memory.h 79.2 KB
Newer Older
A
Avi Kivity 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18
/*
 * Physical memory management API
 *
 * Copyright 2011 Red Hat, Inc. and/or its affiliates
 *
 * Authors:
 *  Avi Kivity <avi@redhat.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#ifndef MEMORY_H
#define MEMORY_H

#ifndef CONFIG_USER_ONLY

19 20
#include "exec/cpu-common.h"
#include "exec/hwaddr.h"
21
#include "exec/memattrs.h"
P
Paolo Bonzini 已提交
22
#include "exec/ramlist.h"
23 24
#include "qemu/queue.h"
#include "qemu/int128.h"
25
#include "qemu/notify.h"
P
Peter Crosthwaite 已提交
26
#include "qom/object.h"
27
#include "qemu/rcu.h"
28
#include "hw/qdev-core.h"
A
Avi Kivity 已提交
29

30 31
#define RAM_ADDR_INVALID (~(ram_addr_t)0)

32 33 34
#define MAX_PHYS_ADDR_SPACE_BITS 62
#define MAX_PHYS_ADDR            (((hwaddr)1 << MAX_PHYS_ADDR_SPACE_BITS) - 1)

P
Peter Crosthwaite 已提交
35 36 37 38
#define TYPE_MEMORY_REGION "qemu:memory-region"
#define MEMORY_REGION(obj) \
        OBJECT_CHECK(MemoryRegion, (obj), TYPE_MEMORY_REGION)

39 40 41
#define TYPE_IOMMU_MEMORY_REGION "qemu:iommu-memory-region"
#define IOMMU_MEMORY_REGION(obj) \
        OBJECT_CHECK(IOMMUMemoryRegion, (obj), TYPE_IOMMU_MEMORY_REGION)
42 43 44 45 46 47
#define IOMMU_MEMORY_REGION_CLASS(klass) \
        OBJECT_CLASS_CHECK(IOMMUMemoryRegionClass, (klass), \
                         TYPE_IOMMU_MEMORY_REGION)
#define IOMMU_MEMORY_REGION_GET_CLASS(obj) \
        OBJECT_GET_CLASS(IOMMUMemoryRegionClass, (obj), \
                         TYPE_IOMMU_MEMORY_REGION)
48

A
Avi Kivity 已提交
49
typedef struct MemoryRegionOps MemoryRegionOps;
50
typedef struct MemoryRegionMmio MemoryRegionMmio;
A
Avi Kivity 已提交
51

52 53 54 55 56
struct MemoryRegionMmio {
    CPUReadMemoryFunc *read[3];
    CPUWriteMemoryFunc *write[3];
};

A
Avi Kivity 已提交
57 58 59 60 61 62 63 64 65 66
typedef struct IOMMUTLBEntry IOMMUTLBEntry;

/* See address_space_translate: bit 0 is read, bit 1 is write.  */
typedef enum {
    IOMMU_NONE = 0,
    IOMMU_RO   = 1,
    IOMMU_WO   = 2,
    IOMMU_RW   = 3,
} IOMMUAccessFlags;

67 68
#define IOMMU_ACCESS_FLAG(r, w) (((r) ? IOMMU_RO : 0) | ((w) ? IOMMU_WO : 0))

A
Avi Kivity 已提交
69 70 71 72 73 74 75 76
struct IOMMUTLBEntry {
    AddressSpace    *target_as;
    hwaddr           iova;
    hwaddr           translated_addr;
    hwaddr           addr_mask;  /* 0xfff = 4k translation */
    IOMMUAccessFlags perm;
};

77 78 79 80 81 82 83 84 85 86 87 88 89 90
/*
 * Bitmap for different IOMMUNotifier capabilities. Each notifier can
 * register with one or multiple IOMMU Notifier capability bit(s).
 */
typedef enum {
    IOMMU_NOTIFIER_NONE = 0,
    /* Notify cache invalidations */
    IOMMU_NOTIFIER_UNMAP = 0x1,
    /* Notify entry changes (newly created entries) */
    IOMMU_NOTIFIER_MAP = 0x2,
} IOMMUNotifierFlag;

#define IOMMU_NOTIFIER_ALL (IOMMU_NOTIFIER_MAP | IOMMU_NOTIFIER_UNMAP)

91 92 93 94
struct IOMMUNotifier;
typedef void (*IOMMUNotify)(struct IOMMUNotifier *notifier,
                            IOMMUTLBEntry *data);

95
struct IOMMUNotifier {
96
    IOMMUNotify notify;
97
    IOMMUNotifierFlag notifier_flags;
98 99 100
    /* Notify for address space range start <= addr <= end */
    hwaddr start;
    hwaddr end;
101
    int iommu_idx;
102 103 104 105
    QLIST_ENTRY(IOMMUNotifier) node;
};
typedef struct IOMMUNotifier IOMMUNotifier;

106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125
/* RAM is pre-allocated and passed into qemu_ram_alloc_from_ptr */
#define RAM_PREALLOC   (1 << 0)

/* RAM is mmap-ed with MAP_SHARED */
#define RAM_SHARED     (1 << 1)

/* Only a portion of RAM (used_length) is actually used, and migrated.
 * This used_length size can change across reboots.
 */
#define RAM_RESIZEABLE (1 << 2)

/* UFFDIO_ZEROPAGE is available on this RAMBlock to atomically
 * zero the page and wake waiting processes.
 * (Set during postcopy)
 */
#define RAM_UF_ZEROPAGE (1 << 3)

/* RAM can be migrated */
#define RAM_MIGRATABLE (1 << 4)

J
Junyan He 已提交
126 127 128
/* RAM is a persistent kind memory */
#define RAM_PMEM (1 << 5)

129 130
static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn,
                                       IOMMUNotifierFlag flags,
131 132
                                       hwaddr start, hwaddr end,
                                       int iommu_idx)
133 134 135 136 137
{
    n->notify = fn;
    n->notifier_flags = flags;
    n->start = start;
    n->end = end;
138
    n->iommu_idx = iommu_idx;
139 140
}

A
Avi Kivity 已提交
141 142 143 144 145 146 147
/*
 * Memory region callbacks
 */
struct MemoryRegionOps {
    /* Read from the memory region. @addr is relative to @mr; @size is
     * in bytes. */
    uint64_t (*read)(void *opaque,
A
Avi Kivity 已提交
148
                     hwaddr addr,
A
Avi Kivity 已提交
149 150 151 152
                     unsigned size);
    /* Write to the memory region. @addr is relative to @mr; @size is
     * in bytes. */
    void (*write)(void *opaque,
A
Avi Kivity 已提交
153
                  hwaddr addr,
A
Avi Kivity 已提交
154 155 156
                  uint64_t data,
                  unsigned size);

157 158 159 160 161 162 163 164 165 166 167
    MemTxResult (*read_with_attrs)(void *opaque,
                                   hwaddr addr,
                                   uint64_t *data,
                                   unsigned size,
                                   MemTxAttrs attrs);
    MemTxResult (*write_with_attrs)(void *opaque,
                                    hwaddr addr,
                                    uint64_t data,
                                    unsigned size,
                                    MemTxAttrs attrs);

A
Avi Kivity 已提交
168 169 170 171 172 173 174 175 176 177 178 179
    enum device_endian endianness;
    /* Guest-visible constraints: */
    struct {
        /* If nonzero, specify bounds on access sizes beyond which a machine
         * check is thrown.
         */
        unsigned min_access_size;
        unsigned max_access_size;
        /* If true, unaligned accesses are supported.  Otherwise unaligned
         * accesses throw machine checks.
         */
         bool unaligned;
180 181 182 183 184
        /*
         * If present, and returns #false, the transaction is not accepted
         * by the device (and results in machine dependent behaviour such
         * as a machine check exception).
         */
A
Avi Kivity 已提交
185
        bool (*accepts)(void *opaque, hwaddr addr,
186 187
                        unsigned size, bool is_write,
                        MemTxAttrs attrs);
A
Avi Kivity 已提交
188 189 190 191 192 193 194 195 196 197 198 199 200 201
    } valid;
    /* Internal implementation constraints: */
    struct {
        /* If nonzero, specifies the minimum size implemented.  Smaller sizes
         * will be rounded upwards and a partial result will be returned.
         */
        unsigned min_access_size;
        /* If nonzero, specifies the maximum size implemented.  Larger sizes
         * will be done as a series of accesses with smaller sizes.
         */
        unsigned max_access_size;
        /* If true, unaligned accesses are supported.  Otherwise all accesses
         * are converted to (possibly multiple) naturally aligned accesses.
         */
202
        bool unaligned;
A
Avi Kivity 已提交
203 204 205
    } impl;
};

206 207 208 209
enum IOMMUMemoryRegionAttr {
    IOMMU_ATTR_SPAPR_TCE_FD
};

210 211 212 213 214 215 216 217 218 219 220
/**
 * 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).
221 222 223 224 225 226 227 228 229 230 231 232 233 234
 *
 * Conceptually an IOMMU provides a mapping from input address
 * to an output TLB entry. If the IOMMU is aware of memory transaction
 * attributes and the output TLB entry depends on the transaction
 * attributes, we represent this using IOMMU indexes. Each index
 * selects a particular translation table that the IOMMU has:
 *   @attrs_to_index returns the IOMMU index for a set of transaction attributes
 *   @translate takes an input address and an IOMMU index
 * and the mapping returned can only depend on the input address and the
 * IOMMU index.
 *
 * Most IOMMUs don't care about the transaction attributes and support
 * only a single IOMMU index. A more complex IOMMU might have one index
 * for secure transactions and one for non-secure transactions.
235
 */
236 237 238
typedef struct IOMMUMemoryRegionClass {
    /* private */
    struct DeviceClass parent_class;
A
Avi Kivity 已提交
239

240
    /*
241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262
     * 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
263
     * @iommu_idx: IOMMU index for the translation
264
     */
265
    IOMMUTLBEntry (*translate)(IOMMUMemoryRegion *iommu, hwaddr addr,
266
                               IOMMUAccessFlags flag, int iommu_idx);
267 268 269 270 271 272
    /* 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
     */
273
    uint64_t (*get_min_page_size)(IOMMUMemoryRegion *iommu);
274 275 276 277 278 279 280 281 282
    /* 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
     */
283
    void (*notify_flag_changed)(IOMMUMemoryRegion *iommu,
284 285
                                IOMMUNotifierFlag old_flags,
                                IOMMUNotifierFlag new_flags);
286 287 288 289 290 291 292 293 294 295 296 297 298 299 300
    /* 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.
     */
301
    void (*replay)(IOMMUMemoryRegion *iommu, IOMMUNotifier *notifier);
302

303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318
    /* 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,
319
                    void *data);
320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342

    /* Return the IOMMU index to use for a given set of transaction attributes.
     *
     * Optional method: if an IOMMU only supports a single IOMMU index then
     * the default implementation of memory_region_iommu_attrs_to_index()
     * will return 0.
     *
     * The indexes supported by an IOMMU must be contiguous, starting at 0.
     *
     * @iommu: the IOMMUMemoryRegion
     * @attrs: memory transaction attributes
     */
    int (*attrs_to_index)(IOMMUMemoryRegion *iommu, MemTxAttrs attrs);

    /* Return the number of IOMMU indexes this IOMMU supports.
     *
     * Optional method: if this method is not provided, then
     * memory_region_iommu_num_indexes() will return 1, indicating that
     * only a single IOMMU index is supported.
     *
     * @iommu: the IOMMUMemoryRegion
     */
    int (*num_indexes)(IOMMUMemoryRegion *iommu);
343
} IOMMUMemoryRegionClass;
A
Avi Kivity 已提交
344

A
Avi Kivity 已提交
345
typedef struct CoalescedMemoryRange CoalescedMemoryRange;
A
Avi Kivity 已提交
346
typedef struct MemoryRegionIoeventfd MemoryRegionIoeventfd;
A
Avi Kivity 已提交
347 348

struct MemoryRegion {
P
Peter Crosthwaite 已提交
349
    Object parent_obj;
350

A
Avi Kivity 已提交
351
    /* All fields are private - violators will be prosecuted */
352 353 354 355 356 357

    /* The following fields should fit in a cache line */
    bool romd_mode;
    bool ram;
    bool subpage;
    bool readonly; /* For RAM regions */
358
    bool nonvolatile;
359 360 361 362
    bool rom_device;
    bool flush_coalesced_mmio;
    bool global_locking;
    uint8_t dirty_log_mask;
363
    bool is_iommu;
364
    RAMBlock *ram_block;
365
    Object *owner;
366 367

    const MemoryRegionOps *ops;
A
Avi Kivity 已提交
368
    void *opaque;
369
    MemoryRegion *container;
370
    Int128 size;
A
Avi Kivity 已提交
371
    hwaddr addr;
372
    void (*destructor)(MemoryRegion *mr);
373
    uint64_t align;
374
    bool terminates;
375
    bool ram_device;
376
    bool enabled;
377
    bool warning_printed; /* For reservations */
378
    uint8_t vga_logging_count;
A
Avi Kivity 已提交
379
    MemoryRegion *alias;
A
Avi Kivity 已提交
380
    hwaddr alias_offset;
381
    int32_t priority;
A
Avi Kivity 已提交
382 383 384
    QTAILQ_HEAD(subregions, MemoryRegion) subregions;
    QTAILQ_ENTRY(MemoryRegion) subregions_link;
    QTAILQ_HEAD(coalesced_ranges, CoalescedMemoryRange) coalesced;
385
    const char *name;
A
Avi Kivity 已提交
386 387
    unsigned ioeventfd_nb;
    MemoryRegionIoeventfd *ioeventfds;
388 389 390 391 392
};

struct IOMMUMemoryRegion {
    MemoryRegion parent_obj;

393
    QLIST_HEAD(, IOMMUNotifier) iommu_notify;
394
    IOMMUNotifierFlag iommu_notify_flags;
A
Avi Kivity 已提交
395 396
};

397 398 399
#define IOMMU_NOTIFIER_FOREACH(n, mr) \
    QLIST_FOREACH((n), &(mr)->iommu_notify, node)

400 401 402 403 404 405 406 407 408 409 410 411
/**
 * MemoryListener: callbacks structure for updates to the physical memory map
 *
 * Allows a component to adjust to changes in the guest-visible memory map.
 * Use with memory_listener_register() and memory_listener_unregister().
 */
struct MemoryListener {
    void (*begin)(MemoryListener *listener);
    void (*commit)(MemoryListener *listener);
    void (*region_add)(MemoryListener *listener, MemoryRegionSection *section);
    void (*region_del)(MemoryListener *listener, MemoryRegionSection *section);
    void (*region_nop)(MemoryListener *listener, MemoryRegionSection *section);
412 413 414 415
    void (*log_start)(MemoryListener *listener, MemoryRegionSection *section,
                      int old, int new);
    void (*log_stop)(MemoryListener *listener, MemoryRegionSection *section,
                     int old, int new);
416 417 418 419 420 421 422
    void (*log_sync)(MemoryListener *listener, MemoryRegionSection *section);
    void (*log_global_start)(MemoryListener *listener);
    void (*log_global_stop)(MemoryListener *listener);
    void (*eventfd_add)(MemoryListener *listener, MemoryRegionSection *section,
                        bool match_data, uint64_t data, EventNotifier *e);
    void (*eventfd_del)(MemoryListener *listener, MemoryRegionSection *section,
                        bool match_data, uint64_t data, EventNotifier *e);
P
Peng Hao 已提交
423
    void (*coalesced_io_add)(MemoryListener *listener, MemoryRegionSection *section,
424
                               hwaddr addr, hwaddr len);
P
Peng Hao 已提交
425
    void (*coalesced_io_del)(MemoryListener *listener, MemoryRegionSection *section,
426 427 428
                               hwaddr addr, hwaddr len);
    /* Lower = earlier (during add), later (during del) */
    unsigned priority;
429
    AddressSpace *address_space;
430
    QTAILQ_ENTRY(MemoryListener) link;
431
    QTAILQ_ENTRY(MemoryListener) link_as;
432 433
};

A
Avi Kivity 已提交
434 435 436 437 438
/**
 * AddressSpace: describes a mapping of addresses to #MemoryRegion objects
 */
struct AddressSpace {
    /* All fields are private. */
439
    struct rcu_head rcu;
440
    char *name;
A
Avi Kivity 已提交
441
    MemoryRegion *root;
442 443

    /* Accessed via RCU.  */
A
Avi Kivity 已提交
444
    struct FlatView *current_map;
445

A
Avi Kivity 已提交
446 447
    int ioeventfd_nb;
    struct MemoryRegionIoeventfd *ioeventfds;
448
    QTAILQ_HEAD(memory_listeners_as, MemoryListener) listeners;
449
    QTAILQ_ENTRY(AddressSpace) address_spaces_link;
A
Avi Kivity 已提交
450 451
};

452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472
typedef struct AddressSpaceDispatch AddressSpaceDispatch;
typedef struct FlatRange FlatRange;

/* Flattened global view of current active memory hierarchy.  Kept in sorted
 * order.
 */
struct FlatView {
    struct rcu_head rcu;
    unsigned ref;
    FlatRange *ranges;
    unsigned nr;
    unsigned nr_allocated;
    struct AddressSpaceDispatch *dispatch;
    MemoryRegion *root;
};

static inline FlatView *address_space_to_flatview(AddressSpace *as)
{
    return atomic_rcu_read(&as->current_map);
}

473

474 475 476 477
/**
 * MemoryRegionSection: describes a fragment of a #MemoryRegion
 *
 * @mr: the region, or %NULL if empty
478
 * @fv: the flat view of the address space the region is mapped in
479 480 481 482
 * @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
483
 * @readonly: writes to this section are ignored
484
 * @nonvolatile: this section is non-volatile
485 486 487
 */
struct MemoryRegionSection {
    MemoryRegion *mr;
488
    FlatView *fv;
A
Avi Kivity 已提交
489
    hwaddr offset_within_region;
490
    Int128 size;
A
Avi Kivity 已提交
491
    hwaddr offset_within_address_space;
492
    bool readonly;
493
    bool nonvolatile;
494 495
};

A
Avi Kivity 已提交
496 497 498
/**
 * memory_region_init: Initialize a memory region
 *
499
 * The region typically acts as a container for other memory regions.  Use
A
Avi Kivity 已提交
500 501 502
 * memory_region_add_subregion() to add subregions.
 *
 * @mr: the #MemoryRegion to be initialized
503
 * @owner: the object that tracks the region's reference count
A
Avi Kivity 已提交
504 505 506 507
 * @name: used for debugging; not visible to the user or ABI
 * @size: size of the region; any subregions beyond this size will be clipped
 */
void memory_region_init(MemoryRegion *mr,
508
                        struct Object *owner,
A
Avi Kivity 已提交
509 510
                        const char *name,
                        uint64_t size);
P
Paolo Bonzini 已提交
511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540

/**
 * memory_region_ref: Add 1 to a memory region's reference count
 *
 * Whenever memory regions are accessed outside the BQL, they need to be
 * preserved against hot-unplug.  MemoryRegions actually do not have their
 * own reference count; they piggyback on a QOM object, their "owner".
 * This function adds a reference to the owner.
 *
 * All MemoryRegions must have an owner if they can disappear, even if the
 * device they belong to operates exclusively under the BQL.  This is because
 * the region could be returned at any time by memory_region_find, and this
 * is usually under guest control.
 *
 * @mr: the #MemoryRegion
 */
void memory_region_ref(MemoryRegion *mr);

/**
 * memory_region_unref: Remove 1 to a memory region's reference count
 *
 * Whenever memory regions are accessed outside the BQL, they need to be
 * preserved against hot-unplug.  MemoryRegions actually do not have their
 * own reference count; they piggyback on a QOM object, their "owner".
 * This function removes a reference to the owner and possibly destroys it.
 *
 * @mr: the #MemoryRegion
 */
void memory_region_unref(MemoryRegion *mr);

A
Avi Kivity 已提交
541 542 543
/**
 * memory_region_init_io: Initialize an I/O memory region.
 *
544
 * Accesses into the region will cause the callbacks in @ops to be called.
A
Avi Kivity 已提交
545 546 547
 * if @size is nonzero, subregions will be clipped to @size.
 *
 * @mr: the #MemoryRegion to be initialized.
548
 * @owner: the object that tracks the region's reference count
A
Avi Kivity 已提交
549 550
 * @ops: a structure containing read and write callbacks to be used when
 *       I/O is performed on the region.
551
 * @opaque: passed to the read and write callbacks of the @ops structure.
A
Avi Kivity 已提交
552 553 554 555
 * @name: used for debugging; not visible to the user or ABI
 * @size: size of the region.
 */
void memory_region_init_io(MemoryRegion *mr,
556
                           struct Object *owner,
A
Avi Kivity 已提交
557 558 559 560 561 562
                           const MemoryRegionOps *ops,
                           void *opaque,
                           const char *name,
                           uint64_t size);

/**
563 564 565
 * memory_region_init_ram_nomigrate:  Initialize RAM memory region.  Accesses
 *                                    into the region will modify memory
 *                                    directly.
A
Avi Kivity 已提交
566 567
 *
 * @mr: the #MemoryRegion to be initialized.
568
 * @owner: the object that tracks the region's reference count
569 570
 * @name: Region name, becomes part of RAMBlock name used in migration stream
 *        must be unique within any device
A
Avi Kivity 已提交
571
 * @size: size of the region.
572
 * @errp: pointer to Error*, to store an error if it happens.
573 574 575
 *
 * Note that this function does not do anything to cause the data in the
 * RAM memory region to be migrated; that is the responsibility of the caller.
A
Avi Kivity 已提交
576
 */
577 578 579 580 581
void memory_region_init_ram_nomigrate(MemoryRegion *mr,
                                      struct Object *owner,
                                      const char *name,
                                      uint64_t size,
                                      Error **errp);
A
Avi Kivity 已提交
582

583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605
/**
 * memory_region_init_ram_shared_nomigrate:  Initialize RAM memory region.
 *                                           Accesses into the region will
 *                                           modify memory directly.
 *
 * @mr: the #MemoryRegion to be initialized.
 * @owner: the object that tracks the region's reference count
 * @name: Region name, becomes part of RAMBlock name used in migration stream
 *        must be unique within any device
 * @size: size of the region.
 * @share: allow remapping RAM to different addresses
 * @errp: pointer to Error*, to store an error if it happens.
 *
 * Note that this function is similar to memory_region_init_ram_nomigrate.
 * The only difference is part of the RAM region can be remapped.
 */
void memory_region_init_ram_shared_nomigrate(MemoryRegion *mr,
                                             struct Object *owner,
                                             const char *name,
                                             uint64_t size,
                                             bool share,
                                             Error **errp);

606 607 608 609 610 611 612 613 614
/**
 * memory_region_init_resizeable_ram:  Initialize memory region with resizeable
 *                                     RAM.  Accesses into the region will
 *                                     modify memory directly.  Only an initial
 *                                     portion of this RAM is actually used.
 *                                     The used size can change across reboots.
 *
 * @mr: the #MemoryRegion to be initialized.
 * @owner: the object that tracks the region's reference count
615 616
 * @name: Region name, becomes part of RAMBlock name used in migration stream
 *        must be unique within any device
617 618 619 620
 * @size: used size of the region.
 * @max_size: max size of the region.
 * @resized: callback to notify owner about used size change.
 * @errp: pointer to Error*, to store an error if it happens.
621 622 623
 *
 * Note that this function does not do anything to cause the data in the
 * RAM memory region to be migrated; that is the responsibility of the caller.
624 625 626 627 628 629 630 631 632 633
 */
void memory_region_init_resizeable_ram(MemoryRegion *mr,
                                       struct Object *owner,
                                       const char *name,
                                       uint64_t size,
                                       uint64_t max_size,
                                       void (*resized)(const char*,
                                                       uint64_t length,
                                                       void *host),
                                       Error **errp);
634
#ifdef CONFIG_POSIX
635

636 637 638 639 640 641
/**
 * memory_region_init_ram_from_file:  Initialize RAM memory region with a
 *                                    mmap-ed backend.
 *
 * @mr: the #MemoryRegion to be initialized.
 * @owner: the object that tracks the region's reference count
642 643
 * @name: Region name, becomes part of RAMBlock name used in migration stream
 *        must be unique within any device
644
 * @size: size of the region.
645 646
 * @align: alignment of the region base address; if 0, the default alignment
 *         (getpagesize()) will be used.
647 648
 * @ram_flags: Memory region features:
 *             - RAM_SHARED: memory must be mmaped with the MAP_SHARED flag
J
Junyan He 已提交
649
 *             - RAM_PMEM: the memory is persistent memory
650
 *             Other bits are ignored now.
651
 * @path: the path in which to allocate the RAM.
652
 * @errp: pointer to Error*, to store an error if it happens.
653 654 655
 *
 * Note that this function does not do anything to cause the data in the
 * RAM memory region to be migrated; that is the responsibility of the caller.
656 657 658 659 660
 */
void memory_region_init_ram_from_file(MemoryRegion *mr,
                                      struct Object *owner,
                                      const char *name,
                                      uint64_t size,
661
                                      uint64_t align,
662
                                      uint32_t ram_flags,
663 664
                                      const char *path,
                                      Error **errp);
665 666 667 668 669 670 671 672 673 674 675 676

/**
 * memory_region_init_ram_from_fd:  Initialize RAM memory region with a
 *                                  mmap-ed backend.
 *
 * @mr: the #MemoryRegion to be initialized.
 * @owner: the object that tracks the region's reference count
 * @name: the name of the region.
 * @size: size of the region.
 * @share: %true if memory must be mmaped with the MAP_SHARED flag
 * @fd: the fd to mmap.
 * @errp: pointer to Error*, to store an error if it happens.
677 678 679
 *
 * Note that this function does not do anything to cause the data in the
 * RAM memory region to be migrated; that is the responsibility of the caller.
680 681 682 683 684 685 686 687
 */
void memory_region_init_ram_from_fd(MemoryRegion *mr,
                                    struct Object *owner,
                                    const char *name,
                                    uint64_t size,
                                    bool share,
                                    int fd,
                                    Error **errp);
688 689
#endif

A
Avi Kivity 已提交
690
/**
691 692 693
 * memory_region_init_ram_ptr:  Initialize RAM memory region from a
 *                              user-provided pointer.  Accesses into the
 *                              region will modify memory directly.
A
Avi Kivity 已提交
694 695
 *
 * @mr: the #MemoryRegion to be initialized.
696
 * @owner: the object that tracks the region's reference count
697 698
 * @name: Region name, becomes part of RAMBlock name used in migration stream
 *        must be unique within any device
A
Avi Kivity 已提交
699 700
 * @size: size of the region.
 * @ptr: memory to be mapped; must contain at least @size bytes.
701 702 703
 *
 * Note that this function does not do anything to cause the data in the
 * RAM memory region to be migrated; that is the responsibility of the caller.
A
Avi Kivity 已提交
704 705
 */
void memory_region_init_ram_ptr(MemoryRegion *mr,
706
                                struct Object *owner,
A
Avi Kivity 已提交
707 708 709 710
                                const char *name,
                                uint64_t size,
                                void *ptr);

711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727
/**
 * memory_region_init_ram_device_ptr:  Initialize RAM device memory region from
 *                                     a user-provided pointer.
 *
 * A RAM device represents a mapping to a physical device, such as to a PCI
 * MMIO BAR of an vfio-pci assigned device.  The memory region may be mapped
 * into the VM address space and access to the region will modify memory
 * directly.  However, the memory region should not be included in a memory
 * dump (device may not be enabled/mapped at the time of the dump), and
 * operations incompatible with manipulating MMIO should be avoided.  Replaces
 * skip_dump flag.
 *
 * @mr: the #MemoryRegion to be initialized.
 * @owner: the object that tracks the region's reference count
 * @name: the name of the region.
 * @size: size of the region.
 * @ptr: memory to be mapped; must contain at least @size bytes.
728 729 730 731
 *
 * Note that this function does not do anything to cause the data in the
 * RAM memory region to be migrated; that is the responsibility of the caller.
 * (For RAM device memory regions, migrating the contents rarely makes sense.)
732 733 734 735 736 737 738
 */
void memory_region_init_ram_device_ptr(MemoryRegion *mr,
                                       struct Object *owner,
                                       const char *name,
                                       uint64_t size,
                                       void *ptr);

A
Avi Kivity 已提交
739 740 741 742 743
/**
 * memory_region_init_alias: Initialize a memory region that aliases all or a
 *                           part of another memory region.
 *
 * @mr: the #MemoryRegion to be initialized.
744
 * @owner: the object that tracks the region's reference count
A
Avi Kivity 已提交
745 746 747 748 749 750 751
 * @name: used for debugging; not visible to the user or ABI
 * @orig: the region to be referenced; @mr will be equivalent to
 *        @orig between @offset and @offset + @size - 1.
 * @offset: start of the section in @orig to be referenced.
 * @size: size of the region.
 */
void memory_region_init_alias(MemoryRegion *mr,
752
                              struct Object *owner,
A
Avi Kivity 已提交
753 754
                              const char *name,
                              MemoryRegion *orig,
A
Avi Kivity 已提交
755
                              hwaddr offset,
A
Avi Kivity 已提交
756
                              uint64_t size);
757

758
/**
759
 * memory_region_init_rom_nomigrate: Initialize a ROM memory region.
760
 *
761
 * This has the same effect as calling memory_region_init_ram_nomigrate()
762 763 764
 * and then marking the resulting region read-only with
 * memory_region_set_readonly().
 *
765 766 767 768
 * Note that this function does not do anything to cause the data in the
 * RAM side of the memory region to be migrated; that is the responsibility
 * of the caller.
 *
769 770
 * @mr: the #MemoryRegion to be initialized.
 * @owner: the object that tracks the region's reference count
771 772
 * @name: Region name, becomes part of RAMBlock name used in migration stream
 *        must be unique within any device
773 774 775
 * @size: size of the region.
 * @errp: pointer to Error*, to store an error if it happens.
 */
776 777 778 779 780
void memory_region_init_rom_nomigrate(MemoryRegion *mr,
                                      struct Object *owner,
                                      const char *name,
                                      uint64_t size,
                                      Error **errp);
781

782
/**
783 784 785 786 787 788
 * memory_region_init_rom_device_nomigrate:  Initialize a ROM memory region.
 *                                 Writes are handled via callbacks.
 *
 * Note that this function does not do anything to cause the data in the
 * RAM side of the memory region to be migrated; that is the responsibility
 * of the caller.
789 790
 *
 * @mr: the #MemoryRegion to be initialized.
791
 * @owner: the object that tracks the region's reference count
792
 * @ops: callbacks for write access handling (must not be NULL).
793
 * @opaque: passed to the read and write callbacks of the @ops structure.
794 795
 * @name: Region name, becomes part of RAMBlock name used in migration stream
 *        must be unique within any device
796
 * @size: size of the region.
797
 * @errp: pointer to Error*, to store an error if it happens.
798
 */
799 800 801 802 803 804 805
void memory_region_init_rom_device_nomigrate(MemoryRegion *mr,
                                             struct Object *owner,
                                             const MemoryRegionOps *ops,
                                             void *opaque,
                                             const char *name,
                                             uint64_t size,
                                             Error **errp);
806

A
Avi Kivity 已提交
807
/**
808 809
 * memory_region_init_iommu: Initialize a memory region of a custom type
 * that translates addresses
A
Avi Kivity 已提交
810 811 812 813
 *
 * An IOMMU region translates addresses and forwards accesses to a target
 * memory region.
 *
814 815 816 817 818 819 820 821
 * 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.
 *
822 823
 * @_iommu_mr: the #IOMMUMemoryRegion to be initialized
 * @instance_size: the IOMMUMemoryRegion subclass instance size
824
 * @mrtypename: the type name of the #IOMMUMemoryRegion
825
 * @owner: the object that tracks the region's reference count
A
Avi Kivity 已提交
826 827 828
 * @name: used for debugging; not visible to the user or ABI
 * @size: size of the region.
 */
829 830 831 832
void memory_region_init_iommu(void *_iommu_mr,
                              size_t instance_size,
                              const char *mrtypename,
                              Object *owner,
A
Avi Kivity 已提交
833 834 835
                              const char *name,
                              uint64_t size);

836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923
/**
 * memory_region_init_ram - Initialize RAM memory region.  Accesses into the
 *                          region will modify memory directly.
 *
 * @mr: the #MemoryRegion to be initialized
 * @owner: the object that tracks the region's reference count (must be
 *         TYPE_DEVICE or a subclass of TYPE_DEVICE, or NULL)
 * @name: name of the memory region
 * @size: size of the region in bytes
 * @errp: pointer to Error*, to store an error if it happens.
 *
 * This function allocates RAM for a board model or device, and
 * arranges for it to be migrated (by calling vmstate_register_ram()
 * if @owner is a DeviceState, or vmstate_register_ram_global() if
 * @owner is NULL).
 *
 * TODO: Currently we restrict @owner to being either NULL (for
 * global RAM regions with no owner) or devices, so that we can
 * give the RAM block a unique name for migration purposes.
 * We should lift this restriction and allow arbitrary Objects.
 * If you pass a non-NULL non-device @owner then we will assert.
 */
void memory_region_init_ram(MemoryRegion *mr,
                            struct Object *owner,
                            const char *name,
                            uint64_t size,
                            Error **errp);

/**
 * memory_region_init_rom: Initialize a ROM memory region.
 *
 * This has the same effect as calling memory_region_init_ram()
 * and then marking the resulting region read-only with
 * memory_region_set_readonly(). This includes arranging for the
 * contents to be migrated.
 *
 * TODO: Currently we restrict @owner to being either NULL (for
 * global RAM regions with no owner) or devices, so that we can
 * give the RAM block a unique name for migration purposes.
 * We should lift this restriction and allow arbitrary Objects.
 * If you pass a non-NULL non-device @owner then we will assert.
 *
 * @mr: the #MemoryRegion to be initialized.
 * @owner: the object that tracks the region's reference count
 * @name: Region name, becomes part of RAMBlock name used in migration stream
 *        must be unique within any device
 * @size: size of the region.
 * @errp: pointer to Error*, to store an error if it happens.
 */
void memory_region_init_rom(MemoryRegion *mr,
                            struct Object *owner,
                            const char *name,
                            uint64_t size,
                            Error **errp);

/**
 * memory_region_init_rom_device:  Initialize a ROM memory region.
 *                                 Writes are handled via callbacks.
 *
 * This function initializes a memory region backed by RAM for reads
 * and callbacks for writes, and arranges for the RAM backing to
 * be migrated (by calling vmstate_register_ram()
 * if @owner is a DeviceState, or vmstate_register_ram_global() if
 * @owner is NULL).
 *
 * TODO: Currently we restrict @owner to being either NULL (for
 * global RAM regions with no owner) or devices, so that we can
 * give the RAM block a unique name for migration purposes.
 * We should lift this restriction and allow arbitrary Objects.
 * If you pass a non-NULL non-device @owner then we will assert.
 *
 * @mr: the #MemoryRegion to be initialized.
 * @owner: the object that tracks the region's reference count
 * @ops: callbacks for write access handling (must not be NULL).
 * @name: Region name, becomes part of RAMBlock name used in migration stream
 *        must be unique within any device
 * @size: size of the region.
 * @errp: pointer to Error*, to store an error if it happens.
 */
void memory_region_init_rom_device(MemoryRegion *mr,
                                   struct Object *owner,
                                   const MemoryRegionOps *ops,
                                   void *opaque,
                                   const char *name,
                                   uint64_t size,
                                   Error **errp);


P
Paolo Bonzini 已提交
924 925 926 927 928 929 930
/**
 * memory_region_owner: get a memory region's owner.
 *
 * @mr: the memory region being queried.
 */
struct Object *memory_region_owner(MemoryRegion *mr);

A
Avi Kivity 已提交
931 932 933 934 935 936 937
/**
 * memory_region_size: get a memory region's size.
 *
 * @mr: the memory region being queried.
 */
uint64_t memory_region_size(MemoryRegion *mr);

A
Avi Kivity 已提交
938 939 940
/**
 * memory_region_is_ram: check whether a memory region is random access
 *
L
Li Qiang 已提交
941
 * Returns %true if a memory region is random access.
A
Avi Kivity 已提交
942 943 944
 *
 * @mr: the memory region being queried
 */
945 946 947 948
static inline bool memory_region_is_ram(MemoryRegion *mr)
{
    return mr->ram;
}
A
Avi Kivity 已提交
949

950
/**
951
 * memory_region_is_ram_device: check whether a memory region is a ram device
952
 *
L
Li Qiang 已提交
953
 * Returns %true if a memory region is a device backed ram region
954 955 956
 *
 * @mr: the memory region being queried
 */
957
bool memory_region_is_ram_device(MemoryRegion *mr);
958

959
/**
960
 * memory_region_is_romd: check whether a memory region is in ROMD mode
961
 *
962
 * Returns %true if a memory region is a ROM device and currently set to allow
963 964 965 966 967 968
 * direct reads.
 *
 * @mr: the memory region being queried
 */
static inline bool memory_region_is_romd(MemoryRegion *mr)
{
969
    return mr->rom_device && mr->romd_mode;
970 971
}

A
Avi Kivity 已提交
972
/**
973
 * memory_region_get_iommu: check whether a memory region is an iommu
A
Avi Kivity 已提交
974
 *
975 976
 * Returns pointer to IOMMUMemoryRegion if a memory region is an iommu,
 * otherwise NULL.
A
Avi Kivity 已提交
977 978 979
 *
 * @mr: the memory region being queried
 */
980
static inline IOMMUMemoryRegion *memory_region_get_iommu(MemoryRegion *mr)
981
{
982
    if (mr->alias) {
983 984 985 986
        return memory_region_get_iommu(mr->alias);
    }
    if (mr->is_iommu) {
        return (IOMMUMemoryRegion *) mr;
987
    }
988
    return NULL;
989 990
}

991 992 993 994
/**
 * memory_region_get_iommu_class_nocheck: returns iommu memory region class
 *   if an iommu or NULL if not
 *
995 996
 * Returns pointer to IOMMUMemoryRegionClass if a memory region is an iommu,
 * otherwise NULL. This is fast path avoiding QOM checking, use with caution.
997 998 999 1000 1001 1002 1003 1004 1005
 *
 * @mr: the memory region being queried
 */
static inline IOMMUMemoryRegionClass *memory_region_get_iommu_class_nocheck(
        IOMMUMemoryRegion *iommu_mr)
{
    return (IOMMUMemoryRegionClass *) (((Object *)iommu_mr)->class);
}

1006
#define memory_region_is_iommu(mr) (memory_region_get_iommu(mr) != NULL)
A
Avi Kivity 已提交
1007

1008 1009 1010 1011 1012 1013
/**
 * memory_region_iommu_get_min_page_size: get minimum supported page size
 * for an iommu
 *
 * Returns minimum supported page size for an iommu.
 *
1014
 * @iommu_mr: the memory region being queried
1015
 */
1016
uint64_t memory_region_iommu_get_min_page_size(IOMMUMemoryRegion *iommu_mr);
1017

1018 1019 1020
/**
 * memory_region_notify_iommu: notify a change in an IOMMU translation entry.
 *
1021 1022 1023 1024 1025 1026 1027 1028 1029
 * The notification type will be decided by entry.perm bits:
 *
 * - For UNMAP (cache invalidation) notifies: set entry.perm to IOMMU_NONE.
 * - For MAP (newly added entry) notifies: set entry.perm to the
 *   permission of the page (which is definitely !IOMMU_NONE).
 *
 * Note: for any IOMMU implementation, an in-place mapping change
 * should be notified with an UNMAP followed by a MAP.
 *
1030
 * @iommu_mr: the memory region that was changed
1031
 * @iommu_idx: the IOMMU index for the translation table which has changed
1032 1033 1034 1035
 * @entry: the new entry in the IOMMU translation table.  The entry
 *         replaces all old entries for the same virtual I/O address range.
 *         Deleted entries have .@perm == 0.
 */
1036
void memory_region_notify_iommu(IOMMUMemoryRegion *iommu_mr,
1037
                                int iommu_idx,
1038 1039
                                IOMMUTLBEntry entry);

1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054
/**
 * memory_region_notify_one: notify a change in an IOMMU translation
 *                           entry to a single notifier
 *
 * This works just like memory_region_notify_iommu(), but it only
 * notifies a specific notifier, not all of them.
 *
 * @notifier: the notifier to be notified
 * @entry: the new entry in the IOMMU translation table.  The entry
 *         replaces all old entries for the same virtual I/O address range.
 *         Deleted entries have .@perm == 0.
 */
void memory_region_notify_one(IOMMUNotifier *notifier,
                              IOMMUTLBEntry *entry);

1055 1056 1057 1058 1059
/**
 * memory_region_register_iommu_notifier: register a notifier for changes to
 * IOMMU translation entries.
 *
 * @mr: the memory region to observe
1060 1061 1062
 * @n: the IOMMUNotifier to be added; the notify callback receives a
 *     pointer to an #IOMMUTLBEntry as the opaque value; the pointer
 *     ceases to be valid on exit from the notifier.
1063
 */
1064 1065
void memory_region_register_iommu_notifier(MemoryRegion *mr,
                                           IOMMUNotifier *n);
1066

1067 1068
/**
 * memory_region_iommu_replay: replay existing IOMMU translations to
1069 1070
 * a notifier with the minimum page granularity returned by
 * mr->iommu_ops->get_page_size().
1071
 *
1072 1073
 * Note: this is not related to record-and-replay functionality.
 *
1074
 * @iommu_mr: the memory region to observe
1075 1076
 * @n: the notifier to which to replay iommu mappings
 */
1077
void memory_region_iommu_replay(IOMMUMemoryRegion *iommu_mr, IOMMUNotifier *n);
1078

P
Peter Xu 已提交
1079 1080 1081 1082
/**
 * memory_region_iommu_replay_all: replay existing IOMMU translations
 * to all the notifiers registered.
 *
1083 1084
 * Note: this is not related to record-and-replay functionality.
 *
1085
 * @iommu_mr: the memory region to observe
P
Peter Xu 已提交
1086
 */
1087
void memory_region_iommu_replay_all(IOMMUMemoryRegion *iommu_mr);
P
Peter Xu 已提交
1088

1089 1090 1091 1092
/**
 * memory_region_unregister_iommu_notifier: unregister a notifier for
 * changes to IOMMU translation entries.
 *
1093 1094
 * @mr: the memory region which was observed and for which notity_stopped()
 *      needs to be called
1095 1096
 * @n: the notifier to be removed.
 */
1097 1098
void memory_region_unregister_iommu_notifier(MemoryRegion *mr,
                                             IOMMUNotifier *n);
1099

1100 1101 1102 1103
/**
 * memory_region_iommu_get_attr: return an IOMMU attr if get_attr() is
 * defined on the IOMMU.
 *
1104 1105 1106
 * Returns 0 on success, or a negative errno otherwise. In particular,
 * -EINVAL indicates that the IOMMU does not support the requested
 * attribute.
1107 1108 1109 1110 1111 1112 1113 1114 1115
 *
 * @iommu_mr: the memory region
 * @attr: the requested attribute
 * @data: a pointer to the requested attribute data
 */
int memory_region_iommu_get_attr(IOMMUMemoryRegion *iommu_mr,
                                 enum IOMMUMemoryRegionAttr attr,
                                 void *data);

1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133
/**
 * memory_region_iommu_attrs_to_index: return the IOMMU index to
 * use for translations with the given memory transaction attributes.
 *
 * @iommu_mr: the memory region
 * @attrs: the memory transaction attributes
 */
int memory_region_iommu_attrs_to_index(IOMMUMemoryRegion *iommu_mr,
                                       MemTxAttrs attrs);

/**
 * memory_region_iommu_num_indexes: return the total number of IOMMU
 * indexes that this IOMMU supports.
 *
 * @iommu_mr: the memory region
 */
int memory_region_iommu_num_indexes(IOMMUMemoryRegion *iommu_mr);

1134 1135 1136 1137 1138 1139 1140
/**
 * memory_region_name: get a memory region's name
 *
 * Returns the string that was used to initialize the memory region.
 *
 * @mr: the memory region being queried
 */
1141
const char *memory_region_name(const MemoryRegion *mr);
1142

1143 1144 1145
/**
 * memory_region_is_logging: return whether a memory region is logging writes
 *
1146
 * Returns %true if the memory region is logging writes for the given client
1147 1148
 *
 * @mr: the memory region being queried
1149
 * @client: the client being queried
1150
 */
1151 1152 1153 1154 1155 1156
bool memory_region_is_logging(MemoryRegion *mr, uint8_t client);

/**
 * memory_region_get_dirty_log_mask: return the clients for which a
 * memory region is logging writes.
 *
1157 1158
 * Returns a bitmap of clients, in which the DIRTY_MEMORY_* constants
 * are the bit indices.
1159 1160 1161 1162
 *
 * @mr: the memory region being queried
 */
uint8_t memory_region_get_dirty_log_mask(MemoryRegion *mr);
1163

A
Avi Kivity 已提交
1164 1165 1166
/**
 * memory_region_is_rom: check whether a memory region is ROM
 *
L
Li Qiang 已提交
1167
 * Returns %true if a memory region is read-only memory.
A
Avi Kivity 已提交
1168 1169 1170
 *
 * @mr: the memory region being queried
 */
1171 1172 1173 1174 1175
static inline bool memory_region_is_rom(MemoryRegion *mr)
{
    return mr->ram && mr->readonly;
}

1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186
/**
 * memory_region_is_nonvolatile: check whether a memory region is non-volatile
 *
 * Returns %true is a memory region is non-volatile memory.
 *
 * @mr: the memory region being queried
 */
static inline bool memory_region_is_nonvolatile(MemoryRegion *mr)
{
    return mr->nonvolatile;
}
A
Avi Kivity 已提交
1187

1188 1189 1190 1191 1192 1193 1194 1195 1196 1197
/**
 * memory_region_get_fd: Get a file descriptor backing a RAM memory region.
 *
 * Returns a file descriptor backing a file-based RAM memory region,
 * or -1 if the region is not a file-based RAM memory region.
 *
 * @mr: the RAM or alias memory region being queried.
 */
int memory_region_get_fd(MemoryRegion *mr);

1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211
/**
 * memory_region_from_host: Convert a pointer into a RAM memory region
 * and an offset within it.
 *
 * Given a host pointer inside a RAM memory region (created with
 * memory_region_init_ram() or memory_region_init_ram_ptr()), return
 * the MemoryRegion and the offset within it.
 *
 * Use with care; by the time this function returns, the returned pointer is
 * not protected by RCU anymore.  If the caller is not within an RCU critical
 * section and does not hold the iothread lock, it must have other means of
 * protecting the pointer, such as a reference to the region that includes
 * the incoming ram_addr_t.
 *
1212 1213
 * @ptr: the host pointer to be converted
 * @offset: the offset within memory region
1214 1215 1216
 */
MemoryRegion *memory_region_from_host(void *ptr, ram_addr_t *offset);

A
Avi Kivity 已提交
1217 1218 1219 1220
/**
 * memory_region_get_ram_ptr: Get a pointer into a RAM memory region.
 *
 * Returns a host pointer to a RAM memory region (created with
1221 1222 1223 1224 1225 1226 1227
 * memory_region_init_ram() or memory_region_init_ram_ptr()).
 *
 * Use with care; by the time this function returns, the returned pointer is
 * not protected by RCU anymore.  If the caller is not within an RCU critical
 * section and does not hold the iothread lock, it must have other means of
 * protecting the pointer, such as a reference to the region that includes
 * the incoming ram_addr_t.
A
Avi Kivity 已提交
1228 1229 1230 1231 1232
 *
 * @mr: the memory region being queried.
 */
void *memory_region_get_ram_ptr(MemoryRegion *mr);

1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244
/* memory_region_ram_resize: Resize a RAM region.
 *
 * Only legal before guest might have detected the memory size: e.g. on
 * incoming migration, or right after reset.
 *
 * @mr: a memory region created with @memory_region_init_resizeable_ram.
 * @newsize: the new size the region
 * @errp: pointer to Error*, to store an error if it happens.
 */
void memory_region_ram_resize(MemoryRegion *mr, ram_addr_t newsize,
                              Error **errp);

A
Avi Kivity 已提交
1245 1246 1247 1248 1249 1250 1251 1252
/**
 * memory_region_set_log: Turn dirty logging on or off for a region.
 *
 * Turns dirty logging on or off for a specified client (display, migration).
 * Only meaningful for RAM regions.
 *
 * @mr: the memory region being updated.
 * @log: whether dirty logging is to be enabled or disabled.
1253
 * @client: the user of the logging information; %DIRTY_MEMORY_VGA only.
A
Avi Kivity 已提交
1254 1255 1256 1257
 */
void memory_region_set_log(MemoryRegion *mr, bool log, unsigned client);

/**
1258 1259
 * memory_region_get_dirty: Check whether a range of bytes is dirty
 *                          for a specified client.
A
Avi Kivity 已提交
1260
 *
1261
 * Checks whether a range of bytes has been written to since the last
A
Avi Kivity 已提交
1262 1263 1264 1265 1266
 * call to memory_region_reset_dirty() with the same @client.  Dirty logging
 * must be enabled.
 *
 * @mr: the memory region being queried.
 * @addr: the address (relative to the start of the region) being queried.
1267
 * @size: the size of the range being queried.
A
Avi Kivity 已提交
1268 1269 1270
 * @client: the user of the logging information; %DIRTY_MEMORY_MIGRATION or
 *          %DIRTY_MEMORY_VGA.
 */
A
Avi Kivity 已提交
1271 1272
bool memory_region_get_dirty(MemoryRegion *mr, hwaddr addr,
                             hwaddr size, unsigned client);
A
Avi Kivity 已提交
1273 1274

/**
1275
 * memory_region_set_dirty: Mark a range of bytes as dirty in a memory region.
A
Avi Kivity 已提交
1276
 *
1277 1278
 * Marks a range of bytes as dirty, after it has been dirtied outside
 * guest code.
A
Avi Kivity 已提交
1279
 *
1280
 * @mr: the memory region being dirtied.
A
Avi Kivity 已提交
1281
 * @addr: the address (relative to the start of the region) being dirtied.
1282
 * @size: size of the range being dirtied.
A
Avi Kivity 已提交
1283
 */
A
Avi Kivity 已提交
1284 1285
void memory_region_set_dirty(MemoryRegion *mr, hwaddr addr,
                             hwaddr size);
A
Avi Kivity 已提交
1286

1287 1288 1289 1290 1291 1292
/**
 * memory_region_snapshot_and_clear_dirty: Get a snapshot of the dirty
 *                                         bitmap and clear it.
 *
 * Creates a snapshot of the dirty bitmap, clears the dirty bitmap and
 * returns the snapshot.  The snapshot can then be used to query dirty
1293 1294 1295
 * status, using memory_region_snapshot_get_dirty.  Snapshotting allows
 * querying the same page multiple times, which is especially useful for
 * display updates where the scanlines often are not page aligned.
1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331
 *
 * The dirty bitmap region which gets copyed into the snapshot (and
 * cleared afterwards) can be larger than requested.  The boundaries
 * are rounded up/down so complete bitmap longs (covering 64 pages on
 * 64bit hosts) can be copied over into the bitmap snapshot.  Which
 * isn't a problem for display updates as the extra pages are outside
 * the visible area, and in case the visible area changes a full
 * display redraw is due anyway.  Should other use cases for this
 * function emerge we might have to revisit this implementation
 * detail.
 *
 * Use g_free to release DirtyBitmapSnapshot.
 *
 * @mr: the memory region being queried.
 * @addr: the address (relative to the start of the region) being queried.
 * @size: the size of the range being queried.
 * @client: the user of the logging information; typically %DIRTY_MEMORY_VGA.
 */
DirtyBitmapSnapshot *memory_region_snapshot_and_clear_dirty(MemoryRegion *mr,
                                                            hwaddr addr,
                                                            hwaddr size,
                                                            unsigned client);

/**
 * memory_region_snapshot_get_dirty: Check whether a range of bytes is dirty
 *                                   in the specified dirty bitmap snapshot.
 *
 * @mr: the memory region being queried.
 * @snap: the dirty bitmap snapshot
 * @addr: the address (relative to the start of the region) being queried.
 * @size: the size of the range being queried.
 */
bool memory_region_snapshot_get_dirty(MemoryRegion *mr,
                                      DirtyBitmapSnapshot *snap,
                                      hwaddr addr, hwaddr size);

A
Avi Kivity 已提交
1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343
/**
 * memory_region_reset_dirty: Mark a range of pages as clean, for a specified
 *                            client.
 *
 * Marks a range of pages as no longer dirty.
 *
 * @mr: the region being updated.
 * @addr: the start of the subrange being cleaned.
 * @size: the size of the subrange being cleaned.
 * @client: the user of the logging information; %DIRTY_MEMORY_MIGRATION or
 *          %DIRTY_MEMORY_VGA.
 */
A
Avi Kivity 已提交
1344 1345
void memory_region_reset_dirty(MemoryRegion *mr, hwaddr addr,
                               hwaddr size, unsigned client);
A
Avi Kivity 已提交
1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357

/**
 * memory_region_set_readonly: Turn a memory region read-only (or read-write)
 *
 * Allows a memory region to be marked as read-only (turning it into a ROM).
 * only useful on RAM regions.
 *
 * @mr: the region being updated.
 * @readonly: whether rhe region is to be ROM or RAM.
 */
void memory_region_set_readonly(MemoryRegion *mr, bool readonly);

1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368
/**
 * memory_region_set_nonvolatile: Turn a memory region non-volatile
 *
 * Allows a memory region to be marked as non-volatile.
 * only useful on RAM regions.
 *
 * @mr: the region being updated.
 * @nonvolatile: whether rhe region is to be non-volatile.
 */
void memory_region_set_nonvolatile(MemoryRegion *mr, bool nonvolatile);

1369
/**
1370
 * memory_region_rom_device_set_romd: enable/disable ROMD mode
1371 1372
 *
 * Allows a ROM device (initialized with memory_region_init_rom_device() to
1373 1374 1375 1376
 * set to ROMD mode (default) or MMIO mode.  When it is in ROMD mode, the
 * device is mapped to guest memory and satisfies read access directly.
 * When in MMIO mode, reads are forwarded to the #MemoryRegion.read function.
 * Writes are always handled by the #MemoryRegion.write function.
1377 1378
 *
 * @mr: the memory region to be updated
1379
 * @romd_mode: %true to put the region into ROMD mode
1380
 */
1381
void memory_region_rom_device_set_romd(MemoryRegion *mr, bool romd_mode);
1382

A
Avi Kivity 已提交
1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405
/**
 * memory_region_set_coalescing: Enable memory coalescing for the region.
 *
 * Enabled writes to a region to be queued for later processing. MMIO ->write
 * callbacks may be delayed until a non-coalesced MMIO is issued.
 * Only useful for IO regions.  Roughly similar to write-combining hardware.
 *
 * @mr: the memory region to be write coalesced
 */
void memory_region_set_coalescing(MemoryRegion *mr);

/**
 * memory_region_add_coalescing: Enable memory coalescing for a sub-range of
 *                               a region.
 *
 * Like memory_region_set_coalescing(), but works on a sub-range of a region.
 * Multiple calls can be issued coalesced disjoint ranges.
 *
 * @mr: the memory region to be updated.
 * @offset: the start of the range within the region to be coalesced.
 * @size: the size of the subrange to be coalesced.
 */
void memory_region_add_coalescing(MemoryRegion *mr,
A
Avi Kivity 已提交
1406
                                  hwaddr offset,
A
Avi Kivity 已提交
1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419
                                  uint64_t size);

/**
 * memory_region_clear_coalescing: Disable MMIO coalescing for the region.
 *
 * Disables any coalescing caused by memory_region_set_coalescing() or
 * memory_region_add_coalescing().  Roughly equivalent to uncacheble memory
 * hardware.
 *
 * @mr: the memory region to be updated.
 */
void memory_region_clear_coalescing(MemoryRegion *mr);

1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444
/**
 * memory_region_set_flush_coalesced: Enforce memory coalescing flush before
 *                                    accesses.
 *
 * Ensure that pending coalesced MMIO request are flushed before the memory
 * region is accessed. This property is automatically enabled for all regions
 * passed to memory_region_set_coalescing() and memory_region_add_coalescing().
 *
 * @mr: the memory region to be updated.
 */
void memory_region_set_flush_coalesced(MemoryRegion *mr);

/**
 * memory_region_clear_flush_coalesced: Disable memory coalescing flush before
 *                                      accesses.
 *
 * Clear the automatic coalesced MMIO flushing enabled via
 * memory_region_set_flush_coalesced. Note that this service has no effect on
 * memory regions that have MMIO coalescing enabled for themselves. For them,
 * automatic flushing will stop once coalescing is disabled.
 *
 * @mr: the memory region to be updated.
 */
void memory_region_clear_flush_coalesced(MemoryRegion *mr);

1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457
/**
 * memory_region_clear_global_locking: Declares that access processing does
 *                                     not depend on the QEMU global lock.
 *
 * By clearing this property, accesses to the memory region will be processed
 * outside of QEMU's global lock (unless the lock is held on when issuing the
 * access request). In this case, the device model implementing the access
 * handlers is responsible for synchronization of concurrency.
 *
 * @mr: the memory region to be updated.
 */
void memory_region_clear_global_locking(MemoryRegion *mr);

A
Avi Kivity 已提交
1458 1459 1460 1461 1462 1463
/**
 * memory_region_add_eventfd: Request an eventfd to be triggered when a word
 *                            is written to a location.
 *
 * Marks a word in an IO region (initialized with memory_region_init_io())
 * as a trigger for an eventfd event.  The I/O callback will not be called.
1464
 * The caller must be prepared to handle failure (that is, take the required
A
Avi Kivity 已提交
1465 1466 1467 1468 1469 1470 1471
 * action if the callback _is_ called).
 *
 * @mr: the memory region being updated.
 * @addr: the address within @mr that is to be monitored
 * @size: the size of the access to trigger the eventfd
 * @match_data: whether to match against @data, instead of just @addr
 * @data: the data to match against the guest write
1472
 * @e: event notifier to be triggered when @addr, @size, and @data all match.
A
Avi Kivity 已提交
1473 1474
 **/
void memory_region_add_eventfd(MemoryRegion *mr,
A
Avi Kivity 已提交
1475
                               hwaddr addr,
A
Avi Kivity 已提交
1476 1477 1478
                               unsigned size,
                               bool match_data,
                               uint64_t data,
1479
                               EventNotifier *e);
A
Avi Kivity 已提交
1480 1481

/**
1482
 * memory_region_del_eventfd: Cancel an eventfd.
A
Avi Kivity 已提交
1483
 *
1484 1485
 * Cancels an eventfd trigger requested by a previous
 * memory_region_add_eventfd() call.
A
Avi Kivity 已提交
1486 1487 1488 1489 1490 1491
 *
 * @mr: the memory region being updated.
 * @addr: the address within @mr that is to be monitored
 * @size: the size of the access to trigger the eventfd
 * @match_data: whether to match against @data, instead of just @addr
 * @data: the data to match against the guest write
1492
 * @e: event notifier to be triggered when @addr, @size, and @data all match.
A
Avi Kivity 已提交
1493 1494
 */
void memory_region_del_eventfd(MemoryRegion *mr,
A
Avi Kivity 已提交
1495
                               hwaddr addr,
A
Avi Kivity 已提交
1496 1497 1498
                               unsigned size,
                               bool match_data,
                               uint64_t data,
1499 1500
                               EventNotifier *e);

A
Avi Kivity 已提交
1501
/**
1502
 * memory_region_add_subregion: Add a subregion to a container.
A
Avi Kivity 已提交
1503
 *
1504
 * Adds a subregion at @offset.  The subregion may not overlap with other
A
Avi Kivity 已提交
1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515
 * subregions (except for those explicitly marked as overlapping).  A region
 * may only be added once as a subregion (unless removed with
 * memory_region_del_subregion()); use memory_region_init_alias() if you
 * want a region to be a subregion in multiple locations.
 *
 * @mr: the region to contain the new subregion; must be a container
 *      initialized with memory_region_init().
 * @offset: the offset relative to @mr where @subregion is added.
 * @subregion: the subregion to be added.
 */
void memory_region_add_subregion(MemoryRegion *mr,
A
Avi Kivity 已提交
1516
                                 hwaddr offset,
A
Avi Kivity 已提交
1517 1518
                                 MemoryRegion *subregion);
/**
1519 1520
 * memory_region_add_subregion_overlap: Add a subregion to a container
 *                                      with overlap.
A
Avi Kivity 已提交
1521
 *
1522
 * Adds a subregion at @offset.  The subregion may overlap with other
A
Avi Kivity 已提交
1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535
 * subregions.  Conflicts are resolved by having a higher @priority hide a
 * lower @priority. Subregions without priority are taken as @priority 0.
 * A region may only be added once as a subregion (unless removed with
 * memory_region_del_subregion()); use memory_region_init_alias() if you
 * want a region to be a subregion in multiple locations.
 *
 * @mr: the region to contain the new subregion; must be a container
 *      initialized with memory_region_init().
 * @offset: the offset relative to @mr where @subregion is added.
 * @subregion: the subregion to be added.
 * @priority: used for resolving overlaps; highest priority wins.
 */
void memory_region_add_subregion_overlap(MemoryRegion *mr,
A
Avi Kivity 已提交
1536
                                         hwaddr offset,
A
Avi Kivity 已提交
1537
                                         MemoryRegion *subregion,
1538
                                         int priority);
1539 1540 1541 1542 1543

/**
 * memory_region_get_ram_addr: Get the ram address associated with a memory
 *                             region
 */
1544
ram_addr_t memory_region_get_ram_addr(MemoryRegion *mr);
1545

1546
uint64_t memory_region_get_alignment(const MemoryRegion *mr);
A
Avi Kivity 已提交
1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557
/**
 * memory_region_del_subregion: Remove a subregion.
 *
 * Removes a subregion from its container.
 *
 * @mr: the container to be updated.
 * @subregion: the region being removed; must be a current subregion of @mr.
 */
void memory_region_del_subregion(MemoryRegion *mr,
                                 MemoryRegion *subregion);

1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572
/*
 * memory_region_set_enabled: dynamically enable or disable a region
 *
 * Enables or disables a memory region.  A disabled memory region
 * ignores all accesses to itself and its subregions.  It does not
 * obscure sibling subregions with lower priority - it simply behaves as
 * if it was removed from the hierarchy.
 *
 * Regions default to being enabled.
 *
 * @mr: the region to be updated
 * @enabled: whether to enable or disable the region
 */
void memory_region_set_enabled(MemoryRegion *mr, bool enabled);

1573 1574 1575
/*
 * memory_region_set_address: dynamically update the address of a region
 *
1576
 * Dynamically updates the address of a region, relative to its container.
1577 1578 1579
 * May be used on regions are currently part of a memory hierarchy.
 *
 * @mr: the region to be updated
1580
 * @addr: new address, relative to container region
1581
 */
A
Avi Kivity 已提交
1582
void memory_region_set_address(MemoryRegion *mr, hwaddr addr);
1583

1584 1585 1586 1587 1588 1589 1590 1591 1592 1593
/*
 * memory_region_set_size: dynamically update the size of a region.
 *
 * Dynamically updates the size of a region.
 *
 * @mr: the region to be updated
 * @size: used size of the region.
 */
void memory_region_set_size(MemoryRegion *mr, uint64_t size);

1594 1595 1596 1597 1598 1599 1600 1601 1602 1603
/*
 * memory_region_set_alias_offset: dynamically update a memory alias's offset
 *
 * Dynamically updates the offset into the target region that an alias points
 * to, as if the fourth argument to memory_region_init_alias() has changed.
 *
 * @mr: the #MemoryRegion to be updated; should be an alias.
 * @offset: the new offset into the target memory region
 */
void memory_region_set_alias_offset(MemoryRegion *mr,
A
Avi Kivity 已提交
1604
                                    hwaddr offset);
1605

1606
/**
1607 1608
 * memory_region_present: checks if an address relative to a @container
 * translates into #MemoryRegion within @container
1609
 *
1610
 * Answer whether a #MemoryRegion within @container covers the address
1611 1612
 * @addr.
 *
1613 1614
 * @container: a #MemoryRegion within which @addr is a relative address
 * @addr: the area within @container to be searched
1615
 */
1616
bool memory_region_present(MemoryRegion *container, hwaddr addr);
1617

1618 1619 1620 1621 1622 1623 1624 1625
/**
 * memory_region_is_mapped: returns true if #MemoryRegion is mapped
 * into any address space.
 *
 * @mr: a #MemoryRegion which should be checked if it's mapped
 */
bool memory_region_is_mapped(MemoryRegion *mr);

1626
/**
1627 1628
 * memory_region_find: translate an address/size relative to a
 * MemoryRegion into a #MemoryRegionSection.
1629
 *
1630 1631
 * Locates the first #MemoryRegion within @mr that overlaps the range
 * given by @addr and @size.
1632 1633 1634 1635 1636 1637
 *
 * Returns a #MemoryRegionSection that describes a contiguous overlap.
 * It will have the following characteristics:
 *    .@size = 0 iff no overlap was found
 *    .@mr is non-%NULL iff an overlap was found
 *
1638 1639 1640 1641 1642 1643 1644
 * Remember that in the return value the @offset_within_region is
 * relative to the returned region (in the .@mr field), not to the
 * @mr argument.
 *
 * Similarly, the .@offset_within_address_space is relative to the
 * address space that contains both regions, the passed and the
 * returned one.  However, in the special case where the @mr argument
1645
 * has no container (and thus is the root of the address space), the
1646 1647 1648 1649 1650 1651
 * following will hold:
 *    .@offset_within_address_space >= @addr
 *    .@offset_within_address_space + .@size <= @addr + @size
 *
 * @mr: a MemoryRegion within which @addr is a relative address
 * @addr: start of the area within @as to be searched
1652 1653
 * @size: size of the area to be searched
 */
1654
MemoryRegionSection memory_region_find(MemoryRegion *mr,
A
Avi Kivity 已提交
1655
                                       hwaddr addr, uint64_t size);
1656

1657
/**
1658
 * memory_global_dirty_log_sync: synchronize the dirty log for all memory
1659
 *
1660
 * Synchronizes the dirty page log for all address spaces.
1661
 */
1662
void memory_global_dirty_log_sync(void);
1663

1664 1665 1666 1667
/**
 * memory_region_transaction_begin: Start a transaction.
 *
 * During a transaction, changes will be accumulated and made visible
1668
 * only when the transaction ends (is committed).
A
Avi Kivity 已提交
1669 1670
 */
void memory_region_transaction_begin(void);
1671 1672 1673 1674

/**
 * memory_region_transaction_commit: Commit a transaction and make changes
 *                                   visible to the guest.
A
Avi Kivity 已提交
1675 1676 1677
 */
void memory_region_transaction_commit(void);

1678 1679 1680 1681 1682 1683
/**
 * memory_listener_register: register callbacks to be called when memory
 *                           sections are mapped or unmapped into an address
 *                           space
 *
 * @listener: an object containing the callbacks to be called
1684
 * @filter: if non-%NULL, only regions in this address space will be observed
1685
 */
1686
void memory_listener_register(MemoryListener *listener, AddressSpace *filter);
1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700

/**
 * memory_listener_unregister: undo the effect of memory_listener_register()
 *
 * @listener: an object containing the callbacks to be removed
 */
void memory_listener_unregister(MemoryListener *listener);

/**
 * memory_global_dirty_log_start: begin dirty logging for all regions
 */
void memory_global_dirty_log_start(void);

/**
1701
 * memory_global_dirty_log_stop: end dirty logging for all regions
1702 1703 1704
 */
void memory_global_dirty_log_stop(void);

1705
void mtree_info(fprintf_function mon_printf, void *f, bool flatview,
1706
                bool dispatch_tree, bool owner);
B
Blue Swirl 已提交
1707

1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738
/**
 * memory_region_dispatch_read: perform a read directly to the specified
 * MemoryRegion.
 *
 * @mr: #MemoryRegion to access
 * @addr: address within that region
 * @pval: pointer to uint64_t which the data is written to
 * @size: size of the access in bytes
 * @attrs: memory transaction attributes to use for the access
 */
MemTxResult memory_region_dispatch_read(MemoryRegion *mr,
                                        hwaddr addr,
                                        uint64_t *pval,
                                        unsigned size,
                                        MemTxAttrs attrs);
/**
 * memory_region_dispatch_write: perform a write directly to the specified
 * MemoryRegion.
 *
 * @mr: #MemoryRegion to access
 * @addr: address within that region
 * @data: data to write
 * @size: size of the access in bytes
 * @attrs: memory transaction attributes to use for the access
 */
MemTxResult memory_region_dispatch_write(MemoryRegion *mr,
                                         hwaddr addr,
                                         uint64_t data,
                                         unsigned size,
                                         MemTxAttrs attrs);

A
Avi Kivity 已提交
1739 1740 1741 1742
/**
 * address_space_init: initializes an address space
 *
 * @as: an uninitialized #AddressSpace
V
Veres Lajos 已提交
1743
 * @root: a #MemoryRegion that routes addresses for the address space
1744 1745
 * @name: an address space name.  The name is only used for debugging
 *        output.
A
Avi Kivity 已提交
1746
 */
1747
void address_space_init(AddressSpace *as, MemoryRegion *root, const char *name);
A
Avi Kivity 已提交
1748

A
Avi Kivity 已提交
1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759
/**
 * address_space_destroy: destroy an address space
 *
 * Releases all resources associated with an address space.  After an address space
 * is destroyed, its root memory region (given by address_space_init()) may be destroyed
 * as well.
 *
 * @as: address space to be destroyed
 */
void address_space_destroy(AddressSpace *as);

A
Avi Kivity 已提交
1760 1761 1762
/**
 * address_space_rw: read from or write to an address space.
 *
1763 1764 1765
 * Return a MemTxResult indicating whether the operation succeeded
 * or failed (eg unassigned memory, device rejected the transaction,
 * IOMMU fault).
1766
 *
A
Avi Kivity 已提交
1767 1768
 * @as: #AddressSpace to be accessed
 * @addr: address within that address space
1769
 * @attrs: memory transaction attributes
A
Avi Kivity 已提交
1770
 * @buf: buffer with the data transferred
1771
 * @len: the number of bytes to read or write
A
Avi Kivity 已提交
1772 1773
 * @is_write: indicates the transfer direction
 */
1774 1775 1776
MemTxResult address_space_rw(AddressSpace *as, hwaddr addr,
                             MemTxAttrs attrs, uint8_t *buf,
                             int len, bool is_write);
A
Avi Kivity 已提交
1777 1778 1779 1780

/**
 * address_space_write: write to address space.
 *
1781 1782 1783
 * Return a MemTxResult indicating whether the operation succeeded
 * or failed (eg unassigned memory, device rejected the transaction,
 * IOMMU fault).
1784
 *
A
Avi Kivity 已提交
1785 1786
 * @as: #AddressSpace to be accessed
 * @addr: address within that address space
1787
 * @attrs: memory transaction attributes
A
Avi Kivity 已提交
1788
 * @buf: buffer with the data transferred
1789
 * @len: the number of bytes to write
A
Avi Kivity 已提交
1790
 */
1791 1792 1793
MemTxResult address_space_write(AddressSpace *as, hwaddr addr,
                                MemTxAttrs attrs,
                                const uint8_t *buf, int len);
A
Avi Kivity 已提交
1794

1795
/* address_space_ld*: load from an address space
1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814
 * address_space_st*: store to an address space
 *
 * These functions perform a load or store of the byte, word,
 * longword or quad to the specified address within the AddressSpace.
 * The _le suffixed functions treat the data as little endian;
 * _be indicates big endian; no suffix indicates "same endianness
 * as guest CPU".
 *
 * The "guest CPU endianness" accessors are deprecated for use outside
 * target-* code; devices should be CPU-agnostic and use either the LE
 * or the BE accessors.
 *
 * @as #AddressSpace to be accessed
 * @addr: address within that address space
 * @val: data value, for stores
 * @attrs: memory transaction attributes
 * @result: location to write the success/failure of the transaction;
 *   if NULL, this information is discarded
 */
1815 1816 1817 1818 1819 1820 1821 1822 1823 1824

#define SUFFIX
#define ARG1         as
#define ARG1_DECL    AddressSpace *as
#include "exec/memory_ldst.inc.h"

#define SUFFIX
#define ARG1         as
#define ARG1_DECL    AddressSpace *as
#include "exec/memory_ldst_phys.inc.h"
P
Paolo Bonzini 已提交
1825

P
Paolo Bonzini 已提交
1826
struct MemoryRegionCache {
1827
    void *ptr;
P
Paolo Bonzini 已提交
1828 1829
    hwaddr xlat;
    hwaddr len;
1830 1831 1832
    FlatView *fv;
    MemoryRegionSection mrs;
    bool is_write;
P
Paolo Bonzini 已提交
1833 1834
};

1835 1836
#define MEMORY_REGION_CACHE_INVALID ((MemoryRegionCache) { .mrs.mr = NULL })

1837

1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861
/* address_space_ld*_cached: load from a cached #MemoryRegion
 * address_space_st*_cached: store into a cached #MemoryRegion
 *
 * These functions perform a load or store of the byte, word,
 * longword or quad to the specified address.  The address is
 * a physical address in the AddressSpace, but it must lie within
 * a #MemoryRegion that was mapped with address_space_cache_init.
 *
 * The _le suffixed functions treat the data as little endian;
 * _be indicates big endian; no suffix indicates "same endianness
 * as guest CPU".
 *
 * The "guest CPU endianness" accessors are deprecated for use outside
 * target-* code; devices should be CPU-agnostic and use either the LE
 * or the BE accessors.
 *
 * @cache: previously initialized #MemoryRegionCache to be accessed
 * @addr: address within the address space
 * @val: data value, for stores
 * @attrs: memory transaction attributes
 * @result: location to write the success/failure of the transaction;
 *   if NULL, this information is discarded
 */

1862
#define SUFFIX       _cached_slow
1863 1864 1865 1866
#define ARG1         cache
#define ARG1_DECL    MemoryRegionCache *cache
#include "exec/memory_ldst.inc.h"

1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895
/* Inline fast path for direct RAM access.  */
static inline uint8_t address_space_ldub_cached(MemoryRegionCache *cache,
    hwaddr addr, MemTxAttrs attrs, MemTxResult *result)
{
    assert(addr < cache->len);
    if (likely(cache->ptr)) {
        return ldub_p(cache->ptr + addr);
    } else {
        return address_space_ldub_cached_slow(cache, addr, attrs, result);
    }
}

static inline void address_space_stb_cached(MemoryRegionCache *cache,
    hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result)
{
    assert(addr < cache->len);
    if (likely(cache->ptr)) {
        stb_p(cache->ptr + addr, val);
    } else {
        address_space_stb_cached_slow(cache, addr, val, attrs, result);
    }
}

#define ENDIANNESS   _le
#include "exec/memory_ldst_cached.inc.h"

#define ENDIANNESS   _be
#include "exec/memory_ldst_cached.inc.h"

1896 1897 1898 1899 1900
#define SUFFIX       _cached
#define ARG1         cache
#define ARG1_DECL    MemoryRegionCache *cache
#include "exec/memory_ldst_phys.inc.h"

P
Paolo Bonzini 已提交
1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944
/* address_space_cache_init: prepare for repeated access to a physical
 * memory region
 *
 * @cache: #MemoryRegionCache to be filled
 * @as: #AddressSpace to be accessed
 * @addr: address within that address space
 * @len: length of buffer
 * @is_write: indicates the transfer direction
 *
 * Will only work with RAM, and may map a subset of the requested range by
 * returning a value that is less than @len.  On failure, return a negative
 * errno value.
 *
 * Because it only works with RAM, this function can be used for
 * read-modify-write operations.  In this case, is_write should be %true.
 *
 * Note that addresses passed to the address_space_*_cached functions
 * are relative to @addr.
 */
int64_t address_space_cache_init(MemoryRegionCache *cache,
                                 AddressSpace *as,
                                 hwaddr addr,
                                 hwaddr len,
                                 bool is_write);

/**
 * address_space_cache_invalidate: complete a write to a #MemoryRegionCache
 *
 * @cache: The #MemoryRegionCache to operate on.
 * @addr: The first physical address that was written, relative to the
 * address that was passed to @address_space_cache_init.
 * @access_len: The number of bytes that were written starting at @addr.
 */
void address_space_cache_invalidate(MemoryRegionCache *cache,
                                    hwaddr addr,
                                    hwaddr access_len);

/**
 * address_space_cache_destroy: free a #MemoryRegionCache
 *
 * @cache: The #MemoryRegionCache whose memory should be released.
 */
void address_space_cache_destroy(MemoryRegionCache *cache);

1945 1946 1947 1948
/* address_space_get_iotlb_entry: translate an address into an IOTLB
 * entry. Should be called from an RCU critical section.
 */
IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr,
1949
                                            bool is_write, MemTxAttrs attrs);
P
Paolo Bonzini 已提交
1950

1951
/* address_space_translate: translate an address range into an address space
1952 1953 1954
 * into a MemoryRegion and an address range into that section.  Should be
 * called from an RCU critical section, to avoid that the last reference
 * to the returned region disappears after address_space_translate returns.
1955
 *
1956
 * @fv: #FlatView to be accessed
1957 1958 1959 1960 1961
 * @addr: address within that address space
 * @xlat: pointer to address within the returned memory region section's
 * #MemoryRegion.
 * @len: pointer to length
 * @is_write: indicates the transfer direction
1962
 * @attrs: memory attributes
1963
 */
1964 1965
MemoryRegion *flatview_translate(FlatView *fv,
                                 hwaddr addr, hwaddr *xlat,
1966 1967
                                 hwaddr *len, bool is_write,
                                 MemTxAttrs attrs);
1968 1969 1970

static inline MemoryRegion *address_space_translate(AddressSpace *as,
                                                    hwaddr addr, hwaddr *xlat,
1971 1972
                                                    hwaddr *len, bool is_write,
                                                    MemTxAttrs attrs)
1973 1974
{
    return flatview_translate(address_space_to_flatview(as),
1975
                              addr, xlat, len, is_write, attrs);
1976
}
1977

1978 1979 1980
/* address_space_access_valid: check for validity of accessing an address
 * space range
 *
A
Avi Kivity 已提交
1981 1982 1983
 * Check whether memory is assigned to the given address space range, and
 * access is permitted by any IOMMU regions that are active for the address
 * space.
1984 1985 1986 1987 1988 1989 1990 1991
 *
 * For now, addr and len should be aligned to a page size.  This limitation
 * will be lifted in the future.
 *
 * @as: #AddressSpace to be accessed
 * @addr: address within that address space
 * @len: length of the area to be checked
 * @is_write: indicates the transfer direction
1992
 * @attrs: memory attributes
1993
 */
1994 1995
bool address_space_access_valid(AddressSpace *as, hwaddr addr, int len,
                                bool is_write, MemTxAttrs attrs);
1996

A
Avi Kivity 已提交
1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008
/* address_space_map: map a physical memory region into a host virtual address
 *
 * May map a subset of the requested range, given by and returned in @plen.
 * May return %NULL if resources needed to perform the mapping are exhausted.
 * Use only for reads OR writes - not for read-modify-write operations.
 * Use cpu_register_map_client() to know when retrying the map operation is
 * likely to succeed.
 *
 * @as: #AddressSpace to be accessed
 * @addr: address within that address space
 * @plen: pointer to length of buffer; updated on return
 * @is_write: indicates the transfer direction
2009
 * @attrs: memory attributes
A
Avi Kivity 已提交
2010
 */
A
Avi Kivity 已提交
2011
void *address_space_map(AddressSpace *as, hwaddr addr,
2012
                        hwaddr *plen, bool is_write, MemTxAttrs attrs);
A
Avi Kivity 已提交
2013 2014 2015 2016 2017 2018 2019

/* address_space_unmap: Unmaps a memory region previously mapped by address_space_map()
 *
 * Will also mark the memory as dirty if @is_write == %true.  @access_len gives
 * the amount of memory that was actually read or written by the caller.
 *
 * @as: #AddressSpace used
2020
 * @buffer: host pointer as returned by address_space_map()
A
Avi Kivity 已提交
2021 2022 2023 2024
 * @len: buffer length as returned by address_space_map()
 * @access_len: amount of data actually transferred
 * @is_write: indicates the transfer direction
 */
A
Avi Kivity 已提交
2025 2026
void address_space_unmap(AddressSpace *as, void *buffer, hwaddr len,
                         int is_write, hwaddr access_len);
A
Avi Kivity 已提交
2027 2028


2029
/* Internal functions, part of the implementation of address_space_read.  */
2030 2031
MemTxResult address_space_read_full(AddressSpace *as, hwaddr addr,
                                    MemTxAttrs attrs, uint8_t *buf, int len);
2032 2033 2034 2035
MemTxResult flatview_read_continue(FlatView *fv, hwaddr addr,
                                   MemTxAttrs attrs, uint8_t *buf,
                                   int len, hwaddr addr1, hwaddr l,
                                   MemoryRegion *mr);
2036
void *qemu_map_ram_ptr(RAMBlock *ram_block, ram_addr_t addr);
2037

2038 2039 2040 2041 2042 2043 2044
/* Internal functions, part of the implementation of address_space_read_cached
 * and address_space_write_cached.  */
void address_space_read_cached_slow(MemoryRegionCache *cache,
                                    hwaddr addr, void *buf, int len);
void address_space_write_cached_slow(MemoryRegionCache *cache,
                                     hwaddr addr, const void *buf, int len);

2045 2046 2047
static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write)
{
    if (is_write) {
2048 2049
        return memory_region_is_ram(mr) &&
               !mr->readonly && !memory_region_is_ram_device(mr);
2050
    } else {
2051 2052
        return (memory_region_is_ram(mr) && !memory_region_is_ram_device(mr)) ||
               memory_region_is_romd(mr);
2053 2054 2055 2056 2057 2058 2059 2060
    }
}

/**
 * address_space_read: read from an address space.
 *
 * Return a MemTxResult indicating whether the operation succeeded
 * or failed (eg unassigned memory, device rejected the transaction,
2061
 * IOMMU fault).  Called within RCU critical section.
2062
 *
2063
 * @as: #AddressSpace to be accessed
2064 2065 2066 2067 2068
 * @addr: address within that address space
 * @attrs: memory transaction attributes
 * @buf: buffer with the data transferred
 */
static inline __attribute__((__always_inline__))
2069 2070 2071
MemTxResult address_space_read(AddressSpace *as, hwaddr addr,
                               MemTxAttrs attrs, uint8_t *buf,
                               int len)
2072 2073 2074 2075 2076
{
    MemTxResult result = MEMTX_OK;
    hwaddr l, addr1;
    void *ptr;
    MemoryRegion *mr;
2077
    FlatView *fv;
2078 2079 2080 2081

    if (__builtin_constant_p(len)) {
        if (len) {
            rcu_read_lock();
2082
            fv = address_space_to_flatview(as);
2083
            l = len;
2084
            mr = flatview_translate(fv, addr, &addr1, &l, false, attrs);
2085
            if (len == l && memory_access_is_direct(mr, false)) {
2086
                ptr = qemu_map_ram_ptr(mr->ram_block, addr1);
2087 2088
                memcpy(buf, ptr, len);
            } else {
2089 2090
                result = flatview_read_continue(fv, addr, attrs, buf, len,
                                                addr1, l, mr);
2091 2092 2093 2094
            }
            rcu_read_unlock();
        }
    } else {
2095
        result = address_space_read_full(as, addr, attrs, buf, len);
2096 2097 2098
    }
    return result;
}
2099

P
Paolo Bonzini 已提交
2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112
/**
 * address_space_read_cached: read from a cached RAM region
 *
 * @cache: Cached region to be addressed
 * @addr: address relative to the base of the RAM region
 * @buf: buffer with the data transferred
 * @len: length of the data transferred
 */
static inline void
address_space_read_cached(MemoryRegionCache *cache, hwaddr addr,
                          void *buf, int len)
{
    assert(addr < cache->len && len <= cache->len - addr);
2113 2114 2115 2116 2117
    if (likely(cache->ptr)) {
        memcpy(buf, cache->ptr + addr, len);
    } else {
        address_space_read_cached_slow(cache, addr, buf, len);
    }
P
Paolo Bonzini 已提交
2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132
}

/**
 * address_space_write_cached: write to a cached RAM region
 *
 * @cache: Cached region to be addressed
 * @addr: address relative to the base of the RAM region
 * @buf: buffer with the data transferred
 * @len: length of the data transferred
 */
static inline void
address_space_write_cached(MemoryRegionCache *cache, hwaddr addr,
                           void *buf, int len)
{
    assert(addr < cache->len && len <= cache->len - addr);
2133 2134 2135 2136 2137
    if (likely(cache->ptr)) {
        memcpy(cache->ptr + addr, buf, len);
    } else {
        address_space_write_cached_slow(cache, addr, buf, len);
    }
P
Paolo Bonzini 已提交
2138 2139
}

A
Avi Kivity 已提交
2140 2141 2142
#endif

#endif