aboutsummaryrefslogtreecommitdiffstats
path: root/arch/m32r/kernel/setup.c
blob: 1ff483c8a4c9749c99d8f70b052ee9d805cc3aa6 (plain) (blame)
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
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
/*
 *  linux/arch/m32r/kernel/setup.c
 *
 *  Setup routines for Renesas M32R
 *
 *  Copyright (c) 2001, 2002  Hiroyuki Kondo, Hirokazu Takata,
 *                            Hitoshi Yamamoto
 */

#include <linux/config.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/stddef.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/ioport.h>
#include <linux/mm.h>
#include <linux/bootmem.h>
#include <linux/console.h>
#include <linux/initrd.h>
#include <linux/major.h>
#include <linux/root_dev.h>
#include <linux/seq_file.h>
#include <linux/timex.h>
#include <linux/tty.h>
#include <linux/cpu.h>
#include <linux/nodemask.h>
#include <linux/pfn.h>

#include <asm/processor.h>
#include <asm/pgtable.h>
#include <asm/io.h>
#include <asm/mmu_context.h>
#include <asm/m32r.h>
#include <asm/setup.h>
#include <asm/sections.h>

#ifdef CONFIG_MMU
extern void init_mmu(void);
#endif

extern char _end[];

/*
 * Machine setup..
 */
struct cpuinfo_m32r boot_cpu_data;

#ifdef CONFIG_BLK_DEV_RAM
extern int rd_doload;	/* 1 = load ramdisk, 0 = don't load */
extern int rd_prompt;	/* 1 = prompt for ramdisk, 0 = don't prompt */
extern int rd_image_start;	/* starting block # of image */
#endif

#if defined(CONFIG_VGA_CONSOLE)
struct screen_info screen_info = {
	.orig_video_lines      = 25,
	.orig_video_cols       = 80,
	.orig_video_mode       = 0,
	.orig_video_ega_bx     = 0,
	.orig_video_isVGA      = 1,
	.orig_video_points     = 8
};
#endif

extern int root_mountflags;

static char command_line[COMMAND_LINE_SIZE];

static struct resource data_resource = {
	.name   = "Kernel data",
	.start  = 0,
	.end    = 0,
	.flags  = IORESOURCE_BUSY | IORESOURCE_MEM
};

static struct resource code_resource = {
	.name   = "Kernel code",
	.start  = 0,
	.end    = 0,
	.flags  = IORESOURCE_BUSY | IORESOURCE_MEM
};

unsigned long memory_start;
unsigned long memory_end;

void __init setup_arch(char **);
int get_cpuinfo(char *);

static __inline__ void parse_mem_cmdline(char ** cmdline_p)
{
	char c = ' ';
	char *to = command_line;
	char *from = COMMAND_LINE;
	int len = 0;
	int usermem = 0;

	/* Save unparsed command line copy for /proc/cmdline */
	memcpy(saved_command_line, COMMAND_LINE, COMMAND_LINE_SIZE);
	saved_command_line[COMMAND_LINE_SIZE-1] = '\0';

	memory_start = (unsigned long)CONFIG_MEMORY_START+PAGE_OFFSET;
	memory_end = memory_start+(unsigned long)CONFIG_MEMORY_SIZE;

	for ( ; ; ) {
		if (c == ' ' && !memcmp(from, "mem=", 4)) {
			if (to != command_line)
				to--;

			{
				unsigned long mem_size;

				usermem = 1;
				mem_size = memparse(from+4, &from);
				memory_end = memory_start + mem_size;
			}
		}
		c = *(from++);
		if (!c)
			break;

		if (COMMAND_LINE_SIZE <= ++len)
			break;

		*(to++) = c;
	}
	*to = '\0';
	*cmdline_p = command_line;
	if (usermem)
		printk(KERN_INFO "user-defined physical RAM map:\n");
}

#ifndef CONFIG_DISCONTIGMEM
static unsigned long __init setup_memory(void)
{
	unsigned long start_pfn, max_low_pfn, bootmap_size;

	start_pfn = PFN_UP( __pa(_end) );
	max_low_pfn = PFN_DOWN( __pa(memory_end) );

	/*
	 * Initialize the boot-time allocator (with low memory only):
	 */
	bootmap_size = init_bootmem_node(NODE_DATA(0), start_pfn,
		CONFIG_MEMORY_START>>PAGE_SHIFT, max_low_pfn);

	/*
	 * Register fully available low RAM pages with the bootmem allocator.
	 */
	{
		unsigned long curr_pfn;
		unsigned long last_pfn;
		unsigned long pages;

		/*
		 * We are rounding up the start address of usable memory:
		 */
		curr_pfn = PFN_UP(__pa(memory_start));

		/*
		 * ... and at the end of the usable range downwards:
		 */
		last_pfn = PFN_DOWN(__pa(memory_end));

		if (last_pfn > max_low_pfn)
			last_pfn = max_low_pfn;

		pages = last_pfn - curr_pfn;
		free_bootmem(PFN_PHYS(curr_pfn), PFN_PHYS(pages));
	}

	/*
	 * Reserve the kernel text and
	 * Reserve the bootmem bitmap. We do this in two steps (first step
	 * was init_bootmem()), because this catches the (definitely buggy)
	 * case of us accidentally initializing the bootmem allocator with
	 * an invalid RAM area.
	 */
	reserve_bootmem(CONFIG_MEMORY_START + PAGE_SIZE,
		(PFN_PHYS(start_pfn) + bootmap_size + PAGE_SIZE - 1)
		- CONFIG_MEMORY_START);

	/*
	 * reserve physical page 0 - it's a special BIOS page on many boxes,
	 * enabling clean reboots, SMP operation, laptop functions.
	 */
	reserve_bootmem(CONFIG_MEMORY_START, PAGE_SIZE);

	/*
	 * reserve memory hole
	 */
#ifdef CONFIG_MEMHOLE
	reserve_bootmem(CONFIG_MEMHOLE_START, CONFIG_MEMHOLE_SIZE);
#endif

#ifdef CONFIG_BLK_DEV_INITRD
	if (LOADER_TYPE && INITRD_START) {
		if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) {
			reserve_bootmem(INITRD_START, INITRD_SIZE);
			initrd_start = INITRD_START ?
				INITRD_START + PAGE_OFFSET : 0;

			initrd_end = initrd_start + INITRD_SIZE;
			printk("initrd:start[%08lx],size[%08lx]\n",
				initrd_start, INITRD_SIZE);
		} else {
			printk("initrd extends beyond end of memory "
				"(0x%08lx > 0x%08lx)\ndisabling initrd\n",
				INITRD_START + INITRD_SIZE,
				max_low_pfn << PAGE_SHIFT);

			initrd_start = 0;
		}
	}
#endif

	return max_low_pfn;
}
#else	/* CONFIG_DISCONTIGMEM */
extern unsigned long setup_memory(void);
#endif	/* CONFIG_DISCONTIGMEM */

void __init setup_arch(char **cmdline_p)
{
	ROOT_DEV = old_decode_dev(ORIG_ROOT_DEV);

	boot_cpu_data.cpu_clock = M32R_CPUCLK;
	boot_cpu_data.bus_clock = M32R_BUSCLK;
	boot_cpu_data.timer_divide = M32R_TIMER_DIVIDE;

#ifdef CONFIG_BLK_DEV_RAM
	rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK;
	rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0);
	rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0);
#endif

	if (!MOUNT_ROOT_RDONLY)
		root_mountflags &= ~MS_RDONLY;

#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
	conswitchp = &vga_con;
#elif defined(CONFIG_DUMMY_CONSOLE)
	conswitchp = &dummy_con;
#endif
#endif

#ifdef CONFIG_DISCONTIGMEM
	nodes_clear(node_online_map);
	node_set_online(0);
	node_set_online(1);
#endif	/* CONFIG_DISCONTIGMEM */

	init_mm.start_code = (unsigned long) _text;
	init_mm.end_code = (unsigned long) _etext;
	init_mm.end_data = (unsigned long) _edata;
	init_mm.brk = (unsigned long) _end;

	code_resource.start = virt_to_phys(_text);
	code_resource.end = virt_to_phys(_etext)-1;
	data_resource.start = virt_to_phys(_etext);
	data_resource.end = virt_to_phys(_edata)-1;

	parse_mem_cmdline(cmdline_p);

	setup_memory();

	paging_init();
}

static struct cpu cpu_devices[NR_CPUS];

static int __init topology_init(void)
{
	int i;

	for_each_present_cpu(i)
		register_cpu(&cpu_devices[i], i);

	return 0;
}

subsys_initcall(topology_init);

#ifdef CONFIG_PROC_FS
/*
 *	Get CPU information for use by the procfs.
 */
static int show_cpuinfo(struct seq_file *m, void *v)
{
	struct cpuinfo_m32r *c = v;
	unsigned long cpu = c - cpu_data;

#ifdef CONFIG_SMP
	if (!cpu_online(cpu))
		return 0;
#endif	/* CONFIG_SMP */

	seq_printf(m, "processor\t: %ld\n", cpu);

#if defined(CONFIG_CHIP_VDEC2)
	seq_printf(m, "cpu family\t: VDEC2\n"
		"cache size\t: Unknown\n");
#elif defined(CONFIG_CHIP_M32700)
	seq_printf(m,"cpu family\t: M32700\n"
		"cache size\t: I-8KB/D-8KB\n");
#elif defined(CONFIG_CHIP_M32102)
	seq_printf(m,"cpu family\t: M32102\n"
		"cache size\t: I-8KB\n");
#elif defined(CONFIG_CHIP_OPSP)
	seq_printf(m,"cpu family\t: OPSP\n"
		"cache size\t: I-8KB/D-8KB\n");
#elif defined(CONFIG_CHIP_MP)
	seq_printf(m, "cpu family\t: M32R-MP\n"
		"cache size\t: I-xxKB/D-xxKB\n");
#elif  defined(CONFIG_CHIP_M32104)
	seq_printf(m,"cpu family\t: M32104\n"
		"cache size\t: I-8KB/D-8KB\n");
#else
	seq_printf(m, "cpu family\t: Unknown\n");
#endif
	seq_printf(m, "bogomips\t: %lu.%02lu\n",
		c->loops_per_jiffy/(500000/HZ),
		(c->loops_per_jiffy/(5000/HZ)) % 100);
#if defined(CONFIG_PLAT_MAPPI)
	seq_printf(m, "Machine\t\t: Mappi Evaluation board\n");
#elif defined(CONFIG_PLAT_MAPPI2)
	seq_printf(m, "Machine\t\t: Mappi-II Evaluation board\n");
#elif defined(CONFIG_PLAT_MAPPI3)
	seq_printf(m, "Machine\t\t: Mappi-III Evaluation board\n");
#elif defined(CONFIG_PLAT_M32700UT)
	seq_printf(m, "Machine\t\t: M32700UT Evaluation board\n");
#elif defined(CONFIG_PLAT_OPSPUT)
	seq_printf(m, "Machine\t\t: OPSPUT Evaluation board\n");
#elif defined(CONFIG_PLAT_USRV)
	seq_printf(m, "Machine\t\t: uServer\n");
#elif defined(CONFIG_PLAT_OAKS32R)
	seq_printf(m, "Machine\t\t: OAKS32R\n");
#elif  defined(CONFIG_PLAT_M32104UT)
	seq_printf(m, "Machine\t\t: M3T-M32104UT uT Engine board\n");
#else
	seq_printf(m, "Machine\t\t: Unknown\n");
#endif

#define PRINT_CLOCK(name, value)				\
	seq_printf(m, name " clock\t: %d.%02dMHz\n",		\
		((value) / 1000000), ((value) % 1000000)/10000)

	PRINT_CLOCK("CPU", (int)c->cpu_clock);
	PRINT_CLOCK("Bus", (int)c->bus_clock);

	seq_printf(m, "\n");

	return 0;
}

static void *c_start(struct seq_file *m, loff_t *pos)
{
	return *pos < NR_CPUS ? cpu_data + *pos : NULL;
}

static void *c_next(struct seq_file *m, void *v, loff_t *pos)
{
	++*pos;
	return c_start(m, pos);
}

static void c_stop(struct seq_file *m, void *v)
{
}

struct seq_operations cpuinfo_op = {
	start:	c_start,
	next:	c_next,
	stop:	c_stop,
	show:	show_cpuinfo,
};
#endif	/* CONFIG_PROC_FS */

unsigned long cpu_initialized __initdata = 0;

/*
 * cpu_init() initializes state that is per-CPU. Some data is already
 * initialized (naturally) in the bootstrap process.
 * We reload them nevertheless, this function acts as a
 * 'CPU state barrier', nothing should get across.
 */
#if defined(CONFIG_CHIP_VDEC2) || defined(CONFIG_CHIP_XNUX2)	\
	|| defined(CONFIG_CHIP_M32700) || defined(CONFIG_CHIP_M32102) \
	|| defined(CONFIG_CHIP_OPSP) || defined(CONFIG_CHIP_M32104)
void __init cpu_init (void)
{
	int cpu_id = smp_processor_id();

	if (test_and_set_bit(cpu_id, &cpu_initialized)) {
		printk(KERN_WARNING "CPU#%d already initialized!\n", cpu_id);
		for ( ; ; )
			local_irq_enable();
	}
	printk(KERN_INFO "Initializing CPU#%d\n", cpu_id);

	/* Set up and load the per-CPU TSS and LDT */
	atomic_inc(&init_mm.mm_count);
	current->active_mm = &init_mm;
	if (current->mm)
		BUG();

	/* Force FPU initialization */
	current_thread_info()->status = 0;
	clear_used_math();

#ifdef CONFIG_MMU
	/* Set up MMU */
	init_mmu();
#endif

	/* Set up ICUIMASK */
	outl(0x00070000, M32R_ICU_IMASK_PORTL);		/* imask=111 */
}
#endif	/* defined(CONFIG_CHIP_VDEC2) ... */
74' href='#n1574'>1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757
/*
 *  linux/kernel/signal.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  1997-11-02  Modified for POSIX.1b signals by Richard Henderson
 *
 *  2003-06-02  Jim Houston - Concurrent Computer Corp.
 *		Changes to use preallocated sigqueue structures
 *		to allow signals to be sent reliably.
 */

#include <linux/config.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/tty.h>
#include <linux/binfmts.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/ptrace.h>
#include <linux/posix-timers.h>
#include <linux/signal.h>
#include <linux/audit.h>
#include <linux/capability.h>
#include <asm/param.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/siginfo.h>

/*
 * SLAB caches for signal bits.
 */

static kmem_cache_t *sigqueue_cachep;

/*
 * In POSIX a signal is sent either to a specific thread (Linux task)
 * or to the process as a whole (Linux thread group).  How the signal
 * is sent determines whether it's to one thread or the whole group,
 * which determines which signal mask(s) are involved in blocking it
 * from being delivered until later.  When the signal is delivered,
 * either it's caught or ignored by a user handler or it has a default
 * effect that applies to the whole thread group (POSIX process).
 *
 * The possible effects an unblocked signal set to SIG_DFL can have are:
 *   ignore	- Nothing Happens
 *   terminate	- kill the process, i.e. all threads in the group,
 * 		  similar to exit_group.  The group leader (only) reports
 *		  WIFSIGNALED status to its parent.
 *   coredump	- write a core dump file describing all threads using
 *		  the same mm and then kill all those threads
 *   stop 	- stop all the threads in the group, i.e. TASK_STOPPED state
 *
 * SIGKILL and SIGSTOP cannot be caught, blocked, or ignored.
 * Other signals when not blocked and set to SIG_DFL behaves as follows.
 * The job control signals also have other special effects.
 *
 *	+--------------------+------------------+
 *	|  POSIX signal      |  default action  |
 *	+--------------------+------------------+
 *	|  SIGHUP            |  terminate	|
 *	|  SIGINT            |	terminate	|
 *	|  SIGQUIT           |	coredump 	|
 *	|  SIGILL            |	coredump 	|
 *	|  SIGTRAP           |	coredump 	|
 *	|  SIGABRT/SIGIOT    |	coredump 	|
 *	|  SIGBUS            |	coredump 	|
 *	|  SIGFPE            |	coredump 	|
 *	|  SIGKILL           |	terminate(+)	|
 *	|  SIGUSR1           |	terminate	|
 *	|  SIGSEGV           |	coredump 	|
 *	|  SIGUSR2           |	terminate	|
 *	|  SIGPIPE           |	terminate	|
 *	|  SIGALRM           |	terminate	|
 *	|  SIGTERM           |	terminate	|
 *	|  SIGCHLD           |	ignore   	|
 *	|  SIGCONT           |	ignore(*)	|
 *	|  SIGSTOP           |	stop(*)(+)  	|
 *	|  SIGTSTP           |	stop(*)  	|
 *	|  SIGTTIN           |	stop(*)  	|
 *	|  SIGTTOU           |	stop(*)  	|
 *	|  SIGURG            |	ignore   	|
 *	|  SIGXCPU           |	coredump 	|
 *	|  SIGXFSZ           |	coredump 	|
 *	|  SIGVTALRM         |	terminate	|
 *	|  SIGPROF           |	terminate	|
 *	|  SIGPOLL/SIGIO     |	terminate	|
 *	|  SIGSYS/SIGUNUSED  |	coredump 	|
 *	|  SIGSTKFLT         |	terminate	|
 *	|  SIGWINCH          |	ignore   	|
 *	|  SIGPWR            |	terminate	|
 *	|  SIGRTMIN-SIGRTMAX |	terminate       |
 *	+--------------------+------------------+
 *	|  non-POSIX signal  |  default action  |
 *	+--------------------+------------------+
 *	|  SIGEMT            |  coredump	|
 *	+--------------------+------------------+
 *
 * (+) For SIGKILL and SIGSTOP the action is "always", not just "default".
 * (*) Special job control effects:
 * When SIGCONT is sent, it resumes the process (all threads in the group)
 * from TASK_STOPPED state and also clears any pending/queued stop signals
 * (any of those marked with "stop(*)").  This happens regardless of blocking,
 * catching, or ignoring SIGCONT.  When any stop signal is sent, it clears
 * any pending/queued SIGCONT signals; this happens regardless of blocking,
 * catching, or ignored the stop signal, though (except for SIGSTOP) the
 * default action of stopping the process may happen later or never.
 */

#ifdef SIGEMT
#define M_SIGEMT	M(SIGEMT)
#else
#define M_SIGEMT	0
#endif

#if SIGRTMIN > BITS_PER_LONG
#define M(sig) (1ULL << ((sig)-1))
#else
#define M(sig) (1UL << ((sig)-1))
#endif
#define T(sig, mask) (M(sig) & (mask))

#define SIG_KERNEL_ONLY_MASK (\
	M(SIGKILL)   |  M(SIGSTOP)                                   )

#define SIG_KERNEL_STOP_MASK (\
	M(SIGSTOP)   |  M(SIGTSTP)   |  M(SIGTTIN)   |  M(SIGTTOU)   )

#define SIG_KERNEL_COREDUMP_MASK (\
        M(SIGQUIT)   |  M(SIGILL)    |  M(SIGTRAP)   |  M(SIGABRT)   | \
        M(SIGFPE)    |  M(SIGSEGV)   |  M(SIGBUS)    |  M(SIGSYS)    | \
        M(SIGXCPU)   |  M(SIGXFSZ)   |  M_SIGEMT                     )

#define SIG_KERNEL_IGNORE_MASK (\
        M(SIGCONT)   |  M(SIGCHLD)   |  M(SIGWINCH)  |  M(SIGURG)    )

#define sig_kernel_only(sig) \
		(((sig) < SIGRTMIN)  && T(sig, SIG_KERNEL_ONLY_MASK))
#define sig_kernel_coredump(sig) \
		(((sig) < SIGRTMIN)  && T(sig, SIG_KERNEL_COREDUMP_MASK))
#define sig_kernel_ignore(sig) \
		(((sig) < SIGRTMIN)  && T(sig, SIG_KERNEL_IGNORE_MASK))
#define sig_kernel_stop(sig) \
		(((sig) < SIGRTMIN)  && T(sig, SIG_KERNEL_STOP_MASK))

#define sig_user_defined(t, signr) \
	(((t)->sighand->action[(signr)-1].sa.sa_handler != SIG_DFL) &&	\
	 ((t)->sighand->action[(signr)-1].sa.sa_handler != SIG_IGN))

#define sig_fatal(t, signr) \
	(!T(signr, SIG_KERNEL_IGNORE_MASK|SIG_KERNEL_STOP_MASK) && \
	 (t)->sighand->action[(signr)-1].sa.sa_handler == SIG_DFL)

static int sig_ignored(struct task_struct *t, int sig)
{
	void __user * handler;

	/*
	 * Tracers always want to know about signals..
	 */
	if (t->ptrace & PT_PTRACED)
		return 0;

	/*
	 * Blocked signals are never ignored, since the
	 * signal handler may change by the time it is
	 * unblocked.
	 */
	if (sigismember(&t->blocked, sig))
		return 0;

	/* Is it explicitly or implicitly ignored? */
	handler = t->sighand->action[sig-1].sa.sa_handler;
	return   handler == SIG_IGN ||
		(handler == SIG_DFL && sig_kernel_ignore(sig));
}

/*
 * Re-calculate pending state from the set of locally pending
 * signals, globally pending signals, and blocked signals.
 */
static inline int has_pending_signals(sigset_t *signal, sigset_t *blocked)
{
	unsigned long ready;
	long i;

	switch (_NSIG_WORDS) {
	default:
		for (i = _NSIG_WORDS, ready = 0; --i >= 0 ;)
			ready |= signal->sig[i] &~ blocked->sig[i];
		break;

	case 4: ready  = signal->sig[3] &~ blocked->sig[3];
		ready |= signal->sig[2] &~ blocked->sig[2];
		ready |= signal->sig[1] &~ blocked->sig[1];
		ready |= signal->sig[0] &~ blocked->sig[0];
		break;

	case 2: ready  = signal->sig[1] &~ blocked->sig[1];
		ready |= signal->sig[0] &~ blocked->sig[0];
		break;

	case 1: ready  = signal->sig[0] &~ blocked->sig[0];
	}
	return ready !=	0;
}

#define PENDING(p,b) has_pending_signals(&(p)->signal, (b))

fastcall void recalc_sigpending_tsk(struct task_struct *t)
{
	if (t->signal->group_stop_count > 0 ||
	    (freezing(t)) ||
	    PENDING(&t->pending, &t->blocked) ||
	    PENDING(&t->signal->shared_pending, &t->blocked))
		set_tsk_thread_flag(t, TIF_SIGPENDING);
	else
		clear_tsk_thread_flag(t, TIF_SIGPENDING);
}

void recalc_sigpending(void)
{
	recalc_sigpending_tsk(current);
}

/* Given the mask, find the first available signal that should be serviced. */

static int
next_signal(struct sigpending *pending, sigset_t *mask)
{
	unsigned long i, *s, *m, x;
	int sig = 0;
	
	s = pending->signal.sig;
	m = mask->sig;
	switch (_NSIG_WORDS) {
	default:
		for (i = 0; i < _NSIG_WORDS; ++i, ++s, ++m)
			if ((x = *s &~ *m) != 0) {
				sig = ffz(~x) + i*_NSIG_BPW + 1;
				break;
			}
		break;

	case 2: if ((x = s[0] &~ m[0]) != 0)
			sig = 1;
		else if ((x = s[1] &~ m[1]) != 0)
			sig = _NSIG_BPW + 1;
		else
			break;
		sig += ffz(~x);
		break;

	case 1: if ((x = *s &~ *m) != 0)
			sig = ffz(~x) + 1;
		break;
	}
	
	return sig;
}

static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
					 int override_rlimit)
{
	struct sigqueue *q = NULL;

	atomic_inc(&t->user->sigpending);
	if (override_rlimit ||
	    atomic_read(&t->user->sigpending) <=
			t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur)
		q = kmem_cache_alloc(sigqueue_cachep, flags);
	if (unlikely(q == NULL)) {
		atomic_dec(&t->user->sigpending);
	} else {
		INIT_LIST_HEAD(&q->list);
		q->flags = 0;
		q->user = get_uid(t->user);
	}
	return(q);
}

static inline void __sigqueue_free(struct sigqueue *q)
{
	if (q->flags & SIGQUEUE_PREALLOC)
		return;
	atomic_dec(&q->user->sigpending);
	free_uid(q->user);
	kmem_cache_free(sigqueue_cachep, q);
}

static void flush_sigqueue(struct sigpending *queue)
{
	struct sigqueue *q;

	sigemptyset(&queue->signal);
	while (!list_empty(&queue->list)) {
		q = list_entry(queue->list.next, struct sigqueue , list);
		list_del_init(&q->list);
		__sigqueue_free(q);
	}
}

/*
 * Flush all pending signals for a task.
 */

void
flush_signals(struct task_struct *t)
{
	unsigned long flags;

	spin_lock_irqsave(&t->sighand->siglock, flags);
	clear_tsk_thread_flag(t,TIF_SIGPENDING);
	flush_sigqueue(&t->pending);
	flush_sigqueue(&t->signal->shared_pending);
	spin_unlock_irqrestore(&t->sighand->siglock, flags);
}

/*
 * This function expects the tasklist_lock write-locked.
 */
void __exit_sighand(struct task_struct *tsk)
{
	struct sighand_struct * sighand = tsk->sighand;

	/* Ok, we're done with the signal handlers */
	tsk->sighand = NULL;
	if (atomic_dec_and_test(&sighand->count))
		sighand_free(sighand);
}

void exit_sighand(struct task_struct *tsk)
{
	write_lock_irq(&tasklist_lock);
	rcu_read_lock();
	if (tsk->sighand != NULL) {
		struct sighand_struct *sighand = rcu_dereference(tsk->sighand);
		spin_lock(&sighand->siglock);
		__exit_sighand(tsk);
		spin_unlock(&sighand->siglock);
	}
	rcu_read_unlock();
	write_unlock_irq(&tasklist_lock);
}

/*
 * This function expects the tasklist_lock write-locked.
 */
void __exit_signal(struct task_struct *tsk)
{
	struct signal_struct * sig = tsk->signal;
	struct sighand_struct * sighand;

	if (!sig)
		BUG();
	if (!atomic_read(&sig->count))
		BUG();
	rcu_read_lock();
	sighand = rcu_dereference(tsk->sighand);
	spin_lock(&sighand->siglock);
	posix_cpu_timers_exit(tsk);
	if (atomic_dec_and_test(&sig->count)) {
		posix_cpu_timers_exit_group(tsk);
		tsk->signal = NULL;
		__exit_sighand(tsk);
		spin_unlock(&sighand->siglock);
		flush_sigqueue(&sig->shared_pending);
	} else {
		/*
		 * If there is any task waiting for the group exit
		 * then notify it:
		 */
		if (sig->group_exit_task && atomic_read(&sig->count) == sig->notify_count) {
			wake_up_process(sig->group_exit_task);
			sig->group_exit_task = NULL;
		}
		if (tsk == sig->curr_target)
			sig->curr_target = next_thread(tsk);
		tsk->signal = NULL;
		/*
		 * Accumulate here the counters for all threads but the
		 * group leader as they die, so they can be added into
		 * the process-wide totals when those are taken.
		 * The group leader stays around as a zombie as long
		 * as there are other threads.  When it gets reaped,
		 * the exit.c code will add its counts into these totals.
		 * We won't ever get here for the group leader, since it
		 * will have been the last reference on the signal_struct.
		 */
		sig->utime = cputime_add(sig->utime, tsk->utime);
		sig->stime = cputime_add(sig->stime, tsk->stime);
		sig->min_flt += tsk->min_flt;
		sig->maj_flt += tsk->maj_flt;
		sig->nvcsw += tsk->nvcsw;
		sig->nivcsw += tsk->nivcsw;
		sig->sched_time += tsk->sched_time;
		__exit_sighand(tsk);
		spin_unlock(&sighand->siglock);
		sig = NULL;	/* Marker for below.  */
	}
	rcu_read_unlock();
	clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
	flush_sigqueue(&tsk->pending);
	if (sig) {
		/*
		 * We are cleaning up the signal_struct here.
		 */
		exit_thread_group_keys(sig);
		kmem_cache_free(signal_cachep, sig);
	}
}

void exit_signal(struct task_struct *tsk)
{
	atomic_dec(&tsk->signal->live);

	write_lock_irq(&tasklist_lock);
	__exit_signal(tsk);
	write_unlock_irq(&tasklist_lock);
}

/*
 * Flush all handlers for a task.
 */

void
flush_signal_handlers(struct task_struct *t, int force_default)
{
	int i;
	struct k_sigaction *ka = &t->sighand->action[0];
	for (i = _NSIG ; i != 0 ; i--) {
		if (force_default || ka->sa.sa_handler != SIG_IGN)
			ka->sa.sa_handler = SIG_DFL;
		ka->sa.sa_flags = 0;
		sigemptyset(&ka->sa.sa_mask);
		ka++;
	}
}


/* Notify the system that a driver wants to block all signals for this
 * process, and wants to be notified if any signals at all were to be
 * sent/acted upon.  If the notifier routine returns non-zero, then the
 * signal will be acted upon after all.  If the notifier routine returns 0,
 * then then signal will be blocked.  Only one block per process is
 * allowed.  priv is a pointer to private data that the notifier routine
 * can use to determine if the signal should be blocked or not.  */

void
block_all_signals(int (*notifier)(void *priv), void *priv, sigset_t *mask)
{
	unsigned long flags;

	spin_lock_irqsave(&current->sighand->siglock, flags);
	current->notifier_mask = mask;
	current->notifier_data = priv;
	current->notifier = notifier;
	spin_unlock_irqrestore(&current->sighand->siglock, flags);
}

/* Notify the system that blocking has ended. */

void
unblock_all_signals(void)
{
	unsigned long flags;

	spin_lock_irqsave(&current->sighand->siglock, flags);
	current->notifier = NULL;
	current->notifier_data = NULL;
	recalc_sigpending();
	spin_unlock_irqrestore(&current->sighand->siglock, flags);
}

static int collect_signal(int sig, struct sigpending *list, siginfo_t *info)
{
	struct sigqueue *q, *first = NULL;
	int still_pending = 0;

	if (unlikely(!sigismember(&list->signal, sig)))
		return 0;

	/*
	 * Collect the siginfo appropriate to this signal.  Check if
	 * there is another siginfo for the same signal.
	*/
	list_for_each_entry(q, &list->list, list) {
		if (q->info.si_signo == sig) {
			if (first) {
				still_pending = 1;
				break;
			}
			first = q;
		}
	}
	if (first) {
		list_del_init(&first->list);
		copy_siginfo(info, &first->info);
		__sigqueue_free(first);
		if (!still_pending)
			sigdelset(&list->signal, sig);
	} else {

		/* Ok, it wasn't in the queue.  This must be
		   a fast-pathed signal or we must have been
		   out of queue space.  So zero out the info.
		 */
		sigdelset(&list->signal, sig);
		info->si_signo = sig;
		info->si_errno = 0;
		info->si_code = 0;
		info->si_pid = 0;
		info->si_uid = 0;
	}
	return 1;
}

static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
			siginfo_t *info)
{
	int sig = 0;

	sig = next_signal(pending, mask);
	if (sig) {
		if (current->notifier) {
			if (sigismember(current->notifier_mask, sig)) {
				if (!(current->notifier)(current->notifier_data)) {
					clear_thread_flag(TIF_SIGPENDING);
					return 0;
				}
			}
		}

		if (!collect_signal(sig, pending, info))
			sig = 0;
				
	}
	recalc_sigpending();

	return sig;
}

/*
 * Dequeue a signal and return the element to the caller, which is 
 * expected to free it.
 *
 * All callers have to hold the siglock.
 */
int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
{
	int signr = __dequeue_signal(&tsk->pending, mask, info);
	if (!signr)
		signr = __dequeue_signal(&tsk->signal->shared_pending,
					 mask, info);
 	if (signr && unlikely(sig_kernel_stop(signr))) {
 		/*
 		 * Set a marker that we have dequeued a stop signal.  Our
 		 * caller might release the siglock and then the pending
 		 * stop signal it is about to process is no longer in the
 		 * pending bitmasks, but must still be cleared by a SIGCONT
 		 * (and overruled by a SIGKILL).  So those cases clear this
 		 * shared flag after we've set it.  Note that this flag may
 		 * remain set after the signal we return is ignored or
 		 * handled.  That doesn't matter because its only purpose
 		 * is to alert stop-signal processing code when another
 		 * processor has come along and cleared the flag.
 		 */
 		if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT))
 			tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
 	}
	if ( signr &&
	     ((info->si_code & __SI_MASK) == __SI_TIMER) &&
	     info->si_sys_private){
		/*
		 * Release the siglock to ensure proper locking order
		 * of timer locks outside of siglocks.  Note, we leave
		 * irqs disabled here, since the posix-timers code is
		 * about to disable them again anyway.
		 */
		spin_unlock(&tsk->sighand->siglock);
		do_schedule_next_timer(info);
		spin_lock(&tsk->sighand->siglock);
	}
	return signr;
}

/*
 * Tell a process that it has a new active signal..
 *
 * NOTE! we rely on the previous spin_lock to
 * lock interrupts for us! We can only be called with
 * "siglock" held, and the local interrupt must
 * have been disabled when that got acquired!
 *
 * No need to set need_resched since signal event passing
 * goes through ->blocked
 */
void signal_wake_up(struct task_struct *t, int resume)
{
	unsigned int mask;

	set_tsk_thread_flag(t, TIF_SIGPENDING);

	/*
	 * For SIGKILL, we want to wake it up in the stopped/traced case.
	 * We don't check t->state here because there is a race with it
	 * executing another processor and just now entering stopped state.
	 * By using wake_up_state, we ensure the process will wake up and
	 * handle its death signal.
	 */
	mask = TASK_INTERRUPTIBLE;
	if (resume)
		mask |= TASK_STOPPED | TASK_TRACED;
	if (!wake_up_state(t, mask))
		kick_process(t);
}

/*
 * Remove signals in mask from the pending set and queue.
 * Returns 1 if any signals were found.
 *
 * All callers must be holding the siglock.
 *
 * This version takes a sigset mask and looks at all signals,
 * not just those in the first mask word.
 */
static int rm_from_queue_full(sigset_t *mask, struct sigpending *s)
{
	struct sigqueue *q, *n;
	sigset_t m;

	sigandsets(&m, mask, &s->signal);
	if (sigisemptyset(&m))
		return 0;

	signandsets(&s->signal, &s->signal, mask);
	list_for_each_entry_safe(q, n, &s->list, list) {
		if (sigismember(mask, q->info.si_signo)) {
			list_del_init(&q->list);
			__sigqueue_free(q);
		}
	}
	return 1;
}
/*
 * Remove signals in mask from the pending set and queue.
 * Returns 1 if any signals were found.
 *
 * All callers must be holding the siglock.
 */
static int rm_from_queue(unsigned long mask, struct sigpending *s)
{
	struct sigqueue *q, *n;

	if (!sigtestsetmask(&s->signal, mask))
		return 0;

	sigdelsetmask(&s->signal, mask);
	list_for_each_entry_safe(q, n, &s->list, list) {
		if (q->info.si_signo < SIGRTMIN &&
		    (mask & sigmask(q->info.si_signo))) {
			list_del_init(&q->list);
			__sigqueue_free(q);
		}
	}
	return 1;
}

/*
 * Bad permissions for sending the signal
 */
static int check_kill_permission(int sig, struct siginfo *info,
				 struct task_struct *t)
{
	int error = -EINVAL;
	if (!valid_signal(sig))
		return error;
	error = -EPERM;
	if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)))
	    && ((sig != SIGCONT) ||
		(current->signal->session != t->signal->session))
	    && (current->euid ^ t->suid) && (current->euid ^ t->uid)
	    && (current->uid ^ t->suid) && (current->uid ^ t->uid)
	    && !capable(CAP_KILL))
		return error;

	error = security_task_kill(t, info, sig);
	if (!error)
		audit_signal_info(sig, t); /* Let audit system see the signal */
	return error;
}

/* forward decl */
static void do_notify_parent_cldstop(struct task_struct *tsk,
				     int to_self,
				     int why);

/*
 * Handle magic process-wide effects of stop/continue signals.
 * Unlike the signal actions, these happen immediately at signal-generation
 * time regardless of blocking, ignoring, or handling.  This does the
 * actual continuing for SIGCONT, but not the actual stopping for stop
 * signals.  The process stop is done as a signal action for SIG_DFL.
 */
static void handle_stop_signal(int sig, struct task_struct *p)
{
	struct task_struct *t;

	if (p->signal->flags & SIGNAL_GROUP_EXIT)
		/*
		 * The process is in the middle of dying already.
		 */
		return;

	if (sig_kernel_stop(sig)) {
		/*
		 * This is a stop signal.  Remove SIGCONT from all queues.
		 */
		rm_from_queue(sigmask(SIGCONT), &p->signal->shared_pending);
		t = p;
		do {
			rm_from_queue(sigmask(SIGCONT), &t->pending);
			t = next_thread(t);
		} while (t != p);
	} else if (sig == SIGCONT) {
		/*
		 * Remove all stop signals from all queues,
		 * and wake all threads.
		 */
		if (unlikely(p->signal->group_stop_count > 0)) {
			/*
			 * There was a group stop in progress.  We'll
			 * pretend it finished before we got here.  We are
			 * obliged to report it to the parent: if the
			 * SIGSTOP happened "after" this SIGCONT, then it
			 * would have cleared this pending SIGCONT.  If it
			 * happened "before" this SIGCONT, then the parent
			 * got the SIGCHLD about the stop finishing before
			 * the continue happened.  We do the notification
			 * now, and it's as if the stop had finished and
			 * the SIGCHLD was pending on entry to this kill.
			 */
			p->signal->group_stop_count = 0;
			p->signal->flags = SIGNAL_STOP_CONTINUED;
			spin_unlock(&p->sighand->siglock);
			do_notify_parent_cldstop(p, (p->ptrace & PT_PTRACED), CLD_STOPPED);
			spin_lock(&p->sighand->siglock);
		}
		rm_from_queue(SIG_KERNEL_STOP_MASK, &p->signal->shared_pending);
		t = p;
		do {
			unsigned int state;
			rm_from_queue(SIG_KERNEL_STOP_MASK, &t->pending);
			
			/*
			 * If there is a handler for SIGCONT, we must make
			 * sure that no thread returns to user mode before
			 * we post the signal, in case it was the only
			 * thread eligible to run the signal handler--then
			 * it must not do anything between resuming and
			 * running the handler.  With the TIF_SIGPENDING
			 * flag set, the thread will pause and acquire the
			 * siglock that we hold now and until we've queued
			 * the pending signal. 
			 *
			 * Wake up the stopped thread _after_ setting
			 * TIF_SIGPENDING
			 */
			state = TASK_STOPPED;
			if (sig_user_defined(t, SIGCONT) && !sigismember(&t->blocked, SIGCONT)) {
				set_tsk_thread_flag(t, TIF_SIGPENDING);
				state |= TASK_INTERRUPTIBLE;
			}
			wake_up_state(t, state);

			t = next_thread(t);
		} while (t != p);

		if (p->signal->flags & SIGNAL_STOP_STOPPED) {
			/*
			 * We were in fact stopped, and are now continued.
			 * Notify the parent with CLD_CONTINUED.
			 */
			p->signal->flags = SIGNAL_STOP_CONTINUED;
			p->signal->group_exit_code = 0;
			spin_unlock(&p->sighand->siglock);
			do_notify_parent_cldstop(p, (p->ptrace & PT_PTRACED), CLD_CONTINUED);
			spin_lock(&p->sighand->siglock);
		} else {
			/*
			 * We are not stopped, but there could be a stop
			 * signal in the middle of being processed after
			 * being removed from the queue.  Clear that too.
			 */
			p->signal->flags = 0;
		}
	} else if (sig == SIGKILL) {
		/*
		 * Make sure that any pending stop signal already dequeued
		 * is undone by the wakeup for SIGKILL.
		 */
		p->signal->flags = 0;
	}
}

static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
			struct sigpending *signals)
{
	struct sigqueue * q = NULL;
	int ret = 0;

	/*
	 * fast-pathed signals for kernel-internal things like SIGSTOP
	 * or SIGKILL.
	 */
	if (info == SEND_SIG_FORCED)
		goto out_set;

	/* Real-time signals must be queued if sent by sigqueue, or
	   some other real-time mechanism.  It is implementation
	   defined whether kill() does so.  We attempt to do so, on
	   the principle of least surprise, but since kill is not
	   allowed to fail with EAGAIN when low on memory we just
	   make sure at least one signal gets delivered and don't
	   pass on the info struct.  */

	q = __sigqueue_alloc(t, GFP_ATOMIC, (sig < SIGRTMIN &&
					     (is_si_special(info) ||
					      info->si_code >= 0)));
	if (q) {
		list_add_tail(&q->list, &signals->list);
		switch ((unsigned long) info) {
		case (unsigned long) SEND_SIG_NOINFO:
			q->info.si_signo = sig;
			q->info.si_errno = 0;
			q->info.si_code = SI_USER;
			q->info.si_pid = current->pid;
			q->info.si_uid = current->uid;
			break;
		case (unsigned long) SEND_SIG_PRIV:
			q->info.si_signo = sig;
			q->info.si_errno = 0;
			q->info.si_code = SI_KERNEL;
			q->info.si_pid = 0;
			q->info.si_uid = 0;
			break;
		default:
			copy_siginfo(&q->info, info);
			break;
		}
	} else if (!is_si_special(info)) {
		if (sig >= SIGRTMIN && info->si_code != SI_USER)
		/*
		 * Queue overflow, abort.  We may abort if the signal was rt
		 * and sent by user using something other than kill().
		 */
			return -EAGAIN;
	}

out_set:
	sigaddset(&signals->signal, sig);
	return ret;
}

#define LEGACY_QUEUE(sigptr, sig) \
	(((sig) < SIGRTMIN) && sigismember(&(sigptr)->signal, (sig)))


static int
specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t)
{
	int ret = 0;

	if (!irqs_disabled())
		BUG();
	assert_spin_locked(&t->sighand->siglock);

	/* Short-circuit ignored signals.  */
	if (sig_ignored(t, sig))
		goto out;

	/* Support queueing exactly one non-rt signal, so that we
	   can get more detailed information about the cause of
	   the signal. */
	if (LEGACY_QUEUE(&t->pending, sig))
		goto out;

	ret = send_signal(sig, info, t, &t->pending);
	if (!ret && !sigismember(&t->blocked, sig))
		signal_wake_up(t, sig == SIGKILL);
out:
	return ret;
}

/*
 * Force a signal that the process can't ignore: if necessary
 * we unblock the signal and change any SIG_IGN to SIG_DFL.
 */

int
force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
{
	unsigned long int flags;
	int ret;

	spin_lock_irqsave(&t->sighand->siglock, flags);
	if (t->sighand->action[sig-1].sa.sa_handler == SIG_IGN) {
		t->sighand->action[sig-1].sa.sa_handler = SIG_DFL;
	}
	if (sigismember(&t->blocked, sig)) {
		sigdelset(&t->blocked, sig);
	}
	recalc_sigpending_tsk(t);
	ret = specific_send_sig_info(sig, info, t);
	spin_unlock_irqrestore(&t->sighand->siglock, flags);

	return ret;
}

void
force_sig_specific(int sig, struct task_struct *t)
{
	force_sig_info(sig, SEND_SIG_FORCED, t);
}

/*
 * Test if P wants to take SIG.  After we've checked all threads with this,
 * it's equivalent to finding no threads not blocking SIG.  Any threads not
 * blocking SIG were ruled out because they are not running and already
 * have pending signals.  Such threads will dequeue from the shared queue
 * as soon as they're available, so putting the signal on the shared queue
 * will be equivalent to sending it to one such thread.
 */
static inline int wants_signal(int sig, struct task_struct *p)
{
	if (sigismember(&p->blocked, sig))
		return 0;
	if (p->flags & PF_EXITING)
		return 0;
	if (sig == SIGKILL)
		return 1;
	if (p->state & (TASK_STOPPED | TASK_TRACED))
		return 0;
	return task_curr(p) || !signal_pending(p);
}

static void
__group_complete_signal(int sig, struct task_struct *p)
{
	struct task_struct *t;

	/*
	 * Now find a thread we can wake up to take the signal off the queue.
	 *
	 * If the main thread wants the signal, it gets first crack.
	 * Probably the least surprising to the average bear.
	 */
	if (wants_signal(sig, p))
		t = p;
	else if (thread_group_empty(p))
		/*
		 * There is just one thread and it does not need to be woken.
		 * It will dequeue unblocked signals before it runs again.
		 */
		return;
	else {
		/*
		 * Otherwise try to find a suitable thread.
		 */
		t = p->signal->curr_target;
		if (t == NULL)
			/* restart balancing at this thread */
			t = p->signal->curr_target = p;
		BUG_ON(t->tgid != p->tgid);

		while (!wants_signal(sig, t)) {
			t = next_thread(t);
			if (t == p->signal->curr_target)
				/*
				 * No thread needs to be woken.
				 * Any eligible threads will see
				 * the signal in the queue soon.
				 */
				return;
		}
		p->signal->curr_target = t;
	}

	/*
	 * Found a killable thread.  If the signal will be fatal,
	 * then start taking the whole group down immediately.
	 */
	if (sig_fatal(p, sig) && !(p->signal->flags & SIGNAL_GROUP_EXIT) &&
	    !sigismember(&t->real_blocked, sig) &&
	    (sig == SIGKILL || !(t->ptrace & PT_PTRACED))) {
		/*
		 * This signal will be fatal to the whole group.
		 */
		if (!sig_kernel_coredump(sig)) {
			/*
			 * Start a group exit and wake everybody up.
			 * This way we don't have other threads
			 * running and doing things after a slower
			 * thread has the fatal signal pending.
			 */
			p->signal->flags = SIGNAL_GROUP_EXIT;
			p->signal->group_exit_code = sig;
			p->signal->group_stop_count = 0;
			t = p;
			do {
				sigaddset(&t->pending.signal, SIGKILL);
				signal_wake_up(t, 1);
				t = next_thread(t);
			} while (t != p);
			return;
		}

		/*
		 * There will be a core dump.  We make all threads other
		 * than the chosen one go into a group stop so that nothing
		 * happens until it gets scheduled, takes the signal off
		 * the shared queue, and does the core dump.  This is a
		 * little more complicated than strictly necessary, but it
		 * keeps the signal state that winds up in the core dump
		 * unchanged from the death state, e.g. which thread had
		 * the core-dump signal unblocked.
		 */
		rm_from_queue(SIG_KERNEL_STOP_MASK, &t->pending);
		rm_from_queue(SIG_KERNEL_STOP_MASK, &p->signal->shared_pending);
		p->signal->group_stop_count = 0;
		p->signal->group_exit_task = t;
		t = p;
		do {
			p->signal->group_stop_count++;
			signal_wake_up(t, 0);
			t = next_thread(t);
		} while (t != p);
		wake_up_process(p->signal->group_exit_task);
		return;
	}

	/*
	 * The signal is already in the shared-pending queue.
	 * Tell the chosen thread to wake up and dequeue it.
	 */
	signal_wake_up(t, sig == SIGKILL);
	return;
}

int
__group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
	int ret = 0;

	assert_spin_locked(&p->sighand->siglock);
	handle_stop_signal(sig, p);

	/* Short-circuit ignored signals.  */
	if (sig_ignored(p, sig))
		return ret;

	if (LEGACY_QUEUE(&p->signal->shared_pending, sig))
		/* This is a non-RT signal and we already have one queued.  */
		return ret;

	/*
	 * Put this signal on the shared-pending queue, or fail with EAGAIN.
	 * We always use the shared queue for process-wide signals,
	 * to avoid several races.
	 */
	ret = send_signal(sig, info, p, &p->signal->shared_pending);
	if (unlikely(ret))
		return ret;

	__group_complete_signal(sig, p);
	return 0;
}

/*
 * Nuke all other threads in the group.
 */
void zap_other_threads(struct task_struct *p)
{
	struct task_struct *t;

	p->signal->flags = SIGNAL_GROUP_EXIT;
	p->signal->group_stop_count = 0;

	if (thread_group_empty(p))
		return;

	for (t = next_thread(p); t != p; t = next_thread(t)) {
		/*
		 * Don't bother with already dead threads
		 */
		if (t->exit_state)
			continue;

		/*
		 * We don't want to notify the parent, since we are
		 * killed as part of a thread group due to another
		 * thread doing an execve() or similar. So set the
		 * exit signal to -1 to allow immediate reaping of
		 * the process.  But don't detach the thread group
		 * leader.
		 */
		if (t != p->group_leader)
			t->exit_signal = -1;

		/* SIGKILL will be handled before any pending SIGSTOP */
		sigaddset(&t->pending.signal, SIGKILL);
		signal_wake_up(t, 1);
	}
}

/*
 * Must be called under rcu_read_lock() or with tasklist_lock read-held.
 */
int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
	unsigned long flags;
	struct sighand_struct *sp;
	int ret;

retry:
	ret = check_kill_permission(sig, info, p);
	if (!ret && sig && (sp = rcu_dereference(p->sighand))) {
		spin_lock_irqsave(&sp->siglock, flags);
		if (p->sighand != sp) {
			spin_unlock_irqrestore(&sp->siglock, flags);
			goto retry;
		}
		if ((atomic_read(&sp->count) == 0) ||
				(atomic_read(&p->usage) == 0)) {
			spin_unlock_irqrestore(&sp->siglock, flags);
			return -ESRCH;
		}
		ret = __group_send_sig_info(sig, info, p);
		spin_unlock_irqrestore(&sp->siglock, flags);
	}

	return ret;
}

/*
 * kill_pg_info() sends a signal to a process group: this is what the tty
 * control characters do (^C, ^Z etc)
 */

int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp)
{
	struct task_struct *p = NULL;
	int retval, success;

	if (pgrp <= 0)
		return -EINVAL;

	success = 0;
	retval = -ESRCH;
	do_each_task_pid(pgrp, PIDTYPE_PGID, p) {
		int err = group_send_sig_info(sig, info, p);
		success |= !err;
		retval = err;
	} while_each_task_pid(pgrp, PIDTYPE_PGID, p);
	return success ? 0 : retval;
}

int
kill_pg_info(int sig, struct siginfo *info, pid_t pgrp)
{
	int retval;

	read_lock(&tasklist_lock);
	retval = __kill_pg_info(sig, info, pgrp);
	read_unlock(&tasklist_lock);

	return retval;
}

int
kill_proc_info(int sig, struct siginfo *info, pid_t pid)
{
	int error;
	int acquired_tasklist_lock = 0;
	struct task_struct *p;

	rcu_read_lock();
	if (unlikely(sig_kernel_stop(sig) || sig == SIGCONT)) {
		read_lock(&tasklist_lock);
		acquired_tasklist_lock = 1;
	}
	p = find_task_by_pid(pid);
	error = -ESRCH;
	if (p)
		error = group_send_sig_info(sig, info, p);
	if (unlikely(acquired_tasklist_lock))
		read_unlock(&tasklist_lock);
	rcu_read_unlock();
	return error;
}

/* like kill_proc_info(), but doesn't use uid/euid of "current" */
int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid,
		      uid_t uid, uid_t euid)
{
	int ret = -EINVAL;
	struct task_struct *p;

	if (!valid_signal(sig))
		return ret;

	read_lock(&tasklist_lock);
	p = find_task_by_pid(pid);
	if (!p) {
		ret = -ESRCH;
		goto out_unlock;
	}
	if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)))
	    && (euid != p->suid) && (euid != p->uid)
	    && (uid != p->suid) && (uid != p->uid)) {
		ret = -EPERM;
		goto out_unlock;
	}
	if (sig && p->sighand) {
		unsigned long flags;
		spin_lock_irqsave(&p->sighand->siglock, flags);
		ret = __group_send_sig_info(sig, info, p);
		spin_unlock_irqrestore(&p->sighand->siglock, flags);
	}
out_unlock:
	read_unlock(&tasklist_lock);
	return ret;
}
EXPORT_SYMBOL_GPL(kill_proc_info_as_uid);

/*
 * kill_something_info() interprets pid in interesting ways just like kill(2).
 *
 * POSIX specifies that kill(-1,sig) is unspecified, but what we have
 * is probably wrong.  Should make it like BSD or SYSV.
 */

static int kill_something_info(int sig, struct siginfo *info, int pid)
{
	if (!pid) {
		return kill_pg_info(sig, info, process_group(current));
	} else if (pid == -1) {
		int retval = 0, count = 0;
		struct task_struct * p;

		read_lock(&tasklist_lock);
		for_each_process(p) {
			if (p->pid > 1 && p->tgid != current->tgid) {
				int err = group_send_sig_info(sig, info, p);
				++count;
				if (err != -EPERM)
					retval = err;
			}
		}
		read_unlock(&tasklist_lock);
		return count ? retval : -ESRCH;
	} else if (pid < 0) {
		return kill_pg_info(sig, info, -pid);
	} else {
		return kill_proc_info(sig, info, pid);
	}
}

/*
 * These are for backward compatibility with the rest of the kernel source.
 */

/*
 * These two are the most common entry points.  They send a signal
 * just to the specific thread.
 */
int
send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
	int ret;
	unsigned long flags;

	/*
	 * Make sure legacy kernel users don't send in bad values
	 * (normal paths check this in check_kill_permission).
	 */
	if (!valid_signal(sig))
		return -EINVAL;

	/*
	 * We need the tasklist lock even for the specific
	 * thread case (when we don't need to follow the group
	 * lists) in order to avoid races with "p->sighand"
	 * going away or changing from under us.
	 */
	read_lock(&tasklist_lock);  
	spin_lock_irqsave(&p->sighand->siglock, flags);
	ret = specific_send_sig_info(sig, info, p);
	spin_unlock_irqrestore(&p->sighand->siglock, flags);
	read_unlock(&tasklist_lock);
	return ret;
}

#define __si_special(priv) \
	((priv) ? SEND_SIG_PRIV : SEND_SIG_NOINFO)

int
send_sig(int sig, struct task_struct *p, int priv)
{
	return send_sig_info(sig, __si_special(priv), p);
}

/*
 * This is the entry point for "process-wide" signals.
 * They will go to an appropriate thread in the thread group.
 */
int
send_group_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
	int ret;
	read_lock(&tasklist_lock);
	ret = group_send_sig_info(sig, info, p);
	read_unlock(&tasklist_lock);
	return ret;
}

void
force_sig(int sig, struct task_struct *p)
{
	force_sig_info(sig, SEND_SIG_PRIV, p);
}

/*
 * When things go south during signal handling, we
 * will force a SIGSEGV. And if the signal that caused
 * the problem was already a SIGSEGV, we'll want to
 * make sure we don't even try to deliver the signal..
 */
int
force_sigsegv(int sig, struct task_struct *p)
{
	if (sig == SIGSEGV) {
		unsigned long flags;
		spin_lock_irqsave(&p->sighand->siglock, flags);
		p->sighand->action[sig - 1].sa.sa_handler = SIG_DFL;
		spin_unlock_irqrestore(&p->sighand->siglock, flags);
	}
	force_sig(SIGSEGV, p);
	return 0;
}

int
kill_pg(pid_t pgrp, int sig, int priv)
{
	return kill_pg_info(sig, __si_special(priv), pgrp);
}

int
kill_proc(pid_t pid, int sig, int priv)
{
	return kill_proc_info(sig, __si_special(priv), pid);
}

/*
 * These functions support sending signals using preallocated sigqueue
 * structures.  This is needed "because realtime applications cannot
 * afford to lose notifications of asynchronous events, like timer
 * expirations or I/O completions".  In the case of Posix Timers 
 * we allocate the sigqueue structure from the timer_create.  If this
 * allocation fails we are able to report the failure to the application
 * with an EAGAIN error.
 */
 
struct sigqueue *sigqueue_alloc(void)
{
	struct sigqueue *q;

	if ((q = __sigqueue_alloc(current, GFP_KERNEL, 0)))
		q->flags |= SIGQUEUE_PREALLOC;
	return(q);
}

void sigqueue_free(struct sigqueue *q)
{
	unsigned long flags;
	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
	/*
	 * If the signal is still pending remove it from the
	 * pending queue.
	 */
	if (unlikely(!list_empty(&q->list))) {
		spinlock_t *lock = &current->sighand->siglock;
		read_lock(&tasklist_lock);
		spin_lock_irqsave(lock, flags);
		if (!list_empty(&q->list))
			list_del_init(&q->list);
		spin_unlock_irqrestore(lock, flags);
		read_unlock(&tasklist_lock);
	}
	q->flags &= ~SIGQUEUE_PREALLOC;
	__sigqueue_free(q);
}

int
send_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
{
	unsigned long flags;
	int ret = 0;
	struct sighand_struct *sh;

	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));

	/*
	 * The rcu based delayed sighand destroy makes it possible to
	 * run this without tasklist lock held. The task struct itself
	 * cannot go away as create_timer did get_task_struct().
	 *
	 * We return -1, when the task is marked exiting, so
	 * posix_timer_event can redirect it to the group leader
	 */
	rcu_read_lock();

	if (unlikely(p->flags & PF_EXITING)) {
		ret = -1;
		goto out_err;
	}

retry:
	sh = rcu_dereference(p->sighand);

	spin_lock_irqsave(&sh->siglock, flags);
	if (p->sighand != sh) {
		/* We raced with exec() in a multithreaded process... */
		spin_unlock_irqrestore(&sh->siglock, flags);
		goto retry;
	}

	/*
	 * We do the check here again to handle the following scenario:
	 *
	 * CPU 0		CPU 1
	 * send_sigqueue
	 * check PF_EXITING
	 * interrupt		exit code running
	 *			__exit_signal
	 *			lock sighand->siglock
	 *			unlock sighand->siglock
	 * lock sh->siglock
	 * add(tsk->pending) 	flush_sigqueue(tsk->pending)
	 *
	 */

	if (unlikely(p->flags & PF_EXITING)) {
		ret = -1;
		goto out;
	}

	if (unlikely(!list_empty(&q->list))) {
		/*
		 * If an SI_TIMER entry is already queue just increment
		 * the overrun count.
		 */
		if (q->info.si_code != SI_TIMER)
			BUG();
		q->info.si_overrun++;
		goto out;
	}
	/* Short-circuit ignored signals.  */
	if (sig_ignored(p, sig)) {
		ret = 1;
		goto out;
	}

	list_add_tail(&q->list, &p->pending.list);
	sigaddset(&p->pending.signal, sig);
	if (!sigismember(&p->blocked, sig))
		signal_wake_up(p, sig == SIGKILL);

out:
	spin_unlock_irqrestore(&sh->siglock, flags);
out_err:
	rcu_read_unlock();

	return ret;
}

int
send_group_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
{
	unsigned long flags;
	int ret = 0;

	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));

	read_lock(&tasklist_lock);
	/* Since it_lock is held, p->sighand cannot be NULL. */
	spin_lock_irqsave(&p->sighand->siglock, flags);
	handle_stop_signal(sig, p);

	/* Short-circuit ignored signals.  */
	if (sig_ignored(p, sig)) {
		ret = 1;
		goto out;
	}

	if (unlikely(!list_empty(&q->list))) {
		/*
		 * If an SI_TIMER entry is already queue just increment
		 * the overrun count.  Other uses should not try to
		 * send the signal multiple times.
		 */
		if (q->info.si_code != SI_TIMER)
			BUG();
		q->info.si_overrun++;
		goto out;
	} 

	/*
	 * Put this signal on the shared-pending queue.
	 * We always use the shared queue for process-wide signals,
	 * to avoid several races.
	 */
	list_add_tail(&q->list, &p->signal->shared_pending.list);
	sigaddset(&p->signal->shared_pending.signal, sig);

	__group_complete_signal(sig, p);
out: