diff options
Diffstat (limited to 'include')
37 files changed, 793 insertions, 44 deletions
diff --git a/include/block/accounting.h b/include/block/accounting.h index 66637cd..0f46cb4 100644 --- a/include/block/accounting.h +++ b/include/block/accounting.h @@ -2,6 +2,7 @@ * QEMU System Emulator block accounting * * Copyright (c) 2011 Christoph Hellwig + * Copyright (c) 2015 Igalia, S.L. * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal @@ -25,8 +26,12 @@ #define BLOCK_ACCOUNTING_H #include <stdint.h> +#include <stdbool.h> #include "qemu/typedefs.h" +#include "qemu/timed-average.h" + +typedef struct BlockAcctTimedStats BlockAcctTimedStats; enum BlockAcctType { BLOCK_ACCT_READ, @@ -35,11 +40,23 @@ enum BlockAcctType { BLOCK_MAX_IOTYPE, }; +struct BlockAcctTimedStats { + TimedAverage latency[BLOCK_MAX_IOTYPE]; + unsigned interval_length; /* in seconds */ + QSLIST_ENTRY(BlockAcctTimedStats) entries; +}; + typedef struct BlockAcctStats { uint64_t nr_bytes[BLOCK_MAX_IOTYPE]; uint64_t nr_ops[BLOCK_MAX_IOTYPE]; + uint64_t invalid_ops[BLOCK_MAX_IOTYPE]; + uint64_t failed_ops[BLOCK_MAX_IOTYPE]; uint64_t total_time_ns[BLOCK_MAX_IOTYPE]; uint64_t merged[BLOCK_MAX_IOTYPE]; + int64_t last_access_time_ns; + QSLIST_HEAD(, BlockAcctTimedStats) intervals; + bool account_invalid; + bool account_failed; } BlockAcctStats; typedef struct BlockAcctCookie { @@ -48,10 +65,21 @@ typedef struct BlockAcctCookie { enum BlockAcctType type; } BlockAcctCookie; +void block_acct_init(BlockAcctStats *stats, bool account_invalid, + bool account_failed); +void block_acct_cleanup(BlockAcctStats *stats); +void block_acct_add_interval(BlockAcctStats *stats, unsigned interval_length); +BlockAcctTimedStats *block_acct_interval_next(BlockAcctStats *stats, + BlockAcctTimedStats *s); void block_acct_start(BlockAcctStats *stats, BlockAcctCookie *cookie, int64_t bytes, enum BlockAcctType type); void block_acct_done(BlockAcctStats *stats, BlockAcctCookie *cookie); +void block_acct_failed(BlockAcctStats *stats, BlockAcctCookie *cookie); +void block_acct_invalid(BlockAcctStats *stats, enum BlockAcctType type); void block_acct_merge_done(BlockAcctStats *stats, enum BlockAcctType type, int num_requests); +int64_t block_acct_idle_time_ns(BlockAcctStats *stats); +double block_acct_queue_depth(BlockAcctTimedStats *stats, + enum BlockAcctType type); #endif diff --git a/include/block/aio.h b/include/block/aio.h index bcc7d43..e086e3b 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -124,6 +124,11 @@ struct AioContext { QEMUTimerListGroup tlg; int external_disable_cnt; + + /* epoll(7) state used when built with CONFIG_EPOLL */ + int epollfd; + bool epoll_enabled; + bool epoll_available; }; /** @@ -209,6 +214,11 @@ void aio_notify(AioContext *ctx); void aio_notify_accept(AioContext *ctx); /** + * aio_bh_call: Executes callback function of the specified BH. + */ +void aio_bh_call(QEMUBH *bh); + +/** * aio_bh_poll: Poll bottom halves for an AioContext. * * These are internal functions used by the QEMU main loop. @@ -401,6 +411,17 @@ static inline void aio_enable_external(AioContext *ctx) } /** + * aio_external_disabled: + * @ctx: the aio context + * + * Return true if the external clients are disabled. + */ +static inline bool aio_external_disabled(AioContext *ctx) +{ + return atomic_read(&ctx->external_disable_cnt); +} + +/** * aio_node_check: * @ctx: the aio context * @is_external: Whether or not the checked node is an external event source. @@ -413,4 +434,12 @@ static inline bool aio_node_check(AioContext *ctx, bool is_external) return !is_external || !atomic_read(&ctx->external_disable_cnt); } +/** + * aio_context_setup: + * @ctx: the aio context + * + * Initialize the aio context. + */ +void aio_context_setup(AioContext *ctx, Error **errp); + #endif diff --git a/include/block/block.h b/include/block/block.h index 610db92..73edb1a 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -14,6 +14,7 @@ typedef struct BlockDriver BlockDriver; typedef struct BlockJob BlockJob; typedef struct BdrvChild BdrvChild; typedef struct BdrvChildRole BdrvChildRole; +typedef struct BlockJobTxn BlockJobTxn; typedef struct BlockDriverInfo { /* in bytes, 0 if irrelevant */ @@ -335,10 +336,18 @@ void bdrv_aio_cancel_async(BlockAIOCB *acb); typedef struct BlockRequest { /* Fields to be filled by multiwrite caller */ - int64_t sector; - int nb_sectors; - int flags; - QEMUIOVector *qiov; + union { + struct { + int64_t sector; + int nb_sectors; + int flags; + QEMUIOVector *qiov; + }; + struct { + int req; + void *buf; + }; + }; BlockCompletionFunc *cb; void *opaque; @@ -493,7 +502,6 @@ void bdrv_set_dirty_bitmap(BdrvDirtyBitmap *bitmap, int64_t cur_sector, int nr_sectors); void bdrv_reset_dirty_bitmap(BdrvDirtyBitmap *bitmap, int64_t cur_sector, int nr_sectors); -void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap); void bdrv_dirty_iter_init(BdrvDirtyBitmap *bitmap, struct HBitmapIter *hbi); void bdrv_set_dirty_iter(struct HBitmapIter *hbi, int64_t offset); int64_t bdrv_get_dirty_count(BdrvDirtyBitmap *bitmap); diff --git a/include/block/block_int.h b/include/block/block_int.h index 3ceeb5a..4012e36 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -60,11 +60,19 @@ #define BLOCK_PROBE_BUF_SIZE 512 +enum BdrvTrackedRequestType { + BDRV_TRACKED_READ, + BDRV_TRACKED_WRITE, + BDRV_TRACKED_FLUSH, + BDRV_TRACKED_IOCTL, + BDRV_TRACKED_DISCARD, +}; + typedef struct BdrvTrackedRequest { BlockDriverState *bs; int64_t offset; unsigned int bytes; - bool is_write; + enum BdrvTrackedRequestType type; bool serialising; int64_t overlap_offset; @@ -219,7 +227,6 @@ struct BlockDriver { void (*bdrv_lock_medium)(BlockDriverState *bs, bool locked); /* to control generic scsi devices */ - int (*bdrv_ioctl)(BlockDriverState *bs, unsigned long int req, void *buf); BlockAIOCB *(*bdrv_aio_ioctl)(BlockDriverState *bs, unsigned long int req, void *buf, BlockCompletionFunc *cb, void *opaque); @@ -288,6 +295,12 @@ struct BlockDriver { */ int (*bdrv_probe_geometry)(BlockDriverState *bs, HDGeometry *geo); + /** + * Drain and stop any internal sources of requests in the driver, and + * remain so until next I/O callback (e.g. bdrv_co_writev) is called. + */ + void (*bdrv_drain)(BlockDriverState *bs); + QLIST_ENTRY(BlockDriver) list; }; @@ -390,7 +403,10 @@ struct BlockDriverState { /* number of in-flight serialising requests */ unsigned int serialising_in_flight; - /* I/O throttling */ + /* I/O throttling. + * throttle_state tells us if this BDS has I/O limits configured. + * io_limits_enabled tells us if they are currently being + * enforced, but it can be temporarily set to false */ CoQueue throttled_reqs[2]; bool io_limits_enabled; /* The following fields are protected by the ThrottleGroup lock. @@ -473,6 +489,8 @@ extern BlockDriver bdrv_file; extern BlockDriver bdrv_raw; extern BlockDriver bdrv_qcow2; +extern QTAILQ_HEAD(BdrvStates, BlockDriverState) bdrv_states; + /** * bdrv_setup_io_funcs: * @@ -651,6 +669,7 @@ void mirror_start(BlockDriverState *bs, BlockDriverState *target, * @on_target_error: The action to take upon error writing to the target. * @cb: Completion function for the job. * @opaque: Opaque pointer value passed to @cb. + * @txn: Transaction that this job is part of (may be NULL). * * Start a backup operation on @bs. Clusters in @bs are written to @target * until the job is cancelled or manually completed. @@ -661,7 +680,7 @@ void backup_start(BlockDriverState *bs, BlockDriverState *target, BlockdevOnError on_source_error, BlockdevOnError on_target_error, BlockCompletionFunc *cb, void *opaque, - Error **errp); + BlockJobTxn *txn, Error **errp); void blk_set_bs(BlockBackend *blk, BlockDriverState *bs); @@ -675,4 +694,7 @@ void blk_dev_resize_cb(BlockBackend *blk); void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, int nr_sectors); bool bdrv_requests_pending(BlockDriverState *bs); +void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out); +void bdrv_undo_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *in); + #endif /* BLOCK_INT_H */ diff --git a/include/block/blockjob.h b/include/block/blockjob.h index 289b13f..d84ccd8 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -50,6 +50,26 @@ typedef struct BlockJobDriver { * manually. */ void (*complete)(BlockJob *job, Error **errp); + + /** + * If the callback is not NULL, it will be invoked when all the jobs + * belonging to the same transaction complete; or upon this job's + * completion if it is not in a transaction. Skipped if NULL. + * + * All jobs will complete with a call to either .commit() or .abort() but + * never both. + */ + void (*commit)(BlockJob *job); + + /** + * If the callback is not NULL, it will be invoked when any job in the + * same transaction fails; or upon this job's failure (due to error or + * cancellation) if it is not in a transaction. Skipped if NULL. + * + * All jobs will complete with a call to either .commit() or .abort() but + * never both. + */ + void (*abort)(BlockJob *job); } BlockJobDriver; /** @@ -130,6 +150,21 @@ struct BlockJob { /** The opaque value that is passed to the completion function. */ void *opaque; + + /** Reference count of the block job */ + int refcnt; + + /* True if this job has reported completion by calling block_job_completed. + */ + bool completed; + + /* ret code passed to block_job_completed. + */ + int ret; + + /** Non-NULL if this job is part of a transaction */ + BlockJobTxn *txn; + QLIST_ENTRY(BlockJob) txn_list; }; /** @@ -174,12 +209,21 @@ void block_job_sleep_ns(BlockJob *job, QEMUClockType type, int64_t ns); void block_job_yield(BlockJob *job); /** - * block_job_release: + * block_job_ref: * @bs: The block device. * - * Release job resources when an error occurred or job completed. + * Grab a reference to the block job. Should be paired with block_job_unref. */ -void block_job_release(BlockDriverState *bs); +void block_job_ref(BlockJob *job); + +/** + * block_job_unref: + * @bs: The block device. + * + * Release reference to the block job and release resources if it is the last + * reference. + */ +void block_job_unref(BlockJob *job); /** * block_job_completed: @@ -364,4 +408,39 @@ void block_job_defer_to_main_loop(BlockJob *job, BlockJobDeferToMainLoopFn *fn, void *opaque); +/** + * block_job_txn_new: + * + * Allocate and return a new block job transaction. Jobs can be added to the + * transaction using block_job_txn_add_job(). + * + * The transaction is automatically freed when the last job completes or is + * cancelled. + * + * All jobs in the transaction either complete successfully or fail/cancel as a + * group. Jobs wait for each other before completing. Cancelling one job + * cancels all jobs in the transaction. + */ +BlockJobTxn *block_job_txn_new(void); + +/** + * block_job_txn_unref: + * + * Release a reference that was previously acquired with block_job_txn_add_job + * or block_job_txn_new. If it's the last reference to the object, it will be + * freed. + */ +void block_job_txn_unref(BlockJobTxn *txn); + +/** + * block_job_txn_add_job: + * @txn: The transaction (may be NULL) + * @job: Job to add to the transaction + * + * Add @job to the transaction. The @job must not already be in a transaction. + * The caller must call either block_job_txn_unref() or block_job_completed() + * to release the reference that is automatically grabbed here. + */ +void block_job_txn_add_job(BlockJobTxn *txn, BlockJob *job); + #endif diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h index 9fb1d54..85aa403 100644 --- a/include/exec/cpu-common.h +++ b/include/exec/cpu-common.h @@ -64,8 +64,12 @@ typedef uint32_t CPUReadMemoryFunc(void *opaque, hwaddr addr); void qemu_ram_remap(ram_addr_t addr, ram_addr_t length); /* This should not be used by devices. */ MemoryRegion *qemu_ram_addr_from_host(void *ptr, ram_addr_t *ram_addr); +RAMBlock *qemu_ram_block_by_name(const char *name); +RAMBlock *qemu_ram_block_from_host(void *ptr, bool round_offset, + ram_addr_t *ram_addr, ram_addr_t *offset); void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev); void qemu_ram_unset_idstr(ram_addr_t addr); +const char *qemu_ram_get_idstr(RAMBlock *rb); void cpu_physical_memory_rw(hwaddr addr, uint8_t *buf, int len, int is_write); diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index 9b93b9b..d900b0d 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -72,7 +72,6 @@ void restore_state_to_opc(CPUArchState *env, struct TranslationBlock *tb, void cpu_gen_init(void); bool cpu_restore_state(CPUState *cpu, uintptr_t searched_pc); -void page_size_init(void); void QEMU_NORETURN cpu_resume_from_signal(CPUState *cpu, void *puc); void QEMU_NORETURN cpu_io_recompile(CPUState *cpu, uintptr_t retaddr); @@ -190,6 +189,7 @@ struct TranslationBlock { #define CF_LAST_IO 0x8000 /* Last insn may be an IO access. */ #define CF_NOCACHE 0x10000 /* To be freed after execution */ #define CF_USE_ICOUNT 0x20000 +#define CF_IGNORE_ICOUNT 0x40000 /* Do not generate icount code */ void *tc_ptr; /* pointer to the translated code */ uint8_t *tc_search; /* pointer to search data */ diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index 3360ac5..7115154 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -22,8 +22,6 @@ #ifndef CONFIG_USER_ONLY #include "hw/xen/xen.h" -typedef struct RAMBlock RAMBlock; - struct RAMBlock { struct rcu_head rcu; struct MemoryRegion *mr; diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index 01a189b..6b32a99 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -7,6 +7,8 @@ #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/allwinner-a10-pic.h" #include "hw/net/allwinner_emac.h" +#include "hw/ide/pci.h" +#include "hw/ide/ahci.h" #include "sysemu/sysemu.h" #include "exec/address-spaces.h" @@ -16,6 +18,7 @@ #define AW_A10_PIT_REG_BASE 0x01c20c00 #define AW_A10_UART0_REG_BASE 0x01c28000 #define AW_A10_EMAC_BASE 0x01c0b000 +#define AW_A10_SATA_BASE 0x01c18000 #define AW_A10_SDRAM_BASE 0x40000000 @@ -32,6 +35,7 @@ typedef struct AwA10State { AwA10PITState timer; AwA10PICState intc; AwEmacState emac; + AllwinnerAHCIState sata; } AwA10State; #define ALLWINNER_H_ diff --git a/include/hw/arm/arm.h b/include/hw/arm/arm.h index 67ba7db..c26b0e3 100644 --- a/include/hw/arm/arm.h +++ b/include/hw/arm/arm.h @@ -97,6 +97,12 @@ struct arm_boot_info { hwaddr board_setup_addr; void (*write_board_setup)(ARMCPU *cpu, const struct arm_boot_info *info); + + /* If set, the board specific loader/setup blob will be run from secure + * mode, regardless of secure_boot. The blob becomes responsible for + * changing to non-secure state if implementing a non-secure boot + */ + bool secure_board_setup; }; /** diff --git a/include/hw/compat.h b/include/hw/compat.h index 93e71af..d0b1c4f 100644 --- a/include/hw/compat.h +++ b/include/hw/compat.h @@ -6,6 +6,18 @@ .driver = "virtio-blk-device",\ .property = "scsi",\ .value = "true",\ + },{\ + .driver = "e1000",\ + .property = "extra_mac_registers",\ + .value = "off",\ + },{\ + .driver = "virtio-pci",\ + .property = "x-disable-pcie",\ + .value = "on",\ + },{\ + .driver = "virtio-pci",\ + .property = "migrate-extra",\ + .value = "off",\ }, #define HW_COMPAT_2_3 \ diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index 606dbc2..4bbc0ff 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -322,6 +322,31 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *); .driver = "host" "-" TYPE_X86_CPU,\ .property = "host-cache-info",\ .value = "on",\ + },\ + {\ + .driver = TYPE_X86_CPU,\ + .property = "check",\ + .value = "off",\ + },\ + {\ + .driver = "qemu64" "-" TYPE_X86_CPU,\ + .property = "sse4a",\ + .value = "on",\ + },\ + {\ + .driver = "qemu64" "-" TYPE_X86_CPU,\ + .property = "abm",\ + .value = "on",\ + },\ + {\ + .driver = "qemu64" "-" TYPE_X86_CPU,\ + .property = "popcnt",\ + .value = "on",\ + },\ + {\ + .driver = "qemu32" "-" TYPE_X86_CPU,\ + .property = "popcnt",\ + .value = "on",\ }, #define PC_COMPAT_2_3 \ diff --git a/include/hw/misc/zynq-xadc.h b/include/hw/misc/zynq-xadc.h new file mode 100644 index 0000000..f1a410a --- /dev/null +++ b/include/hw/misc/zynq-xadc.h @@ -0,0 +1,46 @@ +/* + * Device model for Zynq ADC controller + * + * Copyright (c) 2015 Guenter Roeck <linux@roeck-us.net> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef ZYNQ_XADC_H +#define ZYNQ_XADC_H + +#include "hw/sysbus.h" + +#define ZYNQ_XADC_MMIO_SIZE 0x0020 +#define ZYNQ_XADC_NUM_IO_REGS (ZYNQ_XADC_MMIO_SIZE / 4) +#define ZYNQ_XADC_NUM_ADC_REGS 128 +#define ZYNQ_XADC_FIFO_DEPTH 15 + +#define TYPE_ZYNQ_XADC "xlnx,zynq-xadc" +#define ZYNQ_XADC(obj) \ + OBJECT_CHECK(ZynqXADCState, (obj), TYPE_ZYNQ_XADC) + +typedef struct ZynqXADCState { + /*< private >*/ + SysBusDevice parent_obj; + + /*< public >*/ + MemoryRegion iomem; + + uint32_t regs[ZYNQ_XADC_NUM_IO_REGS]; + uint16_t xadc_regs[ZYNQ_XADC_NUM_ADC_REGS]; + uint16_t xadc_read_reg_previous; + uint16_t xadc_dfifo[ZYNQ_XADC_FIFO_DEPTH]; + uint16_t xadc_dfifo_entries; + + struct IRQState *qemu_irq; + +} ZynqXADCState; + +#endif /* ZYNQ_XADC_H */ diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h index 8057aed..e6dbde4 100644 --- a/include/hw/qdev-core.h +++ b/include/hw/qdev-core.h @@ -337,6 +337,7 @@ int qdev_walk_children(DeviceState *dev, void *opaque); void qdev_reset_all(DeviceState *dev); +void qdev_reset_all_fn(void *opaque); /** * @qbus_reset_all: diff --git a/include/hw/virtio/virtio-bus.h b/include/hw/virtio/virtio-bus.h index 8811415..6c3d4cb 100644 --- a/include/hw/virtio/virtio-bus.h +++ b/include/hw/virtio/virtio-bus.h @@ -44,9 +44,12 @@ typedef struct VirtioBusClass { void (*notify)(DeviceState *d, uint16_t vector); void (*save_config)(DeviceState *d, QEMUFile *f); void (*save_queue)(DeviceState *d, int n, QEMUFile *f); + void (*save_extra_state)(DeviceState *d, QEMUFile *f); int (*load_config)(DeviceState *d, QEMUFile *f); int (*load_queue)(DeviceState *d, int n, QEMUFile *f); int (*load_done)(DeviceState *d, QEMUFile *f); + int (*load_extra_state)(DeviceState *d, QEMUFile *f); + bool (*has_extra_state)(DeviceState *d); bool (*query_guest_notifiers)(DeviceState *d); int (*set_guest_notifiers)(DeviceState *d, int nvqs, bool assign); int (*set_host_notifier)(DeviceState *d, int n, bool assigned); diff --git a/include/migration/migration.h b/include/migration/migration.h index 8334621..fd018b7 100644 --- a/include/migration/migration.h +++ b/include/migration/migration.h @@ -35,6 +35,7 @@ #define QEMU_VM_SUBSECTION 0x05 #define QEMU_VM_VMDESCRIPTION 0x06 #define QEMU_VM_CONFIGURATION 0x07 +#define QEMU_VM_COMMAND 0x08 #define QEMU_VM_SECTION_FOOTER 0x7e struct MigrationParams { @@ -42,13 +43,67 @@ struct MigrationParams { bool shared; }; -typedef struct MigrationState MigrationState; +/* Messages sent on the return path from destination to source */ +enum mig_rp_message_type { + MIG_RP_MSG_INVALID = 0, /* Must be 0 */ + MIG_RP_MSG_SHUT, /* sibling will not send any more RP messages */ + MIG_RP_MSG_PONG, /* Response to a PING; data (seq: be32 ) */ + + MIG_RP_MSG_REQ_PAGES_ID, /* data (start: be64, len: be32, id: string) */ + MIG_RP_MSG_REQ_PAGES, /* data (start: be64, len: be32) */ + + MIG_RP_MSG_MAX +}; typedef QLIST_HEAD(, LoadStateEntry) LoadStateEntry_Head; +/* The current postcopy state is read/set by postcopy_state_get/set + * which update it atomically. + * The state is updated as postcopy messages are received, and + * in general only one thread should be writing to the state at any one + * time, initially the main thread and then the listen thread; + * Corner cases are where either thread finishes early and/or errors. + * The state is checked as messages are received to ensure that + * the source is sending us messages in the correct order. + * The state is also used by the RAM reception code to know if it + * has to place pages atomically, and the cleanup code at the end of + * the main thread to know if it has to delay cleanup until the end + * of postcopy. + */ +typedef enum { + POSTCOPY_INCOMING_NONE = 0, /* Initial state - no postcopy */ + POSTCOPY_INCOMING_ADVISE, + POSTCOPY_INCOMING_DISCARD, + POSTCOPY_INCOMING_LISTENING, + POSTCOPY_INCOMING_RUNNING, + POSTCOPY_INCOMING_END +} PostcopyState; + /* State for the incoming migration */ struct MigrationIncomingState { - QEMUFile *file; + QEMUFile *from_src_file; + + /* + * Free at the start of the main state load, set as the main thread finishes + * loading state. + */ + QemuEvent main_thread_load_event; + + bool have_fault_thread; + QemuThread fault_thread; + QemuSemaphore fault_thread_sem; + + bool have_listen_thread; + QemuThread listen_thread; + QemuSemaphore listen_thread_sem; + + /* For the kernel to send us notifications */ + int userfault_fd; + /* To tell the fault_thread to quit */ + int userfault_quit_fd; + QEMUFile *to_src_file; + QemuMutex rp_mutex; /* We send replies from multiple threads */ + void *postcopy_tmp_page; /* See savevm.c */ LoadStateEntry_Head loadvm_handlers; @@ -58,6 +113,18 @@ MigrationIncomingState *migration_incoming_get_current(void); MigrationIncomingState *migration_incoming_state_new(QEMUFile *f); void migration_incoming_state_destroy(void); +/* + * An outstanding page request, on the source, having been received + * and queued + */ +struct MigrationSrcPageRequest { + RAMBlock *rb; + hwaddr offset; + hwaddr len; + + QSIMPLEQ_ENTRY(MigrationSrcPageRequest) next_req; +}; + struct MigrationState { int64_t bandwidth_limit; @@ -70,6 +137,14 @@ struct MigrationState int state; MigrationParams params; + + /* State related to return path */ + struct { + QEMUFile *from_dst_file; + QemuThread rp_thread; + bool error; + } rp_state; + double mbps; int64_t total_time; int64_t downtime; @@ -80,6 +155,18 @@ struct MigrationState int64_t xbzrle_cache_size; int64_t setup_time; int64_t dirty_sync_count; + + /* Flag set once the migration has been asked to enter postcopy */ + bool start_postcopy; + + /* Flag set once the migration thread is running (and needs joining) */ + bool migration_thread_running; + + /* Queue of outstanding page requests from the destination */ + QemuMutex src_page_req_mutex; + QSIMPLEQ_HEAD(src_page_requests, MigrationSrcPageRequest) src_page_requests; + /* The RAMBlock used in the last src_page_request */ + RAMBlock *last_req_rb; }; void process_incoming_migration(QEMUFile *f); @@ -116,9 +203,12 @@ int migrate_fd_close(MigrationState *s); void add_migration_state_change_notifier(Notifier *notify); void remove_migration_state_change_notifier(Notifier *notify); +MigrationState *migrate_init(const MigrationParams *params); bool migration_in_setup(MigrationState *); bool migration_has_finished(MigrationState *); bool migration_has_failed(MigrationState *); +/* True if outgoing migration has entered postcopy phase */ +bool migration_in_postcopy(MigrationState *); MigrationState *migrate_get_current(void); void migrate_compress_threads_create(void); @@ -145,6 +235,13 @@ uint64_t xbzrle_mig_pages_cache_miss(void); double xbzrle_mig_cache_miss_rate(void); void ram_handle_compressed(void *host, uint8_t ch, uint64_t size); +void ram_debug_dump_bitmap(unsigned long *todump, bool expected); +/* For outgoing discard bitmap */ +int ram_postcopy_send_discard_bitmap(MigrationState *ms); +/* For incoming postcopy discard */ +int ram_discard_range(MigrationIncomingState *mis, const char *block_name, + uint64_t start, size_t length); +int ram_postcopy_incoming_init(MigrationIncomingState *mis); /** * @migrate_add_blocker - prevent migration from proceeding @@ -160,6 +257,7 @@ void migrate_add_blocker(Error *reason); */ void migrate_del_blocker(Error *reason); +bool migrate_postcopy_ram(void); bool migrate_zero_blocks(void); bool migrate_auto_converge(void); @@ -179,6 +277,17 @@ int migrate_compress_threads(void); int migrate_decompress_threads(void); bool migrate_use_events(void); +/* Sending on the return path - generic and then for each message type */ +void migrate_send_rp_message(MigrationIncomingState *mis, + enum mig_rp_message_type message_type, + uint16_t len, void *data); +void migrate_send_rp_shut(MigrationIncomingState *mis, + uint32_t value); +void migrate_send_rp_pong(MigrationIncomingState *mis, + uint32_t value); +void migrate_send_rp_req_pages(MigrationIncomingState *mis, const char* rbname, + ram_addr_t start, size_t len); + void ram_control_before_iterate(QEMUFile *f, uint64_t flags); void ram_control_after_iterate(QEMUFile *f, uint64_t flags); void ram_control_load_hook(QEMUFile *f, uint64_t flags, void *data); @@ -204,4 +313,12 @@ void global_state_set_optional(void); void savevm_skip_configuration(void); int global_state_store(void); void global_state_store_running(void); + +void flush_page_queue(MigrationState *ms); +int ram_save_queue_pages(MigrationState *ms, const char *rbname, + ram_addr_t start, ram_addr_t len); + +PostcopyState postcopy_state_get(void); +/* Set the state and return the old state */ +PostcopyState postcopy_state_set(PostcopyState new_state); #endif diff --git a/include/migration/postcopy-ram.h b/include/migration/postcopy-ram.h new file mode 100644 index 0000000..b6a7491 --- /dev/null +++ b/include/migration/postcopy-ram.h @@ -0,0 +1,99 @@ +/* + * Postcopy migration for RAM + * + * Copyright 2013 Red Hat, Inc. and/or its affiliates + * + * Authors: + * Dave Gilbert <dgilbert@redhat.com> + * + * 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 QEMU_POSTCOPY_RAM_H +#define QEMU_POSTCOPY_RAM_H + +/* Return true if the host supports everything we need to do postcopy-ram */ +bool postcopy_ram_supported_by_host(void); + +/* + * Make all of RAM sensitive to accesses to areas that haven't yet been written + * and wire up anything necessary to deal with it. + */ +int postcopy_ram_enable_notify(MigrationIncomingState *mis); + +/* + * Initialise postcopy-ram, setting the RAM to a state where we can go into + * postcopy later; must be called prior to any precopy. + * called from ram.c's similarly named ram_postcopy_incoming_init + */ +int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages); + +/* + * At the end of a migration where postcopy_ram_incoming_init was called. + */ +int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis); + +/* + * Discard the contents of 'length' bytes from 'start' + * We can assume that if we've been called postcopy_ram_hosttest returned true + */ +int postcopy_ram_discard_range(MigrationIncomingState *mis, uint8_t *start, + size_t length); + +/* + * Userfault requires us to mark RAM as NOHUGEPAGE prior to discard + * however leaving it until after precopy means that most of the precopy + * data is still THPd + */ +int postcopy_ram_prepare_discard(MigrationIncomingState *mis); + +/* + * Called at the start of each RAMBlock by the bitmap code. + * 'offset' is the bitmap offset of the named RAMBlock in the migration + * bitmap. + * Returns a new PDS + */ +PostcopyDiscardState *postcopy_discard_send_init(MigrationState *ms, + unsigned long offset, + const char *name); + +/* + * Called by the bitmap code for each chunk to discard. + * May send a discard message, may just leave it queued to + * be sent later. + * @start,@length: a range of pages in the migration bitmap in the + * RAM block passed to postcopy_discard_send_init() (length=1 is one page) + */ +void postcopy_discard_send_range(MigrationState *ms, PostcopyDiscardState *pds, + unsigned long start, unsigned long length); + +/* + * Called at the end of each RAMBlock by the bitmap code. + * Sends any outstanding discard messages, frees the PDS. + */ +void postcopy_discard_send_finish(MigrationState *ms, + PostcopyDiscardState *pds); + +/* + * Place a page (from) at (host) efficiently + * There are restrictions on how 'from' must be mapped, in general best + * to use other postcopy_ routines to allocate. + * returns 0 on success + */ +int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from); + +/* + * Place a zero page at (host) atomically + * returns 0 on success + */ +int postcopy_place_page_zero(MigrationIncomingState *mis, void *host); + +/* + * Allocate a page of memory that can be mapped at a later point in time + * using postcopy_place_page + * Returns: Pointer to allocated page + */ +void *postcopy_get_tmp_page(MigrationIncomingState *mis); + +#endif diff --git a/include/migration/qemu-file.h b/include/migration/qemu-file.h index 29a338d..b5d08d2 100644 --- a/include/migration/qemu-file.h +++ b/include/migration/qemu-file.h @@ -89,6 +89,11 @@ typedef size_t (QEMURamSaveFunc)(QEMUFile *f, void *opaque, uint64_t *bytes_sent); /* + * Return a QEMUFile for comms in the opposite direction + */ +typedef QEMUFile *(QEMURetPathFunc)(void *opaque); + +/* * Stop any read or write (depending on flags) on the underlying * transport on the QEMUFile. * Existing blocking reads/writes must be woken @@ -106,6 +111,7 @@ typedef struct QEMUFileOps { QEMURamHookFunc *after_ram_iterate; QEMURamHookFunc *hook_ram_load; QEMURamSaveFunc *save_page; + QEMURetPathFunc *get_return_path; QEMUFileShutdownFunc *shut_down; } QEMUFileOps; @@ -163,9 +169,11 @@ void qemu_put_be32(QEMUFile *f, unsigned int v); void qemu_put_be64(QEMUFile *f, uint64_t v); size_t qemu_peek_buffer(QEMUFile *f, uint8_t **buf, size_t size, size_t offset); size_t qemu_get_buffer(QEMUFile *f, uint8_t *buf, size_t size); +size_t qemu_get_buffer_in_place(QEMUFile *f, uint8_t **buf, size_t size); ssize_t qemu_put_compression_data(QEMUFile *f, const uint8_t *p, size_t size, int level); int qemu_put_qemu_file(QEMUFile *f_des, QEMUFile *f_src); + /* * Note that you can only peek continuous bytes from where the current pointer * is; you aren't guaranteed to be able to peak to +n bytes unless you've @@ -194,7 +202,9 @@ int64_t qemu_file_get_rate_limit(QEMUFile *f); int qemu_file_get_error(QEMUFile *f); void qemu_file_set_error(QEMUFile *f, int ret); int qemu_file_shutdown(QEMUFile *f); +QEMUFile *qemu_file_get_return_path(QEMUFile *f); void qemu_fflush(QEMUFile *f); +void qemu_file_set_blocking(QEMUFile *f, bool block); static inline void qemu_put_be64s(QEMUFile *f, const uint64_t *pv) { diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h index 9a65522..7267e38 100644 --- a/include/migration/vmstate.h +++ b/include/migration/vmstate.h @@ -39,8 +39,9 @@ typedef struct SaveVMHandlers { void (*set_params)(const MigrationParams *params, void * opaque); SaveStateHandler *save_state; - void (*cancel)(void *opaque); - int (*save_live_complete)(QEMUFile *f, void *opaque); + void (*cleanup)(void *opaque); + int (*save_live_complete_postcopy)(QEMUFile *f, void *opaque); + int (*save_live_complete_precopy)(QEMUFile *f, void *opaque); /* This runs both outside and inside the iothread lock. */ bool (*is_active)(void *opaque); @@ -54,8 +55,9 @@ typedef struct SaveVMHandlers { /* This runs outside the iothread lock! */ int (*save_live_setup)(QEMUFile *f, void *opaque); - uint64_t (*save_live_pending)(QEMUFile *f, void *opaque, uint64_t max_size); - + void (*save_live_pending)(QEMUFile *f, void *opaque, uint64_t max_size, + uint64_t *non_postcopiable_pending, + uint64_t *postcopiable_pending); LoadStateHandler *load_state; } SaveVMHandlers; diff --git a/include/monitor/hmp-target.h b/include/monitor/hmp-target.h index 213566c..bc2c9c0 100644 --- a/include/monitor/hmp-target.h +++ b/include/monitor/hmp-target.h @@ -35,6 +35,7 @@ struct MonitorDef { }; const MonitorDef *target_monitor_defs(void); +int target_get_monitor_def(CPUState *cs, const char *name, uint64_t *pval); CPUArchState *mon_get_cpu_env(void); CPUState *mon_get_cpu(void); diff --git a/include/qapi/error.h b/include/qapi/error.h index c69dddb..4d42cdc 100644 --- a/include/qapi/error.h +++ b/include/qapi/error.h @@ -30,6 +30,10 @@ * Handle an error without reporting it (just for completeness): * error_free(err); * + * Assert that an expected error occurred, but clean it up without + * reporting it (primarily useful in testsuites): + * error_free_or_abort(&err); + * * Pass an existing error to the caller: * error_propagate(errp, err); * where Error **errp is a parameter, by convention the last one. @@ -190,6 +194,11 @@ Error *error_copy(const Error *err); void error_free(Error *err); /* + * Convenience function to assert that *@errp is set, then silently free it. + */ +void error_free_or_abort(Error **errp); + +/* * Convenience function to error_report() and free @err. */ void error_report_err(Error *); diff --git a/include/qapi/qmp/qerror.h b/include/qapi/qmp/qerror.h index 842b27a..f601499 100644 --- a/include/qapi/qmp/qerror.h +++ b/include/qapi/qmp/qerror.h @@ -106,4 +106,7 @@ #define QERR_UNSUPPORTED \ "this feature or command is not currently supported" +#define QERR_REPLAY_NOT_SUPPORTED \ + "Record/replay feature is not supported for '%s'" + #endif /* QERROR_H */ diff --git a/include/qapi/qmp/qobject.h b/include/qapi/qmp/qobject.h index c856f55..4b96ed5 100644 --- a/include/qapi/qmp/qobject.h +++ b/include/qapi/qmp/qobject.h @@ -90,6 +90,7 @@ static inline void qobject_incref(QObject *obj) */ static inline void qobject_decref(QObject *obj) { + assert(!obj || obj->refcnt); if (obj && --obj->refcnt == 0) { assert(obj->type != NULL); assert(obj->type->destroy != NULL); diff --git a/include/qemu-common.h b/include/qemu-common.h index 2f74540..405364f 100644 --- a/include/qemu-common.h +++ b/include/qemu-common.h @@ -499,5 +499,6 @@ size_t buffer_find_nonzero_offset(const void *buf, size_t len); int parse_debug_env(const char *name, int max, int initial); const char *qemu_ether_ntoa(const MACAddr *mac); +void page_size_init(void); #endif diff --git a/include/qemu/log.h b/include/qemu/log.h index 7de4500..362cbc4 100644 --- a/include/qemu/log.h +++ b/include/qemu/log.h @@ -35,7 +35,6 @@ static inline bool qemu_log_enabled(void) #define CPU_LOG_INT (1 << 4) #define CPU_LOG_EXEC (1 << 5) #define CPU_LOG_PCALL (1 << 6) -#define CPU_LOG_IOPORT (1 << 7) #define CPU_LOG_TB_CPU (1 << 8) #define CPU_LOG_RESET (1 << 9) #define LOG_UNIMP (1 << 10) diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h index b568424..861d84b 100644 --- a/include/qemu/osdep.h +++ b/include/qemu/osdep.h @@ -139,6 +139,8 @@ void qemu_anon_ram_free(void *ptr, size_t size); #if defined(CONFIG_MADVISE) +#include <sys/mman.h> + #define QEMU_MADV_WILLNEED MADV_WILLNEED #define QEMU_MADV_DONTNEED MADV_DONTNEED #ifdef MADV_DONTFORK @@ -171,6 +173,11 @@ void qemu_anon_ram_free(void *ptr, size_t size); #else #define QEMU_MADV_HUGEPAGE QEMU_MADV_INVALID #endif +#ifdef MADV_NOHUGEPAGE +#define QEMU_MADV_NOHUGEPAGE MADV_NOHUGEPAGE +#else +#define QEMU_MADV_NOHUGEPAGE QEMU_MADV_INVALID +#endif #elif defined(CONFIG_POSIX_MADVISE) @@ -182,6 +189,7 @@ void qemu_anon_ram_free(void *ptr, size_t size); #define QEMU_MADV_DODUMP QEMU_MADV_INVALID #define QEMU_MADV_DONTDUMP QEMU_MADV_INVALID #define QEMU_MADV_HUGEPAGE QEMU_MADV_INVALID +#define QEMU_MADV_NOHUGEPAGE QEMU_MADV_INVALID #else /* no-op */ @@ -193,6 +201,7 @@ void qemu_anon_ram_free(void *ptr, size_t size); #define QEMU_MADV_DODUMP QEMU_MADV_INVALID #define QEMU_MADV_DONTDUMP QEMU_MADV_INVALID #define QEMU_MADV_HUGEPAGE QEMU_MADV_INVALID +#define QEMU_MADV_NOHUGEPAGE QEMU_MADV_INVALID #endif @@ -247,8 +256,8 @@ static inline void qemu_timersub(const struct timeval *val1, void qemu_set_cloexec(int fd); -void qemu_set_version(const char *); -const char *qemu_get_version(void); +void qemu_set_hw_version(const char *); +const char *qemu_hw_version(void); void fips_set_state(bool requested); bool fips_get_state(void); diff --git a/include/qemu/timed-average.h b/include/qemu/timed-average.h new file mode 100644 index 0000000..364bf88 --- /dev/null +++ b/include/qemu/timed-average.h @@ -0,0 +1,64 @@ +/* + * QEMU timed average computation + * + * Copyright (C) Nodalink, EURL. 2014 + * Copyright (C) Igalia, S.L. 2015 + * + * Authors: + * BenoƮt Canet <benoit.canet@nodalink.com> + * Alberto Garcia <berto@igalia.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) version 3 or any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef TIMED_AVERAGE_H +#define TIMED_AVERAGE_H + +#include <stdint.h> + +#include "qemu/timer.h" + +typedef struct TimedAverageWindow TimedAverageWindow; +typedef struct TimedAverage TimedAverage; + +/* All fields of both structures are private */ + +struct TimedAverageWindow { + uint64_t min; /* minimum value accounted in the window */ + uint64_t max; /* maximum value accounted in the window */ + uint64_t sum; /* sum of all values */ + uint64_t count; /* number of values */ + int64_t expiration; /* the end of the current window in ns */ +}; + +struct TimedAverage { + uint64_t period; /* period in nanoseconds */ + TimedAverageWindow windows[2]; /* two overlapping windows of with + * an offset of period / 2 between them */ + unsigned current; /* the current window index: it's also the + * oldest window index */ + QEMUClockType clock_type; /* the clock used */ +}; + +void timed_average_init(TimedAverage *ta, QEMUClockType clock_type, + uint64_t period); + +void timed_average_account(TimedAverage *ta, uint64_t value); + +uint64_t timed_average_min(TimedAverage *ta); +uint64_t timed_average_avg(TimedAverage *ta); +uint64_t timed_average_max(TimedAverage *ta); +uint64_t timed_average_sum(TimedAverage *ta, uint64_t *elapsed); + +#endif diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h index d961362..6b1093d 100644 --- a/include/qemu/typedefs.h +++ b/include/qemu/typedefs.h @@ -9,6 +9,7 @@ struct Monitor; typedef struct AdapterInfo AdapterInfo; typedef struct AddressSpace AddressSpace; typedef struct AioContext AioContext; +typedef struct AllwinnerAHCIState AllwinnerAHCIState; typedef struct AudioState AudioState; typedef struct BlockBackend BlockBackend; typedef struct BlockBackendRootState BlockBackendRootState; @@ -43,6 +44,7 @@ typedef struct MemoryRegion MemoryRegion; typedef struct MemoryRegionSection MemoryRegionSection; typedef struct MigrationIncomingState MigrationIncomingState; typedef struct MigrationParams MigrationParams; +typedef struct MigrationState MigrationState; typedef struct Monitor Monitor; typedef struct MouseTransformInfo MouseTransformInfo; typedef struct MSIMessage MSIMessage; @@ -65,6 +67,7 @@ typedef struct PCMachineState PCMachineState; typedef struct PCMachineClass PCMachineClass; typedef struct PCMCIACardState PCMCIACardState; typedef struct PixelFormat PixelFormat; +typedef struct PostcopyDiscardState PostcopyDiscardState; typedef struct PropertyInfo PropertyInfo; typedef struct Property Property; typedef struct QEMUBH QEMUBH; @@ -78,6 +81,7 @@ typedef struct QEMUSizedBuffer QEMUSizedBuffer; typedef struct QEMUTimerListGroup QEMUTimerListGroup; typedef struct QEMUTimer QEMUTimer; typedef struct Range Range; +typedef struct RAMBlock RAMBlock; typedef struct SerialState SerialState; typedef struct SHPCDevice SHPCDevice; typedef struct SMBusDevice SMBusDevice; diff --git a/include/qom/object.h b/include/qom/object.h index be7280c..0bb89d4 100644 --- a/include/qom/object.h +++ b/include/qom/object.h @@ -510,16 +510,16 @@ struct TypeInfo /** * OBJECT_CLASS_CHECK: - * @class: The C type to use for the return value. - * @obj: A derivative of @type to cast. - * @name: the QOM typename of @class. + * @class_type: The C type to use for the return value. + * @class: A derivative class of @class_type to cast. + * @name: the QOM typename of @class_type. * * A type safe version of @object_class_dynamic_cast_assert. This macro is * typically wrapped by each type to perform type safe casts of a class to a * specific class type. */ -#define OBJECT_CLASS_CHECK(class, obj, name) \ - ((class *)object_class_dynamic_cast_assert(OBJECT_CLASS(obj), (name), \ +#define OBJECT_CLASS_CHECK(class_type, class, name) \ + ((class_type *)object_class_dynamic_cast_assert(OBJECT_CLASS(class), (name), \ __FILE__, __LINE__, __func__)) /** diff --git a/include/sysemu/balloon.h b/include/sysemu/balloon.h index 17fe300..3f976b4 100644 --- a/include/sysemu/balloon.h +++ b/include/sysemu/balloon.h @@ -22,5 +22,7 @@ typedef void (QEMUBalloonStatus)(void *opaque, BalloonInfo *info); int qemu_add_balloon_handler(QEMUBalloonEvent *event_func, QEMUBalloonStatus *stat_func, void *opaque); void qemu_remove_balloon_handler(void *opaque); +bool qemu_balloon_is_inhibited(void); +void qemu_balloon_inhibit(bool state); #endif diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h index 9306a52..f4a68e2 100644 --- a/include/sysemu/block-backend.h +++ b/include/sysemu/block-backend.h @@ -65,6 +65,7 @@ BlockBackend *blk_new_with_bs(const char *name, Error **errp); BlockBackend *blk_new_open(const char *name, const char *filename, const char *reference, QDict *options, int flags, Error **errp); +int blk_get_refcnt(BlockBackend *blk); void blk_ref(BlockBackend *blk); void blk_unref(BlockBackend *blk); const char *blk_name(BlockBackend *blk); @@ -72,6 +73,7 @@ BlockBackend *blk_by_name(const char *name); BlockBackend *blk_next(BlockBackend *blk); BlockDriverState *blk_bs(BlockBackend *blk); +void blk_remove_bs(BlockBackend *blk); void blk_insert_bs(BlockBackend *blk, BlockDriverState *bs); void blk_hide_on_behalf_of_hmp_drive_del(BlockBackend *blk); @@ -166,6 +168,8 @@ void blk_io_unplug(BlockBackend *blk); BlockAcctStats *blk_get_stats(BlockBackend *blk); BlockBackendRootState *blk_get_root_state(BlockBackend *blk); void blk_update_root_state(BlockBackend *blk); +void blk_apply_root_state(BlockBackend *blk, BlockDriverState *bs); +int blk_get_open_flags_from_root_state(BlockBackend *blk); void *blk_aio_get(const AIOCBInfo *aiocb_info, BlockBackend *blk, BlockCompletionFunc *cb, void *opaque); diff --git a/include/sysemu/blockdev.h b/include/sysemu/blockdev.h index a00be94..b06a060 100644 --- a/include/sysemu/blockdev.h +++ b/include/sysemu/blockdev.h @@ -63,8 +63,6 @@ DriveInfo *drive_new(QemuOpts *arg, BlockInterfaceType block_default_type); /* device-hotplug */ -void qmp_change_blockdev(const char *device, const char *filename, - const char *format, Error **errp); void hmp_commit(Monitor *mon, const QDict *qdict); void hmp_drive_del(Monitor *mon, const QDict *qdict); #endif diff --git a/include/sysemu/cpus.h b/include/sysemu/cpus.h index 30ddd12..3d1e5ba 100644 --- a/include/sysemu/cpus.h +++ b/include/sysemu/cpus.h @@ -11,7 +11,6 @@ void cpu_stop_current(void); void cpu_synchronize_all_states(void); void cpu_synchronize_all_post_reset(void); void cpu_synchronize_all_post_init(void); -void cpu_clean_all_dirty(void); void qtest_clock_warp(int64_t dest); diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h index 461ef65..b31f325 100644 --- a/include/sysemu/kvm.h +++ b/include/sysemu/kvm.h @@ -53,6 +53,7 @@ extern bool kvm_gsi_routing_allowed; extern bool kvm_gsi_direct_mapping; extern bool kvm_readonly_mem_allowed; extern bool kvm_direct_msi_allowed; +extern bool kvm_ioeventfd_any_length_allowed; #if defined CONFIG_KVM || !defined NEED_CPU_H #define kvm_enabled() (kvm_allowed) @@ -153,6 +154,12 @@ extern bool kvm_direct_msi_allowed; */ #define kvm_direct_msi_enabled() (kvm_direct_msi_allowed) +/** + * kvm_ioeventfd_any_length_enabled: + * Returns: true if KVM allows any length io eventfd. + */ +#define kvm_ioeventfd_any_length_enabled() (kvm_ioeventfd_any_length_allowed) + #else #define kvm_enabled() (0) #define kvm_irqchip_in_kernel() (false) @@ -166,6 +173,7 @@ extern bool kvm_direct_msi_allowed; #define kvm_gsi_direct_mapping() (false) #define kvm_readonly_mem_enabled() (false) #define kvm_direct_msi_enabled() (false) +#define kvm_ioeventfd_any_length_enabled() (false) #endif struct kvm_run; @@ -417,7 +425,6 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram_addr, void kvm_cpu_synchronize_state(CPUState *cpu); void kvm_cpu_synchronize_post_reset(CPUState *cpu); void kvm_cpu_synchronize_post_init(CPUState *cpu); -void kvm_cpu_clean_state(CPUState *cpu); /* generic hooks - to be moved/refactored once there are more users */ @@ -442,13 +449,6 @@ static inline void cpu_synchronize_post_init(CPUState *cpu) } } -static inline void cpu_clean_state(CPUState *cpu) -{ - if (kvm_enabled()) { - kvm_cpu_clean_state(cpu); - } -} - int kvm_irqchip_add_msi_route(KVMState *s, MSIMessage msg, PCIDevice *dev); int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg, PCIDevice *dev); diff --git a/include/sysemu/replay.h b/include/sysemu/replay.h new file mode 100644 index 0000000..abb4688 --- /dev/null +++ b/include/sysemu/replay.h @@ -0,0 +1,120 @@ +#ifndef REPLAY_H +#define REPLAY_H + +/* + * replay.h + * + * Copyright (c) 2010-2015 Institute for System Programming + * of the Russian Academy of Sciences. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include <stdbool.h> +#include <stdint.h> +#include "qapi-types.h" +#include "qapi/error.h" +#include "qemu/typedefs.h" + +/* replay clock kinds */ +enum ReplayClockKind { + /* host_clock */ + REPLAY_CLOCK_HOST, + /* virtual_rt_clock */ + REPLAY_CLOCK_VIRTUAL_RT, + REPLAY_CLOCK_COUNT +}; +typedef enum ReplayClockKind ReplayClockKind; + +/* IDs of the checkpoints */ +enum ReplayCheckpoint { + CHECKPOINT_CLOCK_WARP, + CHECKPOINT_RESET_REQUESTED, + CHECKPOINT_SUSPEND_REQUESTED, + CHECKPOINT_CLOCK_VIRTUAL, + CHECKPOINT_CLOCK_HOST, + CHECKPOINT_CLOCK_VIRTUAL_RT, + CHECKPOINT_INIT, + CHECKPOINT_RESET, + CHECKPOINT_COUNT +}; +typedef enum ReplayCheckpoint ReplayCheckpoint; + +extern ReplayMode replay_mode; + +/* Replay process control functions */ + +/*! Enables recording or saving event log with specified parameters */ +void replay_configure(struct QemuOpts *opts); +/*! Initializes timers used for snapshotting and enables events recording */ +void replay_start(void); +/*! Closes replay log file and frees other resources. */ +void replay_finish(void); +/*! Adds replay blocker with the specified error description */ +void replay_add_blocker(Error *reason); + +/* Processing the instructions */ + +/*! Returns number of executed instructions. */ +uint64_t replay_get_current_step(void); +/*! Returns number of instructions to execute in replay mode. */ +int replay_get_instructions(void); +/*! Updates instructions counter in replay mode. */ +void replay_account_executed_instructions(void); + +/* Interrupts and exceptions */ + +/*! Called by exception handler to write or read + exception processing events. */ +bool replay_exception(void); +/*! Used to determine that exception is pending. + Does not proceed to the next event in the log. */ +bool replay_has_exception(void); +/*! Called by interrupt handlers to write or read + interrupt processing events. + \return true if interrupt should be processed */ +bool replay_interrupt(void); +/*! Tries to read interrupt event from the file. + Returns true, when interrupt request is pending */ +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); +/*! 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)) \ + : (value)) + +/* Events */ + +/*! Called when qemu shutdown is requested. */ +void replay_shutdown_request(void); +/*! Should be called at check points in the execution. + These check points are skipped, if they were not met. + Saves checkpoint in the SAVE mode and validates in the PLAY mode. + Returns 0 in PLAY mode if checkpoint was not found. + Returns 1 in all other cases. */ +bool replay_checkpoint(ReplayCheckpoint checkpoint); + +/* Asynchronous events queue */ + +/*! Disables storing events in the queue */ +void replay_disable_events(void); +/*! Returns true when saving events is enabled */ +bool replay_events_enabled(void); +/*! Adds bottom half event to the queue */ +void replay_bh_schedule_event(QEMUBH *bh); +/*! Adds input event to the queue */ +void replay_input_event(QemuConsole *src, InputEvent *evt); +/*! Adds input sync event to the queue */ +void replay_input_sync_event(void); + +#endif diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h index c439975..3bb8897 100644 --- a/include/sysemu/sysemu.h +++ b/include/sysemu/sysemu.h @@ -70,6 +70,7 @@ void qemu_system_killed(int signal, pid_t pid); void qemu_devices_reset(void); void qemu_system_reset(bool report); void qemu_system_guest_panicked(void); +size_t qemu_target_page_bits(void); void qemu_add_exit_notifier(Notifier *notify); void qemu_remove_exit_notifier(Notifier *notify); @@ -83,14 +84,52 @@ void hmp_info_snapshots(Monitor *mon, const QDict *qdict); void qemu_announce_self(void); +/* Subcommands for QEMU_VM_COMMAND */ +enum qemu_vm_cmd { + MIG_CMD_INVALID = 0, /* Must be 0 */ + MIG_CMD_OPEN_RETURN_PATH, /* Tell the dest to open the Return path */ + MIG_CMD_PING, /* Request a PONG on the RP */ + + MIG_CMD_POSTCOPY_ADVISE, /* Prior to any page transfers, just + warn we might want to do PC */ + MIG_CMD_POSTCOPY_LISTEN, /* Start listening for incoming + pages as it's running. */ + MIG_CMD_POSTCOPY_RUN, /* Start execution */ + + MIG_CMD_POSTCOPY_RAM_DISCARD, /* A list of pages to discard that + were previously sent during + precopy but are dirty. */ + MIG_CMD_PACKAGED, /* Send a wrapped stream within this stream */ + MIG_CMD_MAX +}; + +#define MAX_VM_CMD_PACKAGED_SIZE (1ul << 24) + bool qemu_savevm_state_blocked(Error **errp); void qemu_savevm_state_begin(QEMUFile *f, const MigrationParams *params); void qemu_savevm_state_header(QEMUFile *f); -int qemu_savevm_state_iterate(QEMUFile *f); -void qemu_savevm_state_complete(QEMUFile *f); -void qemu_savevm_state_cancel(void); -uint64_t qemu_savevm_state_pending(QEMUFile *f, uint64_t max_size); +int qemu_savevm_state_iterate(QEMUFile *f, bool postcopy); +void qemu_savevm_state_cleanup(void); +void qemu_savevm_state_complete_postcopy(QEMUFile *f); +void qemu_savevm_state_complete_precopy(QEMUFile *f, bool iterable_only); +void qemu_savevm_state_pending(QEMUFile *f, uint64_t max_size, + uint64_t *res_non_postcopiable, + uint64_t *res_postcopiable); +void qemu_savevm_command_send(QEMUFile *f, enum qemu_vm_cmd command, + uint16_t len, uint8_t *data); +void qemu_savevm_send_ping(QEMUFile *f, uint32_t value); +void qemu_savevm_send_open_return_path(QEMUFile *f); +int qemu_savevm_send_packaged(QEMUFile *f, const QEMUSizedBuffer *qsb); +void qemu_savevm_send_postcopy_advise(QEMUFile *f); +void qemu_savevm_send_postcopy_listen(QEMUFile *f); +void qemu_savevm_send_postcopy_run(QEMUFile *f); + +void qemu_savevm_send_postcopy_ram_discard(QEMUFile *f, const char *name, + uint16_t len, + uint64_t *start_list, + uint64_t *length_list); + int qemu_loadvm_state(QEMUFile *f); typedef enum DisplayType @@ -133,6 +172,7 @@ extern int boot_menu; extern bool boot_strict; extern uint8_t *boot_splash_filedata; extern size_t boot_splash_filedata_size; +extern bool enable_mlock; extern uint8_t qemu_extra_params_fw[2]; extern QEMUClockType rtc_clock; extern const char *mem_path; diff --git a/include/ui/input.h b/include/ui/input.h index 5d5ac00..d06a12d 100644 --- a/include/ui/input.h +++ b/include/ui/input.h @@ -33,7 +33,9 @@ void qemu_input_handler_bind(QemuInputHandlerState *s, const char *device_id, int head, Error **errp); void qemu_input_event_send(QemuConsole *src, InputEvent *evt); +void qemu_input_event_send_impl(QemuConsole *src, InputEvent *evt); void qemu_input_event_sync(void); +void qemu_input_event_sync_impl(void); InputEvent *qemu_input_event_new_key(KeyValue *key, bool down); void qemu_input_event_send_key(QemuConsole *src, KeyValue *key, bool down); |