diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/block/aio.h | 24 | ||||
| -rw-r--r-- | include/block/block.h | 36 | ||||
| -rw-r--r-- | include/block/block_int.h | 53 | ||||
| -rw-r--r-- | include/block/blockjob.h | 255 | ||||
| -rw-r--r-- | include/block/blockjob_int.h | 239 | ||||
| -rw-r--r-- | include/exec/exec-all.h | 2 | ||||
| -rw-r--r-- | include/exec/memory.h | 47 | ||||
| -rw-r--r-- | include/hw/i386/pc.h | 1 | ||||
| -rw-r--r-- | include/hw/xen/xen_backend.h | 72 | ||||
| -rw-r--r-- | include/hw/xen/xen_pvdev.h | 78 | ||||
| -rw-r--r-- | include/migration/colo.h | 38 | ||||
| -rw-r--r-- | include/migration/failover.h | 26 | ||||
| -rw-r--r-- | include/migration/migration.h | 8 | ||||
| -rw-r--r-- | include/monitor/monitor.h | 2 | ||||
| -rw-r--r-- | include/qemu/log.h | 16 | ||||
| -rw-r--r-- | include/qemu/rfifolock.h | 54 | ||||
| -rw-r--r-- | include/qemu/sockets.h | 2 | ||||
| -rw-r--r-- | include/qemu/thread-posix.h | 6 | ||||
| -rw-r--r-- | include/qemu/thread-win32.h | 10 | ||||
| -rw-r--r-- | include/qemu/thread.h | 3 | ||||
| -rw-r--r-- | include/qom/cpu.h | 31 | ||||
| -rw-r--r-- | include/sysemu/os-posix.h | 12 | ||||
| -rw-r--r-- | include/sysemu/os-win32.h | 15 |
23 files changed, 653 insertions, 377 deletions
diff --git a/include/block/aio.h b/include/block/aio.h index b9fe2cb37e..c7ae27c91c 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -18,7 +18,6 @@ #include "qemu/queue.h" #include "qemu/event_notifier.h" #include "qemu/thread.h" -#include "qemu/rfifolock.h" #include "qemu/timer.h" typedef struct BlockAIOCB BlockAIOCB; @@ -54,7 +53,7 @@ struct AioContext { GSource source; /* Protects all fields from multi-threaded access */ - RFifoLock lock; + QemuRecMutex lock; /* The list of registered AIO handlers */ QLIST_HEAD(, AioHandler) aio_handlers; @@ -116,9 +115,6 @@ struct AioContext { bool notified; EventNotifier notifier; - /* Scheduling this BH forces the event loop it iterate */ - QEMUBH *notify_dummy_bh; - /* Thread pool for performing work and receiving completion callbacks */ struct ThreadPool *thread_pool; @@ -453,6 +449,24 @@ static inline bool aio_node_check(AioContext *ctx, bool is_external) } /** + * Return the AioContext whose event loop runs in the current thread. + * + * If called from an IOThread this will be the IOThread's AioContext. If + * called from another thread it will be the main loop AioContext. + */ +AioContext *qemu_get_current_aio_context(void); + +/** + * @ctx: the aio context + * + * Return whether we are running in the I/O thread that manages @ctx. + */ +static inline bool aio_context_in_iothread(AioContext *ctx) +{ + return ctx == qemu_get_current_aio_context(); +} + +/** * aio_context_setup: * @ctx: the aio context * diff --git a/include/block/block.h b/include/block/block.h index 398a050176..49bb0b239a 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -7,16 +7,15 @@ #include "qemu/coroutine.h" #include "block/accounting.h" #include "block/dirty-bitmap.h" +#include "block/blockjob.h" #include "qapi/qmp/qobject.h" #include "qapi-types.h" #include "qemu/hbitmap.h" /* block.c */ 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 */ @@ -218,7 +217,7 @@ BlockDriverState *bdrv_open(const char *filename, const char *reference, BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue, BlockDriverState *bs, QDict *options, int flags); -int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp); +int bdrv_reopen_multiple(AioContext *ctx, BlockReopenQueue *bs_queue, Error **errp); int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp); int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue, Error **errp); @@ -332,8 +331,39 @@ int bdrv_flush_all(void); void bdrv_close_all(void); void bdrv_drain(BlockDriverState *bs); void coroutine_fn bdrv_co_drain(BlockDriverState *bs); +void bdrv_drain_all_begin(void); +void bdrv_drain_all_end(void); void bdrv_drain_all(void); +#define BDRV_POLL_WHILE(bs, cond) ({ \ + bool waited_ = false; \ + BlockDriverState *bs_ = (bs); \ + AioContext *ctx_ = bdrv_get_aio_context(bs_); \ + if (aio_context_in_iothread(ctx_)) { \ + while ((cond)) { \ + aio_poll(ctx_, true); \ + waited_ = true; \ + } \ + } else { \ + assert(qemu_get_current_aio_context() == \ + qemu_get_aio_context()); \ + /* Ask bdrv_dec_in_flight to wake up the main \ + * QEMU AioContext. Extra I/O threads never take \ + * other I/O threads' AioContexts (see for example \ + * block_job_defer_to_main_loop for how to do it). \ + */ \ + assert(!bs_->wakeup); \ + bs_->wakeup = true; \ + while ((cond)) { \ + aio_context_release(ctx_); \ + aio_poll(qemu_get_aio_context(), true); \ + aio_context_acquire(ctx_); \ + waited_ = true; \ + } \ + bs_->wakeup = false; \ + } \ + waited_; }) + int bdrv_pdiscard(BlockDriverState *bs, int64_t offset, int count); int bdrv_co_pdiscard(BlockDriverState *bs, int64_t offset, int count); int bdrv_has_zero_init_1(BlockDriverState *bs); diff --git a/include/block/block_int.h b/include/block/block_int.h index e96e9ada57..b02abbd618 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -62,8 +62,6 @@ enum BdrvTrackedRequestType { BDRV_TRACKED_READ, BDRV_TRACKED_WRITE, - BDRV_TRACKED_FLUSH, - BDRV_TRACKED_IOCTL, BDRV_TRACKED_DISCARD, }; @@ -445,7 +443,7 @@ struct BlockDriverState { note this is a reference count */ CoQueue flush_queue; /* Serializing flush queue */ - BdrvTrackedRequest *active_flush_req; /* Flush request in flight */ + bool active_flush_req; /* Flush request in flight? */ unsigned int write_gen; /* Current data generation */ unsigned int flushed_gen; /* Flushed write generation */ @@ -473,9 +471,12 @@ struct BlockDriverState { /* Callback before write request is processed */ NotifierWithReturnList before_write_notifiers; - /* number of in-flight serialising requests */ + /* number of in-flight requests; overall and serialising */ + unsigned int in_flight; unsigned int serialising_in_flight; + bool wakeup; + /* Offset after the highest byte written to */ uint64_t wr_highest_offset; @@ -634,6 +635,21 @@ void bdrv_remove_aio_context_notifier(BlockDriverState *bs, void (*aio_context_detached)(void *), void *opaque); +/** + * bdrv_wakeup: + * @bs: The BlockDriverState for which an I/O operation has been completed. + * + * Wake up the main thread if it is waiting on BDRV_POLL_WHILE. During + * synchronous I/O on a BlockDriverState that is attached to another + * I/O thread, the main thread lets the I/O thread's event loop run, + * waiting for the I/O operation to complete. A bdrv_wakeup will wake + * up the main thread if necessary. + * + * Manual calls to bdrv_wakeup are rarely necessary, because + * bdrv_dec_in_flight already calls it. + */ +void bdrv_wakeup(BlockDriverState *bs); + #ifdef _WIN32 int is_windows_drive(const char *filename); #endif @@ -649,8 +665,6 @@ int is_windows_drive(const char *filename); * the new backing file if the job completes. Ignored if @base is %NULL. * @speed: The maximum speed, in bytes per second, or 0 for unlimited. * @on_error: The action to take upon error. - * @cb: Completion function for the job. - * @opaque: Opaque pointer value passed to @cb. * @errp: Error object. * * Start a streaming operation on @bs. Clusters that are unallocated @@ -662,8 +676,7 @@ int is_windows_drive(const char *filename); */ void stream_start(const char *job_id, BlockDriverState *bs, BlockDriverState *base, const char *backing_file_str, - int64_t speed, BlockdevOnError on_error, - BlockCompletionFunc *cb, void *opaque, Error **errp); + int64_t speed, BlockdevOnError on_error, Error **errp); /** * commit_start: @@ -674,22 +687,22 @@ void stream_start(const char *job_id, BlockDriverState *bs, * @base: Block device that will be written into, and become the new top. * @speed: The maximum speed, in bytes per second, or 0 for unlimited. * @on_error: The action to take upon error. - * @cb: Completion function for the job. - * @opaque: Opaque pointer value passed to @cb. * @backing_file_str: String to use as the backing file in @top's overlay * @errp: Error object. * */ void commit_start(const char *job_id, BlockDriverState *bs, BlockDriverState *base, BlockDriverState *top, int64_t speed, - BlockdevOnError on_error, BlockCompletionFunc *cb, - void *opaque, const char *backing_file_str, Error **errp); + BlockdevOnError on_error, const char *backing_file_str, + Error **errp); /** * commit_active_start: * @job_id: The id of the newly-created job, or %NULL to use the * device name of @bs. * @bs: Active block device to be committed. * @base: Block device that will be written into, and become the new top. + * @creation_flags: Flags that control the behavior of the Job lifetime. + * See @BlockJobCreateFlags * @speed: The maximum speed, in bytes per second, or 0 for unlimited. * @on_error: The action to take upon error. * @cb: Completion function for the job. @@ -699,8 +712,8 @@ void commit_start(const char *job_id, BlockDriverState *bs, * */ void commit_active_start(const char *job_id, BlockDriverState *bs, - BlockDriverState *base, int64_t speed, - BlockdevOnError on_error, + BlockDriverState *base, int creation_flags, + int64_t speed, BlockdevOnError on_error, BlockCompletionFunc *cb, void *opaque, Error **errp, bool auto_complete); /* @@ -719,8 +732,6 @@ void commit_active_start(const char *job_id, BlockDriverState *bs, * @on_source_error: The action to take upon error reading from the source. * @on_target_error: The action to take upon error writing to the target. * @unmap: Whether to unmap target where source sectors only contain zeroes. - * @cb: Completion function for the job. - * @opaque: Opaque pointer value passed to @cb. * @errp: Error object. * * Start a mirroring operation on @bs. Clusters that are allocated @@ -734,9 +745,7 @@ void mirror_start(const char *job_id, BlockDriverState *bs, MirrorSyncMode mode, BlockMirrorBackingMode backing_mode, BlockdevOnError on_source_error, BlockdevOnError on_target_error, - bool unmap, - BlockCompletionFunc *cb, - void *opaque, Error **errp); + bool unmap, Error **errp); /* * backup_start: @@ -749,6 +758,8 @@ void mirror_start(const char *job_id, BlockDriverState *bs, * @sync_bitmap: The dirty bitmap if sync_mode is MIRROR_SYNC_MODE_INCREMENTAL. * @on_source_error: The action to take upon error reading from the source. * @on_target_error: The action to take upon error writing to the target. + * @creation_flags: Flags that control the behavior of the Job lifetime. + * See @BlockJobCreateFlags * @cb: Completion function for the job. * @opaque: Opaque pointer value passed to @cb. * @txn: Transaction that this job is part of (may be NULL). @@ -762,6 +773,7 @@ void backup_start(const char *job_id, BlockDriverState *bs, bool compress, BlockdevOnError on_source_error, BlockdevOnError on_target_error, + int creation_flags, BlockCompletionFunc *cb, void *opaque, BlockJobTxn *txn, Error **errp); @@ -787,6 +799,9 @@ 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); +void bdrv_inc_in_flight(BlockDriverState *bs); +void bdrv_dec_in_flight(BlockDriverState *bs); + void blockdev_close_all_bdrv_states(void); #endif /* BLOCK_INT_H */ diff --git a/include/block/blockjob.h b/include/block/blockjob.h index 4ddb4ae2e1..356cacf004 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -28,78 +28,15 @@ #include "block/block.h" -/** - * BlockJobDriver: - * - * A class type for block job driver. - */ -typedef struct BlockJobDriver { - /** Derived BlockJob struct size */ - size_t instance_size; - - /** String describing the operation, part of query-block-jobs QMP API */ - BlockJobType job_type; - - /** Optional callback for job types that support setting a speed limit */ - void (*set_speed)(BlockJob *job, int64_t speed, Error **errp); - - /** Optional callback for job types that need to forward I/O status reset */ - void (*iostatus_reset)(BlockJob *job); - - /** - * Optional callback for job types whose completion must be triggered - * 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); - - /** - * If the callback is not NULL, it will be invoked when the job transitions - * into the paused state. Paused jobs must not perform any asynchronous - * I/O or event loop activity. This callback is used to quiesce jobs. - */ - void coroutine_fn (*pause)(BlockJob *job); - - /** - * If the callback is not NULL, it will be invoked when the job transitions - * out of the paused state. Any asynchronous I/O or event loop activity - * should be restarted from this callback. - */ - void coroutine_fn (*resume)(BlockJob *job); - - /* - * If the callback is not NULL, it will be invoked before the job is - * resumed in a new AioContext. This is the place to move any resources - * besides job->blk to the new AioContext. - */ - void (*attached_aio_context)(BlockJob *job, AioContext *new_context); -} BlockJobDriver; +typedef struct BlockJobDriver BlockJobDriver; +typedef struct BlockJobTxn BlockJobTxn; /** * BlockJob: * * Long-running operation on a BlockDriverState. */ -struct BlockJob { +typedef struct BlockJob { /** The job type, including the job vtable. */ const BlockJobDriver *driver; @@ -107,7 +44,7 @@ struct BlockJob { BlockBackend *blk; /** - * The ID of the block job. + * The ID of the block job. May be NULL for internal jobs. */ char *id; @@ -181,6 +118,9 @@ struct BlockJob { /** Block other operations when block job is running */ Error *blocker; + /** BlockDriverStates that are involved in this block job */ + GSList *nodes; + /** The opaque value that is passed to the completion function. */ void *opaque; @@ -198,7 +138,12 @@ struct BlockJob { /** Non-NULL if this job is part of a transaction */ BlockJobTxn *txn; QLIST_ENTRY(BlockJob) txn_list; -}; +} BlockJob; + +typedef enum BlockJobCreateFlags { + BLOCK_JOB_DEFAULT = 0x00, + BLOCK_JOB_INTERNAL = 0x01, +} BlockJobCreateFlags; /** * block_job_next: @@ -222,74 +167,15 @@ BlockJob *block_job_next(BlockJob *job); BlockJob *block_job_get(const char *id); /** - * block_job_create: - * @job_id: The id of the newly-created job, or %NULL to have one - * generated automatically. - * @job_type: The class object for the newly-created job. - * @bs: The block - * @speed: The maximum speed, in bytes per second, or 0 for unlimited. - * @cb: Completion function for the job. - * @opaque: Opaque pointer value passed to @cb. - * @errp: Error object. - * - * Create a new long-running block device job and return it. The job - * will call @cb asynchronously when the job completes. Note that - * @bs may have been closed at the time the @cb it is called. If - * this is the case, the job may be reported as either cancelled or - * completed. - * - * This function is not part of the public job interface; it should be - * called from a wrapper that is specific to the job type. - */ -void *block_job_create(const char *job_id, const BlockJobDriver *driver, - BlockDriverState *bs, int64_t speed, - BlockCompletionFunc *cb, void *opaque, Error **errp); - -/** - * block_job_sleep_ns: - * @job: The job that calls the function. - * @clock: The clock to sleep on. - * @ns: How many nanoseconds to stop for. - * - * Put the job to sleep (assuming that it wasn't canceled) for @ns - * nanoseconds. Canceling the job will interrupt the wait immediately. - */ -void block_job_sleep_ns(BlockJob *job, QEMUClockType type, int64_t ns); - -/** - * block_job_yield: - * @job: The job that calls the function. - * - * Yield the block job coroutine. - */ -void block_job_yield(BlockJob *job); - -/** - * block_job_ref: - * @bs: The block device. - * - * Grab a reference to the block job. Should be paired with block_job_unref. - */ -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: - * @job: The job being completed. - * @ret: The status code. + * block_job_add_bdrv: + * @job: A block job + * @bs: A BlockDriverState that is involved in @job * - * Call the completion function that was registered at creation time, and - * free @job. + * Add @bs to the list of BlockDriverState that are involved in + * @job. This means that all operations will be blocked on @bs while + * @job exists. */ -void block_job_completed(BlockJob *job, int ret); +void block_job_add_bdrv(BlockJob *job, BlockDriverState *bs); /** * block_job_set_speed: @@ -320,29 +206,12 @@ void block_job_cancel(BlockJob *job); void block_job_complete(BlockJob *job, Error **errp); /** - * block_job_is_cancelled: - * @job: The job being queried. - * - * Returns whether the job is scheduled for cancellation. - */ -bool block_job_is_cancelled(BlockJob *job); - -/** * block_job_query: * @job: The job to get information about. * * Return information about a job. */ -BlockJobInfo *block_job_query(BlockJob *job); - -/** - * block_job_pause_point: - * @job: The job that is ready to pause. - * - * Pause now if block_job_pause() has been called. Block jobs that perform - * lots of I/O must call this between requests so that the job can be paused. - */ -void coroutine_fn block_job_pause_point(BlockJob *job); +BlockJobInfo *block_job_query(BlockJob *job, Error **errp); /** * block_job_pause: @@ -353,45 +222,38 @@ void coroutine_fn block_job_pause_point(BlockJob *job); void block_job_pause(BlockJob *job); /** - * block_job_resume: - * @job: The job to be resumed. - * - * Resume the specified job. Must be paired with a preceding block_job_pause. - */ -void block_job_resume(BlockJob *job); - -/** - * block_job_enter: - * @job: The job to enter. + * block_job_user_pause: + * @job: The job to be paused. * - * Continue the specified job by entering the coroutine. + * Asynchronously pause the specified job. + * Do not allow a resume until a matching call to block_job_user_resume. */ -void block_job_enter(BlockJob *job); +void block_job_user_pause(BlockJob *job); /** - * block_job_event_cancelled: - * @job: The job whose information is requested. + * block_job_paused: + * @job: The job to query. * - * Send a BLOCK_JOB_CANCELLED event for the specified job. + * Returns true if the job is user-paused. */ -void block_job_event_cancelled(BlockJob *job); +bool block_job_user_paused(BlockJob *job); /** - * block_job_ready: - * @job: The job which is now ready to complete. - * @msg: Error message. Only present on failure. + * block_job_resume: + * @job: The job to be resumed. * - * Send a BLOCK_JOB_COMPLETED event for the specified job. + * Resume the specified job. Must be paired with a preceding block_job_pause. */ -void block_job_event_completed(BlockJob *job, const char *msg); +void block_job_resume(BlockJob *job); /** - * block_job_ready: - * @job: The job which is now ready to complete. + * block_job_user_resume: + * @job: The job to be resumed. * - * Send a BLOCK_JOB_READY event for the specified job. + * Resume the specified job. + * Must be paired with a preceding block_job_user_pause. */ -void block_job_event_ready(BlockJob *job); +void block_job_user_resume(BlockJob *job); /** * block_job_cancel_sync: @@ -439,37 +301,6 @@ int block_job_complete_sync(BlockJob *job, Error **errp); void block_job_iostatus_reset(BlockJob *job); /** - * block_job_error_action: - * @job: The job to signal an error for. - * @on_err: The error action setting. - * @is_read: Whether the operation was a read. - * @error: The error that was reported. - * - * Report an I/O error for a block job and possibly stop the VM. Return the - * action that was selected based on @on_err and @error. - */ -BlockErrorAction block_job_error_action(BlockJob *job, BlockdevOnError on_err, - int is_read, int error); - -typedef void BlockJobDeferToMainLoopFn(BlockJob *job, void *opaque); - -/** - * block_job_defer_to_main_loop: - * @job: The job - * @fn: The function to run in the main loop - * @opaque: The opaque value that is passed to @fn - * - * Execute a given function in the main loop with the BlockDriverState - * AioContext acquired. Block jobs must call bdrv_unref(), bdrv_close(), and - * anything that uses bdrv_drain_all() in the main loop. - * - * The @job AioContext is held while @fn executes. - */ -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 @@ -504,4 +335,12 @@ void block_job_txn_unref(BlockJobTxn *txn); */ void block_job_txn_add_job(BlockJobTxn *txn, BlockJob *job); +/** + * block_job_is_internal: + * @job: The job to determine if it is user-visible or not. + * + * Returns true if the job should not be visible to the management layer. + */ +bool block_job_is_internal(BlockJob *job); + #endif diff --git a/include/block/blockjob_int.h b/include/block/blockjob_int.h new file mode 100644 index 0000000000..40275e4437 --- /dev/null +++ b/include/block/blockjob_int.h @@ -0,0 +1,239 @@ +/* + * Declarations for long-running block device operations + * + * Copyright (c) 2011 IBM Corp. + * Copyright (c) 2012 Red Hat, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef BLOCKJOB_INT_H +#define BLOCKJOB_INT_H + +#include "block/blockjob.h" +#include "block/block.h" + +/** + * BlockJobDriver: + * + * A class type for block job driver. + */ +struct BlockJobDriver { + /** Derived BlockJob struct size */ + size_t instance_size; + + /** String describing the operation, part of query-block-jobs QMP API */ + BlockJobType job_type; + + /** Optional callback for job types that support setting a speed limit */ + void (*set_speed)(BlockJob *job, int64_t speed, Error **errp); + + /** Optional callback for job types that need to forward I/O status reset */ + void (*iostatus_reset)(BlockJob *job); + + /** + * Optional callback for job types whose completion must be triggered + * 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); + + /** + * If the callback is not NULL, it will be invoked when the job transitions + * into the paused state. Paused jobs must not perform any asynchronous + * I/O or event loop activity. This callback is used to quiesce jobs. + */ + void coroutine_fn (*pause)(BlockJob *job); + + /** + * If the callback is not NULL, it will be invoked when the job transitions + * out of the paused state. Any asynchronous I/O or event loop activity + * should be restarted from this callback. + */ + void coroutine_fn (*resume)(BlockJob *job); + + /* + * If the callback is not NULL, it will be invoked before the job is + * resumed in a new AioContext. This is the place to move any resources + * besides job->blk to the new AioContext. + */ + void (*attached_aio_context)(BlockJob *job, AioContext *new_context); + + /* + * If the callback is not NULL, it will be invoked when the job has to be + * synchronously cancelled or completed; it should drain BlockDriverStates + * as required to ensure progress. + */ + void (*drain)(BlockJob *job); +}; + +/** + * block_job_create: + * @job_id: The id of the newly-created job, or %NULL to have one + * generated automatically. + * @job_type: The class object for the newly-created job. + * @bs: The block + * @speed: The maximum speed, in bytes per second, or 0 for unlimited. + * @cb: Completion function for the job. + * @opaque: Opaque pointer value passed to @cb. + * @errp: Error object. + * + * Create a new long-running block device job and return it. The job + * will call @cb asynchronously when the job completes. Note that + * @bs may have been closed at the time the @cb it is called. If + * this is the case, the job may be reported as either cancelled or + * completed. + * + * This function is not part of the public job interface; it should be + * called from a wrapper that is specific to the job type. + */ +void *block_job_create(const char *job_id, const BlockJobDriver *driver, + BlockDriverState *bs, int64_t speed, int flags, + BlockCompletionFunc *cb, void *opaque, Error **errp); + +/** + * block_job_sleep_ns: + * @job: The job that calls the function. + * @clock: The clock to sleep on. + * @ns: How many nanoseconds to stop for. + * + * Put the job to sleep (assuming that it wasn't canceled) for @ns + * nanoseconds. Canceling the job will interrupt the wait immediately. + */ +void block_job_sleep_ns(BlockJob *job, QEMUClockType type, int64_t ns); + +/** + * block_job_yield: + * @job: The job that calls the function. + * + * Yield the block job coroutine. + */ +void block_job_yield(BlockJob *job); + +/** + * block_job_ref: + * @bs: The block device. + * + * Grab a reference to the block job. Should be paired with block_job_unref. + */ +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: + * @job: The job being completed. + * @ret: The status code. + * + * Call the completion function that was registered at creation time, and + * free @job. + */ +void block_job_completed(BlockJob *job, int ret); + +/** + * block_job_is_cancelled: + * @job: The job being queried. + * + * Returns whether the job is scheduled for cancellation. + */ +bool block_job_is_cancelled(BlockJob *job); + +/** + * block_job_pause_point: + * @job: The job that is ready to pause. + * + * Pause now if block_job_pause() has been called. Block jobs that perform + * lots of I/O must call this between requests so that the job can be paused. + */ +void coroutine_fn block_job_pause_point(BlockJob *job); + +/** + * block_job_enter: + * @job: The job to enter. + * + * Continue the specified job by entering the coroutine. + */ +void block_job_enter(BlockJob *job); + +/** + * block_job_event_ready: + * @job: The job which is now ready to be completed. + * + * Send a BLOCK_JOB_READY event for the specified job. + */ +void block_job_event_ready(BlockJob *job); + +/** + * block_job_error_action: + * @job: The job to signal an error for. + * @on_err: The error action setting. + * @is_read: Whether the operation was a read. + * @error: The error that was reported. + * + * Report an I/O error for a block job and possibly stop the VM. Return the + * action that was selected based on @on_err and @error. + */ +BlockErrorAction block_job_error_action(BlockJob *job, BlockdevOnError on_err, + int is_read, int error); + +typedef void BlockJobDeferToMainLoopFn(BlockJob *job, void *opaque); + +/** + * block_job_defer_to_main_loop: + * @job: The job + * @fn: The function to run in the main loop + * @opaque: The opaque value that is passed to @fn + * + * Execute a given function in the main loop with the BlockDriverState + * AioContext acquired. Block jobs must call bdrv_unref(), bdrv_close(), and + * anything that uses bdrv_drain_all() in the main loop. + * + * The @job AioContext is held while @fn executes. + */ +void block_job_defer_to_main_loop(BlockJob *job, + BlockJobDeferToMainLoopFn *fn, + void *opaque); + +#endif diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index cb624e4acc..a8c13cee66 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -316,6 +316,7 @@ static inline void tb_set_jmp_target(TranslationBlock *tb, #endif +/* Called with tb_lock held. */ static inline void tb_add_jump(TranslationBlock *tb, int n, TranslationBlock *tb_next) { @@ -369,6 +370,7 @@ void tlb_fill(CPUState *cpu, target_ulong addr, MMUAccessType access_type, #if defined(CONFIG_USER_ONLY) void mmap_lock(void); void mmap_unlock(void); +bool have_mmap_lock(void); static inline tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr) { diff --git a/include/exec/memory.h b/include/exec/memory.h index 79ccaaba1f..9728a2fb1a 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -209,7 +209,7 @@ struct MemoryRegion { void (*destructor)(MemoryRegion *mr); uint64_t align; bool terminates; - bool skip_dump; + bool ram_device; bool enabled; bool warning_printed; /* For reservations */ uint8_t vga_logging_count; @@ -449,6 +449,30 @@ void memory_region_init_ram_ptr(MemoryRegion *mr, void *ptr); /** + * memory_region_init_ram_device_ptr: Initialize RAM device memory region from + * a user-provided pointer. + * + * A RAM device represents a mapping to a physical device, such as to a PCI + * MMIO BAR of an vfio-pci assigned device. The memory region may be mapped + * into the VM address space and access to the region will modify memory + * directly. However, the memory region should not be included in a memory + * dump (device may not be enabled/mapped at the time of the dump), and + * operations incompatible with manipulating MMIO should be avoided. Replaces + * skip_dump flag. + * + * @mr: the #MemoryRegion to be initialized. + * @owner: the object that tracks the region's reference count + * @name: the name of the region. + * @size: size of the region. + * @ptr: memory to be mapped; must contain at least @size bytes. + */ +void memory_region_init_ram_device_ptr(MemoryRegion *mr, + struct Object *owner, + const char *name, + uint64_t size, + void *ptr); + +/** * memory_region_init_alias: Initialize a memory region that aliases all or a * part of another memory region. * @@ -574,22 +598,13 @@ static inline bool memory_region_is_ram(MemoryRegion *mr) } /** - * memory_region_is_skip_dump: check whether a memory region should not be - * dumped - * - * Returns %true is a memory region should not be dumped(e.g. VFIO BAR MMAP). + * memory_region_is_ram_device: check whether a memory region is a ram device * - * @mr: the memory region being queried - */ -bool memory_region_is_skip_dump(MemoryRegion *mr); - -/** - * memory_region_set_skip_dump: Set skip_dump flag, dump will ignore this memory - * region + * Returns %true is a memory region is a device backed ram region * * @mr: the memory region being queried */ -void memory_region_set_skip_dump(MemoryRegion *mr); +bool memory_region_is_ram_device(MemoryRegion *mr); /** * memory_region_is_romd: check whether a memory region is in ROMD mode @@ -1465,9 +1480,11 @@ void *qemu_map_ram_ptr(RAMBlock *ram_block, ram_addr_t addr); static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write) { if (is_write) { - return memory_region_is_ram(mr) && !mr->readonly; + return memory_region_is_ram(mr) && + !mr->readonly && !memory_region_is_ram_device(mr); } else { - return memory_region_is_ram(mr) || memory_region_is_romd(mr); + return (memory_region_is_ram(mr) && !memory_region_is_ram_device(mr)) || + memory_region_is_romd(mr); } } diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index 17fff80c8a..98dc7722c3 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -13,7 +13,6 @@ #include "qemu/bitmap.h" #include "sysemu/sysemu.h" #include "hw/pci/pci.h" -#include "hw/boards.h" #include "hw/compat.h" #include "hw/mem/pc-dimm.h" #include "hw/mem/nvdimm.h" diff --git a/include/hw/xen/xen_backend.h b/include/hw/xen/xen_backend.h index 0df282ab5f..cbda40ee53 100644 --- a/include/hw/xen/xen_backend.h +++ b/include/hw/xen/xen_backend.h @@ -2,60 +2,10 @@ #define QEMU_HW_XEN_BACKEND_H #include "hw/xen/xen_common.h" +#include "hw/xen/xen_pvdev.h" #include "sysemu/sysemu.h" #include "net/net.h" -/* ------------------------------------------------------------- */ - -#define XEN_BUFSIZE 1024 - -struct XenDevice; - -/* driver uses grant tables -> open gntdev device (xendev->gnttabdev) */ -#define DEVOPS_FLAG_NEED_GNTDEV 1 -/* don't expect frontend doing correct state transitions (aka console quirk) */ -#define DEVOPS_FLAG_IGNORE_STATE 2 - -struct XenDevOps { - size_t size; - uint32_t flags; - void (*alloc)(struct XenDevice *xendev); - int (*init)(struct XenDevice *xendev); - int (*initialise)(struct XenDevice *xendev); - void (*connected)(struct XenDevice *xendev); - void (*event)(struct XenDevice *xendev); - void (*disconnect)(struct XenDevice *xendev); - int (*free)(struct XenDevice *xendev); - void (*backend_changed)(struct XenDevice *xendev, const char *node); - void (*frontend_changed)(struct XenDevice *xendev, const char *node); - int (*backend_register)(void); -}; - -struct XenDevice { - const char *type; - int dom; - int dev; - char name[64]; - int debug; - - enum xenbus_state be_state; - enum xenbus_state fe_state; - int online; - char be[XEN_BUFSIZE]; - char *fe; - char *protocol; - int remote_port; - int local_port; - - xenevtchn_handle *evtchndev; - xengnttab_handle *gnttabdev; - - struct XenDevOps *ops; - QTAILQ_ENTRY(XenDevice) next; -}; - -/* ------------------------------------------------------------- */ - /* variables */ extern xc_interface *xen_xc; extern xenforeignmemory_handle *xen_fmem; @@ -63,26 +13,20 @@ extern struct xs_handle *xenstore; extern const char *xen_protocol; extern DeviceState *xen_sysdev; -/* xenstore helper functions */ int xenstore_mkdir(char *path, int p); -int xenstore_write_str(const char *base, const char *node, const char *val); -int xenstore_write_int(const char *base, const char *node, int ival); -int xenstore_write_int64(const char *base, const char *node, int64_t ival); -char *xenstore_read_str(const char *base, const char *node); -int xenstore_read_int(const char *base, const char *node, int *ival); - int xenstore_write_be_str(struct XenDevice *xendev, const char *node, const char *val); int xenstore_write_be_int(struct XenDevice *xendev, const char *node, int ival); int xenstore_write_be_int64(struct XenDevice *xendev, const char *node, int64_t ival); char *xenstore_read_be_str(struct XenDevice *xendev, const char *node); int xenstore_read_be_int(struct XenDevice *xendev, const char *node, int *ival); +void xenstore_update_fe(char *watch, struct XenDevice *xendev); +void xenstore_update_be(char *watch, char *type, int dom, + struct XenDevOps *ops); char *xenstore_read_fe_str(struct XenDevice *xendev, const char *node); int xenstore_read_fe_int(struct XenDevice *xendev, const char *node, int *ival); -int xenstore_read_uint64(const char *base, const char *node, uint64_t *uval); -int xenstore_read_fe_uint64(struct XenDevice *xendev, const char *node, uint64_t *uval); +int xenstore_read_fe_uint64(struct XenDevice *xendev, const char *node, + uint64_t *uval); -const char *xenbus_strstate(enum xenbus_state state); -struct XenDevice *xen_be_find_xendev(const char *type, int dom, int dev); void xen_be_check_state(struct XenDevice *xendev); /* xen backend driver bits */ @@ -91,10 +35,6 @@ void xen_be_register_common(void); int xen_be_register(const char *type, struct XenDevOps *ops); int xen_be_set_state(struct XenDevice *xendev, enum xenbus_state state); int xen_be_bind_evtchn(struct XenDevice *xendev); -void xen_be_unbind_evtchn(struct XenDevice *xendev); -int xen_be_send_notify(struct XenDevice *xendev); -void xen_be_printf(struct XenDevice *xendev, int msg_level, const char *fmt, ...) - GCC_FMT_ATTR(3, 4); /* actual backend drivers */ extern struct XenDevOps xen_console_ops; /* xen_console.c */ diff --git a/include/hw/xen/xen_pvdev.h b/include/hw/xen/xen_pvdev.h new file mode 100644 index 0000000000..083f0a9cc7 --- /dev/null +++ b/include/hw/xen/xen_pvdev.h @@ -0,0 +1,78 @@ +#ifndef QEMU_HW_XEN_PVDEV_H +#define QEMU_HW_XEN_PVDEV_H + +#include "hw/xen/xen_common.h" +/* ------------------------------------------------------------- */ + +#define XEN_BUFSIZE 1024 + +struct XenDevice; + +/* driver uses grant tables -> open gntdev device (xendev->gnttabdev) */ +#define DEVOPS_FLAG_NEED_GNTDEV 1 +/* don't expect frontend doing correct state transitions (aka console quirk) */ +#define DEVOPS_FLAG_IGNORE_STATE 2 + +struct XenDevOps { + size_t size; + uint32_t flags; + void (*alloc)(struct XenDevice *xendev); + int (*init)(struct XenDevice *xendev); + int (*initialise)(struct XenDevice *xendev); + void (*connected)(struct XenDevice *xendev); + void (*event)(struct XenDevice *xendev); + void (*disconnect)(struct XenDevice *xendev); + int (*free)(struct XenDevice *xendev); + void (*backend_changed)(struct XenDevice *xendev, const char *node); + void (*frontend_changed)(struct XenDevice *xendev, const char *node); + int (*backend_register)(void); +}; + +struct XenDevice { + const char *type; + int dom; + int dev; + char name[64]; + int debug; + + enum xenbus_state be_state; + enum xenbus_state fe_state; + int online; + char be[XEN_BUFSIZE]; + char *fe; + char *protocol; + int remote_port; + int local_port; + + xenevtchn_handle *evtchndev; + xengnttab_handle *gnttabdev; + + struct XenDevOps *ops; + QTAILQ_ENTRY(XenDevice) next; +}; + +/* ------------------------------------------------------------- */ + +/* xenstore helper functions */ +int xenstore_write_str(const char *base, const char *node, const char *val); +int xenstore_write_int(const char *base, const char *node, int ival); +int xenstore_write_int64(const char *base, const char *node, int64_t ival); +char *xenstore_read_str(const char *base, const char *node); +int xenstore_read_int(const char *base, const char *node, int *ival); +int xenstore_read_uint64(const char *base, const char *node, uint64_t *uval); +void xenstore_update(void *unused); + +const char *xenbus_strstate(enum xenbus_state state); + +void xen_pv_evtchn_event(void *opaque); +void xen_pv_insert_xendev(struct XenDevice *xendev); +void xen_pv_del_xendev(struct XenDevice *xendev); +struct XenDevice *xen_pv_find_xendev(const char *type, int dom, int dev); + +void xen_pv_unbind_evtchn(struct XenDevice *xendev); +int xen_pv_send_notify(struct XenDevice *xendev); + +void xen_pv_printf(struct XenDevice *xendev, int msg_level, + const char *fmt, ...) GCC_FMT_ATTR(3, 4); + +#endif /* QEMU_HW_XEN_PVDEV_H */ diff --git a/include/migration/colo.h b/include/migration/colo.h new file mode 100644 index 0000000000..e32eef4763 --- /dev/null +++ b/include/migration/colo.h @@ -0,0 +1,38 @@ +/* + * COarse-grain LOck-stepping Virtual Machines for Non-stop Service (COLO) + * (a.k.a. Fault Tolerance or Continuous Replication) + * + * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO., LTD. + * Copyright (c) 2016 FUJITSU LIMITED + * Copyright (c) 2016 Intel Corporation + * + * 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_COLO_H +#define QEMU_COLO_H + +#include "qemu-common.h" +#include "migration/migration.h" +#include "qemu/coroutine_int.h" +#include "qemu/thread.h" +#include "qemu/main-loop.h" + +bool colo_supported(void); +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 *colo_process_incoming_thread(void *opaque); +bool migration_incoming_in_colo_state(void); + +COLOMode get_colo_mode(void); + +/* failover */ +void colo_do_failover(MigrationState *s); +#endif diff --git a/include/migration/failover.h b/include/migration/failover.h new file mode 100644 index 0000000000..ad91ef2381 --- /dev/null +++ b/include/migration/failover.h @@ -0,0 +1,26 @@ +/* + * COarse-grain LOck-stepping Virtual Machines for Non-stop Service (COLO) + * (a.k.a. Fault Tolerance or Continuous Replication) + * + * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO.,LTD. + * Copyright (c) 2016 FUJITSU LIMITED + * Copyright (c) 2016 Intel Corporation + * + * 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_FAILOVER_H +#define QEMU_FAILOVER_H + +#include "qemu-common.h" +#include "qapi-types.h" + +void failover_init_state(void); +FailoverStatus failover_set_state(FailoverStatus old_state, + FailoverStatus new_state); +FailoverStatus failover_get_state(void); +void failover_request_active(Error **errp); +bool failover_request_is_active(void); + +#endif diff --git a/include/migration/migration.h b/include/migration/migration.h index 2791b90c00..c309d23370 100644 --- a/include/migration/migration.h +++ b/include/migration/migration.h @@ -21,6 +21,7 @@ #include "migration/vmstate.h" #include "qapi-types.h" #include "exec/cpu-common.h" +#include "qemu/coroutine_int.h" #define QEMU_VM_FILE_MAGIC 0x5145564d #define QEMU_VM_FILE_VERSION_COMPAT 0x00000002 @@ -107,6 +108,12 @@ struct MigrationIncomingState { QEMUBH *bh; int state; + + bool have_colo_incoming_thread; + QemuThread colo_incoming_thread; + /* The coroutine we should enter (back) after failover */ + Coroutine *migration_incoming_co; + /* See savevm.c */ LoadStateEntry_Head loadvm_handlers; }; @@ -298,6 +305,7 @@ int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen); int migrate_use_xbzrle(void); int64_t migrate_xbzrle_cache_size(void); +bool migrate_colo_enabled(void); int64_t xbzrle_cache_resize(int64_t new_size); diff --git a/include/monitor/monitor.h b/include/monitor/monitor.h index a714d8ef80..8cc532ec0e 100644 --- a/include/monitor/monitor.h +++ b/include/monitor/monitor.h @@ -9,7 +9,7 @@ extern Monitor *cur_mon; /* flags for monitor_init */ -#define MONITOR_IS_DEFAULT 0x01 +/* 0x01 unused */ #define MONITOR_USE_READLINE 0x02 #define MONITOR_USE_CONTROL 0x04 #define MONITOR_USE_PRETTY 0x08 diff --git a/include/qemu/log.h b/include/qemu/log.h index 00bf37fc0f..a50e994c21 100644 --- a/include/qemu/log.h +++ b/include/qemu/log.h @@ -51,6 +51,22 @@ static inline bool qemu_loglevel_mask(int mask) return (qemu_loglevel & mask) != 0; } +/* Lock output for a series of related logs. Since this is not needed + * for a single qemu_log / qemu_log_mask / qemu_log_mask_and_addr, we + * assume that qemu_loglevel_mask has already been tested, and that + * qemu_loglevel is never set when qemu_logfile is unset. + */ + +static inline void qemu_log_lock(void) +{ + qemu_flockfile(qemu_logfile); +} + +static inline void qemu_log_unlock(void) +{ + qemu_funlockfile(qemu_logfile); +} + /* Logging functions: */ /* main logging function diff --git a/include/qemu/rfifolock.h b/include/qemu/rfifolock.h deleted file mode 100644 index b23ab538a6..0000000000 --- a/include/qemu/rfifolock.h +++ /dev/null @@ -1,54 +0,0 @@ -/* - * Recursive FIFO lock - * - * Copyright Red Hat, Inc. 2013 - * - * Authors: - * Stefan Hajnoczi <stefanha@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_RFIFOLOCK_H -#define QEMU_RFIFOLOCK_H - -#include "qemu/thread.h" - -/* Recursive FIFO lock - * - * This lock provides more features than a plain mutex: - * - * 1. Fairness - enforces FIFO order. - * 2. Nesting - can be taken recursively. - * 3. Contention callback - optional, called when thread must wait. - * - * The recursive FIFO lock is heavyweight so prefer other synchronization - * primitives if you do not need its features. - */ -typedef struct { - QemuMutex lock; /* protects all fields */ - - /* FIFO order */ - unsigned int head; /* active ticket number */ - unsigned int tail; /* waiting ticket number */ - QemuCond cond; /* used to wait for our ticket number */ - - /* Nesting */ - QemuThread owner_thread; /* thread that currently has ownership */ - unsigned int nesting; /* amount of nesting levels */ - - /* Contention callback */ - void (*cb)(void *); /* called when thread must wait, with ->lock - * held so it may not recursively lock/unlock - */ - void *cb_opaque; -} RFifoLock; - -void rfifolock_init(RFifoLock *r, void (*cb)(void *), void *opaque); -void rfifolock_destroy(RFifoLock *r); -void rfifolock_lock(RFifoLock *r); -void rfifolock_unlock(RFifoLock *r); - -#endif /* QEMU_RFIFOLOCK_H */ diff --git a/include/qemu/sockets.h b/include/qemu/sockets.h index 9eb24707df..5589e6842b 100644 --- a/include/qemu/sockets.h +++ b/include/qemu/sockets.h @@ -34,6 +34,8 @@ typedef void NonBlockingConnectHandler(int fd, Error *err, void *opaque); InetSocketAddress *inet_parse(const char *str, Error **errp); int inet_connect(const char *str, Error **errp); +int inet_connect_saddr(InetSocketAddress *saddr, Error **errp, + NonBlockingConnectHandler *callback, void *opaque); NetworkAddressFamily inet_netfamily(int family); diff --git a/include/qemu/thread-posix.h b/include/qemu/thread-posix.h index aa03567e5e..09d1e15728 100644 --- a/include/qemu/thread-posix.h +++ b/include/qemu/thread-posix.h @@ -4,6 +4,12 @@ #include <pthread.h> #include <semaphore.h> +typedef QemuMutex QemuRecMutex; +#define qemu_rec_mutex_destroy qemu_mutex_destroy +#define qemu_rec_mutex_lock qemu_mutex_lock +#define qemu_rec_mutex_try_lock qemu_mutex_try_lock +#define qemu_rec_mutex_unlock qemu_mutex_unlock + struct QemuMutex { pthread_mutex_t lock; }; diff --git a/include/qemu/thread-win32.h b/include/qemu/thread-win32.h index c7ce8dcd45..5fb6541ae9 100644 --- a/include/qemu/thread-win32.h +++ b/include/qemu/thread-win32.h @@ -8,6 +8,16 @@ struct QemuMutex { LONG owner; }; +typedef struct QemuRecMutex QemuRecMutex; +struct QemuRecMutex { + CRITICAL_SECTION lock; +}; + +void qemu_rec_mutex_destroy(QemuRecMutex *mutex); +void qemu_rec_mutex_lock(QemuRecMutex *mutex); +int qemu_rec_mutex_trylock(QemuRecMutex *mutex); +void qemu_rec_mutex_unlock(QemuRecMutex *mutex); + struct QemuCond { LONG waiters, target; HANDLE sema; diff --git a/include/qemu/thread.h b/include/qemu/thread.h index 31237e93ee..e8e665f020 100644 --- a/include/qemu/thread.h +++ b/include/qemu/thread.h @@ -25,6 +25,9 @@ void qemu_mutex_lock(QemuMutex *mutex); int qemu_mutex_trylock(QemuMutex *mutex); void qemu_mutex_unlock(QemuMutex *mutex); +/* Prototypes for other functions are in thread-posix.h/thread-win32.h. */ +void qemu_rec_mutex_init(QemuRecMutex *mutex); + void qemu_cond_init(QemuCond *cond); void qemu_cond_destroy(QemuCond *cond); diff --git a/include/qom/cpu.h b/include/qom/cpu.h index 633c3fc124..3f79a8e955 100644 --- a/include/qom/cpu.h +++ b/include/qom/cpu.h @@ -231,7 +231,25 @@ struct kvm_run; #define TB_JMP_CACHE_SIZE (1 << TB_JMP_CACHE_BITS) /* work queue */ -typedef void (*run_on_cpu_func)(CPUState *cpu, void *data); + +/* The union type allows passing of 64 bit target pointers on 32 bit + * hosts in a single parameter + */ +typedef union { + int host_int; + unsigned long host_ulong; + void *host_ptr; + vaddr target_ptr; +} run_on_cpu_data; + +#define RUN_ON_CPU_HOST_PTR(p) ((run_on_cpu_data){.host_ptr = (p)}) +#define RUN_ON_CPU_HOST_INT(i) ((run_on_cpu_data){.host_int = (i)}) +#define RUN_ON_CPU_HOST_ULONG(ul) ((run_on_cpu_data){.host_ulong = (ul)}) +#define RUN_ON_CPU_TARGET_PTR(v) ((run_on_cpu_data){.target_ptr = (v)}) +#define RUN_ON_CPU_NULL RUN_ON_CPU_HOST_PTR(NULL) + +typedef void (*run_on_cpu_func)(CPUState *cpu, run_on_cpu_data data); + struct qemu_work_item; /** @@ -319,7 +337,10 @@ struct CPUState { MemoryRegion *memory; void *env_ptr; /* CPUArchState */ + + /* Writes protected by tb_lock, reads not thread-safe */ struct TranslationBlock *tb_jmp_cache[TB_JMP_CACHE_SIZE]; + struct GDBRegisterState *gdb_regs; int gdb_num_regs; int gdb_num_g_regs; @@ -634,7 +655,7 @@ bool cpu_is_stopped(CPUState *cpu); * * Used internally in the implementation of run_on_cpu. */ -void do_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data, +void do_run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data, QemuMutex *mutex); /** @@ -645,7 +666,7 @@ void do_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data, * * Schedules the function @func for execution on the vCPU @cpu. */ -void run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data); +void run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data); /** * async_run_on_cpu: @@ -655,7 +676,7 @@ void run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data); * * Schedules the function @func for execution on the vCPU @cpu asynchronously. */ -void async_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data); +void async_run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data); /** * async_safe_run_on_cpu: @@ -669,7 +690,7 @@ void async_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data); * Unlike run_on_cpu and async_run_on_cpu, the function is run outside the * BQL. */ -void async_safe_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data); +void async_safe_run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data); /** * qemu_get_cpu: diff --git a/include/sysemu/os-posix.h b/include/sysemu/os-posix.h index 3cfedbc28b..b0a6c0695b 100644 --- a/include/sysemu/os-posix.h +++ b/include/sysemu/os-posix.h @@ -87,4 +87,16 @@ void *qemu_alloc_stack(size_t *sz); */ void qemu_free_stack(void *stack, size_t sz); +/* POSIX and Mingw32 differ in the name of the stdio lock functions. */ + +static inline void qemu_flockfile(FILE *f) +{ + flockfile(f); +} + +static inline void qemu_funlockfile(FILE *f) +{ + funlockfile(f); +} + #endif diff --git a/include/sysemu/os-win32.h b/include/sysemu/os-win32.h index 17aad3b20f..ff18b23db1 100644 --- a/include/sysemu/os-win32.h +++ b/include/sysemu/os-win32.h @@ -103,6 +103,21 @@ static inline char *realpath(const char *path, char *resolved_path) return resolved_path; } +/* ??? Mingw appears to export _lock_file and _unlock_file as the functions + * with which to lock a stdio handle. But something is wrong in the markup, + * either in the header or the library, such that we get undefined references + * to "_imp___lock_file" etc when linking. Since we seem to have no other + * alternative, and the usage within the logging functions isn't critical, + * ignore FILE locking. + */ + +static inline void qemu_flockfile(FILE *f) +{ +} + +static inline void qemu_funlockfile(FILE *f) +{ +} /* We wrap all the sockets functions so that we can * set errno based on WSAGetLastError() |