X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=memory.c;h=28f64491d06fcbb217928733491dbb5e6547da9d;hb=8b7acc79b9adb4dda6cc867b90e3a1e873f4f7e8;hp=24027c507755b81dc789ef03c0a6ab33a831b225;hpb=3ce10901ca8da9142dcdcde198fda1a4c290934c;p=qemu.git diff --git a/memory.c b/memory.c index 24027c507..28f64491d 100644 --- a/memory.c +++ b/memory.c @@ -18,7 +18,7 @@ #include "exec/ioport.h" #include "qemu/bitops.h" #include "qom/object.h" -#include "sysemu/kvm.h" +#include "trace.h" #include #include "exec/memory-internal.h" @@ -29,12 +29,26 @@ static unsigned memory_region_transaction_depth; static bool memory_region_update_pending; static bool global_dirty_log = false; +/* flat_view_mutex is taken around reading as->current_map; the critical + * section is extremely short, so I'm using a single mutex for every AS. + * We could also RCU for the read-side. + * + * The BQL is taken around transaction commits, hence both locks are taken + * while writing to as->current_map (with the BQL taken outside). + */ +static QemuMutex flat_view_mutex; + static QTAILQ_HEAD(memory_listeners, MemoryListener) memory_listeners = QTAILQ_HEAD_INITIALIZER(memory_listeners); static QTAILQ_HEAD(, AddressSpace) address_spaces = QTAILQ_HEAD_INITIALIZER(address_spaces); +static void memory_init(void) +{ + qemu_mutex_init(&flat_view_mutex); +} + typedef struct AddrRange AddrRange; /* @@ -148,6 +162,7 @@ static bool memory_listener_match(MemoryListener *listener, } \ } while (0) +/* No need to ref/unref .mr, the FlatRange keeps it alive. */ #define MEMORY_LISTENER_UPDATE_REGION(fr, as, dir, callback) \ MEMORY_LISTENER_CALL(callback, dir, (&(MemoryRegionSection) { \ .mr = (fr)->mr, \ @@ -224,6 +239,7 @@ struct FlatRange { * order. */ struct FlatView { + unsigned ref; FlatRange *ranges; unsigned nr; unsigned nr_allocated; @@ -245,6 +261,7 @@ static bool flatrange_equal(FlatRange *a, FlatRange *b) static void flatview_init(FlatView *view) { + view->ref = 1; view->ranges = NULL; view->nr = 0; view->nr_allocated = 0; @@ -263,12 +280,31 @@ static void flatview_insert(FlatView *view, unsigned pos, FlatRange *range) memmove(view->ranges + pos + 1, view->ranges + pos, (view->nr - pos) * sizeof(FlatRange)); view->ranges[pos] = *range; + memory_region_ref(range->mr); ++view->nr; } static void flatview_destroy(FlatView *view) { + int i; + + for (i = 0; i < view->nr; i++) { + memory_region_unref(view->ranges[i].mr); + } g_free(view->ranges); + g_free(view); +} + +static void flatview_ref(FlatView *view) +{ + atomic_inc(&view->ref); +} + +static void flatview_unref(FlatView *view) +{ + if (atomic_fetch_dec(&view->ref) == 1) { + flatview_destroy(view); + } } static bool can_merge(FlatRange *r1, FlatRange *r2) @@ -303,65 +339,104 @@ static void flatview_simplify(FlatView *view) } } -static void memory_region_oldmmio_read_accessor(void *opaque, +static bool memory_region_big_endian(MemoryRegion *mr) +{ +#ifdef TARGET_WORDS_BIGENDIAN + return mr->ops->endianness != DEVICE_LITTLE_ENDIAN; +#else + return mr->ops->endianness == DEVICE_BIG_ENDIAN; +#endif +} + +static bool memory_region_wrong_endianness(MemoryRegion *mr) +{ +#ifdef TARGET_WORDS_BIGENDIAN + return mr->ops->endianness == DEVICE_LITTLE_ENDIAN; +#else + return mr->ops->endianness == DEVICE_BIG_ENDIAN; +#endif +} + +static void adjust_endianness(MemoryRegion *mr, uint64_t *data, unsigned size) +{ + if (memory_region_wrong_endianness(mr)) { + switch (size) { + case 1: + break; + case 2: + *data = bswap16(*data); + break; + case 4: + *data = bswap32(*data); + break; + case 8: + *data = bswap64(*data); + break; + default: + abort(); + } + } +} + +static void memory_region_oldmmio_read_accessor(MemoryRegion *mr, hwaddr addr, uint64_t *value, unsigned size, unsigned shift, uint64_t mask) { - MemoryRegion *mr = opaque; uint64_t tmp; tmp = mr->ops->old_mmio.read[ctz32(size)](mr->opaque, addr); + trace_memory_region_ops_read(mr, addr, tmp, size); *value |= (tmp & mask) << shift; } -static void memory_region_read_accessor(void *opaque, +static void memory_region_read_accessor(MemoryRegion *mr, hwaddr addr, uint64_t *value, unsigned size, unsigned shift, uint64_t mask) { - MemoryRegion *mr = opaque; uint64_t tmp; if (mr->flush_coalesced_mmio) { qemu_flush_coalesced_mmio_buffer(); } tmp = mr->ops->read(mr->opaque, addr, size); + trace_memory_region_ops_read(mr, addr, tmp, size); *value |= (tmp & mask) << shift; } -static void memory_region_oldmmio_write_accessor(void *opaque, +static void memory_region_oldmmio_write_accessor(MemoryRegion *mr, hwaddr addr, uint64_t *value, unsigned size, unsigned shift, uint64_t mask) { - MemoryRegion *mr = opaque; uint64_t tmp; tmp = (*value >> shift) & mask; + trace_memory_region_ops_write(mr, addr, tmp, size); mr->ops->old_mmio.write[ctz32(size)](mr->opaque, addr, tmp); } -static void memory_region_write_accessor(void *opaque, +static void memory_region_write_accessor(MemoryRegion *mr, hwaddr addr, uint64_t *value, unsigned size, unsigned shift, uint64_t mask) { - MemoryRegion *mr = opaque; uint64_t tmp; if (mr->flush_coalesced_mmio) { qemu_flush_coalesced_mmio_buffer(); } tmp = (*value >> shift) & mask; + trace_memory_region_ops_write(mr, addr, tmp, size); mr->ops->write(mr->opaque, addr, tmp, size); } @@ -370,13 +445,13 @@ static void access_with_adjusted_size(hwaddr addr, unsigned size, unsigned access_size_min, unsigned access_size_max, - void (*access)(void *opaque, + void (*access)(MemoryRegion *mr, hwaddr addr, uint64_t *value, unsigned size, unsigned shift, uint64_t mask), - void *opaque) + MemoryRegion *mr) { uint64_t access_mask; unsigned access_size; @@ -392,13 +467,15 @@ static void access_with_adjusted_size(hwaddr addr, /* FIXME: support unaligned access? */ access_size = MAX(MIN(size, access_size_max), access_size_min); access_mask = -1ULL >> (64 - access_size * 8); - for (i = 0; i < size; i += access_size) { -#ifdef TARGET_WORDS_BIGENDIAN - access(opaque, addr + i, value, access_size, - (size - access_size - i) * 8, access_mask); -#else - access(opaque, addr + i, value, access_size, i * 8, access_mask); -#endif + if (memory_region_big_endian(mr)) { + for (i = 0; i < size; i += access_size) { + access(mr, addr + i, value, access_size, + (size - access_size - i) * 8, access_mask); + } + } else { + for (i = 0; i < size; i += access_size) { + access(mr, addr + i, value, access_size, i * 8, access_mask); + } } } @@ -505,17 +582,18 @@ static void render_memory_region(FlatView *view, } /* Render a memory topology into a list of disjoint absolute ranges. */ -static FlatView generate_memory_topology(MemoryRegion *mr) +static FlatView *generate_memory_topology(MemoryRegion *mr) { - FlatView view; + FlatView *view; - flatview_init(&view); + view = g_new(FlatView, 1); + flatview_init(view); if (mr) { - render_memory_region(&view, mr, int128_zero(), + render_memory_region(view, mr, int128_zero(), addrrange_make(int128_zero(), int128_2_64()), false); } - flatview_simplify(&view); + flatview_simplify(view); return view; } @@ -569,15 +647,28 @@ static void address_space_add_del_ioeventfds(AddressSpace *as, } } +static FlatView *address_space_get_flatview(AddressSpace *as) +{ + FlatView *view; + + qemu_mutex_lock(&flat_view_mutex); + view = as->current_map; + flatview_ref(view); + qemu_mutex_unlock(&flat_view_mutex); + return view; +} + static void address_space_update_ioeventfds(AddressSpace *as) { + FlatView *view; FlatRange *fr; unsigned ioeventfd_nb = 0; MemoryRegionIoeventfd *ioeventfds = NULL; AddrRange tmp; unsigned i; - FOR_EACH_FLAT_RANGE(fr, as->current_map) { + view = address_space_get_flatview(as); + FOR_EACH_FLAT_RANGE(fr, view) { for (i = 0; i < fr->mr->ioeventfd_nb; ++i) { tmp = addrrange_shift(fr->mr->ioeventfds[i].addr, int128_sub(fr->addr.start, @@ -598,11 +689,12 @@ static void address_space_update_ioeventfds(AddressSpace *as) g_free(as->ioeventfds); as->ioeventfds = ioeventfds; as->ioeventfd_nb = ioeventfd_nb; + flatview_unref(view); } static void address_space_update_topology_pass(AddressSpace *as, - FlatView old_view, - FlatView new_view, + const FlatView *old_view, + const FlatView *new_view, bool adding) { unsigned iold, inew; @@ -612,14 +704,14 @@ static void address_space_update_topology_pass(AddressSpace *as, * Kill ranges in the old map, and instantiate ranges in the new map. */ iold = inew = 0; - while (iold < old_view.nr || inew < new_view.nr) { - if (iold < old_view.nr) { - frold = &old_view.ranges[iold]; + while (iold < old_view->nr || inew < new_view->nr) { + if (iold < old_view->nr) { + frold = &old_view->ranges[iold]; } else { frold = NULL; } - if (inew < new_view.nr) { - frnew = &new_view.ranges[inew]; + if (inew < new_view->nr) { + frnew = &new_view->ranges[inew]; } else { frnew = NULL; } @@ -665,14 +757,25 @@ static void address_space_update_topology_pass(AddressSpace *as, static void address_space_update_topology(AddressSpace *as) { - FlatView old_view = *as->current_map; - FlatView new_view = generate_memory_topology(as->root); + FlatView *old_view = address_space_get_flatview(as); + FlatView *new_view = generate_memory_topology(as->root); address_space_update_topology_pass(as, old_view, new_view, false); address_space_update_topology_pass(as, old_view, new_view, true); - *as->current_map = new_view; - flatview_destroy(&old_view); + qemu_mutex_lock(&flat_view_mutex); + flatview_unref(as->current_map); + as->current_map = new_view; + qemu_mutex_unlock(&flat_view_mutex); + + /* Note that all the old MemoryRegions are still alive up to this + * point. This relieves most MemoryListeners from the need to + * ref/unref the MemoryRegions they get---unless they use them + * outside the iothread mutex, in which case precise reference + * counting is necessary. + */ + flatview_unref(old_view); + address_space_update_ioeventfds(as); } @@ -709,6 +812,11 @@ static void memory_region_destructor_ram(MemoryRegion *mr) qemu_ram_free(mr->ram_addr); } +static void memory_region_destructor_alias(MemoryRegion *mr) +{ + memory_region_unref(mr->alias); +} + static void memory_region_destructor_ram_from_ptr(MemoryRegion *mr) { qemu_ram_free_from_ptr(mr->ram_addr); @@ -719,15 +827,6 @@ static void memory_region_destructor_rom_device(MemoryRegion *mr) qemu_ram_free(mr->ram_addr & TARGET_PAGE_MASK); } -static bool memory_region_wrong_endianness(MemoryRegion *mr) -{ -#ifdef TARGET_WORDS_BIGENDIAN - return mr->ops->endianness == DEVICE_LITTLE_ENDIAN; -#else - return mr->ops->endianness == DEVICE_BIG_ENDIAN; -#endif -} - void memory_region_init(MemoryRegion *mr, Object *owner, const char *name, @@ -738,7 +837,6 @@ void memory_region_init(MemoryRegion *mr, mr->owner = owner; mr->iommu_ops = NULL; mr->parent = NULL; - mr->owner = NULL; mr->size = int128_make64(size); if (size == UINT64_MAX) { mr->size = int128_2_64(); @@ -771,9 +869,8 @@ static uint64_t unassigned_mem_read(void *opaque, hwaddr addr, #ifdef DEBUG_UNASSIGNED printf("Unassigned mem read " TARGET_FMT_plx "\n", addr); #endif - if (cpu_single_env != NULL) { - cpu_unassigned_access(ENV_GET_CPU(cpu_single_env), - addr, false, false, 0, size); + if (current_cpu != NULL) { + cpu_unassigned_access(current_cpu, addr, false, false, 0, size); } return 0; } @@ -784,9 +881,8 @@ static void unassigned_mem_write(void *opaque, hwaddr addr, #ifdef DEBUG_UNASSIGNED printf("Unassigned mem write " TARGET_FMT_plx " = 0x%"PRIx64"\n", addr, val); #endif - if (cpu_single_env != NULL) { - cpu_unassigned_access(ENV_GET_CPU(cpu_single_env), - addr, true, false, 0, size); + if (current_cpu != NULL) { + cpu_unassigned_access(current_cpu, addr, true, false, 0, size); } } @@ -857,27 +953,6 @@ static uint64_t memory_region_dispatch_read1(MemoryRegion *mr, return data; } -static void adjust_endianness(MemoryRegion *mr, uint64_t *data, unsigned size) -{ - if (memory_region_wrong_endianness(mr)) { - switch (size) { - case 1: - break; - case 2: - *data = bswap16(*data); - break; - case 4: - *data = bswap32(*data); - break; - case 8: - *data = bswap64(*data); - break; - default: - abort(); - } - } -} - static bool memory_region_dispatch_read(MemoryRegion *mr, hwaddr addr, uint64_t *pval, @@ -964,6 +1039,8 @@ void memory_region_init_alias(MemoryRegion *mr, uint64_t size) { memory_region_init(mr, owner, name, size); + memory_region_ref(orig); + mr->destructor = memory_region_destructor_alias; mr->alias = orig; mr->alias_offset = offset; } @@ -1130,11 +1207,13 @@ void memory_region_sync_dirty_bitmap(MemoryRegion *mr) FlatRange *fr; QTAILQ_FOREACH(as, &address_spaces, address_spaces_link) { - FOR_EACH_FLAT_RANGE(fr, as->current_map) { + FlatView *view = address_space_get_flatview(as); + FOR_EACH_FLAT_RANGE(fr, view) { if (fr->mr == mr) { MEMORY_LISTENER_UPDATE_REGION(fr, as, Forward, log_sync); } } + flatview_unref(view); } } @@ -1180,12 +1259,14 @@ void *memory_region_get_ram_ptr(MemoryRegion *mr) static void memory_region_update_coalesced_range_as(MemoryRegion *mr, AddressSpace *as) { + FlatView *view; FlatRange *fr; CoalescedMemoryRange *cmr; AddrRange tmp; MemoryRegionSection section; - FOR_EACH_FLAT_RANGE(fr, as->current_map) { + view = address_space_get_flatview(as); + FOR_EACH_FLAT_RANGE(fr, view) { if (fr->mr == mr) { section = (MemoryRegionSection) { .address_space = as, @@ -1210,6 +1291,7 @@ static void memory_region_update_coalesced_range_as(MemoryRegion *mr, AddressSpa } } } + flatview_unref(view); } static void memory_region_update_coalesced_range(MemoryRegion *mr) @@ -1342,6 +1424,7 @@ static void memory_region_add_subregion_common(MemoryRegion *mr, memory_region_transaction_begin(); assert(!subregion->parent); + memory_region_ref(subregion); subregion->parent = mr; subregion->addr = offset; QTAILQ_FOREACH(other, &mr->subregions, subregions_link) { @@ -1390,7 +1473,7 @@ void memory_region_add_subregion(MemoryRegion *mr, void memory_region_add_subregion_overlap(MemoryRegion *mr, hwaddr offset, MemoryRegion *subregion, - unsigned priority) + int priority) { subregion->may_overlap = true; subregion->priority = priority; @@ -1404,6 +1487,7 @@ void memory_region_del_subregion(MemoryRegion *mr, assert(subregion->parent == mr); subregion->parent = NULL; QTAILQ_REMOVE(&mr->subregions, subregion, subregions_link); + memory_region_unref(subregion); memory_region_update_pending |= mr->enabled && subregion->enabled; memory_region_transaction_commit(); } @@ -1422,7 +1506,7 @@ void memory_region_set_enabled(MemoryRegion *mr, bool enabled) void memory_region_set_address(MemoryRegion *mr, hwaddr addr) { MemoryRegion *parent = mr->parent; - unsigned priority = mr->priority; + int priority = mr->priority; bool may_overlap = mr->may_overlap; if (addr == mr->addr || !parent) { @@ -1431,12 +1515,14 @@ void memory_region_set_address(MemoryRegion *mr, hwaddr addr) } memory_region_transaction_begin(); + memory_region_ref(mr); memory_region_del_subregion(parent, mr); if (may_overlap) { memory_region_add_subregion_overlap(parent, addr, mr, priority); } else { memory_region_add_subregion(parent, addr, mr); } + memory_region_unref(mr); memory_region_transaction_commit(); } @@ -1472,9 +1558,9 @@ static int cmp_flatrange_addr(const void *addr_, const void *fr_) return 0; } -static FlatRange *address_space_lookup(AddressSpace *as, AddrRange addr) +static FlatRange *flatview_lookup(FlatView *view, AddrRange addr) { - return bsearch(&addr, as->current_map->ranges, as->current_map->nr, + return bsearch(&addr, view->ranges, view->nr, sizeof(FlatRange), cmp_flatrange_addr); } @@ -1484,6 +1570,7 @@ bool memory_region_present(MemoryRegion *parent, hwaddr addr) if (!mr) { return false; } + memory_region_unref(mr); return true; } @@ -1494,6 +1581,7 @@ MemoryRegionSection memory_region_find(MemoryRegion *mr, MemoryRegion *root; AddressSpace *as; AddrRange range; + FlatView *view; FlatRange *fr; addr += mr->addr; @@ -1504,13 +1592,14 @@ MemoryRegionSection memory_region_find(MemoryRegion *mr, as = memory_region_to_address_space(root); range = addrrange_make(int128_make64(addr), int128_make64(size)); - fr = address_space_lookup(as, range); + + view = address_space_get_flatview(as); + fr = flatview_lookup(view, range); if (!fr) { return ret; } - while (fr > as->current_map->ranges - && addrrange_intersects(fr[-1].addr, range)) { + while (fr > view->ranges && addrrange_intersects(fr[-1].addr, range)) { --fr; } @@ -1523,16 +1612,22 @@ MemoryRegionSection memory_region_find(MemoryRegion *mr, ret.size = range.size; ret.offset_within_address_space = int128_get64(range.start); ret.readonly = fr->readonly; + memory_region_ref(ret.mr); + + flatview_unref(view); return ret; } void address_space_sync_dirty_bitmap(AddressSpace *as) { + FlatView *view; FlatRange *fr; - FOR_EACH_FLAT_RANGE(fr, as->current_map) { + view = address_space_get_flatview(as); + FOR_EACH_FLAT_RANGE(fr, view) { MEMORY_LISTENER_UPDATE_REGION(fr, as, Forward, log_sync); } + flatview_unref(view); } void memory_global_dirty_log_start(void) @@ -1550,6 +1645,7 @@ void memory_global_dirty_log_stop(void) static void listener_add_address_space(MemoryListener *listener, AddressSpace *as) { + FlatView *view; FlatRange *fr; if (listener->address_space_filter @@ -1563,7 +1659,8 @@ static void listener_add_address_space(MemoryListener *listener, } } - FOR_EACH_FLAT_RANGE(fr, as->current_map) { + view = address_space_get_flatview(as); + FOR_EACH_FLAT_RANGE(fr, view) { MemoryRegionSection section = { .mr = fr->mr, .address_space = as, @@ -1576,6 +1673,7 @@ static void listener_add_address_space(MemoryListener *listener, listener->region_add(listener, §ion); } } + flatview_unref(view); } void memory_listener_register(MemoryListener *listener, AddressSpace *filter) @@ -1609,6 +1707,10 @@ void memory_listener_unregister(MemoryListener *listener) void address_space_init(AddressSpace *as, MemoryRegion *root, const char *name) { + if (QTAILQ_EMPTY(&address_spaces)) { + memory_init(); + } + memory_region_transaction_begin(); as->root = root; as->current_map = g_new(FlatView, 1); @@ -1630,9 +1732,8 @@ void address_space_destroy(AddressSpace *as) memory_region_transaction_commit(); QTAILQ_REMOVE(&address_spaces, as, address_spaces_link); address_space_destroy_dispatch(as); - flatview_destroy(as->current_map); + flatview_unref(as->current_map); g_free(as->name); - g_free(as->current_map); g_free(as->ioeventfds); } @@ -1697,7 +1798,9 @@ static void mtree_print_mr(fprintf_function mon_printf, void *f, "-" TARGET_FMT_plx "\n", base + mr->addr, base + mr->addr - + (hwaddr)int128_get64(int128_sub(mr->size, int128_make64(1))), + + (int128_nz(mr->size) ? + (hwaddr)int128_get64(int128_sub(mr->size, + int128_one())) : 0), mr->priority, mr->romd_mode ? 'R' : '-', !mr->readonly && !(mr->rom_device && mr->romd_mode) ? 'W' @@ -1706,13 +1809,17 @@ static void mtree_print_mr(fprintf_function mon_printf, void *f, mr->alias->name, mr->alias_offset, mr->alias_offset - + (hwaddr)int128_get64(mr->size) - 1); + + (int128_nz(mr->size) ? + (hwaddr)int128_get64(int128_sub(mr->size, + int128_one())) : 0)); } else { mon_printf(f, TARGET_FMT_plx "-" TARGET_FMT_plx " (prio %d, %c%c): %s\n", base + mr->addr, base + mr->addr - + (hwaddr)int128_get64(int128_sub(mr->size, int128_make64(1))), + + (int128_nz(mr->size) ? + (hwaddr)int128_get64(int128_sub(mr->size, + int128_one())) : 0), mr->priority, mr->romd_mode ? 'R' : '-', !mr->readonly && !(mr->rom_device && mr->romd_mode) ? 'W'