Skip to main content

Browse the archive

Revision c403f6a3a792a6601185497c12b0bdf4be880439 authored by Qian Cai on 15 August 2020, 00:31:53 UTC, committed by Linus Torvalds on 15 August 2020, 02:56:57 UTC 
mm: annotate a data race in page_zonenum()
 
 BUG: KCSAN: data-race in page_cpupid_xchg_last / put_page

 write (marked) to 0xfffffc0d48ec1a00 of 8 bytes by task 91442 on cpu 3:
  page_cpupid_xchg_last+0x51/0x80
  page_cpupid_xchg_last at mm/mmzone.c:109 (discriminator 11)
  wp_page_reuse+0x3e/0xc0
  wp_page_reuse at mm/memory.c:2453
  do_wp_page+0x472/0x7b0
  do_wp_page at mm/memory.c:2798
  __handle_mm_fault+0xcb0/0xd00
  handle_pte_fault at mm/memory.c:4049
  (inlined by) __handle_mm_fault at mm/memory.c:4163
  handle_mm_fault+0xfc/0x2f0
  handle_mm_fault at mm/memory.c:4200
  do_page_fault+0x263/0x6f9
  do_user_addr_fault at arch/x86/mm/fault.c:1465
  (inlined by) do_page_fault at arch/x86/mm/fault.c:1539
  page_fault+0x34/0x40

 read to 0xfffffc0d48ec1a00 of 8 bytes by task 94817 on cpu 69:
  put_page+0x15a/0x1f0
  page_zonenum at include/linux/mm.h:923
  (inlined by) is_zone_device_page at include/linux/mm.h:929
  (inlined by) page_is_devmap_managed at include/linux/mm.h:948
  (inlined by) put_page at include/linux/mm.h:1023
  wp_page_copy+0x571/0x930
  wp_page_copy at mm/memory.c:2615
  do_wp_page+0x107/0x7b0
  __handle_mm_fault+0xcb0/0xd00
  handle_mm_fault+0xfc/0x2f0
  do_page_fault+0x263/0x6f9
  page_fault+0x34/0x40

 Reported by Kernel Concurrency Sanitizer on:
 CPU: 69 PID: 94817 Comm: systemd-udevd Tainted: G        W  O L 5.5.0-next-20200204+ #6
 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019

A page never changes its zone number. The zone number happens to be
stored in the same word as other bits which are modified, but the zone
number bits will never be modified by any other write, so it can accept
a reload of the zone bits after an intervening write and it don't need
to use READ_ONCE(). Thus, annotate this data race using
ASSERT_EXCLUSIVE_BITS() to also assert that there are no concurrent
writes to it.

Suggested-by: Marco Elver <elver@google.com>
Signed-off-by: Qian Cai <cai@lca.pw>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Link: http://lkml.kernel.org/r/1581619089-14472-1-git-send-email-cai@lca.pw
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 7e0cc01
Raw File
ipv6_stubs.h 
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _IPV6_STUBS_H
#define _IPV6_STUBS_H

#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <net/dst.h>
#include <net/flow.h>
#include <net/neighbour.h>
#include <net/sock.h>

/* structs from net/ip6_fib.h */
struct fib6_info;
struct fib6_nh;
struct fib6_config;
struct fib6_result;

/* This is ugly, ideally these symbols should be built
 * into the core kernel.
 */
struct ipv6_stub {
	int (*ipv6_sock_mc_join)(struct sock *sk, int ifindex,
				 const struct in6_addr *addr);
	int (*ipv6_sock_mc_drop)(struct sock *sk, int ifindex,
				 const struct in6_addr *addr);
	struct dst_entry *(*ipv6_dst_lookup_flow)(struct net *net,
						  const struct sock *sk,
						  struct flowi6 *fl6,
						  const struct in6_addr *final_dst);
	int (*ipv6_route_input)(struct sk_buff *skb);

	struct fib6_table *(*fib6_get_table)(struct net *net, u32 id);
	int (*fib6_lookup)(struct net *net, int oif, struct flowi6 *fl6,
			   struct fib6_result *res, int flags);
	int (*fib6_table_lookup)(struct net *net, struct fib6_table *table,
				 int oif, struct flowi6 *fl6,
				 struct fib6_result *res, int flags);
	void (*fib6_select_path)(const struct net *net, struct fib6_result *res,
				 struct flowi6 *fl6, int oif, bool oif_match,
				 const struct sk_buff *skb, int strict);
	u32 (*ip6_mtu_from_fib6)(const struct fib6_result *res,
				 const struct in6_addr *daddr,
				 const struct in6_addr *saddr);

	int (*fib6_nh_init)(struct net *net, struct fib6_nh *fib6_nh,
			    struct fib6_config *cfg, gfp_t gfp_flags,
			    struct netlink_ext_ack *extack);
	void (*fib6_nh_release)(struct fib6_nh *fib6_nh);
	void (*fib6_update_sernum)(struct net *net, struct fib6_info *rt);
	int (*ip6_del_rt)(struct net *net, struct fib6_info *rt, bool skip_notify);
	void (*fib6_rt_update)(struct net *net, struct fib6_info *rt,
			       struct nl_info *info);

	void (*udpv6_encap_enable)(void);
	void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr,
			      const struct in6_addr *solicited_addr,
			      bool router, bool solicited, bool override, bool inc_opt);
#if IS_ENABLED(CONFIG_XFRM)
	void (*xfrm6_local_rxpmtu)(struct sk_buff *skb, u32 mtu);
	int (*xfrm6_udp_encap_rcv)(struct sock *sk, struct sk_buff *skb);
	int (*xfrm6_rcv_encap)(struct sk_buff *skb, int nexthdr, __be32 spi,
			       int encap_type);
#endif
	struct neigh_table *nd_tbl;
};
extern const struct ipv6_stub *ipv6_stub __read_mostly;

/* A stub used by bpf helpers. Similarly ugly as ipv6_stub */
struct ipv6_bpf_stub {
	int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len,
			  u32 flags);
	struct sock *(*udp6_lib_lookup)(struct net *net,
				     const struct in6_addr *saddr, __be16 sport,
				     const struct in6_addr *daddr, __be16 dport,
				     int dif, int sdif, struct udp_table *tbl,
				     struct sk_buff *skb);
};
extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly;

#endif
back to top