Revision e91467ecd1ef381377fd327c0ded922835ec52ab authored by Christian Borntraeger on 05 August 2006, 19:13:52 UTC, committed by Linus Torvalds on 06 August 2006, 15:57:46 UTC
This patch adds a barrier() in futex unqueue_me to avoid aliasing of two pointers. On my s390x system I saw the following oops: Unable to handle kernel pointer dereference at virtual kernel address 0000000000000000 Oops: 0004 [#1] CPU: 0 Not tainted Process mytool (pid: 13613, task: 000000003ecb6ac0, ksp: 00000000366bdbd8) Krnl PSW : 0704d00180000000 00000000003c9ac2 (_spin_lock+0xe/0x30) Krnl GPRS: 00000000ffffffff 000000003ecb6ac0 0000000000000000 0700000000000000 0000000000000000 0000000000000000 000001fe00002028 00000000000c091f 000001fe00002054 000001fe00002054 0000000000000000 00000000366bddc0 00000000005ef8c0 00000000003d00e8 0000000000144f91 00000000366bdcb8 Krnl Code: ba 4e 20 00 12 44 b9 16 00 3e a7 84 00 08 e3 e0 f0 88 00 04 Call Trace: ([<0000000000144f90>] unqueue_me+0x40/0xe4) [<0000000000145a0c>] do_futex+0x33c/0xc40 [<000000000014643e>] sys_futex+0x12e/0x144 [<000000000010bb00>] sysc_noemu+0x10/0x16 [<000002000003741c>] 0x2000003741c The code in question is: static int unqueue_me(struct futex_q *q) { int ret = 0; spinlock_t *lock_ptr; /* In the common case we don't take the spinlock, which is nice. */ retry: lock_ptr = q->lock_ptr; if (lock_ptr != 0) { spin_lock(lock_ptr); /* * q->lock_ptr can change between reading it and * spin_lock(), causing us to take the wrong lock. This * corrects the race condition. [...] and my compiler (gcc 4.1.0) makes the following out of it: 00000000000003c8 <unqueue_me>: 3c8: eb bf f0 70 00 24 stmg %r11,%r15,112(%r15) 3ce: c0 d0 00 00 00 00 larl %r13,3ce <unqueue_me+0x6> 3d0: R_390_PC32DBL .rodata+0x2a 3d4: a7 f1 1e 00 tml %r15,7680 3d8: a7 84 00 01 je 3da <unqueue_me+0x12> 3dc: b9 04 00 ef lgr %r14,%r15 3e0: a7 fb ff d0 aghi %r15,-48 3e4: b9 04 00 b2 lgr %r11,%r2 3e8: e3 e0 f0 98 00 24 stg %r14,152(%r15) 3ee: e3 c0 b0 28 00 04 lg %r12,40(%r11) /* write q->lock_ptr in r12 */ 3f4: b9 02 00 cc ltgr %r12,%r12 3f8: a7 84 00 4b je 48e <unqueue_me+0xc6> /* if r12 is zero then jump over the code.... */ 3fc: e3 20 b0 28 00 04 lg %r2,40(%r11) /* write q->lock_ptr in r2 */ 402: c0 e5 00 00 00 00 brasl %r14,402 <unqueue_me+0x3a> 404: R_390_PC32DBL _spin_lock+0x2 /* use r2 as parameter for spin_lock */ So the code becomes more or less: if (q->lock_ptr != 0) spin_lock(q->lock_ptr) instead of if (lock_ptr != 0) spin_lock(lock_ptr) Which caused the oops from above. After adding a barrier gcc creates code without this problem: [...] (the same) 3ee: e3 c0 b0 28 00 04 lg %r12,40(%r11) 3f4: b9 02 00 cc ltgr %r12,%r12 3f8: b9 04 00 2c lgr %r2,%r12 3fc: a7 84 00 48 je 48c <unqueue_me+0xc4> 400: c0 e5 00 00 00 00 brasl %r14,400 <unqueue_me+0x38> 402: R_390_PC32DBL _spin_lock+0x2 As a general note, this code of unqueue_me seems a bit fishy. The retry logic of unqueue_me only works if we can guarantee, that the original value of q->lock_ptr is always a spinlock (Otherwise we overwrite kernel memory). We know that q->lock_ptr can change. I dont know what happens with the original spinlock, as I am not an expert with the futex code. Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Acked-by: Ingo Molnar <mingo@redhat.com> Cc: Thomas Gleixner <tglx@timesys.com> Signed-off-by: Christian Borntraeger <borntrae@de.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
1 parent 72f0b4e
processor.h
/*
* include/asm-alpha/processor.h
*
* Copyright (C) 1994 Linus Torvalds
*/
#ifndef __ASM_ALPHA_PROCESSOR_H
#define __ASM_ALPHA_PROCESSOR_H
#include <linux/personality.h> /* for ADDR_LIMIT_32BIT */
/*
* Returns current instruction pointer ("program counter").
*/
#define current_text_addr() \
({ void *__pc; __asm__ ("br %0,.+4" : "=r"(__pc)); __pc; })
/*
* We have a 42-bit user address space: 4TB user VM...
*/
#define TASK_SIZE (0x40000000000UL)
/* This decides where the kernel will search for a free chunk of vm
* space during mmap's.
*/
#define TASK_UNMAPPED_BASE \
((current->personality & ADDR_LIMIT_32BIT) ? 0x40000000 : TASK_SIZE / 2)
typedef struct {
unsigned long seg;
} mm_segment_t;
/* This is dead. Everything has been moved to thread_info. */
struct thread_struct { };
#define INIT_THREAD { }
/* Return saved PC of a blocked thread. */
struct task_struct;
extern unsigned long thread_saved_pc(struct task_struct *);
/* Do necessary setup to start up a newly executed thread. */
extern void start_thread(struct pt_regs *, unsigned long, unsigned long);
/* Free all resources held by a thread. */
extern void release_thread(struct task_struct *);
/* Prepare to copy thread state - unlazy all lazy status */
#define prepare_to_copy(tsk) do { } while (0)
/* Create a kernel thread without removing it from tasklists. */
extern long kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
unsigned long get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc)
#define KSTK_ESP(tsk) \
((tsk) == current ? rdusp() : task_thread_info(tsk)->pcb.usp)
#define cpu_relax() barrier()
#define ARCH_HAS_PREFETCH
#define ARCH_HAS_PREFETCHW
#define ARCH_HAS_SPINLOCK_PREFETCH
#ifndef CONFIG_SMP
/* Nothing to prefetch. */
#define spin_lock_prefetch(lock) do { } while (0)
#endif
extern inline void prefetch(const void *ptr)
{
__builtin_prefetch(ptr, 0, 3);
}
extern inline void prefetchw(const void *ptr)
{
__builtin_prefetch(ptr, 1, 3);
}
#ifdef CONFIG_SMP
extern inline void spin_lock_prefetch(const void *ptr)
{
__builtin_prefetch(ptr, 1, 3);
}
#endif
#endif /* __ASM_ALPHA_PROCESSOR_H */
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...