diff options
Diffstat (limited to 'include')
43 files changed, 1023 insertions, 591 deletions
diff --git a/include/block/block_int.h b/include/block/block_int.h index 76b589da57..6c0927bce3 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -1029,7 +1029,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, BlockdevOnError on_target_error, int creation_flags, BlockCompletionFunc *cb, void *opaque, - BlockJobTxn *txn, Error **errp); + JobTxn *txn, Error **errp); void hmp_drive_add_node(Monitor *mon, const char *optstr); diff --git a/include/block/blockjob.h b/include/block/blockjob.h index 0f56f723de..32c00b7dc0 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -26,13 +26,13 @@ #ifndef BLOCKJOB_H #define BLOCKJOB_H +#include "qemu/job.h" #include "block/block.h" #include "qemu/ratelimit.h" #define BLOCK_JOB_SLICE_TIME 100000000ULL /* ns */ typedef struct BlockJobDriver BlockJobDriver; -typedef struct BlockJobTxn BlockJobTxn; /** * BlockJob: @@ -40,141 +40,40 @@ typedef struct BlockJobTxn BlockJobTxn; * Long-running operation on a BlockDriverState. */ typedef struct BlockJob { - /** The job type, including the job vtable. */ - const BlockJobDriver *driver; + /** Data belonging to the generic Job infrastructure */ + Job job; /** The block device on which the job is operating. */ BlockBackend *blk; - /** - * The ID of the block job. May be NULL for internal jobs. - */ - char *id; - - /** - * The coroutine that executes the job. If not NULL, it is - * reentered when busy is false and the job is cancelled. - */ - Coroutine *co; - - /** - * Set to true if the job should cancel itself. The flag must - * always be tested just before toggling the busy flag from false - * to true. After a job has been cancelled, it should only yield - * if #aio_poll will ("sooner or later") reenter the coroutine. - */ - bool cancelled; - - /** - * Set to true if the job should abort immediately without waiting - * for data to be in sync. - */ - bool force; - - /** - * Counter for pause request. If non-zero, the block job is either paused, - * or if busy == true will pause itself as soon as possible. - */ - int pause_count; - - /** - * Set to true if the job is paused by user. Can be unpaused with the - * block-job-resume QMP command. - */ - bool user_paused; - - /** - * Set to false by the job while the coroutine has yielded and may be - * re-entered by block_job_enter(). There may still be I/O or event loop - * activity pending. Accessed under block_job_mutex (in blockjob.c). - */ - bool busy; - - /** - * Set to true by the job while it is in a quiescent state, where - * no I/O or event loop activity is pending. - */ - bool paused; - - /** - * Set to true when the job is ready to be completed. - */ - bool ready; - - /** - * Set to true when the job has deferred work to the main loop. - */ - bool deferred_to_main_loop; - - /** Element of the list of block jobs */ - QLIST_ENTRY(BlockJob) job_list; - /** Status that is published by the query-block-jobs QMP API */ BlockDeviceIoStatus iostatus; - /** Offset that is published by the query-block-jobs QMP API */ - int64_t offset; - - /** Length that is published by the query-block-jobs QMP API */ - int64_t len; - /** Speed that was set with @block_job_set_speed. */ int64_t speed; /** Rate limiting data structure for implementing @speed. */ RateLimit limit; - /** The completion function that will be called when the job completes. */ - BlockCompletionFunc *cb; - /** 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; - - /** Reference count of the block job */ - int refcnt; - - /** True when job has reported completion by calling block_job_completed. */ - bool completed; - - /** ret code passed to block_job_completed. */ - int ret; - - /** - * Timer that is used by @block_job_sleep_ns. Accessed under - * block_job_mutex (in blockjob.c). - */ - QEMUTimer sleep_timer; + /** Called when a cancelled job is finalised. */ + Notifier finalize_cancelled_notifier; - /** Current state; See @BlockJobStatus for details. */ - BlockJobStatus status; + /** Called when a successfully completed job is finalised. */ + Notifier finalize_completed_notifier; - /** True if this job should automatically finalize itself */ - bool auto_finalize; + /** Called when the job transitions to PENDING */ + Notifier pending_notifier; - /** True if this job should automatically dismiss itself */ - bool auto_dismiss; + /** Called when the job transitions to READY */ + Notifier ready_notifier; - BlockJobTxn *txn; - QLIST_ENTRY(BlockJob) txn_list; + /** BlockDriverStates that are involved in this block job */ + GSList *nodes; } BlockJob; -typedef enum BlockJobCreateFlags { - /* Default behavior */ - BLOCK_JOB_DEFAULT = 0x00, - /* BlockJob is not QMP-created and should not send QMP events */ - BLOCK_JOB_INTERNAL = 0x01, - /* BlockJob requires manual finalize step */ - BLOCK_JOB_MANUAL_FINALIZE = 0x02, - /* BlockJob requires manual dismiss step */ - BLOCK_JOB_MANUAL_DISMISS = 0x04, -} BlockJobCreateFlags; - /** * block_job_next: * @job: A block job, or %NULL. @@ -231,78 +130,6 @@ void block_job_remove_all_bdrv(BlockJob *job); void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp); /** - * block_job_start: - * @job: A job that has not yet been started. - * - * Begins execution of a block job. - * Takes ownership of one reference to the job object. - */ -void block_job_start(BlockJob *job); - -/** - * block_job_cancel: - * @job: The job to be canceled. - * @force: Quit a job without waiting for data to be in sync. - * - * Asynchronously cancel the specified job. - */ -void block_job_cancel(BlockJob *job, bool force); - -/** - * block_job_complete: - * @job: The job to be completed. - * @errp: Error object. - * - * Asynchronously complete the specified job. - */ -void block_job_complete(BlockJob *job, Error **errp); - - -/** - * block_job_finalize: - * @job: The job to fully commit and finish. - * @errp: Error object. - * - * For jobs that have finished their work and are pending - * awaiting explicit acknowledgement to commit their work, - * This will commit that work. - * - * FIXME: Make the below statement universally true: - * For jobs that support the manual workflow mode, all graph - * changes that occur as a result will occur after this command - * and before a successful reply. - */ -void block_job_finalize(BlockJob *job, Error **errp); - -/** - * block_job_dismiss: - * @job: The job to be dismissed. - * @errp: Error object. - * - * Remove a concluded job from the query list. - */ -void block_job_dismiss(BlockJob **job, Error **errp); - -/** - * block_job_progress_update: - * @job: The job that has made progress - * @done: How much progress the job made - * - * Updates the progress counter of the job. - */ -void block_job_progress_update(BlockJob *job, uint64_t done); - -/** - * block_job_progress_set_remaining: - * @job: The job whose expected progress end value is set - * @remaining: Expected end value of the progress counter of the job - * - * Sets the expected end value of the progress counter of a job so that a - * completion percentage can be calculated when the progress is updated. - */ -void block_job_progress_set_remaining(BlockJob *job, uint64_t remaining); - -/** * block_job_query: * @job: The job to get information about. * @@ -311,78 +138,6 @@ void block_job_progress_set_remaining(BlockJob *job, uint64_t remaining); BlockJobInfo *block_job_query(BlockJob *job, Error **errp); /** - * block_job_user_pause: - * @job: The job to be paused. - * - * Asynchronously pause the specified job. - * Do not allow a resume until a matching call to block_job_user_resume. - */ -void block_job_user_pause(BlockJob *job, Error **errp); - -/** - * block_job_paused: - * @job: The job to query. - * - * Returns true if the job is user-paused. - */ -bool block_job_user_paused(BlockJob *job); - -/** - * block_job_user_resume: - * @job: The job to be resumed. - * - * Resume the specified job. - * Must be paired with a preceding block_job_user_pause. - */ -void block_job_user_resume(BlockJob *job, Error **errp); - -/** - * block_job_user_cancel: - * @job: The job to be cancelled. - * @force: Quit a job without waiting for data to be in sync. - * - * Cancels the specified job, but may refuse to do so if the - * operation isn't currently meaningful. - */ -void block_job_user_cancel(BlockJob *job, bool force, Error **errp); - -/** - * block_job_cancel_sync: - * @job: The job to be canceled. - * - * Synchronously cancel the job. The completion callback is called - * before the function returns. The job may actually complete - * instead of canceling itself; the circumstances under which this - * happens depend on the kind of job that is active. - * - * Returns the return value from the job if the job actually completed - * during the call, or -ECANCELED if it was canceled. - */ -int block_job_cancel_sync(BlockJob *job); - -/** - * block_job_cancel_sync_all: - * - * Synchronously cancels all jobs using block_job_cancel_sync(). - */ -void block_job_cancel_sync_all(void); - -/** - * block_job_complete_sync: - * @job: The job to be completed. - * @errp: Error object which may be set by block_job_complete(); this is not - * necessarily set on every error, the job return value has to be - * checked as well. - * - * Synchronously complete the job. The completion callback is called before the - * function returns, unless it is NULL (which is permissible when using this - * function). - * - * Returns the return value from the job. - */ -int block_job_complete_sync(BlockJob *job, Error **errp); - -/** * block_job_iostatus_reset: * @job: The job whose I/O status should be reset. * @@ -392,59 +147,6 @@ int block_job_complete_sync(BlockJob *job, Error **errp); void block_job_iostatus_reset(BlockJob *job); /** - * 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_ref: - * - * Add a reference to BlockJob refcnt, it will be decreased with - * block_job_unref, and then be freed if it comes to be the last - * reference. - */ -void block_job_ref(BlockJob *job); - -/** - * block_job_unref: - * - * Release a reference that was previously acquired with block_job_ref - * or block_job_create. If it's the last reference to the object, it will be - * freed. - */ -void block_job_unref(BlockJob *job); - -/** - * 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); - -/** * block_job_is_internal: * @job: The job to determine if it is user-visible or not. * diff --git a/include/block/blockjob_int.h b/include/block/blockjob_int.h index 62ec964d09..5cd50c6639 100644 --- a/include/block/blockjob_int.h +++ b/include/block/blockjob_int.h @@ -35,72 +35,8 @@ * 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; - - /** Mandatory: Entrypoint for the Coroutine. */ - CoroutineEntry *start; - - /** - * Optional callback for job types whose completion must be triggered - * manually. - */ - void (*complete)(BlockJob *job, Error **errp); - - /** - * If the callback is not NULL, prepare 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. - * - * This callback will not be invoked if the job has already failed. - * If it fails, abort and then clean will be called. - */ - int (*prepare)(BlockJob *job); - - /** - * 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 after a call to either - * .commit() or .abort(). Regardless of which callback is invoked after - * completion, .clean() will always be called, even if the job does not - * belong to a transaction group. - */ - void (*clean)(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); + /** Generic JobDriver callbacks and settings */ + JobDriver job_driver; /* * If the callback is not NULL, it will be invoked before the job is @@ -113,6 +49,10 @@ struct BlockJobDriver { * 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. + * + * Block jobs must use the default implementation for job_driver.drain, + * which will in turn call this callback after doing generic block job + * stuff. */ void (*drain)(BlockJob *job); }; @@ -126,8 +66,7 @@ struct BlockJobDriver { * @bs: The block * @perm, @shared_perm: Permissions to request for @bs * @speed: The maximum speed, in bytes per second, or 0 for unlimited. - * @flags: Creation flags for the Block Job. - * See @BlockJobCreateFlags + * @flags: Creation flags for the Block Job. See @JobCreateFlags. * @cb: Completion function for the job. * @opaque: Opaque pointer value passed to @cb. * @errp: Error object. @@ -142,28 +81,31 @@ struct BlockJobDriver { * called from a wrapper that is specific to the job type. */ void *block_job_create(const char *job_id, const BlockJobDriver *driver, - BlockJobTxn *txn, BlockDriverState *bs, uint64_t perm, + JobTxn *txn, BlockDriverState *bs, uint64_t perm, uint64_t shared_perm, int64_t speed, int flags, BlockCompletionFunc *cb, void *opaque, Error **errp); /** - * block_job_sleep_ns: - * @job: The job that calls the function. - * @ns: How many nanoseconds to stop for. - * - * Put the job to sleep (assuming that it wasn't canceled) for @ns - * %QEMU_CLOCK_REALTIME nanoseconds. Canceling the job will immediately - * interrupt the wait. + * block_job_free: + * Callback to be used for JobDriver.free in all block jobs. Frees block job + * specific resources in @job. */ -void block_job_sleep_ns(BlockJob *job, int64_t ns); +void block_job_free(Job *job); /** - * block_job_yield: - * @job: The job that calls the function. - * - * Yield the block job coroutine. + * block_job_user_resume: + * Callback to be used for JobDriver.user_resume in all block jobs. Resets the + * iostatus when the user resumes @job. + */ +void block_job_user_resume(Job *job); + +/** + * block_job_drain: + * Callback to be used for JobDriver.drain in all block jobs. Drains the main + * block node associated with the block jobs and calls BlockJobDriver.drain for + * job-specific actions. */ -void block_job_yield(BlockJob *job); +void block_job_drain(Job *job); /** * block_job_ratelimit_get_delay: @@ -174,57 +116,6 @@ void block_job_yield(BlockJob *job); int64_t block_job_ratelimit_get_delay(BlockJob *job, uint64_t n); /** - * block_job_early_fail: - * @bs: The block device. - * - * The block job could not be started, free it. - */ -void block_job_early_fail(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. @@ -237,23 +128,4 @@ void block_job_event_ready(BlockJob *job); 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 - * - * This function must be called by the main job coroutine just before it - * returns. @fn is executed 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 bd68328ed9..4d09eaba72 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -255,7 +255,7 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, void tlb_set_page(CPUState *cpu, target_ulong vaddr, hwaddr paddr, int prot, int mmu_idx, target_ulong size); -void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr); +void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr, MemTxAttrs attrs); void probe_write(CPUArchState *env, target_ulong addr, int size, int mmu_idx, uintptr_t retaddr); #else @@ -303,7 +303,8 @@ static inline void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu, uint16_t idxmap) { } -static inline void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr) +static inline void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr, + MemTxAttrs attrs) { } #endif diff --git a/include/exec/gdbstub.h b/include/exec/gdbstub.h index 2e8a4b83b9..08363969c1 100644 --- a/include/exec/gdbstub.h +++ b/include/exec/gdbstub.h @@ -48,6 +48,21 @@ int use_gdb_syscalls(void); void gdb_set_stop_cpu(CPUState *cpu); void gdb_exit(CPUArchState *, int); #ifdef CONFIG_USER_ONLY +/** + * gdb_handlesig: yield control to gdb + * @cpu: CPU + * @sig: if non-zero, the signal number which caused us to stop + * + * This function yields control to gdb, when a user-mode-only target + * needs to stop execution. If @sig is non-zero, then we will send a + * stop packet to tell gdb that we have stopped because of this signal. + * + * This function will block (handling protocol requests from gdb) + * until gdb tells us to continue target execution. When it does + * return, the return value is a signal to deliver to the target, + * or 0 if no signal should be delivered, ie the signal that caused + * us to stop should be ignored. + */ int gdb_handlesig(CPUState *, int); void gdb_signalled(CPUArchState *, int); void gdbserver_fork(CPUState *); diff --git a/include/exec/helper-head.h b/include/exec/helper-head.h index 15b6a68de3..276dd5afce 100644 --- a/include/exec/helper-head.h +++ b/include/exec/helper-head.h @@ -39,7 +39,7 @@ #define dh_ctype_int int #define dh_ctype_i64 uint64_t #define dh_ctype_s64 int64_t -#define dh_ctype_f16 float16 +#define dh_ctype_f16 uint32_t #define dh_ctype_f32 float32 #define dh_ctype_f64 float64 #define dh_ctype_ptr void * diff --git a/include/exec/memory-internal.h b/include/exec/memory-internal.h index 58399b9318..56c25c0ef7 100644 --- a/include/exec/memory-internal.h +++ b/include/exec/memory-internal.h @@ -37,7 +37,8 @@ void flatview_unref(FlatView *view); extern const MemoryRegionOps unassigned_mem_ops; bool memory_region_access_valid(MemoryRegion *mr, hwaddr addr, - unsigned size, bool is_write); + unsigned size, bool is_write, + MemTxAttrs attrs); void flatview_add_to_dispatch(FlatView *fv, MemoryRegionSection *section); AddressSpaceDispatch *address_space_dispatch_new(FlatView *fv); diff --git a/include/exec/memory.h b/include/exec/memory.h index 525619a5f4..eb2ba06519 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -166,7 +166,8 @@ struct MemoryRegionOps { * as a machine check exception). */ bool (*accepts)(void *opaque, hwaddr addr, - unsigned size, bool is_write); + unsigned size, bool is_write, + MemTxAttrs attrs); } valid; /* Internal implementation constraints: */ struct { @@ -194,29 +195,100 @@ enum IOMMUMemoryRegionAttr { IOMMU_ATTR_SPAPR_TCE_FD }; +/** + * IOMMUMemoryRegionClass: + * + * All IOMMU implementations need to subclass TYPE_IOMMU_MEMORY_REGION + * and provide an implementation of at least the @translate method here + * to handle requests to the memory region. Other methods are optional. + * + * The IOMMU implementation must use the IOMMU notifier infrastructure + * to report whenever mappings are changed, by calling + * memory_region_notify_iommu() (or, if necessary, by calling + * memory_region_notify_one() for each registered notifier). + */ typedef struct IOMMUMemoryRegionClass { /* private */ struct DeviceClass parent_class; /* - * Return a TLB entry that contains a given address. Flag should - * be the access permission of this translation operation. We can - * set flag to IOMMU_NONE to mean that we don't need any - * read/write permission checks, like, when for region replay. + * Return a TLB entry that contains a given address. + * + * The IOMMUAccessFlags indicated via @flag are optional and may + * be specified as IOMMU_NONE to indicate that the caller needs + * the full translation information for both reads and writes. If + * the access flags are specified then the IOMMU implementation + * may use this as an optimization, to stop doing a page table + * walk as soon as it knows that the requested permissions are not + * allowed. If IOMMU_NONE is passed then the IOMMU must do the + * full page table walk and report the permissions in the returned + * IOMMUTLBEntry. (Note that this implies that an IOMMU may not + * return different mappings for reads and writes.) + * + * The returned information remains valid while the caller is + * holding the big QEMU lock or is inside an RCU critical section; + * if the caller wishes to cache the mapping beyond that it must + * register an IOMMU notifier so it can invalidate its cached + * information when the IOMMU mapping changes. + * + * @iommu: the IOMMUMemoryRegion + * @hwaddr: address to be translated within the memory region + * @flag: requested access permissions */ IOMMUTLBEntry (*translate)(IOMMUMemoryRegion *iommu, hwaddr addr, IOMMUAccessFlags flag); - /* Returns minimum supported page size */ + /* Returns minimum supported page size in bytes. + * If this method is not provided then the minimum is assumed to + * be TARGET_PAGE_SIZE. + * + * @iommu: the IOMMUMemoryRegion + */ uint64_t (*get_min_page_size)(IOMMUMemoryRegion *iommu); - /* Called when IOMMU Notifier flag changed */ + /* Called when IOMMU Notifier flag changes (ie when the set of + * events which IOMMU users are requesting notification for changes). + * Optional method -- need not be provided if the IOMMU does not + * need to know exactly which events must be notified. + * + * @iommu: the IOMMUMemoryRegion + * @old_flags: events which previously needed to be notified + * @new_flags: events which now need to be notified + */ void (*notify_flag_changed)(IOMMUMemoryRegion *iommu, IOMMUNotifierFlag old_flags, IOMMUNotifierFlag new_flags); - /* Set this up to provide customized IOMMU replay function */ + /* Called to handle memory_region_iommu_replay(). + * + * The default implementation of memory_region_iommu_replay() is to + * call the IOMMU translate method for every page in the address space + * with flag == IOMMU_NONE and then call the notifier if translate + * returns a valid mapping. If this method is implemented then it + * overrides the default behaviour, and must provide the full semantics + * of memory_region_iommu_replay(), by calling @notifier for every + * translation present in the IOMMU. + * + * Optional method -- an IOMMU only needs to provide this method + * if the default is inefficient or produces undesirable side effects. + * + * Note: this is not related to record-and-replay functionality. + */ void (*replay)(IOMMUMemoryRegion *iommu, IOMMUNotifier *notifier); - /* Get IOMMU misc attributes */ - int (*get_attr)(IOMMUMemoryRegion *iommu, enum IOMMUMemoryRegionAttr, + /* Get IOMMU misc attributes. This is an optional method that + * can be used to allow users of the IOMMU to get implementation-specific + * information. The IOMMU implements this method to handle calls + * by IOMMU users to memory_region_iommu_get_attr() by filling in + * the arbitrary data pointer for any IOMMUMemoryRegionAttr values that + * the IOMMU supports. If the method is unimplemented then + * memory_region_iommu_get_attr() will always return -EINVAL. + * + * @iommu: the IOMMUMemoryRegion + * @attr: attribute being queried + * @data: memory to fill in with the attribute data + * + * Returns 0 on success, or a negative errno; in particular + * returns -EINVAL for unrecognized or unimplemented attribute types. + */ + int (*get_attr)(IOMMUMemoryRegion *iommu, enum IOMMUMemoryRegionAttr attr, void *data); } IOMMUMemoryRegionClass; @@ -676,35 +748,20 @@ void memory_region_init_rom_device_nomigrate(MemoryRegion *mr, Error **errp); /** - * memory_region_init_reservation: Initialize a memory region that reserves - * I/O space. - * - * A reservation region primariy serves debugging purposes. It claims I/O - * space that is not supposed to be handled by QEMU itself. Any access via - * the memory API will cause an abort(). - * This function is deprecated. Use memory_region_init_io() with NULL - * callbacks instead. - * - * @mr: the #MemoryRegion to be initialized - * @owner: the object that tracks the region's reference count - * @name: used for debugging; not visible to the user or ABI - * @size: size of the region. - */ -static inline void memory_region_init_reservation(MemoryRegion *mr, - Object *owner, - const char *name, - uint64_t size) -{ - memory_region_init_io(mr, owner, NULL, mr, name, size); -} - -/** * memory_region_init_iommu: Initialize a memory region of a custom type * that translates addresses * * An IOMMU region translates addresses and forwards accesses to a target * memory region. * + * The IOMMU implementation must define a subclass of TYPE_IOMMU_MEMORY_REGION. + * @_iommu_mr should be a pointer to enough memory for an instance of + * that subclass, @instance_size is the size of that subclass, and + * @mrtypename is its name. This function will initialize @_iommu_mr as an + * instance of the subclass, and its methods will then be called to handle + * accesses to the memory region. See the documentation of + * #IOMMUMemoryRegionClass for further details. + * * @_iommu_mr: the #IOMMUMemoryRegion to be initialized * @instance_size: the IOMMUMemoryRegion subclass instance size * @mrtypename: the type name of the #IOMMUMemoryRegion @@ -953,6 +1010,8 @@ void memory_region_register_iommu_notifier(MemoryRegion *mr, * a notifier with the minimum page granularity returned by * mr->iommu_ops->get_page_size(). * + * Note: this is not related to record-and-replay functionality. + * * @iommu_mr: the memory region to observe * @n: the notifier to which to replay iommu mappings */ @@ -962,6 +1021,8 @@ void memory_region_iommu_replay(IOMMUMemoryRegion *iommu_mr, IOMMUNotifier *n); * memory_region_iommu_replay_all: replay existing IOMMU translations * to all the notifiers registered. * + * Note: this is not related to record-and-replay functionality. + * * @iommu_mr: the memory region to observe */ void memory_region_iommu_replay_all(IOMMUMemoryRegion *iommu_mr); @@ -981,7 +1042,9 @@ void memory_region_unregister_iommu_notifier(MemoryRegion *mr, * memory_region_iommu_get_attr: return an IOMMU attr if get_attr() is * defined on the IOMMU. * - * Returns 0 if succeded, error code otherwise. + * Returns 0 on success, or a negative errno otherwise. In particular, + * -EINVAL indicates that the IOMMU does not support the requested + * attribute. * * @iommu_mr: the memory region * @attr: the requested attribute @@ -1810,7 +1873,7 @@ void address_space_cache_destroy(MemoryRegionCache *cache); * entry. Should be called from an RCU critical section. */ IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr, - bool is_write); + bool is_write, MemTxAttrs attrs); /* address_space_translate: translate an address range into an address space * into a MemoryRegion and an address range into that section. Should be @@ -1823,17 +1886,20 @@ IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr, * #MemoryRegion. * @len: pointer to length * @is_write: indicates the transfer direction + * @attrs: memory attributes */ MemoryRegion *flatview_translate(FlatView *fv, hwaddr addr, hwaddr *xlat, - hwaddr *len, bool is_write); + hwaddr *len, bool is_write, + MemTxAttrs attrs); static inline MemoryRegion *address_space_translate(AddressSpace *as, hwaddr addr, hwaddr *xlat, - hwaddr *len, bool is_write) + hwaddr *len, bool is_write, + MemTxAttrs attrs) { return flatview_translate(address_space_to_flatview(as), - addr, xlat, len, is_write); + addr, xlat, len, is_write, attrs); } /* address_space_access_valid: check for validity of accessing an address @@ -1850,8 +1916,10 @@ static inline MemoryRegion *address_space_translate(AddressSpace *as, * @addr: address within that address space * @len: length of the area to be checked * @is_write: indicates the transfer direction + * @attrs: memory attributes */ -bool address_space_access_valid(AddressSpace *as, hwaddr addr, int len, bool is_write); +bool address_space_access_valid(AddressSpace *as, hwaddr addr, int len, + bool is_write, MemTxAttrs attrs); /* address_space_map: map a physical memory region into a host virtual address * @@ -1865,9 +1933,10 @@ bool address_space_access_valid(AddressSpace *as, hwaddr addr, int len, bool is_ * @addr: address within that address space * @plen: pointer to length of buffer; updated on return * @is_write: indicates the transfer direction + * @attrs: memory attributes */ void *address_space_map(AddressSpace *as, hwaddr addr, - hwaddr *plen, bool is_write); + hwaddr *plen, bool is_write, MemTxAttrs attrs); /* address_space_unmap: Unmaps a memory region previously mapped by address_space_map() * @@ -1939,7 +2008,7 @@ MemTxResult address_space_read(AddressSpace *as, hwaddr addr, rcu_read_lock(); fv = address_space_to_flatview(as); l = len; - mr = flatview_translate(fv, addr, &addr1, &l, false); + mr = flatview_translate(fv, addr, &addr1, &l, false, attrs); if (len == l && memory_access_is_direct(mr, false)) { ptr = qemu_map_ram_ptr(mr->ram_block, addr1); memcpy(buf, ptr, len); diff --git a/include/exec/user/thunk.h b/include/exec/user/thunk.h index 8f55b233b3..8d3af5a3be 100644 --- a/include/exec/user/thunk.h +++ b/include/exec/user/thunk.h @@ -135,7 +135,7 @@ static inline int thunk_type_size(const argtype *type_ptr, int is_host) se = struct_entries + type_ptr[1]; return se->size[is_host]; default: - return -1; + g_assert_not_reached(); } } @@ -185,7 +185,7 @@ static inline int thunk_type_align(const argtype *type_ptr, int is_host) se = struct_entries + type_ptr[1]; return se->align[is_host]; default: - return -1; + g_assert_not_reached(); } } diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index 6b32a99e21..efb8fc8123 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -11,7 +11,6 @@ #include "hw/ide/ahci.h" #include "sysemu/sysemu.h" -#include "exec/address-spaces.h" #define AW_A10_PIC_REG_BASE 0x01c20400 diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h index 122b286de7..f5b193f670 100644 --- a/include/hw/arm/bcm2835_peripherals.h +++ b/include/hw/arm/bcm2835_peripherals.h @@ -12,7 +12,6 @@ #define BCM2835_PERIPHERALS_H #include "qemu-common.h" -#include "exec/address-spaces.h" #include "hw/sysbus.h" #include "hw/char/bcm2835_aux.h" #include "hw/display/bcm2835_fb.h" diff --git a/include/hw/devices.h b/include/hw/devices.h index 861ddea8af..0e27feb0c2 100644 --- a/include/hw/devices.h +++ b/include/hw/devices.h @@ -1,13 +1,10 @@ #ifndef QEMU_DEVICES_H #define QEMU_DEVICES_H -#include "hw/irq.h" - -/* ??? Not all users of this file can include cpu-common.h. */ -struct MemoryRegion; - /* Devices that have nowhere better to go. */ +#include "hw/hw.h" + /* smc91c111.c */ void smc91c111_init(NICInfo *, uint32_t, qemu_irq); diff --git a/include/hw/display/bcm2835_fb.h b/include/hw/display/bcm2835_fb.h index 9a12d7afa2..ae0a3807f2 100644 --- a/include/hw/display/bcm2835_fb.h +++ b/include/hw/display/bcm2835_fb.h @@ -12,7 +12,6 @@ #define BCM2835_FB_H #include "hw/sysbus.h" -#include "exec/address-spaces.h" #include "ui/console.h" #define TYPE_BCM2835_FB "bcm2835-fb" diff --git a/include/hw/display/bochs-vbe.h b/include/hw/display/bochs-vbe.h new file mode 100644 index 0000000000..bc2f046eee --- /dev/null +++ b/include/hw/display/bochs-vbe.h @@ -0,0 +1,69 @@ +#ifndef HW_DISPLAY_BOCHS_VBE_H +#define HW_DISPLAY_BOCHS_VBE_H + +/* + * bochs vesa bios extension interface + */ + +#define VBE_DISPI_MAX_XRES 16000 +#define VBE_DISPI_MAX_YRES 12000 +#define VBE_DISPI_MAX_BPP 32 + +#define VBE_DISPI_INDEX_ID 0x0 +#define VBE_DISPI_INDEX_XRES 0x1 +#define VBE_DISPI_INDEX_YRES 0x2 +#define VBE_DISPI_INDEX_BPP 0x3 +#define VBE_DISPI_INDEX_ENABLE 0x4 +#define VBE_DISPI_INDEX_BANK 0x5 +#define VBE_DISPI_INDEX_VIRT_WIDTH 0x6 +#define VBE_DISPI_INDEX_VIRT_HEIGHT 0x7 +#define VBE_DISPI_INDEX_X_OFFSET 0x8 +#define VBE_DISPI_INDEX_Y_OFFSET 0x9 +#define VBE_DISPI_INDEX_NB 0xa /* size of vbe_regs[] */ +#define VBE_DISPI_INDEX_VIDEO_MEMORY_64K 0xa /* read-only, not in vbe_regs */ + +/* VBE_DISPI_INDEX_ID */ +#define VBE_DISPI_ID0 0xB0C0 +#define VBE_DISPI_ID1 0xB0C1 +#define VBE_DISPI_ID2 0xB0C2 +#define VBE_DISPI_ID3 0xB0C3 +#define VBE_DISPI_ID4 0xB0C4 +#define VBE_DISPI_ID5 0xB0C5 + +/* VBE_DISPI_INDEX_ENABLE */ +#define VBE_DISPI_DISABLED 0x00 +#define VBE_DISPI_ENABLED 0x01 +#define VBE_DISPI_GETCAPS 0x02 +#define VBE_DISPI_8BIT_DAC 0x20 +#define VBE_DISPI_LFB_ENABLED 0x40 +#define VBE_DISPI_NOCLEARMEM 0x80 + +/* only used by isa-vga, pci vga devices use a memory bar */ +#define VBE_DISPI_LFB_PHYSICAL_ADDRESS 0xE0000000 + + +/* + * qemu extension: mmio bar (region 2) + */ + +#define PCI_VGA_MMIO_SIZE 0x1000 + +/* vga register region */ +#define PCI_VGA_IOPORT_OFFSET 0x400 +#define PCI_VGA_IOPORT_SIZE (0x3e0 - 0x3c0) + +/* bochs vbe register region */ +#define PCI_VGA_BOCHS_OFFSET 0x500 +#define PCI_VGA_BOCHS_SIZE (0x0b * 2) + +/* qemu extension register region */ +#define PCI_VGA_QEXT_OFFSET 0x600 +#define PCI_VGA_QEXT_SIZE (2 * 4) + +/* qemu extension registers */ +#define PCI_VGA_QEXT_REG_SIZE (0 * 4) +#define PCI_VGA_QEXT_REG_BYTEORDER (1 * 4) +#define PCI_VGA_QEXT_LITTLE_ENDIAN 0x1e1e1e1e +#define PCI_VGA_QEXT_BIG_ENDIAN 0xbebebebe + +#endif /* HW_DISPLAY_BOCHS_VBE_H */ diff --git a/include/hw/dma/bcm2835_dma.h b/include/hw/dma/bcm2835_dma.h index 75312e2e17..60138f4d31 100644 --- a/include/hw/dma/bcm2835_dma.h +++ b/include/hw/dma/bcm2835_dma.h @@ -7,7 +7,6 @@ #define BCM2835_DMA_H #include "qemu-common.h" -#include "exec/address-spaces.h" #include "hw/sysbus.h" typedef struct { diff --git a/include/hw/i2c/i2c.h b/include/hw/i2c/i2c.h index d727379b48..5dc166158b 100644 --- a/include/hw/i2c/i2c.h +++ b/include/hw/i2c/i2c.h @@ -28,9 +28,6 @@ typedef struct I2CSlave I2CSlave; typedef struct I2CSlaveClass { DeviceClass parent_class; - /* Callbacks provided by the device. */ - int (*init)(I2CSlave *dev); - /* Master to slave. Returns non-zero for a NAK, 0 for success. */ int (*send)(I2CSlave *s, uint8_t data); diff --git a/include/hw/i2c/smbus.h b/include/hw/i2c/smbus.h index 544bbc1957..cfe3fa69f3 100644 --- a/include/hw/i2c/smbus.h +++ b/include/hw/i2c/smbus.h @@ -38,7 +38,6 @@ typedef struct SMBusDeviceClass { I2CSlaveClass parent_class; - int (*init)(SMBusDevice *dev); void (*quick_cmd)(SMBusDevice *dev, uint8_t read); void (*send_byte)(SMBusDevice *dev, uint8_t val); uint8_t (*receive_byte)(SMBusDevice *dev); diff --git a/include/hw/misc/bcm2835_mbox.h b/include/hw/misc/bcm2835_mbox.h index f4e9ff9ef6..7e8f3ce86d 100644 --- a/include/hw/misc/bcm2835_mbox.h +++ b/include/hw/misc/bcm2835_mbox.h @@ -8,7 +8,6 @@ #include "bcm2835_mbox_defs.h" #include "hw/sysbus.h" -#include "exec/address-spaces.h" #define TYPE_BCM2835_MBOX "bcm2835-mbox" #define BCM2835_MBOX(obj) \ diff --git a/include/hw/misc/bcm2835_property.h b/include/hw/misc/bcm2835_property.h index edcab603ce..11be0dbeac 100644 --- a/include/hw/misc/bcm2835_property.h +++ b/include/hw/misc/bcm2835_property.h @@ -7,7 +7,6 @@ #define BCM2835_PROPERTY_H #include "hw/sysbus.h" -#include "exec/address-spaces.h" #include "net/net.h" #include "hw/display/bcm2835_fb.h" diff --git a/include/hw/misc/mips_itu.h b/include/hw/misc/mips_itu.h index b3a4532036..030eb4ac62 100644 --- a/include/hw/misc/mips_itu.h +++ b/include/hw/misc/mips_itu.h @@ -20,6 +20,8 @@ #ifndef MIPS_ITU_H #define MIPS_ITU_H +#include "hw/sysbus.h" + #define TYPE_MIPS_ITU "mips-itu" #define MIPS_ITU(obj) OBJECT_CHECK(MIPSITUState, (obj), TYPE_MIPS_ITU) diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h index 9453588160..f1fd0f8736 100644 --- a/include/hw/qdev-core.h +++ b/include/hw/qdev-core.h @@ -29,8 +29,6 @@ typedef enum DeviceCategory { DEVICE_CATEGORY_MAX } DeviceCategory; -typedef int (*qdev_initfn)(DeviceState *dev); -typedef int (*qdev_event)(DeviceState *dev); typedef void (*DeviceRealize)(DeviceState *dev, Error **errp); typedef void (*DeviceUnrealize)(DeviceState *dev, Error **errp); typedef void (*DeviceReset)(DeviceState *dev); @@ -43,13 +41,9 @@ struct VMStateDescription; * DeviceClass: * @props: Properties accessing state fields. * @realize: Callback function invoked when the #DeviceState:realized - * property is changed to %true. The default invokes @init if not %NULL. + * property is changed to %true. * @unrealize: Callback function invoked when the #DeviceState:realized * property is changed to %false. - * @init: Callback function invoked when the #DeviceState::realized property - * is changed to %true. Deprecated, new types inheriting directly from - * TYPE_DEVICE should use @realize instead, new leaf types should consult - * their respective parent type. * @hotpluggable: indicates if #DeviceClass is hotpluggable, available * as readonly "hotpluggable" property of #DeviceState instance * @@ -73,19 +67,15 @@ struct VMStateDescription; * object_initialize() in their own #TypeInfo.instance_init and forward the * realization events appropriately. * - * The @init callback is considered private to a particular bus implementation - * (immediate abstract child types of TYPE_DEVICE). Derived leaf types set an - * "init" callback on their parent class instead. - * * Any type may override the @realize and/or @unrealize callbacks but needs * to call the parent type's implementation if keeping their functionality * is desired. Refer to QOM documentation for further discussion and examples. * * <note> * <para> - * If a type derived directly from TYPE_DEVICE implements @realize, it does - * not need to implement @init and therefore does not need to store and call - * #DeviceClass' default @realize callback. + * Since TYPE_DEVICE doesn't implement @realize and @unrealize, types + * derived directly from it need not call their parent's @realize and + * @unrealize. * For other types consult the documentation and implementation of the * respective parent types. * </para> @@ -124,8 +114,6 @@ typedef struct DeviceClass { const struct VMStateDescription *vmsd; /* Private to qdev / bus. */ - qdev_initfn init; /* TODO remove, once users are converted to realize */ - qdev_event exit; /* TODO remove, once users are converted to unrealize */ const char *bus_type; } DeviceClass; diff --git a/include/hw/sh4/sh_intc.h b/include/hw/sh4/sh_intc.h index 7913bc48a2..fbcee94ed7 100644 --- a/include/hw/sh4/sh_intc.h +++ b/include/hw/sh4/sh_intc.h @@ -3,7 +3,6 @@ #include "qemu-common.h" #include "hw/irq.h" -#include "exec/address-spaces.h" typedef unsigned char intc_enum; diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index d9360148e6..8264a65fa5 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -22,7 +22,6 @@ #define HW_VFIO_VFIO_COMMON_H #include "qemu-common.h" -#include "exec/address-spaces.h" #include "exec/memory.h" #include "qemu/queue.h" #include "qemu/notify.h" diff --git a/include/hw/virtio/virtio-access.h b/include/hw/virtio/virtio-access.h index 2e92074bd1..bdf58f3119 100644 --- a/include/hw/virtio/virtio-access.h +++ b/include/hw/virtio/virtio-access.h @@ -18,7 +18,6 @@ #include "hw/virtio/virtio.h" #include "hw/virtio/virtio-bus.h" -#include "exec/address-spaces.h" #if defined(TARGET_PPC64) || defined(TARGET_ARM) #define LEGACY_VIRTIO_IS_BIENDIAN 1 diff --git a/include/hw/virtio/virtio-gpu.h b/include/hw/virtio/virtio-gpu.h index 79bb3fb3dd..d6ba61f2f1 100644 --- a/include/hw/virtio/virtio-gpu.h +++ b/include/hw/virtio/virtio-gpu.h @@ -21,6 +21,12 @@ #include "qemu/log.h" #include "standard-headers/linux/virtio_gpu.h" + +/* Not yet(?) defined in standard-headers, remove when possible */ +#ifndef VIRTIO_GPU_CAPSET_VIRGL2 +#define VIRTIO_GPU_CAPSET_VIRGL2 2 +#endif + #define TYPE_VIRTIO_GPU "virtio-gpu-device" #define VIRTIO_GPU(obj) \ OBJECT_CHECK(VirtIOGPU, (obj), TYPE_VIRTIO_GPU) diff --git a/include/hw/xen/xen_backend.h b/include/hw/xen/xen_backend.h index 3a27692407..9c17fdd85d 100644 --- a/include/hw/xen/xen_backend.h +++ b/include/hw/xen/xen_backend.h @@ -16,7 +16,6 @@ /* variables */ extern struct xs_handle *xenstore; extern const char *xen_protocol; -extern bool xen_feature_grant_copy; extern DeviceState *xen_sysdev; extern BusState *xen_sysbus; @@ -42,6 +41,39 @@ 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_set_max_grant_refs(struct XenDevice *xendev, + unsigned int nr_refs); +void *xen_be_map_grant_refs(struct XenDevice *xendev, uint32_t *refs, + unsigned int nr_refs, int prot); +void xen_be_unmap_grant_refs(struct XenDevice *xendev, void *ptr, + unsigned int nr_refs); + +typedef struct XenGrantCopySegment { + union { + void *virt; + struct { + uint32_t ref; + off_t offset; + } foreign; + } source, dest; + size_t len; +} XenGrantCopySegment; + +int xen_be_copy_grant_refs(struct XenDevice *xendev, + bool to_domain, XenGrantCopySegment segs[], + unsigned int nr_segs); + +static inline void *xen_be_map_grant_ref(struct XenDevice *xendev, + uint32_t ref, int prot) +{ + return xen_be_map_grant_refs(xendev, &ref, 1, prot); +} + +static inline void xen_be_unmap_grant_ref(struct XenDevice *xendev, + void *ptr) +{ + return xen_be_unmap_grant_refs(xendev, ptr, 1); +} /* actual backend drivers */ extern struct XenDevOps xen_console_ops; /* xen_console.c */ diff --git a/include/hw/xen/xen_common.h b/include/hw/xen/xen_common.h index 5f1402b494..93f631e5bf 100644 --- a/include/hw/xen/xen_common.h +++ b/include/hw/xen/xen_common.h @@ -119,6 +119,22 @@ static inline int xendevicemodel_pin_memory_cacheattr( return xc_domain_pin_memory_cacheattr(xen_xc, domid, start, end, type); } +typedef void xenforeignmemory_resource_handle; + +#define XENMEM_resource_ioreq_server 0 + +#define XENMEM_resource_ioreq_server_frame_bufioreq 0 +#define XENMEM_resource_ioreq_server_frame_ioreq(n) (1 + (n)) + +static inline xenforeignmemory_resource_handle *xenforeignmemory_map_resource( + xenforeignmemory_handle *fmem, domid_t domid, unsigned int type, + unsigned int id, unsigned long frame, unsigned long nr_frames, + void **paddr, int prot, int flags) +{ + errno = EOPNOTSUPP; + return NULL; +} + #endif /* CONFIG_XEN_CTRL_INTERFACE_VERSION < 41100 */ #if CONFIG_XEN_CTRL_INTERFACE_VERSION < 41000 @@ -667,8 +683,21 @@ static inline int xen_domain_create(xc_interface *xc, uint32_t ssidref, #if CONFIG_XEN_CTRL_INTERFACE_VERSION < 40800 - -typedef void *xengnttab_grant_copy_segment_t; +struct xengnttab_grant_copy_segment { + union xengnttab_copy_ptr { + void *virt; + struct { + uint32_t ref; + uint16_t offset; + uint16_t domid; + } foreign; + } source, dest; + uint16_t len; + uint16_t flags; + int16_t status; +}; + +typedef struct xengnttab_grant_copy_segment xengnttab_grant_copy_segment_t; static inline int xengnttab_grant_copy(xengnttab_handle *xgt, uint32_t count, xengnttab_grant_copy_segment_t *segs) diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h index 5877caed90..3747110f95 100644 --- a/include/migration/vmstate.h +++ b/include/migration/vmstate.h @@ -143,6 +143,11 @@ enum VMStateFlags { * to determine the number of entries in the array. Only valid in * combination with one of VMS_VARRAY*. */ VMS_MULTIPLY_ELEMENTS = 0x4000, + + /* A structure field that is like VMS_STRUCT, but uses + * VMStateField.struct_version_id to tell which version of the + * structure we are referencing to use. */ + VMS_VSTRUCT = 0x8000, }; typedef enum { @@ -167,6 +172,7 @@ struct VMStateField { enum VMStateFlags flags; const VMStateDescription *vmsd; int version_id; + int struct_version_id; bool (*field_exists)(void *opaque, int version_id); }; @@ -248,6 +254,25 @@ extern const VMStateInfo vmstate_info_qtailq; vmstate_offset_array(_state, _field, uint8_t, \ sizeof(typeof_field(_state, _field))) +/* In the macros below, if there is a _version, that means the macro's + * field will be processed only if the version being received is >= + * the _version specified. In general, if you add a new field, you + * would increment the structure's version and put that version + * number into the new field so it would only be processed with the + * new version. + * + * In particular, for VMSTATE_STRUCT() and friends the _version does + * *NOT* pick the version of the sub-structure. It works just as + * specified above. The version of the top-level structure received + * is passed down to all sub-structures. This means that the + * sub-structures must have version that are compatible with all the + * structures that use them. + * + * If you want to specify the version of the sub-structure, use + * VMSTATE_VSTRUCT(), which allows the specific sub-structure version + * to be directly specified. + */ + #define VMSTATE_SINGLE_TEST(_field, _state, _test, _version, _info, _type) { \ .name = (stringify(_field)), \ .version_id = (_version), \ @@ -395,6 +420,17 @@ extern const VMStateInfo vmstate_info_qtailq; .offset = offsetof(_state, _field), \ } +#define VMSTATE_VSTRUCT_TEST(_field, _state, _test, _version, _vmsd, _type, _struct_version) { \ + .name = (stringify(_field)), \ + .version_id = (_version), \ + .struct_version_id = (_struct_version), \ + .field_exists = (_test), \ + .vmsd = &(_vmsd), \ + .size = sizeof(_type), \ + .flags = VMS_VSTRUCT, \ + .offset = vmstate_offset_value(_state, _field, _type), \ +} + #define VMSTATE_STRUCT_TEST(_field, _state, _test, _version, _vmsd, _type) { \ .name = (stringify(_field)), \ .version_id = (_version), \ @@ -712,6 +748,13 @@ extern const VMStateInfo vmstate_info_qtailq; #define VMSTATE_SINGLE(_field, _state, _version, _info, _type) \ VMSTATE_SINGLE_TEST(_field, _state, NULL, _version, _info, _type) +#define VMSTATE_VSTRUCT(_field, _state, _vmsd, _type, _struct_version)\ + VMSTATE_VSTRUCT_TEST(_field, _state, NULL, 0, _vmsd, _type, _struct_version) + +#define VMSTATE_VSTRUCT_V(_field, _state, _version, _vmsd, _type, _struct_version) \ + VMSTATE_VSTRUCT_TEST(_field, _state, NULL, _version, _vmsd, _type, \ + _struct_version) + #define VMSTATE_STRUCT(_field, _state, _version, _vmsd, _type) \ VMSTATE_STRUCT_TEST(_field, _state, NULL, _version, _vmsd, _type) @@ -870,6 +913,9 @@ extern const VMStateInfo vmstate_info_qtailq; #define VMSTATE_BOOL_ARRAY(_f, _s, _n) \ VMSTATE_BOOL_ARRAY_V(_f, _s, _n, 0) +#define VMSTATE_BOOL_SUB_ARRAY(_f, _s, _start, _num) \ + VMSTATE_SUB_ARRAY(_f, _s, _start, _num, 0, vmstate_info_bool, bool) + #define VMSTATE_UINT16_ARRAY_V(_f, _s, _n, _v) \ VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_uint16, uint16_t) @@ -1000,6 +1046,8 @@ int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd, void *opaque, int version_id); int vmstate_save_state(QEMUFile *f, const VMStateDescription *vmsd, void *opaque, QJSON *vmdesc); +int vmstate_save_state_v(QEMUFile *f, const VMStateDescription *vmsd, + void *opaque, QJSON *vmdesc, int version_id); bool vmstate_save_needed(const VMStateDescription *vmsd, void *opaque); diff --git a/include/qapi/qmp/dispatch.h b/include/qapi/qmp/dispatch.h index ffb4652f71..b366bb48bd 100644 --- a/include/qapi/qmp/dispatch.h +++ b/include/qapi/qmp/dispatch.h @@ -23,6 +23,7 @@ typedef enum QmpCommandOptions QCO_NO_OPTIONS = 0x0, QCO_NO_SUCCESS_RESP = (1U << 0), QCO_ALLOW_OOB = (1U << 1), + QCO_ALLOW_PRECONFIG = (1U << 2), } QmpCommandOptions; typedef struct QmpCommand diff --git a/include/qemu/job.h b/include/qemu/job.h new file mode 100644 index 0000000000..1d820530fa --- /dev/null +++ b/include/qemu/job.h @@ -0,0 +1,567 @@ +/* + * Declarations for background jobs + * + * Copyright (c) 2011 IBM Corp. + * Copyright (c) 2012, 2018 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 JOB_H +#define JOB_H + +#include "qapi/qapi-types-block-core.h" +#include "qemu/queue.h" +#include "qemu/coroutine.h" +#include "block/aio.h" + +typedef struct JobDriver JobDriver; +typedef struct JobTxn JobTxn; + + +/** + * Long-running operation. + */ +typedef struct Job { + /** The ID of the job. May be NULL for internal jobs. */ + char *id; + + /** The type of this job. */ + const JobDriver *driver; + + /** Reference count of the block job */ + int refcnt; + + /** Current state; See @JobStatus for details. */ + JobStatus status; + + /** AioContext to run the job coroutine in */ + AioContext *aio_context; + + /** + * The coroutine that executes the job. If not NULL, it is reentered when + * busy is false and the job is cancelled. + */ + Coroutine *co; + + /** + * Timer that is used by @job_sleep_ns. Accessed under job_mutex (in + * job.c). + */ + QEMUTimer sleep_timer; + + /** + * Counter for pause request. If non-zero, the block job is either paused, + * or if busy == true will pause itself as soon as possible. + */ + int pause_count; + + /** + * Set to false by the job while the coroutine has yielded and may be + * re-entered by job_enter(). There may still be I/O or event loop activity + * pending. Accessed under block_job_mutex (in blockjob.c). + */ + bool busy; + + /** + * Set to true by the job while it is in a quiescent state, where + * no I/O or event loop activity is pending. + */ + bool paused; + + /** + * Set to true if the job is paused by user. Can be unpaused with the + * block-job-resume QMP command. + */ + bool user_paused; + + /** + * Set to true if the job should cancel itself. The flag must + * always be tested just before toggling the busy flag from false + * to true. After a job has been cancelled, it should only yield + * if #aio_poll will ("sooner or later") reenter the coroutine. + */ + bool cancelled; + + /** + * Set to true if the job should abort immediately without waiting + * for data to be in sync. + */ + bool force_cancel; + + /** Set to true when the job has deferred work to the main loop. */ + bool deferred_to_main_loop; + + /** True if this job should automatically finalize itself */ + bool auto_finalize; + + /** True if this job should automatically dismiss itself */ + bool auto_dismiss; + + /** + * Current progress. The unit is arbitrary as long as the ratio between + * progress_current and progress_total represents the estimated percentage + * of work already done. + */ + int64_t progress_current; + + /** Estimated progress_current value at the completion of the job */ + int64_t progress_total; + + /** Error string for a failed job (NULL if, and only if, job->ret == 0) */ + char *error; + + /** ret code passed to job_completed. */ + int ret; + + /** The completion function that will be called when the job completes. */ + BlockCompletionFunc *cb; + + /** The opaque value that is passed to the completion function. */ + void *opaque; + + /** Notifiers called when a cancelled job is finalised */ + NotifierList on_finalize_cancelled; + + /** Notifiers called when a successfully completed job is finalised */ + NotifierList on_finalize_completed; + + /** Notifiers called when the job transitions to PENDING */ + NotifierList on_pending; + + /** Notifiers called when the job transitions to READY */ + NotifierList on_ready; + + /** Element of the list of jobs */ + QLIST_ENTRY(Job) job_list; + + /** Transaction this job is part of */ + JobTxn *txn; + + /** Element of the list of jobs in a job transaction */ + QLIST_ENTRY(Job) txn_list; +} Job; + +/** + * Callbacks and other information about a Job driver. + */ +struct JobDriver { + /** Derived Job struct size */ + size_t instance_size; + + /** Enum describing the operation */ + JobType job_type; + + /** Mandatory: Entrypoint for the Coroutine. */ + CoroutineEntry *start; + + /** + * 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)(Job *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)(Job *job); + + /** + * Called when the job is resumed by the user (i.e. user_paused becomes + * false). .user_resume is called before .resume. + */ + void (*user_resume)(Job *job); + + /** + * Optional callback for job types whose completion must be triggered + * manually. + */ + void (*complete)(Job *job, Error **errp); + + /* + * If the callback is not NULL, it will be invoked when the job has to be + * synchronously cancelled or completed; it should drain any activities + * as required to ensure progress. + */ + void (*drain)(Job *job); + + /** + * If the callback is not NULL, prepare 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. + * + * This callback will not be invoked if the job has already failed. + * If it fails, abort and then clean will be called. + */ + int (*prepare)(Job *job); + + /** + * 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)(Job *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)(Job *job); + + /** + * If the callback is not NULL, it will be invoked after a call to either + * .commit() or .abort(). Regardless of which callback is invoked after + * completion, .clean() will always be called, even if the job does not + * belong to a transaction group. + */ + void (*clean)(Job *job); + + + /** Called when the job is freed */ + void (*free)(Job *job); +}; + +typedef enum JobCreateFlags { + /* Default behavior */ + JOB_DEFAULT = 0x00, + /* Job is not QMP-created and should not send QMP events */ + JOB_INTERNAL = 0x01, + /* Job requires manual finalize step */ + JOB_MANUAL_FINALIZE = 0x02, + /* Job requires manual dismiss step */ + JOB_MANUAL_DISMISS = 0x04, +} JobCreateFlags; + +/** + * Allocate and return a new job transaction. Jobs can be added to the + * transaction using 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. + */ +JobTxn *job_txn_new(void); + +/** + * Release a reference that was previously acquired with job_txn_add_job or + * job_txn_new. If it's the last reference to the object, it will be freed. + */ +void job_txn_unref(JobTxn *txn); + +/** + * @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 job_txn_unref() or job_completed() to release + * the reference that is automatically grabbed here. + * + * If @txn is NULL, the function does nothing. + */ +void job_txn_add_job(JobTxn *txn, Job *job); + +/** + * Create a new long-running job and return it. + * + * @job_id: The id of the newly-created job, or %NULL for internal jobs + * @driver: The class object for the newly-created job. + * @txn: The transaction this job belongs to, if any. %NULL otherwise. + * @ctx: The AioContext to run the job coroutine in. + * @flags: Creation flags for the job. See @JobCreateFlags. + * @cb: Completion function for the job. + * @opaque: Opaque pointer value passed to @cb. + * @errp: Error object. + */ +void *job_create(const char *job_id, const JobDriver *driver, JobTxn *txn, + AioContext *ctx, int flags, BlockCompletionFunc *cb, + void *opaque, Error **errp); + +/** + * Add a reference to Job refcnt, it will be decreased with job_unref, and then + * be freed if it comes to be the last reference. + */ +void job_ref(Job *job); + +/** + * Release a reference that was previously acquired with job_ref() or + * job_create(). If it's the last reference to the object, it will be freed. + */ +void job_unref(Job *job); + +/** + * @job: The job that has made progress + * @done: How much progress the job made since the last call + * + * Updates the progress counter of the job. + */ +void job_progress_update(Job *job, uint64_t done); + +/** + * @job: The job whose expected progress end value is set + * @remaining: Missing progress (on top of the current progress counter value) + * until the new expected end value is reached + * + * Sets the expected end value of the progress counter of a job so that a + * completion percentage can be calculated when the progress is updated. + */ +void job_progress_set_remaining(Job *job, uint64_t remaining); + +/** To be called when a cancelled job is finalised. */ +void job_event_cancelled(Job *job); + +/** To be called when a successfully completed job is finalised. */ +void job_event_completed(Job *job); + +/** + * Conditionally enter the job coroutine if the job is ready to run, not + * already busy and fn() returns true. fn() is called while under the job_lock + * critical section. + */ +void job_enter_cond(Job *job, bool(*fn)(Job *job)); + +/** + * @job: A job that has not yet been started. + * + * Begins execution of a job. + * Takes ownership of one reference to the job object. + */ +void job_start(Job *job); + +/** + * @job: The job to enter. + * + * Continue the specified job by entering the coroutine. + */ +void job_enter(Job *job); + +/** + * @job: The job that is ready to pause. + * + * Pause now if job_pause() has been called. Jobs that perform lots of I/O + * must call this between requests so that the job can be paused. + */ +void coroutine_fn job_pause_point(Job *job); + +/** + * @job: The job that calls the function. + * + * Yield the job coroutine. + */ +void job_yield(Job *job); + +/** + * @job: The job that calls the function. + * @ns: How many nanoseconds to stop for. + * + * Put the job to sleep (assuming that it wasn't canceled) for @ns + * %QEMU_CLOCK_REALTIME nanoseconds. Canceling the job will immediately + * interrupt the wait. + */ +void coroutine_fn job_sleep_ns(Job *job, int64_t ns); + + +/** Returns the JobType of a given Job. */ +JobType job_type(const Job *job); + +/** Returns the enum string for the JobType of a given Job. */ +const char *job_type_str(const Job *job); + +/** Returns true if the job should not be visible to the management layer. */ +bool job_is_internal(Job *job); + +/** Returns whether the job is scheduled for cancellation. */ +bool job_is_cancelled(Job *job); + +/** Returns whether the job is in a completed state. */ +bool job_is_completed(Job *job); + +/** Returns whether the job is ready to be completed. */ +bool job_is_ready(Job *job); + +/** + * Request @job to pause at the next pause point. Must be paired with + * job_resume(). If the job is supposed to be resumed by user action, call + * job_user_pause() instead. + */ +void job_pause(Job *job); + +/** Resumes a @job paused with job_pause. */ +void job_resume(Job *job); + +/** + * Asynchronously pause the specified @job. + * Do not allow a resume until a matching call to job_user_resume. + */ +void job_user_pause(Job *job, Error **errp); + +/** Returns true if the job is user-paused. */ +bool job_user_paused(Job *job); + +/** + * Resume the specified @job. + * Must be paired with a preceding job_user_pause. + */ +void job_user_resume(Job *job, Error **errp); + +/* + * Drain any activities as required to ensure progress. This can be called in a + * loop to synchronously complete a job. + */ +void job_drain(Job *job); + +/** + * Get the next element from the list of block jobs after @job, or the + * first one if @job is %NULL. + * + * Returns the requested job, or %NULL if there are no more jobs left. + */ +Job *job_next(Job *job); + +/** + * Get the job identified by @id (which must not be %NULL). + * + * Returns the requested job, or %NULL if it doesn't exist. + */ +Job *job_get(const char *id); + +/** + * Check whether the verb @verb can be applied to @job in its current state. + * Returns 0 if the verb can be applied; otherwise errp is set and -EPERM + * returned. + */ +int job_apply_verb(Job *job, JobVerb verb, Error **errp); + +/** The @job could not be started, free it. */ +void job_early_fail(Job *job); + +/** Moves the @job from RUNNING to READY */ +void job_transition_to_ready(Job *job); + +/** + * @job: The job being completed. + * @ret: The status code. + * @error: The error message for a failing job (only with @ret < 0). If @ret is + * negative, but NULL is given for @error, strerror() is used. + * + * Marks @job as completed. If @ret is non-zero, the job transaction it is part + * of is aborted. If @ret is zero, the job moves into the WAITING state. If it + * is the last job to complete in its transaction, all jobs in the transaction + * move from WAITING to PENDING. + */ +void job_completed(Job *job, int ret, Error *error); + +/** Asynchronously complete the specified @job. */ +void job_complete(Job *job, Error **errp); + +/** + * Asynchronously cancel the specified @job. If @force is true, the job should + * be cancelled immediately without waiting for a consistent state. + */ +void job_cancel(Job *job, bool force); + +/** + * Cancels the specified job like job_cancel(), but may refuse to do so if the + * operation isn't meaningful in the current state of the job. + */ +void job_user_cancel(Job *job, bool force, Error **errp); + +/** + * Synchronously cancel the @job. The completion callback is called + * before the function returns. The job may actually complete + * instead of canceling itself; the circumstances under which this + * happens depend on the kind of job that is active. + * + * Returns the return value from the job if the job actually completed + * during the call, or -ECANCELED if it was canceled. + */ +int job_cancel_sync(Job *job); + +/** Synchronously cancels all jobs using job_cancel_sync(). */ +void job_cancel_sync_all(void); + +/** + * @job: The job to be completed. + * @errp: Error object which may be set by job_complete(); this is not + * necessarily set on every error, the job return value has to be + * checked as well. + * + * Synchronously complete the job. The completion callback is called before the + * function returns, unless it is NULL (which is permissible when using this + * function). + * + * Returns the return value from the job. + */ +int job_complete_sync(Job *job, Error **errp); + +/** + * For a @job that has finished its work and is pending awaiting explicit + * acknowledgement to commit its work, this will commit that work. + * + * FIXME: Make the below statement universally true: + * For jobs that support the manual workflow mode, all graph changes that occur + * as a result will occur after this command and before a successful reply. + */ +void job_finalize(Job *job, Error **errp); + +/** + * Remove the concluded @job from the query list and resets the passed pointer + * to %NULL. Returns an error if the job is not actually concluded. + */ +void job_dismiss(Job **job, Error **errp); + +typedef void JobDeferToMainLoopFn(Job *job, void *opaque); + +/** + * @job: The job + * @fn: The function to run in the main loop + * @opaque: The opaque value that is passed to @fn + * + * This function must be called by the main job coroutine just before it + * returns. @fn is executed in the main loop with the job 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 job_defer_to_main_loop(Job *job, JobDeferToMainLoopFn *fn, void *opaque); + +/** + * Synchronously finishes the given @job. If @finish is given, it is called to + * trigger completion or cancellation of the job. + * + * Returns 0 if the job is successfully completed, -ECANCELED if the job was + * cancelled before completing, and -errno in other error cases. + */ +int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp); + +#endif diff --git a/include/standard-headers/asm-x86/hyperv.h b/include/standard-headers/asm-x86/hyperv.h deleted file mode 100644 index ce87d0c344..0000000000 --- a/include/standard-headers/asm-x86/hyperv.h +++ /dev/null @@ -1 +0,0 @@ - /* this is a temporary placeholder until kvm_para.h stops including it */ diff --git a/include/standard-headers/asm-x86/kvm_para.h b/include/standard-headers/asm-x86/kvm_para.h index 53a85ae3ed..1617c84b0d 100644 --- a/include/standard-headers/asm-x86/kvm_para.h +++ b/include/standard-headers/asm-x86/kvm_para.h @@ -29,7 +29,7 @@ #define KVM_FEATURE_PV_TLB_FLUSH 9 #define KVM_FEATURE_ASYNC_PF_VMEXIT 10 -#define KVM_HINTS_DEDICATED 0 +#define KVM_HINTS_REALTIME 0 /* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored. diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h index 94aacb7adf..eb10c075e4 100644 --- a/include/standard-headers/linux/ethtool.h +++ b/include/standard-headers/linux/ethtool.h @@ -217,10 +217,14 @@ struct ethtool_value { uint32_t data; }; +#define PFC_STORM_PREVENTION_AUTO 0xffff +#define PFC_STORM_PREVENTION_DISABLE 0 + enum tunable_id { ETHTOOL_ID_UNSPEC, ETHTOOL_RX_COPYBREAK, ETHTOOL_TX_COPYBREAK, + ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */ /* * Add your fresh new tubale attribute above and remember to update * tunable_strings[] in net/core/ethtool.c @@ -914,12 +918,15 @@ static inline uint64_t ethtool_get_flow_spec_ring_vf(uint64_t ring_cookie) * @flow_type: Type of flow to be affected, e.g. %TCP_V4_FLOW * @data: Command-dependent value * @fs: Flow classification rule + * @rss_context: RSS context to be affected * @rule_cnt: Number of rules to be affected * @rule_locs: Array of used rule locations * * For %ETHTOOL_GRXFH and %ETHTOOL_SRXFH, @data is a bitmask indicating * the fields included in the flow hash, e.g. %RXH_IP_SRC. The following - * structure fields must not be used. + * structure fields must not be used, except that if @flow_type includes + * the %FLOW_RSS flag, then @rss_context determines which RSS context to + * act on. * * For %ETHTOOL_GRXRINGS, @data is set to the number of RX rings/queues * on return. @@ -931,7 +938,9 @@ static inline uint64_t ethtool_get_flow_spec_ring_vf(uint64_t ring_cookie) * set in @data then special location values should not be used. * * For %ETHTOOL_GRXCLSRULE, @fs.@location specifies the location of an - * existing rule on entry and @fs contains the rule on return. + * existing rule on entry and @fs contains the rule on return; if + * @fs.@flow_type includes the %FLOW_RSS flag, then @rss_context is + * filled with the RSS context ID associated with the rule. * * For %ETHTOOL_GRXCLSRLALL, @rule_cnt specifies the array size of the * user buffer for @rule_locs on entry. On return, @data is the size @@ -942,7 +951,11 @@ static inline uint64_t ethtool_get_flow_spec_ring_vf(uint64_t ring_cookie) * For %ETHTOOL_SRXCLSRLINS, @fs specifies the rule to add or update. * @fs.@location either specifies the location to use or is a special * location value with %RX_CLS_LOC_SPECIAL flag set. On return, - * @fs.@location is the actual rule location. + * @fs.@location is the actual rule location. If @fs.@flow_type + * includes the %FLOW_RSS flag, @rss_context is the RSS context ID to + * use for flow spreading traffic which matches this rule. The value + * from the rxfh indirection table will be added to @fs.@ring_cookie + * to choose which ring to deliver to. * * For %ETHTOOL_SRXCLSRLDEL, @fs.@location specifies the location of an * existing rule on entry. @@ -963,7 +976,10 @@ struct ethtool_rxnfc { uint32_t flow_type; uint64_t data; struct ethtool_rx_flow_spec fs; - uint32_t rule_cnt; + union { + uint32_t rule_cnt; + uint32_t rss_context; + }; uint32_t rule_locs[0]; }; @@ -990,7 +1006,11 @@ struct ethtool_rxfh_indir { /** * struct ethtool_rxfh - command to get/set RX flow hash indir or/and hash key. * @cmd: Specific command number - %ETHTOOL_GRSSH or %ETHTOOL_SRSSH - * @rss_context: RSS context identifier. + * @rss_context: RSS context identifier. Context 0 is the default for normal + * traffic; other contexts can be referenced as the destination for RX flow + * classification rules. %ETH_RXFH_CONTEXT_ALLOC is used with command + * %ETHTOOL_SRSSH to allocate a new RSS context; on return this field will + * contain the ID of the newly allocated context. * @indir_size: On entry, the array size of the user buffer for the * indirection table, which may be zero, or (for %ETHTOOL_SRSSH), * %ETH_RXFH_INDIR_NO_CHANGE. On return from %ETHTOOL_GRSSH, @@ -1009,7 +1029,8 @@ struct ethtool_rxfh_indir { * size should be returned. For %ETHTOOL_SRSSH, an @indir_size of * %ETH_RXFH_INDIR_NO_CHANGE means that indir table setting is not requested * and a @indir_size of zero means the indir table should be reset to default - * values. An hfunc of zero means that hash function setting is not requested. + * values (if @rss_context == 0) or that the RSS context should be deleted. + * An hfunc of zero means that hash function setting is not requested. */ struct ethtool_rxfh { uint32_t cmd; @@ -1021,6 +1042,7 @@ struct ethtool_rxfh { uint32_t rsvd32; uint32_t rss_config[0]; }; +#define ETH_RXFH_CONTEXT_ALLOC 0xffffffff #define ETH_RXFH_INDIR_NO_CHANGE 0xffffffff /** @@ -1635,6 +1657,8 @@ static inline int ethtool_validate_duplex(uint8_t duplex) /* Flag to enable additional fields in struct ethtool_rx_flow_spec */ #define FLOW_EXT 0x80000000 #define FLOW_MAC_EXT 0x40000000 +/* Flag to enable RSS spreading of traffic matching rule (nfc only) */ +#define FLOW_RSS 0x20000000 /* L3-L4 network traffic flow hash options */ #define RXH_L2DA (1 << 1) diff --git a/include/standard-headers/linux/input.h b/include/standard-headers/linux/input.h index 939b62775c..6d6128c081 100644 --- a/include/standard-headers/linux/input.h +++ b/include/standard-headers/linux/input.h @@ -28,8 +28,8 @@ struct input_event { #define input_event_sec time.tv_sec #define input_event_usec time.tv_usec #else - __kernel_ulong_t __sec; - __kernel_ulong_t __usec; + unsigned long __sec; + unsigned long __usec; #define input_event_sec __sec #define input_event_usec __usec #endif diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h index 0c79eac5e9..103ba797a8 100644 --- a/include/standard-headers/linux/pci_regs.h +++ b/include/standard-headers/linux/pci_regs.h @@ -520,6 +520,7 @@ #define PCI_EXP_LNKCAP_SLS_2_5GB 0x00000001 /* LNKCAP2 SLS Vector bit 0 */ #define PCI_EXP_LNKCAP_SLS_5_0GB 0x00000002 /* LNKCAP2 SLS Vector bit 1 */ #define PCI_EXP_LNKCAP_SLS_8_0GB 0x00000003 /* LNKCAP2 SLS Vector bit 2 */ +#define PCI_EXP_LNKCAP_SLS_16_0GB 0x00000004 /* LNKCAP2 SLS Vector bit 3 */ #define PCI_EXP_LNKCAP_MLW 0x000003f0 /* Maximum Link Width */ #define PCI_EXP_LNKCAP_ASPMS 0x00000c00 /* ASPM Support */ #define PCI_EXP_LNKCAP_L0SEL 0x00007000 /* L0s Exit Latency */ @@ -547,6 +548,7 @@ #define PCI_EXP_LNKSTA_CLS_2_5GB 0x0001 /* Current Link Speed 2.5GT/s */ #define PCI_EXP_LNKSTA_CLS_5_0GB 0x0002 /* Current Link Speed 5.0GT/s */ #define PCI_EXP_LNKSTA_CLS_8_0GB 0x0003 /* Current Link Speed 8.0GT/s */ +#define PCI_EXP_LNKSTA_CLS_16_0GB 0x0004 /* Current Link Speed 16.0GT/s */ #define PCI_EXP_LNKSTA_NLW 0x03f0 /* Negotiated Link Width */ #define PCI_EXP_LNKSTA_NLW_X1 0x0010 /* Current Link Width x1 */ #define PCI_EXP_LNKSTA_NLW_X2 0x0020 /* Current Link Width x2 */ @@ -648,8 +650,9 @@ #define PCI_CAP_EXP_RC_ENDPOINT_SIZEOF_V2 44 /* v2 endpoints without link end here */ #define PCI_EXP_LNKCAP2 44 /* Link Capabilities 2 */ #define PCI_EXP_LNKCAP2_SLS_2_5GB 0x00000002 /* Supported Speed 2.5GT/s */ -#define PCI_EXP_LNKCAP2_SLS_5_0GB 0x00000004 /* Supported Speed 5.0GT/s */ -#define PCI_EXP_LNKCAP2_SLS_8_0GB 0x00000008 /* Supported Speed 8.0GT/s */ +#define PCI_EXP_LNKCAP2_SLS_5_0GB 0x00000004 /* Supported Speed 5GT/s */ +#define PCI_EXP_LNKCAP2_SLS_8_0GB 0x00000008 /* Supported Speed 8GT/s */ +#define PCI_EXP_LNKCAP2_SLS_16_0GB 0x00000010 /* Supported Speed 16GT/s */ #define PCI_EXP_LNKCAP2_CROSSLINK 0x00000100 /* Crosslink supported */ #define PCI_EXP_LNKCTL2 48 /* Link Control 2 */ #define PCI_EXP_LNKSTA2 50 /* Link Status 2 */ diff --git a/include/standard-headers/linux/virtio_balloon.h b/include/standard-headers/linux/virtio_balloon.h index e446805ae9..4dbb7dc6c0 100644 --- a/include/standard-headers/linux/virtio_balloon.h +++ b/include/standard-headers/linux/virtio_balloon.h @@ -57,6 +57,21 @@ struct virtio_balloon_config { #define VIRTIO_BALLOON_S_HTLB_PGFAIL 9 /* Hugetlb page allocation failures */ #define VIRTIO_BALLOON_S_NR 10 +#define VIRTIO_BALLOON_S_NAMES_WITH_PREFIX(VIRTIO_BALLOON_S_NAMES_prefix) { \ + VIRTIO_BALLOON_S_NAMES_prefix "swap-in", \ + VIRTIO_BALLOON_S_NAMES_prefix "swap-out", \ + VIRTIO_BALLOON_S_NAMES_prefix "major-faults", \ + VIRTIO_BALLOON_S_NAMES_prefix "minor-faults", \ + VIRTIO_BALLOON_S_NAMES_prefix "free-memory", \ + VIRTIO_BALLOON_S_NAMES_prefix "total-memory", \ + VIRTIO_BALLOON_S_NAMES_prefix "available-memory", \ + VIRTIO_BALLOON_S_NAMES_prefix "disk-caches", \ + VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-allocations", \ + VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-failures" \ +} + +#define VIRTIO_BALLOON_S_NAMES VIRTIO_BALLOON_S_NAMES_WITH_PREFIX("") + /* * Memory statistics structure. * Driver fills an array of these structures and passes to device. diff --git a/include/standard-headers/linux/virtio_gpu.h b/include/standard-headers/linux/virtio_gpu.h index 52a830dcf8..c1c8f0751d 100644 --- a/include/standard-headers/linux/virtio_gpu.h +++ b/include/standard-headers/linux/virtio_gpu.h @@ -260,7 +260,6 @@ struct virtio_gpu_cmd_submit { }; #define VIRTIO_GPU_CAPSET_VIRGL 1 -#define VIRTIO_GPU_CAPSET_VIRGL2 2 /* VIRTIO_GPU_CMD_GET_CAPSET_INFO */ struct virtio_gpu_get_capset_info { diff --git a/include/standard-headers/rdma/vmw_pvrdma-abi.h b/include/standard-headers/rdma/vmw_pvrdma-abi.h index 07a820d337..6c2bc46116 100644 --- a/include/standard-headers/rdma/vmw_pvrdma-abi.h +++ b/include/standard-headers/rdma/vmw_pvrdma-abi.h @@ -143,7 +143,7 @@ struct pvrdma_alloc_pd_resp { }; struct pvrdma_create_cq { - uint64_t buf_addr; + uint64_t __attribute__((aligned(8))) buf_addr; uint32_t buf_size; uint32_t reserved; }; @@ -154,13 +154,13 @@ struct pvrdma_create_cq_resp { }; struct pvrdma_resize_cq { - uint64_t buf_addr; + uint64_t __attribute__((aligned(8))) buf_addr; uint32_t buf_size; uint32_t reserved; }; struct pvrdma_create_srq { - uint64_t buf_addr; + uint64_t __attribute__((aligned(8))) buf_addr; uint32_t buf_size; uint32_t reserved; }; @@ -171,25 +171,25 @@ struct pvrdma_create_srq_resp { }; struct pvrdma_create_qp { - uint64_t rbuf_addr; - uint64_t sbuf_addr; + uint64_t __attribute__((aligned(8))) rbuf_addr; + uint64_t __attribute__((aligned(8))) sbuf_addr; uint32_t rbuf_size; uint32_t sbuf_size; - uint64_t qp_addr; + uint64_t __attribute__((aligned(8))) qp_addr; }; /* PVRDMA masked atomic compare and swap */ struct pvrdma_ex_cmp_swap { - uint64_t swap_val; - uint64_t compare_val; - uint64_t swap_mask; - uint64_t compare_mask; + uint64_t __attribute__((aligned(8))) swap_val; + uint64_t __attribute__((aligned(8))) compare_val; + uint64_t __attribute__((aligned(8))) swap_mask; + uint64_t __attribute__((aligned(8))) compare_mask; }; /* PVRDMA masked atomic fetch and add */ struct pvrdma_ex_fetch_add { - uint64_t add_val; - uint64_t field_boundary; + uint64_t __attribute__((aligned(8))) add_val; + uint64_t __attribute__((aligned(8))) field_boundary; }; /* PVRDMA address vector. */ @@ -207,14 +207,14 @@ struct pvrdma_av { /* PVRDMA scatter/gather entry */ struct pvrdma_sge { - uint64_t addr; + uint64_t __attribute__((aligned(8))) addr; uint32_t length; uint32_t lkey; }; /* PVRDMA receive queue work request */ struct pvrdma_rq_wqe_hdr { - uint64_t wr_id; /* wr id */ + uint64_t __attribute__((aligned(8))) wr_id; /* wr id */ uint32_t num_sge; /* size of s/g array */ uint32_t total_len; /* reserved */ }; @@ -222,7 +222,7 @@ struct pvrdma_rq_wqe_hdr { /* PVRDMA send queue work request */ struct pvrdma_sq_wqe_hdr { - uint64_t wr_id; /* wr id */ + uint64_t __attribute__((aligned(8))) wr_id; /* wr id */ uint32_t num_sge; /* size of s/g array */ uint32_t total_len; /* reserved */ uint32_t opcode; /* operation type */ @@ -234,19 +234,19 @@ struct pvrdma_sq_wqe_hdr { uint32_t reserved; union { struct { - uint64_t remote_addr; + uint64_t __attribute__((aligned(8))) remote_addr; uint32_t rkey; uint8_t reserved[4]; } rdma; struct { - uint64_t remote_addr; - uint64_t compare_add; - uint64_t swap; + uint64_t __attribute__((aligned(8))) remote_addr; + uint64_t __attribute__((aligned(8))) compare_add; + uint64_t __attribute__((aligned(8))) swap; uint32_t rkey; uint32_t reserved; } atomic; struct { - uint64_t remote_addr; + uint64_t __attribute__((aligned(8))) remote_addr; uint32_t log_arg_sz; uint32_t rkey; union { @@ -255,13 +255,14 @@ struct pvrdma_sq_wqe_hdr { } wr_data; } masked_atomics; struct { - uint64_t iova_start; - uint64_t pl_pdir_dma; + uint64_t __attribute__((aligned(8))) iova_start; + uint64_t __attribute__((aligned(8))) pl_pdir_dma; uint32_t page_shift; uint32_t page_list_len; uint32_t length; uint32_t access_flags; uint32_t rkey; + uint32_t reserved; } fast_reg; struct { uint32_t remote_qpn; @@ -274,8 +275,8 @@ struct pvrdma_sq_wqe_hdr { /* Completion queue element. */ struct pvrdma_cqe { - uint64_t wr_id; - uint64_t qp; + uint64_t __attribute__((aligned(8))) wr_id; + uint64_t __attribute__((aligned(8))) qp; uint32_t opcode; uint32_t status; uint32_t byte_len; diff --git a/include/sysemu/dma.h b/include/sysemu/dma.h index c228c66513..5da3c4e3c5 100644 --- a/include/sysemu/dma.h +++ b/include/sysemu/dma.h @@ -77,7 +77,8 @@ static inline bool dma_memory_valid(AddressSpace *as, DMADirection dir) { return address_space_access_valid(as, addr, len, - dir == DMA_DIRECTION_FROM_DEVICE); + dir == DMA_DIRECTION_FROM_DEVICE, + MEMTXATTRS_UNSPECIFIED); } static inline int dma_memory_rw_relaxed(AddressSpace *as, dma_addr_t addr, @@ -132,7 +133,8 @@ static inline void *dma_memory_map(AddressSpace *as, hwaddr xlen = *len; void *p; - p = address_space_map(as, addr, &xlen, dir == DMA_DIRECTION_FROM_DEVICE); + p = address_space_map(as, addr, &xlen, dir == DMA_DIRECTION_FROM_DEVICE, + MEMTXATTRS_UNSPECIFIED); *len = xlen; return p; } diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h index d99e5474b4..7a0ae751aa 100644 --- a/include/sysemu/numa.h +++ b/include/sysemu/numa.h @@ -22,7 +22,9 @@ struct NumaNodeMem { }; extern NodeInfo numa_info[MAX_NODES]; +int parse_numa(void *opaque, QemuOpts *opts, Error **errp); void parse_numa_opts(MachineState *ms); +void numa_complete_configuration(MachineState *ms); void query_numa_node_mem(NumaNodeMem node_mem[]); extern QemuOptsList qemu_numa_opts; void numa_legacy_auto_assign_ram(MachineClass *mc, NodeInfo *nodes, diff --git a/include/sysemu/seccomp.h b/include/sysemu/seccomp.h index 9b092aa23f..fe859894f6 100644 --- a/include/sysemu/seccomp.h +++ b/include/sysemu/seccomp.h @@ -21,5 +21,6 @@ #define QEMU_SECCOMP_SET_SPAWN (1 << 3) #define QEMU_SECCOMP_SET_RESOURCECTL (1 << 4) -int seccomp_start(uint32_t seccomp_opts); +int parse_sandbox(void *opaque, QemuOpts *opts, Error **errp); + #endif diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h index 544ab77a2b..e893f72f3b 100644 --- a/include/sysemu/sysemu.h +++ b/include/sysemu/sysemu.h @@ -66,6 +66,7 @@ typedef enum WakeupReason { QEMU_WAKEUP_REASON_OTHER, } WakeupReason; +void qemu_exit_preconfig_request(void); void qemu_system_reset_request(ShutdownCause reason); void qemu_system_suspend_request(void); void qemu_register_suspend_notifier(Notifier *notifier); diff --git a/include/sysemu/xen-mapcache.h b/include/sysemu/xen-mapcache.h index bd4d49e0a4..a03e2f1878 100644 --- a/include/sysemu/xen-mapcache.h +++ b/include/sysemu/xen-mapcache.h @@ -9,9 +9,8 @@ #ifndef XEN_MAPCACHE_H #define XEN_MAPCACHE_H -typedef hwaddr (*phys_offset_to_gaddr_t)(hwaddr start_addr, - ram_addr_t size, - void *opaque); +typedef hwaddr (*phys_offset_to_gaddr_t)(hwaddr phys_offset, + ram_addr_t size); #ifdef CONFIG_XEN void xen_map_cache_init(phys_offset_to_gaddr_t f, |