/* * drivers/acpi/resource.c - ACPI device resources interpretation. * * Copyright (C) 2012, Intel Corp. * Author: Rafael J. Wysocki * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as published * by the Free Software Foundation. * * 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. * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ #include #include #include #include #include #include #ifdef CONFIG_X86 #define valid_IRQ(i) (((i) != 0) && ((i) != 2)) static inline bool acpi_iospace_resource_valid(struct resource *res) { /* On X86 IO space is limited to the [0 - 64K] IO port range */ return res->end < 0x10003; } #else #define valid_IRQ(i) (true) /* * ACPI IO descriptors on arches other than X86 contain MMIO CPU physical * addresses mapping IO space in CPU physical address space, IO space * resources can be placed anywhere in the 64-bit physical address space. */ static inline bool acpi_iospace_resource_valid(struct resource *res) { return true; } #endif static bool acpi_dev_resource_len_valid(u64 start, u64 end, u64 len, bool io) { u64 reslen = end - start + 1; /* * CHECKME: len might be required to check versus a minimum * length as well. 1 for io is fine, but for memory it does * not make any sense at all. * Note: some BIOSes report incorrect length for ACPI address space * descriptor, so remove check of 'reslen == len' to avoid regression. */ if (len && reslen && start <= end) return true; pr_debug("ACPI: invalid or unassigned resource %s [%016llx - %016llx] length [%016llx]\n", io ? "io" : "mem", start, end, len); return false; } static void acpi_dev_memresource_flags(struct resource *res, u64 len, u8 write_protect) { res->flags = IORESOURCE_MEM; if (!acpi_dev_resource_len_valid(res->start, res->end, len, false)) res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET; if (write_protect == ACPI_READ_WRITE_MEMORY) res->flags |= IORESOURCE_MEM_WRITEABLE; } static void acpi_dev_get_memresource(struct resource *res, u64 start, u64 len, u8 write_protect) { res->start = start; res->end = start + len - 1; acpi_dev_memresource_flags(res, len, write_protect); } /** * acpi_dev_resource_memory - Extract ACPI memory resource information. * @ares: Input ACPI resource object. * @res: Output generic resource object. * * Check if the given ACPI resource object represents a memory resource and * if that's the case, use the information in it to populate the generic * resource object pointed to by @res. * * Return: * 1) false with res->flags setting to zero: not the expected resource type * 2) false with IORESOURCE_DISABLED in res->flags: valid unassigned resource * 3) true: valid assigned resource */ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res) { struct acpi_resource_memory24 *memory24; struct acpi_resource_memory32 *memory32; struct acpi_resource_fixed_memory32 *fixed_memory32; switch (ares->type) { case ACPI_RESOURCE_TYPE_MEMORY24: memory24 = &ares->data.memory24; acpi_dev_get_memresource(res, memory24->minimum << 8, memory24->address_length << 8, memory24->write_protect); break; case ACPI_RESOURCE_TYPE_MEMORY32: memory32 = &ares->data.memory32; acpi_dev_get_memresource(res, memory32->minimum, memory32->address_length, memory32->write_protect); break; case ACPI_RESOURCE_TYPE_FIXED_MEMORY32: fixed_memory32 = &ares->data.fixed_memory32; acpi_dev_get_memresource(res, fixed_memory32->address, fixed_memory32->address_length, fixed_memory32->write_protect); break; default: res->flags = 0; return false; } return !(res->flags & IORESOURCE_DISABLED); } EXPORT_SYMBOL_GPL(acpi_dev_resource_memory); static void acpi_dev_ioresource_flags(struct resource *res, u64 len, u8 io_decode, u8 translation_type) { res->flags = IORESOURCE_IO; if (!acpi_dev_resource_len_valid(res->start, res->end, len, true)) res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET; if (!acpi_iospace_resource_valid(res)) res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET; if (io_decode == ACPI_DECODE_16) res->flags |= IORESOURCE_IO_16BIT_ADDR; if (translation_type == ACPI_SPARSE_TRANSLATION) res->flags |= IORESOURCE_IO_SPARSE; } static void acpi_dev_get_ioresource(struct resource *res, u64 start, u64 len, u8 io_decode) { res->start = start; res->end = start + len - 1; acpi_dev_ioresource_flags(res, len, io_decode, 0); } /** * acpi_dev_resource_io - Extract ACPI I/O resource information. * @ares: Input ACPI resource object. * @res: Output generic resource object. * * Check if the given ACPI resource object represents an I/O resource and * if that's the case, use the information in it to populate the generic * resource object pointed to by @res. * * Return: * 1) false with res->flags setting to zero: not the expected resource type * 2) false with IORESOURCE_DISABLED in res->flags: valid unassigned resource * 3) true: valid assigned resource */ bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res) { struct acpi_resource_io *io; struct acpi_resource_fixed_io *fixed_io; switch (ares->type) { case ACPI_RESOURCE_TYPE_IO: io = &ares->data.io; acpi_dev_get_ioresource(res, io->minimum, io->address_length, io->io_decode); break; case ACPI_RESOURCE_TYPE_FIXED_IO: fixed_io = &ares->data.fixed_io; acpi_dev_get_ioresource(res, fixed_io->address, fixed_io->address_length, ACPI_DECODE_10); break; default: res->flags = 0; return false; } return !(res->flags & IORESOURCE_DISABLED); } EXPORT_SYMBOL_GPL(acpi_dev_resource_io); static bool acpi_decode_space(struct resource_win *win, struct acpi_resource_address *addr, struct acpi_address64_attribute *attr) { u8 iodec = attr->granularity == 0xfff ? ACPI_DECODE_10 : ACPI_DECODE_16; bool wp = addr->info.mem.write_protect; u64 len = attr->address_length; u64 start, end, offset = 0; struct resource *res = &win->res; /* * Filter out invalid descriptor according to ACPI Spec 5.0, section * 6.4.3.5 Address Space Resource Descriptors. */ if ((addr->min_address_fixed != addr->max_address_fixed && len) || (addr->min_address_fixed && addr->max_address_fixed && !len)) pr_debug("ACPI: Invalid address space min_addr_fix %d, max_addr_fix %d, len %llx\n", addr->min_address_fixed, addr->max_address_fixed, len); /* * For bridges that translate addresses across the bridge, * translation_offset is the offset that must be added to the * address on the secondary side to obtain the address on the * primary side. Non-bridge devices must list 0 for all Address * Translation offset bits. */ if (addr->producer_consumer == ACPI_PRODUCER) offset = attr->translation_offset; else if (attr->translation_offset) pr_debug("ACPI: translation_offset(%lld) is invalid for non-bridge device.\n", attr->translation_offset); start = attr->minimum + offset; end = attr->maximum + offset; win->offset = offset; res->start = start; res->end = end; if (sizeof(resource_size_t) < sizeof(u64) && (offset != win->offset || start != res->start || end != res->end)) { pr_warn("acpi resource window ([%#llx-%#llx] ignored, not CPU addressable)\n", attr->minimum, attr->maximum); return false; } switch (addr->resource_type) { case ACPI_MEMORY_RANGE: acpi_dev_memresource_flags(res, len, wp); break; case ACPI_IO_RANGE: acpi_dev_ioresource_flags(res, len, iodec, addr->info.io.translation_type); break; case ACPI_BUS_NUMBER_RANGE: res->flags = IORESOURCE_BUS; break; default: return false; } if (addr->producer_consumer == ACPI_PRODUCER) res->flags |= IORESOURCE_WINDOW; if (addr->info.mem.caching == ACPI_PREFETCHABLE_MEMORY) res->flags |= IORESOURCE_PREFETCH; return !(res->flags & IORESOURCE_DISABLED); } /** * acpi_dev_resource_address_space - Extract ACPI address space information. * @ares: Input ACPI resource object. * @win: Output generic resource object. * * Check if the given ACPI resource object represents an address space resource * and if that's the case, use the information in it to populate the generic * resource object pointed to by @win. * * Return: * 1) false with win->res.flags setting to zero: not the expected resource type * 2) false with IORESOURCE_DISABLED in win->res.flags: valid unassigned * resource * 3) true: valid assigned resource */ bool acpi_dev_resource_address_space(struct acpi_resource *ares, struct resource_win *win) { struct acpi_resource_address64 addr; win->res.flags = 0; if (ACPI_FAILURE(acpi_resource_to_address64(ares, &addr))) return false; return acpi_decode_space(win, (struct acpi_resource_address *)&addr, &addr.address); } EXPORT_SYMBOL_GPL(acpi_dev_resource_address_space); /** * acpi_dev_resource_ext_address_space - Extract ACPI address space information. * @ares: Input ACPI resource object. * @win: Output generic resource object. * * Check if the given ACPI resource object represents an extended address space * resource and if that's the case, use the information in it to populate the * generic resource object pointed to by @win. * * Return: * 1) false with win->res.flags setting to zero: not the expected resource type * 2) false with IORESOURCE_DISABLED in win->res.flags: valid unassigned * resource * 3) true: valid assigned resource */ bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, struct resource_win *win) { struct acpi_resource_extended_address64 *ext_addr; win->res.flags = 0; if (ares->type != ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS64) return false; ext_addr = &ares->data.ext_address64; return acpi_decode_space(win, (struct acpi_resource_address *)ext_addr, &ext_addr->address); } EXPORT_SYMBOL_GPL(acpi_dev_resource_ext_address_space); /** * acpi_dev_irq_flags - Determine IRQ resource flags. * @triggering: Triggering type as provided by ACPI. * @polarity: Interrupt polarity as provided by ACPI. * @shareable: Whether or not the interrupt is shareable. */ unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable) { unsigned long flags; if (triggering == ACPI_LEVEL_SENSITIVE) flags = polarity == ACPI_ACTIVE_LOW ? IORESOURCE_IRQ_LOWLEVEL : IORESOURCE_IRQ_HIGHLEVEL; else flags = polarity == ACPI_ACTIVE_LOW ? IORESOURCE_IRQ_LOWEDGE : IORESOURCE_IRQ_HIGHEDGE; if (shareable == ACPI_SHARED) flags |= IORESOURCE_IRQ_SHAREABLE; return flags | IORESOURCE_IRQ; } EXPORT_SYMBOL_GPL(acpi_dev_irq_flags); /** * acpi_dev_get_irq_type - Determine irq type. * @triggering: Triggering type as provided by ACPI. * @polarity: Interrupt polarity as provided by ACPI. */ unsigned int acpi_dev_get_irq_type(int triggering, int polarity) { switch (polarity) { case ACPI_ACTIVE_LOW: return triggering == ACPI_EDGE_SENSITIVE ? IRQ_TYPE_EDGE_FALLING : IRQ_TYPE_LEVEL_LOW; case ACPI_ACTIVE_HIGH: return triggering == ACPI_EDGE_SENSITIVE ? IRQ_TYPE_EDGE_RISING : IRQ_TYPE_LEVEL_HIGH; case ACPI_ACTIVE_BOTH: if (triggering == ACPI_EDGE_SENSITIVE) return IRQ_TYPE_EDGE_BOTH; default: return IRQ_TYPE_NONE; } } EXPORT_SYMBOL_GPL(acpi_dev_get_irq_type); static void acpi_dev_irqresource_disabled(struct resource *res, u32 gsi) { res->start = gsi; res->end = gsi; res->flags = IORESOURCE_IRQ | IORESOURCE_DISABLED | IORESOURCE_UNSET; } static void acpi_dev_get_irqresource(struct resource *res, u32 gsi, u8 triggering, u8 polarity, u8 shareable, bool legacy) { int irq, p, t; if (!valid_IRQ(gsi)) { acpi_dev_irqresource_disabled(res, gsi); return; } /* * In IO-APIC mode, use overrided attribute. Two reasons: * 1. BIOS bug in DSDT * 2. BIOS uses IO-APIC mode Interrupt Source Override * * We do this only if we are dealing with IRQ() or IRQNoFlags() * resource (the legacy ISA resources). With modern ACPI 5 devices * using extended IRQ descriptors we take the IRQ configuration * from _CRS directly. */ if (legacy && !acpi_get_override_irq(gsi, &t, &p)) { u8 trig = t ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE; u8 pol = p ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH; if (triggering != trig || polarity != pol) { pr_warning("ACPI: IRQ %d override to %s, %s\n", gsi, t ? "level" : "edge", p ? "low" : "high"); triggering = trig; polarity = pol; } } res->flags = acpi_dev_irq_flags(triggering, polarity, shareable); irq = acpi_register_gsi(NULL, gsi, triggering, polarity); if (irq >= 0) { res->start = irq; res->end = irq; } else { acpi_dev_irqresource_disabled(res, gsi); } } /** * acpi_dev_resource_interrupt - Extract ACPI interrupt resource information. * @ares: Input ACPI resource object. * @index: Index into the array of GSIs represented by the resource. * @res: Output generic resource object. * * Check if the given ACPI resource object represents an interrupt resource * and @index does not exceed the resource's interrupt count (true is returned * in that case regardless of the results of the other checks)). If that's the * case, register the GSI corresponding to @index from the array of interrupts * represented by the resource and populate the generic resource object pointed * to by @res accordingly. If the registration of the GSI is not successful, * IORESOURCE_DISABLED will be set it that object's flags. * * Return: * 1) false with res->flags setting to zero: not the expected resource type * 2) false with IORESOURCE_DISABLED in res->flags: valid unassigned resource * 3) true: valid assigned resource */ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res) { struct acpi_resource_irq *irq; struct acpi_resource_extended_irq *ext_irq; switch (ares->type) { case ACPI_RESOURCE_TYPE_IRQ: /* * Per spec, only one interrupt per descriptor is allowed in * _CRS, but some firmware violates this, so parse them all. */ irq = &ares->data.irq; if (index >= irq->interrupt_count) { acpi_dev_irqresource_disabled(res, 0); return false; } acpi_dev_get_irqresource(res, irq->interrupts[index], irq->triggering, irq->polarity, irq->sharable, true); break; case ACPI_RESOURCE_TYPE_EXTENDED_IRQ: ext_irq = &ares->data.extended_irq; if (index >= ext_irq->interrupt_count) { acpi_dev_irqresource_disabled(res, 0); return false; } acpi_dev_get_irqresource(res, ext_irq->interrupts[index], ext_irq->triggering, ext_irq->polarity, ext_irq->sharable, false); break; default: res->flags = 0; return false; } return true; } EXPORT_SYMBOL_GPL(acpi_dev_resource_interrupt); /** * acpi_dev_free_resource_list - Free resource from %acpi_dev_get_resources(). * @list: The head of the resource list to free. */ void acpi_dev_free_resource_list(struct list_head *list) { resource_list_free(list); } EXPORT_SYMBOL_GPL(acpi_dev_free_resource_list); struct res_proc_context { struct list_head *list; int (*preproc)(struct acpi_resource *, void *); void *preproc_data; int count; int error; }; static acpi_status acpi_dev_new_resource_entry(struct resource_win *win, struct res_proc_context *c) { struct resource_entry *rentry; rentry = resource_list_create_entry(NULL, 0); if (!rentry) { c->error = -ENOMEM; return AE_NO_MEMORY; } *rentry->res = win->res; rentry->offset = win->offset; resource_list_add_tail(rentry, c->list); c->count++; return AE_OK; } static acpi_status acpi_dev_process_resource(struct acpi_resource *ares, void *context) { struct res_proc_context *c = context; struct resource_win win; struct resource *res = &win.res; int i; if (c->preproc) { int ret; ret = c->preproc(ares, c->preproc_data); if (ret < 0) { c->error = ret; return AE_CTRL_TERMINATE; } else if (ret > 0) { return AE_OK; } } memset(&win, 0, sizeof(win)); if (acpi_dev_resource_memory(ares, res) || acpi_dev_resource_io(ares, res) || acpi_dev_resource_address_space(ares, &win) || acpi_dev_resource_ext_address_space(ares, &win)) return acpi_dev_new_resource_entry(&win, c); for (i = 0; acpi_dev_resource_interrupt(ares, i, res); i++) { acpi_status status; status = acpi_dev_new_resource_entry(&win, c); if (ACPI_FAILURE(status)) return status; } return AE_OK; } /** * acpi_dev_get_resources - Get current resources of a device. * @adev: ACPI device node to get the resources for. * @list: Head of the resultant list of resources (must be empty). * @preproc: The caller's preprocessing routine. * @preproc_data: Pointer passed to the caller's preprocessing routine. * * Evaluate the _CRS method for the given device node and process its output by * (1) executing the @preproc() rountine provided by the caller, passing the * resource pointer and @preproc_data to it as arguments, for each ACPI resource * returned and (2) converting all of the returned ACPI resources into struct * resource objects if possible. If the return value of @preproc() in step (1) * is different from 0, step (2) is not applied to the given ACPI resource and * if that value is negative, the whole processing is aborted and that value is * returned as the final error code. * * The resultant struct resource objects are put on the list pointed to by * @list, that must be empty initially, as members of struct resource_entry * objects. Callers of this routine should use %acpi_dev_free_resource_list() to * free that list. * * The number of resources in the output list is returned on success, an error * code reflecting the error condition is returned otherwise. */ int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, int (*preproc)(struct acpi_resource *, void *), void *preproc_data) { struct res_proc_context c; acpi_status status; if (!adev || !adev->handle || !list_empty(list)) return -EINVAL; if (!acpi_has_method(adev->handle, METHOD_NAME__CRS)) return 0; c.list = list; c.preproc = preproc; c.preproc_data = preproc_data; c.count = 0; c.error = 0; status = acpi_walk_resources(adev->handle, METHOD_NAME__CRS, acpi_dev_process_resource, &c); if (ACPI_FAILURE(status)) { acpi_dev_free_resource_list(list); return c.error ? c.error : -EIO; } return c.count; } EXPORT_SYMBOL_GPL(acpi_dev_get_resources); /** * acpi_dev_filter_resource_type - Filter ACPI resource according to resource * types * @ares: Input ACPI resource object. * @types: Valid resource types of IORESOURCE_XXX * * This is a helper function to support acpi_dev_get_resources(), which filters * ACPI resource objects according to resource types. */ int acpi_dev_filter_resource_type(struct acpi_resource *ares, unsigned long types) { unsigned long type = 0; switch (ares->type) { case ACPI_RESOURCE_TYPE_MEMORY24: case ACPI_RESOURCE_TYPE_MEMORY32: case ACPI_RESOURCE_TYPE_FIXED_MEMORY32: type = IORESOURCE_MEM; break; case ACPI_RESOURCE_TYPE_IO: case ACPI_RESOURCE_TYPE_FIXED_IO: type = IORESOURCE_IO; break; case ACPI_RESOURCE_TYPE_IRQ: case ACPI_RESOURCE_TYPE_EXTENDED_IRQ: type = IORESOURCE_IRQ; break; case ACPI_RESOURCE_TYPE_DMA: case ACPI_RESOURCE_TYPE_FIXED_DMA: type = IORESOURCE_DMA; break; case ACPI_RESOURCE_TYPE_GENERIC_REGISTER: type = IORESOURCE_REG; break; case ACPI_RESOURCE_TYPE_ADDRESS16: case ACPI_RESOURCE_TYPE_ADDRESS32: case ACPI_RESOURCE_TYPE_ADDRESS64: case ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS64: if (ares->data.address.resource_type == ACPI_MEMORY_RANGE) type = IORESOURCE_MEM; else if (ares->data.address.resource_type == ACPI_IO_RANGE) type = IORESOURCE_IO; else if (ares->data.address.resource_type == ACPI_BUS_NUMBER_RANGE) type = IORESOURCE_BUS; break; default: break; } return (type & types) ? 0 : 1; } EXPORT_SYMBOL_GPL(acpi_dev_filter_resource_type); >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 
#include "builtin.h"
#include "perf.h"

#include "util/evsel.h"
#include "util/evlist.h"
#include "util/util.h"
#include "util/cache.h"
#include "util/symbol.h"
#include "util/thread.h"
#include "util/header.h"
#include "util/session.h"
#include "util/intlist.h"
#include <subcmd/parse-options.h>
#include "util/trace-event.h"
#include "util/debug.h"
#include "util/tool.h"
#include "util/stat.h"
#include "util/top.h"
#include "util/data.h"
#include "util/ordered-events.h"

#include <sys/prctl.h>
#ifdef HAVE_TIMERFD_SUPPORT
#include <sys/timerfd.h>
#endif

#include <termios.h>
#include <semaphore.h>
#include <pthread.h>
#include <math.h>

#ifdef HAVE_KVM_STAT_SUPPORT
#include "util/kvm-stat.h"

void exit_event_get_key(struct perf_evsel *evsel,
			struct perf_sample *sample,
			struct event_key *key)
{
	key->info = 0;
	key->key = perf_evsel__intval(evsel, sample, kvm_exit_reason);
}

bool kvm_exit_event(struct perf_evsel *evsel)
{
	return !strcmp(evsel->name, kvm_exit_trace);
}

bool exit_event_begin(struct perf_evsel *evsel,
		      struct perf_sample *sample, struct event_key *key)
{
	if (kvm_exit_event(evsel)) {
		exit_event_get_key(evsel, sample, key);
		return true;
	}

	return false;
}

bool kvm_entry_event(struct perf_evsel *evsel)
{
	return !strcmp(evsel->name, kvm_entry_trace);
}

bool exit_event_end(struct perf_evsel *evsel,
		    struct perf_sample *sample __maybe_unused,
		    struct event_key *key __maybe_unused)
{
	return kvm_entry_event(evsel);
}

static const char *get_exit_reason(struct perf_kvm_stat *kvm,
				   struct exit_reasons_table *tbl,
				   u64 exit_code)
{
	while (tbl->reason != NULL) {
		if (tbl->exit_code == exit_code)
			return tbl->reason;
		tbl++;
	}

	pr_err("unknown kvm exit code:%lld on %s\n",
		(unsigned long long)exit_code, kvm->exit_reasons_isa);
	return "UNKNOWN";
}

void exit_event_decode_key(struct perf_kvm_stat *kvm,
			   struct event_key *key,
			   char *decode)
{
	const char *exit_reason = get_exit_reason(kvm, key->exit_reasons,
						  key->key);

	scnprintf(decode, decode_str_len, "%s", exit_reason);
}

static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
{
	struct kvm_reg_events_ops *events_ops = kvm_reg_events_ops;

	for (events_ops = kvm_reg_events_ops; events_ops->name; events_ops++) {
		if (!strcmp(events_ops->name, kvm->report_event)) {
			kvm->events_ops = events_ops->ops;
			return true;
		}
	}

	return false;
}

struct vcpu_event_record {
	int vcpu_id;
	u64 start_time;
	struct kvm_event *last_event;
};


static void init_kvm_event_record(struct perf_kvm_stat *kvm)
{
	unsigned int i;

	for (i = 0; i < EVENTS_CACHE_SIZE; i++)
		INIT_LIST_HEAD(&kvm->kvm_events_cache[i]);
}

#ifdef HAVE_TIMERFD_SUPPORT
static void clear_events_cache_stats(struct list_head *kvm_events_cache)
{
	struct list_head *head;
	struct kvm_event *event;
	unsigned int i;
	int j;

	for (i = 0; i < EVENTS_CACHE_SIZE; i++) {
		head = &kvm_events_cache[i];
		list_for_each_entry(event, head, hash_entry) {
			/* reset stats for event */
			event->total.time = 0;
			init_stats(&event->total.stats);

			for (j = 0; j < event->max_vcpu; ++j) {
				event->vcpu[j].time = 0;
				init_stats(&event->vcpu[j].stats);
			}
		}
	}
}
#endif

static int kvm_events_hash_fn(u64 key)
{
	return key & (EVENTS_CACHE_SIZE - 1);
}

static bool kvm_event_expand(struct kvm_event *event, int vcpu_id)
{
	int old_max_vcpu = event->max_vcpu;
	void *prev;

	if (vcpu_id < event->max_vcpu)
		return true;

	while (event->max_vcpu <= vcpu_id)
		event->max_vcpu += DEFAULT_VCPU_NUM;

	prev = event->vcpu;
	event->vcpu = realloc(event->vcpu,
			      event->max_vcpu * sizeof(*event->vcpu));
	if (!event->vcpu) {
		free(prev);
		pr_err("Not enough memory\n");
		return false;
	}

	memset(event->vcpu + old_max_vcpu, 0,
	       (event->max_vcpu - old_max_vcpu) * sizeof(*event->vcpu));
	return true;
}

static struct kvm_event *kvm_alloc_init_event(struct event_key *key)
{
	struct kvm_event *event;

	event = zalloc(sizeof(*event));
	if (!event) {
		pr_err("Not enough memory\n");
		return NULL;
	}

	event->key = *key;
	init_stats(&event->total.stats);
	return event;
}

static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm,
					       struct event_key *key)
{
	struct kvm_event *event;
	struct list_head *head;

	BUG_ON(key->key == INVALID_KEY);

	head = &kvm->kvm_events_cache[kvm_events_hash_fn(key->key)];
	list_for_each_entry(event, head, hash_entry) {
		if (event->key.key == key->key && event->key.info == key->info)
			return event;
	}

	event = kvm_alloc_init_event(key);
	if (!event)
		return NULL;

	list_add(&event->hash_entry, head);
	return event;
}

static bool handle_begin_event(struct perf_kvm_stat *kvm,
			       struct vcpu_event_record *vcpu_record,
			       struct event_key *key, u64 timestamp)
{
	struct kvm_event *event = NULL;

	if (key->key != INVALID_KEY)
		event = find_create_kvm_event(kvm, key);

	vcpu_record->last_event = event;
	vcpu_record->start_time = timestamp;
	return true;
}

static void
kvm_update_event_stats(struct kvm_event_stats *kvm_stats, u64 time_diff)
{
	kvm_stats->time += time_diff;
	update_stats(&kvm_stats->stats, time_diff);
}

static double kvm_event_rel_stddev(int vcpu_id, struct kvm_event *event)
{
	struct kvm_event_stats *kvm_stats = &event->total;

	if (vcpu_id != -1)
		kvm_stats = &event->vcpu[vcpu_id];

	return rel_stddev_stats(stddev_stats(&kvm_stats->stats),
				avg_stats(&kvm_stats->stats));
}

static bool update_kvm_event(struct kvm_event *event, int vcpu_id,
			     u64 time_diff)
{
	if (vcpu_id == -1) {
		kvm_update_event_stats(&event->total, time_diff);
		return true;
	}

	if (!kvm_event_expand(event, vcpu_id))
		return false;

	kvm_update_event_stats(&event->vcpu[vcpu_id], time_diff);
	return true;
}

static bool is_child_event(struct perf_kvm_stat *kvm,
			   struct perf_evsel *evsel,
			   struct perf_sample *sample,
			   struct event_key *key)
{
	struct child_event_ops *child_ops;

	child_ops = kvm->events_ops->child_ops;

	if (!child_ops)
		return false;

	for (; child_ops->name; child_ops++) {
		if (!strcmp(evsel->name, child_ops->name)) {
			child_ops->get_key(evsel, sample, key);
			return true;
		}
	}

	return false;
}

static bool handle_child_event(struct perf_kvm_stat *kvm,
			       struct vcpu_event_record *vcpu_record,
			       struct event_key *key,
			       struct perf_sample *sample __maybe_unused)
{
	struct kvm_event *event = NULL;

	if (key->key != INVALID_KEY)
		event = find_create_kvm_event(kvm, key);

	vcpu_record->last_event = event;

	return true;
}

static bool skip_event(const char *event)
{
	const char * const *skip_events;

	for (skip_events = kvm_skip_events; *skip_events; skip_events++)
		if (!strcmp(event, *skip_events))
			return true;

	return false;
}

static bool handle_end_event(struct perf_kvm_stat *kvm,
			     struct vcpu_event_record *vcpu_record,
			     struct event_key *key,
			     struct perf_sample *sample)
{
	struct kvm_event *event;
	u64 time_begin, time_diff;
	int vcpu;

	if (kvm->trace_vcpu == -1)
		vcpu = -1;
	else
		vcpu = vcpu_record->vcpu_id;

	event = vcpu_record->last_event;
	time_begin = vcpu_record->start_time;

	/* The begin event is not caught. */
	if (!time_begin)
		return true;

	/*
	 * In some case, the 'begin event' only records the start timestamp,
	 * the actual event is recognized in the 'end event' (e.g. mmio-event).
	 */

	/* Both begin and end events did not get the key. */
	if (!event && key->key == INVALID_KEY)
		return true;

	if (!event)
		event = find_create_kvm_event(kvm, key);

	if (!event)
		return false;

	vcpu_record->last_event = NULL;
	vcpu_record->start_time = 0;

	/* seems to happen once in a while during live mode */
	if (sample->time < time_begin) {
		pr_debug("End time before begin time; skipping event.\n");
		return true;
	}

	time_diff = sample->time - time_begin;

	if (kvm->duration && time_diff > kvm->duration) {
		char decode[decode_str_len];

		kvm->events_ops->decode_key(kvm, &event->key, decode);
		if (!skip_event(decode)) {
			pr_info("%" PRIu64 " VM %d, vcpu %d: %s event took %" PRIu64 "usec\n",
				 sample->time, sample->pid, vcpu_record->vcpu_id,
				 decode, time_diff/1000);
		}
	}

	return update_kvm_event(event, vcpu, time_diff);
}

static
struct vcpu_event_record *per_vcpu_record(struct thread *thread,
					  struct perf_evsel *evsel,
					  struct perf_sample *sample)
{
	/* Only kvm_entry records vcpu id. */
	if (!thread__priv(thread) && kvm_entry_event(evsel)) {
		struct vcpu_event_record *vcpu_record;

		vcpu_record = zalloc(sizeof(*vcpu_record));
		if (!vcpu_record) {
			pr_err("%s: Not enough memory\n", __func__);
			return NULL;
		}

		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample,
							  vcpu_id_str);
		thread__set_priv(thread, vcpu_record);
	}

	return thread__priv(thread);
}

static bool handle_kvm_event(struct perf_kvm_stat *kvm,
			     struct thread *thread,
			     struct perf_evsel *evsel,
			     struct perf_sample *sample)
{
	struct vcpu_event_record *vcpu_record;
	struct event_key key = { .key = INVALID_KEY,
				 .exit_reasons = kvm->exit_reasons };

	vcpu_record = per_vcpu_record(thread, evsel, sample);
	if (!vcpu_record)
		return true;

	/* only process events for vcpus user cares about */
	if ((kvm->trace_vcpu != -1) &&
	    (kvm->trace_vcpu != vcpu_record->vcpu_id))
		return true;

	if (kvm->events_ops->is_begin_event(evsel, sample, &key))
		return handle_begin_event(kvm, vcpu_record, &key, sample->time);

	if (is_child_event(kvm, evsel, sample, &key))
		return handle_child_event(kvm, vcpu_record, &key, sample);

	if (kvm->events_ops->is_end_event(evsel, sample, &key))
		return handle_end_event(kvm, vcpu_record, &key, sample);

	return true;
}

#define GET_EVENT_KEY(func, field)					\
static u64 get_event_ ##func(struct kvm_event *event, int vcpu)		\
{									\
	if (vcpu == -1)							\
		return event->total.field;				\
									\
	if (vcpu >= event->max_vcpu)					\
		return 0;						\
									\
	return event->vcpu[vcpu].field;					\
}

#define COMPARE_EVENT_KEY(func, field)					\
GET_EVENT_KEY(func, field)						\
static int compare_kvm_event_ ## func(struct kvm_event *one,		\
					struct kvm_event *two, int vcpu)\
{									\
	return get_event_ ##func(one, vcpu) >				\
				get_event_ ##func(two, vcpu);		\
}

GET_EVENT_KEY(time, time);
COMPARE_EVENT_KEY(count, stats.n);
COMPARE_EVENT_KEY(mean, stats.mean);
GET_EVENT_KEY(max, stats.max);
GET_EVENT_KEY(min, stats.min);

#define DEF_SORT_NAME_KEY(name, compare_key)				\
	{ #name, compare_kvm_event_ ## compare_key }

static struct kvm_event_key keys[] = {
	DEF_SORT_NAME_KEY(sample, count),
	DEF_SORT_NAME_KEY(time, mean),
	{ NULL, NULL }
};

static bool select_key(struct perf_kvm_stat *kvm)
{
	int i;

	for (i = 0; keys[i].name; i++) {
		if (!strcmp(keys[i].name, kvm->sort_key)) {
			kvm->compare = keys[i].key;
			return true;
		}
	}

	pr_err("Unknown compare key:%s\n", kvm->sort_key);
	return false;
}

static void insert_to_result(struct rb_root *result, struct kvm_event *event,
			     key_cmp_fun bigger, int vcpu)
{
	struct rb_node **rb = &result->rb_node;
	struct rb_node *parent = NULL;
	struct kvm_event *p;

	while (*rb) {
		p = container_of(*rb, struct kvm_event, rb);
		parent = *rb;

		if (bigger(event, p, vcpu))
			rb = &(*rb)->rb_left;
		else
			rb = &(*rb)->rb_right;
	}

	rb_link_node(&event->rb, parent, rb);
	rb_insert_color(&event->rb, result);
}

static void
update_total_count(struct perf_kvm_stat *kvm, struct kvm_event *event)
{
	int vcpu = kvm->trace_vcpu;

	kvm->total_count += get_event_count(event, vcpu);
	kvm->total_time += get_event_time(event, vcpu);
}

static bool event_is_valid(struct kvm_event *event, int vcpu)
{
	return !!get_event_count(event, vcpu);
}

static void sort_result(struct perf_kvm_stat *kvm)
{
	unsigned int i;
	int vcpu = kvm->trace_vcpu;
	struct kvm_event *event;

	for (i = 0; i < EVENTS_CACHE_SIZE; i++) {
		list_for_each_entry(event, &kvm->kvm_events_cache[i], hash_entry) {
			if (event_is_valid(event, vcpu)) {
				update_total_count(kvm, event);
				insert_to_result(&kvm->result, event,
						 kvm->compare, vcpu);
			}
		}
	}
}

/* returns left most element of result, and erase it */
static struct kvm_event *pop_from_result(struct rb_root *result)
{
	struct rb_node *node = rb_first(result);

	if (!node)
		return NULL;

	rb_erase(node, result);
	return container_of(node, struct kvm_event, rb);
}

static void print_vcpu_info(struct perf_kvm_stat *kvm)
{
	int vcpu = kvm->trace_vcpu;

	pr_info("Analyze events for ");

	if (kvm->opts.target.system_wide)
		pr_info("all VMs, ");
	else if (kvm->opts.target.pid)
		pr_info("pid(s) %s, ", kvm->opts.target.pid);
	else
		pr_info("dazed and confused on what is monitored, ");

	if (vcpu == -1)
		pr_info("all VCPUs:\n\n");
	else
		pr_info("VCPU %d:\n\n", vcpu);
}

static void show_timeofday(void)
{
	char date[64];
	struct timeval tv;
	struct tm ltime;

	gettimeofday(&tv, NULL);
	if (localtime_r(&tv.tv_sec, &ltime)) {
		strftime(date, sizeof(date), "%H:%M:%S", &ltime);
		pr_info("%s.%06ld", date, tv.tv_usec);
	} else
		pr_info("00:00:00.000000");

	return;
}

static void print_result(struct perf_kvm_stat *kvm)
{
	char decode[decode_str_len];
	struct kvm_event *event;
	int vcpu = kvm->trace_vcpu;

	if (kvm->live) {
		puts(CONSOLE_CLEAR);
		show_timeofday();
	}

	pr_info("\n\n");
	print_vcpu_info(kvm);
	pr_info("%*s ", decode_str_len, kvm->events_ops->name);
	pr_info("%10s ", "Samples");
	pr_info("%9s ", "Samples%");

	pr_info("%9s ", "Time%");
	pr_info("%11s ", "Min Time");
	pr_info("%11s ", "Max Time");
	pr_info("%16s ", "Avg time");
	pr_info("\n\n");

	while ((event = pop_from_result(&kvm->result))) {
		u64 ecount, etime, max, min;

		ecount = get_event_count(event, vcpu);
		etime = get_event_time(event, vcpu);