diff options
Diffstat (limited to 'include')
-rw-r--r-- | include/block/aio.h | 31 | ||||
-rw-r--r-- | include/exec/memory.h | 324 | ||||
-rw-r--r-- | include/hw/block/block.h | 3 | ||||
-rw-r--r-- | include/hw/vfio/vfio-common.h | 12 | ||||
-rw-r--r-- | include/hw/virtio/virtio-mem.h | 3 | ||||
-rw-r--r-- | include/migration/vmstate.h | 1 | ||||
-rw-r--r-- | include/qemu/main-loop.h | 4 |
7 files changed, 350 insertions, 28 deletions
diff --git a/include/block/aio.h b/include/block/aio.h index 10fcae1515..807edce9b5 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -292,19 +292,44 @@ void aio_context_acquire(AioContext *ctx); void aio_context_release(AioContext *ctx); /** + * aio_bh_schedule_oneshot_full: Allocate a new bottom half structure that will + * run only once and as soon as possible. + * + * @name: A human-readable identifier for debugging purposes. + */ +void aio_bh_schedule_oneshot_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque, + const char *name); + +/** * aio_bh_schedule_oneshot: Allocate a new bottom half structure that will run * only once and as soon as possible. + * + * A convenience wrapper for aio_bh_schedule_oneshot_full() that uses cb as the + * name string. */ -void aio_bh_schedule_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque); +#define aio_bh_schedule_oneshot(ctx, cb, opaque) \ + aio_bh_schedule_oneshot_full((ctx), (cb), (opaque), (stringify(cb))) /** - * aio_bh_new: Allocate a new bottom half structure. + * aio_bh_new_full: Allocate a new bottom half structure. * * Bottom halves are lightweight callbacks whose invocation is guaranteed * to be wait-free, thread-safe and signal-safe. The #QEMUBH structure * is opaque and must be allocated prior to its use. + * + * @name: A human-readable identifier for debugging purposes. + */ +QEMUBH *aio_bh_new_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque, + const char *name); + +/** + * aio_bh_new: Allocate a new bottom half structure + * + * A convenience wrapper for aio_bh_new_full() that uses the cb as the name + * string. */ -QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque); +#define aio_bh_new(ctx, cb, opaque) \ + aio_bh_new_full((ctx), (cb), (opaque), (stringify(cb))) /** * aio_notify: Force processing of pending events. diff --git a/include/exec/memory.h b/include/exec/memory.h index b116f7c64e..c3d417d317 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -42,6 +42,12 @@ typedef struct IOMMUMemoryRegionClass IOMMUMemoryRegionClass; DECLARE_OBJ_CHECKERS(IOMMUMemoryRegion, IOMMUMemoryRegionClass, IOMMU_MEMORY_REGION, TYPE_IOMMU_MEMORY_REGION) +#define TYPE_RAM_DISCARD_MANAGER "qemu:ram-discard-manager" +typedef struct RamDiscardManagerClass RamDiscardManagerClass; +typedef struct RamDiscardManager RamDiscardManager; +DECLARE_OBJ_CHECKERS(RamDiscardManager, RamDiscardManagerClass, + RAM_DISCARD_MANAGER, TYPE_RAM_DISCARD_MANAGER); + #ifdef CONFIG_FUZZ void fuzz_dma_read_cb(size_t addr, size_t len, @@ -65,6 +71,28 @@ struct ReservedRegion { unsigned type; }; +/** + * struct MemoryRegionSection: describes a fragment of a #MemoryRegion + * + * @mr: the region, or %NULL if empty + * @fv: the flat view of the address space the region is mapped in + * @offset_within_region: the beginning of the section, relative to @mr's start + * @size: the size of the section; will not exceed @mr's boundaries + * @offset_within_address_space: the address of the first byte of the section + * relative to the region's address space + * @readonly: writes to this section are ignored + * @nonvolatile: this section is non-volatile + */ +struct MemoryRegionSection { + Int128 size; + MemoryRegion *mr; + FlatView *fv; + hwaddr offset_within_region; + hwaddr offset_within_address_space; + bool readonly; + bool nonvolatile; +}; + typedef struct IOMMUTLBEntry IOMMUTLBEntry; /* See address_space_translate: bit 0 is read, bit 1 is write. */ @@ -448,6 +476,206 @@ struct IOMMUMemoryRegionClass { Error **errp); }; +typedef struct RamDiscardListener RamDiscardListener; +typedef int (*NotifyRamPopulate)(RamDiscardListener *rdl, + MemoryRegionSection *section); +typedef void (*NotifyRamDiscard)(RamDiscardListener *rdl, + MemoryRegionSection *section); + +struct RamDiscardListener { + /* + * @notify_populate: + * + * Notification that previously discarded memory is about to get populated. + * Listeners are able to object. If any listener objects, already + * successfully notified listeners are notified about a discard again. + * + * @rdl: the #RamDiscardListener getting notified + * @section: the #MemoryRegionSection to get populated. The section + * is aligned within the memory region to the minimum granularity + * unless it would exceed the registered section. + * + * Returns 0 on success. If the notification is rejected by the listener, + * an error is returned. + */ + NotifyRamPopulate notify_populate; + + /* + * @notify_discard: + * + * Notification that previously populated memory was discarded successfully + * and listeners should drop all references to such memory and prevent + * new population (e.g., unmap). + * + * @rdl: the #RamDiscardListener getting notified + * @section: the #MemoryRegionSection to get populated. The section + * is aligned within the memory region to the minimum granularity + * unless it would exceed the registered section. + */ + NotifyRamDiscard notify_discard; + + /* + * @double_discard_supported: + * + * The listener suppors getting @notify_discard notifications that span + * already discarded parts. + */ + bool double_discard_supported; + + MemoryRegionSection *section; + QLIST_ENTRY(RamDiscardListener) next; +}; + +static inline void ram_discard_listener_init(RamDiscardListener *rdl, + NotifyRamPopulate populate_fn, + NotifyRamDiscard discard_fn, + bool double_discard_supported) +{ + rdl->notify_populate = populate_fn; + rdl->notify_discard = discard_fn; + rdl->double_discard_supported = double_discard_supported; +} + +typedef int (*ReplayRamPopulate)(MemoryRegionSection *section, void *opaque); + +/* + * RamDiscardManagerClass: + * + * A #RamDiscardManager coordinates which parts of specific RAM #MemoryRegion + * regions are currently populated to be used/accessed by the VM, notifying + * after parts were discarded (freeing up memory) and before parts will be + * populated (consuming memory), to be used/acessed by the VM. + * + * A #RamDiscardManager can only be set for a RAM #MemoryRegion while the + * #MemoryRegion isn't mapped yet; it cannot change while the #MemoryRegion is + * mapped. + * + * The #RamDiscardManager is intended to be used by technologies that are + * incompatible with discarding of RAM (e.g., VFIO, which may pin all + * memory inside a #MemoryRegion), and require proper coordination to only + * map the currently populated parts, to hinder parts that are expected to + * remain discarded from silently getting populated and consuming memory. + * Technologies that support discarding of RAM don't have to bother and can + * simply map the whole #MemoryRegion. + * + * An example #RamDiscardManager is virtio-mem, which logically (un)plugs + * memory within an assigned RAM #MemoryRegion, coordinated with the VM. + * Logically unplugging memory consists of discarding RAM. The VM agreed to not + * access unplugged (discarded) memory - especially via DMA. virtio-mem will + * properly coordinate with listeners before memory is plugged (populated), + * and after memory is unplugged (discarded). + * + * Listeners are called in multiples of the minimum granularity (unless it + * would exceed the registered range) and changes are aligned to the minimum + * granularity within the #MemoryRegion. Listeners have to prepare for memory + * becomming discarded in a different granularity than it was populated and the + * other way around. + */ +struct RamDiscardManagerClass { + /* private */ + InterfaceClass parent_class; + + /* public */ + + /** + * @get_min_granularity: + * + * Get the minimum granularity in which listeners will get notified + * about changes within the #MemoryRegion via the #RamDiscardManager. + * + * @rdm: the #RamDiscardManager + * @mr: the #MemoryRegion + * + * Returns the minimum granularity. + */ + uint64_t (*get_min_granularity)(const RamDiscardManager *rdm, + const MemoryRegion *mr); + + /** + * @is_populated: + * + * Check whether the given #MemoryRegionSection is completely populated + * (i.e., no parts are currently discarded) via the #RamDiscardManager. + * There are no alignment requirements. + * + * @rdm: the #RamDiscardManager + * @section: the #MemoryRegionSection + * + * Returns whether the given range is completely populated. + */ + bool (*is_populated)(const RamDiscardManager *rdm, + const MemoryRegionSection *section); + + /** + * @replay_populated: + * + * Call the #ReplayRamPopulate callback for all populated parts within the + * #MemoryRegionSection via the #RamDiscardManager. + * + * In case any call fails, no further calls are made. + * + * @rdm: the #RamDiscardManager + * @section: the #MemoryRegionSection + * @replay_fn: the #ReplayRamPopulate callback + * @opaque: pointer to forward to the callback + * + * Returns 0 on success, or a negative error if any notification failed. + */ + int (*replay_populated)(const RamDiscardManager *rdm, + MemoryRegionSection *section, + ReplayRamPopulate replay_fn, void *opaque); + + /** + * @register_listener: + * + * Register a #RamDiscardListener for the given #MemoryRegionSection and + * immediately notify the #RamDiscardListener about all populated parts + * within the #MemoryRegionSection via the #RamDiscardManager. + * + * In case any notification fails, no further notifications are triggered + * and an error is logged. + * + * @rdm: the #RamDiscardManager + * @rdl: the #RamDiscardListener + * @section: the #MemoryRegionSection + */ + void (*register_listener)(RamDiscardManager *rdm, + RamDiscardListener *rdl, + MemoryRegionSection *section); + + /** + * @unregister_listener: + * + * Unregister a previously registered #RamDiscardListener via the + * #RamDiscardManager after notifying the #RamDiscardListener about all + * populated parts becoming unpopulated within the registered + * #MemoryRegionSection. + * + * @rdm: the #RamDiscardManager + * @rdl: the #RamDiscardListener + */ + void (*unregister_listener)(RamDiscardManager *rdm, + RamDiscardListener *rdl); +}; + +uint64_t ram_discard_manager_get_min_granularity(const RamDiscardManager *rdm, + const MemoryRegion *mr); + +bool ram_discard_manager_is_populated(const RamDiscardManager *rdm, + const MemoryRegionSection *section); + +int ram_discard_manager_replay_populated(const RamDiscardManager *rdm, + MemoryRegionSection *section, + ReplayRamPopulate replay_fn, + void *opaque); + +void ram_discard_manager_register_listener(RamDiscardManager *rdm, + RamDiscardListener *rdl, + MemoryRegionSection *section); + +void ram_discard_manager_unregister_listener(RamDiscardManager *rdm, + RamDiscardListener *rdl); + typedef struct CoalescedMemoryRange CoalescedMemoryRange; typedef struct MemoryRegionIoeventfd MemoryRegionIoeventfd; @@ -494,6 +722,7 @@ struct MemoryRegion { const char *name; unsigned ioeventfd_nb; MemoryRegionIoeventfd *ioeventfds; + RamDiscardManager *rdm; /* Only for RAM */ }; struct IOMMUMemoryRegion { @@ -825,28 +1054,6 @@ typedef bool (*flatview_cb)(Int128 start, */ void flatview_for_each_range(FlatView *fv, flatview_cb cb, void *opaque); -/** - * struct MemoryRegionSection: describes a fragment of a #MemoryRegion - * - * @mr: the region, or %NULL if empty - * @fv: the flat view of the address space the region is mapped in - * @offset_within_region: the beginning of the section, relative to @mr's start - * @size: the size of the section; will not exceed @mr's boundaries - * @offset_within_address_space: the address of the first byte of the section - * relative to the region's address space - * @readonly: writes to this section are ignored - * @nonvolatile: this section is non-volatile - */ -struct MemoryRegionSection { - Int128 size; - MemoryRegion *mr; - FlatView *fv; - hwaddr offset_within_region; - hwaddr offset_within_address_space; - bool readonly; - bool nonvolatile; -}; - static inline bool MemoryRegionSection_eq(MemoryRegionSection *a, MemoryRegionSection *b) { @@ -860,6 +1067,26 @@ static inline bool MemoryRegionSection_eq(MemoryRegionSection *a, } /** + * memory_region_section_new_copy: Copy a memory region section + * + * Allocate memory for a new copy, copy the memory region section, and + * properly take a reference on all relevant members. + * + * @s: the #MemoryRegionSection to copy + */ +MemoryRegionSection *memory_region_section_new_copy(MemoryRegionSection *s); + +/** + * memory_region_section_new_copy: Free a copied memory region section + * + * Free a copy of a memory section created via memory_region_section_new_copy(). + * properly dropping references on all relevant members. + * + * @s: the #MemoryRegionSection to copy + */ +void memory_region_section_free_copy(MemoryRegionSection *s); + +/** * memory_region_init: Initialize a memory region * * The region typically acts as a container for other memory regions. Use @@ -2024,6 +2251,41 @@ bool memory_region_present(MemoryRegion *container, hwaddr addr); bool memory_region_is_mapped(MemoryRegion *mr); /** + * memory_region_get_ram_discard_manager: get the #RamDiscardManager for a + * #MemoryRegion + * + * The #RamDiscardManager cannot change while a memory region is mapped. + * + * @mr: the #MemoryRegion + */ +RamDiscardManager *memory_region_get_ram_discard_manager(MemoryRegion *mr); + +/** + * memory_region_has_ram_discard_manager: check whether a #MemoryRegion has a + * #RamDiscardManager assigned + * + * @mr: the #MemoryRegion + */ +static inline bool memory_region_has_ram_discard_manager(MemoryRegion *mr) +{ + return !!memory_region_get_ram_discard_manager(mr); +} + +/** + * memory_region_set_ram_discard_manager: set the #RamDiscardManager for a + * #MemoryRegion + * + * This function must not be called for a mapped #MemoryRegion, a #MemoryRegion + * that does not cover RAM, or a #MemoryRegion that already has a + * #RamDiscardManager assigned. + * + * @mr: the #MemoryRegion + * @rdm: #RamDiscardManager to set + */ +void memory_region_set_ram_discard_manager(MemoryRegion *mr, + RamDiscardManager *rdm); + +/** * memory_region_find: translate an address/size relative to a * MemoryRegion into a #MemoryRegionSection. * @@ -2632,6 +2894,12 @@ static inline MemOp devend_memop(enum device_endian end) int ram_block_discard_disable(bool state); /* + * See ram_block_discard_disable(): only disable uncoordinated discards, + * keeping coordinated discards (via the RamDiscardManager) enabled. + */ +int ram_block_uncoordinated_discard_disable(bool state); + +/* * Inhibit technologies that disable discarding of pages in RAM blocks. * * Returns 0 if successful. Returns -EBUSY if discards are already set to @@ -2640,12 +2908,20 @@ int ram_block_discard_disable(bool state); int ram_block_discard_require(bool state); /* - * Test if discarding of memory in ram blocks is disabled. + * See ram_block_discard_require(): only inhibit technologies that disable + * uncoordinated discarding of pages in RAM blocks, allowing co-existance with + * technologies that only inhibit uncoordinated discards (via the + * RamDiscardManager). + */ +int ram_block_coordinated_discard_require(bool state); + +/* + * Test if any discarding of memory in ram blocks is disabled. */ bool ram_block_discard_is_disabled(void); /* - * Test if discarding of memory in ram blocks is required to work reliably. + * Test if any discarding of memory in ram blocks is required to work reliably. */ bool ram_block_discard_is_required(void); diff --git a/include/hw/block/block.h b/include/hw/block/block.h index c172cbe65f..5902c0440a 100644 --- a/include/hw/block/block.h +++ b/include/hw/block/block.h @@ -19,6 +19,7 @@ typedef struct BlockConf { BlockBackend *blk; + OnOffAuto backend_defaults; uint32_t physical_block_size; uint32_t logical_block_size; uint32_t min_io_size; @@ -48,6 +49,8 @@ static inline unsigned int get_physical_block_exp(BlockConf *conf) } #define DEFINE_BLOCK_PROPERTIES_BASE(_state, _conf) \ + DEFINE_PROP_ON_OFF_AUTO("backend_defaults", _state, \ + _conf.backend_defaults, ON_OFF_AUTO_AUTO), \ DEFINE_PROP_BLOCKSIZE("logical_block_size", _state, \ _conf.logical_block_size), \ DEFINE_PROP_BLOCKSIZE("physical_block_size", _state, \ diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 6141162d7a..8af11b0a76 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -88,9 +88,11 @@ typedef struct VFIOContainer { uint64_t dirty_pgsizes; uint64_t max_dirty_bitmap_size; unsigned long pgsizes; + unsigned int dma_max_mappings; QLIST_HEAD(, VFIOGuestIOMMU) giommu_list; QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list; QLIST_HEAD(, VFIOGroup) group_list; + QLIST_HEAD(, VFIORamDiscardListener) vrdl_list; QLIST_ENTRY(VFIOContainer) next; } VFIOContainer; @@ -102,6 +104,16 @@ typedef struct VFIOGuestIOMMU { QLIST_ENTRY(VFIOGuestIOMMU) giommu_next; } VFIOGuestIOMMU; +typedef struct VFIORamDiscardListener { + VFIOContainer *container; + MemoryRegion *mr; + hwaddr offset_within_address_space; + hwaddr size; + uint64_t granularity; + RamDiscardListener listener; + QLIST_ENTRY(VFIORamDiscardListener) next; +} VFIORamDiscardListener; + typedef struct VFIOHostDMAWindow { hwaddr min_iova; hwaddr max_iova; diff --git a/include/hw/virtio/virtio-mem.h b/include/hw/virtio/virtio-mem.h index 4eeb82d5dd..9a6e348fa2 100644 --- a/include/hw/virtio/virtio-mem.h +++ b/include/hw/virtio/virtio-mem.h @@ -67,6 +67,9 @@ struct VirtIOMEM { /* don't migrate unplugged memory */ NotifierWithReturn precopy_notifier; + + /* listeners to notify on plug/unplug activity. */ + QLIST_HEAD(, RamDiscardListener) rdl_list; }; struct VirtIOMEMClass { diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h index 8df7b69f38..017c03675c 100644 --- a/include/migration/vmstate.h +++ b/include/migration/vmstate.h @@ -153,6 +153,7 @@ typedef enum { MIG_PRI_DEFAULT = 0, MIG_PRI_IOMMU, /* Must happen before PCI devices */ MIG_PRI_PCI_BUS, /* Must happen before IOMMU */ + MIG_PRI_VIRTIO_MEM, /* Must happen before IOMMU */ MIG_PRI_GICV3_ITS, /* Must happen before PCI devices */ MIG_PRI_GICV3, /* Must happen before the ITS */ MIG_PRI_MAX, diff --git a/include/qemu/main-loop.h b/include/qemu/main-loop.h index 98aef5647c..8dbc6fcb89 100644 --- a/include/qemu/main-loop.h +++ b/include/qemu/main-loop.h @@ -294,7 +294,9 @@ void qemu_cond_timedwait_iothread(QemuCond *cond, int ms); void qemu_fd_register(int fd); -QEMUBH *qemu_bh_new(QEMUBHFunc *cb, void *opaque); +#define qemu_bh_new(cb, opaque) \ + qemu_bh_new_full((cb), (opaque), (stringify(cb))) +QEMUBH *qemu_bh_new_full(QEMUBHFunc *cb, void *opaque, const char *name); void qemu_bh_schedule_idle(QEMUBH *bh); enum { |