X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=exec.c;h=6ab62f4eee0945aacbcadfe6d06bf618874bf4b8;hb=be1092afa07794e5247eb504095fb5f2ae421ec6;hp=e7be0761c28a3b9574711007aedf573de11b253e;hpb=55a7cb144d8565583d31c323672745f87fca9954;p=mirror_qemu.git diff --git a/exec.c b/exec.c index e7be0761c2..6ab62f4eee 100644 --- a/exec.c +++ b/exec.c @@ -87,26 +87,6 @@ AddressSpace address_space_memory; MemoryRegion io_mem_rom, io_mem_notdirty; static MemoryRegion io_mem_unassigned; - -/* 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) #endif #ifdef TARGET_PAGE_BITS_VARY @@ -114,7 +94,8 @@ int target_page_bits; bool target_page_bits_decided; #endif -struct CPUTailQ cpus = QTAILQ_HEAD_INITIALIZER(cpus); +CPUTailQ cpus = QTAILQ_HEAD_INITIALIZER(cpus); + /* current CPU in the current thread. It is only valid inside cpu_exec() */ __thread CPUState *current_cpu; @@ -684,7 +665,7 @@ static void tcg_register_iommu_notifier(CPUState *cpu, int i; for (i = 0; i < cpu->iommu_notifiers->len; i++) { - notifier = &g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier, i); + notifier = g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier *, i); if (notifier->mr == mr && notifier->iommu_idx == iommu_idx) { break; } @@ -692,7 +673,8 @@ static void tcg_register_iommu_notifier(CPUState *cpu, if (i == cpu->iommu_notifiers->len) { /* Not found, add a new entry at the end of the array */ cpu->iommu_notifiers = g_array_set_size(cpu->iommu_notifiers, i + 1); - notifier = &g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier, i); + notifier = g_new0(TCGIOMMUNotifier, 1); + g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier *, i) = notifier; notifier->mr = mr; notifier->iommu_idx = iommu_idx; @@ -724,8 +706,9 @@ static void tcg_iommu_free_notifier_list(CPUState *cpu) TCGIOMMUNotifier *notifier; for (i = 0; i < cpu->iommu_notifiers->len; i++) { - notifier = &g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier, i); + notifier = g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier *, i); memory_region_unregister_iommu_notifier(notifier->mr, ¬ifier->n); + g_free(notifier); } g_array_free(cpu->iommu_notifiers, true); } @@ -985,6 +968,7 @@ void cpu_exec_realizefn(CPUState *cpu, Error **errp) tcg_target_initialized = true; cc->tcg_initialize(); } + tlb_init(cpu); #ifndef CONFIG_USER_ONLY if (qdev_get_vmsd(DEVICE(cpu)) == NULL) { @@ -994,7 +978,7 @@ void cpu_exec_realizefn(CPUState *cpu, Error **errp) vmstate_register(NULL, cpu->cpu_index, cc->vmsd, cpu); } - cpu->iommu_notifiers = g_array_new(false, true, sizeof(TCGIOMMUNotifier)); + cpu->iommu_notifiers = g_array_new(false, true, sizeof(TCGIOMMUNotifier *)); #endif } @@ -1615,35 +1599,49 @@ static void register_multipage(FlatView *fv, phys_page_set(d, start_addr >> TARGET_PAGE_BITS, num_pages, section_index); } +/* + * The range in *section* may look like this: + * + * |s|PPPPPPP|s| + * + * where s stands for subpage and P for page. + */ void flatview_add_to_dispatch(FlatView *fv, MemoryRegionSection *section) { - MemoryRegionSection now = *section, remain = *section; + MemoryRegionSection remain = *section; Int128 page_size = int128_make64(TARGET_PAGE_SIZE); - if (now.offset_within_address_space & ~TARGET_PAGE_MASK) { - uint64_t left = TARGET_PAGE_ALIGN(now.offset_within_address_space) - - now.offset_within_address_space; + /* register first subpage */ + if (remain.offset_within_address_space & ~TARGET_PAGE_MASK) { + uint64_t left = TARGET_PAGE_ALIGN(remain.offset_within_address_space) + - remain.offset_within_address_space; + MemoryRegionSection now = remain; now.size = int128_min(int128_make64(left), now.size); register_subpage(fv, &now); - } else { - now.size = int128_zero(); - } - while (int128_ne(remain.size, now.size)) { + if (int128_eq(remain.size, now.size)) { + return; + } remain.size = int128_sub(remain.size, now.size); remain.offset_within_address_space += int128_get64(now.size); remain.offset_within_region += int128_get64(now.size); - now = remain; - if (int128_lt(remain.size, page_size)) { - register_subpage(fv, &now); - } else if (remain.offset_within_address_space & ~TARGET_PAGE_MASK) { - now.size = page_size; - register_subpage(fv, &now); - } else { - now.size = int128_and(now.size, int128_neg(page_size)); - register_multipage(fv, &now); + } + + /* register whole pages */ + if (int128_ge(remain.size, page_size)) { + MemoryRegionSection now = remain; + now.size = int128_and(now.size, int128_neg(page_size)); + register_multipage(fv, &now); + if (int128_eq(remain.size, now.size)) { + return; } + remain.size = int128_sub(remain.size, now.size); + remain.offset_within_address_space += int128_get64(now.size); + remain.offset_within_region += int128_get64(now.size); } + + /* register last subpage */ + register_subpage(fv, &remain); } void qemu_flush_coalesced_mmio_buffer(void) @@ -1694,9 +1692,10 @@ static int find_max_supported_pagesize(Object *obj, void *opaque) long *hpsize_min = opaque; if (object_dynamic_cast(obj, TYPE_MEMORY_BACKEND)) { - long hpsize = host_memory_backend_pagesize(MEMORY_BACKEND(obj)); + HostMemoryBackend *backend = MEMORY_BACKEND(obj); + long hpsize = host_memory_backend_pagesize(backend); - if (hpsize < *hpsize_min) { + if (host_memory_backend_is_mapped(backend) && (hpsize < *hpsize_min)) { *hpsize_min = hpsize; } } @@ -1754,7 +1753,7 @@ long qemu_getrampagesize(void) } #endif -#ifdef __linux__ +#ifdef CONFIG_POSIX static int64_t get_file_size(int fd) { int64_t size = lseek(fd, 0, SEEK_END); @@ -1889,7 +1888,7 @@ static void *file_ram_alloc(RAMBlock *block, if (mem_prealloc) { os_mem_prealloc(fd, area, memory, smp_cpus, errp); if (errp && *errp) { - qemu_ram_munmap(area, memory); + qemu_ram_munmap(fd, area, memory); return NULL; } } @@ -1988,6 +1987,21 @@ const char *qemu_ram_get_idstr(RAMBlock *rb) return rb->idstr; } +void *qemu_ram_get_host_addr(RAMBlock *rb) +{ + return rb->host; +} + +ram_addr_t qemu_ram_get_offset(RAMBlock *rb) +{ + return rb->offset; +} + +ram_addr_t qemu_ram_get_used_length(RAMBlock *rb) +{ + return rb->used_length; +} + bool qemu_ram_is_shared(RAMBlock *rb) { return rb->flags & RAM_SHARED; @@ -2250,15 +2264,18 @@ static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared) } } -#ifdef __linux__ +#ifdef CONFIG_POSIX RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, - bool share, int fd, + uint32_t ram_flags, int fd, Error **errp) { RAMBlock *new_block; Error *local_err = NULL; int64_t file_size; + /* Just support these ram flags by now. */ + assert((ram_flags & ~(RAM_SHARED | RAM_PMEM)) == 0); + if (xen_enabled()) { error_setg(errp, "-mem-path not supported with Xen"); return NULL; @@ -2294,14 +2311,14 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, new_block->mr = mr; new_block->used_length = size; new_block->max_length = size; - new_block->flags = share ? RAM_SHARED : 0; + new_block->flags = ram_flags; new_block->host = file_ram_alloc(new_block, size, fd, !file_size, errp); if (!new_block->host) { g_free(new_block); return NULL; } - ram_block_add(new_block, &local_err, share); + ram_block_add(new_block, &local_err, ram_flags & RAM_SHARED); if (local_err) { g_free(new_block); error_propagate(errp, local_err); @@ -2313,7 +2330,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr, - bool share, const char *mem_path, + uint32_t ram_flags, const char *mem_path, Error **errp) { int fd; @@ -2325,7 +2342,7 @@ RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr, return NULL; } - block = qemu_ram_alloc_from_fd(size, mr, share, fd, errp); + block = qemu_ram_alloc_from_fd(size, mr, ram_flags, fd, errp); if (!block) { if (created) { unlink(mem_path); @@ -2407,7 +2424,7 @@ static void reclaim_ramblock(RAMBlock *block) xen_invalidate_map_cache_entry(block->host); #ifndef _WIN32 } else if (block->fd >= 0) { - qemu_ram_munmap(block->host, block->max_length); + qemu_ram_munmap(block->fd, block->host, block->max_length); close(block->fd); #endif } else { @@ -2864,10 +2881,10 @@ static const MemoryRegionOps watch_mem_ops = { }; static MemTxResult flatview_read(FlatView *fv, hwaddr addr, - MemTxAttrs attrs, uint8_t *buf, int len); + MemTxAttrs attrs, uint8_t *buf, hwaddr len); static MemTxResult flatview_write(FlatView *fv, hwaddr addr, MemTxAttrs attrs, - const uint8_t *buf, int len); -static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, + const uint8_t *buf, hwaddr len); +static bool flatview_access_valid(FlatView *fv, hwaddr addr, hwaddr len, bool is_write, MemTxAttrs attrs); static MemTxResult subpage_read(void *opaque, hwaddr addr, uint64_t *data, @@ -3115,10 +3132,10 @@ MemoryRegion *get_system_io(void) /* physical memory access (slow version, mainly for debug) */ #if defined(CONFIG_USER_ONLY) int cpu_memory_rw_debug(CPUState *cpu, target_ulong addr, - uint8_t *buf, int len, int is_write) + uint8_t *buf, target_ulong len, int is_write) { - int l, flags; - target_ulong page; + int flags; + target_ulong l, page; void * p; while (len > 0) { @@ -3177,6 +3194,19 @@ static void invalidate_and_set_dirty(MemoryRegion *mr, hwaddr addr, cpu_physical_memory_set_dirty_range(addr, length, dirty_log_mask); } +void memory_region_flush_rom_device(MemoryRegion *mr, hwaddr addr, hwaddr size) +{ + /* + * In principle this function would work on other memory region types too, + * but the ROM device use case is the only one where this operation is + * necessary. Other memory regions should use the + * address_space_read/write() APIs. + */ + assert(memory_region_is_romd(mr)); + + invalidate_and_set_dirty(mr, addr, size); +} + static int memory_access_size(MemoryRegion *mr, unsigned l, hwaddr addr) { unsigned access_size_max = mr->ops->valid.max_access_size; @@ -3231,7 +3261,7 @@ static bool prepare_mmio_access(MemoryRegion *mr) static MemTxResult flatview_write_continue(FlatView *fv, hwaddr addr, MemTxAttrs attrs, const uint8_t *buf, - int len, hwaddr addr1, + hwaddr len, hwaddr addr1, hwaddr l, MemoryRegion *mr) { uint8_t *ptr; @@ -3276,7 +3306,7 @@ static MemTxResult flatview_write_continue(FlatView *fv, hwaddr addr, /* Called from RCU critical section. */ static MemTxResult flatview_write(FlatView *fv, hwaddr addr, MemTxAttrs attrs, - const uint8_t *buf, int len) + const uint8_t *buf, hwaddr len) { hwaddr l; hwaddr addr1; @@ -3294,7 +3324,7 @@ static MemTxResult flatview_write(FlatView *fv, hwaddr addr, MemTxAttrs attrs, /* Called within RCU critical section. */ MemTxResult flatview_read_continue(FlatView *fv, hwaddr addr, MemTxAttrs attrs, uint8_t *buf, - int len, hwaddr addr1, hwaddr l, + hwaddr len, hwaddr addr1, hwaddr l, MemoryRegion *mr) { uint8_t *ptr; @@ -3337,7 +3367,7 @@ MemTxResult flatview_read_continue(FlatView *fv, hwaddr addr, /* Called from RCU critical section. */ static MemTxResult flatview_read(FlatView *fv, hwaddr addr, - MemTxAttrs attrs, uint8_t *buf, int len) + MemTxAttrs attrs, uint8_t *buf, hwaddr len) { hwaddr l; hwaddr addr1; @@ -3350,7 +3380,7 @@ static MemTxResult flatview_read(FlatView *fv, hwaddr addr, } MemTxResult address_space_read_full(AddressSpace *as, hwaddr addr, - MemTxAttrs attrs, uint8_t *buf, int len) + MemTxAttrs attrs, uint8_t *buf, hwaddr len) { MemTxResult result = MEMTX_OK; FlatView *fv; @@ -3367,7 +3397,7 @@ MemTxResult address_space_read_full(AddressSpace *as, hwaddr addr, MemTxResult address_space_write(AddressSpace *as, hwaddr addr, MemTxAttrs attrs, - const uint8_t *buf, int len) + const uint8_t *buf, hwaddr len) { MemTxResult result = MEMTX_OK; FlatView *fv; @@ -3383,7 +3413,7 @@ MemTxResult address_space_write(AddressSpace *as, hwaddr addr, } MemTxResult address_space_rw(AddressSpace *as, hwaddr addr, MemTxAttrs attrs, - uint8_t *buf, int len, bool is_write) + uint8_t *buf, hwaddr len, bool is_write) { if (is_write) { return address_space_write(as, addr, attrs, buf, len); @@ -3393,7 +3423,7 @@ MemTxResult address_space_rw(AddressSpace *as, hwaddr addr, MemTxAttrs attrs, } void cpu_physical_memory_rw(hwaddr addr, uint8_t *buf, - int len, int is_write) + hwaddr len, int is_write) { address_space_rw(&address_space_memory, addr, MEMTXATTRS_UNSPECIFIED, buf, len, is_write); @@ -3404,8 +3434,12 @@ enum write_rom_type { FLUSH_CACHE, }; -static inline void cpu_physical_memory_write_rom_internal(AddressSpace *as, - hwaddr addr, const uint8_t *buf, int len, enum write_rom_type type) +static inline MemTxResult address_space_write_rom_internal(AddressSpace *as, + hwaddr addr, + MemTxAttrs attrs, + const uint8_t *buf, + hwaddr len, + enum write_rom_type type) { hwaddr l; uint8_t *ptr; @@ -3415,8 +3449,7 @@ static inline void cpu_physical_memory_write_rom_internal(AddressSpace *as, rcu_read_lock(); while (len > 0) { l = len; - mr = address_space_translate(as, addr, &addr1, &l, true, - MEMTXATTRS_UNSPECIFIED); + mr = address_space_translate(as, addr, &addr1, &l, true, attrs); if (!(memory_region_is_ram(mr) || memory_region_is_romd(mr))) { @@ -3439,16 +3472,19 @@ static inline void cpu_physical_memory_write_rom_internal(AddressSpace *as, addr += l; } rcu_read_unlock(); + return MEMTX_OK; } /* used for ROM loading : can write in RAM and ROM */ -void cpu_physical_memory_write_rom(AddressSpace *as, hwaddr addr, - const uint8_t *buf, int len) +MemTxResult address_space_write_rom(AddressSpace *as, hwaddr addr, + MemTxAttrs attrs, + const uint8_t *buf, hwaddr len) { - cpu_physical_memory_write_rom_internal(as, addr, buf, len, WRITE_DATA); + return address_space_write_rom_internal(as, addr, attrs, + buf, len, WRITE_DATA); } -void cpu_flush_icache_range(hwaddr start, int len) +void cpu_flush_icache_range(hwaddr start, hwaddr len) { /* * This function should do the same thing as an icache flush that was @@ -3460,8 +3496,9 @@ void cpu_flush_icache_range(hwaddr start, int len) return; } - cpu_physical_memory_write_rom_internal(&address_space_memory, - start, NULL, len, FLUSH_CACHE); + address_space_write_rom_internal(&address_space_memory, + start, MEMTXATTRS_UNSPECIFIED, + NULL, len, FLUSH_CACHE); } typedef struct { @@ -3480,7 +3517,7 @@ typedef struct MapClient { } MapClient; QemuMutex map_client_list_lock; -static QLIST_HEAD(map_client_list, MapClient) map_client_list +static QLIST_HEAD(, MapClient) map_client_list = QLIST_HEAD_INITIALIZER(map_client_list); static void cpu_unregister_map_client_do(MapClient *client) @@ -3550,7 +3587,7 @@ static void cpu_notify_map_clients(void) qemu_mutex_unlock(&map_client_list_lock); } -static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, +static bool flatview_access_valid(FlatView *fv, hwaddr addr, hwaddr len, bool is_write, MemTxAttrs attrs) { MemoryRegion *mr; @@ -3573,7 +3610,7 @@ static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, } bool address_space_access_valid(AddressSpace *as, hwaddr addr, - int len, bool is_write, + hwaddr len, bool is_write, MemTxAttrs attrs) { FlatView *fv; @@ -3826,7 +3863,7 @@ static inline MemoryRegion *address_space_translate_cached( */ void address_space_read_cached_slow(MemoryRegionCache *cache, hwaddr addr, - void *buf, int len) + void *buf, hwaddr len) { hwaddr addr1, l; MemoryRegion *mr; @@ -3844,7 +3881,7 @@ address_space_read_cached_slow(MemoryRegionCache *cache, hwaddr addr, */ void address_space_write_cached_slow(MemoryRegionCache *cache, hwaddr addr, - const void *buf, int len) + const void *buf, hwaddr len) { hwaddr addr1, l; MemoryRegion *mr; @@ -3867,11 +3904,10 @@ address_space_write_cached_slow(MemoryRegionCache *cache, hwaddr addr, /* virtual memory access for debug (includes writing to ROM) */ int cpu_memory_rw_debug(CPUState *cpu, target_ulong addr, - uint8_t *buf, int len, int is_write) + uint8_t *buf, target_ulong len, int is_write) { - int l; hwaddr phys_addr; - target_ulong page; + target_ulong l, page; cpu_synchronize_state(cpu); while (len > 0) { @@ -3889,12 +3925,11 @@ int cpu_memory_rw_debug(CPUState *cpu, target_ulong addr, l = len; phys_addr += (addr & ~TARGET_PAGE_MASK); if (is_write) { - cpu_physical_memory_write_rom(cpu->cpu_ases[asidx].as, - phys_addr, buf, l); + address_space_write_rom(cpu->cpu_ases[asidx].as, phys_addr, + attrs, buf, l); } else { address_space_rw(cpu->cpu_ases[asidx].as, phys_addr, - MEMTXATTRS_UNSPECIFIED, - buf, l, 0); + attrs, buf, l, 0); } len -= l; buf += l; @@ -3923,11 +3958,6 @@ int qemu_target_page_bits_min(void) } #endif -/* - * A helper function for the _utterly broken_ virtio device model to find out if - * it's running on a big endian machine. Don't do this at home kids! - */ -bool target_words_bigendian(void); bool target_words_bigendian(void) { #if defined(TARGET_WORDS_BIGENDIAN) @@ -3961,28 +3991,7 @@ int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque) rcu_read_lock(); RAMBLOCK_FOREACH(block) { - ret = func(block->idstr, block->host, block->offset, - block->used_length, opaque); - if (ret) { - break; - } - } - rcu_read_unlock(); - return ret; -} - -int qemu_ram_foreach_migratable_block(RAMBlockIterFunc func, void *opaque) -{ - RAMBlock *block; - int ret = 0; - - rcu_read_lock(); - RAMBLOCK_FOREACH(block) { - if (!qemu_ram_is_migratable(block)) { - continue; - } - ret = func(block->idstr, block->host, block->offset, - block->used_length, opaque); + ret = func(block, opaque); if (ret) { break; } @@ -4086,6 +4095,11 @@ err: return ret; } +bool ramblock_is_pmem(RAMBlock *rb) +{ + return rb->flags & RAM_PMEM; +} + #endif void page_size_init(void)