linux/kernel/tsacct.c
Heiko Carstens 6d5b5acca9 Fix fixpoint divide exception in acct_update_integrals
Frans Pop reported the crash below when running an s390 kernel under Hercules:

  Kernel BUG at 000738b4  verbose debug info unavailable!
  fixpoint divide exception: 0009  ! SMP
  Modules linked in: nfs lockd nfs_acl sunrpc ctcm fsm tape_34xx
     cu3088 tape ccwgroup tape_class ext3 jbd mbcache dm_mirror dm_log dm_snapshot
     dm_mod dasd_eckd_mod dasd_mod
  CPU: 0 Not tainted 2.6.27.19 
  Process awk (pid: 2069, task: 0f9ed9b8, ksp: 0f4f7d18)
  Krnl PSW : 070c1000 800738b4 (acct_update_integrals+0x4c/0x118)
             R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:0 CC:1 PM:0
  Krnl GPRS: 00000000 000007d0 7fffffff fffff830
             00000000 ffffffff 00000002 0f9ed9b8
             00000000 00008ca0 00000000 0f9ed9b8
             0f9edda4 8007386e 0f4f7ec8 0f4f7e98
  Krnl Code: 800738aa: a71807d0         lhi     %r1,2000
             800738ae: 8c200001         srdl    %r2,1
             800738b2: 1d21             dr      %r2,%r1
            >800738b4: 5810d10e         l       %r1,270(%r13)
             800738b8: 1823             lr      %r2,%r3
             800738ba: 4130f060         la      %r3,96(%r15)
             800738be: 0de1             basr    %r14,%r1
             800738c0: 5800f060         l       %r0,96(%r15)
  Call Trace:
  ( <000000000004fdea>! blocking_notifier_call_chain+0x1e/0x2c)
    <0000000000038502>! do_exit+0x106/0x7c0
    <0000000000038c36>! do_group_exit+0x7a/0xb4
    <0000000000038c8e>! SyS_exit_group+0x1e/0x30
    <0000000000021c28>! sysc_do_restart+0x12/0x16
    <0000000077e7e924>! 0x77e7e924

Reason for this is that cpu time accounting usually only happens from
interrupt context, but acct_update_integrals gets also called from
process context with interrupts enabled.

So in acct_update_integrals we may end up with the following scenario:

Between reading tsk->stime/tsk->utime and tsk->acct_timexpd an interrupt
happens which updates accouting values.  This causes acct_timexpd to be
greater than the former stime + utime.  The subsequent calculation of

	dtime = cputime_sub(time, tsk->acct_timexpd);

will be negative and the division performed by

	cputime_to_jiffies(dtime)

will generate an exception since the result won't fit into a 32 bit
register.

In order to fix this just always disable interrupts while accessing any
of the accounting values.

Reported by: Frans Pop <elendil@planet.nl>
Tested by: Frans Pop <elendil@planet.nl>
Cc: stable@kernel.org
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-09 08:13:35 -07:00

156 lines
4.2 KiB
C

/*
* tsacct.c - System accounting over taskstats interface
*
* Copyright (C) Jay Lan, <jlan@sgi.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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
*/
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/tsacct_kern.h>
#include <linux/acct.h>
#include <linux/jiffies.h>
/*
* fill in basic accounting fields
*/
void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk)
{
const struct cred *tcred;
struct timespec uptime, ts;
u64 ac_etime;
BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN);
/* calculate task elapsed time in timespec */
do_posix_clock_monotonic_gettime(&uptime);
ts = timespec_sub(uptime, tsk->start_time);
/* rebase elapsed time to usec (should never be negative) */
ac_etime = timespec_to_ns(&ts);
do_div(ac_etime, NSEC_PER_USEC);
stats->ac_etime = ac_etime;
stats->ac_btime = get_seconds() - ts.tv_sec;
if (thread_group_leader(tsk)) {
stats->ac_exitcode = tsk->exit_code;
if (tsk->flags & PF_FORKNOEXEC)
stats->ac_flag |= AFORK;
}
if (tsk->flags & PF_SUPERPRIV)
stats->ac_flag |= ASU;
if (tsk->flags & PF_DUMPCORE)
stats->ac_flag |= ACORE;
if (tsk->flags & PF_SIGNALED)
stats->ac_flag |= AXSIG;
stats->ac_nice = task_nice(tsk);
stats->ac_sched = tsk->policy;
stats->ac_pid = tsk->pid;
rcu_read_lock();
tcred = __task_cred(tsk);
stats->ac_uid = tcred->uid;
stats->ac_gid = tcred->gid;
stats->ac_ppid = pid_alive(tsk) ?
rcu_dereference(tsk->real_parent)->tgid : 0;
rcu_read_unlock();
stats->ac_utime = cputime_to_msecs(tsk->utime) * USEC_PER_MSEC;
stats->ac_stime = cputime_to_msecs(tsk->stime) * USEC_PER_MSEC;
stats->ac_utimescaled =
cputime_to_msecs(tsk->utimescaled) * USEC_PER_MSEC;
stats->ac_stimescaled =
cputime_to_msecs(tsk->stimescaled) * USEC_PER_MSEC;
stats->ac_minflt = tsk->min_flt;
stats->ac_majflt = tsk->maj_flt;
strncpy(stats->ac_comm, tsk->comm, sizeof(stats->ac_comm));
}
#ifdef CONFIG_TASK_XACCT
#define KB 1024
#define MB (1024*KB)
/*
* fill in extended accounting fields
*/
void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
{
struct mm_struct *mm;
/* convert pages-usec to Mbyte-usec */
stats->coremem = p->acct_rss_mem1 * PAGE_SIZE / MB;
stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE / MB;
mm = get_task_mm(p);
if (mm) {
/* adjust to KB unit */
stats->hiwater_rss = get_mm_hiwater_rss(mm) * PAGE_SIZE / KB;
stats->hiwater_vm = get_mm_hiwater_vm(mm) * PAGE_SIZE / KB;
mmput(mm);
}
stats->read_char = p->ioac.rchar;
stats->write_char = p->ioac.wchar;
stats->read_syscalls = p->ioac.syscr;
stats->write_syscalls = p->ioac.syscw;
#ifdef CONFIG_TASK_IO_ACCOUNTING
stats->read_bytes = p->ioac.read_bytes;
stats->write_bytes = p->ioac.write_bytes;
stats->cancelled_write_bytes = p->ioac.cancelled_write_bytes;
#else
stats->read_bytes = 0;
stats->write_bytes = 0;
stats->cancelled_write_bytes = 0;
#endif
}
#undef KB
#undef MB
/**
* acct_update_integrals - update mm integral fields in task_struct
* @tsk: task_struct for accounting
*/
void acct_update_integrals(struct task_struct *tsk)
{
if (likely(tsk->mm)) {
cputime_t time, dtime;
struct timeval value;
unsigned long flags;
u64 delta;
local_irq_save(flags);
time = tsk->stime + tsk->utime;
dtime = cputime_sub(time, tsk->acct_timexpd);
jiffies_to_timeval(cputime_to_jiffies(dtime), &value);
delta = value.tv_sec;
delta = delta * USEC_PER_SEC + value.tv_usec;
if (delta == 0)
goto out;
tsk->acct_timexpd = time;
tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
out:
local_irq_restore(flags);
}
}
/**
* acct_clear_integrals - clear the mm integral fields in task_struct
* @tsk: task_struct whose accounting fields are cleared
*/
void acct_clear_integrals(struct task_struct *tsk)
{
tsk->acct_timexpd = 0;
tsk->acct_rss_mem1 = 0;
tsk->acct_vm_mem1 = 0;
}
#endif