aboutsummaryrefslogtreecommitdiffstats
path: root/net/x25/x25_facilities.c
blob: 8e1a49b0c0dc5c58d0a69ffd25525f8d7b07211e (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
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *	X.25 Packet Layer release 002
 *
 *	This is ALPHA test software. This code may break your machine,
 *	randomly fail to work with new releases, misbehave and/or generally
 *	screw up. It might even work.
 *
 *	This code REQUIRES 2.1.15 or higher
 *
 *	History
 *	X.25 001	Split from x25_subr.c
 *	mar/20/00	Daniela Squassoni Disabling/enabling of facilities
 *					  negotiation.
 *	apr/14/05	Shaun Pereira - Allow fast select with no restriction
 *					on response.
 */

#define pr_fmt(fmt) "X25: " fmt

#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/x25.h>

/**
 * x25_parse_facilities - Parse facilities from skb into the facilities structs
 *
 * @skb: sk_buff to parse
 * @facilities: Regular facilities, updated as facilities are found
 * @dte_facs: ITU DTE facilities, updated as DTE facilities are found
 * @vc_fac_mask: mask is updated with all facilities found
 *
 * Return codes:
 *  -1 - Parsing error, caller should drop call and clean up
 *   0 - Parse OK, this skb has no facilities
 *  >0 - Parse OK, returns the length of the facilities header
 *
 */
int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities,
		struct x25_dte_facilities *dte_facs, unsigned long *vc_fac_mask)
{
	unsigned char *p;
	unsigned int len;

	*vc_fac_mask = 0;

	/*
	 * The kernel knows which facilities were set on an incoming call but
	 * currently this information is not available to userspace.  Here we
	 * give userspace who read incoming call facilities 0 length to indicate
	 * it wasn't set.
	 */
	dte_facs->calling_len = 0;
	dte_facs->called_len = 0;
	memset(dte_facs->called_ae, '\0', sizeof(dte_facs->called_ae));
	memset(dte_facs->calling_ae, '\0', sizeof(dte_facs->calling_ae));

	if (!pskb_may_pull(skb, 1))
		return 0;

	len = skb->data[0];

	if (!pskb_may_pull(skb, 1 + len))
		return -1;

	p = skb->data + 1;

	while (len > 0) {
		switch (*p & X25_FAC_CLASS_MASK) {
		case X25_FAC_CLASS_A:
			if (len < 2)
				return -1;
			switch (*p) {
			case X25_FAC_REVERSE:
				if((p[1] & 0x81) == 0x81) {
					facilities->reverse = p[1] & 0x81;
					*vc_fac_mask |= X25_MASK_REVERSE;
					break;
				}

				if((p[1] & 0x01) == 0x01) {
					facilities->reverse = p[1] & 0x01;
					*vc_fac_mask |= X25_MASK_REVERSE;
					break;
				}

				if((p[1] & 0x80) == 0x80) {
					facilities->reverse = p[1] & 0x80;
					*vc_fac_mask |= X25_MASK_REVERSE;
					break;
				}

				if(p[1] == 0x00) {
					facilities->reverse
						= X25_DEFAULT_REVERSE;
					*vc_fac_mask |= X25_MASK_REVERSE;
					break;
				}
				fallthrough;
			case X25_FAC_THROUGHPUT:
				facilities->throughput = p[1];
				*vc_fac_mask |= X25_MASK_THROUGHPUT;
				break;
			case X25_MARKER:
				break;
			default:
				pr_debug("unknown facility "
				       "%02X, value %02X\n",
				       p[0], p[1]);
				break;
			}
			p   += 2;
			len -= 2;
			break;
		case X25_FAC_CLASS_B:
			if (len < 3)
				return -1;
			switch (*p) {
			case X25_FAC_PACKET_SIZE:
				facilities->pacsize_in  = p[1];
				facilities->pacsize_out = p[2];
				*vc_fac_mask |= X25_MASK_PACKET_SIZE;
				break;
			case X25_FAC_WINDOW_SIZE:
				facilities->winsize_in  = p[1];
				facilities->winsize_out = p[2];
				*vc_fac_mask |= X25_MASK_WINDOW_SIZE;
				break;
			default:
				pr_debug("unknown facility "
				       "%02X, values %02X, %02X\n",
				       p[0], p[1], p[2]);
				break;
			}
			p   += 3;
			len -= 3;
			break;
		case X25_FAC_CLASS_C:
			if (len < 4)
				return -1;
			pr_debug("unknown facility %02X, "
			       "values %02X, %02X, %02X\n",
			       p[0], p[1], p[2], p[3]);
			p   += 4;
			len -= 4;
			break;
		case X25_FAC_CLASS_D:
			if (len < p[1] + 2)
				return -1;
			switch (*p) {
			case X25_FAC_CALLING_AE:
				if (p[1] > X25_MAX_DTE_FACIL_LEN || p[1] <= 1)
					return -1;
				if (p[2] > X25_MAX_AE_LEN)
					return -1;
				dte_facs->calling_len = p[2];
				memcpy(dte_facs->calling_ae, &p[3], p[1] - 1);
				*vc_fac_mask |= X25_MASK_CALLING_AE;
				break;
			case X25_FAC_CALLED_AE:
				if (p[1] > X25_MAX_DTE_FACIL_LEN || p[1] <= 1)
					return -1;
				if (p[2] > X25_MAX_AE_LEN)
					return -1;
				dte_facs->called_len = p[2];
				memcpy(dte_facs->called_ae, &p[3], p[1] - 1);
				*vc_fac_mask |= X25_MASK_CALLED_AE;
				break;
			default:
				pr_debug("unknown facility %02X,"
					"length %d\n", p[0], p[1]);
				break;
			}
			len -= p[1] + 2;
			p += p[1] + 2;
			break;
		}
	}

	return p - skb->data;
}

/*
 *	Create a set of facilities.
 */
int x25_create_facilities(unsigned char *buffer,
		struct x25_facilities *facilities,
		struct x25_dte_facilities *dte_facs, unsigned long facil_mask)
{
	unsigned char *p = buffer + 1;
	int len;

	if (!facil_mask) {
		/*
		 * Length of the facilities field in call_req or
		 * call_accept packets
		 */
		buffer[0] = 0;
		len = 1; /* 1 byte for the length field */
		return len;
	}

	if (facilities->reverse && (facil_mask & X25_MASK_REVERSE)) {
		*p++ = X25_FAC_REVERSE;
		*p++ = facilities->reverse;
	}

	if (facilities->throughput && (facil_mask & X25_MASK_THROUGHPUT)) {
		*p++ = X25_FAC_THROUGHPUT;
		*p++ = facilities->throughput;
	}

	if ((facilities->pacsize_in || facilities->pacsize_out) &&
	    (facil_mask & X25_MASK_PACKET_SIZE)) {
		*p++ = X25_FAC_PACKET_SIZE;
		*p++ = facilities->pacsize_in ? : facilities->pacsize_out;
		*p++ = facilities->pacsize_out ? : facilities->pacsize_in;
	}

	if ((facilities->winsize_in || facilities->winsize_out) &&
	    (facil_mask & X25_MASK_WINDOW_SIZE)) {
		*p++ = X25_FAC_WINDOW_SIZE;
		*p++ = facilities->winsize_in ? : facilities->winsize_out;
		*p++ = facilities->winsize_out ? : facilities->winsize_in;
	}

	if (facil_mask & (X25_MASK_CALLING_AE|X25_MASK_CALLED_AE)) {
		*p++ = X25_MARKER;
		*p++ = X25_DTE_SERVICES;
	}

	if (dte_facs->calling_len && (facil_mask & X25_MASK_CALLING_AE)) {
		unsigned int bytecount = (dte_facs->calling_len + 1) >> 1;
		*p++ = X25_FAC_CALLING_AE;
		*p++ = 1 + bytecount;
		*p++ = dte_facs->calling_len;
		memcpy(p, dte_facs->calling_ae, bytecount);
		p += bytecount;
	}

	if (dte_facs->called_len && (facil_mask & X25_MASK_CALLED_AE)) {
		unsigned int bytecount = (dte_facs->called_len % 2) ?
		dte_facs->called_len / 2 + 1 :
		dte_facs->called_len / 2;
		*p++ = X25_FAC_CALLED_AE;
		*p++ = 1 + bytecount;
		*p++ = dte_facs->called_len;
		memcpy(p, dte_facs->called_ae, bytecount);
		p+=bytecount;
	}

	len       = p - buffer;
	buffer[0] = len - 1;

	return len;
}

/*
 *	Try to reach a compromise on a set of facilities.
 *
 *	The only real problem is with reverse charging.
 */
int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk,
		struct x25_facilities *new, struct x25_dte_facilities *dte)
{
	struct x25_sock *x25 = x25_sk(sk);
	struct x25_facilities *ours = &x25->facilities;
	struct x25_facilities theirs;
	int len;

	memset(&theirs, 0, sizeof(theirs));
	memcpy(new, ours, sizeof(*new));
	memset(dte, 0, sizeof(*dte));

	len = x25_parse_facilities(skb, &theirs, dte, &x25->vc_facil_mask);
	if (len < 0)
		return len;

	/*
	 *	They want reverse charging, we won't accept it.
	 */
	if ((theirs.reverse & 0x01 ) && (ours->reverse & 0x01)) {
		SOCK_DEBUG(sk, "X.25: rejecting reverse charging request\n");
		return -1;
	}

	new->reverse = theirs.reverse;

	if (theirs.throughput) {
		int theirs_in =  theirs.throughput & 0x0f;
		int theirs_out = theirs.throughput & 0xf0;
		int ours_in  = ours->throughput & 0x0f;
		int ours_out = ours->throughput & 0xf0;
		if (!ours_in || theirs_in < ours_in) {
			SOCK_DEBUG(sk, "X.25: inbound throughput negotiated\n");
			new->throughput = (new->throughput & 0xf0) | theirs_in;
		}
		if (!ours_out || theirs_out < ours_out) {
			SOCK_DEBUG(sk,
				"X.25: outbound throughput negotiated\n");
			new->throughput = (new->throughput & 0x0f) | theirs_out;
		}
	}

	if (theirs.pacsize_in && theirs.pacsize_out) {
		if (theirs.pacsize_in < ours->pacsize_in) {
			SOCK_DEBUG(sk, "X.25: packet size inwards negotiated down\n");
			new->pacsize_in = theirs.pacsize_in;
		}
		if (theirs.pacsize_out < ours->pacsize_out) {
			SOCK_DEBUG(sk, "X.25: packet size outwards negotiated down\n");
			new->pacsize_out = theirs.pacsize_out;
		}
	}

	if (theirs.winsize_in && theirs.winsize_out) {
		if (theirs.winsize_in < ours->winsize_in) {
			SOCK_DEBUG(sk, "X.25: window size inwards negotiated down\n");
			new->winsize_in = theirs.winsize_in;
		}
		if (theirs.winsize_out < ours->winsize_out) {
			SOCK_DEBUG(sk, "X.25: window size outwards negotiated down\n");
			new->winsize_out = theirs.winsize_out;
		}
	}

	return len;
}

/*
 *	Limit values of certain facilities according to the capability of the
 *      currently attached x25 link.
 */
void x25_limit_facilities(struct x25_facilities *facilities,
			  struct x25_neigh *nb)
{

	if (!nb->extended) {
		if (facilities->winsize_in  > 7) {
			pr_debug("incoming winsize limited to 7\n");
			facilities->winsize_in = 7;
		}
		if (facilities->winsize_out > 7) {
			facilities->winsize_out = 7;
			pr_debug("outgoing winsize limited to 7\n");
		}
	}
}
d='n1528' href='#n1528'>1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 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 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153
/*
 * Copyright (c) 2006, Intel Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope 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.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
 * Place - Suite 330, Boston, MA 02111-1307 USA.
 *
 * Copyright (C) 2006-2008 Intel Corporation
 * Author: Ashok Raj <ashok.raj@intel.com>
 * Author: Shaohua Li <shaohua.li@intel.com>
 * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
 * Author: Fenghua Yu <fenghua.yu@intel.com>
 */

#include <linux/init.h>
#include <linux/bitmap.h>
#include <linux/debugfs.h>
#include <linux/slab.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/spinlock.h>
#include <linux/pci.h>
#include <linux/dmar.h>
#include <linux/dma-mapping.h>
#include <linux/mempool.h>
#include <linux/timer.h>
#include <linux/iova.h>
#include <linux/iommu.h>
#include <linux/intel-iommu.h>
#include <asm/cacheflush.h>
#include <asm/iommu.h>
#include "pci.h"

#define ROOT_SIZE		VTD_PAGE_SIZE
#define CONTEXT_SIZE		VTD_PAGE_SIZE

#define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY)
#define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA)

#define IOAPIC_RANGE_START	(0xfee00000)
#define IOAPIC_RANGE_END	(0xfeefffff)
#define IOVA_START_ADDR		(0x1000)

#define DEFAULT_DOMAIN_ADDRESS_WIDTH 48

#define DOMAIN_MAX_ADDR(gaw) ((((u64)1) << gaw) - 1)

#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
#define DMA_32BIT_PFN		IOVA_PFN(DMA_32BIT_MASK)
#define DMA_64BIT_PFN		IOVA_PFN(DMA_64BIT_MASK)

/* global iommu list, set NULL for ignored DMAR units */
static struct intel_iommu **g_iommus;

static int rwbf_quirk;

/*
 * 0: Present
 * 1-11: Reserved
 * 12-63: Context Ptr (12 - (haw-1))
 * 64-127: Reserved
 */
struct root_entry {
	u64	val;
	u64	rsvd1;
};
#define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
static inline bool root_present(struct root_entry *root)
{
	return (root->val & 1);
}
static inline void set_root_present(struct root_entry *root)
{
	root->val |= 1;
}
static inline void set_root_value(struct root_entry *root, unsigned long value)
{
	root->val |= value & VTD_PAGE_MASK;
}

static inline struct context_entry *
get_context_addr_from_root(struct root_entry *root)
{
	return (struct context_entry *)
		(root_present(root)?phys_to_virt(
		root->val & VTD_PAGE_MASK) :
		NULL);
}

/*
 * low 64 bits:
 * 0: present
 * 1: fault processing disable
 * 2-3: translation type
 * 12-63: address space root
 * high 64 bits:
 * 0-2: address width
 * 3-6: aval
 * 8-23: domain id
 */
struct context_entry {
	u64 lo;
	u64 hi;
};

static inline bool context_present(struct context_entry *context)
{
	return (context->lo & 1);
}
static inline void context_set_present(struct context_entry *context)
{
	context->lo |= 1;
}

static inline void context_set_fault_enable(struct context_entry *context)
{
	context->lo &= (((u64)-1) << 2) | 1;
}

#define CONTEXT_TT_MULTI_LEVEL 0

static inline void context_set_translation_type(struct context_entry *context,
						unsigned long value)
{
	context->lo &= (((u64)-1) << 4) | 3;
	context->lo |= (value & 3) << 2;
}

static inline void context_set_address_root(struct context_entry *context,
					    unsigned long value)
{
	context->lo |= value & VTD_PAGE_MASK;
}

static inline void context_set_address_width(struct context_entry *context,
					     unsigned long value)
{
	context->hi |= value & 7;
}

static inline void context_set_domain_id(struct context_entry *context,
					 unsigned long value)
{
	context->hi |= (value & ((1 << 16) - 1)) << 8;
}

static inline void context_clear_entry(struct context_entry *context)
{
	context->lo = 0;
	context->hi = 0;
}

/*
 * 0: readable
 * 1: writable
 * 2-6: reserved
 * 7: super page
 * 8-11: available
 * 12-63: Host physcial address
 */
struct dma_pte {
	u64 val;
};

static inline void dma_clear_pte(struct dma_pte *pte)
{
	pte->val = 0;
}

static inline void dma_set_pte_readable(struct dma_pte *pte)
{
	pte->val |= DMA_PTE_READ;
}

static inline void dma_set_pte_writable(struct dma_pte *pte)
{
	pte->val |= DMA_PTE_WRITE;
}

static inline void dma_set_pte_prot(struct dma_pte *pte, unsigned long prot)
{
	pte->val = (pte->val & ~3) | (prot & 3);
}

static inline u64 dma_pte_addr(struct dma_pte *pte)
{
	return (pte->val & VTD_PAGE_MASK);
}

static inline void dma_set_pte_addr(struct dma_pte *pte, u64 addr)
{
	pte->val |= (addr & VTD_PAGE_MASK);
}

static inline bool dma_pte_present(struct dma_pte *pte)
{
	return (pte->val & 3) != 0;
}

/* devices under the same p2p bridge are owned in one domain */
#define DOMAIN_FLAG_P2P_MULTIPLE_DEVICES (1 << 0)

/* domain represents a virtual machine, more than one devices
 * across iommus may be owned in one domain, e.g. kvm guest.
 */
#define DOMAIN_FLAG_VIRTUAL_MACHINE	(1 << 1)

struct dmar_domain {
	int	id;			/* domain id */
	unsigned long iommu_bmp;	/* bitmap of iommus this domain uses*/

	struct list_head devices; 	/* all devices' list */
	struct iova_domain iovad;	/* iova's that belong to this domain */

	struct dma_pte	*pgd;		/* virtual address */
	spinlock_t	mapping_lock;	/* page table lock */
	int		gaw;		/* max guest address width */

	/* adjusted guest address width, 0 is level 2 30-bit */
	int		agaw;

	int		flags;		/* flags to find out type of domain */

	int		iommu_coherency;/* indicate coherency of iommu access */
	int		iommu_count;	/* reference count of iommu */
	spinlock_t	iommu_lock;	/* protect iommu set in domain */
	u64		max_addr;	/* maximum mapped address */
};

/* PCI domain-device relationship */
struct device_domain_info {
	struct list_head link;	/* link to domain siblings */
	struct list_head global; /* link to global list */
	u8 bus;			/* PCI bus numer */
	u8 devfn;		/* PCI devfn number */
	struct pci_dev *dev; /* it's NULL for PCIE-to-PCI bridge */
	struct dmar_domain *domain; /* pointer to domain */
};

static void flush_unmaps_timeout(unsigned long data);

DEFINE_TIMER(unmap_timer,  flush_unmaps_timeout, 0, 0);

#define HIGH_WATER_MARK 250
struct deferred_flush_tables {
	int next;
	struct iova *iova[HIGH_WATER_MARK];
	struct dmar_domain *domain[HIGH_WATER_MARK];
};

static struct deferred_flush_tables *deferred_flush;

/* bitmap for indexing intel_iommus */
static int g_num_of_iommus;

static DEFINE_SPINLOCK(async_umap_flush_lock);
static LIST_HEAD(unmaps_to_do);

static int timer_on;
static long list_size;

static void domain_remove_dev_info(struct dmar_domain *domain);

#ifdef CONFIG_DMAR_DEFAULT_ON
int dmar_disabled = 0;
#else
int dmar_disabled = 1;
#endif /*CONFIG_DMAR_DEFAULT_ON*/

static int __initdata dmar_map_gfx = 1;
static int dmar_forcedac;
static int intel_iommu_strict;

#define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
static DEFINE_SPINLOCK(device_domain_lock);
static LIST_HEAD(device_domain_list);

static struct iommu_ops intel_iommu_ops;

static int __init intel_iommu_setup(char *str)
{
	if (!str)
		return -EINVAL;
	while (*str) {
		if (!strncmp(str, "on", 2)) {
			dmar_disabled = 0;
			printk(KERN_INFO "Intel-IOMMU: enabled\n");
		} else if (!strncmp(str, "off", 3)) {
			dmar_disabled = 1;
			printk(KERN_INFO "Intel-IOMMU: disabled\n");
		} else if (!strncmp(str, "igfx_off", 8)) {
			dmar_map_gfx = 0;
			printk(KERN_INFO
				"Intel-IOMMU: disable GFX device mapping\n");
		} else if (!strncmp(str, "forcedac", 8)) {
			printk(KERN_INFO
				"Intel-IOMMU: Forcing DAC for PCI devices\n");
			dmar_forcedac = 1;
		} else if (!strncmp(str, "strict", 6)) {
			printk(KERN_INFO
				"Intel-IOMMU: disable batched IOTLB flush\n");
			intel_iommu_strict = 1;
		}

		str += strcspn(str, ",");
		while (*str == ',')
			str++;
	}
	return 0;
}
__setup("intel_iommu=", intel_iommu_setup);

static struct kmem_cache *iommu_domain_cache;
static struct kmem_cache *iommu_devinfo_cache;
static struct kmem_cache *iommu_iova_cache;

static inline void *iommu_kmem_cache_alloc(struct kmem_cache *cachep)
{
	unsigned int flags;
	void *vaddr;

	/* trying to avoid low memory issues */
	flags = current->flags & PF_MEMALLOC;
	current->flags |= PF_MEMALLOC;
	vaddr = kmem_cache_alloc(cachep, GFP_ATOMIC);
	current->flags &= (~PF_MEMALLOC | flags);
	return vaddr;
}


static inline void *alloc_pgtable_page(void)
{
	unsigned int flags;
	void *vaddr;

	/* trying to avoid low memory issues */
	flags = current->flags & PF_MEMALLOC;
	current->flags |= PF_MEMALLOC;
	vaddr = (void *)get_zeroed_page(GFP_ATOMIC);
	current->flags &= (~PF_MEMALLOC | flags);
	return vaddr;
}

static inline void free_pgtable_page(void *vaddr)
{
	free_page((unsigned long)vaddr);
}

static inline void *alloc_domain_mem(void)
{
	return iommu_kmem_cache_alloc(iommu_domain_cache);
}

static void free_domain_mem(void *vaddr)
{
	kmem_cache_free(iommu_domain_cache, vaddr);
}

static inline void * alloc_devinfo_mem(void)
{
	return iommu_kmem_cache_alloc(iommu_devinfo_cache);
}

static inline void free_devinfo_mem(void *vaddr)
{
	kmem_cache_free(iommu_devinfo_cache, vaddr);
}

struct iova *alloc_iova_mem(void)
{
	return iommu_kmem_cache_alloc(iommu_iova_cache);
}

void free_iova_mem(struct iova *iova)
{
	kmem_cache_free(iommu_iova_cache, iova);
}


static inline int width_to_agaw(int width);

/* calculate agaw for each iommu.
 * "SAGAW" may be different across iommus, use a default agaw, and
 * get a supported less agaw for iommus that don't support the default agaw.
 */
int iommu_calculate_agaw(struct intel_iommu *iommu)
{
	unsigned long sagaw;
	int agaw = -1;

	sagaw = cap_sagaw(iommu->cap);
	for (agaw = width_to_agaw(DEFAULT_DOMAIN_ADDRESS_WIDTH);
	     agaw >= 0; agaw--) {
		if (test_bit(agaw, &sagaw))
			break;
	}

	return agaw;
}

/* in native case, each domain is related to only one iommu */
static struct intel_iommu *domain_get_iommu(struct dmar_domain *domain)
{
	int iommu_id;

	BUG_ON(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE);

	iommu_id = find_first_bit(&domain->iommu_bmp, g_num_of_iommus);
	if (iommu_id < 0 || iommu_id >= g_num_of_iommus)
		return NULL;

	return g_iommus[iommu_id];
}

/* "Coherency" capability may be different across iommus */
static void domain_update_iommu_coherency(struct dmar_domain *domain)
{
	int i;

	domain->iommu_coherency = 1;

	i = find_first_bit(&domain->iommu_bmp, g_num_of_iommus);
	for (; i < g_num_of_iommus; ) {
		if (!ecap_coherent(g_iommus[i]->ecap)) {
			domain->iommu_coherency = 0;
			break;
		}
		i = find_next_bit(&domain->iommu_bmp, g_num_of_iommus, i+1);
	}
}

static struct intel_iommu *device_to_iommu(u8 bus, u8 devfn)
{
	struct dmar_drhd_unit *drhd = NULL;
	int i;

	for_each_drhd_unit(drhd) {
		if (drhd->ignored)
			continue;

		for (i = 0; i < drhd->devices_cnt; i++)
			if (drhd->devices[i] &&
			    drhd->devices[i]->bus->number == bus &&
			    drhd->devices[i]->devfn == devfn)
				return drhd->iommu;

		if (drhd->include_all)
			return drhd->iommu;
	}

	return NULL;
}

static void domain_flush_cache(struct dmar_domain *domain,
			       void *addr, int size)
{
	if (!domain->iommu_coherency)
		clflush_cache_range(addr, size);
}

/* Gets context entry for a given bus and devfn */
static struct context_entry * device_to_context_entry(struct intel_iommu *iommu,
		u8 bus, u8 devfn)
{
	struct root_entry *root;
	struct context_entry *context;
	unsigned long phy_addr;
	unsigned long flags;

	spin_lock_irqsave(&iommu->lock, flags);
	root = &iommu->root_entry[bus];
	context = get_context_addr_from_root(root);
	if (!context) {
		context = (struct context_entry *)alloc_pgtable_page();
		if (!context) {
			spin_unlock_irqrestore(&iommu->lock, flags);
			return NULL;
		}
		__iommu_flush_cache(iommu, (void *)context, CONTEXT_SIZE);
		phy_addr = virt_to_phys((void *)context);
		set_root_value(root, phy_addr);
		set_root_present(root);
		__iommu_flush_cache(iommu, root, sizeof(*root));
	}
	spin_unlock_irqrestore(&iommu->lock, flags);
	return &context[devfn];
}

static int device_context_mapped(struct intel_iommu *iommu, u8 bus, u8 devfn)
{
	struct root_entry *root;
	struct context_entry *context;
	int ret;
	unsigned long flags;

	spin_lock_irqsave(&iommu->lock, flags);
	root = &iommu->root_entry[bus];
	context = get_context_addr_from_root(root);
	if (!context) {
		ret = 0;
		goto out;
	}
	ret = context_present(&context[devfn]);
out:
	spin_unlock_irqrestore(&iommu->lock, flags);
	return ret;
}

static void clear_context_table(struct intel_iommu *iommu, u8 bus, u8 devfn)
{
	struct root_entry *root;
	struct context_entry *context;
	unsigned long flags;

	spin_lock_irqsave(&iommu->lock, flags);
	root = &iommu->root_entry[bus];
	context = get_context_addr_from_root(root);
	if (context) {
		context_clear_entry(&context[devfn]);
		__iommu_flush_cache(iommu, &context[devfn], \
			sizeof(*context));
	}
	spin_unlock_irqrestore(&iommu->lock, flags);
}

static void free_context_table(struct intel_iommu *iommu)
{
	struct root_entry *root;
	int i;
	unsigned long flags;
	struct context_entry *context;

	spin_lock_irqsave(&iommu->lock, flags);
	if (!iommu->root_entry) {
		goto out;
	}
	for (i = 0; i < ROOT_ENTRY_NR; i++) {
		root = &iommu->root_entry[i];
		context = get_context_addr_from_root(root);
		if (context)
			free_pgtable_page(context);
	}
	free_pgtable_page(iommu->root_entry);
	iommu->root_entry = NULL;
out:
	spin_unlock_irqrestore(&iommu->lock, flags);
}

/* page table handling */
#define LEVEL_STRIDE		(9)
#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)

static inline int agaw_to_level(int agaw)
{
	return agaw + 2;
}

static inline int agaw_to_width(int agaw)
{
	return 30 + agaw * LEVEL_STRIDE;

}

static inline int width_to_agaw(int width)
{
	return (width - 30) / LEVEL_STRIDE;
}

static inline unsigned int level_to_offset_bits(int level)
{
	return (12 + (level - 1) * LEVEL_STRIDE);
}

static inline int address_level_offset(u64 addr, int level)
{
	return ((addr >> level_to_offset_bits(level)) & LEVEL_MASK);
}

static inline u64 level_mask(int level)
{
	return ((u64)-1 << level_to_offset_bits(level));
}

static inline u64 level_size(int level)
{
	return ((u64)1 << level_to_offset_bits(level));
}

static inline u64 align_to_level(u64 addr, int level)
{
	return ((addr + level_size(level) - 1) & level_mask(level));
}

static struct dma_pte * addr_to_dma_pte(struct dmar_domain *domain, u64 addr)
{
	int addr_width = agaw_to_width(domain->agaw);
	struct dma_pte *parent, *pte = NULL;
	int level = agaw_to_level(domain->agaw);
	int offset;
	unsigned long flags;

	BUG_ON(!domain->pgd);

	addr &= (((u64)1) << addr_width) - 1;
	parent = domain->pgd;

	spin_lock_irqsave(&domain->mapping_lock, flags);
	while (level > 0) {
		void *tmp_page;

		offset = address_level_offset(addr, level);
		pte = &parent[offset];
		if (level == 1)
			break;

		if (!dma_pte_present(pte)) {
			tmp_page = alloc_pgtable_page();

			if (!tmp_page) {
				spin_unlock_irqrestore(&domain->mapping_lock,
					flags);
				return NULL;
			}
			domain_flush_cache(domain, tmp_page, PAGE_SIZE);
			dma_set_pte_addr(pte, virt_to_phys(tmp_page));
			/*
			 * high level table always sets r/w, last level page
			 * table control read/write
			 */
			dma_set_pte_readable(pte);
			dma_set_pte_writable(pte);
			domain_flush_cache(domain, pte, sizeof(*pte));
		}
		parent = phys_to_virt(dma_pte_addr(pte));
		level--;
	}

	spin_unlock_irqrestore(&domain->mapping_lock, flags);
	return pte;
}

/* return address's pte at specific level */
static struct dma_pte *dma_addr_level_pte(struct dmar_domain *domain, u64 addr,
		int level)
{
	struct dma_pte *parent, *pte = NULL;
	int total = agaw_to_level(domain->agaw);
	int offset;

	parent = domain->pgd;
	while (level <= total) {
		offset = address_level_offset(addr, total);
		pte = &parent[offset];
		if (level == total)
			return pte;

		if (!dma_pte_present(pte))
			break;
		parent = phys_to_virt(dma_pte_addr(pte));
		total--;
	}
	return NULL;
}

/* clear one page's page table */
static void dma_pte_clear_one(struct dmar_domain *domain, u64 addr)
{
	struct dma_pte *pte = NULL;

	/* get last level pte */
	pte = dma_addr_level_pte(domain, addr, 1);

	if (pte) {
		dma_clear_pte(pte);
		domain_flush_cache(domain, pte, sizeof(*pte));
	}
}

/* clear last level pte, a tlb flush should be followed */
static void dma_pte_clear_range(struct dmar_domain *domain, u64 start, u64 end)
{
	int addr_width = agaw_to_width(domain->agaw);

	start &= (((u64)1) << addr_width) - 1;
	end &= (((u64)1) << addr_width) - 1;
	/* in case it's partial page */
	start = PAGE_ALIGN(start);
	end &= PAGE_MASK;

	/* we don't need lock here, nobody else touches the iova range */
	while (start < end) {
		dma_pte_clear_one(domain, start);
		start += VTD_PAGE_SIZE;
	}
}

/* free page table pages. last level pte should already be cleared */
static void dma_pte_free_pagetable(struct dmar_domain *domain,
	u64 start, u64 end)
{
	int addr_width = agaw_to_width(domain->agaw);
	struct dma_pte *pte;
	int total = agaw_to_level(domain->agaw);
	int level;
	u64 tmp;

	start &= (((u64)1) << addr_width) - 1;
	end &= (((u64)1) << addr_width) - 1;

	/* we don't need lock here, nobody else touches the iova range */
	level = 2;
	while (level <= total) {
		tmp = align_to_level(start, level);
		if (tmp >= end || (tmp + level_size(level) > end))
			return;

		while (tmp < end) {
			pte = dma_addr_level_pte(domain, tmp, level);
			if (pte) {
				free_pgtable_page(
					phys_to_virt(dma_pte_addr(pte)));
				dma_clear_pte(pte);
				domain_flush_cache(domain, pte, sizeof(*pte));
			}
			tmp += level_size(level);
		}
		level++;
	}
	/* free pgd */
	if (start == 0 && end >= ((((u64)1) << addr_width) - 1)) {
		free_pgtable_page(domain->pgd);
		domain->pgd = NULL;
	}
}

/* iommu handling */
static int iommu_alloc_root_entry(struct intel_iommu *iommu)
{
	struct root_entry *root;
	unsigned long flags;

	root = (struct root_entry *)alloc_pgtable_page();
	if (!root)
		return -ENOMEM;

	__iommu_flush_cache(iommu, root, ROOT_SIZE);

	spin_lock_irqsave(&iommu->lock, flags);
	iommu->root_entry = root;
	spin_unlock_irqrestore(&iommu->lock, flags);

	return 0;
}

static void iommu_set_root_entry(struct intel_iommu *iommu)
{
	void *addr;
	u32 cmd, sts;
	unsigned long flag;

	addr = iommu->root_entry;

	spin_lock_irqsave(&iommu->register_lock, flag);
	dmar_writeq(iommu->reg + DMAR_RTADDR_REG, virt_to_phys(addr));

	cmd = iommu->gcmd | DMA_GCMD_SRTP;
	writel(cmd, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		readl, (sts & DMA_GSTS_RTPS), sts);

	spin_unlock_irqrestore(&iommu->register_lock, flag);
}

static void iommu_flush_write_buffer(struct intel_iommu *iommu)
{
	u32 val;
	unsigned long flag;

	if (!rwbf_quirk && !cap_rwbf(iommu->cap))
		return;
	val = iommu->gcmd | DMA_GCMD_WBF;

	spin_lock_irqsave(&iommu->register_lock, flag);
	writel(val, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
			readl, (!(val & DMA_GSTS_WBFS)), val);

	spin_unlock_irqrestore(&iommu->register_lock, flag);
}

/* return value determine if we need a write buffer flush */
static int __iommu_flush_context(struct intel_iommu *iommu,
	u16 did, u16 source_id, u8 function_mask, u64 type,
	int non_present_entry_flush)
{
	u64 val = 0;
	unsigned long flag;

	/*
	 * In the non-present entry flush case, if hardware doesn't cache
	 * non-present entry we do nothing and if hardware cache non-present
	 * entry, we flush entries of domain 0 (the domain id is used to cache
	 * any non-present entries)
	 */
	if (non_present_entry_flush) {
		if (!cap_caching_mode(iommu->cap))
			return 1;
		else
			did = 0;
	}

	switch (type) {
	case DMA_CCMD_GLOBAL_INVL:
		val = DMA_CCMD_GLOBAL_INVL;
		break;
	case DMA_CCMD_DOMAIN_INVL:
		val = DMA_CCMD_DOMAIN_INVL|DMA_CCMD_DID(did);
		break;
	case DMA_CCMD_DEVICE_INVL:
		val = DMA_CCMD_DEVICE_INVL|DMA_CCMD_DID(did)
			| DMA_CCMD_SID(source_id) | DMA_CCMD_FM(function_mask);
		break;
	default:
		BUG();
	}
	val |= DMA_CCMD_ICC;

	spin_lock_irqsave(&iommu->register_lock, flag);
	dmar_writeq(iommu->reg + DMAR_CCMD_REG, val);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_CCMD_REG,
		dmar_readq, (!(val & DMA_CCMD_ICC)), val);

	spin_unlock_irqrestore(&iommu->register_lock, flag);

	/* flush context entry will implicitly flush write buffer */
	return 0;
}

/* return value determine if we need a write buffer flush */
static int __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did,
	u64 addr, unsigned int size_order, u64 type,
	int non_present_entry_flush)
{
	int tlb_offset = ecap_iotlb_offset(iommu->ecap);
	u64 val = 0, val_iva = 0;
	unsigned long flag;

	/*
	 * In the non-present entry flush case, if hardware doesn't cache
	 * non-present entry we do nothing and if hardware cache non-present
	 * entry, we flush entries of domain 0 (the domain id is used to cache
	 * any non-present entries)
	 */
	if (non_present_entry_flush) {
		if (!cap_caching_mode(iommu->cap))
			return 1;
		else
			did = 0;
	}

	switch (type) {
	case DMA_TLB_GLOBAL_FLUSH:
		/* global flush doesn't need set IVA_REG */
		val = DMA_TLB_GLOBAL_FLUSH|DMA_TLB_IVT;
		break;
	case DMA_TLB_DSI_FLUSH:
		val = DMA_TLB_DSI_FLUSH|DMA_TLB_IVT|DMA_TLB_DID(did);
		break;
	case DMA_TLB_PSI_FLUSH:
		val = DMA_TLB_PSI_FLUSH|DMA_TLB_IVT|DMA_TLB_DID(did);
		/* Note: always flush non-leaf currently */
		val_iva = size_order | addr;
		break;
	default:
		BUG();
	}
	/* Note: set drain read/write */
#if 0
	/*
	 * This is probably to be super secure.. Looks like we can
	 * ignore it without any impact.
	 */
	if (cap_read_drain(iommu->cap))
		val |= DMA_TLB_READ_DRAIN;
#endif
	if (cap_write_drain(iommu->cap))
		val |= DMA_TLB_WRITE_DRAIN;

	spin_lock_irqsave(&iommu->register_lock, flag);
	/* Note: Only uses first TLB reg currently */
	if (val_iva)
		dmar_writeq(iommu->reg + tlb_offset, val_iva);
	dmar_writeq(iommu->reg + tlb_offset + 8, val);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, tlb_offset + 8,
		dmar_readq, (!(val & DMA_TLB_IVT)), val);

	spin_unlock_irqrestore(&iommu->register_lock, flag);

	/* check IOTLB invalidation granularity */
	if (DMA_TLB_IAIG(val) == 0)
		printk(KERN_ERR"IOMMU: flush IOTLB failed\n");
	if (DMA_TLB_IAIG(val) != DMA_TLB_IIRG(type))
		pr_debug("IOMMU: tlb flush request %Lx, actual %Lx\n",
			(unsigned long long)DMA_TLB_IIRG(type),
			(unsigned long long)DMA_TLB_IAIG(val));
	/* flush iotlb entry will implicitly flush write buffer */
	return 0;
}

static int iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
	u64 addr, unsigned int pages, int non_present_entry_flush)
{
	unsigned int mask;

	BUG_ON(addr & (~VTD_PAGE_MASK));
	BUG_ON(pages == 0);

	/* Fallback to domain selective flush if no PSI support */
	if (!cap_pgsel_inv(iommu->cap))
		return iommu->flush.flush_iotlb(iommu, did, 0, 0,
						DMA_TLB_DSI_FLUSH,
						non_present_entry_flush);

	/*
	 * PSI requires page size to be 2 ^ x, and the base address is naturally
	 * aligned to the size
	 */
	mask = ilog2(__roundup_pow_of_two(pages));
	/* Fallback to domain selective flush if size is too big */
	if (mask > cap_max_amask_val(iommu->cap))
		return iommu->flush.flush_iotlb(iommu, did, 0, 0,
			DMA_TLB_DSI_FLUSH, non_present_entry_flush);

	return iommu->flush.flush_iotlb(iommu, did, addr, mask,
					DMA_TLB_PSI_FLUSH,
					non_present_entry_flush);
}

static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
{
	u32 pmen;
	unsigned long flags;

	spin_lock_irqsave(&iommu->register_lock, flags);
	pmen = readl(iommu->reg + DMAR_PMEN_REG);
	pmen &= ~DMA_PMEN_EPM;
	writel(pmen, iommu->reg + DMAR_PMEN_REG);

	/* wait for the protected region status bit to clear */
	IOMMU_WAIT_OP(iommu, DMAR_PMEN_REG,
		readl, !(pmen & DMA_PMEN_PRS), pmen);

	spin_unlock_irqrestore(&iommu->register_lock, flags);
}

static int iommu_enable_translation(struct intel_iommu *iommu)
{
	u32 sts;
	unsigned long flags;

	spin_lock_irqsave(&iommu->register_lock, flags);
	writel(iommu->gcmd|DMA_GCMD_TE, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		readl, (sts & DMA_GSTS_TES), sts);

	iommu->gcmd |= DMA_GCMD_TE;
	spin_unlock_irqrestore(&iommu->register_lock, flags);
	return 0;
}

static int iommu_disable_translation(struct intel_iommu *iommu)
{
	u32 sts;
	unsigned long flag;

	spin_lock_irqsave(&iommu->register_lock, flag);
	iommu->gcmd &= ~DMA_GCMD_TE;
	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		readl, (!(sts & DMA_GSTS_TES)), sts);

	spin_unlock_irqrestore(&iommu->register_lock, flag);
	return 0;
}

/* iommu interrupt handling. Most stuff are MSI-like. */

static const char *fault_reason_strings[] =
{
	"Software",
	"Present bit in root entry is clear",
	"Present bit in context entry is clear",
	"Invalid context entry",
	"Access beyond MGAW",
	"PTE Write access is not set",
	"PTE Read access is not set",
	"Next page table ptr is invalid",
	"Root table address invalid",
	"Context table ptr is invalid",
	"non-zero reserved fields in RTP",
	"non-zero reserved fields in CTP",
	"non-zero reserved fields in PTE",
};
#define MAX_FAULT_REASON_IDX 	(ARRAY_SIZE(fault_reason_strings) - 1)

const char *dmar_get_fault_reason(u8 fault_reason)
{
	if (fault_reason > MAX_FAULT_REASON_IDX)
		return "Unknown";
	else
		return fault_reason_strings[fault_reason];
}

void dmar_msi_unmask(unsigned int irq)
{
	struct intel_iommu *iommu = get_irq_data(irq);
	unsigned long flag;

	/* unmask it */
	spin_lock_irqsave(&iommu->register_lock, flag);
	writel(0, iommu->reg + DMAR_FECTL_REG);
	/* Read a reg to force flush the post write */
	readl(iommu->reg + DMAR_FECTL_REG);
	spin_unlock_irqrestore(&iommu->register_lock, flag);
}

void dmar_msi_mask(unsigned int irq)
{
	unsigned long flag;
	struct intel_iommu *iommu = get_irq_data(irq);

	/* mask it */
	spin_lock_irqsave(&iommu->register_lock, flag);
	writel(DMA_FECTL_IM, iommu->reg + DMAR_FECTL_REG);
	/* Read a reg to force flush the post write */
	readl(iommu->reg + DMAR_FECTL_REG);
	spin_unlock_irqrestore(&iommu->register_lock, flag);
}

void dmar_msi_write(int irq, struct msi_msg *msg)
{
	struct intel_iommu *iommu = get_irq_data(irq);
	unsigned long flag;

	spin_lock_irqsave(&iommu->register_lock, flag);
	writel(msg->data, iommu->reg + DMAR_FEDATA_REG);
	writel(msg->address_lo, iommu->reg + DMAR_FEADDR_REG);
	writel(msg->address_hi, iommu->reg + DMAR_FEUADDR_REG);
	spin_unlock_irqrestore(&iommu->register_lock, flag);
}

void dmar_msi_read(int irq, struct msi_msg *msg)
{
	struct intel_iommu *iommu = get_irq_data(irq);
	unsigned long flag;

	spin_lock_irqsave(&iommu->register_lock, flag);
	msg->data = readl(iommu->reg + DMAR_FEDATA_REG);
	msg->address_lo = readl(iommu->reg + DMAR_FEADDR_REG);
	msg->address_hi = readl(iommu->reg + DMAR_FEUADDR_REG);
	spin_unlock_irqrestore(&iommu->register_lock, flag);
}

static int iommu_page_fault_do_one(struct intel_iommu *iommu, int type,
		u8 fault_reason, u16 source_id, unsigned long long addr)
{
	const char *reason;

	reason = dmar_get_fault_reason(fault_reason);

	printk(KERN_ERR
		"DMAR:[%s] Request device [%02x:%02x.%d] "
		"fault addr %llx \n"
		"DMAR:[fault reason %02d] %s\n",
		(type ? "DMA Read" : "DMA Write"),
		(source_id >> 8), PCI_SLOT(source_id & 0xFF),
		PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
	return 0;
}

#define PRIMARY_FAULT_REG_LEN (16)
static irqreturn_t iommu_page_fault(int irq, void *dev_id)
{
	struct intel_iommu *iommu = dev_id;
	int reg, fault_index;
	u32 fault_status;
	unsigned long flag;

	spin_lock_irqsave(&iommu->register_lock, flag);
	fault_status = readl(iommu->reg + DMAR_FSTS_REG);

	/* TBD: ignore advanced fault log currently */
	if (!(fault_status & DMA_FSTS_PPF))
		goto clear_overflow;

	fault_index = dma_fsts_fault_record_index(fault_status);
	reg = cap_fault_reg_offset(iommu->cap);
	while (1) {
		u8 fault_reason;
		u16 source_id;
		u64 guest_addr;
		int type;
		u32 data;

		/* highest 32 bits */
		data = readl(iommu->reg + reg +
				fault_index * PRIMARY_FAULT_REG_LEN + 12);
		if (!(data & DMA_FRCD_F))
			break;

		fault_reason = dma_frcd_fault_reason(data);
		type = dma_frcd_type(data);

		data = readl(iommu->reg + reg +
				fault_index * PRIMARY_FAULT_REG_LEN + 8);
		source_id = dma_frcd_source_id(data);

		guest_addr = dmar_readq(iommu->reg + reg +
				fault_index * PRIMARY_FAULT_REG_LEN);
		guest_addr = dma_frcd_page_addr(guest_addr);
		/* clear the fault */
		writel(DMA_FRCD_F, iommu->reg + reg +
			fault_index * PRIMARY_FAULT_REG_LEN + 12);

		spin_unlock_irqrestore(&iommu->register_lock, flag);

		iommu_page_fault_do_one(iommu, type, fault_reason,
				source_id, guest_addr);

		fault_index++;
		if (fault_index > cap_num_fault_regs(iommu->cap))
			fault_index = 0;
		spin_lock_irqsave(&iommu->register_lock, flag);
	}
clear_overflow:
	/* clear primary fault overflow */
	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
	if (fault_status & DMA_FSTS_PFO)
		writel(DMA_FSTS_PFO, iommu->reg + DMAR_FSTS_REG);

	spin_unlock_irqrestore(&iommu->register_lock, flag);
	return IRQ_HANDLED;
}

int dmar_set_interrupt(struct intel_iommu *iommu)
{
	int irq, ret;

	irq = create_irq();
	if (!irq) {
		printk(KERN_ERR "IOMMU: no free vectors\n");
		return -EINVAL;
	}

	set_irq_data(irq, iommu);
	iommu->irq = irq;

	ret = arch_setup_dmar_msi(irq);
	if (ret) {
		set_irq_data(irq, NULL);
		iommu->irq = 0;
		destroy_irq(irq);
		return 0;
	}

	/* Force fault register is cleared */
	iommu_page_fault(irq, iommu);

	ret = request_irq(irq, iommu_page_fault, 0, iommu->name, iommu);
	if (ret)
		printk(KERN_ERR "IOMMU: can't request irq\n");
	return ret;
}

static int iommu_init_domains(struct intel_iommu *iommu)
{
	unsigned long ndomains;
	unsigned long nlongs;

	ndomains = cap_ndoms(iommu->cap);
	pr_debug("Number of Domains supportd <%ld>\n", ndomains);
	nlongs = BITS_TO_LONGS(ndomains);

	/* TBD: there might be 64K domains,
	 * consider other allocation for future chip
	 */
	iommu->domain_ids = kcalloc(nlongs, sizeof(unsigned long), GFP_KERNEL);
	if (!iommu->domain_ids) {
		printk(KERN_ERR "Allocating domain id array failed\n");
		return -ENOMEM;
	}
	iommu->domains = kcalloc(ndomains, sizeof(struct dmar_domain *),
			GFP_KERNEL);
	if (!iommu->domains) {
		printk(KERN_ERR "Allocating domain array failed\n");
		kfree(iommu->domain_ids);
		return -ENOMEM;
	}

	spin_lock_init(&iommu->lock);

	/*
	 * if Caching mode is set, then invalid translations are tagged
	 * with domainid 0. Hence we need to pre-allocate it.
	 */
	if (cap_caching_mode(iommu->cap))
		set_bit(0, iommu->domain_ids);
	return 0;
}


static void domain_exit(struct dmar_domain *domain);
static void vm_domain_exit(struct dmar_domain *domain);

void free_dmar_iommu(struct intel_iommu *iommu)
{
	struct dmar_domain *domain;
	int i;
	unsigned long flags;

	i = find_first_bit(iommu->domain_ids, cap_ndoms(iommu->cap));
	for (; i < cap_ndoms(iommu->cap); ) {
		domain = iommu->domains[i];
		clear_bit(i, iommu->domain_ids);

		spin_lock_irqsave(&domain->iommu_lock, flags);
		if (--domain->iommu_count == 0) {
			if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE)
				vm_domain_exit(domain);
			else
				domain_exit(domain);
		}
		spin_unlock_irqrestore(&domain->iommu_lock, flags);

		i = find_next_bit(iommu->domain_ids,
			cap_ndoms(iommu->cap), i+1);
	}

	if (iommu->gcmd & DMA_GCMD_TE)
		iommu_disable_translation(iommu);

	if (iommu->irq) {
		set_irq_data(iommu->irq, NULL);
		/* This will mask the irq */
		free_irq(iommu->irq, iommu);
		destroy_irq(iommu->irq);
	}

	kfree(iommu->domains);
	kfree(iommu->domain_ids);

	g_iommus[iommu->seq_id] = NULL;

	/* if all iommus are freed, free g_iommus */
	for (i = 0; i < g_num_of_iommus; i++) {
		if (g_iommus[i])
			break;
	}

	if (i == g_num_of_iommus)
		kfree(g_iommus);

	/* free context mapping */
	free_context_table(iommu);
}

static struct dmar_domain * iommu_alloc_domain(struct intel_iommu *iommu)
{
	unsigned long num;
	unsigned long ndomains;
	struct dmar_domain *domain;
	unsigned long flags;

	domain = alloc_domain_mem();
	if (!domain)
		return NULL;

	ndomains = cap_ndoms(iommu->cap);

	spin_lock_irqsave(&iommu->lock, flags);
	num = find_first_zero_bit(iommu->domain_ids, ndomains);
	if (num >= ndomains) {
		spin_unlock_irqrestore(&iommu->lock, flags);
		free_domain_mem(domain);
		printk(KERN_ERR "IOMMU: no free domain ids\n");
		return NULL;
	}

	set_bit(num, iommu->domain_ids);
	domain->id = num;
	memset(&domain->iommu_bmp, 0, sizeof(unsigned long));
	set_bit(iommu->seq_id, &domain->iommu_bmp);
	domain->flags = 0;
	iommu->domains[num] = domain;
	spin_unlock_irqrestore(&iommu->lock, flags);

	return domain;
}

static void iommu_free_domain(struct dmar_domain *domain)
{
	unsigned long flags;
	struct intel_iommu *iommu;

	iommu = domain_get_iommu(domain);

	spin_lock_irqsave(&iommu->lock, flags);
	clear_bit(domain->id, iommu->domain_ids);
	spin_unlock_irqrestore(&iommu->lock, flags);
}

static struct iova_domain reserved_iova_list;
static struct lock_class_key reserved_alloc_key;
static struct lock_class_key reserved_rbtree_key;

static void dmar_init_reserved_ranges(void)
{
	struct pci_dev *pdev = NULL;
	struct iova *iova;
	int i;
	u64 addr, size;

	init_iova_domain(&reserved_iova_list, DMA_32BIT_PFN);

	lockdep_set_class(&reserved_iova_list.iova_alloc_lock,
		&reserved_alloc_key);
	lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
		&reserved_rbtree_key);

	/* IOAPIC ranges shouldn't be accessed by DMA */
	iova = reserve_iova(&reserved_iova_list, IOVA_PFN(IOAPIC_RANGE_START),
		IOVA_PFN(IOAPIC_RANGE_END));
	if (!iova)
		printk(KERN_ERR "Reserve IOAPIC range failed\n");

	/* Reserve all PCI MMIO to avoid peer-to-peer access */
	for_each_pci_dev(pdev) {
		struct resource *r;

		for (i = 0; i < PCI_NUM_RESOURCES; i++) {
			r = &pdev->resource[i];
			if (!r->flags || !(r->flags & IORESOURCE_MEM))
				continue;
			addr = r->start;
			addr &= PAGE_MASK;
			size = r->end - addr;
			size = PAGE_ALIGN(size);
			iova = reserve_iova(&reserved_iova_list, IOVA_PFN(addr),
				IOVA_PFN(size + addr) - 1);
			if (!iova)
				printk(KERN_ERR "Reserve iova failed\n");
		}
	}

}

static void domain_reserve_special_ranges(struct dmar_domain *domain)
{
	copy_reserved_iova(&reserved_iova_list, &domain->iovad);
}

static inline int guestwidth_to_adjustwidth(int gaw)
{
	int agaw;
	int r = (gaw - 12) % 9;

	if (r == 0)
		agaw = gaw;
	else
		agaw = gaw + 9 - r;
	if (agaw > 64)
		agaw = 64;
	return agaw;
}

static int domain_init(struct dmar_domain *domain, int guest_width)
{
	struct intel_iommu *iommu;
	int adjust_width, agaw;
	unsigned long sagaw;

	init_iova_domain(&domain->iovad, DMA_32BIT_PFN);
	spin_lock_init(&domain->mapping_lock);
	spin_lock_init(&domain->iommu_lock);

	domain_reserve_special_ranges(domain);

	/* calculate AGAW */
	iommu = domain_get_iommu(domain);
	if (guest_width > cap_mgaw(iommu->cap))
		guest_width = cap_mgaw(iommu->cap);
	domain->gaw = guest_width;
	adjust_width = guestwidth_to_adjustwidth(guest_width);
	agaw = width_to_agaw(adjust_width);
	sagaw = cap_sagaw(iommu->cap);
	if (!test_bit(agaw, &sagaw)) {
		/* hardware doesn't support it, choose a bigger one */
		pr_debug("IOMMU: hardware doesn't support agaw %d\n", agaw);
		agaw = find_next_bit(&sagaw, 5, agaw);
		if (agaw >= 5)
			return -ENODEV;
	}
	domain->agaw = agaw;
	INIT_LIST_HEAD(&domain->devices);

	if (ecap_coherent(iommu->ecap))
		domain->iommu_coherency = 1;
	else
		domain->iommu_coherency = 0;

	domain->iommu_count = 1;

	/* always allocate the top pgd */
	domain->pgd = (struct dma_pte *)alloc_pgtable_page();
	if (!domain->pgd)
		return -ENOMEM;
	__iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE);
	return 0;
}

static void domain_exit(struct dmar_domain *domain)
{
	u64 end;

	/* Domain 0 is reserved, so dont process it */
	if (!domain)
		return;

	domain_remove_dev_info(domain);
	/* destroy iovas */
	put_iova_domain(&domain->iovad);
	end = DOMAIN_MAX_ADDR(domain->gaw);
	end = end & (~PAGE_MASK);

	/* clear ptes */
	dma_pte_clear_range(domain, 0, end);

	/* free page tables */
	dma_pte_free_pagetable(domain, 0, end);

	iommu_free_domain(domain);
	free_domain_mem(domain);
}

static int domain_context_mapping_one(struct dmar_domain *domain,
		u8 bus, u8 devfn)
{
	struct context_entry *context;
	unsigned long flags;
	struct intel_iommu *iommu;
	struct dma_pte *pgd;
	unsigned long num;
	unsigned long ndomains;
	int id;
	int agaw;

	pr_debug("Set context mapping for %02x:%02x.%d\n",
		bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
	BUG_ON(!domain->pgd);

	iommu = device_to_iommu(bus, devfn);
	if (!iommu)
		return -ENODEV;

	context = device_to_context_entry(iommu, bus, devfn);
	if (!context)
		return -ENOMEM;
	spin_lock_irqsave(&iommu->lock, flags);
	if (context_present(context)) {
		spin_unlock_irqrestore(&iommu->lock, flags);
		return 0;
	}

	id = domain->id;
	pgd = domain->pgd;

	if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) {
		int found = 0;

		/* find an available domain id for this device in iommu */
		ndomains = cap_ndoms(iommu->cap);
		num = find_first_bit(iommu->domain_ids, ndomains);
		for (; num < ndomains; ) {
			if (iommu->domains[num] == domain) {
				id = num;
				found = 1;
				break;
			}
			num = find_next_bit(iommu->domain_ids,
					    cap_ndoms(iommu->cap), num+1);
		}

		if (found == 0) {
			num = find_first_zero_bit(iommu->domain_ids, ndomains);
			if (num >= ndomains) {
				spin_unlock_irqrestore(&iommu->lock, flags);
				printk(KERN_ERR "IOMMU: no free domain ids\n");
				return -EFAULT;
			}

			set_bit(num, iommu->domain_ids);
			iommu->domains[num] = domain;
			id = num;
		}

		/* Skip top levels of page tables for
		 * iommu which has less agaw than default.
		 */
		for (agaw = domain->agaw; agaw != iommu->agaw; agaw--) {
			pgd = phys_to_virt(dma_pte_addr(pgd));
			if (!dma_pte_present(pgd)) {
				spin_unlock_irqrestore(&iommu->lock, flags);
				return -ENOMEM;
			}
		}
	}