OpenCloudOS-Kernel/security/keys/keyring.c

1362 lines
36 KiB
C
Raw Normal View History

/* Keyring handling
*
* Copyright (C) 2004-2005, 2008, 2013 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/security.h>
#include <linux/seq_file.h>
#include <linux/err.h>
#include <keys/keyring-type.h>
#include <keys/user-type.h>
#include <linux/assoc_array_priv.h>
#include <linux/uaccess.h>
#include "internal.h"
/*
* When plumbing the depths of the key tree, this sets a hard limit
* set on how deep we're willing to go.
*/
#define KEYRING_SEARCH_MAX_DEPTH 6
/*
* We keep all named keyrings in a hash to speed looking them up.
*/
#define KEYRING_NAME_HASH_SIZE (1 << 5)
/*
* We mark pointers we pass to the associative array with bit 1 set if
* they're keyrings and clear otherwise.
*/
#define KEYRING_PTR_SUBTYPE 0x2UL
static inline bool keyring_ptr_is_keyring(const struct assoc_array_ptr *x)
{
return (unsigned long)x & KEYRING_PTR_SUBTYPE;
}
static inline struct key *keyring_ptr_to_key(const struct assoc_array_ptr *x)
{
void *object = assoc_array_ptr_to_leaf(x);
return (struct key *)((unsigned long)object & ~KEYRING_PTR_SUBTYPE);
}
static inline void *keyring_key_to_ptr(struct key *key)
{
if (key->type == &key_type_keyring)
return (void *)((unsigned long)key | KEYRING_PTR_SUBTYPE);
return key;
}
static struct list_head keyring_name_hash[KEYRING_NAME_HASH_SIZE];
static DEFINE_RWLOCK(keyring_name_lock);
static inline unsigned keyring_hash(const char *desc)
{
unsigned bucket = 0;
for (; *desc; desc++)
bucket += (unsigned char)*desc;
return bucket & (KEYRING_NAME_HASH_SIZE - 1);
}
/*
* The keyring key type definition. Keyrings are simply keys of this type and
* can be treated as ordinary keys in addition to having their own special
* operations.
*/
static int keyring_instantiate(struct key *keyring,
KEYS: Add payload preparsing opportunity prior to key instantiate or update Give the key type the opportunity to preparse the payload prior to the instantiation and update routines being called. This is done with the provision of two new key type operations: int (*preparse)(struct key_preparsed_payload *prep); void (*free_preparse)(struct key_preparsed_payload *prep); If the first operation is present, then it is called before key creation (in the add/update case) or before the key semaphore is taken (in the update and instantiate cases). The second operation is called to clean up if the first was called. preparse() is given the opportunity to fill in the following structure: struct key_preparsed_payload { char *description; void *type_data[2]; void *payload; const void *data; size_t datalen; size_t quotalen; }; Before the preparser is called, the first three fields will have been cleared, the payload pointer and size will be stored in data and datalen and the default quota size from the key_type struct will be stored into quotalen. The preparser may parse the payload in any way it likes and may store data in the type_data[] and payload fields for use by the instantiate() and update() ops. The preparser may also propose a description for the key by attaching it as a string to the description field. This can be used by passing a NULL or "" description to the add_key() system call or the key_create_or_update() function. This cannot work with request_key() as that required the description to tell the upcall about the key to be created. This, for example permits keys that store PGP public keys to generate their own name from the user ID and public key fingerprint in the key. The instantiate() and update() operations are then modified to look like this: int (*instantiate)(struct key *key, struct key_preparsed_payload *prep); int (*update)(struct key *key, struct key_preparsed_payload *prep); and the new payload data is passed in *prep, whether or not it was preparsed. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2012-09-13 20:06:29 +08:00
struct key_preparsed_payload *prep);
static void keyring_revoke(struct key *keyring);
static void keyring_destroy(struct key *keyring);
static void keyring_describe(const struct key *keyring, struct seq_file *m);
static long keyring_read(const struct key *keyring,
char __user *buffer, size_t buflen);
struct key_type key_type_keyring = {
.name = "keyring",
.def_datalen = 0,
.instantiate = keyring_instantiate,
.match = user_match,
.revoke = keyring_revoke,
.destroy = keyring_destroy,
.describe = keyring_describe,
.read = keyring_read,
};
EXPORT_SYMBOL(key_type_keyring);
/*
* Semaphore to serialise link/link calls to prevent two link calls in parallel
* introducing a cycle.
*/
static DECLARE_RWSEM(keyring_serialise_link_sem);
/*
* Publish the name of a keyring so that it can be found by name (if it has
* one).
*/
static void keyring_publish_name(struct key *keyring)
{
int bucket;
if (keyring->description) {
bucket = keyring_hash(keyring->description);
write_lock(&keyring_name_lock);
if (!keyring_name_hash[bucket].next)
INIT_LIST_HEAD(&keyring_name_hash[bucket]);
list_add_tail(&keyring->type_data.link,
&keyring_name_hash[bucket]);
write_unlock(&keyring_name_lock);
}
}
/*
* Initialise a keyring.
*
* Returns 0 on success, -EINVAL if given any data.
*/
static int keyring_instantiate(struct key *keyring,
KEYS: Add payload preparsing opportunity prior to key instantiate or update Give the key type the opportunity to preparse the payload prior to the instantiation and update routines being called. This is done with the provision of two new key type operations: int (*preparse)(struct key_preparsed_payload *prep); void (*free_preparse)(struct key_preparsed_payload *prep); If the first operation is present, then it is called before key creation (in the add/update case) or before the key semaphore is taken (in the update and instantiate cases). The second operation is called to clean up if the first was called. preparse() is given the opportunity to fill in the following structure: struct key_preparsed_payload { char *description; void *type_data[2]; void *payload; const void *data; size_t datalen; size_t quotalen; }; Before the preparser is called, the first three fields will have been cleared, the payload pointer and size will be stored in data and datalen and the default quota size from the key_type struct will be stored into quotalen. The preparser may parse the payload in any way it likes and may store data in the type_data[] and payload fields for use by the instantiate() and update() ops. The preparser may also propose a description for the key by attaching it as a string to the description field. This can be used by passing a NULL or "" description to the add_key() system call or the key_create_or_update() function. This cannot work with request_key() as that required the description to tell the upcall about the key to be created. This, for example permits keys that store PGP public keys to generate their own name from the user ID and public key fingerprint in the key. The instantiate() and update() operations are then modified to look like this: int (*instantiate)(struct key *key, struct key_preparsed_payload *prep); int (*update)(struct key *key, struct key_preparsed_payload *prep); and the new payload data is passed in *prep, whether or not it was preparsed. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2012-09-13 20:06:29 +08:00
struct key_preparsed_payload *prep)
{
int ret;
ret = -EINVAL;
KEYS: Add payload preparsing opportunity prior to key instantiate or update Give the key type the opportunity to preparse the payload prior to the instantiation and update routines being called. This is done with the provision of two new key type operations: int (*preparse)(struct key_preparsed_payload *prep); void (*free_preparse)(struct key_preparsed_payload *prep); If the first operation is present, then it is called before key creation (in the add/update case) or before the key semaphore is taken (in the update and instantiate cases). The second operation is called to clean up if the first was called. preparse() is given the opportunity to fill in the following structure: struct key_preparsed_payload { char *description; void *type_data[2]; void *payload; const void *data; size_t datalen; size_t quotalen; }; Before the preparser is called, the first three fields will have been cleared, the payload pointer and size will be stored in data and datalen and the default quota size from the key_type struct will be stored into quotalen. The preparser may parse the payload in any way it likes and may store data in the type_data[] and payload fields for use by the instantiate() and update() ops. The preparser may also propose a description for the key by attaching it as a string to the description field. This can be used by passing a NULL or "" description to the add_key() system call or the key_create_or_update() function. This cannot work with request_key() as that required the description to tell the upcall about the key to be created. This, for example permits keys that store PGP public keys to generate their own name from the user ID and public key fingerprint in the key. The instantiate() and update() operations are then modified to look like this: int (*instantiate)(struct key *key, struct key_preparsed_payload *prep); int (*update)(struct key *key, struct key_preparsed_payload *prep); and the new payload data is passed in *prep, whether or not it was preparsed. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2012-09-13 20:06:29 +08:00
if (prep->datalen == 0) {
assoc_array_init(&keyring->keys);
/* make the keyring available by name if it has one */
keyring_publish_name(keyring);
ret = 0;
}
return ret;
}
/*
* Multiply 64-bits by 32-bits to 96-bits and fold back to 64-bit. Ideally we'd
* fold the carry back too, but that requires inline asm.
*/
static u64 mult_64x32_and_fold(u64 x, u32 y)
{
u64 hi = (u64)(u32)(x >> 32) * y;
u64 lo = (u64)(u32)(x) * y;
return lo + ((u64)(u32)hi << 32) + (u32)(hi >> 32);
}
/*
* Hash a key type and description.
*/
static unsigned long hash_key_type_and_desc(const struct keyring_index_key *index_key)
{
const unsigned level_shift = ASSOC_ARRAY_LEVEL_STEP;
const unsigned long level_mask = ASSOC_ARRAY_LEVEL_STEP_MASK;
const char *description = index_key->description;
unsigned long hash, type;
u32 piece;
u64 acc;
int n, desc_len = index_key->desc_len;
type = (unsigned long)index_key->type;
acc = mult_64x32_and_fold(type, desc_len + 13);
acc = mult_64x32_and_fold(acc, 9207);
for (;;) {
n = desc_len;
if (n <= 0)
break;
if (n > 4)
n = 4;
piece = 0;
memcpy(&piece, description, n);
description += n;
desc_len -= n;
acc = mult_64x32_and_fold(acc, piece);
acc = mult_64x32_and_fold(acc, 9207);
}
/* Fold the hash down to 32 bits if need be. */
hash = acc;
if (ASSOC_ARRAY_KEY_CHUNK_SIZE == 32)
hash ^= acc >> 32;
/* Squidge all the keyrings into a separate part of the tree to
* ordinary keys by making sure the lowest level segment in the hash is
* zero for keyrings and non-zero otherwise.
*/
if (index_key->type != &key_type_keyring && (hash & level_mask) == 0)
return hash | (hash >> (ASSOC_ARRAY_KEY_CHUNK_SIZE - level_shift)) | 1;
if (index_key->type == &key_type_keyring && (hash & level_mask) != 0)
return (hash + (hash << level_shift)) & ~level_mask;
return hash;
}
/*
* Build the next index key chunk.
*
* On 32-bit systems the index key is laid out as:
*
* 0 4 5 9...
* hash desclen typeptr desc[]
*
* On 64-bit systems:
*
* 0 8 9 17...
* hash desclen typeptr desc[]
*
* We return it one word-sized chunk at a time.
*/
static unsigned long keyring_get_key_chunk(const void *data, int level)
{
const struct keyring_index_key *index_key = data;
unsigned long chunk = 0;
long offset = 0;
int desc_len = index_key->desc_len, n = sizeof(chunk);
level /= ASSOC_ARRAY_KEY_CHUNK_SIZE;
switch (level) {
case 0:
return hash_key_type_and_desc(index_key);
case 1:
return ((unsigned long)index_key->type << 8) | desc_len;
case 2:
if (desc_len == 0)
return (u8)((unsigned long)index_key->type >>
(ASSOC_ARRAY_KEY_CHUNK_SIZE - 8));
n--;
offset = 1;
default:
offset += sizeof(chunk) - 1;
offset += (level - 3) * sizeof(chunk);
if (offset >= desc_len)
return 0;
desc_len -= offset;
if (desc_len > n)
desc_len = n;
offset += desc_len;
do {
chunk <<= 8;
chunk |= ((u8*)index_key->description)[--offset];
} while (--desc_len > 0);
if (level == 2) {
chunk <<= 8;
chunk |= (u8)((unsigned long)index_key->type >>
(ASSOC_ARRAY_KEY_CHUNK_SIZE - 8));
}
return chunk;
}
}
static unsigned long keyring_get_object_key_chunk(const void *object, int level)
{
const struct key *key = keyring_ptr_to_key(object);
return keyring_get_key_chunk(&key->index_key, level);
}
static bool keyring_compare_object(const void *object, const void *data)
{
const struct keyring_index_key *index_key = data;
const struct key *key = keyring_ptr_to_key(object);
return key->index_key.type == index_key->type &&
key->index_key.desc_len == index_key->desc_len &&
memcmp(key->index_key.description, index_key->description,
index_key->desc_len) == 0;
}
/*
* Compare the index keys of a pair of objects and determine the bit position
* at which they differ - if they differ.
*/
static int keyring_diff_objects(const void *_a, const void *_b)
{
const struct key *key_a = keyring_ptr_to_key(_a);
const struct key *key_b = keyring_ptr_to_key(_b);
const struct keyring_index_key *a = &key_a->index_key;
const struct keyring_index_key *b = &key_b->index_key;
unsigned long seg_a, seg_b;
int level, i;
level = 0;
seg_a = hash_key_type_and_desc(a);
seg_b = hash_key_type_and_desc(b);
if ((seg_a ^ seg_b) != 0)
goto differ;
/* The number of bits contributed by the hash is controlled by a
* constant in the assoc_array headers. Everything else thereafter we
* can deal with as being machine word-size dependent.
*/
level += ASSOC_ARRAY_KEY_CHUNK_SIZE / 8;
seg_a = a->desc_len;
seg_b = b->desc_len;
if ((seg_a ^ seg_b) != 0)
goto differ;
/* The next bit may not work on big endian */
level++;
seg_a = (unsigned long)a->type;
seg_b = (unsigned long)b->type;
if ((seg_a ^ seg_b) != 0)
goto differ;
level += sizeof(unsigned long);
if (a->desc_len == 0)
goto same;
i = 0;
if (((unsigned long)a->description | (unsigned long)b->description) &
(sizeof(unsigned long) - 1)) {
do {
seg_a = *(unsigned long *)(a->description + i);
seg_b = *(unsigned long *)(b->description + i);
if ((seg_a ^ seg_b) != 0)
goto differ_plus_i;
i += sizeof(unsigned long);
} while (i < (a->desc_len & (sizeof(unsigned long) - 1)));
}
for (; i < a->desc_len; i++) {
seg_a = *(unsigned char *)(a->description + i);
seg_b = *(unsigned char *)(b->description + i);
if ((seg_a ^ seg_b) != 0)
goto differ_plus_i;
}
same:
return -1;
differ_plus_i:
level += i;
differ:
i = level * 8 + __ffs(seg_a ^ seg_b);
return i;
}
/*
* Free an object after stripping the keyring flag off of the pointer.
*/
static void keyring_free_object(void *object)
{
key_put(keyring_ptr_to_key(object));
}
/*
* Operations for keyring management by the index-tree routines.
*/
static const struct assoc_array_ops keyring_assoc_array_ops = {
.get_key_chunk = keyring_get_key_chunk,
.get_object_key_chunk = keyring_get_object_key_chunk,
.compare_object = keyring_compare_object,
.diff_objects = keyring_diff_objects,
.free_object = keyring_free_object,
};
/*
* Clean up a keyring when it is destroyed. Unpublish its name if it had one
* and dispose of its data.
*
* The garbage collector detects the final key_put(), removes the keyring from
* the serial number tree and then does RCU synchronisation before coming here,
* so we shouldn't need to worry about code poking around here with the RCU
* readlock held by this time.
*/
static void keyring_destroy(struct key *keyring)
{
if (keyring->description) {
write_lock(&keyring_name_lock);
if (keyring->type_data.link.next != NULL &&
!list_empty(&keyring->type_data.link))
list_del(&keyring->type_data.link);
write_unlock(&keyring_name_lock);
}
assoc_array_destroy(&keyring->keys, &keyring_assoc_array_ops);
}
/*
* Describe a keyring for /proc.
*/
static void keyring_describe(const struct key *keyring, struct seq_file *m)
{
if (keyring->description)
seq_puts(m, keyring->description);
else
seq_puts(m, "[anon]");
if (key_is_instantiated(keyring)) {
if (keyring->keys.nr_leaves_on_tree != 0)
seq_printf(m, ": %lu", keyring->keys.nr_leaves_on_tree);
else
seq_puts(m, ": empty");
}
}
struct keyring_read_iterator_context {
size_t qty;
size_t count;
key_serial_t __user *buffer;
};
static int keyring_read_iterator(const void *object, void *data)
{
struct keyring_read_iterator_context *ctx = data;
const struct key *key = keyring_ptr_to_key(object);
int ret;
kenter("{%s,%d},,{%zu/%zu}",
key->type->name, key->serial, ctx->count, ctx->qty);
if (ctx->count >= ctx->qty)
return 1;
ret = put_user(key->serial, ctx->buffer);
if (ret < 0)
return ret;
ctx->buffer++;
ctx->count += sizeof(key->serial);
return 0;
}
/*
* Read a list of key IDs from the keyring's contents in binary form
*
* The keyring's semaphore is read-locked by the caller. This prevents someone
* from modifying it under us - which could cause us to read key IDs multiple
* times.
*/
static long keyring_read(const struct key *keyring,
char __user *buffer, size_t buflen)
{
struct keyring_read_iterator_context ctx;
unsigned long nr_keys;
int ret;
kenter("{%d},,%zu", key_serial(keyring), buflen);
if (buflen & (sizeof(key_serial_t) - 1))
return -EINVAL;
nr_keys = keyring->keys.nr_leaves_on_tree;
if (nr_keys == 0)
return 0;
/* Calculate how much data we could return */
ctx.qty = nr_keys * sizeof(key_serial_t);
if (!buffer || !buflen)
return ctx.qty;
if (buflen > ctx.qty)
ctx.qty = buflen;
/* Copy the IDs of the subscribed keys into the buffer */
ctx.buffer = (key_serial_t __user *)buffer;
ctx.count = 0;
ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx);
if (ret < 0) {
kleave(" = %d [iterate]", ret);
return ret;
}
kleave(" = %zu [ok]", ctx.count);
return ctx.count;
}
/*
* Allocate a keyring and link into the destination keyring.
*/
struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid,
KEYS: Reduce initial permissions on keys Reduce the initial permissions on new keys to grant the possessor everything, view permission only to the user (so the keys can be seen in /proc/keys) and nothing else. This gives the creator a chance to adjust the permissions mask before other processes can access the new key or create a link to it. To aid with this, keyring_alloc() now takes a permission argument rather than setting the permissions itself. The following permissions are now set: (1) The user and user-session keyrings grant the user that owns them full permissions and grant a possessor everything bar SETATTR. (2) The process and thread keyrings grant the possessor full permissions but only grant the user VIEW. This permits the user to see them in /proc/keys, but not to do anything with them. (3) Anonymous session keyrings grant the possessor full permissions, but only grant the user VIEW and READ. This means that the user can see them in /proc/keys and can list them, but nothing else. Possibly READ shouldn't be provided either. (4) Named session keyrings grant everything an anonymous session keyring does, plus they grant the user LINK permission. The whole point of named session keyrings is that others can also subscribe to them. Possibly this should be a separate permission to LINK. (5) The temporary session keyring created by call_sbin_request_key() gets the same permissions as an anonymous session keyring. (6) Keys created by add_key() get VIEW, SEARCH, LINK and SETATTR for the possessor, plus READ and/or WRITE if the key type supports them. The used only gets VIEW now. (7) Keys created by request_key() now get the same as those created by add_key(). Reported-by: Lennart Poettering <lennart@poettering.net> Reported-by: Stef Walter <stefw@redhat.com> Signed-off-by: David Howells <dhowells@redhat.com>
2012-10-03 02:24:56 +08:00
const struct cred *cred, key_perm_t perm,
unsigned long flags, struct key *dest)
{
struct key *keyring;
int ret;
keyring = key_alloc(&key_type_keyring, description,
KEYS: Reduce initial permissions on keys Reduce the initial permissions on new keys to grant the possessor everything, view permission only to the user (so the keys can be seen in /proc/keys) and nothing else. This gives the creator a chance to adjust the permissions mask before other processes can access the new key or create a link to it. To aid with this, keyring_alloc() now takes a permission argument rather than setting the permissions itself. The following permissions are now set: (1) The user and user-session keyrings grant the user that owns them full permissions and grant a possessor everything bar SETATTR. (2) The process and thread keyrings grant the possessor full permissions but only grant the user VIEW. This permits the user to see them in /proc/keys, but not to do anything with them. (3) Anonymous session keyrings grant the possessor full permissions, but only grant the user VIEW and READ. This means that the user can see them in /proc/keys and can list them, but nothing else. Possibly READ shouldn't be provided either. (4) Named session keyrings grant everything an anonymous session keyring does, plus they grant the user LINK permission. The whole point of named session keyrings is that others can also subscribe to them. Possibly this should be a separate permission to LINK. (5) The temporary session keyring created by call_sbin_request_key() gets the same permissions as an anonymous session keyring. (6) Keys created by add_key() get VIEW, SEARCH, LINK and SETATTR for the possessor, plus READ and/or WRITE if the key type supports them. The used only gets VIEW now. (7) Keys created by request_key() now get the same as those created by add_key(). Reported-by: Lennart Poettering <lennart@poettering.net> Reported-by: Stef Walter <stefw@redhat.com> Signed-off-by: David Howells <dhowells@redhat.com>
2012-10-03 02:24:56 +08:00
uid, gid, cred, perm, flags);
if (!IS_ERR(keyring)) {
[PATCH] Keys: Make request-key create an authorisation key The attached patch makes the following changes: (1) There's a new special key type called ".request_key_auth". This is an authorisation key for when one process requests a key and another process is started to construct it. This type of key cannot be created by the user; nor can it be requested by kernel services. Authorisation keys hold two references: (a) Each refers to a key being constructed. When the key being constructed is instantiated the authorisation key is revoked, rendering it of no further use. (b) The "authorising process". This is either: (i) the process that called request_key(), or: (ii) if the process that called request_key() itself had an authorisation key in its session keyring, then the authorising process referred to by that authorisation key will also be referred to by the new authorisation key. This means that the process that initiated a chain of key requests will authorise the lot of them, and will, by default, wind up with the keys obtained from them in its keyrings. (2) request_key() creates an authorisation key which is then passed to /sbin/request-key in as part of a new session keyring. (3) When request_key() is searching for a key to hand back to the caller, if it comes across an authorisation key in the session keyring of the calling process, it will also search the keyrings of the process specified therein and it will use the specified process's credentials (fsuid, fsgid, groups) to do that rather than the calling process's credentials. This allows a process started by /sbin/request-key to find keys belonging to the authorising process. (4) A key can be read, even if the process executing KEYCTL_READ doesn't have direct read or search permission if that key is contained within the keyrings of a process specified by an authorisation key found within the calling process's session keyring, and is searchable using the credentials of the authorising process. This allows a process started by /sbin/request-key to read keys belonging to the authorising process. (5) The magic KEY_SPEC_*_KEYRING key IDs when passed to KEYCTL_INSTANTIATE or KEYCTL_NEGATE will specify a keyring of the authorising process, rather than the process doing the instantiation. (6) One of the process keyrings can be nominated as the default to which request_key() should attach new keys if not otherwise specified. This is done with KEYCTL_SET_REQKEY_KEYRING and one of the KEY_REQKEY_DEFL_* constants. The current setting can also be read using this call. (7) request_key() is partially interruptible. If it is waiting for another process to finish constructing a key, it can be interrupted. This permits a request-key cycle to be broken without recourse to rebooting. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-Off-By: Benoit Boissinot <benoit.boissinot@ens-lyon.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:00:56 +08:00
ret = key_instantiate_and_link(keyring, NULL, 0, dest, NULL);
if (ret < 0) {
key_put(keyring);
keyring = ERR_PTR(ret);
}
}
return keyring;
}
EXPORT_SYMBOL(keyring_alloc);
/*
* Iteration function to consider each key found.
*/
static int keyring_search_iterator(const void *object, void *iterator_data)
{
struct keyring_search_context *ctx = iterator_data;
const struct key *key = keyring_ptr_to_key(object);
unsigned long kflags = key->flags;
kenter("{%d}", key->serial);
/* ignore keys not of this type */
if (key->type != ctx->index_key.type) {
kleave(" = 0 [!type]");
return 0;
}
/* skip invalidated, revoked and expired keys */
if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
(1 << KEY_FLAG_REVOKED))) {
ctx->result = ERR_PTR(-EKEYREVOKED);
kleave(" = %d [invrev]", ctx->skipped_ret);
goto skipped;
}
if (key->expiry && ctx->now.tv_sec >= key->expiry) {
ctx->result = ERR_PTR(-EKEYEXPIRED);
kleave(" = %d [expire]", ctx->skipped_ret);
goto skipped;
}
}
/* keys that don't match */
if (!ctx->match(key, ctx->match_data)) {
kleave(" = 0 [!match]");
return 0;
}
keys: check starting keyring as part of search Check the starting keyring as part of the search to (a) see if that is what we're searching for, and (b) to check it is still valid for searching. The scenario: User in process A does things that cause things to be created in its process session keyring. The user then does an su to another user and starts a new process, B. The two processes now share the same process session keyring. Process B does an NFS access which results in an upcall to gssd. When gssd attempts to instantiate the context key (to be linked into the process session keyring), it is denied access even though it has an authorization key. The order of calls is: keyctl_instantiate_key() lookup_user_key() (the default: case) search_process_keyrings(current) search_process_keyrings(rka->context) (recursive call) keyring_search_aux() keyring_search_aux() verifies the keys and keyrings underneath the top-level keyring it is given, but that top-level keyring is neither fully validated nor checked to see if it is the thing being searched for. This patch changes keyring_search_aux() to: 1) do more validation on the top keyring it is given and 2) check whether that top-level keyring is the thing being searched for Signed-off-by: Kevin Coffman <kwc@citi.umich.edu> Signed-off-by: David Howells <dhowells@redhat.com> Cc: Paul Moore <paul.moore@hp.com> Cc: Chris Wright <chrisw@sous-sol.org> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: Kevin Coffman <kwc@citi.umich.edu> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 16:01:22 +08:00
/* key must have search permissions */
if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
key_task_permission(make_key_ref(key, ctx->possessed),
ctx->cred, KEY_SEARCH) < 0) {
ctx->result = ERR_PTR(-EACCES);
kleave(" = %d [!perm]", ctx->skipped_ret);
goto skipped;
keys: check starting keyring as part of search Check the starting keyring as part of the search to (a) see if that is what we're searching for, and (b) to check it is still valid for searching. The scenario: User in process A does things that cause things to be created in its process session keyring. The user then does an su to another user and starts a new process, B. The two processes now share the same process session keyring. Process B does an NFS access which results in an upcall to gssd. When gssd attempts to instantiate the context key (to be linked into the process session keyring), it is denied access even though it has an authorization key. The order of calls is: keyctl_instantiate_key() lookup_user_key() (the default: case) search_process_keyrings(current) search_process_keyrings(rka->context) (recursive call) keyring_search_aux() keyring_search_aux() verifies the keys and keyrings underneath the top-level keyring it is given, but that top-level keyring is neither fully validated nor checked to see if it is the thing being searched for. This patch changes keyring_search_aux() to: 1) do more validation on the top keyring it is given and 2) check whether that top-level keyring is the thing being searched for Signed-off-by: Kevin Coffman <kwc@citi.umich.edu> Signed-off-by: David Howells <dhowells@redhat.com> Cc: Paul Moore <paul.moore@hp.com> Cc: Chris Wright <chrisw@sous-sol.org> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: Kevin Coffman <kwc@citi.umich.edu> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 16:01:22 +08:00
}
if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
/* we set a different error code if we pass a negative key */
if (kflags & (1 << KEY_FLAG_NEGATIVE)) {
KEYS: Fix a race between negating a key and reading the error set key_reject_and_link() marking a key as negative and setting the error with which it was negated races with keyring searches and other things that read that error. The fix is to switch the order in which the assignments are done in key_reject_and_link() and to use memory barriers. Kudos to Dave Wysochanski <dwysocha@redhat.com> and Scott Mayhew <smayhew@redhat.com> for tracking this down. This may be the cause of: BUG: unable to handle kernel NULL pointer dereference at 0000000000000070 IP: [<ffffffff81219011>] wait_for_key_construction+0x31/0x80 PGD c6b2c3067 PUD c59879067 PMD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/devices/system/cpu/cpu3/cache/index2/shared_cpu_map CPU 0 Modules linked in: ... Pid: 13359, comm: amqzxma0 Not tainted 2.6.32-358.20.1.el6.x86_64 #1 IBM System x3650 M3 -[7945PSJ]-/00J6159 RIP: 0010:[<ffffffff81219011>] wait_for_key_construction+0x31/0x80 RSP: 0018:ffff880c6ab33758 EFLAGS: 00010246 RAX: ffffffff81219080 RBX: 0000000000000000 RCX: 0000000000000002 RDX: ffffffff81219060 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff880c6ab33768 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffff880adfcbce40 R13: ffffffffa03afb84 R14: ffff880adfcbce40 R15: ffff880adfcbce43 FS: 00007f29b8042700(0000) GS:ffff880028200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000070 CR3: 0000000c613dc000 CR4: 00000000000007f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process amqzxma0 (pid: 13359, threadinfo ffff880c6ab32000, task ffff880c610deae0) Stack: ffff880adfcbce40 0000000000000000 ffff880c6ab337b8 ffffffff81219695 <d> 0000000000000000 ffff880a000000d0 ffff880c6ab337a8 000000000000000f <d> ffffffffa03afb93 000000000000000f ffff88186c7882c0 0000000000000014 Call Trace: [<ffffffff81219695>] request_key+0x65/0xa0 [<ffffffffa03a0885>] nfs_idmap_request_key+0xc5/0x170 [nfs] [<ffffffffa03a0eb4>] nfs_idmap_lookup_id+0x34/0x80 [nfs] [<ffffffffa03a1255>] nfs_map_group_to_gid+0x75/0xa0 [nfs] [<ffffffffa039a9ad>] decode_getfattr_attrs+0xbdd/0xfb0 [nfs] [<ffffffff81057310>] ? __dequeue_entity+0x30/0x50 [<ffffffff8100988e>] ? __switch_to+0x26e/0x320 [<ffffffffa039ae03>] decode_getfattr+0x83/0xe0 [nfs] [<ffffffffa039b610>] ? nfs4_xdr_dec_getattr+0x0/0xa0 [nfs] [<ffffffffa039b69f>] nfs4_xdr_dec_getattr+0x8f/0xa0 [nfs] [<ffffffffa02dada4>] rpcauth_unwrap_resp+0x84/0xb0 [sunrpc] [<ffffffffa039b610>] ? nfs4_xdr_dec_getattr+0x0/0xa0 [nfs] [<ffffffffa02cf923>] call_decode+0x1b3/0x800 [sunrpc] [<ffffffff81096de0>] ? wake_bit_function+0x0/0x50 [<ffffffffa02cf770>] ? call_decode+0x0/0x800 [sunrpc] [<ffffffffa02d99a7>] __rpc_execute+0x77/0x350 [sunrpc] [<ffffffff81096c67>] ? bit_waitqueue+0x17/0xd0 [<ffffffffa02d9ce1>] rpc_execute+0x61/0xa0 [sunrpc] [<ffffffffa02d03a5>] rpc_run_task+0x75/0x90 [sunrpc] [<ffffffffa02d04c2>] rpc_call_sync+0x42/0x70 [sunrpc] [<ffffffffa038ff80>] _nfs4_call_sync+0x30/0x40 [nfs] [<ffffffffa038836c>] _nfs4_proc_getattr+0xac/0xc0 [nfs] [<ffffffff810aac87>] ? futex_wait+0x227/0x380 [<ffffffffa038b856>] nfs4_proc_getattr+0x56/0x80 [nfs] [<ffffffffa0371403>] __nfs_revalidate_inode+0xe3/0x220 [nfs] [<ffffffffa037158e>] nfs_revalidate_mapping+0x4e/0x170 [nfs] [<ffffffffa036f147>] nfs_file_read+0x77/0x130 [nfs] [<ffffffff811811aa>] do_sync_read+0xfa/0x140 [<ffffffff81096da0>] ? autoremove_wake_function+0x0/0x40 [<ffffffff8100bb8e>] ? apic_timer_interrupt+0xe/0x20 [<ffffffff8100b9ce>] ? common_interrupt+0xe/0x13 [<ffffffff81228ffb>] ? selinux_file_permission+0xfb/0x150 [<ffffffff8121bed6>] ? security_file_permission+0x16/0x20 [<ffffffff81181a95>] vfs_read+0xb5/0x1a0 [<ffffffff81181bd1>] sys_read+0x51/0x90 [<ffffffff810dc685>] ? __audit_syscall_exit+0x265/0x290 [<ffffffff8100b072>] system_call_fastpath+0x16/0x1b Signed-off-by: David Howells <dhowells@redhat.com> cc: Dave Wysochanski <dwysocha@redhat.com> cc: Scott Mayhew <smayhew@redhat.com>
2013-10-30 19:15:24 +08:00
smp_rmb();
ctx->result = ERR_PTR(key->type_data.reject_error);
kleave(" = %d [neg]", ctx->skipped_ret);
goto skipped;
}
}
/* Found */
ctx->result = make_key_ref(key, ctx->possessed);
kleave(" = 1 [found]");
return 1;
skipped:
return ctx->skipped_ret;
}
/*
* Search inside a keyring for a key. We can search by walking to it
* directly based on its index-key or we can iterate over the entire
* tree looking for it, based on the match function.
*/
static int search_keyring(struct key *keyring, struct keyring_search_context *ctx)
{
if ((ctx->flags & KEYRING_SEARCH_LOOKUP_TYPE) ==
KEYRING_SEARCH_LOOKUP_DIRECT) {
const void *object;
object = assoc_array_find(&keyring->keys,
&keyring_assoc_array_ops,
&ctx->index_key);
return object ? ctx->iterator(object, ctx) : 0;
}
return assoc_array_iterate(&keyring->keys, ctx->iterator, ctx);
}
/*
* Search a tree of keyrings that point to other keyrings up to the maximum
* depth.
*/
static bool search_nested_keyrings(struct key *keyring,
struct keyring_search_context *ctx)
{
struct {
struct key *keyring;
struct assoc_array_node *node;
int slot;
} stack[KEYRING_SEARCH_MAX_DEPTH];
struct assoc_array_shortcut *shortcut;
struct assoc_array_node *node;
struct assoc_array_ptr *ptr;
struct key *key;
int sp = 0, slot;
kenter("{%d},{%s,%s}",
keyring->serial,
ctx->index_key.type->name,
ctx->index_key.description);
if (ctx->index_key.description)
ctx->index_key.desc_len = strlen(ctx->index_key.description);
/* Check to see if this top-level keyring is what we are looking for
* and whether it is valid or not.
*/
if (ctx->flags & KEYRING_SEARCH_LOOKUP_ITERATE ||
keyring_compare_object(keyring, &ctx->index_key)) {
ctx->skipped_ret = 2;
ctx->flags |= KEYRING_SEARCH_DO_STATE_CHECK;
switch (ctx->iterator(keyring_key_to_ptr(keyring), ctx)) {
case 1:
goto found;
case 2:
return false;
default:
break;
}
}
ctx->skipped_ret = 0;
if (ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)
ctx->flags &= ~KEYRING_SEARCH_DO_STATE_CHECK;
/* Start processing a new keyring */
descend_to_keyring:
kdebug("descend to %d", keyring->serial);
if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
(1 << KEY_FLAG_REVOKED)))
goto not_this_keyring;
/* Search through the keys in this keyring before its searching its
* subtrees.
*/
if (search_keyring(keyring, ctx))
goto found;
/* Then manually iterate through the keyrings nested in this one.
*
* Start from the root node of the index tree. Because of the way the
* hash function has been set up, keyrings cluster on the leftmost
* branch of the root node (root slot 0) or in the root node itself.
* Non-keyrings avoid the leftmost branch of the root entirely (root
* slots 1-15).
*/
ptr = ACCESS_ONCE(keyring->keys.root);
if (!ptr)
goto not_this_keyring;
if (assoc_array_ptr_is_shortcut(ptr)) {
/* If the root is a shortcut, either the keyring only contains
* keyring pointers (everything clusters behind root slot 0) or
* doesn't contain any keyring pointers.
*/
shortcut = assoc_array_ptr_to_shortcut(ptr);
smp_read_barrier_depends();
if ((shortcut->index_key[0] & ASSOC_ARRAY_FAN_MASK) != 0)
goto not_this_keyring;
ptr = ACCESS_ONCE(shortcut->next_node);
node = assoc_array_ptr_to_node(ptr);
goto begin_node;
}
node = assoc_array_ptr_to_node(ptr);
smp_read_barrier_depends();
ptr = node->slots[0];
if (!assoc_array_ptr_is_meta(ptr))
goto begin_node;
descend_to_node:
/* Descend to a more distal node in this keyring's content tree and go
* through that.
*/
kdebug("descend");
if (assoc_array_ptr_is_shortcut(ptr)) {
shortcut = assoc_array_ptr_to_shortcut(ptr);
smp_read_barrier_depends();
ptr = ACCESS_ONCE(shortcut->next_node);
BUG_ON(!assoc_array_ptr_is_node(ptr));
node = assoc_array_ptr_to_node(ptr);
}
begin_node:
kdebug("begin_node");
smp_read_barrier_depends();
slot = 0;
ascend_to_node:
/* Go through the slots in a node */
for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
ptr = ACCESS_ONCE(node->slots[slot]);
if (assoc_array_ptr_is_meta(ptr) && node->back_pointer)
goto descend_to_node;
if (!keyring_ptr_is_keyring(ptr))
[PATCH] keys: Discard key spinlock and use RCU for key payload The attached patch changes the key implementation in a number of ways: (1) It removes the spinlock from the key structure. (2) The key flags are now accessed using atomic bitops instead of write-locking the key spinlock and using C bitwise operators. The three instantiation flags are dealt with with the construction semaphore held during the request_key/instantiate/negate sequence, thus rendering the spinlock superfluous. The key flags are also now bit numbers not bit masks. (3) The key payload is now accessed using RCU. This permits the recursive keyring search algorithm to be simplified greatly since no locks need be taken other than the usual RCU preemption disablement. Searching now does not require any locks or semaphores to be held; merely that the starting keyring be pinned. (4) The keyring payload now includes an RCU head so that it can be disposed of by call_rcu(). This requires that the payload be copied on unlink to prevent introducing races in copy-down vs search-up. (5) The user key payload is now a structure with the data following it. It includes an RCU head like the keyring payload and for the same reason. It also contains a data length because the data length in the key may be changed on another CPU whilst an RCU protected read is in progress on the payload. This would then see the supposed RCU payload and the on-key data length getting out of sync. I'm tempted to drop the key's datalen entirely, except that it's used in conjunction with quota management and so is a little tricky to get rid of. (6) Update the keys documentation. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:00:49 +08:00
continue;
key = keyring_ptr_to_key(ptr);
if (sp >= KEYRING_SEARCH_MAX_DEPTH) {
if (ctx->flags & KEYRING_SEARCH_DETECT_TOO_DEEP) {
ctx->result = ERR_PTR(-ELOOP);
return false;
}
goto not_this_keyring;
}
/* Search a nested keyring */
if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
key_task_permission(make_key_ref(key, ctx->possessed),
ctx->cred, KEY_SEARCH) < 0)
[PATCH] keys: Discard key spinlock and use RCU for key payload The attached patch changes the key implementation in a number of ways: (1) It removes the spinlock from the key structure. (2) The key flags are now accessed using atomic bitops instead of write-locking the key spinlock and using C bitwise operators. The three instantiation flags are dealt with with the construction semaphore held during the request_key/instantiate/negate sequence, thus rendering the spinlock superfluous. The key flags are also now bit numbers not bit masks. (3) The key payload is now accessed using RCU. This permits the recursive keyring search algorithm to be simplified greatly since no locks need be taken other than the usual RCU preemption disablement. Searching now does not require any locks or semaphores to be held; merely that the starting keyring be pinned. (4) The keyring payload now includes an RCU head so that it can be disposed of by call_rcu(). This requires that the payload be copied on unlink to prevent introducing races in copy-down vs search-up. (5) The user key payload is now a structure with the data following it. It includes an RCU head like the keyring payload and for the same reason. It also contains a data length because the data length in the key may be changed on another CPU whilst an RCU protected read is in progress on the payload. This would then see the supposed RCU payload and the on-key data length getting out of sync. I'm tempted to drop the key's datalen entirely, except that it's used in conjunction with quota management and so is a little tricky to get rid of. (6) Update the keys documentation. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:00:49 +08:00
continue;
/* stack the current position */
KEYS: Do LRU discard in full keyrings Do an LRU discard in keyrings that are full rather than returning ENFILE. To perform this, a time_t is added to the key struct and updated by the creation of a link to a key and by a key being found as the result of a search. At the completion of a successful search, the keyrings in the path between the root of the search and the first found link to it also have their last-used times updated. Note that discarding a link to a key from a keyring does not necessarily destroy the key as there may be references held by other places. An alternate discard method that might suffice is to perform FIFO discard from the keyring, using the spare 2-byte hole in the keylist header as the index of the next link to be discarded. This is useful when using a keyring as a cache for DNS results or foreign filesystem IDs. This can be tested by the following. As root do: echo 1000 >/proc/sys/kernel/keys/root_maxkeys kr=`keyctl newring foo @s` for ((i=0; i<2000; i++)); do keyctl add user a$i a $kr; done Without this patch ENFILE should be reported when the keyring fills up. With this patch, the keyring discards keys in an LRU fashion. Note that the stored LRU time has a granularity of 1s. After doing this, /proc/key-users can be observed and should show that most of the 2000 keys have been discarded: [root@andromeda ~]# cat /proc/key-users 0: 517 516/516 513/1000 5249/20000 The "513/1000" here is the number of quota-accounted keys present for this user out of the maximum permitted. In /proc/keys, the keyring shows the number of keys it has and the number of slots it has allocated: [root@andromeda ~]# grep foo /proc/keys 200c64c4 I--Q-- 1 perm 3b3f0000 0 0 keyring foo: 509/509 The maximum is (PAGE_SIZE - header) / key pointer size. That's typically 509 on a 64-bit system and 1020 on a 32-bit system. Signed-off-by: David Howells <dhowells@redhat.com>
2012-05-11 17:56:56 +08:00
stack[sp].keyring = keyring;
stack[sp].node = node;
stack[sp].slot = slot;
sp++;
/* begin again with the new keyring */
keyring = key;
goto descend_to_keyring;
}
/* We've dealt with all the slots in the current node, so now we need
* to ascend to the parent and continue processing there.
*/
ptr = ACCESS_ONCE(node->back_pointer);
slot = node->parent_slot;
if (ptr && assoc_array_ptr_is_shortcut(ptr)) {
shortcut = assoc_array_ptr_to_shortcut(ptr);
smp_read_barrier_depends();
ptr = ACCESS_ONCE(shortcut->back_pointer);
slot = shortcut->parent_slot;
}
if (!ptr)
goto not_this_keyring;
node = assoc_array_ptr_to_node(ptr);
smp_read_barrier_depends();
slot++;
/* If we've ascended to the root (zero backpointer), we must have just
* finished processing the leftmost branch rather than the root slots -
* so there can't be any more keyrings for us to find.
*/
if (node->back_pointer) {
kdebug("ascend %d", slot);
goto ascend_to_node;
}
/* The keyring we're looking at was disqualified or didn't contain a
* matching key.
*/
not_this_keyring:
kdebug("not_this_keyring %d", sp);
if (sp <= 0) {
kleave(" = false");
return false;
}
/* Resume the processing of a keyring higher up in the tree */
sp--;
keyring = stack[sp].keyring;
node = stack[sp].node;
slot = stack[sp].slot + 1;
kdebug("ascend to %d [%d]", keyring->serial, slot);
goto ascend_to_node;
/* We found a viable match */
found:
key = key_ref_to_ptr(ctx->result);
key_check(key);
if (!(ctx->flags & KEYRING_SEARCH_NO_UPDATE_TIME)) {
key->last_used_at = ctx->now.tv_sec;
keyring->last_used_at = ctx->now.tv_sec;
while (sp > 0)
stack[--sp].keyring->last_used_at = ctx->now.tv_sec;
}
kleave(" = true");
return true;
}
/**
* keyring_search_aux - Search a keyring tree for a key matching some criteria
* @keyring_ref: A pointer to the keyring with possession indicator.
* @ctx: The keyring search context.
*
* Search the supplied keyring tree for a key that matches the criteria given.
* The root keyring and any linked keyrings must grant Search permission to the
* caller to be searchable and keys can only be found if they too grant Search
* to the caller. The possession flag on the root keyring pointer controls use
* of the possessor bits in permissions checking of the entire tree. In
* addition, the LSM gets to forbid keyring searches and key matches.
*
* The search is performed as a breadth-then-depth search up to the prescribed
* limit (KEYRING_SEARCH_MAX_DEPTH).
*
* Keys are matched to the type provided and are then filtered by the match
* function, which is given the description to use in any way it sees fit. The
* match function may use any attributes of a key that it wishes to to
* determine the match. Normally the match function from the key type would be
* used.
*
* RCU can be used to prevent the keyring key lists from disappearing without
* the need to take lots of locks.
*
* Returns a pointer to the found key and increments the key usage count if
* successful; -EAGAIN if no matching keys were found, or if expired or revoked
* keys were found; -ENOKEY if only negative keys were found; -ENOTDIR if the
* specified keyring wasn't a keyring.
*
* In the case of a successful return, the possession attribute from
* @keyring_ref is propagated to the returned key reference.
*/
key_ref_t keyring_search_aux(key_ref_t keyring_ref,
struct keyring_search_context *ctx)
{
struct key *keyring;
long err;
ctx->iterator = keyring_search_iterator;
ctx->possessed = is_key_possessed(keyring_ref);
ctx->result = ERR_PTR(-EAGAIN);
keyring = key_ref_to_ptr(keyring_ref);
key_check(keyring);
if (keyring->type != &key_type_keyring)
return ERR_PTR(-ENOTDIR);
if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM)) {
err = key_task_permission(keyring_ref, ctx->cred, KEY_SEARCH);
if (err < 0)
return ERR_PTR(err);
}
rcu_read_lock();
ctx->now = current_kernel_time();
if (search_nested_keyrings(keyring, ctx))
__key_get(key_ref_to_ptr(ctx->result));
[PATCH] keys: Discard key spinlock and use RCU for key payload The attached patch changes the key implementation in a number of ways: (1) It removes the spinlock from the key structure. (2) The key flags are now accessed using atomic bitops instead of write-locking the key spinlock and using C bitwise operators. The three instantiation flags are dealt with with the construction semaphore held during the request_key/instantiate/negate sequence, thus rendering the spinlock superfluous. The key flags are also now bit numbers not bit masks. (3) The key payload is now accessed using RCU. This permits the recursive keyring search algorithm to be simplified greatly since no locks need be taken other than the usual RCU preemption disablement. Searching now does not require any locks or semaphores to be held; merely that the starting keyring be pinned. (4) The keyring payload now includes an RCU head so that it can be disposed of by call_rcu(). This requires that the payload be copied on unlink to prevent introducing races in copy-down vs search-up. (5) The user key payload is now a structure with the data following it. It includes an RCU head like the keyring payload and for the same reason. It also contains a data length because the data length in the key may be changed on another CPU whilst an RCU protected read is in progress on the payload. This would then see the supposed RCU payload and the on-key data length getting out of sync. I'm tempted to drop the key's datalen entirely, except that it's used in conjunction with quota management and so is a little tricky to get rid of. (6) Update the keys documentation. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:00:49 +08:00
rcu_read_unlock();
return ctx->result;
}
/**
* keyring_search - Search the supplied keyring tree for a matching key
* @keyring: The root of the keyring tree to be searched.
* @type: The type of keyring we want to find.
* @description: The name of the keyring we want to find.
*
* As keyring_search_aux() above, but using the current task's credentials and
* type's default matching function and preferred search method.
*/
key_ref_t keyring_search(key_ref_t keyring,
struct key_type *type,
const char *description)
{
struct keyring_search_context ctx = {
.index_key.type = type,
.index_key.description = description,
.cred = current_cred(),
.match = type->match,
.match_data = description,
.flags = (type->def_lookup_type |
KEYRING_SEARCH_DO_STATE_CHECK),
};
if (!ctx.match)
[PATCH] Keys: Make request-key create an authorisation key The attached patch makes the following changes: (1) There's a new special key type called ".request_key_auth". This is an authorisation key for when one process requests a key and another process is started to construct it. This type of key cannot be created by the user; nor can it be requested by kernel services. Authorisation keys hold two references: (a) Each refers to a key being constructed. When the key being constructed is instantiated the authorisation key is revoked, rendering it of no further use. (b) The "authorising process". This is either: (i) the process that called request_key(), or: (ii) if the process that called request_key() itself had an authorisation key in its session keyring, then the authorising process referred to by that authorisation key will also be referred to by the new authorisation key. This means that the process that initiated a chain of key requests will authorise the lot of them, and will, by default, wind up with the keys obtained from them in its keyrings. (2) request_key() creates an authorisation key which is then passed to /sbin/request-key in as part of a new session keyring. (3) When request_key() is searching for a key to hand back to the caller, if it comes across an authorisation key in the session keyring of the calling process, it will also search the keyrings of the process specified therein and it will use the specified process's credentials (fsuid, fsgid, groups) to do that rather than the calling process's credentials. This allows a process started by /sbin/request-key to find keys belonging to the authorising process. (4) A key can be read, even if the process executing KEYCTL_READ doesn't have direct read or search permission if that key is contained within the keyrings of a process specified by an authorisation key found within the calling process's session keyring, and is searchable using the credentials of the authorising process. This allows a process started by /sbin/request-key to read keys belonging to the authorising process. (5) The magic KEY_SPEC_*_KEYRING key IDs when passed to KEYCTL_INSTANTIATE or KEYCTL_NEGATE will specify a keyring of the authorising process, rather than the process doing the instantiation. (6) One of the process keyrings can be nominated as the default to which request_key() should attach new keys if not otherwise specified. This is done with KEYCTL_SET_REQKEY_KEYRING and one of the KEY_REQKEY_DEFL_* constants. The current setting can also be read using this call. (7) request_key() is partially interruptible. If it is waiting for another process to finish constructing a key, it can be interrupted. This permits a request-key cycle to be broken without recourse to rebooting. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-Off-By: Benoit Boissinot <benoit.boissinot@ens-lyon.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:00:56 +08:00
return ERR_PTR(-ENOKEY);
return keyring_search_aux(keyring, &ctx);
}
EXPORT_SYMBOL(keyring_search);
/*
* Search the given keyring for a key that might be updated.
*
* The caller must guarantee that the keyring is a keyring and that the
* permission is granted to modify the keyring as no check is made here. The
* caller must also hold a lock on the keyring semaphore.
*
* Returns a pointer to the found key with usage count incremented if
* successful and returns NULL if not found. Revoked and invalidated keys are
* skipped over.
*
* If successful, the possession indicator is propagated from the keyring ref
* to the returned key reference.
*/
key_ref_t find_key_to_update(key_ref_t keyring_ref,
const struct keyring_index_key *index_key)
{
struct key *keyring, *key;
const void *object;
keyring = key_ref_to_ptr(keyring_ref);
kenter("{%d},{%s,%s}",
keyring->serial, index_key->type->name, index_key->description);
[PATCH] keys: Discard key spinlock and use RCU for key payload The attached patch changes the key implementation in a number of ways: (1) It removes the spinlock from the key structure. (2) The key flags are now accessed using atomic bitops instead of write-locking the key spinlock and using C bitwise operators. The three instantiation flags are dealt with with the construction semaphore held during the request_key/instantiate/negate sequence, thus rendering the spinlock superfluous. The key flags are also now bit numbers not bit masks. (3) The key payload is now accessed using RCU. This permits the recursive keyring search algorithm to be simplified greatly since no locks need be taken other than the usual RCU preemption disablement. Searching now does not require any locks or semaphores to be held; merely that the starting keyring be pinned. (4) The keyring payload now includes an RCU head so that it can be disposed of by call_rcu(). This requires that the payload be copied on unlink to prevent introducing races in copy-down vs search-up. (5) The user key payload is now a structure with the data following it. It includes an RCU head like the keyring payload and for the same reason. It also contains a data length because the data length in the key may be changed on another CPU whilst an RCU protected read is in progress on the payload. This would then see the supposed RCU payload and the on-key data length getting out of sync. I'm tempted to drop the key's datalen entirely, except that it's used in conjunction with quota management and so is a little tricky to get rid of. (6) Update the keys documentation. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:00:49 +08:00
object = assoc_array_find(&keyring->keys, &keyring_assoc_array_ops,
index_key);
if (object)
goto found;
kleave(" = NULL");
return NULL;
found:
key = keyring_ptr_to_key(object);
if (key->flags & ((1 << KEY_FLAG_INVALIDATED) |
(1 << KEY_FLAG_REVOKED))) {
kleave(" = NULL [x]");
return NULL;
}
__key_get(key);
kleave(" = {%d}", key->serial);
return make_key_ref(key, is_key_possessed(keyring_ref));
}
/*
* Find a keyring with the specified name.
*
* All named keyrings in the current user namespace are searched, provided they
* grant Search permission directly to the caller (unless this check is
* skipped). Keyrings whose usage points have reached zero or who have been
* revoked are skipped.
*
* Returns a pointer to the keyring with the keyring's refcount having being
* incremented on success. -ENOKEY is returned if a key could not be found.
*/
struct key *find_keyring_by_name(const char *name, bool skip_perm_check)
{
struct key *keyring;
int bucket;
if (!name)
KEYS: find_keyring_by_name() can gain access to a freed keyring find_keyring_by_name() can gain access to a keyring that has had its reference count reduced to zero, and is thus ready to be freed. This then allows the dead keyring to be brought back into use whilst it is being destroyed. The following timeline illustrates the process: |(cleaner) (user) | | free_user(user) sys_keyctl() | | | | key_put(user->session_keyring) keyctl_get_keyring_ID() | || //=> keyring->usage = 0 | | |schedule_work(&key_cleanup_task) lookup_user_key() | || | | kmem_cache_free(,user) | | . |[KEY_SPEC_USER_KEYRING] | . install_user_keyrings() | . || | key_cleanup() [<= worker_thread()] || | | || | [spin_lock(&key_serial_lock)] |[mutex_lock(&key_user_keyr..mutex)] | | || | atomic_read() == 0 || | |{ rb_ease(&key->serial_node,) } || | | || | [spin_unlock(&key_serial_lock)] |find_keyring_by_name() | | ||| | keyring_destroy(keyring) ||[read_lock(&keyring_name_lock)] | || ||| | |[write_lock(&keyring_name_lock)] ||atomic_inc(&keyring->usage) | |. ||| *** GET freeing keyring *** | |. ||[read_unlock(&keyring_name_lock)] | || || | |list_del() |[mutex_unlock(&key_user_k..mutex)] | || | | |[write_unlock(&keyring_name_lock)] ** INVALID keyring is returned ** | | . | kmem_cache_free(,keyring) . | . | atomic_dec(&keyring->usage) v *** DESTROYED *** TIME If CONFIG_SLUB_DEBUG=y then we may see the following message generated: ============================================================================= BUG key_jar: Poison overwritten ----------------------------------------------------------------------------- INFO: 0xffff880197a7e200-0xffff880197a7e200. First byte 0x6a instead of 0x6b INFO: Allocated in key_alloc+0x10b/0x35f age=25 cpu=1 pid=5086 INFO: Freed in key_cleanup+0xd0/0xd5 age=12 cpu=1 pid=10 INFO: Slab 0xffffea000592cb90 objects=16 used=2 fp=0xffff880197a7e200 flags=0x200000000000c3 INFO: Object 0xffff880197a7e200 @offset=512 fp=0xffff880197a7e300 Bytes b4 0xffff880197a7e1f0: 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZZZZZZZZZ Object 0xffff880197a7e200: 6a 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b jkkkkkkkkkkkkkkk Alternatively, we may see a system panic happen, such as: BUG: unable to handle kernel NULL pointer dereference at 0000000000000001 IP: [<ffffffff810e61a3>] kmem_cache_alloc+0x5b/0xe9 PGD 6b2b4067 PUD 6a80d067 PMD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/kernel/kexec_crash_loaded CPU 1 ... Pid: 31245, comm: su Not tainted 2.6.34-rc5-nofixed-nodebug #2 D2089/PRIMERGY RIP: 0010:[<ffffffff810e61a3>] [<ffffffff810e61a3>] kmem_cache_alloc+0x5b/0xe9 RSP: 0018:ffff88006af3bd98 EFLAGS: 00010002 RAX: 0000000000000000 RBX: 0000000000000001 RCX: ffff88007d19900b RDX: 0000000100000000 RSI: 00000000000080d0 RDI: ffffffff81828430 RBP: ffffffff81828430 R08: ffff88000a293750 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000100000 R12: 00000000000080d0 R13: 00000000000080d0 R14: 0000000000000296 R15: ffffffff810f20ce FS: 00007f97116bc700(0000) GS:ffff88000a280000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000001 CR3: 000000006a91c000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process su (pid: 31245, threadinfo ffff88006af3a000, task ffff8800374414c0) Stack: 0000000512e0958e 0000000000008000 ffff880037f8d180 0000000000000001 0000000000000000 0000000000008001 ffff88007d199000 ffffffff810f20ce 0000000000008000 ffff88006af3be48 0000000000000024 ffffffff810face3 Call Trace: [<ffffffff810f20ce>] ? get_empty_filp+0x70/0x12f [<ffffffff810face3>] ? do_filp_open+0x145/0x590 [<ffffffff810ce208>] ? tlb_finish_mmu+0x2a/0x33 [<ffffffff810ce43c>] ? unmap_region+0xd3/0xe2 [<ffffffff810e4393>] ? virt_to_head_page+0x9/0x2d [<ffffffff81103916>] ? alloc_fd+0x69/0x10e [<ffffffff810ef4ed>] ? do_sys_open+0x56/0xfc [<ffffffff81008a02>] ? system_call_fastpath+0x16/0x1b Code: 0f 1f 44 00 00 49 89 c6 fa 66 0f 1f 44 00 00 65 4c 8b 04 25 60 e8 00 00 48 8b 45 00 49 01 c0 49 8b 18 48 85 db 74 0d 48 63 45 18 <48> 8b 04 03 49 89 00 eb 14 4c 89 f9 83 ca ff 44 89 e6 48 89 ef RIP [<ffffffff810e61a3>] kmem_cache_alloc+0x5b/0xe9 This problem is that find_keyring_by_name does not confirm that the keyring is valid before accepting it. Skipping keyrings that have been reduced to a zero count seems the way to go. To this end, use atomic_inc_not_zero() to increment the usage count and skip the candidate keyring if that returns false. The following script _may_ cause the bug to happen, but there's no guarantee as the window of opportunity is small: #!/bin/sh LOOP=100000 USER=dummy_user /bin/su -c "exit;" $USER || { /usr/sbin/adduser -m $USER; add=1; } for ((i=0; i<LOOP; i++)) do /bin/su -c "echo '$i' > /dev/null" $USER done (( add == 1 )) && /usr/sbin/userdel -r $USER exit Note that the nominated user must not be in use. An alternative way of testing this may be: for ((i=0; i<100000; i++)) do keyctl session foo /bin/true || break done >&/dev/null as that uses a keyring named "foo" rather than relying on the user and user-session named keyrings. Reported-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Signed-off-by: David Howells <dhowells@redhat.com> Tested-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Acked-by: Serge Hallyn <serue@us.ibm.com> Signed-off-by: James Morris <jmorris@namei.org>
2010-04-30 21:32:13 +08:00
return ERR_PTR(-EINVAL);
bucket = keyring_hash(name);
read_lock(&keyring_name_lock);
if (keyring_name_hash[bucket].next) {
/* search this hash bucket for a keyring with a matching name
* that's readable and that hasn't been revoked */
list_for_each_entry(keyring,
&keyring_name_hash[bucket],
type_data.link
) {
if (!kuid_has_mapping(current_user_ns(), keyring->user->uid))
continue;
[PATCH] keys: Discard key spinlock and use RCU for key payload The attached patch changes the key implementation in a number of ways: (1) It removes the spinlock from the key structure. (2) The key flags are now accessed using atomic bitops instead of write-locking the key spinlock and using C bitwise operators. The three instantiation flags are dealt with with the construction semaphore held during the request_key/instantiate/negate sequence, thus rendering the spinlock superfluous. The key flags are also now bit numbers not bit masks. (3) The key payload is now accessed using RCU. This permits the recursive keyring search algorithm to be simplified greatly since no locks need be taken other than the usual RCU preemption disablement. Searching now does not require any locks or semaphores to be held; merely that the starting keyring be pinned. (4) The keyring payload now includes an RCU head so that it can be disposed of by call_rcu(). This requires that the payload be copied on unlink to prevent introducing races in copy-down vs search-up. (5) The user key payload is now a structure with the data following it. It includes an RCU head like the keyring payload and for the same reason. It also contains a data length because the data length in the key may be changed on another CPU whilst an RCU protected read is in progress on the payload. This would then see the supposed RCU payload and the on-key data length getting out of sync. I'm tempted to drop the key's datalen entirely, except that it's used in conjunction with quota management and so is a little tricky to get rid of. (6) Update the keys documentation. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:00:49 +08:00
if (test_bit(KEY_FLAG_REVOKED, &keyring->flags))
continue;
if (strcmp(keyring->description, name) != 0)
continue;
if (!skip_perm_check &&
key_permission(make_key_ref(keyring, 0),
KEY_SEARCH) < 0)
continue;
KEYS: find_keyring_by_name() can gain access to a freed keyring find_keyring_by_name() can gain access to a keyring that has had its reference count reduced to zero, and is thus ready to be freed. This then allows the dead keyring to be brought back into use whilst it is being destroyed. The following timeline illustrates the process: |(cleaner) (user) | | free_user(user) sys_keyctl() | | | | key_put(user->session_keyring) keyctl_get_keyring_ID() | || //=> keyring->usage = 0 | | |schedule_work(&key_cleanup_task) lookup_user_key() | || | | kmem_cache_free(,user) | | . |[KEY_SPEC_USER_KEYRING] | . install_user_keyrings() | . || | key_cleanup() [<= worker_thread()] || | | || | [spin_lock(&key_serial_lock)] |[mutex_lock(&key_user_keyr..mutex)] | | || | atomic_read() == 0 || | |{ rb_ease(&key->serial_node,) } || | | || | [spin_unlock(&key_serial_lock)] |find_keyring_by_name() | | ||| | keyring_destroy(keyring) ||[read_lock(&keyring_name_lock)] | || ||| | |[write_lock(&keyring_name_lock)] ||atomic_inc(&keyring->usage) | |. ||| *** GET freeing keyring *** | |. ||[read_unlock(&keyring_name_lock)] | || || | |list_del() |[mutex_unlock(&key_user_k..mutex)] | || | | |[write_unlock(&keyring_name_lock)] ** INVALID keyring is returned ** | | . | kmem_cache_free(,keyring) . | . | atomic_dec(&keyring->usage) v *** DESTROYED *** TIME If CONFIG_SLUB_DEBUG=y then we may see the following message generated: ============================================================================= BUG key_jar: Poison overwritten ----------------------------------------------------------------------------- INFO: 0xffff880197a7e200-0xffff880197a7e200. First byte 0x6a instead of 0x6b INFO: Allocated in key_alloc+0x10b/0x35f age=25 cpu=1 pid=5086 INFO: Freed in key_cleanup+0xd0/0xd5 age=12 cpu=1 pid=10 INFO: Slab 0xffffea000592cb90 objects=16 used=2 fp=0xffff880197a7e200 flags=0x200000000000c3 INFO: Object 0xffff880197a7e200 @offset=512 fp=0xffff880197a7e300 Bytes b4 0xffff880197a7e1f0: 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZZZZZZZZZ Object 0xffff880197a7e200: 6a 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b jkkkkkkkkkkkkkkk Alternatively, we may see a system panic happen, such as: BUG: unable to handle kernel NULL pointer dereference at 0000000000000001 IP: [<ffffffff810e61a3>] kmem_cache_alloc+0x5b/0xe9 PGD 6b2b4067 PUD 6a80d067 PMD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/kernel/kexec_crash_loaded CPU 1 ... Pid: 31245, comm: su Not tainted 2.6.34-rc5-nofixed-nodebug #2 D2089/PRIMERGY RIP: 0010:[<ffffffff810e61a3>] [<ffffffff810e61a3>] kmem_cache_alloc+0x5b/0xe9 RSP: 0018:ffff88006af3bd98 EFLAGS: 00010002 RAX: 0000000000000000 RBX: 0000000000000001 RCX: ffff88007d19900b RDX: 0000000100000000 RSI: 00000000000080d0 RDI: ffffffff81828430 RBP: ffffffff81828430 R08: ffff88000a293750 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000100000 R12: 00000000000080d0 R13: 00000000000080d0 R14: 0000000000000296 R15: ffffffff810f20ce FS: 00007f97116bc700(0000) GS:ffff88000a280000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000001 CR3: 000000006a91c000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process su (pid: 31245, threadinfo ffff88006af3a000, task ffff8800374414c0) Stack: 0000000512e0958e 0000000000008000 ffff880037f8d180 0000000000000001 0000000000000000 0000000000008001 ffff88007d199000 ffffffff810f20ce 0000000000008000 ffff88006af3be48 0000000000000024 ffffffff810face3 Call Trace: [<ffffffff810f20ce>] ? get_empty_filp+0x70/0x12f [<ffffffff810face3>] ? do_filp_open+0x145/0x590 [<ffffffff810ce208>] ? tlb_finish_mmu+0x2a/0x33 [<ffffffff810ce43c>] ? unmap_region+0xd3/0xe2 [<ffffffff810e4393>] ? virt_to_head_page+0x9/0x2d [<ffffffff81103916>] ? alloc_fd+0x69/0x10e [<ffffffff810ef4ed>] ? do_sys_open+0x56/0xfc [<ffffffff81008a02>] ? system_call_fastpath+0x16/0x1b Code: 0f 1f 44 00 00 49 89 c6 fa 66 0f 1f 44 00 00 65 4c 8b 04 25 60 e8 00 00 48 8b 45 00 49 01 c0 49 8b 18 48 85 db 74 0d 48 63 45 18 <48> 8b 04 03 49 89 00 eb 14 4c 89 f9 83 ca ff 44 89 e6 48 89 ef RIP [<ffffffff810e61a3>] kmem_cache_alloc+0x5b/0xe9 This problem is that find_keyring_by_name does not confirm that the keyring is valid before accepting it. Skipping keyrings that have been reduced to a zero count seems the way to go. To this end, use atomic_inc_not_zero() to increment the usage count and skip the candidate keyring if that returns false. The following script _may_ cause the bug to happen, but there's no guarantee as the window of opportunity is small: #!/bin/sh LOOP=100000 USER=dummy_user /bin/su -c "exit;" $USER || { /usr/sbin/adduser -m $USER; add=1; } for ((i=0; i<LOOP; i++)) do /bin/su -c "echo '$i' > /dev/null" $USER done (( add == 1 )) && /usr/sbin/userdel -r $USER exit Note that the nominated user must not be in use. An alternative way of testing this may be: for ((i=0; i<100000; i++)) do keyctl session foo /bin/true || break done >&/dev/null as that uses a keyring named "foo" rather than relying on the user and user-session named keyrings. Reported-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Signed-off-by: David Howells <dhowells@redhat.com> Tested-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Acked-by: Serge Hallyn <serue@us.ibm.com> Signed-off-by: James Morris <jmorris@namei.org>
2010-04-30 21:32:13 +08:00
/* we've got a match but we might end up racing with
* key_cleanup() if the keyring is currently 'dead'
* (ie. it has a zero usage count) */
if (!atomic_inc_not_zero(&keyring->usage))
continue;
KEYS: Do LRU discard in full keyrings Do an LRU discard in keyrings that are full rather than returning ENFILE. To perform this, a time_t is added to the key struct and updated by the creation of a link to a key and by a key being found as the result of a search. At the completion of a successful search, the keyrings in the path between the root of the search and the first found link to it also have their last-used times updated. Note that discarding a link to a key from a keyring does not necessarily destroy the key as there may be references held by other places. An alternate discard method that might suffice is to perform FIFO discard from the keyring, using the spare 2-byte hole in the keylist header as the index of the next link to be discarded. This is useful when using a keyring as a cache for DNS results or foreign filesystem IDs. This can be tested by the following. As root do: echo 1000 >/proc/sys/kernel/keys/root_maxkeys kr=`keyctl newring foo @s` for ((i=0; i<2000; i++)); do keyctl add user a$i a $kr; done Without this patch ENFILE should be reported when the keyring fills up. With this patch, the keyring discards keys in an LRU fashion. Note that the stored LRU time has a granularity of 1s. After doing this, /proc/key-users can be observed and should show that most of the 2000 keys have been discarded: [root@andromeda ~]# cat /proc/key-users 0: 517 516/516 513/1000 5249/20000 The "513/1000" here is the number of quota-accounted keys present for this user out of the maximum permitted. In /proc/keys, the keyring shows the number of keys it has and the number of slots it has allocated: [root@andromeda ~]# grep foo /proc/keys 200c64c4 I--Q-- 1 perm 3b3f0000 0 0 keyring foo: 509/509 The maximum is (PAGE_SIZE - header) / key pointer size. That's typically 509 on a 64-bit system and 1020 on a 32-bit system. Signed-off-by: David Howells <dhowells@redhat.com>
2012-05-11 17:56:56 +08:00
keyring->last_used_at = current_kernel_time().tv_sec;
KEYS: find_keyring_by_name() can gain access to a freed keyring find_keyring_by_name() can gain access to a keyring that has had its reference count reduced to zero, and is thus ready to be freed. This then allows the dead keyring to be brought back into use whilst it is being destroyed. The following timeline illustrates the process: |(cleaner) (user) | | free_user(user) sys_keyctl() | | | | key_put(user->session_keyring) keyctl_get_keyring_ID() | || //=> keyring->usage = 0 | | |schedule_work(&key_cleanup_task) lookup_user_key() | || | | kmem_cache_free(,user) | | . |[KEY_SPEC_USER_KEYRING] | . install_user_keyrings() | . || | key_cleanup() [<= worker_thread()] || | | || | [spin_lock(&key_serial_lock)] |[mutex_lock(&key_user_keyr..mutex)] | | || | atomic_read() == 0 || | |{ rb_ease(&key->serial_node,) } || | | || | [spin_unlock(&key_serial_lock)] |find_keyring_by_name() | | ||| | keyring_destroy(keyring) ||[read_lock(&keyring_name_lock)] | || ||| | |[write_lock(&keyring_name_lock)] ||atomic_inc(&keyring->usage) | |. ||| *** GET freeing keyring *** | |. ||[read_unlock(&keyring_name_lock)] | || || | |list_del() |[mutex_unlock(&key_user_k..mutex)] | || | | |[write_unlock(&keyring_name_lock)] ** INVALID keyring is returned ** | | . | kmem_cache_free(,keyring) . | . | atomic_dec(&keyring->usage) v *** DESTROYED *** TIME If CONFIG_SLUB_DEBUG=y then we may see the following message generated: ============================================================================= BUG key_jar: Poison overwritten ----------------------------------------------------------------------------- INFO: 0xffff880197a7e200-0xffff880197a7e200. First byte 0x6a instead of 0x6b INFO: Allocated in key_alloc+0x10b/0x35f age=25 cpu=1 pid=5086 INFO: Freed in key_cleanup+0xd0/0xd5 age=12 cpu=1 pid=10 INFO: Slab 0xffffea000592cb90 objects=16 used=2 fp=0xffff880197a7e200 flags=0x200000000000c3 INFO: Object 0xffff880197a7e200 @offset=512 fp=0xffff880197a7e300 Bytes b4 0xffff880197a7e1f0: 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZZZZZZZZZ Object 0xffff880197a7e200: 6a 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b jkkkkkkkkkkkkkkk Alternatively, we may see a system panic happen, such as: BUG: unable to handle kernel NULL pointer dereference at 0000000000000001 IP: [<ffffffff810e61a3>] kmem_cache_alloc+0x5b/0xe9 PGD 6b2b4067 PUD 6a80d067 PMD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/kernel/kexec_crash_loaded CPU 1 ... Pid: 31245, comm: su Not tainted 2.6.34-rc5-nofixed-nodebug #2 D2089/PRIMERGY RIP: 0010:[<ffffffff810e61a3>] [<ffffffff810e61a3>] kmem_cache_alloc+0x5b/0xe9 RSP: 0018:ffff88006af3bd98 EFLAGS: 00010002 RAX: 0000000000000000 RBX: 0000000000000001 RCX: ffff88007d19900b RDX: 0000000100000000 RSI: 00000000000080d0 RDI: ffffffff81828430 RBP: ffffffff81828430 R08: ffff88000a293750 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000100000 R12: 00000000000080d0 R13: 00000000000080d0 R14: 0000000000000296 R15: ffffffff810f20ce FS: 00007f97116bc700(0000) GS:ffff88000a280000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000001 CR3: 000000006a91c000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process su (pid: 31245, threadinfo ffff88006af3a000, task ffff8800374414c0) Stack: 0000000512e0958e 0000000000008000 ffff880037f8d180 0000000000000001 0000000000000000 0000000000008001 ffff88007d199000 ffffffff810f20ce 0000000000008000 ffff88006af3be48 0000000000000024 ffffffff810face3 Call Trace: [<ffffffff810f20ce>] ? get_empty_filp+0x70/0x12f [<ffffffff810face3>] ? do_filp_open+0x145/0x590 [<ffffffff810ce208>] ? tlb_finish_mmu+0x2a/0x33 [<ffffffff810ce43c>] ? unmap_region+0xd3/0xe2 [<ffffffff810e4393>] ? virt_to_head_page+0x9/0x2d [<ffffffff81103916>] ? alloc_fd+0x69/0x10e [<ffffffff810ef4ed>] ? do_sys_open+0x56/0xfc [<ffffffff81008a02>] ? system_call_fastpath+0x16/0x1b Code: 0f 1f 44 00 00 49 89 c6 fa 66 0f 1f 44 00 00 65 4c 8b 04 25 60 e8 00 00 48 8b 45 00 49 01 c0 49 8b 18 48 85 db 74 0d 48 63 45 18 <48> 8b 04 03 49 89 00 eb 14 4c 89 f9 83 ca ff 44 89 e6 48 89 ef RIP [<ffffffff810e61a3>] kmem_cache_alloc+0x5b/0xe9 This problem is that find_keyring_by_name does not confirm that the keyring is valid before accepting it. Skipping keyrings that have been reduced to a zero count seems the way to go. To this end, use atomic_inc_not_zero() to increment the usage count and skip the candidate keyring if that returns false. The following script _may_ cause the bug to happen, but there's no guarantee as the window of opportunity is small: #!/bin/sh LOOP=100000 USER=dummy_user /bin/su -c "exit;" $USER || { /usr/sbin/adduser -m $USER; add=1; } for ((i=0; i<LOOP; i++)) do /bin/su -c "echo '$i' > /dev/null" $USER done (( add == 1 )) && /usr/sbin/userdel -r $USER exit Note that the nominated user must not be in use. An alternative way of testing this may be: for ((i=0; i<100000; i++)) do keyctl session foo /bin/true || break done >&/dev/null as that uses a keyring named "foo" rather than relying on the user and user-session named keyrings. Reported-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Signed-off-by: David Howells <dhowells@redhat.com> Tested-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Acked-by: Serge Hallyn <serue@us.ibm.com> Signed-off-by: James Morris <jmorris@namei.org>
2010-04-30 21:32:13 +08:00
goto out;
}
}
keyring = ERR_PTR(-ENOKEY);
KEYS: find_keyring_by_name() can gain access to a freed keyring find_keyring_by_name() can gain access to a keyring that has had its reference count reduced to zero, and is thus ready to be freed. This then allows the dead keyring to be brought back into use whilst it is being destroyed. The following timeline illustrates the process: |(cleaner) (user) | | free_user(user) sys_keyctl() | | | | key_put(user->session_keyring) keyctl_get_keyring_ID() | || //=> keyring->usage = 0 | | |schedule_work(&key_cleanup_task) lookup_user_key() | || | | kmem_cache_free(,user) | | . |[KEY_SPEC_USER_KEYRING] | . install_user_keyrings() | . || | key_cleanup() [<= worker_thread()] || | | || | [spin_lock(&key_serial_lock)] |[mutex_lock(&key_user_keyr..mutex)] | | || | atomic_read() == 0 || | |{ rb_ease(&key->serial_node,) } || | | || | [spin_unlock(&key_serial_lock)] |find_keyring_by_name() | | ||| | keyring_destroy(keyring) ||[read_lock(&keyring_name_lock)] | || ||| | |[write_lock(&keyring_name_lock)] ||atomic_inc(&keyring->usage) | |. ||| *** GET freeing keyring *** | |. ||[read_unlock(&keyring_name_lock)] | || || | |list_del() |[mutex_unlock(&key_user_k..mutex)] | || | | |[write_unlock(&keyring_name_lock)] ** INVALID keyring is returned ** | | . | kmem_cache_free(,keyring) . | . | atomic_dec(&keyring->usage) v *** DESTROYED *** TIME If CONFIG_SLUB_DEBUG=y then we may see the following message generated: ============================================================================= BUG key_jar: Poison overwritten ----------------------------------------------------------------------------- INFO: 0xffff880197a7e200-0xffff880197a7e200. First byte 0x6a instead of 0x6b INFO: Allocated in key_alloc+0x10b/0x35f age=25 cpu=1 pid=5086 INFO: Freed in key_cleanup+0xd0/0xd5 age=12 cpu=1 pid=10 INFO: Slab 0xffffea000592cb90 objects=16 used=2 fp=0xffff880197a7e200 flags=0x200000000000c3 INFO: Object 0xffff880197a7e200 @offset=512 fp=0xffff880197a7e300 Bytes b4 0xffff880197a7e1f0: 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZZZZZZZZZ Object 0xffff880197a7e200: 6a 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b jkkkkkkkkkkkkkkk Alternatively, we may see a system panic happen, such as: BUG: unable to handle kernel NULL pointer dereference at 0000000000000001 IP: [<ffffffff810e61a3>] kmem_cache_alloc+0x5b/0xe9 PGD 6b2b4067 PUD 6a80d067 PMD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/kernel/kexec_crash_loaded CPU 1 ... Pid: 31245, comm: su Not tainted 2.6.34-rc5-nofixed-nodebug #2 D2089/PRIMERGY RIP: 0010:[<ffffffff810e61a3>] [<ffffffff810e61a3>] kmem_cache_alloc+0x5b/0xe9 RSP: 0018:ffff88006af3bd98 EFLAGS: 00010002 RAX: 0000000000000000 RBX: 0000000000000001 RCX: ffff88007d19900b RDX: 0000000100000000 RSI: 00000000000080d0 RDI: ffffffff81828430 RBP: ffffffff81828430 R08: ffff88000a293750 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000100000 R12: 00000000000080d0 R13: 00000000000080d0 R14: 0000000000000296 R15: ffffffff810f20ce FS: 00007f97116bc700(0000) GS:ffff88000a280000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000001 CR3: 000000006a91c000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process su (pid: 31245, threadinfo ffff88006af3a000, task ffff8800374414c0) Stack: 0000000512e0958e 0000000000008000 ffff880037f8d180 0000000000000001 0000000000000000 0000000000008001 ffff88007d199000 ffffffff810f20ce 0000000000008000 ffff88006af3be48 0000000000000024 ffffffff810face3 Call Trace: [<ffffffff810f20ce>] ? get_empty_filp+0x70/0x12f [<ffffffff810face3>] ? do_filp_open+0x145/0x590 [<ffffffff810ce208>] ? tlb_finish_mmu+0x2a/0x33 [<ffffffff810ce43c>] ? unmap_region+0xd3/0xe2 [<ffffffff810e4393>] ? virt_to_head_page+0x9/0x2d [<ffffffff81103916>] ? alloc_fd+0x69/0x10e [<ffffffff810ef4ed>] ? do_sys_open+0x56/0xfc [<ffffffff81008a02>] ? system_call_fastpath+0x16/0x1b Code: 0f 1f 44 00 00 49 89 c6 fa 66 0f 1f 44 00 00 65 4c 8b 04 25 60 e8 00 00 48 8b 45 00 49 01 c0 49 8b 18 48 85 db 74 0d 48 63 45 18 <48> 8b 04 03 49 89 00 eb 14 4c 89 f9 83 ca ff 44 89 e6 48 89 ef RIP [<ffffffff810e61a3>] kmem_cache_alloc+0x5b/0xe9 This problem is that find_keyring_by_name does not confirm that the keyring is valid before accepting it. Skipping keyrings that have been reduced to a zero count seems the way to go. To this end, use atomic_inc_not_zero() to increment the usage count and skip the candidate keyring if that returns false. The following script _may_ cause the bug to happen, but there's no guarantee as the window of opportunity is small: #!/bin/sh LOOP=100000 USER=dummy_user /bin/su -c "exit;" $USER || { /usr/sbin/adduser -m $USER; add=1; } for ((i=0; i<LOOP; i++)) do /bin/su -c "echo '$i' > /dev/null" $USER done (( add == 1 )) && /usr/sbin/userdel -r $USER exit Note that the nominated user must not be in use. An alternative way of testing this may be: for ((i=0; i<100000; i++)) do keyctl session foo /bin/true || break done >&/dev/null as that uses a keyring named "foo" rather than relying on the user and user-session named keyrings. Reported-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Signed-off-by: David Howells <dhowells@redhat.com> Tested-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Acked-by: Serge Hallyn <serue@us.ibm.com> Signed-off-by: James Morris <jmorris@namei.org>
2010-04-30 21:32:13 +08:00
out:
read_unlock(&keyring_name_lock);
return keyring;
}
static int keyring_detect_cycle_iterator(const void *object,
void *iterator_data)
{
struct keyring_search_context *ctx = iterator_data;
const struct key *key = keyring_ptr_to_key(object);
kenter("{%d}", key->serial);
BUG_ON(key != ctx->match_data);
ctx->result = ERR_PTR(-EDEADLK);
return 1;
}
/*
* See if a cycle will will be created by inserting acyclic tree B in acyclic
* tree A at the topmost level (ie: as a direct child of A).
*
* Since we are adding B to A at the top level, checking for cycles should just
* be a matter of seeing if node A is somewhere in tree B.
*/
static int keyring_detect_cycle(struct key *A, struct key *B)
{
struct keyring_search_context ctx = {
.index_key = A->index_key,
.match_data = A,
.iterator = keyring_detect_cycle_iterator,
.flags = (KEYRING_SEARCH_LOOKUP_DIRECT |
KEYRING_SEARCH_NO_STATE_CHECK |
KEYRING_SEARCH_NO_UPDATE_TIME |
KEYRING_SEARCH_NO_CHECK_PERM |
KEYRING_SEARCH_DETECT_TOO_DEEP),
};
[PATCH] keys: Discard key spinlock and use RCU for key payload The attached patch changes the key implementation in a number of ways: (1) It removes the spinlock from the key structure. (2) The key flags are now accessed using atomic bitops instead of write-locking the key spinlock and using C bitwise operators. The three instantiation flags are dealt with with the construction semaphore held during the request_key/instantiate/negate sequence, thus rendering the spinlock superfluous. The key flags are also now bit numbers not bit masks. (3) The key payload is now accessed using RCU. This permits the recursive keyring search algorithm to be simplified greatly since no locks need be taken other than the usual RCU preemption disablement. Searching now does not require any locks or semaphores to be held; merely that the starting keyring be pinned. (4) The keyring payload now includes an RCU head so that it can be disposed of by call_rcu(). This requires that the payload be copied on unlink to prevent introducing races in copy-down vs search-up. (5) The user key payload is now a structure with the data following it. It includes an RCU head like the keyring payload and for the same reason. It also contains a data length because the data length in the key may be changed on another CPU whilst an RCU protected read is in progress on the payload. This would then see the supposed RCU payload and the on-key data length getting out of sync. I'm tempted to drop the key's datalen entirely, except that it's used in conjunction with quota management and so is a little tricky to get rid of. (6) Update the keys documentation. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:00:49 +08:00
rcu_read_lock();
search_nested_keyrings(B, &ctx);
[PATCH] keys: Discard key spinlock and use RCU for key payload The attached patch changes the key implementation in a number of ways: (1) It removes the spinlock from the key structure. (2) The key flags are now accessed using atomic bitops instead of write-locking the key spinlock and using C bitwise operators. The three instantiation flags are dealt with with the construction semaphore held during the request_key/instantiate/negate sequence, thus rendering the spinlock superfluous. The key flags are also now bit numbers not bit masks. (3) The key payload is now accessed using RCU. This permits the recursive keyring search algorithm to be simplified greatly since no locks need be taken other than the usual RCU preemption disablement. Searching now does not require any locks or semaphores to be held; merely that the starting keyring be pinned. (4) The keyring payload now includes an RCU head so that it can be disposed of by call_rcu(). This requires that the payload be copied on unlink to prevent introducing races in copy-down vs search-up. (5) The user key payload is now a structure with the data following it. It includes an RCU head like the keyring payload and for the same reason. It also contains a data length because the data length in the key may be changed on another CPU whilst an RCU protected read is in progress on the payload. This would then see the supposed RCU payload and the on-key data length getting out of sync. I'm tempted to drop the key's datalen entirely, except that it's used in conjunction with quota management and so is a little tricky to get rid of. (6) Update the keys documentation. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:00:49 +08:00
rcu_read_unlock();
return PTR_ERR(ctx.result) == -EAGAIN ? 0 : PTR_ERR(ctx.result);
}
/*
* Preallocate memory so that a key can be linked into to a keyring.
*/
int __key_link_begin(struct key *keyring,
const struct keyring_index_key *index_key,
struct assoc_array_edit **_edit)
__acquires(&keyring->sem)
__acquires(&keyring_serialise_link_sem)
{
struct assoc_array_edit *edit;
int ret;
kenter("%d,%s,%s,",
keyring->serial, index_key->type->name, index_key->description);
BUG_ON(index_key->desc_len == 0);
if (keyring->type != &key_type_keyring)
return -ENOTDIR;
down_write(&keyring->sem);
ret = -EKEYREVOKED;
if (test_bit(KEY_FLAG_REVOKED, &keyring->flags))
goto error_krsem;
/* serialise link/link calls to prevent parallel calls causing a cycle
* when linking two keyring in opposite orders */
if (index_key->type == &key_type_keyring)
down_write(&keyring_serialise_link_sem);
/* Create an edit script that will insert/replace the key in the
* keyring tree.
*/
edit = assoc_array_insert(&keyring->keys,
&keyring_assoc_array_ops,
index_key,
NULL);
if (IS_ERR(edit)) {
ret = PTR_ERR(edit);
goto error_sem;
}
/* If we're not replacing a link in-place then we're going to need some
* extra quota.
*/
if (!edit->dead_leaf) {
ret = key_payload_reserve(keyring,
keyring->datalen + KEYQUOTA_LINK_BYTES);
if (ret < 0)
goto error_cancel;
}
*_edit = edit;
kleave(" = 0");
return 0;
error_cancel:
assoc_array_cancel_edit(edit);
error_sem:
if (index_key->type == &key_type_keyring)
up_write(&keyring_serialise_link_sem);
error_krsem:
up_write(&keyring->sem);
kleave(" = %d", ret);
return ret;
}
/*
* Check already instantiated keys aren't going to be a problem.
*
* The caller must have called __key_link_begin(). Don't need to call this for
* keys that were created since __key_link_begin() was called.
*/
int __key_link_check_live_key(struct key *keyring, struct key *key)
{
if (key->type == &key_type_keyring)
/* check that we aren't going to create a cycle by linking one
* keyring to another */
return keyring_detect_cycle(keyring, key);
return 0;
}
/*
* Link a key into to a keyring.
*
* Must be called with __key_link_begin() having being called. Discards any
* already extant link to matching key if there is one, so that each keyring
* holds at most one link to any given key of a particular type+description
* combination.
*/
void __key_link(struct key *key, struct assoc_array_edit **_edit)
{
__key_get(key);
assoc_array_insert_set_object(*_edit, keyring_key_to_ptr(key));
assoc_array_apply_edit(*_edit);
*_edit = NULL;
}
/*
* Finish linking a key into to a keyring.
*
* Must be called with __key_link_begin() having being called.
*/
void __key_link_end(struct key *keyring,
const struct keyring_index_key *index_key,
struct assoc_array_edit *edit)
__releases(&keyring->sem)
__releases(&keyring_serialise_link_sem)
{
BUG_ON(index_key->type == NULL);
kenter("%d,%s,", keyring->serial, index_key->type->name);
if (index_key->type == &key_type_keyring)
up_write(&keyring_serialise_link_sem);
if (edit && !edit->dead_leaf) {
key_payload_reserve(keyring,
keyring->datalen - KEYQUOTA_LINK_BYTES);
assoc_array_cancel_edit(edit);
}
up_write(&keyring->sem);
}
/**
* key_link - Link a key to a keyring
* @keyring: The keyring to make the link in.
* @key: The key to link to.
*
* Make a link in a keyring to a key, such that the keyring holds a reference
* on that key and the key can potentially be found by searching that keyring.
*
* This function will write-lock the keyring's semaphore and will consume some
* of the user's key data quota to hold the link.
*
* Returns 0 if successful, -ENOTDIR if the keyring isn't a keyring,
* -EKEYREVOKED if the keyring has been revoked, -ENFILE if the keyring is
* full, -EDQUOT if there is insufficient key data quota remaining to add
* another link or -ENOMEM if there's insufficient memory.
*
* It is assumed that the caller has checked that it is permitted for a link to
* be made (the keyring should have Write permission and the key Link
* permission).
*/
int key_link(struct key *keyring, struct key *key)
{
struct assoc_array_edit *edit;
int ret;
kenter("{%d,%d}", keyring->serial, atomic_read(&keyring->usage));
key_check(keyring);
key_check(key);
if (test_bit(KEY_FLAG_TRUSTED_ONLY, &keyring->flags) &&
!test_bit(KEY_FLAG_TRUSTED, &key->flags))
return -EPERM;
ret = __key_link_begin(keyring, &key->index_key, &edit);
if (ret == 0) {
kdebug("begun {%d,%d}", keyring->serial, atomic_read(&keyring->usage));
ret = __key_link_check_live_key(keyring, key);
if (ret == 0)
__key_link(key, &edit);
__key_link_end(keyring, &key->index_key, edit);
}
kleave(" = %d {%d,%d}", ret, keyring->serial, atomic_read(&keyring->usage));
return ret;
}
EXPORT_SYMBOL(key_link);
/**
* key_unlink - Unlink the first link to a key from a keyring.
* @keyring: The keyring to remove the link from.
* @key: The key the link is to.
*
* Remove a link from a keyring to a key.
*
* This function will write-lock the keyring's semaphore.
*
* Returns 0 if successful, -ENOTDIR if the keyring isn't a keyring, -ENOENT if
* the key isn't linked to by the keyring or -ENOMEM if there's insufficient
* memory.
*
* It is assumed that the caller has checked that it is permitted for a link to
* be removed (the keyring should have Write permission; no permissions are
* required on the key).
*/
int key_unlink(struct key *keyring, struct key *key)
{
struct assoc_array_edit *edit;
int ret;
key_check(keyring);
key_check(key);
if (keyring->type != &key_type_keyring)
return -ENOTDIR;
down_write(&keyring->sem);
edit = assoc_array_delete(&keyring->keys, &keyring_assoc_array_ops,
&key->index_key);
if (IS_ERR(edit)) {
ret = PTR_ERR(edit);
goto error;
}
ret = -ENOENT;
if (edit == NULL)
goto error;
assoc_array_apply_edit(edit);
key_payload_reserve(keyring, keyring->datalen - KEYQUOTA_LINK_BYTES);
ret = 0;
[PATCH] keys: Discard key spinlock and use RCU for key payload The attached patch changes the key implementation in a number of ways: (1) It removes the spinlock from the key structure. (2) The key flags are now accessed using atomic bitops instead of write-locking the key spinlock and using C bitwise operators. The three instantiation flags are dealt with with the construction semaphore held during the request_key/instantiate/negate sequence, thus rendering the spinlock superfluous. The key flags are also now bit numbers not bit masks. (3) The key payload is now accessed using RCU. This permits the recursive keyring search algorithm to be simplified greatly since no locks need be taken other than the usual RCU preemption disablement. Searching now does not require any locks or semaphores to be held; merely that the starting keyring be pinned. (4) The keyring payload now includes an RCU head so that it can be disposed of by call_rcu(). This requires that the payload be copied on unlink to prevent introducing races in copy-down vs search-up. (5) The user key payload is now a structure with the data following it. It includes an RCU head like the keyring payload and for the same reason. It also contains a data length because the data length in the key may be changed on another CPU whilst an RCU protected read is in progress on the payload. This would then see the supposed RCU payload and the on-key data length getting out of sync. I'm tempted to drop the key's datalen entirely, except that it's used in conjunction with quota management and so is a little tricky to get rid of. (6) Update the keys documentation. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:00:49 +08:00
error:
up_write(&keyring->sem);
return ret;
}
EXPORT_SYMBOL(key_unlink);
/**
* keyring_clear - Clear a keyring
* @keyring: The keyring to clear.
*
* Clear the contents of the specified keyring.
*
* Returns 0 if successful or -ENOTDIR if the keyring isn't a keyring.
*/
int keyring_clear(struct key *keyring)
{
struct assoc_array_edit *edit;
[PATCH] keys: Discard key spinlock and use RCU for key payload The attached patch changes the key implementation in a number of ways: (1) It removes the spinlock from the key structure. (2) The key flags are now accessed using atomic bitops instead of write-locking the key spinlock and using C bitwise operators. The three instantiation flags are dealt with with the construction semaphore held during the request_key/instantiate/negate sequence, thus rendering the spinlock superfluous. The key flags are also now bit numbers not bit masks. (3) The key payload is now accessed using RCU. This permits the recursive keyring search algorithm to be simplified greatly since no locks need be taken other than the usual RCU preemption disablement. Searching now does not require any locks or semaphores to be held; merely that the starting keyring be pinned. (4) The keyring payload now includes an RCU head so that it can be disposed of by call_rcu(). This requires that the payload be copied on unlink to prevent introducing races in copy-down vs search-up. (5) The user key payload is now a structure with the data following it. It includes an RCU head like the keyring payload and for the same reason. It also contains a data length because the data length in the key may be changed on another CPU whilst an RCU protected read is in progress on the payload. This would then see the supposed RCU payload and the on-key data length getting out of sync. I'm tempted to drop the key's datalen entirely, except that it's used in conjunction with quota management and so is a little tricky to get rid of. (6) Update the keys documentation. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:00:49 +08:00
int ret;
if (keyring->type != &key_type_keyring)
return -ENOTDIR;
down_write(&keyring->sem);
edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops);
if (IS_ERR(edit)) {
ret = PTR_ERR(edit);
} else {
if (edit)
assoc_array_apply_edit(edit);
key_payload_reserve(keyring, 0);
ret = 0;
}
up_write(&keyring->sem);
return ret;
}
EXPORT_SYMBOL(keyring_clear);
/*
* Dispose of the links from a revoked keyring.
*
* This is called with the key sem write-locked.
*/
static void keyring_revoke(struct key *keyring)
{
struct assoc_array_edit *edit;
edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops);
if (!IS_ERR(edit)) {
if (edit)
assoc_array_apply_edit(edit);
key_payload_reserve(keyring, 0);
}
}
static bool keyring_gc_select_iterator(void *object, void *iterator_data)
{
struct key *key = keyring_ptr_to_key(object);
time_t *limit = iterator_data;
if (key_is_dead(key, *limit))
return false;
key_get(key);
return true;
}
static int keyring_gc_check_iterator(const void *object, void *iterator_data)
{
const struct key *key = keyring_ptr_to_key(object);
time_t *limit = iterator_data;
key_check(key);
return key_is_dead(key, *limit);
}
/*
* Garbage collect pointers from a keyring.
*
* Not called with any locks held. The keyring's key struct will not be
* deallocated under us as only our caller may deallocate it.
*/
void keyring_gc(struct key *keyring, time_t limit)
{
int result;
kenter("%x{%s}", keyring->serial, keyring->description ?: "");
if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
(1 << KEY_FLAG_REVOKED)))
goto dont_gc;
/* scan the keyring looking for dead keys */
rcu_read_lock();
result = assoc_array_iterate(&keyring->keys,
keyring_gc_check_iterator, &limit);
rcu_read_unlock();
if (result == true)
goto do_gc;
dont_gc:
kleave(" [no gc]");
return;
do_gc:
down_write(&keyring->sem);
assoc_array_gc(&keyring->keys, &keyring_assoc_array_ops,
keyring_gc_select_iterator, &limit);
up_write(&keyring->sem);
kleave(" [gc]");
}