acct.c

linux 2.6.19 kernel source code before patching

	if (acct_globals.file &&
	    acct_globals.file->f_path.mnt->mnt_sb == sb) {
		acct_file_reopen(NULL);
	}
	spin_unlock(&acct_globals.lock);
}

/*
 *  encode an unsigned long into a comp_t
 *
 *  This routine has been adopted from the encode_comp_t() function in
 *  the kern_acct.c file of the FreeBSD operating system. The encoding
 *  is a 13-bit fraction with a 3-bit (base 8) exponent.
 */

#define	MANTSIZE	13			/* 13 bit mantissa. */
#define	EXPSIZE		3			/* Base 8 (3 bit) exponent. */
#define	MAXFRACT	((1 << MANTSIZE) - 1)	/* Maximum fractional value. */

static comp_t encode_comp_t(unsigned long value)
{
	int exp, rnd;

	exp = rnd = 0;
	while (value > MAXFRACT) {
		rnd = value & (1 << (EXPSIZE - 1));	/* Round up? */
		value >>= EXPSIZE;	/* Base 8 exponent == 3 bit shift. */
		exp++;
	}

	/*
         * If we need to round up, do it (and handle overflow correctly).
         */
	if (rnd && (++value > MAXFRACT)) {
		value >>= EXPSIZE;
		exp++;
	}

	/*
         * Clean it up and polish it off.
         */
	exp <<= MANTSIZE;		/* Shift the exponent into place */
	exp += value;			/* and add on the mantissa. */
	return exp;
}

#if ACCT_VERSION==1 || ACCT_VERSION==2
/*
 * encode an u64 into a comp2_t (24 bits)
 *
 * Format: 5 bit base 2 exponent, 20 bits mantissa.
 * The leading bit of the mantissa is not stored, but implied for
 * non-zero exponents.
 * Largest encodable value is 50 bits.
 */

#define MANTSIZE2       20                      /* 20 bit mantissa. */
#define EXPSIZE2        5                       /* 5 bit base 2 exponent. */
#define MAXFRACT2       ((1ul << MANTSIZE2) - 1) /* Maximum fractional value. */
#define MAXEXP2         ((1 <<EXPSIZE2) - 1)    /* Maximum exponent. */

static comp2_t encode_comp2_t(u64 value)
{
        int exp, rnd;

        exp = (value > (MAXFRACT2>>1));
        rnd = 0;
        while (value > MAXFRACT2) {
                rnd = value & 1;
                value >>= 1;
                exp++;
        }

        /*
         * If we need to round up, do it (and handle overflow correctly).
         */
        if (rnd && (++value > MAXFRACT2)) {
                value >>= 1;
                exp++;
        }

        if (exp > MAXEXP2) {
                /* Overflow. Return largest representable number instead. */
                return (1ul << (MANTSIZE2+EXPSIZE2-1)) - 1;
        } else {
                return (value & (MAXFRACT2>>1)) | (exp << (MANTSIZE2-1));
        }
}
#endif

#if ACCT_VERSION==3
/*
 * encode an u64 into a 32 bit IEEE float
 */
static u32 encode_float(u64 value)
{
	unsigned exp = 190;
	unsigned u;

	if (value==0) return 0;
	while ((s64)value > 0){
		value <<= 1;
		exp--;
	}
	u = (u32)(value >> 40) & 0x7fffffu;
	return u | (exp << 23);
}
#endif

/*
 *  Write an accounting entry for an exiting process
 *
 *  The acct_process() call is the workhorse of the process
 *  accounting system. The struct acct is built here and then written
 *  into the accounting file. This function should only be called from
 *  do_exit().
 */

/*
 *  do_acct_process does all actual work. Caller holds the reference to file.
 */
static void do_acct_process(struct file *file)
{
	struct pacct_struct *pacct = &current->signal->pacct;
	acct_t ac;
	mm_segment_t fs;
	unsigned long flim;
	u64 elapsed;
	u64 run_time;
	struct timespec uptime;
	struct tty_struct *tty;

	/*
	 * First check to see if there is enough free_space to continue
	 * the process accounting system.
	 */
	if (!check_free_space(file))
		return;

	/*
	 * Fill the accounting struct with the needed info as recorded
	 * by the different kernel functions.
	 */
	memset((caddr_t)&ac, 0, sizeof(acct_t));

	ac.ac_version = ACCT_VERSION | ACCT_BYTEORDER;
	strlcpy(ac.ac_comm, current->comm, sizeof(ac.ac_comm));

	/* calculate run_time in nsec*/
	do_posix_clock_monotonic_gettime(&uptime);
	run_time = (u64)uptime.tv_sec*NSEC_PER_SEC + uptime.tv_nsec;
	run_time -= (u64)current->group_leader->start_time.tv_sec * NSEC_PER_SEC
		       + current->group_leader->start_time.tv_nsec;
	/* convert nsec -> AHZ */
	elapsed = nsec_to_AHZ(run_time);
#if ACCT_VERSION==3
	ac.ac_etime = encode_float(elapsed);
#else
	ac.ac_etime = encode_comp_t(elapsed < (unsigned long) -1l ?
	                       (unsigned long) elapsed : (unsigned long) -1l);
#endif
#if ACCT_VERSION==1 || ACCT_VERSION==2
	{
		/* new enlarged etime field */
		comp2_t etime = encode_comp2_t(elapsed);
		ac.ac_etime_hi = etime >> 16;
		ac.ac_etime_lo = (u16) etime;
	}
#endif
	do_div(elapsed, AHZ);
	ac.ac_btime = xtime.tv_sec - elapsed;
	/* we really need to bite the bullet and change layout */
	ac.ac_uid = current->uid;
	ac.ac_gid = current->gid;
#if ACCT_VERSION==2
	ac.ac_ahz = AHZ;
#endif
#if ACCT_VERSION==1 || ACCT_VERSION==2
	/* backward-compatible 16 bit fields */
	ac.ac_uid16 = current->uid;
	ac.ac_gid16 = current->gid;
#endif
#if ACCT_VERSION==3
	ac.ac_pid = current->tgid;
	ac.ac_ppid = current->parent->tgid;
#endif

	spin_lock_irq(&current->sighand->siglock);
	tty = current->signal->tty;
	ac.ac_tty = tty ? old_encode_dev(tty_devnum(tty)) : 0;
	ac.ac_utime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_utime)));
	ac.ac_stime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_stime)));
	ac.ac_flag = pacct->ac_flag;
	ac.ac_mem = encode_comp_t(pacct->ac_mem);
	ac.ac_minflt = encode_comp_t(pacct->ac_minflt);
	ac.ac_majflt = encode_comp_t(pacct->ac_majflt);
	ac.ac_exitcode = pacct->ac_exitcode;
	spin_unlock_irq(&current->sighand->siglock);
	ac.ac_io = encode_comp_t(0 /* current->io_usage */);	/* %% */
	ac.ac_rw = encode_comp_t(ac.ac_io / 1024);
	ac.ac_swaps = encode_comp_t(0);

	/*
         * Kernel segment override to datasegment and write it
         * to the accounting file.
         */
	fs = get_fs();
	set_fs(KERNEL_DS);
	/*
 	 * Accounting records are not subject to resource limits.
 	 */
	flim = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY;
	file->f_op->write(file, (char *)&ac,
			       sizeof(acct_t), &file->f_pos);
	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = flim;
	set_fs(fs);
}

/**
 * acct_init_pacct - initialize a new pacct_struct
 * @pacct: per-process accounting info struct to initialize
 */
void acct_init_pacct(struct pacct_struct *pacct)
{
	memset(pacct, 0, sizeof(struct pacct_struct));
	pacct->ac_utime = pacct->ac_stime = cputime_zero;
}

/**
 * acct_collect - collect accounting information into pacct_struct
 * @exitcode: task exit code
 * @group_dead: not 0, if this thread is the last one in the process.
 */
void acct_collect(long exitcode, int group_dead)
{
	struct pacct_struct *pacct = &current->signal->pacct;
	unsigned long vsize = 0;

	if (group_dead && current->mm) {
		struct vm_area_struct *vma;
		down_read(&current->mm->mmap_sem);
		vma = current->mm->mmap;
		while (vma) {
			vsize += vma->vm_end - vma->vm_start;
			vma = vma->vm_next;
		}
		up_read(&current->mm->mmap_sem);
	}

	spin_lock_irq(&current->sighand->siglock);
	if (group_dead)
		pacct->ac_mem = vsize / 1024;
	if (thread_group_leader(current)) {
		pacct->ac_exitcode = exitcode;
		if (current->flags & PF_FORKNOEXEC)
			pacct->ac_flag |= AFORK;
	}
	if (current->flags & PF_SUPERPRIV)
		pacct->ac_flag |= ASU;
	if (current->flags & PF_DUMPCORE)
		pacct->ac_flag |= ACORE;
	if (current->flags & PF_SIGNALED)
		pacct->ac_flag |= AXSIG;
	pacct->ac_utime = cputime_add(pacct->ac_utime, current->utime);
	pacct->ac_stime = cputime_add(pacct->ac_stime, current->stime);
	pacct->ac_minflt += current->min_flt;
	pacct->ac_majflt += current->maj_flt;
	spin_unlock_irq(&current->sighand->siglock);
}

/**
 * acct_process - now just a wrapper around do_acct_process
 * @exitcode: task exit code
 *
 * handles process accounting for an exiting task
 */
void acct_process(void)
{
	struct file *file = NULL;

	/*
	 * accelerate the common fastpath:
	 */
	if (!acct_globals.file)
		return;

	spin_lock(&acct_globals.lock);
	file = acct_globals.file;
	if (unlikely(!file)) {
		spin_unlock(&acct_globals.lock);
		return;
	}
	get_file(file);
	spin_unlock(&acct_globals.lock);

	do_acct_process(file);
	fput(file);
}