summaryrefslogtreecommitdiffstats
path: root/kernel/acct.c
blob: 4229b9ebfb5c87276cebc6ac83263e84d9388008 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
/*
 *  linux/kernel/acct.c
 *
 *  BSD Process Accounting for Linux
 *
 *  Author: Marco van Wieringen <mvw@planets.elm.net>
 *
 *  Some code based on ideas and code from:
 *  Thomas K. Dyas <tdyas@eden.rutgers.edu>
 *
 *  This file implements BSD-style process accounting. Whenever any
 *  process exits, an accounting record of type "struct acct" is
 *  written to the file specified with the acct() system call. It is
 *  up to user-level programs to do useful things with the accounting
 *  log. The kernel just provides the raw accounting information.
 *
 * (C) Copyright 1995 - 1997 Marco van Wieringen - ELM Consultancy B.V.
 *
 */

#include <linux/config.h>
#include <linux/errno.h>
#include <linux/kernel.h>

#ifdef CONFIG_BSD_PROCESS_ACCT
#include <linux/fs.h>
#include <linux/vfs.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/stat.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/timer.h>
#include <linux/tty.h>
#include <linux/acct.h>
#include <linux/major.h>
#include <linux/smp.h>
#include <linux/smp_lock.h>
#include <linux/file.h>

#include <asm/uaccess.h>

/*
 * These constants control the amount of freespace that suspend and
 * resume the process accounting system, and the time delay between
 * each check.
 */

#define RESUME		(4)       /* More than 4% free space will resume */
#define SUSPEND		(2)       /* Less than 2% free space will suspend */
#define ACCT_TIMEOUT	(30 * HZ) /* 30 second timeout between checks */

/*
 * External references and all of the globals.
 */
void acct_timeout(unsigned long);

static volatile int acct_active = 0;
static volatile int acct_needcheck = 0;
static struct file *acct_file = NULL;
static struct timer_list acct_timer = { NULL, NULL, 0, 0, acct_timeout };

/*
 * Called whenever the timer says to check the free space.
 */
void acct_timeout(unsigned long unused)
{
	acct_needcheck = 1;
}

/*
 * Check the amount of free space and suspend/resume accordingly.
 */
static void check_free_space(void)
{
	mm_segment_t fs;
	struct statfs sbuf;

	if (!acct_file || !acct_needcheck)
		return;

	if (!acct_file->f_dentry->d_inode->i_sb->s_op ||
            !acct_file->f_dentry->d_inode->i_sb->s_op->statfs)
		return;

	fs = get_fs();
	set_fs(KERNEL_DS);
	acct_file->f_dentry->d_inode->i_sb->s_op->statfs(acct_file->f_dentry->d_inode->i_sb, &sbuf, sizeof(struct statfs));
	set_fs(fs);

	if (acct_active) {
		if (sbuf.f_bavail <= SUSPEND * sbuf.f_blocks / 100) {
			acct_active = 0;
			printk(KERN_INFO "Process accounting paused\r\n");
		}
	} else {
		if (sbuf.f_bavail >= RESUME * sbuf.f_blocks / 100) {
			acct_active = 1;
			printk(KERN_INFO "Process accounting resumed\r\n");
		}
	}
	del_timer(&acct_timer);
	acct_needcheck = 0;
	acct_timer.expires = jiffies + ACCT_TIMEOUT;
	add_timer(&acct_timer);
}

/*
 *  sys_acct() is the only system call needed to implement process
 *  accounting. It takes the name of the file where accounting records
 *  should be written. If the filename is NULL, accounting will be
 *  shutdown.
 */
asmlinkage int sys_acct(const char *name)
{
	struct dentry *dentry;
	struct inode *inode;
	char *tmp;
	int error = -EPERM;

	lock_kernel();
	if (!suser())
		goto out;

	if (name == (char *)NULL) {
		if (acct_active) {
			acct_process(0); 
		        del_timer(&acct_timer);
			acct_active = 0;
			acct_needcheck = 0;
			fput(acct_file);
		}
		error = 0;
		goto out;
	} else {
		if (!acct_active) {
			tmp = getname(name);
			error = PTR_ERR(tmp);
			if (IS_ERR(tmp))
				goto out;

			dentry = open_namei(tmp, O_RDWR, 0600);
			putname(tmp);

			error = PTR_ERR(dentry);
			if (IS_ERR(dentry))
				goto out;

			inode = dentry->d_inode;

			if (!S_ISREG(inode->i_mode)) {
				dput(dentry);
				error = -EACCES;
				goto out;
			}

			if (!inode->i_op || !inode->i_op->default_file_ops || 
			    !inode->i_op->default_file_ops->write) {
				dput(dentry);
				error = -EIO;
				goto out;
			}

			if ((acct_file = get_empty_filp()) != (struct file *)NULL) {
				acct_file->f_mode = (O_WRONLY + 1) & O_ACCMODE;
				acct_file->f_flags = O_WRONLY;
				acct_file->f_dentry = dentry;
				acct_file->f_pos = inode->i_size;
				acct_file->f_reada = 0;
				acct_file->f_op = inode->i_op->default_file_ops;
				if ((error = get_write_access(acct_file->f_dentry->d_inode)) == 0) {
					if (acct_file->f_op && acct_file->f_op->open)
						error = acct_file->f_op->open(inode, acct_file);
					if (error == 0) {
						acct_needcheck = 0;
						acct_active = 1;
						acct_timer.expires = jiffies + ACCT_TIMEOUT;
						add_timer(&acct_timer);
						error = 0;
						goto out;
					}
					put_write_access(acct_file->f_dentry->d_inode);
				}
				acct_file->f_count--;
			} else
				error = -EUSERS;
			dput(dentry);
		} else
			error = -EBUSY;
	}
out:
	unlock_kernel();
	return error;
}

void acct_auto_close(kdev_t dev)
{
	if (acct_active && acct_file && acct_file->f_dentry->d_inode->i_dev == dev)
		sys_acct((char *)NULL);
}

/*
 *  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;
}

/*
 *  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().
 */
#define KSTK_EIP(stack) (((unsigned long *)(stack))[1019])
#define KSTK_ESP(stack) (((unsigned long *)(stack))[1022])

int acct_process(long exitcode)
{
	struct acct ac;
	mm_segment_t fs;
	unsigned long vsize;

	/*
	 * First check to see if there is enough free_space to continue the process
	 * accounting system. Check_free_space toggle's the acct_active flag so we
	 * need to check that after check_free_space.
	 */
	check_free_space();

	if (!acct_active)
		return 0;


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

	strncpy(ac.ac_comm, current->comm, ACCT_COMM);
	ac.ac_comm[ACCT_COMM - 1] = '\0';

	ac.ac_btime = CT_TO_SECS(current->start_time) + (xtime.tv_sec - (jiffies / HZ));
	ac.ac_etime = encode_comp_t(jiffies - current->start_time);
	ac.ac_utime = encode_comp_t(current->times.tms_utime);
	ac.ac_stime = encode_comp_t(current->times.tms_stime);
	ac.ac_uid = current->uid;
	ac.ac_gid = current->gid;
	ac.ac_tty = (current->tty) ? kdev_t_to_nr(current->tty->device) : 0;

	ac.ac_flag = 0;
	if (current->flags & PF_FORKNOEXEC)
		ac.ac_flag |= AFORK;
	if (current->flags & PF_SUPERPRIV)
		ac.ac_flag |= ASU;
	if (current->flags & PF_DUMPCORE)
		ac.ac_flag |= ACORE;
	if (current->flags & PF_SIGNALED)
		ac.ac_flag |= AXSIG;

	vsize = 0;
	if (current->mm) {
		struct vm_area_struct *vma = current->mm->mmap;
		while (vma) {
			vsize += vma->vm_end - vma->vm_start;
			vma = vma->vm_next;
		}
	}
	vsize = vsize / 1024;
	ac.ac_mem = encode_comp_t(vsize);
	ac.ac_io = encode_comp_t(0 /* current->io_usage */);	/* %% */
	ac.ac_rw = encode_comp_t(ac.ac_io / 1024);
	ac.ac_minflt = encode_comp_t(current->min_flt);
	ac.ac_majflt = encode_comp_t(current->maj_flt);
	ac.ac_swaps = encode_comp_t(current->nswap);
	ac.ac_exitcode = exitcode;

	/*
         * Kernel segment override to datasegment and write it to the accounting file.
         */
	fs = get_fs();
	set_fs(KERNEL_DS);
	acct_file->f_op->write(acct_file, (char *)&ac,
			       sizeof(struct acct), &acct_file->f_pos);
	set_fs(fs);
	return 0;
}

#else
/*
 * Dummy system call when BSD process accounting is not configured
 * into the kernel.
 */

asmlinkage int sys_acct(const char * filename)
{
	return -ENOSYS;
}
#endif