kobj->sd;
kernfs_get(parent);
}
if (parent) {
kernfs_remove_by_name(parent, attr->name);
kernfs_put(parent);
}
}
EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group);
/**
* sysfs_create_bin_file - create binary file for object.
* @kobj: object.
* @attr: attribute descriptor.
*/
int sysfs_create_bin_file(struct kobject *kobj,
const struct bin_attribute *attr)
{
BUG_ON(!kobj || !kobj->sd || !attr);
return sysfs_add_file(kobj->sd, &attr->attr, true);
}
EXPORT_SYMBOL_GPL(sysfs_create_bin_file);
/**
* sysfs_remove_bin_file - remove binary file for object.
* @kobj: object.
* @attr: attribute descriptor.
*/
void sysfs_remove_bin_file(struct kobject *kobj,
const struct bin_attribute *attr)
{
kernfs_remove_by_name(kobj->sd, attr->attr.name);
}
EXPORT_SYMBOL_GPL(sysfs_remove_bin_file);