diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/block/aio.h | 59 | ||||
| -rw-r--r-- | include/exec/cpu-defs.h | 3 | ||||
| -rw-r--r-- | include/exec/cpu_ldst.h | 30 | ||||
| -rw-r--r-- | include/exec/cpu_ldst_template.h | 25 | ||||
| -rw-r--r-- | include/exec/exec-all.h | 8 | ||||
| -rw-r--r-- | include/exec/memory.h | 4 | ||||
| -rw-r--r-- | include/exec/ram_addr.h | 1 | ||||
| -rw-r--r-- | include/hw/hotplug.h | 11 | ||||
| -rw-r--r-- | include/hw/hyperv/hyperv-proto.h | 130 | ||||
| -rw-r--r-- | include/hw/hyperv/hyperv.h | 83 | ||||
| -rw-r--r-- | include/hw/i386/pc.h | 8 | ||||
| -rw-r--r-- | include/migration/colo.h | 11 | ||||
| -rw-r--r-- | include/net/filter.h | 5 | ||||
| -rw-r--r-- | include/qemu/atomic128.h | 153 | ||||
| -rw-r--r-- | include/qemu/compiler.h | 11 | ||||
| -rw-r--r-- | include/qemu/osdep.h | 12 | ||||
| -rw-r--r-- | include/qemu/timer.h | 127 | ||||
| -rw-r--r-- | include/sysemu/hvf.h | 4 | ||||
| -rw-r--r-- | include/sysemu/replay.h | 10 |
19 files changed, 588 insertions, 107 deletions
diff --git a/include/block/aio.h b/include/block/aio.h index f08630c6e5..0ca25dfec6 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -388,18 +388,41 @@ struct LinuxAioState *aio_setup_linux_aio(AioContext *ctx, Error **errp); struct LinuxAioState *aio_get_linux_aio(AioContext *ctx); /** - * aio_timer_new: + * aio_timer_new_with_attrs: * @ctx: the aio context * @type: the clock type * @scale: the scale + * @attributes: 0, or one to multiple OR'ed QEMU_TIMER_ATTR_<id> values + * to assign * @cb: the callback to call on timer expiry * @opaque: the opaque pointer to pass to the callback * - * Allocate a new timer attached to the context @ctx. + * Allocate a new timer (with attributes) attached to the context @ctx. * The function is responsible for memory allocation. * - * The preferred interface is aio_timer_init. Use that - * unless you really need dynamic memory allocation. + * The preferred interface is aio_timer_init or aio_timer_init_with_attrs. + * Use that unless you really need dynamic memory allocation. + * + * Returns: a pointer to the new timer + */ +static inline QEMUTimer *aio_timer_new_with_attrs(AioContext *ctx, + QEMUClockType type, + int scale, int attributes, + QEMUTimerCB *cb, void *opaque) +{ + return timer_new_full(&ctx->tlg, type, scale, attributes, cb, opaque); +} + +/** + * aio_timer_new: + * @ctx: the aio context + * @type: the clock type + * @scale: the scale + * @cb: the callback to call on timer expiry + * @opaque: the opaque pointer to pass to the callback + * + * Allocate a new timer attached to the context @ctx. + * See aio_timer_new_with_attrs for details. * * Returns: a pointer to the new timer */ @@ -407,7 +430,29 @@ static inline QEMUTimer *aio_timer_new(AioContext *ctx, QEMUClockType type, int scale, QEMUTimerCB *cb, void *opaque) { - return timer_new_tl(ctx->tlg.tl[type], scale, cb, opaque); + return timer_new_full(&ctx->tlg, type, scale, 0, cb, opaque); +} + +/** + * aio_timer_init_with_attrs: + * @ctx: the aio context + * @ts: the timer + * @type: the clock type + * @scale: the scale + * @attributes: 0, or one to multiple OR'ed QEMU_TIMER_ATTR_<id> values + * to assign + * @cb: the callback to call on timer expiry + * @opaque: the opaque pointer to pass to the callback + * + * Initialise a new timer (with attributes) attached to the context @ctx. + * The caller is responsible for memory allocation. + */ +static inline void aio_timer_init_with_attrs(AioContext *ctx, + QEMUTimer *ts, QEMUClockType type, + int scale, int attributes, + QEMUTimerCB *cb, void *opaque) +{ + timer_init_full(ts, &ctx->tlg, type, scale, attributes, cb, opaque); } /** @@ -420,14 +465,14 @@ static inline QEMUTimer *aio_timer_new(AioContext *ctx, QEMUClockType type, * @opaque: the opaque pointer to pass to the callback * * Initialise a new timer attached to the context @ctx. - * The caller is responsible for memory allocation. + * See aio_timer_init_with_attrs for details. */ static inline void aio_timer_init(AioContext *ctx, QEMUTimer *ts, QEMUClockType type, int scale, QEMUTimerCB *cb, void *opaque) { - timer_init_tl(ts, ctx->tlg.tl[type], scale, cb, opaque); + timer_init_full(ts, &ctx->tlg, type, scale, 0, cb, opaque); } /** diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index a171ffc1a4..4ff62f32bf 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -24,6 +24,7 @@ #endif #include "qemu/host-utils.h" +#include "qemu/thread.h" #include "qemu/queue.h" #ifdef CONFIG_TCG #include "tcg-target.h" @@ -142,6 +143,8 @@ typedef struct CPUIOTLBEntry { #define CPU_COMMON_TLB \ /* The meaning of the MMU modes is defined in the target code. */ \ + /* tlb_lock serializes updates to tlb_table and tlb_v_table */ \ + QemuSpin tlb_lock; \ CPUTLBEntry tlb_table[NB_MMU_MODES][CPU_TLB_SIZE]; \ CPUTLBEntry tlb_v_table[NB_MMU_MODES][CPU_VTLB_SIZE]; \ CPUIOTLBEntry iotlb[NB_MMU_MODES][CPU_TLB_SIZE]; \ diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index 41ed0526e2..959068495a 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -126,6 +126,29 @@ extern __thread uintptr_t helper_retaddr; /* The memory helpers for tcg-generated code need tcg_target_long etc. */ #include "tcg.h" +static inline target_ulong tlb_addr_write(const CPUTLBEntry *entry) +{ +#if TCG_OVERSIZED_GUEST + return entry->addr_write; +#else + return atomic_read(&entry->addr_write); +#endif +} + +/* Find the TLB index corresponding to the mmu_idx + address pair. */ +static inline uintptr_t tlb_index(CPUArchState *env, uintptr_t mmu_idx, + target_ulong addr) +{ + return (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1); +} + +/* Find the TLB entry corresponding to the mmu_idx + address pair. */ +static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx, + target_ulong addr) +{ + return &env->tlb_table[mmu_idx][tlb_index(env, mmu_idx, addr)]; +} + #ifdef MMU_MODE0_SUFFIX #define CPU_MMU_INDEX 0 #define MEMSUFFIX MMU_MODE0_SUFFIX @@ -416,8 +439,7 @@ static inline void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr, #if defined(CONFIG_USER_ONLY) return g2h(addr); #else - int index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1); - CPUTLBEntry *tlbentry = &env->tlb_table[mmu_idx][index]; + CPUTLBEntry *tlbentry = tlb_entry(env, mmu_idx, addr); abi_ptr tlb_addr; uintptr_t haddr; @@ -426,7 +448,7 @@ static inline void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr, tlb_addr = tlbentry->addr_read; break; case 1: - tlb_addr = tlbentry->addr_write; + tlb_addr = tlb_addr_write(tlbentry); break; case 2: tlb_addr = tlbentry->addr_code; @@ -445,7 +467,7 @@ static inline void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr, return NULL; } - haddr = addr + env->tlb_table[mmu_idx][index].addend; + haddr = addr + tlbentry->addend; return (void *)haddr; #endif /* defined(CONFIG_USER_ONLY) */ } diff --git a/include/exec/cpu_ldst_template.h b/include/exec/cpu_ldst_template.h index 4db2302962..0f061d47ef 100644 --- a/include/exec/cpu_ldst_template.h +++ b/include/exec/cpu_ldst_template.h @@ -81,7 +81,7 @@ glue(glue(glue(cpu_ld, USUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, target_ulong ptr, uintptr_t retaddr) { - int page_index; + CPUTLBEntry *entry; RES_TYPE res; target_ulong addr; int mmu_idx; @@ -94,15 +94,15 @@ glue(glue(glue(cpu_ld, USUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, #endif addr = ptr; - page_index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1); mmu_idx = CPU_MMU_INDEX; - if (unlikely(env->tlb_table[mmu_idx][page_index].ADDR_READ != + entry = tlb_entry(env, mmu_idx, addr); + if (unlikely(entry->ADDR_READ != (addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) { oi = make_memop_idx(SHIFT, mmu_idx); res = glue(glue(helper_ret_ld, URETSUFFIX), MMUSUFFIX)(env, addr, oi, retaddr); } else { - uintptr_t hostaddr = addr + env->tlb_table[mmu_idx][page_index].addend; + uintptr_t hostaddr = addr + entry->addend; res = glue(glue(ld, USUFFIX), _p)((uint8_t *)hostaddr); } return res; @@ -120,7 +120,8 @@ glue(glue(glue(cpu_lds, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, target_ulong ptr, uintptr_t retaddr) { - int res, page_index; + CPUTLBEntry *entry; + int res; target_ulong addr; int mmu_idx; TCGMemOpIdx oi; @@ -132,15 +133,15 @@ glue(glue(glue(cpu_lds, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, #endif addr = ptr; - page_index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1); mmu_idx = CPU_MMU_INDEX; - if (unlikely(env->tlb_table[mmu_idx][page_index].ADDR_READ != + entry = tlb_entry(env, mmu_idx, addr); + if (unlikely(entry->ADDR_READ != (addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) { oi = make_memop_idx(SHIFT, mmu_idx); res = (DATA_STYPE)glue(glue(helper_ret_ld, SRETSUFFIX), MMUSUFFIX)(env, addr, oi, retaddr); } else { - uintptr_t hostaddr = addr + env->tlb_table[mmu_idx][page_index].addend; + uintptr_t hostaddr = addr + entry->addend; res = glue(glue(lds, SUFFIX), _p)((uint8_t *)hostaddr); } return res; @@ -162,7 +163,7 @@ glue(glue(glue(cpu_st, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, target_ulong ptr, RES_TYPE v, uintptr_t retaddr) { - int page_index; + CPUTLBEntry *entry; target_ulong addr; int mmu_idx; TCGMemOpIdx oi; @@ -174,15 +175,15 @@ glue(glue(glue(cpu_st, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, #endif addr = ptr; - page_index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1); mmu_idx = CPU_MMU_INDEX; - if (unlikely(env->tlb_table[mmu_idx][page_index].addr_write != + entry = tlb_entry(env, mmu_idx, addr); + if (unlikely(tlb_addr_write(entry) != (addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) { oi = make_memop_idx(SHIFT, mmu_idx); glue(glue(helper_ret_st, SUFFIX), MMUSUFFIX)(env, addr, v, oi, retaddr); } else { - uintptr_t hostaddr = addr + env->tlb_table[mmu_idx][page_index].addend; + uintptr_t hostaddr = addr + entry->addend; glue(glue(st, SUFFIX), _p)((uint8_t *)hostaddr, v); } } diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index 5f78125582..815e5b1e83 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -100,6 +100,11 @@ void cpu_address_space_init(CPUState *cpu, int asidx, #if !defined(CONFIG_USER_ONLY) && defined(CONFIG_TCG) /* cputlb.c */ /** + * tlb_init - initialize a CPU's TLB + * @cpu: CPU whose TLB should be initialized + */ +void tlb_init(CPUState *cpu); +/** * tlb_flush_page: * @cpu: CPU whose TLB should be flushed * @addr: virtual address of page to be flushed @@ -258,6 +263,9 @@ void tlb_set_page(CPUState *cpu, target_ulong vaddr, void probe_write(CPUArchState *env, target_ulong addr, int size, int mmu_idx, uintptr_t retaddr); #else +static inline void tlb_init(CPUState *cpu) +{ +} static inline void tlb_flush_page(CPUState *cpu, target_ulong addr) { } diff --git a/include/exec/memory.h b/include/exec/memory.h index 3a427aacf1..667466b8f3 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -419,9 +419,9 @@ struct MemoryListener { bool match_data, uint64_t data, EventNotifier *e); void (*eventfd_del)(MemoryListener *listener, MemoryRegionSection *section, bool match_data, uint64_t data, EventNotifier *e); - void (*coalesced_mmio_add)(MemoryListener *listener, MemoryRegionSection *section, + void (*coalesced_io_add)(MemoryListener *listener, MemoryRegionSection *section, hwaddr addr, hwaddr len); - void (*coalesced_mmio_del)(MemoryListener *listener, MemoryRegionSection *section, + void (*coalesced_io_del)(MemoryListener *listener, MemoryRegionSection *section, hwaddr addr, hwaddr len); /* Lower = earlier (during add), later (during del) */ unsigned priority; diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index 3abb639056..9ecd911c3e 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -27,6 +27,7 @@ struct RAMBlock { struct rcu_head rcu; struct MemoryRegion *mr; uint8_t *host; + uint8_t *colo_cache; /* For colo, VM's ram cache */ ram_addr_t offset; ram_addr_t used_length; ram_addr_t max_length; diff --git a/include/hw/hotplug.h b/include/hw/hotplug.h index 51541d63e1..1a0516a479 100644 --- a/include/hw/hotplug.h +++ b/include/hw/hotplug.h @@ -47,8 +47,6 @@ typedef void (*hotplug_fn)(HotplugHandler *plug_handler, * @parent: Opaque parent interface. * @pre_plug: pre plug callback called at start of device.realize(true) * @plug: plug callback called at end of device.realize(true). - * @post_plug: post plug callback called after device.realize(true) and device - * reset * @unplug_request: unplug request callback. * Used as a means to initiate device unplug for devices that * require asynchronous unplug handling. @@ -63,7 +61,6 @@ typedef struct HotplugHandlerClass { /* <public> */ hotplug_fn pre_plug; hotplug_fn plug; - void (*post_plug)(HotplugHandler *plug_handler, DeviceState *plugged_dev); hotplug_fn unplug_request; hotplug_fn unplug; } HotplugHandlerClass; @@ -87,14 +84,6 @@ void hotplug_handler_pre_plug(HotplugHandler *plug_handler, Error **errp); /** - * hotplug_handler_post_plug: - * - * Call #HotplugHandlerClass.post_plug callback of @plug_handler. - */ -void hotplug_handler_post_plug(HotplugHandler *plug_handler, - DeviceState *plugged_dev); - -/** * hotplug_handler_unplug_request: * * Calls #HotplugHandlerClass.unplug_request callback of @plug_handler. diff --git a/include/hw/hyperv/hyperv-proto.h b/include/hw/hyperv/hyperv-proto.h new file mode 100644 index 0000000000..21dc28aee9 --- /dev/null +++ b/include/hw/hyperv/hyperv-proto.h @@ -0,0 +1,130 @@ +/* + * Definitions for Hyper-V guest/hypervisor interaction + * + * Copyright (c) 2017-2018 Virtuozzo International GmbH. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef HW_HYPERV_HYPERV_PROTO_H +#define HW_HYPERV_HYPERV_PROTO_H + +#include "qemu/bitmap.h" + +/* + * Hypercall status code + */ +#define HV_STATUS_SUCCESS 0 +#define HV_STATUS_INVALID_HYPERCALL_CODE 2 +#define HV_STATUS_INVALID_HYPERCALL_INPUT 3 +#define HV_STATUS_INVALID_ALIGNMENT 4 +#define HV_STATUS_INVALID_PARAMETER 5 +#define HV_STATUS_INSUFFICIENT_MEMORY 11 +#define HV_STATUS_INVALID_PORT_ID 17 +#define HV_STATUS_INVALID_CONNECTION_ID 18 +#define HV_STATUS_INSUFFICIENT_BUFFERS 19 + +/* + * Hypercall numbers + */ +#define HV_POST_MESSAGE 0x005c +#define HV_SIGNAL_EVENT 0x005d +#define HV_HYPERCALL_FAST (1u << 16) + +/* + * Message size + */ +#define HV_MESSAGE_PAYLOAD_SIZE 240 + +/* + * Message types + */ +#define HV_MESSAGE_NONE 0x00000000 +#define HV_MESSAGE_VMBUS 0x00000001 +#define HV_MESSAGE_UNMAPPED_GPA 0x80000000 +#define HV_MESSAGE_GPA_INTERCEPT 0x80000001 +#define HV_MESSAGE_TIMER_EXPIRED 0x80000010 +#define HV_MESSAGE_INVALID_VP_REGISTER_VALUE 0x80000020 +#define HV_MESSAGE_UNRECOVERABLE_EXCEPTION 0x80000021 +#define HV_MESSAGE_UNSUPPORTED_FEATURE 0x80000022 +#define HV_MESSAGE_EVENTLOG_BUFFERCOMPLETE 0x80000040 +#define HV_MESSAGE_X64_IOPORT_INTERCEPT 0x80010000 +#define HV_MESSAGE_X64_MSR_INTERCEPT 0x80010001 +#define HV_MESSAGE_X64_CPUID_INTERCEPT 0x80010002 +#define HV_MESSAGE_X64_EXCEPTION_INTERCEPT 0x80010003 +#define HV_MESSAGE_X64_APIC_EOI 0x80010004 +#define HV_MESSAGE_X64_LEGACY_FP_ERROR 0x80010005 + +/* + * Message flags + */ +#define HV_MESSAGE_FLAG_PENDING 0x1 + +/* + * Number of synthetic interrupts + */ +#define HV_SINT_COUNT 16 + +/* + * Event flags number per SINT + */ +#define HV_EVENT_FLAGS_COUNT (256 * 8) + +/* + * Connection id valid bits + */ +#define HV_CONNECTION_ID_MASK 0x00ffffff + +/* + * Input structure for POST_MESSAGE hypercall + */ +struct hyperv_post_message_input { + uint32_t connection_id; + uint32_t _reserved; + uint32_t message_type; + uint32_t payload_size; + uint8_t payload[HV_MESSAGE_PAYLOAD_SIZE]; +}; + +/* + * Input structure for SIGNAL_EVENT hypercall + */ +struct hyperv_signal_event_input { + uint32_t connection_id; + uint16_t flag_number; + uint16_t _reserved_zero; +}; + +/* + * SynIC message structures + */ +struct hyperv_message_header { + uint32_t message_type; + uint8_t payload_size; + uint8_t message_flags; /* HV_MESSAGE_FLAG_XX */ + uint8_t _reserved[2]; + uint64_t sender; +}; + +struct hyperv_message { + struct hyperv_message_header header; + uint8_t payload[HV_MESSAGE_PAYLOAD_SIZE]; +}; + +struct hyperv_message_page { + struct hyperv_message slot[HV_SINT_COUNT]; +}; + +/* + * SynIC event flags structures + */ +struct hyperv_event_flags { + DECLARE_BITMAP(flags, HV_EVENT_FLAGS_COUNT); +}; + +struct hyperv_event_flags_page { + struct hyperv_event_flags slot[HV_SINT_COUNT]; +}; + +#endif diff --git a/include/hw/hyperv/hyperv.h b/include/hw/hyperv/hyperv.h new file mode 100644 index 0000000000..597381cb01 --- /dev/null +++ b/include/hw/hyperv/hyperv.h @@ -0,0 +1,83 @@ +/* + * Hyper-V guest/hypervisor interaction + * + * Copyright (c) 2015-2018 Virtuozzo International GmbH. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef HW_HYPERV_HYPERV_H +#define HW_HYPERV_HYPERV_H + +#include "cpu-qom.h" +#include "hw/hyperv/hyperv-proto.h" + +typedef struct HvSintRoute HvSintRoute; + +/* + * Callback executed in a bottom-half when the status of posting the message + * becomes known, before unblocking the connection for further messages + */ +typedef void (*HvSintMsgCb)(void *data, int status); + +HvSintRoute *hyperv_sint_route_new(uint32_t vp_index, uint32_t sint, + HvSintMsgCb cb, void *cb_data); +void hyperv_sint_route_ref(HvSintRoute *sint_route); +void hyperv_sint_route_unref(HvSintRoute *sint_route); + +int hyperv_sint_route_set_sint(HvSintRoute *sint_route); + +/* + * Submit a message to be posted in vcpu context. If the submission succeeds, + * the status of posting the message is reported via the callback associated + * with the @sint_route; until then no more messages are accepted. + */ +int hyperv_post_msg(HvSintRoute *sint_route, struct hyperv_message *msg); +/* + * Set event flag @eventno, and signal the SINT if the flag has changed. + */ +int hyperv_set_event_flag(HvSintRoute *sint_route, unsigned eventno); + +/* + * Handler for messages arriving from the guest via HV_POST_MESSAGE hypercall. + * Executed in vcpu context. + */ +typedef uint16_t (*HvMsgHandler)(const struct hyperv_post_message_input *msg, + void *data); +/* + * Associate @handler with the message connection @conn_id, such that @handler + * is called with @data when the guest executes HV_POST_MESSAGE hypercall on + * @conn_id. If @handler is NULL clear the association. + */ +int hyperv_set_msg_handler(uint32_t conn_id, HvMsgHandler handler, void *data); +/* + * Associate @notifier with the event connection @conn_id, such that @notifier + * is signaled when the guest executes HV_SIGNAL_EVENT hypercall on @conn_id. + * If @notifier is NULL clear the association. + */ +int hyperv_set_event_flag_handler(uint32_t conn_id, EventNotifier *notifier); + +/* + * Process HV_POST_MESSAGE hypercall: parse the data in the guest memory as + * specified in @param, and call the HvMsgHandler associated with the + * connection on the message contained therein. + */ +uint16_t hyperv_hcall_post_message(uint64_t param, bool fast); +/* + * Process HV_SIGNAL_EVENT hypercall: signal the EventNotifier associated with + * the connection as specified in @param. + */ +uint16_t hyperv_hcall_signal_event(uint64_t param, bool fast); + +static inline uint32_t hyperv_vp_index(CPUState *cs) +{ + return cs->cpu_index; +} + +void hyperv_synic_add(CPUState *cs); +void hyperv_synic_reset(CPUState *cs); +void hyperv_synic_update(CPUState *cs, bool enable, + hwaddr msg_page_addr, hwaddr event_page_addr); + +#endif diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index 6894f37df1..dfe6746692 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -294,6 +294,14 @@ int e820_add_entry(uint64_t, uint64_t, uint32_t); int e820_get_num_entries(void); bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *); +#define PC_COMPAT_3_0 \ + HW_COMPAT_3_0 \ + {\ + .driver = TYPE_X86_CPU,\ + .property = "x-hv-synic-kvm-only",\ + .value = "on",\ + } + #define PC_COMPAT_2_12 \ HW_COMPAT_2_12 \ {\ diff --git a/include/migration/colo.h b/include/migration/colo.h index 2fe48ad353..99ce17aca7 100644 --- a/include/migration/colo.h +++ b/include/migration/colo.h @@ -16,14 +16,21 @@ #include "qemu-common.h" #include "qapi/qapi-types-migration.h" +enum colo_event { + COLO_EVENT_NONE, + COLO_EVENT_CHECKPOINT, + COLO_EVENT_FAILOVER, +}; + void colo_info_init(void); void migrate_start_colo_process(MigrationState *s); bool migration_in_colo_state(void); /* loadvm */ -bool migration_incoming_enable_colo(void); -void migration_incoming_exit_colo(void); +void migration_incoming_enable_colo(void); +void migration_incoming_disable_colo(void); +bool migration_incoming_colo_enabled(void); void *colo_process_incoming_thread(void *opaque); bool migration_incoming_in_colo_state(void); diff --git a/include/net/filter.h b/include/net/filter.h index 435acd6f82..49da666ac0 100644 --- a/include/net/filter.h +++ b/include/net/filter.h @@ -38,6 +38,8 @@ typedef ssize_t (FilterReceiveIOV)(NetFilterState *nc, typedef void (FilterStatusChanged) (NetFilterState *nf, Error **errp); +typedef void (FilterHandleEvent) (NetFilterState *nf, int event, Error **errp); + typedef struct NetFilterClass { ObjectClass parent_class; @@ -45,6 +47,7 @@ typedef struct NetFilterClass { FilterSetup *setup; FilterCleanup *cleanup; FilterStatusChanged *status_changed; + FilterHandleEvent *handle_event; /* mandatory */ FilterReceiveIOV *receive_iov; } NetFilterClass; @@ -77,4 +80,6 @@ ssize_t qemu_netfilter_pass_to_next(NetClientState *sender, int iovcnt, void *opaque); +void colo_notify_filters_event(int event, Error **errp); + #endif /* QEMU_NET_FILTER_H */ diff --git a/include/qemu/atomic128.h b/include/qemu/atomic128.h new file mode 100644 index 0000000000..a6af22ff10 --- /dev/null +++ b/include/qemu/atomic128.h @@ -0,0 +1,153 @@ +/* + * Simple interface for 128-bit atomic operations. + * + * Copyright (C) 2018 Linaro, Ltd. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + * See docs/devel/atomics.txt for discussion about the guarantees each + * atomic primitive is meant to provide. + */ + +#ifndef QEMU_ATOMIC128_H +#define QEMU_ATOMIC128_H + +/* + * GCC is a house divided about supporting large atomic operations. + * + * For hosts that only have large compare-and-swap, a legalistic reading + * of the C++ standard means that one cannot implement __atomic_read on + * read-only memory, and thus all atomic operations must synchronize + * through libatomic. + * + * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=80878 + * + * This interpretation is not especially helpful for QEMU. + * For softmmu, all RAM is always read/write from the hypervisor. + * For user-only, if the guest doesn't implement such an __atomic_read + * then the host need not worry about it either. + * + * Moreover, using libatomic is not an option, because its interface is + * built for std::atomic<T>, and requires that *all* accesses to such an + * object go through the library. In our case we do not have an object + * in the C/C++ sense, but a view of memory as seen by the guest. + * The guest may issue a large atomic operation and then access those + * pieces using word-sized accesses. From the hypervisor, we have no + * way to connect those two actions. + * + * Therefore, special case each platform. + */ + +#if defined(CONFIG_ATOMIC128) +static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new) +{ + return atomic_cmpxchg__nocheck(ptr, cmp, new); +} +# define HAVE_CMPXCHG128 1 +#elif defined(CONFIG_CMPXCHG128) +static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new) +{ + return __sync_val_compare_and_swap_16(ptr, cmp, new); +} +# define HAVE_CMPXCHG128 1 +#elif defined(__aarch64__) +/* Through gcc 8, aarch64 has no support for 128-bit at all. */ +static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new) +{ + uint64_t cmpl = int128_getlo(cmp), cmph = int128_gethi(cmp); + uint64_t newl = int128_getlo(new), newh = int128_gethi(new); + uint64_t oldl, oldh; + uint32_t tmp; + + asm("0: ldaxp %[oldl], %[oldh], %[mem]\n\t" + "cmp %[oldl], %[cmpl]\n\t" + "ccmp %[oldh], %[cmph], #0, eq\n\t" + "b.ne 1f\n\t" + "stlxp %w[tmp], %[newl], %[newh], %[mem]\n\t" + "cbnz %w[tmp], 0b\n" + "1:" + : [mem] "+m"(*ptr), [tmp] "=&r"(tmp), + [oldl] "=&r"(oldl), [oldh] "=r"(oldh) + : [cmpl] "r"(cmpl), [cmph] "r"(cmph), + [newl] "r"(newl), [newh] "r"(newh) + : "memory", "cc"); + + return int128_make128(oldl, oldh); +} +# define HAVE_CMPXCHG128 1 +#else +/* Fallback definition that must be optimized away, or error. */ +Int128 QEMU_ERROR("unsupported atomic") + atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new); +# define HAVE_CMPXCHG128 0 +#endif /* Some definition for HAVE_CMPXCHG128 */ + + +#if defined(CONFIG_ATOMIC128) +static inline Int128 atomic16_read(Int128 *ptr) +{ + return atomic_read__nocheck(ptr); +} + +static inline void atomic16_set(Int128 *ptr, Int128 val) +{ + atomic_set__nocheck(ptr, val); +} + +# define HAVE_ATOMIC128 1 +#elif !defined(CONFIG_USER_ONLY) && defined(__aarch64__) +/* We can do better than cmpxchg for AArch64. */ +static inline Int128 atomic16_read(Int128 *ptr) +{ + uint64_t l, h; + uint32_t tmp; + + /* The load must be paired with the store to guarantee not tearing. */ + asm("0: ldxp %[l], %[h], %[mem]\n\t" + "stxp %w[tmp], %[l], %[h], %[mem]\n\t" + "cbnz %w[tmp], 0b" + : [mem] "+m"(*ptr), [tmp] "=r"(tmp), [l] "=r"(l), [h] "=r"(h)); + + return int128_make128(l, h); +} + +static inline void atomic16_set(Int128 *ptr, Int128 val) +{ + uint64_t l = int128_getlo(val), h = int128_gethi(val); + uint64_t t1, t2; + + /* Load into temporaries to acquire the exclusive access lock. */ + asm("0: ldxp %[t1], %[t2], %[mem]\n\t" + "stxp %w[t1], %[l], %[h], %[mem]\n\t" + "cbnz %w[t1], 0b" + : [mem] "+m"(*ptr), [t1] "=&r"(t1), [t2] "=&r"(t2) + : [l] "r"(l), [h] "r"(h)); +} + +# define HAVE_ATOMIC128 1 +#elif !defined(CONFIG_USER_ONLY) && HAVE_CMPXCHG128 +static inline Int128 atomic16_read(Int128 *ptr) +{ + /* Maybe replace 0 with 0, returning the old value. */ + return atomic16_cmpxchg(ptr, 0, 0); +} + +static inline void atomic16_set(Int128 *ptr, Int128 val) +{ + Int128 old = *ptr, cmp; + do { + cmp = old; + old = atomic16_cmpxchg(ptr, cmp, val); + } while (old != cmp); +} + +# define HAVE_ATOMIC128 1 +#else +/* Fallback definitions that must be optimized away, or error. */ +Int128 QEMU_ERROR("unsupported atomic") atomic16_read(Int128 *ptr); +void QEMU_ERROR("unsupported atomic") atomic16_set(Int128 *ptr, Int128 val); +# define HAVE_ATOMIC128 0 +#endif /* Some definition for HAVE_ATOMIC128 */ + +#endif /* QEMU_ATOMIC128_H */ diff --git a/include/qemu/compiler.h b/include/qemu/compiler.h index 66f8c241dc..6b92710487 100644 --- a/include/qemu/compiler.h +++ b/include/qemu/compiler.h @@ -146,6 +146,17 @@ # define QEMU_FLATTEN #endif +/* + * If __attribute__((error)) is present, use it to produce an error at + * compile time. Otherwise, one must wait for the linker to diagnose + * the missing symbol. + */ +#if __has_attribute(error) +# define QEMU_ERROR(X) __attribute__((error(X))) +#else +# define QEMU_ERROR(X) +#endif + /* Implement C11 _Generic via GCC builtins. Example: * * QEMU_GENERIC(x, (float, sinf), (long double, sinl), sin) (x) diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h index 4f8559e550..3bf48bcdec 100644 --- a/include/qemu/osdep.h +++ b/include/qemu/osdep.h @@ -123,6 +123,18 @@ extern int daemon(int, int); #include "qemu/typedefs.h" /* + * For mingw, as of v6.0.0, the function implementing the assert macro is + * not marked as noreturn, so the compiler cannot delete code following an + * assert(false) as unused. We rely on this within the code base to delete + * code that is unreachable when features are disabled. + * All supported versions of Glib's g_assert() satisfy this requirement. + */ +#ifdef __MINGW32__ +#undef assert +#define assert(x) g_assert(x) +#endif + +/* * According to waitpid man page: * WCOREDUMP * This macro is not specified in POSIX.1-2001 and is not diff --git a/include/qemu/timer.h b/include/qemu/timer.h index a005ed2692..a86330c987 100644 --- a/include/qemu/timer.h +++ b/include/qemu/timer.h @@ -2,6 +2,7 @@ #define QEMU_TIMER_H #include "qemu-common.h" +#include "qemu/bitops.h" #include "qemu/notify.h" #include "qemu/host-utils.h" @@ -42,14 +43,6 @@ * In icount mode, this clock counts nanoseconds while the virtual * machine is running. It is used to increase @QEMU_CLOCK_VIRTUAL * while the CPUs are sleeping and thus not executing instructions. - * - * @QEMU_CLOCK_VIRTUAL_EXT: virtual clock for external subsystems - * - * The virtual clock only runs during the emulation. It stops - * when the virtual machine is stopped. The timers for this clock - * do not recorded in rr mode, therefore this clock could be used - * for the subsystems that operate outside the guest core. - * */ typedef enum { @@ -57,10 +50,27 @@ typedef enum { QEMU_CLOCK_VIRTUAL = 1, QEMU_CLOCK_HOST = 2, QEMU_CLOCK_VIRTUAL_RT = 3, - QEMU_CLOCK_VIRTUAL_EXT = 4, QEMU_CLOCK_MAX } QEMUClockType; +/** + * QEMU Timer attributes: + * + * An individual timer may be given one or multiple attributes when initialized. + * Each attribute corresponds to one bit. Attributes modify the processing + * of timers when they fire. + * + * The following attributes are available: + * + * QEMU_TIMER_ATTR_EXTERNAL: drives external subsystem + * + * Timers with this attribute do not recorded in rr mode, therefore it could be + * used for the subsystems that operate outside the guest core. Applicable only + * with virtual clock type. + */ + +#define QEMU_TIMER_ATTR_EXTERNAL BIT(0) + typedef struct QEMUTimerList QEMUTimerList; struct QEMUTimerListGroup { @@ -76,6 +86,7 @@ struct QEMUTimer { QEMUTimerCB *cb; void *opaque; QEMUTimer *next; + int attributes; int scale; }; @@ -427,22 +438,27 @@ int64_t timerlistgroup_deadline_ns(QEMUTimerListGroup *tlg); */ /** - * timer_init_tl: + * timer_init_full: * @ts: the timer to be initialised - * @timer_list: the timer list to attach the timer to + * @timer_list_group: (optional) the timer list group to attach the timer to + * @type: the clock type to use * @scale: the scale value for the timer + * @attributes: 0, or one or more OR'ed QEMU_TIMER_ATTR_<id> values * @cb: the callback to be called when the timer expires * @opaque: the opaque pointer to be passed to the callback * - * Initialise a new timer and associate it with @timer_list. + * Initialise a timer with the given scale and attributes, + * and associate it with timer list for given clock @type in @timer_list_group + * (or default timer list group, if NULL). * The caller is responsible for allocating the memory. * * You need not call an explicit deinit call. Simply make * sure it is not on a list with timer_del. */ -void timer_init_tl(QEMUTimer *ts, - QEMUTimerList *timer_list, int scale, - QEMUTimerCB *cb, void *opaque); +void timer_init_full(QEMUTimer *ts, + QEMUTimerListGroup *timer_list_group, QEMUClockType type, + int scale, int attributes, + QEMUTimerCB *cb, void *opaque); /** * timer_init: @@ -454,14 +470,12 @@ void timer_init_tl(QEMUTimer *ts, * * Initialize a timer with the given scale on the default timer list * associated with the clock. - * - * You need not call an explicit deinit call. Simply make - * sure it is not on a list with timer_del. + * See timer_init_full for details. */ static inline void timer_init(QEMUTimer *ts, QEMUClockType type, int scale, QEMUTimerCB *cb, void *opaque) { - timer_init_tl(ts, main_loop_tlg.tl[type], scale, cb, opaque); + timer_init_full(ts, NULL, type, scale, 0, cb, opaque); } /** @@ -473,9 +487,7 @@ static inline void timer_init(QEMUTimer *ts, QEMUClockType type, int scale, * * Initialize a timer with nanosecond scale on the default timer list * associated with the clock. - * - * You need not call an explicit deinit call. Simply make - * sure it is not on a list with timer_del. + * See timer_init_full for details. */ static inline void timer_init_ns(QEMUTimer *ts, QEMUClockType type, QEMUTimerCB *cb, void *opaque) @@ -492,9 +504,7 @@ static inline void timer_init_ns(QEMUTimer *ts, QEMUClockType type, * * Initialize a timer with microsecond scale on the default timer list * associated with the clock. - * - * You need not call an explicit deinit call. Simply make - * sure it is not on a list with timer_del. + * See timer_init_full for details. */ static inline void timer_init_us(QEMUTimer *ts, QEMUClockType type, QEMUTimerCB *cb, void *opaque) @@ -511,9 +521,7 @@ static inline void timer_init_us(QEMUTimer *ts, QEMUClockType type, * * Initialize a timer with millisecond scale on the default timer list * associated with the clock. - * - * You need not call an explicit deinit call. Simply make - * sure it is not on a list with timer_del. + * See timer_init_full for details. */ static inline void timer_init_ms(QEMUTimer *ts, QEMUClockType type, QEMUTimerCB *cb, void *opaque) @@ -522,27 +530,37 @@ static inline void timer_init_ms(QEMUTimer *ts, QEMUClockType type, } /** - * timer_new_tl: - * @timer_list: the timer list to attach the timer to + * timer_new_full: + * @timer_list_group: (optional) the timer list group to attach the timer to + * @type: the clock type to use * @scale: the scale value for the timer + * @attributes: 0, or one or more OR'ed QEMU_TIMER_ATTR_<id> values * @cb: the callback to be called when the timer expires * @opaque: the opaque pointer to be passed to the callback * - * Create a new timer and associate it with @timer_list. + * Create a new timer with the given scale and attributes, + * and associate it with timer list for given clock @type in @timer_list_group + * (or default timer list group, if NULL). * The memory is allocated by the function. * * This is not the preferred interface unless you know you - * are going to call timer_free. Use timer_init instead. + * are going to call timer_free. Use timer_init or timer_init_full instead. + * + * The default timer list has one special feature: in icount mode, + * %QEMU_CLOCK_VIRTUAL timers are run in the vCPU thread. This is + * not true of other timer lists, which are typically associated + * with an AioContext---each of them runs its timer callbacks in its own + * AioContext thread. * * Returns: a pointer to the timer */ -static inline QEMUTimer *timer_new_tl(QEMUTimerList *timer_list, - int scale, - QEMUTimerCB *cb, - void *opaque) +static inline QEMUTimer *timer_new_full(QEMUTimerListGroup *timer_list_group, + QEMUClockType type, + int scale, int attributes, + QEMUTimerCB *cb, void *opaque) { QEMUTimer *ts = g_malloc0(sizeof(QEMUTimer)); - timer_init_tl(ts, timer_list, scale, cb, opaque); + timer_init_full(ts, timer_list_group, type, scale, attributes, cb, opaque); return ts; } @@ -553,21 +571,16 @@ static inline QEMUTimer *timer_new_tl(QEMUTimerList *timer_list, * @cb: the callback to be called when the timer expires * @opaque: the opaque pointer to be passed to the callback * - * Create a new timer and associate it with the default - * timer list for the clock type @type. - * - * The default timer list has one special feature: in icount mode, - * %QEMU_CLOCK_VIRTUAL timers are run in the vCPU thread. This is - * not true of other timer lists, which are typically associated - * with an AioContext---each of them runs its timer callbacks in its own - * AioContext thread. + * Create a new timer with the given scale, + * and associate it with the default timer list for the clock type @type. + * See timer_new_full for details. * * Returns: a pointer to the timer */ static inline QEMUTimer *timer_new(QEMUClockType type, int scale, QEMUTimerCB *cb, void *opaque) { - return timer_new_tl(main_loop_tlg.tl[type], scale, cb, opaque); + return timer_new_full(NULL, type, scale, 0, cb, opaque); } /** @@ -578,12 +591,7 @@ static inline QEMUTimer *timer_new(QEMUClockType type, int scale, * * Create a new timer with nanosecond scale on the default timer list * associated with the clock. - * - * The default timer list has one special feature: in icount mode, - * %QEMU_CLOCK_VIRTUAL timers are run in the vCPU thread. This is - * not true of other timer lists, which are typically associated - * with an AioContext---each of them runs its timer callbacks in its own - * AioContext thread. + * See timer_new_full for details. * * Returns: a pointer to the newly created timer */ @@ -599,14 +607,9 @@ static inline QEMUTimer *timer_new_ns(QEMUClockType type, QEMUTimerCB *cb, * @cb: the callback to call when the timer expires * @opaque: the opaque pointer to pass to the callback * - * The default timer list has one special feature: in icount mode, - * %QEMU_CLOCK_VIRTUAL timers are run in the vCPU thread. This is - * not true of other timer lists, which are typically associated - * with an AioContext---each of them runs its timer callbacks in its own - * AioContext thread. - * * Create a new timer with microsecond scale on the default timer list * associated with the clock. + * See timer_new_full for details. * * Returns: a pointer to the newly created timer */ @@ -622,14 +625,9 @@ static inline QEMUTimer *timer_new_us(QEMUClockType type, QEMUTimerCB *cb, * @cb: the callback to call when the timer expires * @opaque: the opaque pointer to pass to the callback * - * The default timer list has one special feature: in icount mode, - * %QEMU_CLOCK_VIRTUAL timers are run in the vCPU thread. This is - * not true of other timer lists, which are typically associated - * with an AioContext---each of them runs its timer callbacks in its own - * AioContext thread. - * * Create a new timer with millisecond scale on the default timer list * associated with the clock. + * See timer_new_full for details. * * Returns: a pointer to the newly created timer */ @@ -1046,7 +1044,6 @@ static inline int64_t profile_getclock(void) return get_clock(); } -extern int64_t tcg_time; extern int64_t dev_time; #endif diff --git a/include/sysemu/hvf.h b/include/sysemu/hvf.h index 241118845c..aaa51d2c51 100644 --- a/include/sysemu/hvf.h +++ b/include/sysemu/hvf.h @@ -17,7 +17,7 @@ #include "exec/memory.h" #include "sysemu/accel.h" -extern int hvf_disabled; +extern bool hvf_allowed; #ifdef CONFIG_HVF #include <Hypervisor/hv.h> #include <Hypervisor/hv_vmx.h> @@ -26,7 +26,7 @@ extern int hvf_disabled; #include "hw/hw.h" uint32_t hvf_get_supported_cpuid(uint32_t func, uint32_t idx, int reg); -#define hvf_enabled() !hvf_disabled +#define hvf_enabled() (hvf_allowed) #else #define hvf_enabled() 0 #define hvf_get_supported_cpuid(func, idx, reg) 0 diff --git a/include/sysemu/replay.h b/include/sysemu/replay.h index 7f7a594eca..3a7c58e423 100644 --- a/include/sysemu/replay.h +++ b/include/sysemu/replay.h @@ -100,14 +100,20 @@ bool replay_has_interrupt(void); /* Processing clocks and other time sources */ /*! Save the specified clock */ -int64_t replay_save_clock(ReplayClockKind kind, int64_t clock); +int64_t replay_save_clock(ReplayClockKind kind, int64_t clock, + int64_t raw_icount); /*! Read the specified clock from the log or return cached data */ int64_t replay_read_clock(ReplayClockKind kind); /*! Saves or reads the clock depending on the current replay mode. */ #define REPLAY_CLOCK(clock, value) \ (replay_mode == REPLAY_MODE_PLAY ? replay_read_clock((clock)) \ : replay_mode == REPLAY_MODE_RECORD \ - ? replay_save_clock((clock), (value)) \ + ? replay_save_clock((clock), (value), cpu_get_icount_raw()) \ + : (value)) +#define REPLAY_CLOCK_LOCKED(clock, value) \ + (replay_mode == REPLAY_MODE_PLAY ? replay_read_clock((clock)) \ + : replay_mode == REPLAY_MODE_RECORD \ + ? replay_save_clock((clock), (value), cpu_get_icount_raw_locked()) \ : (value)) /* Events */ |