*/
#include "qemu/osdep.h"
+#include "qemu/units.h"
#include "qemu/cutils.h"
+#include "qemu/bitops.h"
#include "cpu.h"
#include "exec/exec-all.h"
#include "qom/qom-qobject.h"
#include "sysemu/arch_init.h"
-#if defined(CONFIG_KVM)
-#include <linux/kvm_para.h>
-#endif
+#include "standard-headers/asm-x86/kvm_para.h"
#include "sysemu/sysemu.h"
#include "hw/qdev-properties.h"
#include "disas/capstone.h"
+/* Helpers for building CPUID[2] descriptors: */
-/* Cache topology CPUID constants: */
+struct CPUID2CacheDescriptorInfo {
+ enum CacheType type;
+ int level;
+ int size;
+ int line_size;
+ int associativity;
+};
+
+/*
+ * Known CPUID 2 cache descriptors.
+ * From Intel SDM Volume 2A, CPUID instruction
+ */
+struct CPUID2CacheDescriptorInfo cpuid2_cache_descriptors[] = {
+ [0x06] = { .level = 1, .type = INSTRUCTION_CACHE, .size = 8 * KiB,
+ .associativity = 4, .line_size = 32, },
+ [0x08] = { .level = 1, .type = INSTRUCTION_CACHE, .size = 16 * KiB,
+ .associativity = 4, .line_size = 32, },
+ [0x09] = { .level = 1, .type = INSTRUCTION_CACHE, .size = 32 * KiB,
+ .associativity = 4, .line_size = 64, },
+ [0x0A] = { .level = 1, .type = DATA_CACHE, .size = 8 * KiB,
+ .associativity = 2, .line_size = 32, },
+ [0x0C] = { .level = 1, .type = DATA_CACHE, .size = 16 * KiB,
+ .associativity = 4, .line_size = 32, },
+ [0x0D] = { .level = 1, .type = DATA_CACHE, .size = 16 * KiB,
+ .associativity = 4, .line_size = 64, },
+ [0x0E] = { .level = 1, .type = DATA_CACHE, .size = 24 * KiB,
+ .associativity = 6, .line_size = 64, },
+ [0x1D] = { .level = 2, .type = UNIFIED_CACHE, .size = 128 * KiB,
+ .associativity = 2, .line_size = 64, },
+ [0x21] = { .level = 2, .type = UNIFIED_CACHE, .size = 256 * KiB,
+ .associativity = 8, .line_size = 64, },
+ /* lines per sector is not supported cpuid2_cache_descriptor(),
+ * so descriptors 0x22, 0x23 are not included
+ */
+ [0x24] = { .level = 2, .type = UNIFIED_CACHE, .size = 1 * MiB,
+ .associativity = 16, .line_size = 64, },
+ /* lines per sector is not supported cpuid2_cache_descriptor(),
+ * so descriptors 0x25, 0x20 are not included
+ */
+ [0x2C] = { .level = 1, .type = DATA_CACHE, .size = 32 * KiB,
+ .associativity = 8, .line_size = 64, },
+ [0x30] = { .level = 1, .type = INSTRUCTION_CACHE, .size = 32 * KiB,
+ .associativity = 8, .line_size = 64, },
+ [0x41] = { .level = 2, .type = UNIFIED_CACHE, .size = 128 * KiB,
+ .associativity = 4, .line_size = 32, },
+ [0x42] = { .level = 2, .type = UNIFIED_CACHE, .size = 256 * KiB,
+ .associativity = 4, .line_size = 32, },
+ [0x43] = { .level = 2, .type = UNIFIED_CACHE, .size = 512 * KiB,
+ .associativity = 4, .line_size = 32, },
+ [0x44] = { .level = 2, .type = UNIFIED_CACHE, .size = 1 * MiB,
+ .associativity = 4, .line_size = 32, },
+ [0x45] = { .level = 2, .type = UNIFIED_CACHE, .size = 2 * MiB,
+ .associativity = 4, .line_size = 32, },
+ [0x46] = { .level = 3, .type = UNIFIED_CACHE, .size = 4 * MiB,
+ .associativity = 4, .line_size = 64, },
+ [0x47] = { .level = 3, .type = UNIFIED_CACHE, .size = 8 * MiB,
+ .associativity = 8, .line_size = 64, },
+ [0x48] = { .level = 2, .type = UNIFIED_CACHE, .size = 3 * MiB,
+ .associativity = 12, .line_size = 64, },
+ /* Descriptor 0x49 depends on CPU family/model, so it is not included */
+ [0x4A] = { .level = 3, .type = UNIFIED_CACHE, .size = 6 * MiB,
+ .associativity = 12, .line_size = 64, },
+ [0x4B] = { .level = 3, .type = UNIFIED_CACHE, .size = 8 * MiB,
+ .associativity = 16, .line_size = 64, },
+ [0x4C] = { .level = 3, .type = UNIFIED_CACHE, .size = 12 * MiB,
+ .associativity = 12, .line_size = 64, },
+ [0x4D] = { .level = 3, .type = UNIFIED_CACHE, .size = 16 * MiB,
+ .associativity = 16, .line_size = 64, },
+ [0x4E] = { .level = 2, .type = UNIFIED_CACHE, .size = 6 * MiB,
+ .associativity = 24, .line_size = 64, },
+ [0x60] = { .level = 1, .type = DATA_CACHE, .size = 16 * KiB,
+ .associativity = 8, .line_size = 64, },
+ [0x66] = { .level = 1, .type = DATA_CACHE, .size = 8 * KiB,
+ .associativity = 4, .line_size = 64, },
+ [0x67] = { .level = 1, .type = DATA_CACHE, .size = 16 * KiB,
+ .associativity = 4, .line_size = 64, },
+ [0x68] = { .level = 1, .type = DATA_CACHE, .size = 32 * KiB,
+ .associativity = 4, .line_size = 64, },
+ [0x78] = { .level = 2, .type = UNIFIED_CACHE, .size = 1 * MiB,
+ .associativity = 4, .line_size = 64, },
+ /* lines per sector is not supported cpuid2_cache_descriptor(),
+ * so descriptors 0x79, 0x7A, 0x7B, 0x7C are not included.
+ */
+ [0x7D] = { .level = 2, .type = UNIFIED_CACHE, .size = 2 * MiB,
+ .associativity = 8, .line_size = 64, },
+ [0x7F] = { .level = 2, .type = UNIFIED_CACHE, .size = 512 * KiB,
+ .associativity = 2, .line_size = 64, },
+ [0x80] = { .level = 2, .type = UNIFIED_CACHE, .size = 512 * KiB,
+ .associativity = 8, .line_size = 64, },
+ [0x82] = { .level = 2, .type = UNIFIED_CACHE, .size = 256 * KiB,
+ .associativity = 8, .line_size = 32, },
+ [0x83] = { .level = 2, .type = UNIFIED_CACHE, .size = 512 * KiB,
+ .associativity = 8, .line_size = 32, },
+ [0x84] = { .level = 2, .type = UNIFIED_CACHE, .size = 1 * MiB,
+ .associativity = 8, .line_size = 32, },
+ [0x85] = { .level = 2, .type = UNIFIED_CACHE, .size = 2 * MiB,
+ .associativity = 8, .line_size = 32, },
+ [0x86] = { .level = 2, .type = UNIFIED_CACHE, .size = 512 * KiB,
+ .associativity = 4, .line_size = 64, },
+ [0x87] = { .level = 2, .type = UNIFIED_CACHE, .size = 1 * MiB,
+ .associativity = 8, .line_size = 64, },
+ [0xD0] = { .level = 3, .type = UNIFIED_CACHE, .size = 512 * KiB,
+ .associativity = 4, .line_size = 64, },
+ [0xD1] = { .level = 3, .type = UNIFIED_CACHE, .size = 1 * MiB,
+ .associativity = 4, .line_size = 64, },
+ [0xD2] = { .level = 3, .type = UNIFIED_CACHE, .size = 2 * MiB,
+ .associativity = 4, .line_size = 64, },
+ [0xD6] = { .level = 3, .type = UNIFIED_CACHE, .size = 1 * MiB,
+ .associativity = 8, .line_size = 64, },
+ [0xD7] = { .level = 3, .type = UNIFIED_CACHE, .size = 2 * MiB,
+ .associativity = 8, .line_size = 64, },
+ [0xD8] = { .level = 3, .type = UNIFIED_CACHE, .size = 4 * MiB,
+ .associativity = 8, .line_size = 64, },
+ [0xDC] = { .level = 3, .type = UNIFIED_CACHE, .size = 1.5 * MiB,
+ .associativity = 12, .line_size = 64, },
+ [0xDD] = { .level = 3, .type = UNIFIED_CACHE, .size = 3 * MiB,
+ .associativity = 12, .line_size = 64, },
+ [0xDE] = { .level = 3, .type = UNIFIED_CACHE, .size = 6 * MiB,
+ .associativity = 12, .line_size = 64, },
+ [0xE2] = { .level = 3, .type = UNIFIED_CACHE, .size = 2 * MiB,
+ .associativity = 16, .line_size = 64, },
+ [0xE3] = { .level = 3, .type = UNIFIED_CACHE, .size = 4 * MiB,
+ .associativity = 16, .line_size = 64, },
+ [0xE4] = { .level = 3, .type = UNIFIED_CACHE, .size = 8 * MiB,
+ .associativity = 16, .line_size = 64, },
+ [0xEA] = { .level = 3, .type = UNIFIED_CACHE, .size = 12 * MiB,
+ .associativity = 24, .line_size = 64, },
+ [0xEB] = { .level = 3, .type = UNIFIED_CACHE, .size = 18 * MiB,
+ .associativity = 24, .line_size = 64, },
+ [0xEC] = { .level = 3, .type = UNIFIED_CACHE, .size = 24 * MiB,
+ .associativity = 24, .line_size = 64, },
+};
+
+/*
+ * "CPUID leaf 2 does not report cache descriptor information,
+ * use CPUID leaf 4 to query cache parameters"
+ */
+#define CACHE_DESCRIPTOR_UNAVAILABLE 0xFF
-/* CPUID Leaf 2 Descriptors */
+/*
+ * Return a CPUID 2 cache descriptor for a given cache.
+ * If no known descriptor is found, return CACHE_DESCRIPTOR_UNAVAILABLE
+ */
+static uint8_t cpuid2_cache_descriptor(CPUCacheInfo *cache)
+{
+ int i;
-#define CPUID_2_L1D_32KB_8WAY_64B 0x2c
-#define CPUID_2_L1I_32KB_8WAY_64B 0x30
-#define CPUID_2_L2_2MB_8WAY_64B 0x7d
-#define CPUID_2_L3_16MB_16WAY_64B 0x4d
+ assert(cache->size > 0);
+ assert(cache->level > 0);
+ assert(cache->line_size > 0);
+ assert(cache->associativity > 0);
+ for (i = 0; i < ARRAY_SIZE(cpuid2_cache_descriptors); i++) {
+ struct CPUID2CacheDescriptorInfo *d = &cpuid2_cache_descriptors[i];
+ if (d->level == cache->level && d->type == cache->type &&
+ d->size == cache->size && d->line_size == cache->line_size &&
+ d->associativity == cache->associativity) {
+ return i;
+ }
+ }
+ return CACHE_DESCRIPTOR_UNAVAILABLE;
+}
/* CPUID Leaf 4 constants: */
/* EAX: */
-#define CPUID_4_TYPE_DCACHE 1
-#define CPUID_4_TYPE_ICACHE 2
-#define CPUID_4_TYPE_UNIFIED 3
+#define CACHE_TYPE_D 1
+#define CACHE_TYPE_I 2
+#define CACHE_TYPE_UNIFIED 3
-#define CPUID_4_LEVEL(l) ((l) << 5)
+#define CACHE_LEVEL(l) (l << 5)
-#define CPUID_4_SELF_INIT_LEVEL (1 << 8)
-#define CPUID_4_FULLY_ASSOC (1 << 9)
+#define CACHE_SELF_INIT_LEVEL (1 << 8)
/* EDX: */
-#define CPUID_4_NO_INVD_SHARING (1 << 0)
-#define CPUID_4_INCLUSIVE (1 << 1)
-#define CPUID_4_COMPLEX_IDX (1 << 2)
+#define CACHE_NO_INVD_SHARING (1 << 0)
+#define CACHE_INCLUSIVE (1 << 1)
+#define CACHE_COMPLEX_IDX (1 << 2)
+
+/* Encode CacheType for CPUID[4].EAX */
+#define CACHE_TYPE(t) (((t) == DATA_CACHE) ? CACHE_TYPE_D : \
+ ((t) == INSTRUCTION_CACHE) ? CACHE_TYPE_I : \
+ ((t) == UNIFIED_CACHE) ? CACHE_TYPE_UNIFIED : \
+ 0 /* Invalid value */)
+
+
+/* Encode cache info for CPUID[4] */
+static void encode_cache_cpuid4(CPUCacheInfo *cache,
+ int num_apic_ids, int num_cores,
+ uint32_t *eax, uint32_t *ebx,
+ uint32_t *ecx, uint32_t *edx)
+{
+ assert(cache->size == cache->line_size * cache->associativity *
+ cache->partitions * cache->sets);
+
+ assert(num_apic_ids > 0);
+ *eax = CACHE_TYPE(cache->type) |
+ CACHE_LEVEL(cache->level) |
+ (cache->self_init ? CACHE_SELF_INIT_LEVEL : 0) |
+ ((num_cores - 1) << 26) |
+ ((num_apic_ids - 1) << 14);
+
+ assert(cache->line_size > 0);
+ assert(cache->partitions > 0);
+ assert(cache->associativity > 0);
+ /* We don't implement fully-associative caches */
+ assert(cache->associativity < cache->sets);
+ *ebx = (cache->line_size - 1) |
+ ((cache->partitions - 1) << 12) |
+ ((cache->associativity - 1) << 22);
+
+ assert(cache->sets > 0);
+ *ecx = cache->sets - 1;
+
+ *edx = (cache->no_invd_sharing ? CACHE_NO_INVD_SHARING : 0) |
+ (cache->inclusive ? CACHE_INCLUSIVE : 0) |
+ (cache->complex_indexing ? CACHE_COMPLEX_IDX : 0);
+}
+
+/* Encode cache info for CPUID[0x80000005].ECX or CPUID[0x80000005].EDX */
+static uint32_t encode_cache_cpuid80000005(CPUCacheInfo *cache)
+{
+ assert(cache->size % 1024 == 0);
+ assert(cache->lines_per_tag > 0);
+ assert(cache->associativity > 0);
+ assert(cache->line_size > 0);
+ return ((cache->size / 1024) << 24) | (cache->associativity << 16) |
+ (cache->lines_per_tag << 8) | (cache->line_size);
+}
#define ASSOC_FULL 0xFF
a == ASSOC_FULL ? 0xF : \
0 /* invalid value */)
+/*
+ * Encode cache info for CPUID[0x80000006].ECX and CPUID[0x80000006].EDX
+ * @l3 can be NULL.
+ */
+static void encode_cache_cpuid80000006(CPUCacheInfo *l2,
+ CPUCacheInfo *l3,
+ uint32_t *ecx, uint32_t *edx)
+{
+ assert(l2->size % 1024 == 0);
+ assert(l2->associativity > 0);
+ assert(l2->lines_per_tag > 0);
+ assert(l2->line_size > 0);
+ *ecx = ((l2->size / 1024) << 16) |
+ (AMD_ENC_ASSOC(l2->associativity) << 12) |
+ (l2->lines_per_tag << 8) | (l2->line_size);
+
+ if (l3) {
+ assert(l3->size % (512 * 1024) == 0);
+ assert(l3->associativity > 0);
+ assert(l3->lines_per_tag > 0);
+ assert(l3->line_size > 0);
+ *edx = ((l3->size / (512 * 1024)) << 18) |
+ (AMD_ENC_ASSOC(l3->associativity) << 12) |
+ (l3->lines_per_tag << 8) | (l3->line_size);
+ } else {
+ *edx = 0;
+ }
+}
+
+/*
+ * Definitions used for building CPUID Leaf 0x8000001D and 0x8000001E
+ * Please refer to the AMD64 Architecture Programmer’s Manual Volume 3.
+ * Define the constants to build the cpu topology. Right now, TOPOEXT
+ * feature is enabled only on EPYC. So, these constants are based on
+ * EPYC supported configurations. We may need to handle the cases if
+ * these values change in future.
+ */
+/* Maximum core complexes in a node */
+#define MAX_CCX 2
+/* Maximum cores in a core complex */
+#define MAX_CORES_IN_CCX 4
+/* Maximum cores in a node */
+#define MAX_CORES_IN_NODE 8
+/* Maximum nodes in a socket */
+#define MAX_NODES_PER_SOCKET 4
+
+/*
+ * Figure out the number of nodes required to build this config.
+ * Max cores in a node is 8
+ */
+static int nodes_in_socket(int nr_cores)
+{
+ int nodes;
+
+ nodes = DIV_ROUND_UP(nr_cores, MAX_CORES_IN_NODE);
+
+ /* Hardware does not support config with 3 nodes, return 4 in that case */
+ return (nodes == 3) ? 4 : nodes;
+}
+
+/*
+ * Decide the number of cores in a core complex with the given nr_cores using
+ * following set constants MAX_CCX, MAX_CORES_IN_CCX, MAX_CORES_IN_NODE and
+ * MAX_NODES_PER_SOCKET. Maintain symmetry as much as possible
+ * L3 cache is shared across all cores in a core complex. So, this will also
+ * tell us how many cores are sharing the L3 cache.
+ */
+static int cores_in_core_complex(int nr_cores)
+{
+ int nodes;
+
+ /* Check if we can fit all the cores in one core complex */
+ if (nr_cores <= MAX_CORES_IN_CCX) {
+ return nr_cores;
+ }
+ /* Get the number of nodes required to build this config */
+ nodes = nodes_in_socket(nr_cores);
+
+ /*
+ * Divide the cores accros all the core complexes
+ * Return rounded up value
+ */
+ return DIV_ROUND_UP(nr_cores, nodes * MAX_CCX);
+}
+
+/* Encode cache info for CPUID[8000001D] */
+static void encode_cache_cpuid8000001d(CPUCacheInfo *cache, CPUState *cs,
+ uint32_t *eax, uint32_t *ebx,
+ uint32_t *ecx, uint32_t *edx)
+{
+ uint32_t l3_cores;
+ assert(cache->size == cache->line_size * cache->associativity *
+ cache->partitions * cache->sets);
+
+ *eax = CACHE_TYPE(cache->type) | CACHE_LEVEL(cache->level) |
+ (cache->self_init ? CACHE_SELF_INIT_LEVEL : 0);
+
+ /* L3 is shared among multiple cores */
+ if (cache->level == 3) {
+ l3_cores = cores_in_core_complex(cs->nr_cores);
+ *eax |= ((l3_cores * cs->nr_threads) - 1) << 14;
+ } else {
+ *eax |= ((cs->nr_threads - 1) << 14);
+ }
+
+ assert(cache->line_size > 0);
+ assert(cache->partitions > 0);
+ assert(cache->associativity > 0);
+ /* We don't implement fully-associative caches */
+ assert(cache->associativity < cache->sets);
+ *ebx = (cache->line_size - 1) |
+ ((cache->partitions - 1) << 12) |
+ ((cache->associativity - 1) << 22);
+
+ assert(cache->sets > 0);
+ *ecx = cache->sets - 1;
+
+ *edx = (cache->no_invd_sharing ? CACHE_NO_INVD_SHARING : 0) |
+ (cache->inclusive ? CACHE_INCLUSIVE : 0) |
+ (cache->complex_indexing ? CACHE_COMPLEX_IDX : 0);
+}
+
+/* Data structure to hold the configuration info for a given core index */
+struct core_topology {
+ /* core complex id of the current core index */
+ int ccx_id;
+ /*
+ * Adjusted core index for this core in the topology
+ * This can be 0,1,2,3 with max 4 cores in a core complex
+ */
+ int core_id;
+ /* Node id for this core index */
+ int node_id;
+ /* Number of nodes in this config */
+ int num_nodes;
+};
+
+/*
+ * Build the configuration closely match the EPYC hardware. Using the EPYC
+ * hardware configuration values (MAX_CCX, MAX_CORES_IN_CCX, MAX_CORES_IN_NODE)
+ * right now. This could change in future.
+ * nr_cores : Total number of cores in the config
+ * core_id : Core index of the current CPU
+ * topo : Data structure to hold all the config info for this core index
+ */
+static void build_core_topology(int nr_cores, int core_id,
+ struct core_topology *topo)
+{
+ int nodes, cores_in_ccx;
+
+ /* First get the number of nodes required */
+ nodes = nodes_in_socket(nr_cores);
-/* Definitions of the hardcoded cache entries we expose: */
+ cores_in_ccx = cores_in_core_complex(nr_cores);
+
+ topo->node_id = core_id / (cores_in_ccx * MAX_CCX);
+ topo->ccx_id = (core_id % (cores_in_ccx * MAX_CCX)) / cores_in_ccx;
+ topo->core_id = core_id % cores_in_ccx;
+ topo->num_nodes = nodes;
+}
+
+/* Encode cache info for CPUID[8000001E] */
+static void encode_topo_cpuid8000001e(CPUState *cs, X86CPU *cpu,
+ uint32_t *eax, uint32_t *ebx,
+ uint32_t *ecx, uint32_t *edx)
+{
+ struct core_topology topo = {0};
+ unsigned long nodes;
+ int shift;
+
+ build_core_topology(cs->nr_cores, cpu->core_id, &topo);
+ *eax = cpu->apic_id;
+ /*
+ * CPUID_Fn8000001E_EBX
+ * 31:16 Reserved
+ * 15:8 Threads per core (The number of threads per core is
+ * Threads per core + 1)
+ * 7:0 Core id (see bit decoding below)
+ * SMT:
+ * 4:3 node id
+ * 2 Core complex id
+ * 1:0 Core id
+ * Non SMT:
+ * 5:4 node id
+ * 3 Core complex id
+ * 1:0 Core id
+ */
+ if (cs->nr_threads - 1) {
+ *ebx = ((cs->nr_threads - 1) << 8) | (topo.node_id << 3) |
+ (topo.ccx_id << 2) | topo.core_id;
+ } else {
+ *ebx = (topo.node_id << 4) | (topo.ccx_id << 3) | topo.core_id;
+ }
+ /*
+ * CPUID_Fn8000001E_ECX
+ * 31:11 Reserved
+ * 10:8 Nodes per processor (Nodes per processor is number of nodes + 1)
+ * 7:0 Node id (see bit decoding below)
+ * 2 Socket id
+ * 1:0 Node id
+ */
+ if (topo.num_nodes <= 4) {
+ *ecx = ((topo.num_nodes - 1) << 8) | (cpu->socket_id << 2) |
+ topo.node_id;
+ } else {
+ /*
+ * Node id fix up. Actual hardware supports up to 4 nodes. But with
+ * more than 32 cores, we may end up with more than 4 nodes.
+ * Node id is a combination of socket id and node id. Only requirement
+ * here is that this number should be unique accross the system.
+ * Shift the socket id to accommodate more nodes. We dont expect both
+ * socket id and node id to be big number at the same time. This is not
+ * an ideal config but we need to to support it. Max nodes we can have
+ * is 32 (255/8) with 8 cores per node and 255 max cores. We only need
+ * 5 bits for nodes. Find the left most set bit to represent the total
+ * number of nodes. find_last_bit returns last set bit(0 based). Left
+ * shift(+1) the socket id to represent all the nodes.
+ */
+ nodes = topo.num_nodes - 1;
+ shift = find_last_bit(&nodes, 8);
+ *ecx = ((topo.num_nodes - 1) << 8) | (cpu->socket_id << (shift + 1)) |
+ topo.node_id;
+ }
+ *edx = 0;
+}
+
+/*
+ * Definitions of the hardcoded cache entries we expose:
+ * These are legacy cache values. If there is a need to change any
+ * of these values please use builtin_x86_defs
+ */
/* L1 data cache: */
-#define L1D_LINE_SIZE 64
-#define L1D_ASSOCIATIVITY 8
-#define L1D_SETS 64
-#define L1D_PARTITIONS 1
-/* Size = LINE_SIZE*ASSOCIATIVITY*SETS*PARTITIONS = 32KiB */
-#define L1D_DESCRIPTOR CPUID_2_L1D_32KB_8WAY_64B
+static CPUCacheInfo legacy_l1d_cache = {
+ .type = DATA_CACHE,
+ .level = 1,
+ .size = 32 * KiB,
+ .self_init = 1,
+ .line_size = 64,
+ .associativity = 8,
+ .sets = 64,
+ .partitions = 1,
+ .no_invd_sharing = true,
+};
+
/*FIXME: CPUID leaf 0x80000005 is inconsistent with leaves 2 & 4 */
-#define L1D_LINES_PER_TAG 1
-#define L1D_SIZE_KB_AMD 64
-#define L1D_ASSOCIATIVITY_AMD 2
+static CPUCacheInfo legacy_l1d_cache_amd = {
+ .type = DATA_CACHE,
+ .level = 1,
+ .size = 64 * KiB,
+ .self_init = 1,
+ .line_size = 64,
+ .associativity = 2,
+ .sets = 512,
+ .partitions = 1,
+ .lines_per_tag = 1,
+ .no_invd_sharing = true,
+};
/* L1 instruction cache: */
-#define L1I_LINE_SIZE 64
-#define L1I_ASSOCIATIVITY 8
-#define L1I_SETS 64
-#define L1I_PARTITIONS 1
-/* Size = LINE_SIZE*ASSOCIATIVITY*SETS*PARTITIONS = 32KiB */
-#define L1I_DESCRIPTOR CPUID_2_L1I_32KB_8WAY_64B
+static CPUCacheInfo legacy_l1i_cache = {
+ .type = INSTRUCTION_CACHE,
+ .level = 1,
+ .size = 32 * KiB,
+ .self_init = 1,
+ .line_size = 64,
+ .associativity = 8,
+ .sets = 64,
+ .partitions = 1,
+ .no_invd_sharing = true,
+};
+
/*FIXME: CPUID leaf 0x80000005 is inconsistent with leaves 2 & 4 */
-#define L1I_LINES_PER_TAG 1
-#define L1I_SIZE_KB_AMD 64
-#define L1I_ASSOCIATIVITY_AMD 2
+static CPUCacheInfo legacy_l1i_cache_amd = {
+ .type = INSTRUCTION_CACHE,
+ .level = 1,
+ .size = 64 * KiB,
+ .self_init = 1,
+ .line_size = 64,
+ .associativity = 2,
+ .sets = 512,
+ .partitions = 1,
+ .lines_per_tag = 1,
+ .no_invd_sharing = true,
+};
/* Level 2 unified cache: */
-#define L2_LINE_SIZE 64
-#define L2_ASSOCIATIVITY 16
-#define L2_SETS 4096
-#define L2_PARTITIONS 1
-/* Size = LINE_SIZE*ASSOCIATIVITY*SETS*PARTITIONS = 4MiB */
+static CPUCacheInfo legacy_l2_cache = {
+ .type = UNIFIED_CACHE,
+ .level = 2,
+ .size = 4 * MiB,
+ .self_init = 1,
+ .line_size = 64,
+ .associativity = 16,
+ .sets = 4096,
+ .partitions = 1,
+ .no_invd_sharing = true,
+};
+
/*FIXME: CPUID leaf 2 descriptor is inconsistent with CPUID leaf 4 */
-#define L2_DESCRIPTOR CPUID_2_L2_2MB_8WAY_64B
+static CPUCacheInfo legacy_l2_cache_cpuid2 = {
+ .type = UNIFIED_CACHE,
+ .level = 2,
+ .size = 2 * MiB,
+ .line_size = 64,
+ .associativity = 8,
+};
+
+
/*FIXME: CPUID leaf 0x80000006 is inconsistent with leaves 2 & 4 */
-#define L2_LINES_PER_TAG 1
-#define L2_SIZE_KB_AMD 512
+static CPUCacheInfo legacy_l2_cache_amd = {
+ .type = UNIFIED_CACHE,
+ .level = 2,
+ .size = 512 * KiB,
+ .line_size = 64,
+ .lines_per_tag = 1,
+ .associativity = 16,
+ .sets = 512,
+ .partitions = 1,
+};
/* Level 3 unified cache: */
-#define L3_SIZE_KB 0 /* disabled */
-#define L3_ASSOCIATIVITY 0 /* disabled */
-#define L3_LINES_PER_TAG 0 /* disabled */
-#define L3_LINE_SIZE 0 /* disabled */
-#define L3_N_LINE_SIZE 64
-#define L3_N_ASSOCIATIVITY 16
-#define L3_N_SETS 16384
-#define L3_N_PARTITIONS 1
-#define L3_N_DESCRIPTOR CPUID_2_L3_16MB_16WAY_64B
-#define L3_N_LINES_PER_TAG 1
-#define L3_N_SIZE_KB_AMD 16384
+static CPUCacheInfo legacy_l3_cache = {
+ .type = UNIFIED_CACHE,
+ .level = 3,
+ .size = 16 * MiB,
+ .line_size = 64,
+ .associativity = 16,
+ .sets = 16384,
+ .partitions = 1,
+ .lines_per_tag = 1,
+ .self_init = true,
+ .inclusive = true,
+ .complex_indexing = true,
+};
/* TLB definitions: */
* bit[02]: Support Single-Range Output scheme;
*/
#define INTEL_PT_MINIMAL_ECX 0x7
+/* generated packets which contain IP payloads have LIP values */
+#define INTEL_PT_IP_LIP (1 << 31)
#define INTEL_PT_ADDR_RANGES_NUM 0x2 /* Number of configurable address ranges */
#define INTEL_PT_ADDR_RANGES_NUM_MASK 0x3
#define INTEL_PT_MTC_BITMAP (0x0249 << 16) /* Support ART(0,3,6,9) */
#define TCG_EXT3_FEATURES (CPUID_EXT3_LAHF_LM | CPUID_EXT3_SVM | \
CPUID_EXT3_CR8LEG | CPUID_EXT3_ABM | CPUID_EXT3_SSE4A)
#define TCG_EXT4_FEATURES 0
-#define TCG_SVM_FEATURES 0
+#define TCG_SVM_FEATURES CPUID_SVM_NPT
#define TCG_KVM_FEATURES 0
#define TCG_7_0_EBX_FEATURES (CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_SMAP | \
CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_ADX | \
CPUID_7_0_EBX_HLE, CPUID_7_0_EBX_AVX2,
CPUID_7_0_EBX_INVPCID, CPUID_7_0_EBX_RTM,
CPUID_7_0_EBX_RDSEED */
-#define TCG_7_0_ECX_FEATURES (CPUID_7_0_ECX_PKU | CPUID_7_0_ECX_OSPKE | \
+#define TCG_7_0_ECX_FEATURES (CPUID_7_0_ECX_PKU | \
+ /* CPUID_7_0_ECX_OSPKE is dynamic */ \
CPUID_7_0_ECX_LA57)
#define TCG_7_0_EDX_FEATURES 0
#define TCG_APM_FEATURES 0
uint32_t tcg_features; /* Feature flags supported by TCG */
uint32_t unmigratable_flags; /* Feature flags known to be unmigratable */
uint32_t migratable_flags; /* Feature flags known to be migratable */
+ /* Features that shouldn't be auto-enabled by "-cpu host" */
+ uint32_t no_autoenable_flags;
} FeatureWordInfo;
static FeatureWordInfo feature_word_info[FEATURE_WORDS] = {
"fma", "cx16", "xtpr", "pdcm",
NULL, "pcid", "dca", "sse4.1",
"sse4.2", "x2apic", "movbe", "popcnt",
- "tsc-deadline", "aes", "xsave", "osxsave",
+ "tsc-deadline", "aes", "xsave", NULL /* osxsave */,
"avx", "f16c", "rdrand", "hypervisor",
},
.cpuid_eax = 1, .cpuid_reg = R_ECX,
},
.cpuid_eax = KVM_CPUID_FEATURES, .cpuid_reg = R_EDX,
.tcg_features = TCG_KVM_FEATURES,
+ /*
+ * KVM hints aren't auto-enabled by -cpu host, they need to be
+ * explicitly enabled in the command-line.
+ */
+ .no_autoenable_flags = ~0U,
},
[FEAT_HYPERV_EAX] = {
.feat_names = {
NULL /* hv_vpindex_access */, NULL /* hv_msr_reset_access */,
NULL /* hv_msr_stats_access */, NULL /* hv_reftsc_access */,
NULL /* hv_msr_idle_access */, NULL /* hv_msr_frequency_access */,
- NULL, NULL, NULL, NULL,
+ NULL /* hv_msr_debug_access */, NULL /* hv_msr_reenlightenment_access */,
+ NULL, NULL,
NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL,
[FEAT_7_0_ECX] = {
.feat_names = {
NULL, "avx512vbmi", "umip", "pku",
- "ospke", NULL, "avx512vbmi2", NULL,
+ NULL /* ospke */, NULL, "avx512vbmi2", NULL,
"gfni", "vaes", "vpclmulqdq", "avx512vnni",
"avx512bitalg", NULL, "avx512-vpopcntdq", NULL,
"la57", NULL, NULL, NULL,
NULL, NULL, "rdpid", NULL,
- NULL, NULL, NULL, NULL,
+ NULL, "cldemote", NULL, NULL,
NULL, NULL, NULL, NULL,
},
.cpuid_eax = 7,
NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL,
+ NULL, NULL, "pconfig", NULL,
NULL, NULL, NULL, NULL,
NULL, NULL, "spec-ctrl", NULL,
- NULL, NULL, NULL, NULL,
+ NULL, "arch-capabilities", NULL, "ssbd",
},
.cpuid_eax = 7,
.cpuid_needs_ecx = true, .cpuid_ecx = 0,
.cpuid_reg = R_EDX,
.tcg_features = TCG_7_0_EDX_FEATURES,
+ .unmigratable_flags = CPUID_7_0_EDX_ARCH_CAPABILITIES,
},
[FEAT_8000_0007_EDX] = {
.feat_names = {
.feat_names = {
NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL,
+ NULL, "wbnoinvd", NULL, NULL,
"ibpb", NULL, NULL, NULL,
NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL,
- NULL, NULL, NULL, NULL,
+ "amd-ssbd", "virt-ssbd", "amd-no-ssb", NULL,
NULL, NULL, NULL, NULL,
},
.cpuid_eax = 0x80000008,
static ObjectClass *x86_cpu_class_by_name(const char *cpu_model)
{
ObjectClass *oc;
- char *typename;
-
- if (cpu_model == NULL) {
- return NULL;
- }
-
- typename = x86_cpu_type_name(cpu_model);
+ char *typename = x86_cpu_type_name(cpu_model);
oc = object_class_by_name(typename);
g_free(typename);
return oc;
int stepping;
FeatureWordArray features;
const char *model_id;
+ CPUCaches *cache_info;
+};
+
+static CPUCaches epyc_cache_info = {
+ .l1d_cache = &(CPUCacheInfo) {
+ .type = DATA_CACHE,
+ .level = 1,
+ .size = 32 * KiB,
+ .line_size = 64,
+ .associativity = 8,
+ .partitions = 1,
+ .sets = 64,
+ .lines_per_tag = 1,
+ .self_init = 1,
+ .no_invd_sharing = true,
+ },
+ .l1i_cache = &(CPUCacheInfo) {
+ .type = INSTRUCTION_CACHE,
+ .level = 1,
+ .size = 64 * KiB,
+ .line_size = 64,
+ .associativity = 4,
+ .partitions = 1,
+ .sets = 256,
+ .lines_per_tag = 1,
+ .self_init = 1,
+ .no_invd_sharing = true,
+ },
+ .l2_cache = &(CPUCacheInfo) {
+ .type = UNIFIED_CACHE,
+ .level = 2,
+ .size = 512 * KiB,
+ .line_size = 64,
+ .associativity = 8,
+ .partitions = 1,
+ .sets = 1024,
+ .lines_per_tag = 1,
+ },
+ .l3_cache = &(CPUCacheInfo) {
+ .type = UNIFIED_CACHE,
+ .level = 3,
+ .size = 8 * MiB,
+ .line_size = 64,
+ .associativity = 16,
+ .partitions = 1,
+ .sets = 8192,
+ .lines_per_tag = 1,
+ .self_init = true,
+ .inclusive = true,
+ .complex_indexing = true,
+ },
};
static X86CPUDefinition builtin_x86_defs[] = {
.xlevel = 0x80000008,
.model_id = "Intel Xeon Processor (Skylake, IBRS)",
},
+ {
+ .name = "Icelake-Client",
+ .level = 0xd,
+ .vendor = CPUID_VENDOR_INTEL,
+ .family = 6,
+ .model = 126,
+ .stepping = 0,
+ .features[FEAT_1_EDX] =
+ CPUID_VME | CPUID_SSE2 | CPUID_SSE | CPUID_FXSR | CPUID_MMX |
+ CPUID_CLFLUSH | CPUID_PSE36 | CPUID_PAT | CPUID_CMOV | CPUID_MCA |
+ CPUID_PGE | CPUID_MTRR | CPUID_SEP | CPUID_APIC | CPUID_CX8 |
+ CPUID_MCE | CPUID_PAE | CPUID_MSR | CPUID_TSC | CPUID_PSE |
+ CPUID_DE | CPUID_FP87,
+ .features[FEAT_1_ECX] =
+ CPUID_EXT_AVX | CPUID_EXT_XSAVE | CPUID_EXT_AES |
+ CPUID_EXT_POPCNT | CPUID_EXT_X2APIC | CPUID_EXT_SSE42 |
+ CPUID_EXT_SSE41 | CPUID_EXT_CX16 | CPUID_EXT_SSSE3 |
+ CPUID_EXT_PCLMULQDQ | CPUID_EXT_SSE3 |
+ CPUID_EXT_TSC_DEADLINE_TIMER | CPUID_EXT_FMA | CPUID_EXT_MOVBE |
+ CPUID_EXT_PCID | CPUID_EXT_F16C | CPUID_EXT_RDRAND,
+ .features[FEAT_8000_0001_EDX] =
+ CPUID_EXT2_LM | CPUID_EXT2_RDTSCP | CPUID_EXT2_NX |
+ CPUID_EXT2_SYSCALL,
+ .features[FEAT_8000_0001_ECX] =
+ CPUID_EXT3_ABM | CPUID_EXT3_LAHF_LM | CPUID_EXT3_3DNOWPREFETCH,
+ .features[FEAT_8000_0008_EBX] =
+ CPUID_8000_0008_EBX_WBNOINVD,
+ .features[FEAT_7_0_EBX] =
+ CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 |
+ CPUID_7_0_EBX_HLE | CPUID_7_0_EBX_AVX2 | CPUID_7_0_EBX_SMEP |
+ CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_ERMS | CPUID_7_0_EBX_INVPCID |
+ CPUID_7_0_EBX_RTM | CPUID_7_0_EBX_RDSEED | CPUID_7_0_EBX_ADX |
+ CPUID_7_0_EBX_SMAP | CPUID_7_0_EBX_MPX | CPUID_7_0_EBX_INTEL_PT,
+ .features[FEAT_7_0_ECX] =
+ CPUID_7_0_ECX_VBMI | CPUID_7_0_ECX_UMIP | CPUID_7_0_ECX_PKU |
+ CPUID_7_0_ECX_OSPKE | CPUID_7_0_ECX_VBMI2 | CPUID_7_0_ECX_GFNI |
+ CPUID_7_0_ECX_VAES | CPUID_7_0_ECX_VPCLMULQDQ |
+ CPUID_7_0_ECX_AVX512VNNI | CPUID_7_0_ECX_AVX512BITALG |
+ CPUID_7_0_ECX_AVX512_VPOPCNTDQ,
+ .features[FEAT_7_0_EDX] =
+ CPUID_7_0_EDX_SPEC_CTRL | CPUID_7_0_EDX_SPEC_CTRL_SSBD,
+ /* Missing: XSAVES (not supported by some Linux versions,
+ * including v4.1 to v4.12).
+ * KVM doesn't yet expose any XSAVES state save component,
+ * and the only one defined in Skylake (processor tracing)
+ * probably will block migration anyway.
+ */
+ .features[FEAT_XSAVE] =
+ CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XSAVEC |
+ CPUID_XSAVE_XGETBV1,
+ .features[FEAT_6_EAX] =
+ CPUID_6_EAX_ARAT,
+ .xlevel = 0x80000008,
+ .model_id = "Intel Core Processor (Icelake)",
+ },
+ {
+ .name = "Icelake-Server",
+ .level = 0xd,
+ .vendor = CPUID_VENDOR_INTEL,
+ .family = 6,
+ .model = 134,
+ .stepping = 0,
+ .features[FEAT_1_EDX] =
+ CPUID_VME | CPUID_SSE2 | CPUID_SSE | CPUID_FXSR | CPUID_MMX |
+ CPUID_CLFLUSH | CPUID_PSE36 | CPUID_PAT | CPUID_CMOV | CPUID_MCA |
+ CPUID_PGE | CPUID_MTRR | CPUID_SEP | CPUID_APIC | CPUID_CX8 |
+ CPUID_MCE | CPUID_PAE | CPUID_MSR | CPUID_TSC | CPUID_PSE |
+ CPUID_DE | CPUID_FP87,
+ .features[FEAT_1_ECX] =
+ CPUID_EXT_AVX | CPUID_EXT_XSAVE | CPUID_EXT_AES |
+ CPUID_EXT_POPCNT | CPUID_EXT_X2APIC | CPUID_EXT_SSE42 |
+ CPUID_EXT_SSE41 | CPUID_EXT_CX16 | CPUID_EXT_SSSE3 |
+ CPUID_EXT_PCLMULQDQ | CPUID_EXT_SSE3 |
+ CPUID_EXT_TSC_DEADLINE_TIMER | CPUID_EXT_FMA | CPUID_EXT_MOVBE |
+ CPUID_EXT_PCID | CPUID_EXT_F16C | CPUID_EXT_RDRAND,
+ .features[FEAT_8000_0001_EDX] =
+ CPUID_EXT2_LM | CPUID_EXT2_PDPE1GB | CPUID_EXT2_RDTSCP |
+ CPUID_EXT2_NX | CPUID_EXT2_SYSCALL,
+ .features[FEAT_8000_0001_ECX] =
+ CPUID_EXT3_ABM | CPUID_EXT3_LAHF_LM | CPUID_EXT3_3DNOWPREFETCH,
+ .features[FEAT_8000_0008_EBX] =
+ CPUID_8000_0008_EBX_WBNOINVD,
+ .features[FEAT_7_0_EBX] =
+ CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 |
+ CPUID_7_0_EBX_HLE | CPUID_7_0_EBX_AVX2 | CPUID_7_0_EBX_SMEP |
+ CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_ERMS | CPUID_7_0_EBX_INVPCID |
+ CPUID_7_0_EBX_RTM | CPUID_7_0_EBX_RDSEED | CPUID_7_0_EBX_ADX |
+ CPUID_7_0_EBX_SMAP | CPUID_7_0_EBX_MPX | CPUID_7_0_EBX_CLWB |
+ CPUID_7_0_EBX_AVX512F | CPUID_7_0_EBX_AVX512DQ |
+ CPUID_7_0_EBX_AVX512BW | CPUID_7_0_EBX_AVX512CD |
+ CPUID_7_0_EBX_AVX512VL | CPUID_7_0_EBX_CLFLUSHOPT |
+ CPUID_7_0_EBX_INTEL_PT,
+ .features[FEAT_7_0_ECX] =
+ CPUID_7_0_ECX_VBMI | CPUID_7_0_ECX_UMIP | CPUID_7_0_ECX_PKU |
+ CPUID_7_0_ECX_OSPKE | CPUID_7_0_ECX_VBMI2 | CPUID_7_0_ECX_GFNI |
+ CPUID_7_0_ECX_VAES | CPUID_7_0_ECX_VPCLMULQDQ |
+ CPUID_7_0_ECX_AVX512VNNI | CPUID_7_0_ECX_AVX512BITALG |
+ CPUID_7_0_ECX_AVX512_VPOPCNTDQ | CPUID_7_0_ECX_LA57,
+ .features[FEAT_7_0_EDX] =
+ CPUID_7_0_EDX_PCONFIG | CPUID_7_0_EDX_SPEC_CTRL |
+ CPUID_7_0_EDX_SPEC_CTRL_SSBD,
+ /* Missing: XSAVES (not supported by some Linux versions,
+ * including v4.1 to v4.12).
+ * KVM doesn't yet expose any XSAVES state save component,
+ * and the only one defined in Skylake (processor tracing)
+ * probably will block migration anyway.
+ */
+ .features[FEAT_XSAVE] =
+ CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XSAVEC |
+ CPUID_XSAVE_XGETBV1,
+ .features[FEAT_6_EAX] =
+ CPUID_6_EAX_ARAT,
+ .xlevel = 0x80000008,
+ .model_id = "Intel Xeon Processor (Icelake)",
+ },
+ {
+ .name = "KnightsMill",
+ .level = 0xd,
+ .vendor = CPUID_VENDOR_INTEL,
+ .family = 6,
+ .model = 133,
+ .stepping = 0,
+ .features[FEAT_1_EDX] =
+ CPUID_VME | CPUID_SS | CPUID_SSE2 | CPUID_SSE | CPUID_FXSR |
+ CPUID_MMX | CPUID_CLFLUSH | CPUID_PSE36 | CPUID_PAT | CPUID_CMOV |
+ CPUID_MCA | CPUID_PGE | CPUID_MTRR | CPUID_SEP | CPUID_APIC |
+ CPUID_CX8 | CPUID_MCE | CPUID_PAE | CPUID_MSR | CPUID_TSC |
+ CPUID_PSE | CPUID_DE | CPUID_FP87,
+ .features[FEAT_1_ECX] =
+ CPUID_EXT_AVX | CPUID_EXT_XSAVE | CPUID_EXT_AES |
+ CPUID_EXT_POPCNT | CPUID_EXT_X2APIC | CPUID_EXT_SSE42 |
+ CPUID_EXT_SSE41 | CPUID_EXT_CX16 | CPUID_EXT_SSSE3 |
+ CPUID_EXT_PCLMULQDQ | CPUID_EXT_SSE3 |
+ CPUID_EXT_TSC_DEADLINE_TIMER | CPUID_EXT_FMA | CPUID_EXT_MOVBE |
+ CPUID_EXT_F16C | CPUID_EXT_RDRAND,
+ .features[FEAT_8000_0001_EDX] =
+ CPUID_EXT2_LM | CPUID_EXT2_PDPE1GB | CPUID_EXT2_RDTSCP |
+ CPUID_EXT2_NX | CPUID_EXT2_SYSCALL,
+ .features[FEAT_8000_0001_ECX] =
+ CPUID_EXT3_ABM | CPUID_EXT3_LAHF_LM | CPUID_EXT3_3DNOWPREFETCH,
+ .features[FEAT_7_0_EBX] =
+ CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_AVX2 |
+ CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_ERMS |
+ CPUID_7_0_EBX_RDSEED | CPUID_7_0_EBX_ADX | CPUID_7_0_EBX_AVX512F |
+ CPUID_7_0_EBX_AVX512CD | CPUID_7_0_EBX_AVX512PF |
+ CPUID_7_0_EBX_AVX512ER,
+ .features[FEAT_7_0_ECX] =
+ CPUID_7_0_ECX_AVX512_VPOPCNTDQ,
+ .features[FEAT_7_0_EDX] =
+ CPUID_7_0_EDX_AVX512_4VNNIW | CPUID_7_0_EDX_AVX512_4FMAPS,
+ .features[FEAT_XSAVE] =
+ CPUID_XSAVE_XSAVEOPT,
+ .features[FEAT_6_EAX] =
+ CPUID_6_EAX_ARAT,
+ .xlevel = 0x80000008,
+ .model_id = "Intel Xeon Phi Processor (Knights Mill)",
+ },
{
.name = "Opteron_G1",
.level = 5,
.features[FEAT_8000_0001_ECX] =
CPUID_EXT3_OSVW | CPUID_EXT3_3DNOWPREFETCH |
CPUID_EXT3_MISALIGNSSE | CPUID_EXT3_SSE4A | CPUID_EXT3_ABM |
- CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM,
+ CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM |
+ CPUID_EXT3_TOPOEXT,
.features[FEAT_7_0_EBX] =
CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_AVX2 |
CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_RDSEED |
CPUID_XSAVE_XGETBV1,
.features[FEAT_6_EAX] =
CPUID_6_EAX_ARAT,
- .xlevel = 0x8000000A,
+ .xlevel = 0x8000001E,
.model_id = "AMD EPYC Processor",
+ .cache_info = &epyc_cache_info,
},
{
.name = "EPYC-IBPB",
.features[FEAT_8000_0001_ECX] =
CPUID_EXT3_OSVW | CPUID_EXT3_3DNOWPREFETCH |
CPUID_EXT3_MISALIGNSSE | CPUID_EXT3_SSE4A | CPUID_EXT3_ABM |
- CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM,
+ CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM |
+ CPUID_EXT3_TOPOEXT,
.features[FEAT_8000_0008_EBX] =
CPUID_8000_0008_EBX_IBPB,
.features[FEAT_7_0_EBX] =
CPUID_XSAVE_XGETBV1,
.features[FEAT_6_EAX] =
CPUID_6_EAX_ARAT,
- .xlevel = 0x8000000A,
+ .xlevel = 0x8000001E,
.model_id = "AMD EPYC Processor (with IBPB)",
+ .cache_info = &epyc_cache_info,
},
};
xcc->host_cpuid_required = true;
xcc->ordering = 8;
- if (kvm_enabled()) {
- xcc->model_description =
- "KVM processor with all supported host features ";
- } else if (hvf_enabled()) {
- xcc->model_description =
- "HVF processor with all supported host features ";
- }
+#if defined(CONFIG_KVM)
+ xcc->model_description =
+ "KVM processor with all supported host features ";
+#elif defined(CONFIG_HVF)
+ xcc->model_description =
+ "HVF processor with all supported host features ";
+#endif
}
static const TypeInfo host_x86_cpu_type_info = {
/* Print all cpuid feature names in featureset
*/
-static void listflags(FILE *f, fprintf_function print, const char **featureset)
+static void listflags(FILE *f, fprintf_function print, GList *features)
{
- int bit;
- bool first = true;
-
- for (bit = 0; bit < 32; bit++) {
- if (featureset[bit]) {
- print(f, "%s%s", first ? "" : " ", featureset[bit]);
- first = false;
+ size_t len = 0;
+ GList *tmp;
+
+ for (tmp = features; tmp; tmp = tmp->next) {
+ const char *name = tmp->data;
+ if ((len + strlen(name) + 1) >= 75) {
+ print(f, "\n");
+ len = 0;
}
+ print(f, "%s%s", len == 0 ? " " : " ", name);
+ len += strlen(name) + 1;
}
+ print(f, "\n");
}
/* Sort alphabetically by type name, respecting X86CPUClass::ordering. */
ObjectClass *class_b = (ObjectClass *)b;
X86CPUClass *cc_a = X86_CPU_CLASS(class_a);
X86CPUClass *cc_b = X86_CPU_CLASS(class_b);
- const char *name_a, *name_b;
+ char *name_a, *name_b;
+ int ret;
if (cc_a->ordering != cc_b->ordering) {
- return cc_a->ordering - cc_b->ordering;
+ ret = cc_a->ordering - cc_b->ordering;
} else {
- name_a = object_class_get_name(class_a);
- name_b = object_class_get_name(class_b);
- return strcmp(name_a, name_b);
+ name_a = x86_cpu_class_get_model_name(cc_a);
+ name_b = x86_cpu_class_get_model_name(cc_b);
+ ret = strcmp(name_a, name_b);
+ g_free(name_a);
+ g_free(name_b);
}
+ return ret;
}
static GSList *get_sorted_cpu_model_list(void)
desc = cc->cpu_def->model_id;
}
- (*s->cpu_fprintf)(s->file, "x86 %16s %-48s\n",
+ (*s->cpu_fprintf)(s->file, "x86 %-20s %-48s\n",
name, desc);
g_free(name);
}
/* list available CPU models and flags */
void x86_cpu_list(FILE *f, fprintf_function cpu_fprintf)
{
- int i;
+ int i, j;
CPUListState s = {
.file = f,
.cpu_fprintf = cpu_fprintf,
};
GSList *list;
+ GList *names = NULL;
(*cpu_fprintf)(f, "Available CPUs:\n");
list = get_sorted_cpu_model_list();
g_slist_foreach(list, x86_cpu_list_entry, &s);
g_slist_free(list);
- (*cpu_fprintf)(f, "\nRecognized CPUID flags:\n");
+ names = NULL;
for (i = 0; i < ARRAY_SIZE(feature_word_info); i++) {
FeatureWordInfo *fw = &feature_word_info[i];
-
- (*cpu_fprintf)(f, " ");
- listflags(f, cpu_fprintf, fw->feat_names);
- (*cpu_fprintf)(f, "\n");
+ for (j = 0; j < 32; j++) {
+ if (fw->feat_names[j]) {
+ names = g_list_append(names, (gpointer)fw->feat_names[j]);
+ }
+ }
}
+
+ names = g_list_sort(names, (GCompareFunc)strcmp);
+
+ (*cpu_fprintf)(f, "\nRecognized CPUID flags:\n");
+ listflags(f, cpu_fprintf, names);
+ (*cpu_fprintf)(f, "\n");
+ g_list_free(names);
}
static void x86_cpu_definition_entry(gpointer data, gpointer user_data)
env->features[w] = def->features[w];
}
+ /* legacy-cache defaults to 'off' if CPU model provides cache info */
+ cpu->legacy_cache = !def->cache_info;
+
/* Special cases not set in the X86CPUDefinition structs: */
/* TODO: in-kernel irqchip for hvf */
if (kvm_enabled()) {
xc = x86_cpu_from_model(model->name,
model->has_props ?
- qobject_to_qdict(model->props) :
+ qobject_to(QDict, model->props) :
NULL, &err);
if (err) {
goto out;
if (!cpu->enable_l3_cache) {
*ecx = 0;
} else {
- *ecx = L3_N_DESCRIPTOR;
+ *ecx = cpuid2_cache_descriptor(env->cache_info_cpuid2.l3_cache);
}
- *edx = (L1D_DESCRIPTOR << 16) | \
- (L1I_DESCRIPTOR << 8) | \
- (L2_DESCRIPTOR);
+ *edx = (cpuid2_cache_descriptor(env->cache_info_cpuid2.l1d_cache) << 16) |
+ (cpuid2_cache_descriptor(env->cache_info_cpuid2.l1i_cache) << 8) |
+ (cpuid2_cache_descriptor(env->cache_info_cpuid2.l2_cache));
break;
case 4:
/* cache info: needed for Core compatibility */
if (cpu->cache_info_passthrough) {
host_cpuid(index, count, eax, ebx, ecx, edx);
+ /* QEMU gives out its own APIC IDs, never pass down bits 31..26. */
*eax &= ~0xFC000000;
+ if ((*eax & 31) && cs->nr_cores > 1) {
+ *eax |= (cs->nr_cores - 1) << 26;
+ }
} else {
*eax = 0;
switch (count) {
case 0: /* L1 dcache info */
- *eax |= CPUID_4_TYPE_DCACHE | \
- CPUID_4_LEVEL(1) | \
- CPUID_4_SELF_INIT_LEVEL;
- *ebx = (L1D_LINE_SIZE - 1) | \
- ((L1D_PARTITIONS - 1) << 12) | \
- ((L1D_ASSOCIATIVITY - 1) << 22);
- *ecx = L1D_SETS - 1;
- *edx = CPUID_4_NO_INVD_SHARING;
+ encode_cache_cpuid4(env->cache_info_cpuid4.l1d_cache,
+ 1, cs->nr_cores,
+ eax, ebx, ecx, edx);
break;
case 1: /* L1 icache info */
- *eax |= CPUID_4_TYPE_ICACHE | \
- CPUID_4_LEVEL(1) | \
- CPUID_4_SELF_INIT_LEVEL;
- *ebx = (L1I_LINE_SIZE - 1) | \
- ((L1I_PARTITIONS - 1) << 12) | \
- ((L1I_ASSOCIATIVITY - 1) << 22);
- *ecx = L1I_SETS - 1;
- *edx = CPUID_4_NO_INVD_SHARING;
+ encode_cache_cpuid4(env->cache_info_cpuid4.l1i_cache,
+ 1, cs->nr_cores,
+ eax, ebx, ecx, edx);
break;
case 2: /* L2 cache info */
- *eax |= CPUID_4_TYPE_UNIFIED | \
- CPUID_4_LEVEL(2) | \
- CPUID_4_SELF_INIT_LEVEL;
- if (cs->nr_threads > 1) {
- *eax |= (cs->nr_threads - 1) << 14;
- }
- *ebx = (L2_LINE_SIZE - 1) | \
- ((L2_PARTITIONS - 1) << 12) | \
- ((L2_ASSOCIATIVITY - 1) << 22);
- *ecx = L2_SETS - 1;
- *edx = CPUID_4_NO_INVD_SHARING;
+ encode_cache_cpuid4(env->cache_info_cpuid4.l2_cache,
+ cs->nr_threads, cs->nr_cores,
+ eax, ebx, ecx, edx);
break;
case 3: /* L3 cache info */
- if (!cpu->enable_l3_cache) {
- *eax = 0;
- *ebx = 0;
- *ecx = 0;
- *edx = 0;
+ pkg_offset = apicid_pkg_offset(cs->nr_cores, cs->nr_threads);
+ if (cpu->enable_l3_cache) {
+ encode_cache_cpuid4(env->cache_info_cpuid4.l3_cache,
+ (1 << pkg_offset), cs->nr_cores,
+ eax, ebx, ecx, edx);
break;
}
- *eax |= CPUID_4_TYPE_UNIFIED | \
- CPUID_4_LEVEL(3) | \
- CPUID_4_SELF_INIT_LEVEL;
- pkg_offset = apicid_pkg_offset(cs->nr_cores, cs->nr_threads);
- *eax |= ((1 << pkg_offset) - 1) << 14;
- *ebx = (L3_N_LINE_SIZE - 1) | \
- ((L3_N_PARTITIONS - 1) << 12) | \
- ((L3_N_ASSOCIATIVITY - 1) << 22);
- *ecx = L3_N_SETS - 1;
- *edx = CPUID_4_INCLUSIVE | CPUID_4_COMPLEX_IDX;
- break;
+ /* fall through */
default: /* end of info */
- *eax = 0;
- *ebx = 0;
- *ecx = 0;
- *edx = 0;
+ *eax = *ebx = *ecx = *edx = 0;
break;
}
}
-
- /* QEMU gives out its own APIC IDs, never pass down bits 31..26. */
- if ((*eax & 31) && cs->nr_cores > 1) {
- *eax |= (cs->nr_cores - 1) << 26;
- }
break;
case 5:
- /* mwait info: needed for Core compatibility */
- *eax = 0; /* Smallest monitor-line size in bytes */
- *ebx = 0; /* Largest monitor-line size in bytes */
- *ecx = CPUID_MWAIT_EMX | CPUID_MWAIT_IBE;
- *edx = 0;
+ /* MONITOR/MWAIT Leaf */
+ *eax = cpu->mwait.eax; /* Smallest monitor-line size in bytes */
+ *ebx = cpu->mwait.ebx; /* Largest monitor-line size in bytes */
+ *ecx = cpu->mwait.ecx; /* flags */
+ *edx = cpu->mwait.edx; /* mwait substates */
break;
case 6:
/* Thermal and Power Leaf */
(L1_ITLB_2M_ASSOC << 8) | (L1_ITLB_2M_ENTRIES);
*ebx = (L1_DTLB_4K_ASSOC << 24) | (L1_DTLB_4K_ENTRIES << 16) | \
(L1_ITLB_4K_ASSOC << 8) | (L1_ITLB_4K_ENTRIES);
- *ecx = (L1D_SIZE_KB_AMD << 24) | (L1D_ASSOCIATIVITY_AMD << 16) | \
- (L1D_LINES_PER_TAG << 8) | (L1D_LINE_SIZE);
- *edx = (L1I_SIZE_KB_AMD << 24) | (L1I_ASSOCIATIVITY_AMD << 16) | \
- (L1I_LINES_PER_TAG << 8) | (L1I_LINE_SIZE);
+ *ecx = encode_cache_cpuid80000005(env->cache_info_amd.l1d_cache);
+ *edx = encode_cache_cpuid80000005(env->cache_info_amd.l1i_cache);
break;
case 0x80000006:
/* cache info (L2 cache) */
(L2_DTLB_4K_ENTRIES << 16) | \
(AMD_ENC_ASSOC(L2_ITLB_4K_ASSOC) << 12) | \
(L2_ITLB_4K_ENTRIES);
- *ecx = (L2_SIZE_KB_AMD << 16) | \
- (AMD_ENC_ASSOC(L2_ASSOCIATIVITY) << 12) | \
- (L2_LINES_PER_TAG << 8) | (L2_LINE_SIZE);
- if (!cpu->enable_l3_cache) {
- *edx = ((L3_SIZE_KB / 512) << 18) | \
- (AMD_ENC_ASSOC(L3_ASSOCIATIVITY) << 12) | \
- (L3_LINES_PER_TAG << 8) | (L3_LINE_SIZE);
- } else {
- *edx = ((L3_N_SIZE_KB_AMD / 512) << 18) | \
- (AMD_ENC_ASSOC(L3_N_ASSOCIATIVITY) << 12) | \
- (L3_N_LINES_PER_TAG << 8) | (L3_N_LINE_SIZE);
- }
+ encode_cache_cpuid80000006(env->cache_info_amd.l2_cache,
+ cpu->enable_l3_cache ?
+ env->cache_info_amd.l3_cache : NULL,
+ ecx, edx);
break;
case 0x80000007:
*eax = 0;
*edx = 0;
}
break;
+ case 0x8000001D:
+ *eax = 0;
+ switch (count) {
+ case 0: /* L1 dcache info */
+ encode_cache_cpuid8000001d(env->cache_info_amd.l1d_cache, cs,
+ eax, ebx, ecx, edx);
+ break;
+ case 1: /* L1 icache info */
+ encode_cache_cpuid8000001d(env->cache_info_amd.l1i_cache, cs,
+ eax, ebx, ecx, edx);
+ break;
+ case 2: /* L2 cache info */
+ encode_cache_cpuid8000001d(env->cache_info_amd.l2_cache, cs,
+ eax, ebx, ecx, edx);
+ break;
+ case 3: /* L3 cache info */
+ encode_cache_cpuid8000001d(env->cache_info_amd.l3_cache, cs,
+ eax, ebx, ecx, edx);
+ break;
+ default: /* end of info */
+ *eax = *ebx = *ecx = *edx = 0;
+ break;
+ }
+ break;
+ case 0x8000001E:
+ assert(cpu->core_id <= 255);
+ encode_topo_cpuid8000001e(cs, cpu,
+ eax, ebx, ecx, edx);
+ break;
case 0xC0000000:
*eax = env->cpuid_xlevel2;
*ebx = 0;
*/
env->features[w] |=
x86_cpu_get_supported_feature_word(w, cpu->migratable) &
- ~env->user_features[w];
+ ~env->user_features[w] & \
+ ~feature_word_info[w].no_autoenable_flags;
}
}
((eax_1 & INTEL_PT_ADDR_RANGES_NUM_MASK) <
INTEL_PT_ADDR_RANGES_NUM) ||
((ebx_1 & (INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP)) !=
- (INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP))) {
+ (INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP)) ||
+ (ecx_0 & INTEL_PT_IP_LIP)) {
/*
* Processor Trace capabilities aren't configurable, so if the
* host can't emulate the capabilities we report on
Error *local_err = NULL;
static bool ht_warned;
- if (xcc->host_cpuid_required && !accel_uses_host_cpuid()) {
- char *name = x86_cpu_class_get_model_name(xcc);
- error_setg(&local_err, "CPU model '%s' requires KVM", name);
- g_free(name);
- goto out;
+ if (xcc->host_cpuid_required) {
+ if (!accel_uses_host_cpuid()) {
+ char *name = x86_cpu_class_get_model_name(xcc);
+ error_setg(&local_err, "CPU model '%s' requires KVM", name);
+ g_free(name);
+ goto out;
+ }
+
+ if (enable_cpu_pm) {
+ host_cpuid(5, 0, &cpu->mwait.eax, &cpu->mwait.ebx,
+ &cpu->mwait.ecx, &cpu->mwait.edx);
+ env->features[FEAT_1_ECX] |= CPUID_EXT_MONITOR;
+ }
}
+ /* mwait extended info: needed for Core compatibility */
+ /* We always wake on interrupt even if host does not have the capability */
+ cpu->mwait.ecx |= CPUID_MWAIT_EMX | CPUID_MWAIT_IBE;
+
if (cpu->apic_id == UNASSIGNED_APIC_ID) {
error_setg(errp, "apic-id property was not initialized properly");
return;
cpu->phys_bits = 32;
}
}
+
+ /* Cache information initialization */
+ if (!cpu->legacy_cache) {
+ if (!xcc->cpu_def || !xcc->cpu_def->cache_info) {
+ char *name = x86_cpu_class_get_model_name(xcc);
+ error_setg(errp,
+ "CPU model '%s' doesn't support legacy-cache=off", name);
+ g_free(name);
+ return;
+ }
+ env->cache_info_cpuid2 = env->cache_info_cpuid4 = env->cache_info_amd =
+ *xcc->cpu_def->cache_info;
+ } else {
+ /* Build legacy cache information */
+ env->cache_info_cpuid2.l1d_cache = &legacy_l1d_cache;
+ env->cache_info_cpuid2.l1i_cache = &legacy_l1i_cache;
+ env->cache_info_cpuid2.l2_cache = &legacy_l2_cache_cpuid2;
+ env->cache_info_cpuid2.l3_cache = &legacy_l3_cache;
+
+ env->cache_info_cpuid4.l1d_cache = &legacy_l1d_cache;
+ env->cache_info_cpuid4.l1i_cache = &legacy_l1i_cache;
+ env->cache_info_cpuid4.l2_cache = &legacy_l2_cache;
+ env->cache_info_cpuid4.l3_cache = &legacy_l3_cache;
+
+ env->cache_info_amd.l1d_cache = &legacy_l1d_cache_amd;
+ env->cache_info_amd.l1i_cache = &legacy_l1i_cache_amd;
+ env->cache_info_amd.l2_cache = &legacy_l2_cache_amd;
+ env->cache_info_amd.l3_cache = &legacy_l3_cache;
+ }
+
+
cpu_exec_realizefn(cs, &local_err);
if (local_err != NULL) {
error_propagate(errp, local_err);
qemu_init_vcpu(cs);
- /* Only Intel CPUs support hyperthreading. Even though QEMU fixes this
- * issue by adjusting CPUID_0000_0001_EBX and CPUID_8000_0008_ECX
- * based on inputs (sockets,cores,threads), it is still better to gives
+ /*
+ * Most Intel and certain AMD CPUs support hyperthreading. Even though QEMU
+ * fixes this issue by adjusting CPUID_0000_0001_EBX and CPUID_8000_0008_ECX
+ * based on inputs (sockets,cores,threads), it is still better to give
* users a warning.
*
* NOTE: the following code has to follow qemu_init_vcpu(). Otherwise
* cs->nr_threads hasn't be populated yet and the checking is incorrect.
*/
- if (!IS_INTEL_CPU(env) && cs->nr_threads > 1 && !ht_warned) {
- error_report("AMD CPU doesn't support hyperthreading. Please configure"
- " -smp options properly.");
+ if (IS_AMD_CPU(env) &&
+ !(env->features[FEAT_8000_0001_ECX] & CPUID_EXT3_TOPOEXT) &&
+ cs->nr_threads > 1 && !ht_warned) {
+ error_report("This family of AMD CPU doesn't support "
+ "hyperthreading(%d). Please configure -smp "
+ "options properly or try enabling topoext feature.",
+ cs->nr_threads);
ht_warned = true;
}
DEFINE_PROP_BOOL("hv-runtime", X86CPU, hyperv_runtime, false),
DEFINE_PROP_BOOL("hv-synic", X86CPU, hyperv_synic, false),
DEFINE_PROP_BOOL("hv-stimer", X86CPU, hyperv_stimer, false),
+ DEFINE_PROP_BOOL("hv-frequencies", X86CPU, hyperv_frequencies, false),
+ DEFINE_PROP_BOOL("hv-reenlightenment", X86CPU, hyperv_reenlightenment, false),
+ DEFINE_PROP_BOOL("hv-tlbflush", X86CPU, hyperv_tlbflush, false),
DEFINE_PROP_BOOL("check", X86CPU, check_cpuid, true),
DEFINE_PROP_BOOL("enforce", X86CPU, enforce_cpuid, false),
DEFINE_PROP_BOOL("kvm", X86CPU, expose_kvm, true),
false),
DEFINE_PROP_BOOL("vmware-cpuid-freq", X86CPU, vmware_cpuid_freq, true),
DEFINE_PROP_BOOL("tcg-cpuid", X86CPU, expose_tcg, true),
+ DEFINE_PROP_BOOL("x-migrate-smi-count", X86CPU, migrate_smi_count,
+ true),
+ /*
+ * lecacy_cache defaults to true unless the CPU model provides its
+ * own cache information (see x86_cpu_load_def()).
+ */
+ DEFINE_PROP_BOOL("legacy-cache", X86CPU, legacy_cache, true),
/*
* From "Requirements for Implementing the Microsoft
projects / qemu.git / blobdiff