aboutsummaryrefslogtreecommitdiffstats
path: root/lib
diff options
context:
space:
mode:
authorDavid Decotigny <decot@googlers.com>2013-01-11 17:31:36 -0500
committerLinus Torvalds <torvalds@linux-foundation.org>2013-01-11 17:54:54 -0500
commit896f97ea95c1d29c0520ee0766b66b7f64cb967c (patch)
tree9898ba669c2348294452fcfd5b7b81fe04cb072f /lib
parent254adaa465c40151df11fc1f88f93e6e86eb61d4 (diff)
lib: cpu_rmap: avoid flushing all workqueues
In some cases, free_irq_cpu_rmap() is called while holding a lock (eg rtnl). This can lead to deadlocks, because it invokes flush_scheduled_work() which ends up waiting for whole system workqueue to flush, but some pending works might try to acquire the lock we are already holding. This commit uses reference-counting to replace irq_run_affinity_notifiers(). It also removes irq_run_affinity_notifiers() altogether. [akpm@linux-foundation.org: eliminate free_cpu_rmap, rename cpu_rmap_reclaim() to cpu_rmap_release(), propagate kref_put() retval from cpu_rmap_put()] Signed-off-by: David Decotigny <decot@googlers.com> Reviewed-by: Ben Hutchings <bhutchings@solarflare.com> Acked-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Or Gerlitz <ogerlitz@mellanox.com> Acked-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'lib')
-rw-r--r--lib/cpu_rmap.c54
1 files changed, 49 insertions, 5 deletions
diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
index 145dec5267c9..5fbed5caba6e 100644
--- a/lib/cpu_rmap.c
+++ b/lib/cpu_rmap.c
@@ -45,6 +45,7 @@ struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
45 if (!rmap) 45 if (!rmap)
46 return NULL; 46 return NULL;
47 47
48 kref_init(&rmap->refcount);
48 rmap->obj = (void **)((char *)rmap + obj_offset); 49 rmap->obj = (void **)((char *)rmap + obj_offset);
49 50
50 /* Initially assign CPUs to objects on a rota, since we have 51 /* Initially assign CPUs to objects on a rota, since we have
@@ -63,6 +64,35 @@ struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
63} 64}
64EXPORT_SYMBOL(alloc_cpu_rmap); 65EXPORT_SYMBOL(alloc_cpu_rmap);
65 66
67/**
68 * cpu_rmap_release - internal reclaiming helper called from kref_put
69 * @ref: kref to struct cpu_rmap
70 */
71static void cpu_rmap_release(struct kref *ref)
72{
73 struct cpu_rmap *rmap = container_of(ref, struct cpu_rmap, refcount);
74 kfree(rmap);
75}
76
77/**
78 * cpu_rmap_get - internal helper to get new ref on a cpu_rmap
79 * @rmap: reverse-map allocated with alloc_cpu_rmap()
80 */
81static inline void cpu_rmap_get(struct cpu_rmap *rmap)
82{
83 kref_get(&rmap->refcount);
84}
85
86/**
87 * cpu_rmap_put - release ref on a cpu_rmap
88 * @rmap: reverse-map allocated with alloc_cpu_rmap()
89 */
90int cpu_rmap_put(struct cpu_rmap *rmap)
91{
92 return kref_put(&rmap->refcount, cpu_rmap_release);
93}
94EXPORT_SYMBOL(cpu_rmap_put);
95
66/* Reevaluate nearest object for given CPU, comparing with the given 96/* Reevaluate nearest object for given CPU, comparing with the given
67 * neighbours at the given distance. 97 * neighbours at the given distance.
68 */ 98 */
@@ -197,8 +227,7 @@ struct irq_glue {
197 * free_irq_cpu_rmap - free a CPU affinity reverse-map used for IRQs 227 * free_irq_cpu_rmap - free a CPU affinity reverse-map used for IRQs
198 * @rmap: Reverse-map allocated with alloc_irq_cpu_map(), or %NULL 228 * @rmap: Reverse-map allocated with alloc_irq_cpu_map(), or %NULL
199 * 229 *
200 * Must be called in process context, before freeing the IRQs, and 230 * Must be called in process context, before freeing the IRQs.
201 * without holding any locks required by global workqueue items.
202 */ 231 */
203void free_irq_cpu_rmap(struct cpu_rmap *rmap) 232void free_irq_cpu_rmap(struct cpu_rmap *rmap)
204{ 233{
@@ -212,12 +241,18 @@ void free_irq_cpu_rmap(struct cpu_rmap *rmap)
212 glue = rmap->obj[index]; 241 glue = rmap->obj[index];
213 irq_set_affinity_notifier(glue->notify.irq, NULL); 242 irq_set_affinity_notifier(glue->notify.irq, NULL);
214 } 243 }
215 irq_run_affinity_notifiers();
216 244
217 kfree(rmap); 245 cpu_rmap_put(rmap);
218} 246}
219EXPORT_SYMBOL(free_irq_cpu_rmap); 247EXPORT_SYMBOL(free_irq_cpu_rmap);
220 248
249/**
250 * irq_cpu_rmap_notify - callback for IRQ subsystem when IRQ affinity updated
251 * @notify: struct irq_affinity_notify passed by irq/manage.c
252 * @mask: cpu mask for new SMP affinity
253 *
254 * This is executed in workqueue context.
255 */
221static void 256static void
222irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask) 257irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
223{ 258{
@@ -230,10 +265,16 @@ irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
230 pr_warning("irq_cpu_rmap_notify: update failed: %d\n", rc); 265 pr_warning("irq_cpu_rmap_notify: update failed: %d\n", rc);
231} 266}
232 267
268/**
269 * irq_cpu_rmap_release - reclaiming callback for IRQ subsystem
270 * @ref: kref to struct irq_affinity_notify passed by irq/manage.c
271 */
233static void irq_cpu_rmap_release(struct kref *ref) 272static void irq_cpu_rmap_release(struct kref *ref)
234{ 273{
235 struct irq_glue *glue = 274 struct irq_glue *glue =
236 container_of(ref, struct irq_glue, notify.kref); 275 container_of(ref, struct irq_glue, notify.kref);
276
277 cpu_rmap_put(glue->rmap);
237 kfree(glue); 278 kfree(glue);
238} 279}
239 280
@@ -258,10 +299,13 @@ int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq)
258 glue->notify.notify = irq_cpu_rmap_notify; 299 glue->notify.notify = irq_cpu_rmap_notify;
259 glue->notify.release = irq_cpu_rmap_release; 300 glue->notify.release = irq_cpu_rmap_release;
260 glue->rmap = rmap; 301 glue->rmap = rmap;
302 cpu_rmap_get(rmap);
261 glue->index = cpu_rmap_add(rmap, glue); 303 glue->index = cpu_rmap_add(rmap, glue);
262 rc = irq_set_affinity_notifier(irq, &glue->notify); 304 rc = irq_set_affinity_notifier(irq, &glue->notify);
263 if (rc) 305 if (rc) {
306 cpu_rmap_put(glue->rmap);
264 kfree(glue); 307 kfree(glue);
308 }
265 return rc; 309 return rc;
266} 310}
267EXPORT_SYMBOL(irq_cpu_rmap_add); 311EXPORT_SYMBOL(irq_cpu_rmap_add);
' href='#n1230'>1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 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
/*
 *  sata_nv.c - NVIDIA nForce SATA
 *
 *  Copyright 2004 NVIDIA Corp.  All rights reserved.
 *  Copyright 2004 Andrew Chew
 *
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2, or (at your option)
 *  any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; see the file COPYING.  If not, write to
 *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
 *
 *
 *  libata documentation is available via 'make {ps|pdf}docs',
 *  as Documentation/DocBook/libata.*
 *
 *  No hardware documentation available outside of NVIDIA.
 *  This driver programs the NVIDIA SATA controller in a similar
 *  fashion as with other PCI IDE BMDMA controllers, with a few
 *  NV-specific details such as register offsets, SATA phy location,
 *  hotplug info, etc.
 *
 *  CK804/MCP04 controllers support an alternate programming interface
 *  similar to the ADMA specification (with some modifications).
 *  This allows the use of NCQ. Non-DMA-mapped ATA commands are still
 *  sent through the legacy interface.
 *
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/gfp.h>
#include <linux/pci.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/device.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_device.h>
#include <linux/libata.h>

#define DRV_NAME			"sata_nv"
#define DRV_VERSION			"3.5"

#define NV_ADMA_DMA_BOUNDARY		0xffffffffUL

enum {
	NV_MMIO_BAR			= 5,

	NV_PORTS			= 2,
	NV_PIO_MASK			= ATA_PIO4,
	NV_MWDMA_MASK			= ATA_MWDMA2,
	NV_UDMA_MASK			= ATA_UDMA6,
	NV_PORT0_SCR_REG_OFFSET		= 0x00,
	NV_PORT1_SCR_REG_OFFSET		= 0x40,

	/* INT_STATUS/ENABLE */
	NV_INT_STATUS			= 0x10,
	NV_INT_ENABLE			= 0x11,
	NV_INT_STATUS_CK804		= 0x440,
	NV_INT_ENABLE_CK804		= 0x441,

	/* INT_STATUS/ENABLE bits */
	NV_INT_DEV			= 0x01,
	NV_INT_PM			= 0x02,
	NV_INT_ADDED			= 0x04,
	NV_INT_REMOVED			= 0x08,

	NV_INT_PORT_SHIFT		= 4,	/* each port occupies 4 bits */

	NV_INT_ALL			= 0x0f,
	NV_INT_MASK			= NV_INT_DEV |
					  NV_INT_ADDED | NV_INT_REMOVED,

	/* INT_CONFIG */
	NV_INT_CONFIG			= 0x12,
	NV_INT_CONFIG_METHD		= 0x01, // 0 = INT, 1 = SMI

	// For PCI config register 20
	NV_MCP_SATA_CFG_20		= 0x50,
	NV_MCP_SATA_CFG_20_SATA_SPACE_EN = 0x04,
	NV_MCP_SATA_CFG_20_PORT0_EN	= (1 << 17),
	NV_MCP_SATA_CFG_20_PORT1_EN	= (1 << 16),
	NV_MCP_SATA_CFG_20_PORT0_PWB_EN	= (1 << 14),
	NV_MCP_SATA_CFG_20_PORT1_PWB_EN	= (1 << 12),

	NV_ADMA_MAX_CPBS		= 32,
	NV_ADMA_CPB_SZ			= 128,
	NV_ADMA_APRD_SZ			= 16,
	NV_ADMA_SGTBL_LEN		= (1024 - NV_ADMA_CPB_SZ) /
					   NV_ADMA_APRD_SZ,
	NV_ADMA_SGTBL_TOTAL_LEN		= NV_ADMA_SGTBL_LEN + 5,
	NV_ADMA_SGTBL_SZ                = NV_ADMA_SGTBL_LEN * NV_ADMA_APRD_SZ,
	NV_ADMA_PORT_PRIV_DMA_SZ        = NV_ADMA_MAX_CPBS *
					   (NV_ADMA_CPB_SZ + NV_ADMA_SGTBL_SZ),

	/* BAR5 offset to ADMA general registers */
	NV_ADMA_GEN			= 0x400,
	NV_ADMA_GEN_CTL			= 0x00,
	NV_ADMA_NOTIFIER_CLEAR		= 0x30,

	/* BAR5 offset to ADMA ports */
	NV_ADMA_PORT			= 0x480,

	/* size of ADMA port register space  */
	NV_ADMA_PORT_SIZE		= 0x100,

	/* ADMA port registers */
	NV_ADMA_CTL			= 0x40,
	NV_ADMA_CPB_COUNT		= 0x42,
	NV_ADMA_NEXT_CPB_IDX		= 0x43,
	NV_ADMA_STAT			= 0x44,
	NV_ADMA_CPB_BASE_LOW		= 0x48,
	NV_ADMA_CPB_BASE_HIGH		= 0x4C,
	NV_ADMA_APPEND			= 0x50,
	NV_ADMA_NOTIFIER		= 0x68,
	NV_ADMA_NOTIFIER_ERROR		= 0x6C,

	/* NV_ADMA_CTL register bits */
	NV_ADMA_CTL_HOTPLUG_IEN		= (1 << 0),
	NV_ADMA_CTL_CHANNEL_RESET	= (1 << 5),
	NV_ADMA_CTL_GO			= (1 << 7),
	NV_ADMA_CTL_AIEN		= (1 << 8),
	NV_ADMA_CTL_READ_NON_COHERENT	= (1 << 11),
	NV_ADMA_CTL_WRITE_NON_COHERENT	= (1 << 12),

	/* CPB response flag bits */
	NV_CPB_RESP_DONE		= (1 << 0),
	NV_CPB_RESP_ATA_ERR		= (1 << 3),
	NV_CPB_RESP_CMD_ERR		= (1 << 4),
	NV_CPB_RESP_CPB_ERR		= (1 << 7),

	/* CPB control flag bits */
	NV_CPB_CTL_CPB_VALID		= (1 << 0),
	NV_CPB_CTL_QUEUE		= (1 << 1),
	NV_CPB_CTL_APRD_VALID		= (1 << 2),
	NV_CPB_CTL_IEN			= (1 << 3),
	NV_CPB_CTL_FPDMA		= (1 << 4),

	/* APRD flags */
	NV_APRD_WRITE			= (1 << 1),
	NV_APRD_END			= (1 << 2),
	NV_APRD_CONT			= (1 << 3),

	/* NV_ADMA_STAT flags */
	NV_ADMA_STAT_TIMEOUT		= (1 << 0),
	NV_ADMA_STAT_HOTUNPLUG		= (1 << 1),
	NV_ADMA_STAT_HOTPLUG		= (1 << 2),
	NV_ADMA_STAT_CPBERR		= (1 << 4),
	NV_ADMA_STAT_SERROR		= (1 << 5),
	NV_ADMA_STAT_CMD_COMPLETE	= (1 << 6),
	NV_ADMA_STAT_IDLE		= (1 << 8),
	NV_ADMA_STAT_LEGACY		= (1 << 9),
	NV_ADMA_STAT_STOPPED		= (1 << 10),
	NV_ADMA_STAT_DONE		= (1 << 12),
	NV_ADMA_STAT_ERR		= NV_ADMA_STAT_CPBERR |
					  NV_ADMA_STAT_TIMEOUT,

	/* port flags */
	NV_ADMA_PORT_REGISTER_MODE	= (1 << 0),
	NV_ADMA_ATAPI_SETUP_COMPLETE	= (1 << 1),

	/* MCP55 reg offset */
	NV_CTL_MCP55			= 0x400,
	NV_INT_STATUS_MCP55		= 0x440,
	NV_INT_ENABLE_MCP55		= 0x444,
	NV_NCQ_REG_MCP55		= 0x448,

	/* MCP55 */
	NV_INT_ALL_MCP55		= 0xffff,
	NV_INT_PORT_SHIFT_MCP55		= 16,	/* each port occupies 16 bits */
	NV_INT_MASK_MCP55		= NV_INT_ALL_MCP55 & 0xfffd,

	/* SWNCQ ENABLE BITS*/
	NV_CTL_PRI_SWNCQ		= 0x02,
	NV_CTL_SEC_SWNCQ		= 0x04,

	/* SW NCQ status bits*/
	NV_SWNCQ_IRQ_DEV		= (1 << 0),
	NV_SWNCQ_IRQ_PM			= (1 << 1),
	NV_SWNCQ_IRQ_ADDED		= (1 << 2),
	NV_SWNCQ_IRQ_REMOVED		= (1 << 3),

	NV_SWNCQ_IRQ_BACKOUT		= (1 << 4),
	NV_SWNCQ_IRQ_SDBFIS		= (1 << 5),
	NV_SWNCQ_IRQ_DHREGFIS		= (1 << 6),
	NV_SWNCQ_IRQ_DMASETUP		= (1 << 7),

	NV_SWNCQ_IRQ_HOTPLUG		= NV_SWNCQ_IRQ_ADDED |
					  NV_SWNCQ_IRQ_REMOVED,

};

/* ADMA Physical Region Descriptor - one SG segment */
struct nv_adma_prd {
	__le64			addr;
	__le32			len;
	u8			flags;
	u8			packet_len;
	__le16			reserved;
};

enum nv_adma_regbits {
	CMDEND	= (1 << 15),		/* end of command list */
	WNB	= (1 << 14),		/* wait-not-BSY */
	IGN	= (1 << 13),		/* ignore this entry */
	CS1n	= (1 << (4 + 8)),	/* std. PATA signals follow... */
	DA2	= (1 << (2 + 8)),
	DA1	= (1 << (1 + 8)),
	DA0	= (1 << (0 + 8)),
};

/* ADMA Command Parameter Block
   The first 5 SG segments are stored inside the Command Parameter Block itself.
   If there are more than 5 segments the remainder are stored in a separate
   memory area indicated by next_aprd. */
struct nv_adma_cpb {
	u8			resp_flags;    /* 0 */
	u8			reserved1;     /* 1 */
	u8			ctl_flags;     /* 2 */
	/* len is length of taskfile in 64 bit words */
	u8			len;		/* 3  */
	u8			tag;           /* 4 */
	u8			next_cpb_idx;  /* 5 */
	__le16			reserved2;     /* 6-7 */
	__le16			tf[12];        /* 8-31 */
	struct nv_adma_prd	aprd[5];       /* 32-111 */
	__le64			next_aprd;     /* 112-119 */
	__le64			reserved3;     /* 120-127 */
};


struct nv_adma_port_priv {
	struct nv_adma_cpb	*cpb;
	dma_addr_t		cpb_dma;
	struct nv_adma_prd	*aprd;
	dma_addr_t		aprd_dma;
	void __iomem		*ctl_block;
	void __iomem		*gen_block;
	void __iomem		*notifier_clear_block;
	u64			adma_dma_mask;
	u8			flags;
	int			last_issue_ncq;
};

struct nv_host_priv {
	unsigned long		type;
};

struct defer_queue {
	u32		defer_bits;
	unsigned int	head;
	unsigned int	tail;
	unsigned int	tag[ATA_MAX_QUEUE];
};

enum ncq_saw_flag_list {
	ncq_saw_d2h	= (1U << 0),
	ncq_saw_dmas	= (1U << 1),
	ncq_saw_sdb	= (1U << 2),
	ncq_saw_backout	= (1U << 3),
};

struct nv_swncq_port_priv {
	struct ata_bmdma_prd *prd;	 /* our SG list */
	dma_addr_t	prd_dma; /* and its DMA mapping */
	void __iomem	*sactive_block;
	void __iomem	*irq_block;
	void __iomem	*tag_block;
	u32		qc_active;

	unsigned int	last_issue_tag;

	/* fifo circular queue to store deferral command */
	struct defer_queue defer_queue;

	/* for NCQ interrupt analysis */
	u32		dhfis_bits;
	u32		dmafis_bits;
	u32		sdbfis_bits;

	unsigned int	ncq_flags;
};


#define NV_ADMA_CHECK_INTR(GCTL, PORT) ((GCTL) & (1 << (19 + (12 * (PORT)))))

static int nv_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
#ifdef CONFIG_PM
static int nv_pci_device_resume(struct pci_dev *pdev);
#endif
static void nv_ck804_host_stop(struct ata_host *host);
static irqreturn_t nv_generic_interrupt(int irq, void *dev_instance);
static irqreturn_t nv_nf2_interrupt(int irq, void *dev_instance);
static irqreturn_t nv_ck804_interrupt(int irq, void *dev_instance);
static int nv_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val);
static int nv_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);

static int nv_hardreset(struct ata_link *link, unsigned int *class,
			unsigned long deadline);
static void nv_nf2_freeze(struct ata_port *ap);
static void nv_nf2_thaw(struct ata_port *ap);
static void nv_ck804_freeze(struct ata_port *ap);
static void nv_ck804_thaw(struct ata_port *ap);
static int nv_adma_slave_config(struct scsi_device *sdev);
static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc);
static void nv_adma_qc_prep(struct ata_queued_cmd *qc);
static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc);
static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance);
static void nv_adma_irq_clear(struct ata_port *ap);
static int nv_adma_port_start(struct ata_port *ap);
static void nv_adma_port_stop(struct ata_port *ap);
#ifdef CONFIG_PM
static int nv_adma_port_suspend(struct ata_port *ap, pm_message_t mesg);
static int nv_adma_port_resume(struct ata_port *ap);
#endif
static void nv_adma_freeze(struct ata_port *ap);
static void nv_adma_thaw(struct ata_port *ap);
static void nv_adma_error_handler(struct ata_port *ap);
static void nv_adma_host_stop(struct ata_host *host);
static void nv_adma_post_internal_cmd(struct ata_queued_cmd *qc);
static void nv_adma_tf_read(struct ata_port *ap, struct ata_taskfile *tf);

static void nv_mcp55_thaw(struct ata_port *ap);
static void nv_mcp55_freeze(struct ata_port *ap);
static void nv_swncq_error_handler(struct ata_port *ap);
static int nv_swncq_slave_config(struct scsi_device *sdev);
static int nv_swncq_port_start(struct ata_port *ap);
static void nv_swncq_qc_prep(struct ata_queued_cmd *qc);
static void nv_swncq_fill_sg(struct ata_queued_cmd *qc);
static unsigned int nv_swncq_qc_issue(struct ata_queued_cmd *qc);
static void nv_swncq_irq_clear(struct ata_port *ap, u16 fis);
static irqreturn_t nv_swncq_interrupt(int irq, void *dev_instance);
#ifdef CONFIG_PM
static int nv_swncq_port_suspend(struct ata_port *ap, pm_message_t mesg);
static int nv_swncq_port_resume(struct ata_port *ap);
#endif

enum nv_host_type
{
	GENERIC,
	NFORCE2,
	NFORCE3 = NFORCE2,	/* NF2 == NF3 as far as sata_nv is concerned */
	CK804,
	ADMA,
	MCP5x,
	SWNCQ,
};

static const struct pci_device_id nv_pci_tbl[] = {
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE2S_SATA), NFORCE2 },
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE3S_SATA), NFORCE3 },
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE3S_SATA2), NFORCE3 },
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_CK804_SATA), CK804 },
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_CK804_SATA2), CK804 },
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP04_SATA), CK804 },
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP04_SATA2), CK804 },
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_SATA), MCP5x },
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_SATA2), MCP5x },
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP55_SATA), MCP5x },
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP55_SATA2), MCP5x },
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP61_SATA), GENERIC },
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP61_SATA2), GENERIC },
	{ PCI_VDEVICE(NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP61_SATA3), GENERIC },

	{ } /* terminate list */
};

static struct pci_driver nv_pci_driver = {
	.name			= DRV_NAME,
	.id_table		= nv_pci_tbl,
	.probe			= nv_init_one,
#ifdef CONFIG_PM
	.suspend		= ata_pci_device_suspend,
	.resume			= nv_pci_device_resume,
#endif
	.remove			= ata_pci_remove_one,
};

static struct scsi_host_template nv_sht = {
	ATA_BMDMA_SHT(DRV_NAME),
};

static struct scsi_host_template nv_adma_sht = {
	ATA_NCQ_SHT(DRV_NAME),
	.can_queue		= NV_ADMA_MAX_CPBS,
	.sg_tablesize		= NV_ADMA_SGTBL_TOTAL_LEN,
	.dma_boundary		= NV_ADMA_DMA_BOUNDARY,
	.slave_configure	= nv_adma_slave_config,
};

static struct scsi_host_template nv_swncq_sht = {
	ATA_NCQ_SHT(DRV_NAME),
	.can_queue		= ATA_MAX_QUEUE,
	.sg_tablesize		= LIBATA_MAX_PRD,
	.dma_boundary		= ATA_DMA_BOUNDARY,
	.slave_configure	= nv_swncq_slave_config,
};

/*
 * NV SATA controllers have various different problems with hardreset
 * protocol depending on the specific controller and device.
 *
 * GENERIC:
 *
 *  bko11195 reports that link doesn't come online after hardreset on
 *  generic nv's and there have been several other similar reports on
 *  linux-ide.
 *
 *  bko12351#c23 reports that warmplug on MCP61 doesn't work with
 *  softreset.
 *
 * NF2/3:
 *
 *  bko3352 reports nf2/3 controllers can't determine device signature
 *  reliably after hardreset.  The following thread reports detection
 *  failure on cold boot with the standard debouncing timing.
 *
 *  http://thread.gmane.org/gmane.linux.ide/34098
 *
 *  bko12176 reports that hardreset fails to bring up the link during
 *  boot on nf2.
 *
 * CK804:
 *
 *  For initial probing after boot and hot plugging, hardreset mostly
 *  works fine on CK804 but curiously, reprobing on the initial port
 *  by rescanning or rmmod/insmod fails to acquire the initial D2H Reg
 *  FIS in somewhat undeterministic way.
 *
 * SWNCQ:
 *
 *  bko12351 reports that when SWNCQ is enabled, for hotplug to work,
 *  hardreset should be used and hardreset can't report proper
 *  signature, which suggests that mcp5x is closer to nf2 as long as
 *  reset quirkiness is concerned.
 *
 *  bko12703 reports that boot probing fails for intel SSD with
 *  hardreset.  Link fails to come online.  Softreset works fine.
 *
 * The failures are varied but the following patterns seem true for
 * all flavors.
 *
 * - Softreset during boot always works.
 *
 * - Hardreset during boot sometimes fails to bring up the link on
 *   certain comibnations and device signature acquisition is
 *   unreliable.
 *
 * - Hardreset is often necessary after hotplug.
 *
 * So, preferring softreset for boot probing and error handling (as
 * hardreset might bring down the link) but using hardreset for
 * post-boot probing should work around the above issues in most
 * cases.  Define nv_hardreset() which only kicks in for post-boot
 * probing and use it for all variants.
 */
static struct ata_port_operations nv_generic_ops = {
	.inherits		= &ata_bmdma_port_ops,
	.lost_interrupt		= ATA_OP_NULL,
	.scr_read		= nv_scr_read,
	.scr_write		= nv_scr_write,
	.hardreset		= nv_hardreset,
};

static struct ata_port_operations nv_nf2_ops = {
	.inherits		= &nv_generic_ops,
	.freeze			= nv_nf2_freeze,
	.thaw			= nv_nf2_thaw,
};

static struct ata_port_operations nv_ck804_ops = {
	.inherits		= &nv_generic_ops,
	.freeze			= nv_ck804_freeze,
	.thaw			= nv_ck804_thaw,
	.host_stop		= nv_ck804_host_stop,
};

static struct ata_port_operations nv_adma_ops = {
	.inherits		= &nv_ck804_ops,

	.check_atapi_dma	= nv_adma_check_atapi_dma,
	.sff_tf_read		= nv_adma_tf_read,
	.qc_defer		= ata_std_qc_defer,
	.qc_prep		= nv_adma_qc_prep,
	.qc_issue		= nv_adma_qc_issue,
	.sff_irq_clear		= nv_adma_irq_clear,

	.freeze			= nv_adma_freeze,
	.thaw			= nv_adma_thaw,
	.error_handler		= nv_adma_error_handler,
	.post_internal_cmd	= nv_adma_post_internal_cmd,

	.port_start		= nv_adma_port_start,
	.port_stop		= nv_adma_port_stop,
#ifdef CONFIG_PM
	.port_suspend		= nv_adma_port_suspend,
	.port_resume		= nv_adma_port_resume,
#endif
	.host_stop		= nv_adma_host_stop,
};

static struct ata_port_operations nv_swncq_ops = {
	.inherits		= &nv_generic_ops,

	.qc_defer		= ata_std_qc_defer,
	.qc_prep		= nv_swncq_qc_prep,
	.qc_issue		= nv_swncq_qc_issue,

	.freeze			= nv_mcp55_freeze,
	.thaw			= nv_mcp55_thaw,
	.error_handler		= nv_swncq_error_handler,

#ifdef CONFIG_PM
	.port_suspend		= nv_swncq_port_suspend,
	.port_resume		= nv_swncq_port_resume,
#endif
	.port_start		= nv_swncq_port_start,
};

struct nv_pi_priv {
	irq_handler_t			irq_handler;
	struct scsi_host_template	*sht;
};

#define NV_PI_PRIV(_irq_handler, _sht) \
	&(struct nv_pi_priv){ .irq_handler = _irq_handler, .sht = _sht }

static const struct ata_port_info nv_port_info[] = {
	/* generic */
	{
		.flags		= ATA_FLAG_SATA,
		.pio_mask	= NV_PIO_MASK,
		.mwdma_mask	= NV_MWDMA_MASK,
		.udma_mask	= NV_UDMA_MASK,
		.port_ops	= &nv_generic_ops,
		.private_data	= NV_PI_PRIV(nv_generic_interrupt, &nv_sht),
	},
	/* nforce2/3 */
	{
		.flags		= ATA_FLAG_SATA,
		.pio_mask	= NV_PIO_MASK,
		.mwdma_mask	= NV_MWDMA_MASK,
		.udma_mask	= NV_UDMA_MASK,
		.port_ops	= &nv_nf2_ops,
		.private_data	= NV_PI_PRIV(nv_nf2_interrupt, &nv_sht),
	},
	/* ck804 */
	{
		.flags		= ATA_FLAG_SATA,
		.pio_mask	= NV_PIO_MASK,
		.mwdma_mask	= NV_MWDMA_MASK,
		.udma_mask	= NV_UDMA_MASK,
		.port_ops	= &nv_ck804_ops,
		.private_data	= NV_PI_PRIV(nv_ck804_interrupt, &nv_sht),
	},
	/* ADMA */
	{
		.flags		= ATA_FLAG_SATA | ATA_FLAG_NCQ,
		.pio_mask	= NV_PIO_MASK,
		.mwdma_mask	= NV_MWDMA_MASK,
		.udma_mask	= NV_UDMA_MASK,
		.port_ops	= &nv_adma_ops,
		.private_data	= NV_PI_PRIV(nv_adma_interrupt, &nv_adma_sht),
	},
	/* MCP5x */
	{
		.flags		= ATA_FLAG_SATA,
		.pio_mask	= NV_PIO_MASK,
		.mwdma_mask	= NV_MWDMA_MASK,
		.udma_mask	= NV_UDMA_MASK,
		.port_ops	= &nv_generic_ops,
		.private_data	= NV_PI_PRIV(nv_generic_interrupt, &nv_sht),
	},
	/* SWNCQ */
	{
		.flags	        = ATA_FLAG_SATA | ATA_FLAG_NCQ,
		.pio_mask	= NV_PIO_MASK,
		.mwdma_mask	= NV_MWDMA_MASK,
		.udma_mask	= NV_UDMA_MASK,
		.port_ops	= &nv_swncq_ops,
		.private_data	= NV_PI_PRIV(nv_swncq_interrupt, &nv_swncq_sht),
	},
};

MODULE_AUTHOR("NVIDIA");
MODULE_DESCRIPTION("low-level driver for NVIDIA nForce SATA controller");
MODULE_LICENSE("GPL");
MODULE_DEVICE_TABLE(pci, nv_pci_tbl);
MODULE_VERSION(DRV_VERSION);

static bool adma_enabled;
static bool swncq_enabled = 1;
static bool msi_enabled;

static void nv_adma_register_mode(struct ata_port *ap)
{
	struct nv_adma_port_priv *pp = ap->private_data;
	void __iomem *mmio = pp->ctl_block;
	u16 tmp, status;
	int count = 0;

	if (pp->flags & NV_ADMA_PORT_REGISTER_MODE)
		return;

	status = readw(mmio + NV_ADMA_STAT);
	while (!(status & NV_ADMA_STAT_IDLE) && count < 20) {
		ndelay(50);
		status = readw(mmio + NV_ADMA_STAT);
		count++;
	}
	if (count == 20)
		ata_port_warn(ap, "timeout waiting for ADMA IDLE, stat=0x%hx\n",
			      status);

	tmp = readw(mmio + NV_ADMA_CTL);
	writew(tmp & ~NV_ADMA_CTL_GO, mmio + NV_ADMA_CTL);

	count = 0;
	status = readw(mmio + NV_ADMA_STAT);
	while (!(status & NV_ADMA_STAT_LEGACY) && count < 20) {
		ndelay(50);
		status = readw(mmio + NV_ADMA_STAT);
		count++;
	}
	if (count == 20)
		ata_port_warn(ap,
			      "timeout waiting for ADMA LEGACY, stat=0x%hx\n",
			      status);

	pp->flags |= NV_ADMA_PORT_REGISTER_MODE;
}

static void nv_adma_mode(struct ata_port *ap)
{
	struct nv_adma_port_priv *pp = ap->private_data;
	void __iomem *mmio = pp->ctl_block;
	u16 tmp, status;
	int count = 0;

	if (!(pp->flags & NV_ADMA_PORT_REGISTER_MODE))
		return;

	WARN_ON(pp->flags & NV_ADMA_ATAPI_SETUP_COMPLETE);

	tmp = readw(mmio + NV_ADMA_CTL);
	writew(tmp | NV_ADMA_CTL_GO, mmio + NV_ADMA_CTL);

	status = readw(mmio + NV_ADMA_STAT);
	while (((status & NV_ADMA_STAT_LEGACY) ||
	      !(status & NV_ADMA_STAT_IDLE)) && count < 20) {
		ndelay(50);
		status = readw(mmio + NV_ADMA_STAT);
		count++;
	}
	if (count == 20)
		ata_port_warn(ap,
			"timeout waiting for ADMA LEGACY clear and IDLE, stat=0x%hx\n",
			status);

	pp->flags &= ~NV_ADMA_PORT_REGISTER_MODE;
}

static int nv_adma_slave_config(struct scsi_device *sdev)
{
	struct ata_port *ap = ata_shost_to_port(sdev->host);
	struct nv_adma_port_priv *pp = ap->private_data;
	struct nv_adma_port_priv *port0, *port1;
	struct scsi_device *sdev0, *sdev1;
	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
	unsigned long segment_boundary, flags;
	unsigned short sg_tablesize;
	int rc;
	int adma_enable;
	u32 current_reg, new_reg, config_mask;

	rc = ata_scsi_slave_config(sdev);

	if (sdev->id >= ATA_MAX_DEVICES || sdev->channel || sdev->lun)
		/* Not a proper libata device, ignore */
		return rc;

	spin_lock_irqsave(ap->lock, flags);

	if (ap->link.device[sdev->id].class == ATA_DEV_ATAPI) {
		/*
		 * NVIDIA reports that ADMA mode does not support ATAPI commands.
		 * Therefore ATAPI commands are sent through the legacy interface.
		 * However, the legacy interface only supports 32-bit DMA.
		 * Restrict DMA parameters as required by the legacy interface
		 * when an ATAPI device is connected.
		 */
		segment_boundary = ATA_DMA_BOUNDARY;
		/* Subtract 1 since an extra entry may be needed for padding, see
		   libata-scsi.c */
		sg_tablesize = LIBATA_MAX_PRD - 1;

		/* Since the legacy DMA engine is in use, we need to disable ADMA
		   on the port. */
		adma_enable = 0;
		nv_adma_register_mode(ap);
	} else {
		segment_boundary = NV_ADMA_DMA_BOUNDARY;
		sg_tablesize = NV_ADMA_SGTBL_TOTAL_LEN;
		adma_enable = 1;
	}

	pci_read_config_dword(pdev, NV_MCP_SATA_CFG_20, &current_reg);

	if (ap->port_no == 1)
		config_mask = NV_MCP_SATA_CFG_20_PORT1_EN |
			      NV_MCP_SATA_CFG_20_PORT1_PWB_EN;
	else
		config_mask = NV_MCP_SATA_CFG_20_PORT0_EN |
			      NV_MCP_SATA_CFG_20_PORT0_PWB_EN;

	if (adma_enable) {
		new_reg = current_reg | config_mask;
		pp->flags &= ~NV_ADMA_ATAPI_SETUP_COMPLETE;
	} else {
		new_reg = current_reg & ~config_mask;
		pp->flags |= NV_ADMA_ATAPI_SETUP_COMPLETE;
	}

	if (current_reg != new_reg)
		pci_write_config_dword(pdev, NV_MCP_SATA_CFG_20, new_reg);

	port0 = ap->host->ports[0]->private_data;
	port1 = ap->host->ports[1]->private_data;