We run into this bug:
[ 2736.063245] Unable to handle kernel paging request for data at address 0x00000000
[ 2736.063293] Faulting instruction address: 0xc00000000037efb0
[ 2736.063300] Oops: Kernel access of bad area, sig: 11 [#1]
[ 2736.063303] SMP NR_CPUS=2048 NUMA pSeries
[ 2736.063310] Modules linked in: sg nfsv3 rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache nf_conntrack_netbios_ns nf_conntrack_broadcast ipt_MASQUERADE ip6table_mangle ip6table_security ip6table_raw ip6t_REJECT iptable_nat nf_nat_ipv4 iptable_mangle iptable_security iptable_raw ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack ebtable_filter ebtables ip6table_filter iptable_filter ip_tables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 nf_nat nf_conntrack ip6_tables ibmveth pseries_rng nx_crypto nfsd auth_rpcgss nfs_acl lockd sunrpc binfmt_misc xfs libcrc32c dm_service_time sd_mod crc_t10dif crct10dif_common ibmvfc scsi_transport_fc scsi_tgt dm_mirror dm_region_hash dm_log dm_multipath dm_mod
[ 2736.063383] CPU: 1 PID: 7128 Comm: ssh Not tainted 3.10.0-48.el7.ppc64 #1
[ 2736.063389] task: c000000131930120 ti: c0000001319a0000 task.ti: c0000001319a0000
[ 2736.063394] NIP: c00000000037efb0 LR: c0000000006c40f8 CTR: 0000000000000000
[ 2736.063399] REGS: c0000001319a3870 TRAP: 0300   Not tainted  (3.10.0-48.el7.ppc64)
[ 2736.063403] MSR: 8000000000009032 <SF,EE,ME,IR,DR,RI>  CR: 28824242  XER: 20000000
[ 2736.063415] SOFTE: 0
[ 2736.063418] CFAR: c00000000000908c
[ 2736.063421] DAR: 0000000000000000, DSISR: 40000000
[ 2736.063425]
GPR00: c0000000006c40f8 c0000001319a3af0 c000000001074788 c0000001319a3bf0
GPR04: 0000000000000000 0000000000000000 0000000000000020 000000000000000a
GPR08: fffffffe00000002 00000000ffff0000 0000000080000001 c000000000924888
GPR12: 0000000028824248 c000000007e00400 00001fffffa0f998 0000000000000000
GPR16: 0000000000000022 00001fffffa0f998 0000010022e92470 0000000000000000
GPR20: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
GPR24: 0000000000000000 c000000000f4a828 00003ffffe527108 0000000000000000
GPR28: c000000000f4a730 c000000000f4a828 0000000000000000 c0000001319a3bf0
[ 2736.063498] NIP [c00000000037efb0] .__list_add+0x30/0x110
[ 2736.063504] LR [c0000000006c40f8] .rwsem_down_write_failed+0x78/0x264
[ 2736.063508] PACATMSCRATCH [800000000280f032]
[ 2736.063511] Call Trace:
[ 2736.063516] [c0000001319a3af0] [c0000001319a3b80] 0xc0000001319a3b80 (unreliable)
[ 2736.063523] [c0000001319a3b80] [c0000000006c40f8] .rwsem_down_write_failed+0x78/0x264
[ 2736.063530] [c0000001319a3c50] [c0000000006c1bb0] .down_write+0x70/0x78
[ 2736.063536] [c0000001319a3cd0] [c0000000002e5ffc] .keyctl_get_persistent+0x20c/0x320
[ 2736.063542] [c0000001319a3dc0] [c0000000002e2388] .SyS_keyctl+0x238/0x260
[ 2736.063548] [c0000001319a3e30] [c000000000009e7c] syscall_exit+0x0/0x7c
[ 2736.063553] Instruction dump:
[ 2736.063556] 7c0802a6 fba1ffe8 fbc1fff0 fbe1fff8 7cbd2b78 7c9e2378 7c7f1b78 f8010010
[ 2736.063566] f821ff71 e8a50008 7fa52040 40de00c0 <e8be0000> 7fbd2840 40de0094 7fbff040
[ 2736.063579] ---[ end trace 2708241785538296 ]---
It's caused by uninitialized persistent_keyring_register_sem.
The bug was introduced by commit f36f8c75, two typos are in that commit:
CONFIG_KEYS_KERBEROS_CACHE should be CONFIG_PERSISTENT_KEYRINGS and
krb_cache_register_sem should be persistent_keyring_register_sem.
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Signed-off-by: David Howells <dhowells@redhat.com>
		
	
			
		
			
				
	
	
		
			226 lines
		
	
	
	
		
			5.3 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			226 lines
		
	
	
	
		
			5.3 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
/*
 | 
						|
 * The "user cache".
 | 
						|
 *
 | 
						|
 * (C) Copyright 1991-2000 Linus Torvalds
 | 
						|
 *
 | 
						|
 * We have a per-user structure to keep track of how many
 | 
						|
 * processes, files etc the user has claimed, in order to be
 | 
						|
 * able to have per-user limits for system resources. 
 | 
						|
 */
 | 
						|
 | 
						|
#include <linux/init.h>
 | 
						|
#include <linux/sched.h>
 | 
						|
#include <linux/slab.h>
 | 
						|
#include <linux/bitops.h>
 | 
						|
#include <linux/key.h>
 | 
						|
#include <linux/interrupt.h>
 | 
						|
#include <linux/export.h>
 | 
						|
#include <linux/user_namespace.h>
 | 
						|
#include <linux/proc_ns.h>
 | 
						|
 | 
						|
/*
 | 
						|
 * userns count is 1 for root user, 1 for init_uts_ns,
 | 
						|
 * and 1 for... ?
 | 
						|
 */
 | 
						|
struct user_namespace init_user_ns = {
 | 
						|
	.uid_map = {
 | 
						|
		.nr_extents = 1,
 | 
						|
		.extent[0] = {
 | 
						|
			.first = 0,
 | 
						|
			.lower_first = 0,
 | 
						|
			.count = 4294967295U,
 | 
						|
		},
 | 
						|
	},
 | 
						|
	.gid_map = {
 | 
						|
		.nr_extents = 1,
 | 
						|
		.extent[0] = {
 | 
						|
			.first = 0,
 | 
						|
			.lower_first = 0,
 | 
						|
			.count = 4294967295U,
 | 
						|
		},
 | 
						|
	},
 | 
						|
	.projid_map = {
 | 
						|
		.nr_extents = 1,
 | 
						|
		.extent[0] = {
 | 
						|
			.first = 0,
 | 
						|
			.lower_first = 0,
 | 
						|
			.count = 4294967295U,
 | 
						|
		},
 | 
						|
	},
 | 
						|
	.count = ATOMIC_INIT(3),
 | 
						|
	.owner = GLOBAL_ROOT_UID,
 | 
						|
	.group = GLOBAL_ROOT_GID,
 | 
						|
	.proc_inum = PROC_USER_INIT_INO,
 | 
						|
#ifdef CONFIG_PERSISTENT_KEYRINGS
 | 
						|
	.persistent_keyring_register_sem =
 | 
						|
	__RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),
 | 
						|
#endif
 | 
						|
};
 | 
						|
EXPORT_SYMBOL_GPL(init_user_ns);
 | 
						|
 | 
						|
/*
 | 
						|
 * UID task count cache, to get fast user lookup in "alloc_uid"
 | 
						|
 * when changing user ID's (ie setuid() and friends).
 | 
						|
 */
 | 
						|
 | 
						|
#define UIDHASH_BITS	(CONFIG_BASE_SMALL ? 3 : 7)
 | 
						|
#define UIDHASH_SZ	(1 << UIDHASH_BITS)
 | 
						|
#define UIDHASH_MASK		(UIDHASH_SZ - 1)
 | 
						|
#define __uidhashfn(uid)	(((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK)
 | 
						|
#define uidhashentry(uid)	(uidhash_table + __uidhashfn((__kuid_val(uid))))
 | 
						|
 | 
						|
static struct kmem_cache *uid_cachep;
 | 
						|
struct hlist_head uidhash_table[UIDHASH_SZ];
 | 
						|
 | 
						|
/*
 | 
						|
 * The uidhash_lock is mostly taken from process context, but it is
 | 
						|
 * occasionally also taken from softirq/tasklet context, when
 | 
						|
 * task-structs get RCU-freed. Hence all locking must be softirq-safe.
 | 
						|
 * But free_uid() is also called with local interrupts disabled, and running
 | 
						|
 * local_bh_enable() with local interrupts disabled is an error - we'll run
 | 
						|
 * softirq callbacks, and they can unconditionally enable interrupts, and
 | 
						|
 * the caller of free_uid() didn't expect that..
 | 
						|
 */
 | 
						|
static DEFINE_SPINLOCK(uidhash_lock);
 | 
						|
 | 
						|
/* root_user.__count is 1, for init task cred */
 | 
						|
struct user_struct root_user = {
 | 
						|
	.__count	= ATOMIC_INIT(1),
 | 
						|
	.processes	= ATOMIC_INIT(1),
 | 
						|
	.files		= ATOMIC_INIT(0),
 | 
						|
	.sigpending	= ATOMIC_INIT(0),
 | 
						|
	.locked_shm     = 0,
 | 
						|
	.uid		= GLOBAL_ROOT_UID,
 | 
						|
};
 | 
						|
 | 
						|
/*
 | 
						|
 * These routines must be called with the uidhash spinlock held!
 | 
						|
 */
 | 
						|
static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
 | 
						|
{
 | 
						|
	hlist_add_head(&up->uidhash_node, hashent);
 | 
						|
}
 | 
						|
 | 
						|
static void uid_hash_remove(struct user_struct *up)
 | 
						|
{
 | 
						|
	hlist_del_init(&up->uidhash_node);
 | 
						|
}
 | 
						|
 | 
						|
static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent)
 | 
						|
{
 | 
						|
	struct user_struct *user;
 | 
						|
 | 
						|
	hlist_for_each_entry(user, hashent, uidhash_node) {
 | 
						|
		if (uid_eq(user->uid, uid)) {
 | 
						|
			atomic_inc(&user->__count);
 | 
						|
			return user;
 | 
						|
		}
 | 
						|
	}
 | 
						|
 | 
						|
	return NULL;
 | 
						|
}
 | 
						|
 | 
						|
/* IRQs are disabled and uidhash_lock is held upon function entry.
 | 
						|
 * IRQ state (as stored in flags) is restored and uidhash_lock released
 | 
						|
 * upon function exit.
 | 
						|
 */
 | 
						|
static void free_user(struct user_struct *up, unsigned long flags)
 | 
						|
	__releases(&uidhash_lock)
 | 
						|
{
 | 
						|
	uid_hash_remove(up);
 | 
						|
	spin_unlock_irqrestore(&uidhash_lock, flags);
 | 
						|
	key_put(up->uid_keyring);
 | 
						|
	key_put(up->session_keyring);
 | 
						|
	kmem_cache_free(uid_cachep, up);
 | 
						|
}
 | 
						|
 | 
						|
/*
 | 
						|
 * Locate the user_struct for the passed UID.  If found, take a ref on it.  The
 | 
						|
 * caller must undo that ref with free_uid().
 | 
						|
 *
 | 
						|
 * If the user_struct could not be found, return NULL.
 | 
						|
 */
 | 
						|
struct user_struct *find_user(kuid_t uid)
 | 
						|
{
 | 
						|
	struct user_struct *ret;
 | 
						|
	unsigned long flags;
 | 
						|
 | 
						|
	spin_lock_irqsave(&uidhash_lock, flags);
 | 
						|
	ret = uid_hash_find(uid, uidhashentry(uid));
 | 
						|
	spin_unlock_irqrestore(&uidhash_lock, flags);
 | 
						|
	return ret;
 | 
						|
}
 | 
						|
 | 
						|
void free_uid(struct user_struct *up)
 | 
						|
{
 | 
						|
	unsigned long flags;
 | 
						|
 | 
						|
	if (!up)
 | 
						|
		return;
 | 
						|
 | 
						|
	local_irq_save(flags);
 | 
						|
	if (atomic_dec_and_lock(&up->__count, &uidhash_lock))
 | 
						|
		free_user(up, flags);
 | 
						|
	else
 | 
						|
		local_irq_restore(flags);
 | 
						|
}
 | 
						|
 | 
						|
struct user_struct *alloc_uid(kuid_t uid)
 | 
						|
{
 | 
						|
	struct hlist_head *hashent = uidhashentry(uid);
 | 
						|
	struct user_struct *up, *new;
 | 
						|
 | 
						|
	spin_lock_irq(&uidhash_lock);
 | 
						|
	up = uid_hash_find(uid, hashent);
 | 
						|
	spin_unlock_irq(&uidhash_lock);
 | 
						|
 | 
						|
	if (!up) {
 | 
						|
		new = kmem_cache_zalloc(uid_cachep, GFP_KERNEL);
 | 
						|
		if (!new)
 | 
						|
			goto out_unlock;
 | 
						|
 | 
						|
		new->uid = uid;
 | 
						|
		atomic_set(&new->__count, 1);
 | 
						|
 | 
						|
		/*
 | 
						|
		 * Before adding this, check whether we raced
 | 
						|
		 * on adding the same user already..
 | 
						|
		 */
 | 
						|
		spin_lock_irq(&uidhash_lock);
 | 
						|
		up = uid_hash_find(uid, hashent);
 | 
						|
		if (up) {
 | 
						|
			key_put(new->uid_keyring);
 | 
						|
			key_put(new->session_keyring);
 | 
						|
			kmem_cache_free(uid_cachep, new);
 | 
						|
		} else {
 | 
						|
			uid_hash_insert(new, hashent);
 | 
						|
			up = new;
 | 
						|
		}
 | 
						|
		spin_unlock_irq(&uidhash_lock);
 | 
						|
	}
 | 
						|
 | 
						|
	return up;
 | 
						|
 | 
						|
out_unlock:
 | 
						|
	return NULL;
 | 
						|
}
 | 
						|
 | 
						|
static int __init uid_cache_init(void)
 | 
						|
{
 | 
						|
	int n;
 | 
						|
 | 
						|
	uid_cachep = kmem_cache_create("uid_cache", sizeof(struct user_struct),
 | 
						|
			0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 | 
						|
 | 
						|
	for(n = 0; n < UIDHASH_SZ; ++n)
 | 
						|
		INIT_HLIST_HEAD(uidhash_table + n);
 | 
						|
 | 
						|
	/* Insert the root user immediately (init already runs as root) */
 | 
						|
	spin_lock_irq(&uidhash_lock);
 | 
						|
	uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID));
 | 
						|
	spin_unlock_irq(&uidhash_lock);
 | 
						|
 | 
						|
	return 0;
 | 
						|
}
 | 
						|
 | 
						|
module_init(uid_cache_init);
 |