timekeeping.c 64.6 KB
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 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
/*
 *  linux/kernel/time/timekeeping.c
 *
 *  Kernel timekeeping code and accessor functions
 *
 *  This code was moved from linux/kernel/timer.c.
 *  Please see that file for copyright and history logs.
 *
 */

#include <linux/timekeeper_internal.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/nmi.h>
#include <linux/sched.h>
#include <linux/sched/loadavg.h>
#include <linux/syscore_ops.h>
#include <linux/clocksource.h>
#include <linux/jiffies.h>
#include <linux/time.h>
#include <linux/tick.h>
#include <linux/stop_machine.h>
#include <linux/pvclock_gtod.h>
#include <linux/compiler.h>

#include "tick-internal.h"
#include "ntp_internal.h"
#include "timekeeping_internal.h"

#define TK_CLEAR_NTP		(1 << 0)
#define TK_MIRROR		(1 << 1)
#define TK_CLOCK_WAS_SET	(1 << 2)

/*
 * The most important data for readout fits into a single 64 byte
 * cache line.
 */
static struct {
	seqcount_t		seq;
	struct timekeeper	timekeeper;
} tk_core ____cacheline_aligned;

static DEFINE_RAW_SPINLOCK(timekeeper_lock);
static struct timekeeper shadow_timekeeper;

/**
 * struct tk_fast - NMI safe timekeeper
 * @seq:	Sequence counter for protecting updates. The lowest bit
 *		is the index for the tk_read_base array
 * @base:	tk_read_base array. Access is indexed by the lowest bit of
 *		@seq.
 *
 * See @update_fast_timekeeper() below.
 */
struct tk_fast {
	seqcount_t		seq;
	struct tk_read_base	base[2];
};

static struct tk_fast tk_fast_mono ____cacheline_aligned;
static struct tk_fast tk_fast_raw  ____cacheline_aligned;

/* flag for if timekeeping is suspended */
int __read_mostly timekeeping_suspended;

static inline void tk_normalize_xtime(struct timekeeper *tk)
{
	while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) {
		tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift;
		tk->xtime_sec++;
	}
	while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) {
		tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift;
		tk->raw_sec++;
	}
}

static inline struct timespec64 tk_xtime(struct timekeeper *tk)
{
	struct timespec64 ts;

	ts.tv_sec = tk->xtime_sec;
	ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
	return ts;
}

static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts)
{
	tk->xtime_sec = ts->tv_sec;
	tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift;
}

static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
{
	tk->xtime_sec += ts->tv_sec;
	tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift;
	tk_normalize_xtime(tk);
}

static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
{
	struct timespec64 tmp;

	/*
	 * Verify consistency of: offset_real = -wall_to_monotonic
	 * before modifying anything
	 */
	set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec,
					-tk->wall_to_monotonic.tv_nsec);
	WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp));
	tk->wall_to_monotonic = wtm;
	set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
	tk->offs_real = timespec64_to_ktime(tmp);
	tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0));
}

static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
{
	tk->offs_boot = ktime_add(tk->offs_boot, delta);
}

/*
 * tk_clock_read - atomic clocksource read() helper
 *
 * This helper is necessary to use in the read paths because, while the
 * seqlock ensures we don't return a bad value while structures are updated,
 * it doesn't protect from potential crashes. There is the possibility that
 * the tkr's clocksource may change between the read reference, and the
 * clock reference passed to the read function.  This can cause crashes if
 * the wrong clocksource is passed to the wrong read function.
 * This isn't necessary to use when holding the timekeeper_lock or doing
 * a read of the fast-timekeeper tkrs (which is protected by its own locking
 * and update logic).
 */
static inline u64 tk_clock_read(struct tk_read_base *tkr)
{
	struct clocksource *clock = READ_ONCE(tkr->clock);

	return clock->read(clock);
}

#ifdef CONFIG_DEBUG_TIMEKEEPING
#define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */

static void timekeeping_check_update(struct timekeeper *tk, u64 offset)
{

	u64 max_cycles = tk->tkr_mono.clock->max_cycles;
	const char *name = tk->tkr_mono.clock->name;

	if (offset > max_cycles) {
		printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n",
				offset, name, max_cycles);
		printk_deferred("         timekeeping: Your kernel is sick, but tries to cope by capping time updates\n");
	} else {
		if (offset > (max_cycles >> 1)) {
			printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the '%s' clock's 50%% safety margin (%lld)\n",
					offset, name, max_cycles >> 1);
			printk_deferred("      timekeeping: Your kernel is still fine, but is feeling a bit nervous\n");
		}
	}

	if (tk->underflow_seen) {
		if (jiffies - tk->last_warning > WARNING_FREQ) {
			printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name);
			printk_deferred("         Please report this, consider using a different clocksource, if possible.\n");
			printk_deferred("         Your kernel is probably still fine.\n");
			tk->last_warning = jiffies;
		}
		tk->underflow_seen = 0;
	}

	if (tk->overflow_seen) {
		if (jiffies - tk->last_warning > WARNING_FREQ) {
			printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name);
			printk_deferred("         Please report this, consider using a different clocksource, if possible.\n");
			printk_deferred("         Your kernel is probably still fine.\n");
			tk->last_warning = jiffies;
		}
		tk->overflow_seen = 0;
	}
}

static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	u64 now, last, mask, max, delta;
	unsigned int seq;

	/*
	 * Since we're called holding a seqlock, the data may shift
	 * under us while we're doing the calculation. This can cause
	 * false positives, since we'd note a problem but throw the
	 * results away. So nest another seqlock here to atomically
	 * grab the points we are checking with.
	 */
	do {
		seq = read_seqcount_begin(&tk_core.seq);
		now = tk_clock_read(tkr);
		last = tkr->cycle_last;
		mask = tkr->mask;
		max = tkr->clock->max_cycles;
	} while (read_seqcount_retry(&tk_core.seq, seq));

	delta = clocksource_delta(now, last, mask);

	/*
	 * Try to catch underflows by checking if we are seeing small
	 * mask-relative negative values.
	 */
	if (unlikely((~delta & mask) < (mask >> 3))) {
		tk->underflow_seen = 1;
		delta = 0;
	}

	/* Cap delta value to the max_cycles values to avoid mult overflows */
	if (unlikely(delta > max)) {
		tk->overflow_seen = 1;
		delta = tkr->clock->max_cycles;
	}

	return delta;
}
#else
static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset)
{
}
static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
{
	u64 cycle_now, delta;

	/* read clocksource */
	cycle_now = tk_clock_read(tkr);

	/* calculate the delta since the last update_wall_time */
	delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask);

	return delta;
}
#endif

/**
 * tk_setup_internals - Set up internals to use clocksource clock.
 *
 * @tk:		The target timekeeper to setup.
 * @clock:		Pointer to clocksource.
 *
 * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment
 * pair and interval request.
 *
 * Unless you're the timekeeping code, you should not be using this!
 */
static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
{
	u64 interval;
	u64 tmp, ntpinterval;
	struct clocksource *old_clock;

	++tk->cs_was_changed_seq;
	old_clock = tk->tkr_mono.clock;
	tk->tkr_mono.clock = clock;
	tk->tkr_mono.mask = clock->mask;
	tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono);

	tk->tkr_raw.clock = clock;
	tk->tkr_raw.mask = clock->mask;
	tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last;

	/* Do the ns -> cycle conversion first, using original mult */
	tmp = NTP_INTERVAL_LENGTH;
	tmp <<= clock->shift;
	ntpinterval = tmp;
	tmp += clock->mult/2;
	do_div(tmp, clock->mult);
	if (tmp == 0)
		tmp = 1;

	interval = (u64) tmp;
	tk->cycle_interval = interval;

	/* Go back from cycles -> shifted ns */
	tk->xtime_interval = interval * clock->mult;
	tk->xtime_remainder = ntpinterval - tk->xtime_interval;
	tk->raw_interval = interval * clock->mult;

	 /* if changing clocks, convert xtime_nsec shift units */
	if (old_clock) {
		int shift_change = clock->shift - old_clock->shift;
		if (shift_change < 0) {
			tk->tkr_mono.xtime_nsec >>= -shift_change;
			tk->tkr_raw.xtime_nsec >>= -shift_change;
		} else {
			tk->tkr_mono.xtime_nsec <<= shift_change;
			tk->tkr_raw.xtime_nsec <<= shift_change;
		}
	}

	tk->tkr_mono.shift = clock->shift;
	tk->tkr_raw.shift = clock->shift;

	tk->ntp_error = 0;
	tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift;
	tk->ntp_tick = ntpinterval << tk->ntp_error_shift;

	/*
	 * The timekeeper keeps its own mult values for the currently
	 * active clocksource. These value will be adjusted via NTP
	 * to counteract clock drifting.
	 */
	tk->tkr_mono.mult = clock->mult;
	tk->tkr_raw.mult = clock->mult;
	tk->ntp_err_mult = 0;
}

/* Timekeeper helper functions. */

#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
static u32 default_arch_gettimeoffset(void) { return 0; }
u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
#else
static inline u32 arch_gettimeoffset(void) { return 0; }
#endif

static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
{
	u64 nsec;

	nsec = delta * tkr->mult + tkr->xtime_nsec;
	nsec >>= tkr->shift;

	/* If arch requires, add in get_arch_timeoffset() */
	return nsec + arch_gettimeoffset();
}

static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
{
	u64 delta;

	delta = timekeeping_get_delta(tkr);
	return timekeeping_delta_to_ns(tkr, delta);
}

static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles)
{
	u64 delta;

	/* calculate the delta since the last update_wall_time */
	delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask);
	return timekeeping_delta_to_ns(tkr, delta);
}

/**
 * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper.
 * @tkr: Timekeeping readout base from which we take the update
 *
 * We want to use this from any context including NMI and tracing /
 * instrumenting the timekeeping code itself.
 *
 * Employ the latch technique; see @raw_write_seqcount_latch.
 *
 * So if a NMI hits the update of base[0] then it will use base[1]
 * which is still consistent. In the worst case this can result is a
 * slightly wrong timestamp (a few nanoseconds). See
 * @ktime_get_mono_fast_ns.
 */
static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf)
{
	struct tk_read_base *base = tkf->base;

	/* Force readers off to base[1] */
	raw_write_seqcount_latch(&tkf->seq);

	/* Update base[0] */
	memcpy(base, tkr, sizeof(*base));

	/* Force readers back to base[0] */
	raw_write_seqcount_latch(&tkf->seq);

	/* Update base[1] */
	memcpy(base + 1, base, sizeof(*base));
}

/**
 * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic
 *
 * This timestamp is not guaranteed to be monotonic across an update.
 * The timestamp is calculated by:
 *
 *	now = base_mono + clock_delta * slope
 *
 * So if the update lowers the slope, readers who are forced to the
 * not yet updated second array are still using the old steeper slope.
 *
 * tmono
 * ^
 * |    o  n
 * |   o n
 * |  u
 * | o
 * |o
 * |12345678---> reader order
 *
 * o = old slope
 * u = update
 * n = new slope
 *
 * So reader 6 will observe time going backwards versus reader 5.
 *
 * While other CPUs are likely to be able observe that, the only way
 * for a CPU local observation is when an NMI hits in the middle of
 * the update. Timestamps taken from that NMI context might be ahead
 * of the following timestamps. Callers need to be aware of that and
 * deal with it.
 */
static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
{
	struct tk_read_base *tkr;
	unsigned int seq;
	u64 now;

	do {
		seq = raw_read_seqcount_latch(&tkf->seq);
		tkr = tkf->base + (seq & 0x01);
		now = ktime_to_ns(tkr->base);

		now += timekeeping_delta_to_ns(tkr,
				clocksource_delta(
					tk_clock_read(tkr),
					tkr->cycle_last,
					tkr->mask));
	} while (read_seqcount_retry(&tkf->seq, seq));

	return now;
}

u64 ktime_get_mono_fast_ns(void)
{
	return __ktime_get_fast_ns(&tk_fast_mono);
}
EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns);

u64 ktime_get_raw_fast_ns(void)
{
	return __ktime_get_fast_ns(&tk_fast_raw);
}
EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns);

/**
 * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock.
 *
 * To keep it NMI safe since we're accessing from tracing, we're not using a
 * separate timekeeper with updates to monotonic clock and boot offset
 * protected with seqlocks. This has the following minor side effects:
 *
 * (1) Its possible that a timestamp be taken after the boot offset is updated
 * but before the timekeeper is updated. If this happens, the new boot offset
 * is added to the old timekeeping making the clock appear to update slightly
 * earlier:
 *    CPU 0                                        CPU 1
 *    timekeeping_inject_sleeptime64()
 *    __timekeeping_inject_sleeptime(tk, delta);
 *                                                 timestamp();
 *    timekeeping_update(tk, TK_CLEAR_NTP...);
 *
 * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be
 * partially updated.  Since the tk->offs_boot update is a rare event, this
 * should be a rare occurrence which postprocessing should be able to handle.
 */
u64 notrace ktime_get_boot_fast_ns(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;

	return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot));
}
EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);

/* Suspend-time cycles value for halted fast timekeeper. */
static u64 cycles_at_suspend;

static u64 dummy_clock_read(struct clocksource *cs)
{
	return cycles_at_suspend;
}

static struct clocksource dummy_clock = {
	.read = dummy_clock_read,
};

/**
 * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource.
 * @tk: Timekeeper to snapshot.
 *
 * It generally is unsafe to access the clocksource after timekeeping has been
 * suspended, so take a snapshot of the readout base of @tk and use it as the
 * fast timekeeper's readout base while suspended.  It will return the same
 * number of cycles every time until timekeeping is resumed at which time the
 * proper readout base for the fast timekeeper will be restored automatically.
 */
static void halt_fast_timekeeper(struct timekeeper *tk)
{
	static struct tk_read_base tkr_dummy;
	struct tk_read_base *tkr = &tk->tkr_mono;

	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
	cycles_at_suspend = tk_clock_read(tkr);
	tkr_dummy.clock = &dummy_clock;
	update_fast_timekeeper(&tkr_dummy, &tk_fast_mono);

	tkr = &tk->tkr_raw;
	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
	tkr_dummy.clock = &dummy_clock;
	update_fast_timekeeper(&tkr_dummy, &tk_fast_raw);
}

#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD
#warning Please contact your maintainers, as GENERIC_TIME_VSYSCALL_OLD compatibity will disappear soon.

static inline void update_vsyscall(struct timekeeper *tk)
{
	struct timespec xt, wm;

	xt = timespec64_to_timespec(tk_xtime(tk));
	wm = timespec64_to_timespec(tk->wall_to_monotonic);
	update_vsyscall_old(&xt, &wm, tk->tkr_mono.clock, tk->tkr_mono.mult,
			    tk->tkr_mono.cycle_last);
}

static inline void old_vsyscall_fixup(struct timekeeper *tk)
{
	s64 remainder;

	/*
	* Store only full nanoseconds into xtime_nsec after rounding
	* it up and add the remainder to the error difference.
	* XXX - This is necessary to avoid small 1ns inconsistnecies caused
	* by truncating the remainder in vsyscalls. However, it causes
	* additional work to be done in timekeeping_adjust(). Once
	* the vsyscall implementations are converted to use xtime_nsec
	* (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD
	* users are removed, this can be killed.
	*/
	remainder = tk->tkr_mono.xtime_nsec & ((1ULL << tk->tkr_mono.shift) - 1);
	if (remainder != 0) {
		tk->tkr_mono.xtime_nsec -= remainder;
		tk->tkr_mono.xtime_nsec += 1ULL << tk->tkr_mono.shift;
		tk->ntp_error += remainder << tk->ntp_error_shift;
		tk->ntp_error -= (1ULL << tk->tkr_mono.shift) << tk->ntp_error_shift;
	}
}
#else
#define old_vsyscall_fixup(tk)
#endif

static RAW_NOTIFIER_HEAD(pvclock_gtod_chain);

static void update_pvclock_gtod(struct timekeeper *tk, bool was_set)
{
	raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk);
}

/**
 * pvclock_gtod_register_notifier - register a pvclock timedata update listener
 */
int pvclock_gtod_register_notifier(struct notifier_block *nb)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long flags;
	int ret;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb);
	update_pvclock_gtod(tk, true);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	return ret;
}
EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier);

/**
 * pvclock_gtod_unregister_notifier - unregister a pvclock
 * timedata update listener
 */
int pvclock_gtod_unregister_notifier(struct notifier_block *nb)
{
	unsigned long flags;
	int ret;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	return ret;
}
EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);

/*
 * tk_update_leap_state - helper to update the next_leap_ktime
 */
static inline void tk_update_leap_state(struct timekeeper *tk)
{
	tk->next_leap_ktime = ntp_get_next_leap();
	if (tk->next_leap_ktime != KTIME_MAX)
		/* Convert to monotonic time */
		tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real);
}

/*
 * Update the ktime_t based scalar nsec members of the timekeeper
 */
static inline void tk_update_ktime_data(struct timekeeper *tk)
{
	u64 seconds;
	u32 nsec;

	/*
	 * The xtime based monotonic readout is:
	 *	nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now();
	 * The ktime based monotonic readout is:
	 *	nsec = base_mono + now();
	 * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec
	 */
	seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec);
	nsec = (u32) tk->wall_to_monotonic.tv_nsec;
	tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec);

	/*
	 * The sum of the nanoseconds portions of xtime and
	 * wall_to_monotonic can be greater/equal one second. Take
	 * this into account before updating tk->ktime_sec.
	 */
	nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
	if (nsec >= NSEC_PER_SEC)
		seconds++;
	tk->ktime_sec = seconds;

	/* Update the monotonic raw base */
	tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC);
}

/* must hold timekeeper_lock */
static void timekeeping_update(struct timekeeper *tk, unsigned int action)
{
	if (action & TK_CLEAR_NTP) {
		tk->ntp_error = 0;
		ntp_clear();
	}

	tk_update_leap_state(tk);
	tk_update_ktime_data(tk);

	update_vsyscall(tk);
	update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);

	update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono);
	update_fast_timekeeper(&tk->tkr_raw,  &tk_fast_raw);

	if (action & TK_CLOCK_WAS_SET)
		tk->clock_was_set_seq++;
	/*
	 * The mirroring of the data to the shadow-timekeeper needs
	 * to happen last here to ensure we don't over-write the
	 * timekeeper structure on the next update with stale data
	 */
	if (action & TK_MIRROR)
		memcpy(&shadow_timekeeper, &tk_core.timekeeper,
		       sizeof(tk_core.timekeeper));
}

/**
 * timekeeping_forward_now - update clock to the current time
 *
 * Forward the current clock to update its state since the last call to
 * update_wall_time(). This is useful before significant clock changes,
 * as it avoids having to deal with this time offset explicitly.
 */
static void timekeeping_forward_now(struct timekeeper *tk)
{
	u64 cycle_now, delta;

	cycle_now = tk_clock_read(&tk->tkr_mono);
	delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
	tk->tkr_mono.cycle_last = cycle_now;
	tk->tkr_raw.cycle_last  = cycle_now;

	tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult;

	/* If arch requires, add in get_arch_timeoffset() */
	tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift;


	tk->tkr_raw.xtime_nsec += delta * tk->tkr_raw.mult;

	/* If arch requires, add in get_arch_timeoffset() */
	tk->tkr_raw.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_raw.shift;

	tk_normalize_xtime(tk);
}

/**
 * __getnstimeofday64 - Returns the time of day in a timespec64.
 * @ts:		pointer to the timespec to be set
 *
 * Updates the time of day in the timespec.
 * Returns 0 on success, or -ve when suspended (timespec will be undefined).
 */
int __getnstimeofday64(struct timespec64 *ts)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long seq;
	u64 nsecs;

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		ts->tv_sec = tk->xtime_sec;
		nsecs = timekeeping_get_ns(&tk->tkr_mono);

	} while (read_seqcount_retry(&tk_core.seq, seq));

	ts->tv_nsec = 0;
	timespec64_add_ns(ts, nsecs);

	/*
	 * Do not bail out early, in case there were callers still using
	 * the value, even in the face of the WARN_ON.
	 */
	if (unlikely(timekeeping_suspended))
		return -EAGAIN;
	return 0;
}
EXPORT_SYMBOL(__getnstimeofday64);

/**
 * getnstimeofday64 - Returns the time of day in a timespec64.
 * @ts:		pointer to the timespec64 to be set
 *
 * Returns the time of day in a timespec64 (WARN if suspended).
 */
void getnstimeofday64(struct timespec64 *ts)
{
	WARN_ON(__getnstimeofday64(ts));
}
EXPORT_SYMBOL(getnstimeofday64);

ktime_t ktime_get(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned int seq;
	ktime_t base;
	u64 nsecs;

	WARN_ON(timekeeping_suspended);

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		base = tk->tkr_mono.base;
		nsecs = timekeeping_get_ns(&tk->tkr_mono);

	} while (read_seqcount_retry(&tk_core.seq, seq));

	return ktime_add_ns(base, nsecs);
}
EXPORT_SYMBOL_GPL(ktime_get);

u32 ktime_get_resolution_ns(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned int seq;
	u32 nsecs;

	WARN_ON(timekeeping_suspended);

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift;
	} while (read_seqcount_retry(&tk_core.seq, seq));

	return nsecs;
}
EXPORT_SYMBOL_GPL(ktime_get_resolution_ns);

static ktime_t *offsets[TK_OFFS_MAX] = {
	[TK_OFFS_REAL]	= &tk_core.timekeeper.offs_real,
	[TK_OFFS_BOOT]	= &tk_core.timekeeper.offs_boot,
	[TK_OFFS_TAI]	= &tk_core.timekeeper.offs_tai,
};

ktime_t ktime_get_with_offset(enum tk_offsets offs)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned int seq;
	ktime_t base, *offset = offsets[offs];
	u64 nsecs;

	WARN_ON(timekeeping_suspended);

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		base = ktime_add(tk->tkr_mono.base, *offset);
		nsecs = timekeeping_get_ns(&tk->tkr_mono);

	} while (read_seqcount_retry(&tk_core.seq, seq));

	return ktime_add_ns(base, nsecs);

}
EXPORT_SYMBOL_GPL(ktime_get_with_offset);

/**
 * ktime_mono_to_any() - convert mononotic time to any other time
 * @tmono:	time to convert.
 * @offs:	which offset to use
 */
ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs)
{
	ktime_t *offset = offsets[offs];
	unsigned long seq;
	ktime_t tconv;

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		tconv = ktime_add(tmono, *offset);
	} while (read_seqcount_retry(&tk_core.seq, seq));

	return tconv;
}
EXPORT_SYMBOL_GPL(ktime_mono_to_any);

/**
 * ktime_get_raw - Returns the raw monotonic time in ktime_t format
 */
ktime_t ktime_get_raw(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned int seq;
	ktime_t base;
	u64 nsecs;

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		base = tk->tkr_raw.base;
		nsecs = timekeeping_get_ns(&tk->tkr_raw);

	} while (read_seqcount_retry(&tk_core.seq, seq));

	return ktime_add_ns(base, nsecs);
}
EXPORT_SYMBOL_GPL(ktime_get_raw);

/**
 * ktime_get_ts64 - get the monotonic clock in timespec64 format
 * @ts:		pointer to timespec variable
 *
 * The function calculates the monotonic clock from the realtime
 * clock and the wall_to_monotonic offset and stores the result
 * in normalized timespec64 format in the variable pointed to by @ts.
 */
void ktime_get_ts64(struct timespec64 *ts)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	struct timespec64 tomono;
	unsigned int seq;
	u64 nsec;

	WARN_ON(timekeeping_suspended);

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		ts->tv_sec = tk->xtime_sec;
		nsec = timekeeping_get_ns(&tk->tkr_mono);
		tomono = tk->wall_to_monotonic;

	} while (read_seqcount_retry(&tk_core.seq, seq));

	ts->tv_sec += tomono.tv_sec;
	ts->tv_nsec = 0;
	timespec64_add_ns(ts, nsec + tomono.tv_nsec);
}
EXPORT_SYMBOL_GPL(ktime_get_ts64);

/**
 * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC
 *
 * Returns the seconds portion of CLOCK_MONOTONIC with a single non
 * serialized read. tk->ktime_sec is of type 'unsigned long' so this
 * works on both 32 and 64 bit systems. On 32 bit systems the readout
 * covers ~136 years of uptime which should be enough to prevent
 * premature wrap arounds.
 */
time64_t ktime_get_seconds(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;

	WARN_ON(timekeeping_suspended);
	return tk->ktime_sec;
}
EXPORT_SYMBOL_GPL(ktime_get_seconds);

/**
 * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME
 *
 * Returns the wall clock seconds since 1970. This replaces the
 * get_seconds() interface which is not y2038 safe on 32bit systems.
 *
 * For 64bit systems the fast access to tk->xtime_sec is preserved. On
 * 32bit systems the access must be protected with the sequence
 * counter to provide "atomic" access to the 64bit tk->xtime_sec
 * value.
 */
time64_t ktime_get_real_seconds(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	time64_t seconds;
	unsigned int seq;

	if (IS_ENABLED(CONFIG_64BIT))
		return tk->xtime_sec;

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		seconds = tk->xtime_sec;

	} while (read_seqcount_retry(&tk_core.seq, seq));

	return seconds;
}
EXPORT_SYMBOL_GPL(ktime_get_real_seconds);

/**
 * __ktime_get_real_seconds - The same as ktime_get_real_seconds
 * but without the sequence counter protect. This internal function
 * is called just when timekeeping lock is already held.
 */
time64_t __ktime_get_real_seconds(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;

	return tk->xtime_sec;
}

/**
 * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter
 * @systime_snapshot:	pointer to struct receiving the system time snapshot
 */
void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long seq;
	ktime_t base_raw;
	ktime_t base_real;
	u64 nsec_raw;
	u64 nsec_real;
	u64 now;

	WARN_ON_ONCE(timekeeping_suspended);

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		now = tk_clock_read(&tk->tkr_mono);
		systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq;
		systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq;
		base_real = ktime_add(tk->tkr_mono.base,
				      tk_core.timekeeper.offs_real);
		base_raw = tk->tkr_raw.base;
		nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now);
		nsec_raw  = timekeeping_cycles_to_ns(&tk->tkr_raw, now);
	} while (read_seqcount_retry(&tk_core.seq, seq));

	systime_snapshot->cycles = now;
	systime_snapshot->real = ktime_add_ns(base_real, nsec_real);
	systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw);
}
EXPORT_SYMBOL_GPL(ktime_get_snapshot);

/* Scale base by mult/div checking for overflow */
static int scale64_check_overflow(u64 mult, u64 div, u64 *base)
{
	u64 tmp, rem;

	tmp = div64_u64_rem(*base, div, &rem);

	if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) ||
	    ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem)))
		return -EOVERFLOW;
	tmp *= mult;
	rem *= mult;

	do_div(rem, div);
	*base = tmp + rem;
	return 0;
}

/**
 * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval
 * @history:			Snapshot representing start of history
 * @partial_history_cycles:	Cycle offset into history (fractional part)
 * @total_history_cycles:	Total history length in cycles
 * @discontinuity:		True indicates clock was set on history period
 * @ts:				Cross timestamp that should be adjusted using
 *	partial/total ratio
 *
 * Helper function used by get_device_system_crosststamp() to correct the
 * crosstimestamp corresponding to the start of the current interval to the
 * system counter value (timestamp point) provided by the driver. The
 * total_history_* quantities are the total history starting at the provided
 * reference point and ending at the start of the current interval. The cycle
 * count between the driver timestamp point and the start of the current
 * interval is partial_history_cycles.
 */
static int adjust_historical_crosststamp(struct system_time_snapshot *history,
					 u64 partial_history_cycles,
					 u64 total_history_cycles,
					 bool discontinuity,
					 struct system_device_crosststamp *ts)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	u64 corr_raw, corr_real;
	bool interp_forward;
	int ret;

	if (total_history_cycles == 0 || partial_history_cycles == 0)
		return 0;

	/* Interpolate shortest distance from beginning or end of history */
	interp_forward = partial_history_cycles > total_history_cycles / 2;
	partial_history_cycles = interp_forward ?
		total_history_cycles - partial_history_cycles :
		partial_history_cycles;

	/*
	 * Scale the monotonic raw time delta by:
	 *	partial_history_cycles / total_history_cycles
	 */
	corr_raw = (u64)ktime_to_ns(
		ktime_sub(ts->sys_monoraw, history->raw));
	ret = scale64_check_overflow(partial_history_cycles,
				     total_history_cycles, &corr_raw);
	if (ret)
		return ret;

	/*
	 * If there is a discontinuity in the history, scale monotonic raw
	 *	correction by:
	 *	mult(real)/mult(raw) yielding the realtime correction
	 * Otherwise, calculate the realtime correction similar to monotonic
	 *	raw calculation
	 */
	if (discontinuity) {
		corr_real = mul_u64_u32_div
			(corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult);
	} else {
		corr_real = (u64)ktime_to_ns(
			ktime_sub(ts->sys_realtime, history->real));
		ret = scale64_check_overflow(partial_history_cycles,
					     total_history_cycles, &corr_real);
		if (ret)
			return ret;
	}

	/* Fixup monotonic raw and real time time values */
	if (interp_forward) {
		ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw);
		ts->sys_realtime = ktime_add_ns(history->real, corr_real);
	} else {
		ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw);
		ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real);
	}

	return 0;
}

/*
 * cycle_between - true if test occurs chronologically between before and after
 */
static bool cycle_between(u64 before, u64 test, u64 after)
{
	if (test > before && test < after)
		return true;
	if (test < before && before > after)
		return true;
	return false;
}

/**
 * get_device_system_crosststamp - Synchronously capture system/device timestamp
 * @get_time_fn:	Callback to get simultaneous device time and
 *	system counter from the device driver
 * @ctx:		Context passed to get_time_fn()
 * @history_begin:	Historical reference point used to interpolate system
 *	time when counter provided by the driver is before the current interval
 * @xtstamp:		Receives simultaneously captured system and device time
 *
 * Reads a timestamp from a device and correlates it to system time
 */
int get_device_system_crosststamp(int (*get_time_fn)
				  (ktime_t *device_time,
				   struct system_counterval_t *sys_counterval,
				   void *ctx),
				  void *ctx,
				  struct system_time_snapshot *history_begin,
				  struct system_device_crosststamp *xtstamp)
{
	struct system_counterval_t system_counterval;
	struct timekeeper *tk = &tk_core.timekeeper;
	u64 cycles, now, interval_start;
	unsigned int clock_was_set_seq = 0;
	ktime_t base_real, base_raw;
	u64 nsec_real, nsec_raw;
	u8 cs_was_changed_seq;
	unsigned long seq;
	bool do_interp;
	int ret;

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		/*
		 * Try to synchronously capture device time and a system
		 * counter value calling back into the device driver
		 */
		ret = get_time_fn(&xtstamp->device, &system_counterval, ctx);
		if (ret)
			return ret;

		/*
		 * Verify that the clocksource associated with the captured
		 * system counter value is the same as the currently installed
		 * timekeeper clocksource
		 */
		if (tk->tkr_mono.clock != system_counterval.cs)
			return -ENODEV;
		cycles = system_counterval.cycles;

		/*
		 * Check whether the system counter value provided by the
		 * device driver is on the current timekeeping interval.
		 */
		now = tk_clock_read(&tk->tkr_mono);
		interval_start = tk->tkr_mono.cycle_last;
		if (!cycle_between(interval_start, cycles, now)) {
			clock_was_set_seq = tk->clock_was_set_seq;
			cs_was_changed_seq = tk->cs_was_changed_seq;
			cycles = interval_start;
			do_interp = true;
		} else {
			do_interp = false;
		}

		base_real = ktime_add(tk->tkr_mono.base,
				      tk_core.timekeeper.offs_real);
		base_raw = tk->tkr_raw.base;

		nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono,
						     system_counterval.cycles);
		nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw,
						    system_counterval.cycles);
	} while (read_seqcount_retry(&tk_core.seq, seq));

	xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real);
	xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw);

	/*
	 * Interpolate if necessary, adjusting back from the start of the
	 * current interval
	 */
	if (do_interp) {
		u64 partial_history_cycles, total_history_cycles;
		bool discontinuity;

		/*
		 * Check that the counter value occurs after the provided
		 * history reference and that the history doesn't cross a
		 * clocksource change
		 */
		if (!history_begin ||
		    !cycle_between(history_begin->cycles,
				   system_counterval.cycles, cycles) ||
		    history_begin->cs_was_changed_seq != cs_was_changed_seq)
			return -EINVAL;
		partial_history_cycles = cycles - system_counterval.cycles;
		total_history_cycles = cycles - history_begin->cycles;
		discontinuity =
			history_begin->clock_was_set_seq != clock_was_set_seq;

		ret = adjust_historical_crosststamp(history_begin,
						    partial_history_cycles,
						    total_history_cycles,
						    discontinuity, xtstamp);
		if (ret)
			return ret;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(get_device_system_crosststamp);

/**
 * do_gettimeofday - Returns the time of day in a timeval
 * @tv:		pointer to the timeval to be set
 *
 * NOTE: Users should be converted to using getnstimeofday()
 */
void do_gettimeofday(struct timeval *tv)
{
	struct timespec64 now;

	getnstimeofday64(&now);
	tv->tv_sec = now.tv_sec;
	tv->tv_usec = now.tv_nsec/1000;
}
EXPORT_SYMBOL(do_gettimeofday);

/**
 * do_settimeofday64 - Sets the time of day.
 * @ts:     pointer to the timespec64 variable containing the new time
 *
 * Sets the time of day to the new time and update NTP and notify hrtimers
 */
int do_settimeofday64(const struct timespec64 *ts)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	struct timespec64 ts_delta, xt;
	unsigned long flags;
	int ret = 0;

	if (!timespec64_valid_strict(ts))
		return -EINVAL;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	timekeeping_forward_now(tk);

	xt = tk_xtime(tk);
	ts_delta.tv_sec = ts->tv_sec - xt.tv_sec;
	ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec;

	if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) {
		ret = -EINVAL;
		goto out;
	}

	tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta));

	tk_set_xtime(tk, ts);
out:
	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);

	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	/* signal hrtimers about time change */
	clock_was_set();

	return ret;
}
EXPORT_SYMBOL(do_settimeofday64);

/**
 * timekeeping_inject_offset - Adds or subtracts from the current time.
 * @tv:		pointer to the timespec variable containing the offset
 *
 * Adds or subtracts an offset value from the current time.
 */
int timekeeping_inject_offset(struct timespec *ts)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long flags;
	struct timespec64 ts64, tmp;
	int ret = 0;

	if (!timespec_inject_offset_valid(ts))
		return -EINVAL;

	ts64 = timespec_to_timespec64(*ts);

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	timekeeping_forward_now(tk);

	/* Make sure the proposed value is valid */
	tmp = timespec64_add(tk_xtime(tk),  ts64);
	if (timespec64_compare(&tk->wall_to_monotonic, &ts64) > 0 ||
	    !timespec64_valid_strict(&tmp)) {
		ret = -EINVAL;
		goto error;
	}

	tk_xtime_add(tk, &ts64);
	tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts64));

error: /* even if we error out, we forwarded the time, so call update */
	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);

	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	/* signal hrtimers about time change */
	clock_was_set();

	return ret;
}
EXPORT_SYMBOL(timekeeping_inject_offset);

/**
 * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic
 *
 */
static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
{
	tk->tai_offset = tai_offset;
	tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0));
}

/**
 * change_clocksource - Swaps clocksources if a new one is available
 *
 * Accumulates current time interval and initializes new clocksource
 */
static int change_clocksource(void *data)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	struct clocksource *new, *old;
	unsigned long flags;

	new = (struct clocksource *) data;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	timekeeping_forward_now(tk);
	/*
	 * If the cs is in module, get a module reference. Succeeds
	 * for built-in code (owner == NULL) as well.
	 */
	if (try_module_get(new->owner)) {
		if (!new->enable || new->enable(new) == 0) {
			old = tk->tkr_mono.clock;
			tk_setup_internals(tk, new);
			if (old->disable)
				old->disable(old);
			module_put(old->owner);
		} else {
			module_put(new->owner);
		}
	}
	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);

	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	return 0;
}

/**
 * timekeeping_notify - Install a new clock source
 * @clock:		pointer to the clock source
 *
 * This function is called from clocksource.c after a new, better clock
 * source has been registered. The caller holds the clocksource_mutex.
 */
int timekeeping_notify(struct clocksource *clock)
{
	struct timekeeper *tk = &tk_core.timekeeper;

	if (tk->tkr_mono.clock == clock)
		return 0;
	stop_machine(change_clocksource, clock, NULL);
	tick_clock_notify();
	return tk->tkr_mono.clock == clock ? 0 : -1;
}

/**
 * getrawmonotonic64 - Returns the raw monotonic time in a timespec
 * @ts:		pointer to the timespec64 to be set
 *
 * Returns the raw monotonic time (completely un-modified by ntp)
 */
void getrawmonotonic64(struct timespec64 *ts)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long seq;
	u64 nsecs;

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		ts->tv_sec = tk->raw_sec;
		nsecs = timekeeping_get_ns(&tk->tkr_raw);

	} while (read_seqcount_retry(&tk_core.seq, seq));

	ts->tv_nsec = 0;
	timespec64_add_ns(ts, nsecs);
}
EXPORT_SYMBOL(getrawmonotonic64);


/**
 * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres
 */
int timekeeping_valid_for_hres(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long seq;
	int ret;

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;

	} while (read_seqcount_retry(&tk_core.seq, seq));

	return ret;
}

/**
 * timekeeping_max_deferment - Returns max time the clocksource can be deferred
 */
u64 timekeeping_max_deferment(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long seq;
	u64 ret;

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		ret = tk->tkr_mono.clock->max_idle_ns;

	} while (read_seqcount_retry(&tk_core.seq, seq));

	return ret;
}

/**
 * read_persistent_clock -  Return time from the persistent clock.
 *
 * Weak dummy function for arches that do not yet support it.
 * Reads the time from the battery backed persistent clock.
 * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported.
 *
 *  XXX - Do be sure to remove it once all arches implement it.
 */
void __weak read_persistent_clock(struct timespec *ts)
{
	ts->tv_sec = 0;
	ts->tv_nsec = 0;
}

void __weak read_persistent_clock64(struct timespec64 *ts64)
{
	struct timespec ts;

	read_persistent_clock(&ts);
	*ts64 = timespec_to_timespec64(ts);
}

/**
 * read_boot_clock64 -  Return time of the system start.
 *
 * Weak dummy function for arches that do not yet support it.
 * Function to read the exact time the system has been started.
 * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported.
 *
 *  XXX - Do be sure to remove it once all arches implement it.
 */
void __weak read_boot_clock64(struct timespec64 *ts)
{
	ts->tv_sec = 0;
	ts->tv_nsec = 0;
}

/* Flag for if timekeeping_resume() has injected sleeptime */
static bool sleeptime_injected;

/* Flag for if there is a persistent clock on this platform */
static bool persistent_clock_exists;

/*
 * timekeeping_init - Initializes the clocksource and common timekeeping values
 */
void __init timekeeping_init(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	struct clocksource *clock;
	unsigned long flags;
	struct timespec64 now, boot, tmp;

	read_persistent_clock64(&now);
	if (!timespec64_valid_strict(&now)) {
		pr_warn("WARNING: Persistent clock returned invalid value!\n"
			"         Check your CMOS/BIOS settings.\n");
		now.tv_sec = 0;
		now.tv_nsec = 0;
	} else if (now.tv_sec || now.tv_nsec)
		persistent_clock_exists = true;

	read_boot_clock64(&boot);
	if (!timespec64_valid_strict(&boot)) {
		pr_warn("WARNING: Boot clock returned invalid value!\n"
			"         Check your CMOS/BIOS settings.\n");
		boot.tv_sec = 0;
		boot.tv_nsec = 0;
	}

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);
	ntp_init();

	clock = clocksource_default_clock();
	if (clock->enable)
		clock->enable(clock);
	tk_setup_internals(tk, clock);

	tk_set_xtime(tk, &now);
	tk->raw_sec = 0;
	if (boot.tv_sec == 0 && boot.tv_nsec == 0)
		boot = tk_xtime(tk);

	set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec);
	tk_set_wall_to_mono(tk, tmp);

	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);

	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
}

/* time in seconds when suspend began for persistent clock */
static struct timespec64 timekeeping_suspend_time;

/**
 * __timekeeping_inject_sleeptime - Internal function to add sleep interval
 * @delta: pointer to a timespec delta value
 *
 * Takes a timespec offset measuring a suspend interval and properly
 * adds the sleep offset to the timekeeping variables.
 */
static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
					   struct timespec64 *delta)
{
	if (!timespec64_valid_strict(delta)) {
		printk_deferred(KERN_WARNING
				"__timekeeping_inject_sleeptime: Invalid "
				"sleep delta value!\n");
		return;
	}
	tk_xtime_add(tk, delta);
	tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta));
	tk_update_sleep_time(tk, timespec64_to_ktime(*delta));
	tk_debug_account_sleep_time(delta);
}

#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE)
/**
 * We have three kinds of time sources to use for sleep time
 * injection, the preference order is:
 * 1) non-stop clocksource
 * 2) persistent clock (ie: RTC accessible when irqs are off)
 * 3) RTC
 *
 * 1) and 2) are used by timekeeping, 3) by RTC subsystem.
 * If system has neither 1) nor 2), 3) will be used finally.
 *
 *
 * If timekeeping has injected sleeptime via either 1) or 2),
 * 3) becomes needless, so in this case we don't need to call
 * rtc_resume(), and this is what timekeeping_rtc_skipresume()
 * means.
 */
bool timekeeping_rtc_skipresume(void)
{
	return sleeptime_injected;
}

/**
 * 1) can be determined whether to use or not only when doing
 * timekeeping_resume() which is invoked after rtc_suspend(),
 * so we can't skip rtc_suspend() surely if system has 1).
 *
 * But if system has 2), 2) will definitely be used, so in this
 * case we don't need to call rtc_suspend(), and this is what
 * timekeeping_rtc_skipsuspend() means.
 */
bool timekeeping_rtc_skipsuspend(void)
{
	return persistent_clock_exists;
}

/**
 * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values
 * @delta: pointer to a timespec64 delta value
 *
 * This hook is for architectures that cannot support read_persistent_clock64
 * because their RTC/persistent clock is only accessible when irqs are enabled.
 * and also don't have an effective nonstop clocksource.
 *
 * This function should only be called by rtc_resume(), and allows
 * a suspend offset to be injected into the timekeeping values.
 */
void timekeeping_inject_sleeptime64(struct timespec64 *delta)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long flags;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	timekeeping_forward_now(tk);

	__timekeeping_inject_sleeptime(tk, delta);

	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);

	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	/* signal hrtimers about time change */
	clock_was_set();
}
#endif

/**
 * timekeeping_resume - Resumes the generic timekeeping subsystem.
 */
void timekeeping_resume(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	struct clocksource *clock = tk->tkr_mono.clock;
	unsigned long flags;
	struct timespec64 ts_new, ts_delta;
	u64 cycle_now;

	sleeptime_injected = false;
	read_persistent_clock64(&ts_new);

	clockevents_resume();
	clocksource_resume();

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	/*
	 * After system resumes, we need to calculate the suspended time and
	 * compensate it for the OS time. There are 3 sources that could be
	 * used: Nonstop clocksource during suspend, persistent clock and rtc
	 * device.
	 *
	 * One specific platform may have 1 or 2 or all of them, and the
	 * preference will be:
	 *	suspend-nonstop clocksource -> persistent clock -> rtc
	 * The less preferred source will only be tried if there is no better
	 * usable source. The rtc part is handled separately in rtc core code.
	 */
	cycle_now = tk_clock_read(&tk->tkr_mono);
	if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
		cycle_now > tk->tkr_mono.cycle_last) {
		u64 nsec, cyc_delta;

		cyc_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last,
					      tk->tkr_mono.mask);
		nsec = mul_u64_u32_shr(cyc_delta, clock->mult, clock->shift);
		ts_delta = ns_to_timespec64(nsec);
		sleeptime_injected = true;
	} else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) {
		ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time);
		sleeptime_injected = true;
	}

	if (sleeptime_injected)
		__timekeeping_inject_sleeptime(tk, &ts_delta);

	/* Re-base the last cycle value */
	tk->tkr_mono.cycle_last = cycle_now;
	tk->tkr_raw.cycle_last  = cycle_now;

	tk->ntp_error = 0;
	timekeeping_suspended = 0;
	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	touch_softlockup_watchdog();

	tick_resume();
	hrtimers_resume();
}

int timekeeping_suspend(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long flags;
	struct timespec64		delta, delta_delta;
	static struct timespec64	old_delta;

	read_persistent_clock64(&timekeeping_suspend_time);

	/*
	 * On some systems the persistent_clock can not be detected at
	 * timekeeping_init by its return value, so if we see a valid
	 * value returned, update the persistent_clock_exists flag.
	 */
	if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
		persistent_clock_exists = true;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);
	timekeeping_forward_now(tk);
	timekeeping_suspended = 1;

	if (persistent_clock_exists) {
		/*
		 * To avoid drift caused by repeated suspend/resumes,
		 * which each can add ~1 second drift error,
		 * try to compensate so the difference in system time
		 * and persistent_clock time stays close to constant.
		 */
		delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time);
		delta_delta = timespec64_sub(delta, old_delta);
		if (abs(delta_delta.tv_sec) >= 2) {
			/*
			 * if delta_delta is too large, assume time correction
			 * has occurred and set old_delta to the current delta.
			 */
			old_delta = delta;
		} else {
			/* Otherwise try to adjust old_system to compensate */
			timekeeping_suspend_time =
				timespec64_add(timekeeping_suspend_time, delta_delta);
		}
	}

	timekeeping_update(tk, TK_MIRROR);
	halt_fast_timekeeper(tk);
	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	tick_suspend();
	clocksource_suspend();
	clockevents_suspend();

	return 0;
}

/* sysfs resume/suspend bits for timekeeping */
static struct syscore_ops timekeeping_syscore_ops = {
	.resume		= timekeeping_resume,
	.suspend	= timekeeping_suspend,
};

static int __init timekeeping_init_ops(void)
{
	register_syscore_ops(&timekeeping_syscore_ops);
	return 0;
}
device_initcall(timekeeping_init_ops);

/*
 * Apply a multiplier adjustment to the timekeeper
 */
static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk,
							 s64 offset,
							 bool negative,
							 int adj_scale)
{
	s64 interval = tk->cycle_interval;
	s32 mult_adj = 1;

	if (negative) {
		mult_adj = -mult_adj;
		interval = -interval;
		offset  = -offset;
	}
	mult_adj <<= adj_scale;
	interval <<= adj_scale;
	offset <<= adj_scale;

	/*
	 * So the following can be confusing.
	 *
	 * To keep things simple, lets assume mult_adj == 1 for now.
	 *
	 * When mult_adj != 1, remember that the interval and offset values
	 * have been appropriately scaled so the math is the same.
	 *
	 * The basic idea here is that we're increasing the multiplier
	 * by one, this causes the xtime_interval to be incremented by
	 * one cycle_interval. This is because:
	 *	xtime_interval = cycle_interval * mult
	 * So if mult is being incremented by one:
	 *	xtime_interval = cycle_interval * (mult + 1)
	 * Its the same as:
	 *	xtime_interval = (cycle_interval * mult) + cycle_interval
	 * Which can be shortened to:
	 *	xtime_interval += cycle_interval
	 *
	 * So offset stores the non-accumulated cycles. Thus the current
	 * time (in shifted nanoseconds) is:
	 *	now = (offset * adj) + xtime_nsec
	 * Now, even though we're adjusting the clock frequency, we have
	 * to keep time consistent. In other words, we can't jump back
	 * in time, and we also want to avoid jumping forward in time.
	 *
	 * So given the same offset value, we need the time to be the same
	 * both before and after the freq adjustment.
	 *	now = (offset * adj_1) + xtime_nsec_1
	 *	now = (offset * adj_2) + xtime_nsec_2
	 * So:
	 *	(offset * adj_1) + xtime_nsec_1 =
	 *		(offset * adj_2) + xtime_nsec_2
	 * And we know:
	 *	adj_2 = adj_1 + 1
	 * So:
	 *	(offset * adj_1) + xtime_nsec_1 =
	 *		(offset * (adj_1+1)) + xtime_nsec_2
	 *	(offset * adj_1) + xtime_nsec_1 =
	 *		(offset * adj_1) + offset + xtime_nsec_2
	 * Canceling the sides:
	 *	xtime_nsec_1 = offset + xtime_nsec_2
	 * Which gives us:
	 *	xtime_nsec_2 = xtime_nsec_1 - offset
	 * Which simplfies to:
	 *	xtime_nsec -= offset
	 *
	 * XXX - TODO: Doc ntp_error calculation.
	 */
	if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) {
		/* NTP adjustment caused clocksource mult overflow */
		WARN_ON_ONCE(1);
		return;
	}

	tk->tkr_mono.mult += mult_adj;
	tk->xtime_interval += interval;
	tk->tkr_mono.xtime_nsec -= offset;
	tk->ntp_error -= (interval - offset) << tk->ntp_error_shift;
}

/*
 * Calculate the multiplier adjustment needed to match the frequency
 * specified by NTP
 */
static __always_inline void timekeeping_freqadjust(struct timekeeper *tk,
							s64 offset)
{
	s64 interval = tk->cycle_interval;
	s64 xinterval = tk->xtime_interval;
	u32 base = tk->tkr_mono.clock->mult;
	u32 max = tk->tkr_mono.clock->maxadj;
	u32 cur_adj = tk->tkr_mono.mult;
	s64 tick_error;
	bool negative;
	u32 adj_scale;

	/* Remove any current error adj from freq calculation */
	if (tk->ntp_err_mult)
		xinterval -= tk->cycle_interval;

	tk->ntp_tick = ntp_tick_length();

	/* Calculate current error per tick */
	tick_error = ntp_tick_length() >> tk->ntp_error_shift;
	tick_error -= (xinterval + tk->xtime_remainder);

	/* Don't worry about correcting it if its small */
	if (likely((tick_error >= 0) && (tick_error <= interval)))
		return;

	/* preserve the direction of correction */
	negative = (tick_error < 0);

	/* If any adjustment would pass the max, just return */
	if (negative && (cur_adj - 1) <= (base - max))
		return;
	if (!negative && (cur_adj + 1) >= (base + max))
		return;
	/*
	 * Sort out the magnitude of the correction, but
	 * avoid making so large a correction that we go
	 * over the max adjustment.
	 */
	adj_scale = 0;
	tick_error = abs(tick_error);
	while (tick_error > interval) {
		u32 adj = 1 << (adj_scale + 1);

		/* Check if adjustment gets us within 1 unit from the max */
		if (negative && (cur_adj - adj) <= (base - max))
			break;
		if (!negative && (cur_adj + adj) >= (base + max))
			break;

		adj_scale++;
		tick_error >>= 1;
	}

	/* scale the corrections */
	timekeeping_apply_adjustment(tk, offset, negative, adj_scale);
}

/*
 * Adjust the timekeeper's multiplier to the correct frequency
 * and also to reduce the accumulated error value.
 */
static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
{
	/* Correct for the current frequency error */
	timekeeping_freqadjust(tk, offset);

	/* Next make a small adjustment to fix any cumulative error */
	if (!tk->ntp_err_mult && (tk->ntp_error > 0)) {
		tk->ntp_err_mult = 1;
		timekeeping_apply_adjustment(tk, offset, 0, 0);
	} else if (tk->ntp_err_mult && (tk->ntp_error <= 0)) {
		/* Undo any existing error adjustment */
		timekeeping_apply_adjustment(tk, offset, 1, 0);
		tk->ntp_err_mult = 0;
	}

	if (unlikely(tk->tkr_mono.clock->maxadj &&
		(abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult)
			> tk->tkr_mono.clock->maxadj))) {
		printk_once(KERN_WARNING
			"Adjusting %s more than 11%% (%ld vs %ld)\n",
			tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult,
			(long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj);
	}

	/*
	 * It may be possible that when we entered this function, xtime_nsec
	 * was very small.  Further, if we're slightly speeding the clocksource
	 * in the code above, its possible the required corrective factor to
	 * xtime_nsec could cause it to underflow.
	 *
	 * Now, since we already accumulated the second, cannot simply roll
	 * the accumulated second back, since the NTP subsystem has been
	 * notified via second_overflow. So instead we push xtime_nsec forward
	 * by the amount we underflowed, and add that amount into the error.
	 *
	 * We'll correct this error next time through this function, when
	 * xtime_nsec is not as small.
	 */
	if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) {
		s64 neg = -(s64)tk->tkr_mono.xtime_nsec;
		tk->tkr_mono.xtime_nsec = 0;
		tk->ntp_error += neg << tk->ntp_error_shift;
	}
}

/**
 * accumulate_nsecs_to_secs - Accumulates nsecs into secs
 *
 * Helper function that accumulates the nsecs greater than a second
 * from the xtime_nsec field to the xtime_secs field.
 * It also calls into the NTP code to handle leapsecond processing.
 *
 */
static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
{
	u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift;
	unsigned int clock_set = 0;

	while (tk->tkr_mono.xtime_nsec >= nsecps) {
		int leap;

		tk->tkr_mono.xtime_nsec -= nsecps;
		tk->xtime_sec++;

		/* Figure out if its a leap sec and apply if needed */
		leap = second_overflow(tk->xtime_sec);
		if (unlikely(leap)) {
			struct timespec64 ts;

			tk->xtime_sec += leap;

			ts.tv_sec = leap;
			ts.tv_nsec = 0;
			tk_set_wall_to_mono(tk,
				timespec64_sub(tk->wall_to_monotonic, ts));

			__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);

			clock_set = TK_CLOCK_WAS_SET;
		}
	}
	return clock_set;
}

/**
 * logarithmic_accumulation - shifted accumulation of cycles
 *
 * This functions accumulates a shifted interval of cycles into
 * into a shifted interval nanoseconds. Allows for O(log) accumulation
 * loop.
 *
 * Returns the unconsumed cycles.
 */
static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset,
				    u32 shift, unsigned int *clock_set)
{
	u64 interval = tk->cycle_interval << shift;
	u64 snsec_per_sec;

	/* If the offset is smaller than a shifted interval, do nothing */
	if (offset < interval)
		return offset;

	/* Accumulate one shifted interval */
	offset -= interval;
	tk->tkr_mono.cycle_last += interval;
	tk->tkr_raw.cycle_last  += interval;

	tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift;
	*clock_set |= accumulate_nsecs_to_secs(tk);

	/* Accumulate raw time */
	tk->tkr_raw.xtime_nsec += tk->raw_interval << shift;
	snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift;
	while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) {
		tk->tkr_raw.xtime_nsec -= snsec_per_sec;
		tk->raw_sec++;
	}

	/* Accumulate error between NTP and clock interval */
	tk->ntp_error += tk->ntp_tick << shift;
	tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) <<
						(tk->ntp_error_shift + shift);

	return offset;
}

/**
 * update_wall_time - Uses the current clocksource to increment the wall time
 *
 */
void update_wall_time(void)
{
	struct timekeeper *real_tk = &tk_core.timekeeper;
	struct timekeeper *tk = &shadow_timekeeper;
	u64 offset;
	int shift = 0, maxshift;
	unsigned int clock_set = 0;
	unsigned long flags;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);

	/* Make sure we're fully resumed: */
	if (unlikely(timekeeping_suspended))
		goto out;

#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
	offset = real_tk->cycle_interval;
#else
	offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
#endif

	/* Check if there's really nothing to do */
	if (offset < real_tk->cycle_interval)
		goto out;

	/* Do some additional sanity checking */
	timekeeping_check_update(tk, offset);

	/*
	 * With NO_HZ we may have to accumulate many cycle_intervals
	 * (think "ticks") worth of time at once. To do this efficiently,
	 * we calculate the largest doubling multiple of cycle_intervals
	 * that is smaller than the offset.  We then accumulate that
	 * chunk in one go, and then try to consume the next smaller
	 * doubled multiple.
	 */
	shift = ilog2(offset) - ilog2(tk->cycle_interval);
	shift = max(0, shift);
	/* Bound shift to one less than what overflows tick_length */
	maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
	shift = min(shift, maxshift);
	while (offset >= tk->cycle_interval) {
		offset = logarithmic_accumulation(tk, offset, shift,
							&clock_set);
		if (offset < tk->cycle_interval<<shift)
			shift--;
	}

	/* correct the clock when NTP error is too big */
	timekeeping_adjust(tk, offset);

	/*
	 * XXX This can be killed once everyone converts
	 * to the new update_vsyscall.
	 */
	old_vsyscall_fixup(tk);

	/*
	 * Finally, make sure that after the rounding
	 * xtime_nsec isn't larger than NSEC_PER_SEC
	 */
	clock_set |= accumulate_nsecs_to_secs(tk);

	write_seqcount_begin(&tk_core.seq);
	/*
	 * Update the real timekeeper.
	 *
	 * We could avoid this memcpy by switching pointers, but that
	 * requires changes to all other timekeeper usage sites as
	 * well, i.e. move the timekeeper pointer getter into the
	 * spinlocked/seqcount protected sections. And we trade this
	 * memcpy under the tk_core.seq against one before we start
	 * updating.
	 */
	timekeeping_update(tk, clock_set);
	memcpy(real_tk, tk, sizeof(*tk));
	/* The memcpy must come last. Do not put anything here! */
	write_seqcount_end(&tk_core.seq);
out:
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
	if (clock_set)
		/* Have to call _delayed version, since in irq context*/
		clock_was_set_delayed();
}

/**
 * getboottime64 - Return the real time of system boot.
 * @ts:		pointer to the timespec64 to be set
 *
 * Returns the wall-time of boot in a timespec64.
 *
 * This is based on the wall_to_monotonic offset and the total suspend
 * time. Calls to settimeofday will affect the value returned (which
 * basically means that however wrong your real time clock is at boot time,
 * you get the right time here).
 */
void getboottime64(struct timespec64 *ts)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot);

	*ts = ktime_to_timespec64(t);
}
EXPORT_SYMBOL_GPL(getboottime64);

unsigned long get_seconds(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;

	return tk->xtime_sec;
}
EXPORT_SYMBOL(get_seconds);

struct timespec __current_kernel_time(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;

	return timespec64_to_timespec(tk_xtime(tk));
}

struct timespec64 current_kernel_time64(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	struct timespec64 now;
	unsigned long seq;

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		now = tk_xtime(tk);
	} while (read_seqcount_retry(&tk_core.seq, seq));

	return now;
}
EXPORT_SYMBOL(current_kernel_time64);

struct timespec64 get_monotonic_coarse64(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	struct timespec64 now, mono;
	unsigned long seq;

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		now = tk_xtime(tk);
		mono = tk->wall_to_monotonic;
	} while (read_seqcount_retry(&tk_core.seq, seq));

	set_normalized_timespec64(&now, now.tv_sec + mono.tv_sec,
				now.tv_nsec + mono.tv_nsec);

	return now;
}
EXPORT_SYMBOL(get_monotonic_coarse64);

/*
 * Must hold jiffies_lock
 */
void do_timer(unsigned long ticks)
{
	jiffies_64 += ticks;
	calc_global_load(ticks);
}

/**
 * ktime_get_update_offsets_now - hrtimer helper
 * @cwsseq:	pointer to check and store the clock was set sequence number
 * @offs_real:	pointer to storage for monotonic -> realtime offset
 * @offs_boot:	pointer to storage for monotonic -> boottime offset
 * @offs_tai:	pointer to storage for monotonic -> clock tai offset
 *
 * Returns current monotonic time and updates the offsets if the
 * sequence number in @cwsseq and timekeeper.clock_was_set_seq are
 * different.
 *
 * Called from hrtimer_interrupt() or retrigger_next_event()
 */
ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
				     ktime_t *offs_boot, ktime_t *offs_tai)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned int seq;
	ktime_t base;
	u64 nsecs;

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		base = tk->tkr_mono.base;
		nsecs = timekeeping_get_ns(&tk->tkr_mono);
		base = ktime_add_ns(base, nsecs);

		if (*cwsseq != tk->clock_was_set_seq) {
			*cwsseq = tk->clock_was_set_seq;
			*offs_real = tk->offs_real;
			*offs_boot = tk->offs_boot;
			*offs_tai = tk->offs_tai;
		}

		/* Handle leapsecond insertion adjustments */
		if (unlikely(base >= tk->next_leap_ktime))
			*offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0));

	} while (read_seqcount_retry(&tk_core.seq, seq));

	return base;
}

/**
 * do_adjtimex() - Accessor function to NTP __do_adjtimex function
 */
int do_adjtimex(struct timex *txc)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long flags;
	struct timespec64 ts;
	s32 orig_tai, tai;
	int ret;

	/* Validate the data before disabling interrupts */
	ret = ntp_validate_timex(txc);
	if (ret)
		return ret;

	if (txc->modes & ADJ_SETOFFSET) {
		struct timespec delta;
		delta.tv_sec  = txc->time.tv_sec;
		delta.tv_nsec = txc->time.tv_usec;
		if (!(txc->modes & ADJ_NANO))
			delta.tv_nsec *= 1000;
		ret = timekeeping_inject_offset(&delta);
		if (ret)
			return ret;
	}

	getnstimeofday64(&ts);

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	orig_tai = tai = tk->tai_offset;
	ret = __do_adjtimex(txc, &ts, &tai);

	if (tai != orig_tai) {
		__timekeeping_set_tai_offset(tk, tai);
		timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
	}
	tk_update_leap_state(tk);

	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	if (tai != orig_tai)
		clock_was_set();

	ntp_notify_cmos_timer();

	return ret;
}

#ifdef CONFIG_NTP_PPS
/**
 * hardpps() - Accessor function to NTP __hardpps function
 */
void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	__hardpps(phase_ts, raw_ts);

	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
}
EXPORT_SYMBOL(hardpps);
#endif /* CONFIG_NTP_PPS */

/**
 * xtime_update() - advances the timekeeping infrastructure
 * @ticks:	number of ticks, that have elapsed since the last call.
 *
 * Must be called with interrupts disabled.
 */
void xtime_update(unsigned long ticks)
{
	write_seqlock(&jiffies_lock);
	do_timer(ticks);
	write_sequnlock(&jiffies_lock);
	update_wall_time();
}