linux_dsm_epyc7002/fs/sysfs/inode.c

332 lines
7.8 KiB
C
Raw Normal View History

/*
* fs/sysfs/inode.c - basic sysfs inode and dentry operations
*
* 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.
*/
#undef DEBUG
#include <linux/pagemap.h>
#include <linux/namei.h>
#include <linux/backing-dev.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/sched.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/sysfs.h>
#include <linux/xattr.h>
#include <linux/security.h>
#include "sysfs.h"
static const struct address_space_operations sysfs_aops = {
.readpage = simple_readpage,
.write_begin = simple_write_begin,
.write_end = simple_write_end,
};
static struct backing_dev_info sysfs_backing_dev_info = {
.name = "sysfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
static const struct inode_operations sysfs_inode_operations = {
.permission = sysfs_permission,
.setattr = sysfs_setattr,
.getattr = sysfs_getattr,
.setxattr = sysfs_setxattr,
};
int __init sysfs_inode_init(void)
{
return bdi_init(&sysfs_backing_dev_info);
}
static struct sysfs_inode_attrs *sysfs_init_inode_attrs(struct sysfs_dirent *sd)
{
struct sysfs_inode_attrs *attrs;
struct iattr *iattrs;
attrs = kzalloc(sizeof(struct sysfs_inode_attrs), GFP_KERNEL);
if (!attrs)
return NULL;
iattrs = &attrs->ia_iattr;
/* assign default attributes */
iattrs->ia_mode = sd->s_mode;
iattrs->ia_uid = GLOBAL_ROOT_UID;
iattrs->ia_gid = GLOBAL_ROOT_GID;
iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME;
return attrs;
}
int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr *iattr)
{
struct sysfs_inode_attrs *sd_attrs;
struct iattr *iattrs;
unsigned int ia_valid = iattr->ia_valid;
sd_attrs = sd->s_iattr;
if (!sd_attrs) {
/* setting attributes for the first time, allocate now */
sd_attrs = sysfs_init_inode_attrs(sd);
if (!sd_attrs)
return -ENOMEM;
sd->s_iattr = sd_attrs;
}
/* attributes were changed at least once in past */
iattrs = &sd_attrs->ia_iattr;
if (ia_valid & ATTR_UID)
iattrs->ia_uid = iattr->ia_uid;
if (ia_valid & ATTR_GID)
iattrs->ia_gid = iattr->ia_gid;
if (ia_valid & ATTR_ATIME)
iattrs->ia_atime = iattr->ia_atime;
if (ia_valid & ATTR_MTIME)
iattrs->ia_mtime = iattr->ia_mtime;
if (ia_valid & ATTR_CTIME)
iattrs->ia_ctime = iattr->ia_ctime;
if (ia_valid & ATTR_MODE) {
umode_t mode = iattr->ia_mode;
iattrs->ia_mode = sd->s_mode = mode;
}
return 0;
}
int sysfs_setattr(struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = dentry->d_inode;
struct sysfs_dirent *sd = dentry->d_fsdata;
int error;
if (!sd)
return -EINVAL;
mutex_lock(&sysfs_mutex);
error = inode_change_ok(inode, iattr);
if (error)
goto out;
error = sysfs_sd_setattr(sd, iattr);
if (error)
goto out;
/* this ignores size changes */
setattr_copy(inode, iattr);
out:
mutex_unlock(&sysfs_mutex);
return error;
}
static int sysfs_sd_setsecdata(struct sysfs_dirent *sd, void **secdata,
u32 *secdata_len)
{
struct sysfs_inode_attrs *iattrs;
void *old_secdata;
size_t old_secdata_len;
sysfs: Fix memory leak in sysfs_sd_setsecdata(). This patch fixies follwing two memory leak patterns that reported by kmemleak. sysfs_sd_setsecdata() is called during sys_lsetxattr() operation. It checks sd->s_iattr is NULL or not. Then if it is NULL, it calls sysfs_init_inode_attrs() to allocate memory. That code is this. iattrs = sd->s_iattr; if (!iattrs) iattrs = sysfs_init_inode_attrs(sd); The iattrs recieves sysfs_init_inode_attrs()'s result, but sd->s_iattr doesn't know the address. so it needs to set correct address to sd->s_iattr to free memory in other function. unreferenced object 0xffff880250b73e60 (size 32): comm "systemd", pid 1, jiffies 4294683888 (age 94.553s) hex dump (first 32 bytes): 73 79 73 74 65 6d 5f 75 3a 6f 62 6a 65 63 74 5f system_u:object_ 72 3a 73 79 73 66 73 5f 74 3a 73 30 00 00 00 00 r:sysfs_t:s0.... backtrace: [<ffffffff814cb1d0>] kmemleak_alloc+0x73/0x98 [<ffffffff811270ab>] __kmalloc+0x100/0x12c [<ffffffff8120775a>] context_struct_to_string+0x106/0x210 [<ffffffff81207cc1>] security_sid_to_context_core+0x10b/0x129 [<ffffffff812090ef>] security_sid_to_context+0x10/0x12 [<ffffffff811fb0da>] selinux_inode_getsecurity+0x7d/0xa8 [<ffffffff811fb127>] selinux_inode_getsecctx+0x22/0x2e [<ffffffff811f4d62>] security_inode_getsecctx+0x16/0x18 [<ffffffff81191dad>] sysfs_setxattr+0x96/0x117 [<ffffffff811542f0>] __vfs_setxattr_noperm+0x73/0xd9 [<ffffffff811543d9>] vfs_setxattr+0x83/0xa1 [<ffffffff811544c6>] setxattr+0xcf/0x101 [<ffffffff81154745>] sys_lsetxattr+0x6a/0x8f [<ffffffff814efda9>] system_call_fastpath+0x16/0x1b [<ffffffffffffffff>] 0xffffffffffffffff unreferenced object 0xffff88024163c5a0 (size 96): comm "systemd", pid 1, jiffies 4294683888 (age 94.553s) hex dump (first 32 bytes): 00 00 00 00 ed 41 00 00 00 00 00 00 00 00 00 00 .....A.......... 00 00 00 00 00 00 00 00 0c 64 42 4f 00 00 00 00 .........dBO.... backtrace: [<ffffffff814cb1d0>] kmemleak_alloc+0x73/0x98 [<ffffffff81127402>] kmem_cache_alloc_trace+0xc4/0xee [<ffffffff81191cbe>] sysfs_init_inode_attrs+0x2a/0x83 [<ffffffff81191dd6>] sysfs_setxattr+0xbf/0x117 [<ffffffff811542f0>] __vfs_setxattr_noperm+0x73/0xd9 [<ffffffff811543d9>] vfs_setxattr+0x83/0xa1 [<ffffffff811544c6>] setxattr+0xcf/0x101 [<ffffffff81154745>] sys_lsetxattr+0x6a/0x8f [<ffffffff814efda9>] system_call_fastpath+0x16/0x1b [<ffffffffffffffff>] 0xffffffffffffffff ` Signed-off-by: Masami Ichikawa <masami256@gmail.com> Cc: stable <stable@vger.kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-02-21 05:43:50 +07:00
if (!sd->s_iattr) {
sd->s_iattr = sysfs_init_inode_attrs(sd);
if (!sd->s_iattr)
return -ENOMEM;
}
sysfs: Fix memory leak in sysfs_sd_setsecdata(). This patch fixies follwing two memory leak patterns that reported by kmemleak. sysfs_sd_setsecdata() is called during sys_lsetxattr() operation. It checks sd->s_iattr is NULL or not. Then if it is NULL, it calls sysfs_init_inode_attrs() to allocate memory. That code is this. iattrs = sd->s_iattr; if (!iattrs) iattrs = sysfs_init_inode_attrs(sd); The iattrs recieves sysfs_init_inode_attrs()'s result, but sd->s_iattr doesn't know the address. so it needs to set correct address to sd->s_iattr to free memory in other function. unreferenced object 0xffff880250b73e60 (size 32): comm "systemd", pid 1, jiffies 4294683888 (age 94.553s) hex dump (first 32 bytes): 73 79 73 74 65 6d 5f 75 3a 6f 62 6a 65 63 74 5f system_u:object_ 72 3a 73 79 73 66 73 5f 74 3a 73 30 00 00 00 00 r:sysfs_t:s0.... backtrace: [<ffffffff814cb1d0>] kmemleak_alloc+0x73/0x98 [<ffffffff811270ab>] __kmalloc+0x100/0x12c [<ffffffff8120775a>] context_struct_to_string+0x106/0x210 [<ffffffff81207cc1>] security_sid_to_context_core+0x10b/0x129 [<ffffffff812090ef>] security_sid_to_context+0x10/0x12 [<ffffffff811fb0da>] selinux_inode_getsecurity+0x7d/0xa8 [<ffffffff811fb127>] selinux_inode_getsecctx+0x22/0x2e [<ffffffff811f4d62>] security_inode_getsecctx+0x16/0x18 [<ffffffff81191dad>] sysfs_setxattr+0x96/0x117 [<ffffffff811542f0>] __vfs_setxattr_noperm+0x73/0xd9 [<ffffffff811543d9>] vfs_setxattr+0x83/0xa1 [<ffffffff811544c6>] setxattr+0xcf/0x101 [<ffffffff81154745>] sys_lsetxattr+0x6a/0x8f [<ffffffff814efda9>] system_call_fastpath+0x16/0x1b [<ffffffffffffffff>] 0xffffffffffffffff unreferenced object 0xffff88024163c5a0 (size 96): comm "systemd", pid 1, jiffies 4294683888 (age 94.553s) hex dump (first 32 bytes): 00 00 00 00 ed 41 00 00 00 00 00 00 00 00 00 00 .....A.......... 00 00 00 00 00 00 00 00 0c 64 42 4f 00 00 00 00 .........dBO.... backtrace: [<ffffffff814cb1d0>] kmemleak_alloc+0x73/0x98 [<ffffffff81127402>] kmem_cache_alloc_trace+0xc4/0xee [<ffffffff81191cbe>] sysfs_init_inode_attrs+0x2a/0x83 [<ffffffff81191dd6>] sysfs_setxattr+0xbf/0x117 [<ffffffff811542f0>] __vfs_setxattr_noperm+0x73/0xd9 [<ffffffff811543d9>] vfs_setxattr+0x83/0xa1 [<ffffffff811544c6>] setxattr+0xcf/0x101 [<ffffffff81154745>] sys_lsetxattr+0x6a/0x8f [<ffffffff814efda9>] system_call_fastpath+0x16/0x1b [<ffffffffffffffff>] 0xffffffffffffffff ` Signed-off-by: Masami Ichikawa <masami256@gmail.com> Cc: stable <stable@vger.kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-02-21 05:43:50 +07:00
iattrs = sd->s_iattr;
old_secdata = iattrs->ia_secdata;
old_secdata_len = iattrs->ia_secdata_len;
iattrs->ia_secdata = *secdata;
iattrs->ia_secdata_len = *secdata_len;
*secdata = old_secdata;
*secdata_len = old_secdata_len;
return 0;
}
int sysfs_setxattr(struct dentry *dentry, const char *name, const void *value,
size_t size, int flags)
{
struct sysfs_dirent *sd = dentry->d_fsdata;
void *secdata;
int error;
u32 secdata_len = 0;
if (!sd)
return -EINVAL;
if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) {
const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
error = security_inode_setsecurity(dentry->d_inode, suffix,
value, size, flags);
if (error)
goto out;
error = security_inode_getsecctx(dentry->d_inode,
&secdata, &secdata_len);
if (error)
goto out;
mutex_lock(&sysfs_mutex);
error = sysfs_sd_setsecdata(sd, &secdata, &secdata_len);
mutex_unlock(&sysfs_mutex);
if (secdata)
security_release_secctx(secdata, secdata_len);
} else
return -EINVAL;
out:
return error;
}
static inline void set_default_inode_attr(struct inode *inode, umode_t mode)
{
inode->i_mode = mode;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
}
static inline void set_inode_attr(struct inode *inode, struct iattr *iattr)
{
inode->i_uid = iattr->ia_uid;
inode->i_gid = iattr->ia_gid;
inode->i_atime = iattr->ia_atime;
inode->i_mtime = iattr->ia_mtime;
inode->i_ctime = iattr->ia_ctime;
}
static void sysfs_refresh_inode(struct sysfs_dirent *sd, struct inode *inode)
{
struct sysfs_inode_attrs *iattrs = sd->s_iattr;
inode->i_mode = sd->s_mode;
if (iattrs) {
/* sysfs_dirent has non-default attributes
* get them from persistent copy in sysfs_dirent
*/
set_inode_attr(inode, &iattrs->ia_iattr);
security_inode_notifysecctx(inode,
iattrs->ia_secdata,
iattrs->ia_secdata_len);
}
if (sysfs_type(sd) == SYSFS_DIR)
set_nlink(inode, sd->s_dir.subdirs + 2);
}
int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
struct sysfs_dirent *sd = dentry->d_fsdata;
struct inode *inode = dentry->d_inode;
mutex_lock(&sysfs_mutex);
sysfs_refresh_inode(sd, inode);
mutex_unlock(&sysfs_mutex);
generic_fillattr(inode, stat);
return 0;
}
static void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode)
{
struct bin_attribute *bin_attr;
inode->i_private = sysfs_get(sd);
inode->i_mapping->a_ops = &sysfs_aops;
inode->i_mapping->backing_dev_info = &sysfs_backing_dev_info;
inode->i_op = &sysfs_inode_operations;
set_default_inode_attr(inode, sd->s_mode);
sysfs_refresh_inode(sd, inode);
/* initialize inode according to type */
switch (sysfs_type(sd)) {
case SYSFS_DIR:
inode->i_op = &sysfs_dir_inode_operations;
inode->i_fop = &sysfs_dir_operations;
break;
case SYSFS_KOBJ_ATTR:
inode->i_size = PAGE_SIZE;
inode->i_fop = &sysfs_file_operations;
break;
case SYSFS_KOBJ_BIN_ATTR:
bin_attr = sd->s_attr.bin_attr;
inode->i_size = bin_attr->size;
inode->i_fop = &sysfs_bin_operations;
break;
case SYSFS_KOBJ_LINK:
inode->i_op = &sysfs_symlink_inode_operations;
break;
default:
BUG();
}
unlock_new_inode(inode);
}
/**
* sysfs_get_inode - get inode for sysfs_dirent
* @sb: super block
* @sd: sysfs_dirent to allocate inode for
*
* Get inode for @sd. If such inode doesn't exist, a new inode
* is allocated and basics are initialized. New inode is
* returned locked.
*
* LOCKING:
* Kernel thread context (may sleep).
*
* RETURNS:
* Pointer to allocated inode on success, NULL on failure.
*/
struct inode *sysfs_get_inode(struct super_block *sb, struct sysfs_dirent *sd)
{
struct inode *inode;
inode = iget_locked(sb, sd->s_ino);
if (inode && (inode->i_state & I_NEW))
sysfs_init_inode(sd, inode);
return inode;
}
/*
* The sysfs_dirent serves as both an inode and a directory entry for sysfs.
* To prevent the sysfs inode numbers from being freed prematurely we take a
* reference to sysfs_dirent from the sysfs inode. A
* super_operations.evict_inode() implementation is needed to drop that
* reference upon inode destruction.
*/
void sysfs_evict_inode(struct inode *inode)
{
struct sysfs_dirent *sd = inode->i_private;
truncate_inode_pages(&inode->i_data, 0);
clear_inode(inode);
sysfs_put(sd);
}
int sysfs_permission(struct inode *inode, int mask)
{
struct sysfs_dirent *sd;
if (mask & MAY_NOT_BLOCK)
return -ECHILD;
sd = inode->i_private;
mutex_lock(&sysfs_mutex);
sysfs_refresh_inode(sd, inode);
mutex_unlock(&sysfs_mutex);
return generic_permission(inode, mask);
}