diff options
Diffstat (limited to 'system')
| -rw-r--r-- | system/cpus.c | 8 | ||||
| -rw-r--r-- | system/main.c | 13 | ||||
| -rw-r--r-- | system/memory.c | 56 | ||||
| -rw-r--r-- | system/meson.build | 3 | ||||
| -rw-r--r-- | system/physmem.c | 90 | ||||
| -rw-r--r-- | system/ram-block-attributes.c | 444 | ||||
| -rw-r--r-- | system/runstate.c | 100 | ||||
| -rw-r--r-- | system/trace-events | 3 | ||||
| -rw-r--r-- | system/vl.c | 12 |
9 files changed, 645 insertions, 84 deletions
diff --git a/system/cpus.c b/system/cpus.c index 2cc5f88..d16b0df 100644 --- a/system/cpus.c +++ b/system/cpus.c @@ -299,14 +299,18 @@ static int do_vm_stop(RunState state, bool send_stop) if (oldstate == RUN_STATE_RUNNING) { pause_all_vcpus(); } - vm_state_notify(0, state); + ret = vm_state_notify(0, state); if (send_stop) { qapi_event_send_stop(); } } bdrv_drain_all(); - ret = bdrv_flush_all(); + /* + * Even if vm_state_notify() return failure, + * it would be better to flush as before. + */ + ret |= bdrv_flush_all(); trace_vm_stop_flush_all(ret); return ret; diff --git a/system/main.c b/system/main.c index 1c02206..b8f7157 100644 --- a/system/main.c +++ b/system/main.c @@ -69,8 +69,21 @@ int (*qemu_main)(void) = os_darwin_cfrunloop_main; int main(int argc, char **argv) { qemu_init(argc, argv); + + /* + * qemu_init acquires the BQL and replay mutex lock. BQL is acquired when + * initializing cpus, to block associated threads until initialization is + * complete. Replay_mutex lock is acquired on initialization, because it + * must be held when configuring icount_mode. + * + * On MacOS, qemu main event loop runs in a background thread, as main + * thread must be reserved for UI. Thus, we need to transfer lock ownership, + * and the simplest way to do that is to release them, and reacquire them + * from qemu_default_main. + */ bql_unlock(); replay_mutex_unlock(); + if (qemu_main) { QemuThread main_loop_thread; qemu_thread_create(&main_loop_thread, "qemu_main", diff --git a/system/memory.c b/system/memory.c index 71434e7..76b44b8 100644 --- a/system/memory.c +++ b/system/memory.c @@ -1627,7 +1627,7 @@ bool memory_region_init_resizeable_ram(MemoryRegion *mr, return true; } -#ifdef CONFIG_POSIX +#if defined(CONFIG_POSIX) && !defined(EMSCRIPTEN) bool memory_region_init_ram_from_file(MemoryRegion *mr, Object *owner, const char *name, @@ -2106,12 +2106,16 @@ RamDiscardManager *memory_region_get_ram_discard_manager(MemoryRegion *mr) return mr->rdm; } -void memory_region_set_ram_discard_manager(MemoryRegion *mr, - RamDiscardManager *rdm) +int memory_region_set_ram_discard_manager(MemoryRegion *mr, + RamDiscardManager *rdm) { g_assert(memory_region_is_ram(mr)); - g_assert(!rdm || !mr->rdm); + if (mr->rdm && rdm) { + return -EBUSY; + } + mr->rdm = rdm; + return 0; } uint64_t ram_discard_manager_get_min_granularity(const RamDiscardManager *rdm, @@ -2134,7 +2138,7 @@ bool ram_discard_manager_is_populated(const RamDiscardManager *rdm, int ram_discard_manager_replay_populated(const RamDiscardManager *rdm, MemoryRegionSection *section, - ReplayRamPopulate replay_fn, + ReplayRamDiscardState replay_fn, void *opaque) { RamDiscardManagerClass *rdmc = RAM_DISCARD_MANAGER_GET_CLASS(rdm); @@ -2143,15 +2147,15 @@ int ram_discard_manager_replay_populated(const RamDiscardManager *rdm, return rdmc->replay_populated(rdm, section, replay_fn, opaque); } -void ram_discard_manager_replay_discarded(const RamDiscardManager *rdm, - MemoryRegionSection *section, - ReplayRamDiscard replay_fn, - void *opaque) +int ram_discard_manager_replay_discarded(const RamDiscardManager *rdm, + MemoryRegionSection *section, + ReplayRamDiscardState replay_fn, + void *opaque) { RamDiscardManagerClass *rdmc = RAM_DISCARD_MANAGER_GET_CLASS(rdm); g_assert(rdmc->replay_discarded); - rdmc->replay_discarded(rdm, section, replay_fn, opaque); + return rdmc->replay_discarded(rdm, section, replay_fn, opaque); } void ram_discard_manager_register_listener(RamDiscardManager *rdm, @@ -2174,18 +2178,14 @@ void ram_discard_manager_unregister_listener(RamDiscardManager *rdm, } /* Called with rcu_read_lock held. */ -bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr, - ram_addr_t *ram_addr, bool *read_only, - bool *mr_has_discard_manager, Error **errp) +MemoryRegion *memory_translate_iotlb(IOMMUTLBEntry *iotlb, hwaddr *xlat_p, + Error **errp) { MemoryRegion *mr; hwaddr xlat; hwaddr len = iotlb->addr_mask + 1; bool writable = iotlb->perm & IOMMU_WO; - if (mr_has_discard_manager) { - *mr_has_discard_manager = false; - } /* * The IOMMU TLB entry we have just covers translation through * this IOMMU to its immediate target. We need to translate @@ -2195,7 +2195,7 @@ bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr, &xlat, &len, writable, MEMTXATTRS_UNSPECIFIED); if (!memory_region_is_ram(mr)) { error_setg(errp, "iommu map to non memory area %" HWADDR_PRIx "", xlat); - return false; + return NULL; } else if (memory_region_has_ram_discard_manager(mr)) { RamDiscardManager *rdm = memory_region_get_ram_discard_manager(mr); MemoryRegionSection tmp = { @@ -2203,9 +2203,6 @@ bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr, .offset_within_region = xlat, .size = int128_make64(len), }; - if (mr_has_discard_manager) { - *mr_has_discard_manager = true; - } /* * Malicious VMs can map memory into the IOMMU, which is expected * to remain discarded. vfio will pin all pages, populating memory. @@ -2216,7 +2213,7 @@ bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr, error_setg(errp, "iommu map to discarded memory (e.g., unplugged" " via virtio-mem): %" HWADDR_PRIx "", iotlb->translated_addr); - return false; + return NULL; } } @@ -2226,22 +2223,11 @@ bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr, */ if (len & iotlb->addr_mask) { error_setg(errp, "iommu has granularity incompatible with target AS"); - return false; - } - - if (vaddr) { - *vaddr = memory_region_get_ram_ptr(mr) + xlat; - } - - if (ram_addr) { - *ram_addr = memory_region_get_ram_addr(mr) + xlat; - } - - if (read_only) { - *read_only = !writable || mr->readonly; + return NULL; } - return true; + *xlat_p = xlat; + return mr; } void memory_region_set_log(MemoryRegion *mr, bool log, unsigned client) diff --git a/system/meson.build b/system/meson.build index c2f0082..6d21ff9 100644 --- a/system/meson.build +++ b/system/meson.build @@ -7,7 +7,7 @@ system_ss.add(files( 'vl.c', ), sdl, libpmem, libdaxctl) -libsystem_ss.add(files( +system_ss.add(files( 'balloon.c', 'bootdevice.c', 'cpus.c', @@ -17,6 +17,7 @@ libsystem_ss.add(files( 'dma-helpers.c', 'globals.c', 'ioport.c', + 'ram-block-attributes.c', 'memory_mapping.c', 'memory.c', 'physmem.c', diff --git a/system/physmem.c b/system/physmem.c index 16cf557..ff0ca40 100644 --- a/system/physmem.c +++ b/system/physmem.c @@ -29,9 +29,9 @@ #ifdef CONFIG_TCG #include "accel/tcg/cpu-ops.h" +#include "accel/tcg/iommu.h" #endif /* CONFIG_TCG */ -#include "exec/exec-all.h" #include "exec/cputlb.h" #include "exec/page-protection.h" #include "exec/target_page.h" @@ -587,6 +587,8 @@ MemoryRegion *flatview_translate(FlatView *fv, hwaddr addr, hwaddr *xlat, return mr; } +#ifdef CONFIG_TCG + typedef struct TCGIOMMUNotifier { IOMMUNotifier n; MemoryRegion *mr; @@ -746,6 +748,33 @@ translate_fail: return &d->map.sections[PHYS_SECTION_UNASSIGNED]; } +MemoryRegionSection *iotlb_to_section(CPUState *cpu, + hwaddr index, MemTxAttrs attrs) +{ + int asidx = cpu_asidx_from_attrs(cpu, attrs); + CPUAddressSpace *cpuas = &cpu->cpu_ases[asidx]; + AddressSpaceDispatch *d = cpuas->memory_dispatch; + int section_index = index & ~TARGET_PAGE_MASK; + MemoryRegionSection *ret; + + assert(section_index < d->map.sections_nb); + ret = d->map.sections + section_index; + assert(ret->mr); + assert(ret->mr->ops); + + return ret; +} + +/* Called from RCU critical section */ +hwaddr memory_region_section_get_iotlb(CPUState *cpu, + MemoryRegionSection *section) +{ + AddressSpaceDispatch *d = flatview_to_dispatch(section->fv); + return section - d->map.sections; +} + +#endif /* CONFIG_TCG */ + void cpu_address_space_init(CPUState *cpu, int asidx, const char *prefix, MemoryRegion *mr) { @@ -1002,14 +1031,6 @@ bool cpu_physical_memory_snapshot_get_dirty(DirtyBitmapSnapshot *snap, return false; } -/* Called from RCU critical section */ -hwaddr memory_region_section_get_iotlb(CPUState *cpu, - MemoryRegionSection *section) -{ - AddressSpaceDispatch *d = flatview_to_dispatch(section->fv); - return section - d->map.sections; -} - static int subpage_register(subpage_t *mmio, uint32_t start, uint32_t end, uint16_t section); static subpage_t *subpage_init(FlatView *fv, hwaddr base); @@ -1243,7 +1264,7 @@ long qemu_maxrampagesize(void) return pagesize; } -#ifdef CONFIG_POSIX +#if defined(CONFIG_POSIX) && !defined(EMSCRIPTEN) static int64_t get_file_size(int fd) { int64_t size; @@ -1895,7 +1916,7 @@ static void ram_block_add(RAMBlock *new_block, Error **errp) } assert(new_block->guest_memfd < 0); - ret = ram_block_discard_require(true); + ret = ram_block_coordinated_discard_require(true); if (ret < 0) { error_setg_errno(errp, -ret, "cannot set up private guest memory: discard currently blocked"); @@ -1911,6 +1932,24 @@ static void ram_block_add(RAMBlock *new_block, Error **errp) } /* + * The attribute bitmap of the RamBlockAttributes is default to + * discarded, which mimics the behavior of kvm_set_phys_mem() when it + * calls kvm_set_memory_attributes_private(). This leads to a brief + * period of inconsistency between the creation of the RAMBlock and its + * mapping into the physical address space. However, this is not + * problematic, as no users rely on the attribute status to perform + * any actions during this interval. + */ + new_block->attributes = ram_block_attributes_create(new_block); + if (!new_block->attributes) { + error_setg(errp, "Failed to create ram block attribute"); + close(new_block->guest_memfd); + ram_block_coordinated_discard_require(false); + qemu_mutex_unlock_ramlist(); + goto out_free; + } + + /* * Add a specific guest_memfd blocker if a generic one would not be * added by ram_block_add_cpr_blocker. */ @@ -1978,7 +2017,7 @@ out_free: } } -#ifdef CONFIG_POSIX +#if defined(CONFIG_POSIX) && !defined(EMSCRIPTEN) RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, ram_addr_t max_size, qemu_ram_resize_cb resized, MemoryRegion *mr, uint32_t ram_flags, int fd, off_t offset, @@ -2158,7 +2197,8 @@ RAMBlock *qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size, assert(!host ^ (ram_flags & RAM_PREALLOC)); assert(max_size >= size); -#ifdef CONFIG_POSIX /* ignore RAM_SHARED for Windows */ + /* ignore RAM_SHARED for Windows and emscripten*/ +#if defined(CONFIG_POSIX) && !defined(EMSCRIPTEN) if (!host) { if (!share_flags && current_machine->aux_ram_share) { ram_flags |= RAM_SHARED; @@ -2255,7 +2295,7 @@ static void reclaim_ramblock(RAMBlock *block) ; } else if (xen_enabled()) { xen_invalidate_map_cache_entry(block->host); -#ifndef _WIN32 +#if !defined(_WIN32) && !defined(EMSCRIPTEN) } else if (block->fd >= 0) { qemu_ram_munmap(block->fd, block->host, block->max_length); close(block->fd); @@ -2265,8 +2305,9 @@ static void reclaim_ramblock(RAMBlock *block) } if (block->guest_memfd >= 0) { + ram_block_attributes_destroy(block->attributes); close(block->guest_memfd); - ram_block_discard_require(false); + ram_block_coordinated_discard_require(false); } g_free(block); @@ -2669,23 +2710,6 @@ static uint16_t dummy_section(PhysPageMap *map, FlatView *fv, MemoryRegion *mr) return phys_section_add(map, §ion); } -MemoryRegionSection *iotlb_to_section(CPUState *cpu, - hwaddr index, MemTxAttrs attrs) -{ - int asidx = cpu_asidx_from_attrs(cpu, attrs); - CPUAddressSpace *cpuas = &cpu->cpu_ases[asidx]; - AddressSpaceDispatch *d = cpuas->memory_dispatch; - int section_index = index & ~TARGET_PAGE_MASK; - MemoryRegionSection *ret; - - assert(section_index < d->map.sections_nb); - ret = d->map.sections + section_index; - assert(ret->mr); - assert(ret->mr->ops); - - return ret; -} - static void io_mem_init(void) { memory_region_init_io(&io_mem_unassigned, NULL, &unassigned_mem_ops, NULL, @@ -2830,7 +2854,7 @@ static void invalidate_and_set_dirty(MemoryRegion *mr, hwaddr addr, } if (dirty_log_mask & (1 << DIRTY_MEMORY_CODE)) { assert(tcg_enabled()); - tb_invalidate_phys_range(addr, addr + length - 1); + tb_invalidate_phys_range(NULL, addr, addr + length - 1); dirty_log_mask &= ~(1 << DIRTY_MEMORY_CODE); } cpu_physical_memory_set_dirty_range(addr, length, dirty_log_mask); diff --git a/system/ram-block-attributes.c b/system/ram-block-attributes.c new file mode 100644 index 0000000..68e8a02 --- /dev/null +++ b/system/ram-block-attributes.c @@ -0,0 +1,444 @@ +/* + * QEMU ram block attributes + * + * Copyright Intel + * + * Author: + * Chenyi Qiang <chenyi.qiang@intel.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu/error-report.h" +#include "system/ramblock.h" +#include "trace.h" + +OBJECT_DEFINE_SIMPLE_TYPE_WITH_INTERFACES(RamBlockAttributes, + ram_block_attributes, + RAM_BLOCK_ATTRIBUTES, + OBJECT, + { TYPE_RAM_DISCARD_MANAGER }, + { }) + +static size_t +ram_block_attributes_get_block_size(const RamBlockAttributes *attr) +{ + /* + * Because page conversion could be manipulated in the size of at least 4K + * or 4K aligned, Use the host page size as the granularity to track the + * memory attribute. + */ + g_assert(attr && attr->ram_block); + g_assert(attr->ram_block->page_size == qemu_real_host_page_size()); + return attr->ram_block->page_size; +} + + +static bool +ram_block_attributes_rdm_is_populated(const RamDiscardManager *rdm, + const MemoryRegionSection *section) +{ + const RamBlockAttributes *attr = RAM_BLOCK_ATTRIBUTES(rdm); + const size_t block_size = ram_block_attributes_get_block_size(attr); + const uint64_t first_bit = section->offset_within_region / block_size; + const uint64_t last_bit = + first_bit + int128_get64(section->size) / block_size - 1; + unsigned long first_discarded_bit; + + first_discarded_bit = find_next_zero_bit(attr->bitmap, last_bit + 1, + first_bit); + return first_discarded_bit > last_bit; +} + +typedef int (*ram_block_attributes_section_cb)(MemoryRegionSection *s, + void *arg); + +static int +ram_block_attributes_notify_populate_cb(MemoryRegionSection *section, + void *arg) +{ + RamDiscardListener *rdl = arg; + + return rdl->notify_populate(rdl, section); +} + +static int +ram_block_attributes_notify_discard_cb(MemoryRegionSection *section, + void *arg) +{ + RamDiscardListener *rdl = arg; + + rdl->notify_discard(rdl, section); + return 0; +} + +static int +ram_block_attributes_for_each_populated_section(const RamBlockAttributes *attr, + MemoryRegionSection *section, + void *arg, + ram_block_attributes_section_cb cb) +{ + unsigned long first_bit, last_bit; + uint64_t offset, size; + const size_t block_size = ram_block_attributes_get_block_size(attr); + int ret = 0; + + first_bit = section->offset_within_region / block_size; + first_bit = find_next_bit(attr->bitmap, attr->bitmap_size, + first_bit); + + while (first_bit < attr->bitmap_size) { + MemoryRegionSection tmp = *section; + + offset = first_bit * block_size; + last_bit = find_next_zero_bit(attr->bitmap, attr->bitmap_size, + first_bit + 1) - 1; + size = (last_bit - first_bit + 1) * block_size; + + if (!memory_region_section_intersect_range(&tmp, offset, size)) { + break; + } + + ret = cb(&tmp, arg); + if (ret) { + error_report("%s: Failed to notify RAM discard listener: %s", + __func__, strerror(-ret)); + break; + } + + first_bit = find_next_bit(attr->bitmap, attr->bitmap_size, + last_bit + 2); + } + + return ret; +} + +static int +ram_block_attributes_for_each_discarded_section(const RamBlockAttributes *attr, + MemoryRegionSection *section, + void *arg, + ram_block_attributes_section_cb cb) +{ + unsigned long first_bit, last_bit; + uint64_t offset, size; + const size_t block_size = ram_block_attributes_get_block_size(attr); + int ret = 0; + + first_bit = section->offset_within_region / block_size; + first_bit = find_next_zero_bit(attr->bitmap, attr->bitmap_size, + first_bit); + + while (first_bit < attr->bitmap_size) { + MemoryRegionSection tmp = *section; + + offset = first_bit * block_size; + last_bit = find_next_bit(attr->bitmap, attr->bitmap_size, + first_bit + 1) - 1; + size = (last_bit - first_bit + 1) * block_size; + + if (!memory_region_section_intersect_range(&tmp, offset, size)) { + break; + } + + ret = cb(&tmp, arg); + if (ret) { + error_report("%s: Failed to notify RAM discard listener: %s", + __func__, strerror(-ret)); + break; + } + + first_bit = find_next_zero_bit(attr->bitmap, + attr->bitmap_size, + last_bit + 2); + } + + return ret; +} + +static uint64_t +ram_block_attributes_rdm_get_min_granularity(const RamDiscardManager *rdm, + const MemoryRegion *mr) +{ + const RamBlockAttributes *attr = RAM_BLOCK_ATTRIBUTES(rdm); + + g_assert(mr == attr->ram_block->mr); + return ram_block_attributes_get_block_size(attr); +} + +static void +ram_block_attributes_rdm_register_listener(RamDiscardManager *rdm, + RamDiscardListener *rdl, + MemoryRegionSection *section) +{ + RamBlockAttributes *attr = RAM_BLOCK_ATTRIBUTES(rdm); + int ret; + + g_assert(section->mr == attr->ram_block->mr); + rdl->section = memory_region_section_new_copy(section); + + QLIST_INSERT_HEAD(&attr->rdl_list, rdl, next); + + ret = ram_block_attributes_for_each_populated_section(attr, section, rdl, + ram_block_attributes_notify_populate_cb); + if (ret) { + error_report("%s: Failed to register RAM discard listener: %s", + __func__, strerror(-ret)); + exit(1); + } +} + +static void +ram_block_attributes_rdm_unregister_listener(RamDiscardManager *rdm, + RamDiscardListener *rdl) +{ + RamBlockAttributes *attr = RAM_BLOCK_ATTRIBUTES(rdm); + int ret; + + g_assert(rdl->section); + g_assert(rdl->section->mr == attr->ram_block->mr); + + if (rdl->double_discard_supported) { + rdl->notify_discard(rdl, rdl->section); + } else { + ret = ram_block_attributes_for_each_populated_section(attr, + rdl->section, rdl, ram_block_attributes_notify_discard_cb); + if (ret) { + error_report("%s: Failed to unregister RAM discard listener: %s", + __func__, strerror(-ret)); + exit(1); + } + } + + memory_region_section_free_copy(rdl->section); + rdl->section = NULL; + QLIST_REMOVE(rdl, next); +} + +typedef struct RamBlockAttributesReplayData { + ReplayRamDiscardState fn; + void *opaque; +} RamBlockAttributesReplayData; + +static int ram_block_attributes_rdm_replay_cb(MemoryRegionSection *section, + void *arg) +{ + RamBlockAttributesReplayData *data = arg; + + return data->fn(section, data->opaque); +} + +static int +ram_block_attributes_rdm_replay_populated(const RamDiscardManager *rdm, + MemoryRegionSection *section, + ReplayRamDiscardState replay_fn, + void *opaque) +{ + RamBlockAttributes *attr = RAM_BLOCK_ATTRIBUTES(rdm); + RamBlockAttributesReplayData data = { .fn = replay_fn, .opaque = opaque }; + + g_assert(section->mr == attr->ram_block->mr); + return ram_block_attributes_for_each_populated_section(attr, section, &data, + ram_block_attributes_rdm_replay_cb); +} + +static int +ram_block_attributes_rdm_replay_discarded(const RamDiscardManager *rdm, + MemoryRegionSection *section, + ReplayRamDiscardState replay_fn, + void *opaque) +{ + RamBlockAttributes *attr = RAM_BLOCK_ATTRIBUTES(rdm); + RamBlockAttributesReplayData data = { .fn = replay_fn, .opaque = opaque }; + + g_assert(section->mr == attr->ram_block->mr); + return ram_block_attributes_for_each_discarded_section(attr, section, &data, + ram_block_attributes_rdm_replay_cb); +} + +static bool +ram_block_attributes_is_valid_range(RamBlockAttributes *attr, uint64_t offset, + uint64_t size) +{ + MemoryRegion *mr = attr->ram_block->mr; + + g_assert(mr); + + uint64_t region_size = memory_region_size(mr); + const size_t block_size = ram_block_attributes_get_block_size(attr); + + if (!QEMU_IS_ALIGNED(offset, block_size) || + !QEMU_IS_ALIGNED(size, block_size)) { + return false; + } + if (offset + size <= offset) { + return false; + } + if (offset + size > region_size) { + return false; + } + return true; +} + +static void ram_block_attributes_notify_discard(RamBlockAttributes *attr, + uint64_t offset, + uint64_t size) +{ + RamDiscardListener *rdl; + + QLIST_FOREACH(rdl, &attr->rdl_list, next) { + MemoryRegionSection tmp = *rdl->section; + + if (!memory_region_section_intersect_range(&tmp, offset, size)) { + continue; + } + rdl->notify_discard(rdl, &tmp); + } +} + +static int +ram_block_attributes_notify_populate(RamBlockAttributes *attr, + uint64_t offset, uint64_t size) +{ + RamDiscardListener *rdl; + int ret = 0; + + QLIST_FOREACH(rdl, &attr->rdl_list, next) { + MemoryRegionSection tmp = *rdl->section; + + if (!memory_region_section_intersect_range(&tmp, offset, size)) { + continue; + } + ret = rdl->notify_populate(rdl, &tmp); + if (ret) { + break; + } + } + + return ret; +} + +int ram_block_attributes_state_change(RamBlockAttributes *attr, + uint64_t offset, uint64_t size, + bool to_discard) +{ + const size_t block_size = ram_block_attributes_get_block_size(attr); + const unsigned long first_bit = offset / block_size; + const unsigned long nbits = size / block_size; + const unsigned long last_bit = first_bit + nbits - 1; + const bool is_discarded = find_next_bit(attr->bitmap, attr->bitmap_size, + first_bit) > last_bit; + const bool is_populated = find_next_zero_bit(attr->bitmap, + attr->bitmap_size, first_bit) > last_bit; + unsigned long bit; + int ret = 0; + + if (!ram_block_attributes_is_valid_range(attr, offset, size)) { + error_report("%s, invalid range: offset 0x%" PRIx64 ", size " + "0x%" PRIx64, __func__, offset, size); + return -EINVAL; + } + + trace_ram_block_attributes_state_change(offset, size, + is_discarded ? "discarded" : + is_populated ? "populated" : + "mixture", + to_discard ? "discarded" : + "populated"); + if (to_discard) { + if (is_discarded) { + /* Already private */ + } else if (is_populated) { + /* Completely shared */ + bitmap_clear(attr->bitmap, first_bit, nbits); + ram_block_attributes_notify_discard(attr, offset, size); + } else { + /* Unexpected mixture: process individual blocks */ + for (bit = first_bit; bit < first_bit + nbits; bit++) { + if (!test_bit(bit, attr->bitmap)) { + continue; + } + clear_bit(bit, attr->bitmap); + ram_block_attributes_notify_discard(attr, bit * block_size, + block_size); + } + } + } else { + if (is_populated) { + /* Already shared */ + } else if (is_discarded) { + /* Completely private */ + bitmap_set(attr->bitmap, first_bit, nbits); + ret = ram_block_attributes_notify_populate(attr, offset, size); + } else { + /* Unexpected mixture: process individual blocks */ + for (bit = first_bit; bit < first_bit + nbits; bit++) { + if (test_bit(bit, attr->bitmap)) { + continue; + } + set_bit(bit, attr->bitmap); + ret = ram_block_attributes_notify_populate(attr, + bit * block_size, + block_size); + if (ret) { + break; + } + } + } + } + + return ret; +} + +RamBlockAttributes *ram_block_attributes_create(RAMBlock *ram_block) +{ + const int block_size = qemu_real_host_page_size(); + RamBlockAttributes *attr; + MemoryRegion *mr = ram_block->mr; + + attr = RAM_BLOCK_ATTRIBUTES(object_new(TYPE_RAM_BLOCK_ATTRIBUTES)); + + attr->ram_block = ram_block; + if (memory_region_set_ram_discard_manager(mr, RAM_DISCARD_MANAGER(attr))) { + object_unref(OBJECT(attr)); + return NULL; + } + attr->bitmap_size = + ROUND_UP(int128_get64(mr->size), block_size) / block_size; + attr->bitmap = bitmap_new(attr->bitmap_size); + + return attr; +} + +void ram_block_attributes_destroy(RamBlockAttributes *attr) +{ + g_assert(attr); + + g_free(attr->bitmap); + memory_region_set_ram_discard_manager(attr->ram_block->mr, NULL); + object_unref(OBJECT(attr)); +} + +static void ram_block_attributes_init(Object *obj) +{ + RamBlockAttributes *attr = RAM_BLOCK_ATTRIBUTES(obj); + + QLIST_INIT(&attr->rdl_list); +} + +static void ram_block_attributes_finalize(Object *obj) +{ +} + +static void ram_block_attributes_class_init(ObjectClass *klass, + const void *data) +{ + RamDiscardManagerClass *rdmc = RAM_DISCARD_MANAGER_CLASS(klass); + + rdmc->get_min_granularity = ram_block_attributes_rdm_get_min_granularity; + rdmc->register_listener = ram_block_attributes_rdm_register_listener; + rdmc->unregister_listener = ram_block_attributes_rdm_unregister_listener; + rdmc->is_populated = ram_block_attributes_rdm_is_populated; + rdmc->replay_populated = ram_block_attributes_rdm_replay_populated; + rdmc->replay_discarded = ram_block_attributes_rdm_replay_discarded; +} diff --git a/system/runstate.c b/system/runstate.c index 272801d..38900c9 100644 --- a/system/runstate.c +++ b/system/runstate.c @@ -297,6 +297,7 @@ void qemu_system_vmstop_request(RunState state) struct VMChangeStateEntry { VMChangeStateHandler *cb; VMChangeStateHandler *prepare_cb; + VMChangeStateHandlerWithRet *cb_ret; void *opaque; QTAILQ_ENTRY(VMChangeStateEntry) entries; int priority; @@ -320,14 +321,15 @@ static QTAILQ_HEAD(, VMChangeStateEntry) vm_change_state_head = VMChangeStateEntry *qemu_add_vm_change_state_handler_prio( VMChangeStateHandler *cb, void *opaque, int priority) { - return qemu_add_vm_change_state_handler_prio_full(cb, NULL, opaque, - priority); + return qemu_add_vm_change_state_handler_prio_full(cb, NULL, NULL, + opaque, priority); } /** * qemu_add_vm_change_state_handler_prio_full: * @cb: the main callback to invoke * @prepare_cb: a callback to invoke before the main callback + * @cb_ret: the main callback to invoke with return value * @opaque: user data passed to the callbacks * @priority: low priorities execute first when the vm runs and the reverse is * true when the vm stops @@ -344,6 +346,7 @@ VMChangeStateEntry *qemu_add_vm_change_state_handler_prio( VMChangeStateEntry * qemu_add_vm_change_state_handler_prio_full(VMChangeStateHandler *cb, VMChangeStateHandler *prepare_cb, + VMChangeStateHandlerWithRet *cb_ret, void *opaque, int priority) { VMChangeStateEntry *e; @@ -352,6 +355,7 @@ qemu_add_vm_change_state_handler_prio_full(VMChangeStateHandler *cb, e = g_malloc0(sizeof(*e)); e->cb = cb; e->prepare_cb = prepare_cb; + e->cb_ret = cb_ret; e->opaque = opaque; e->priority = priority; @@ -379,9 +383,10 @@ void qemu_del_vm_change_state_handler(VMChangeStateEntry *e) g_free(e); } -void vm_state_notify(bool running, RunState state) +int vm_state_notify(bool running, RunState state) { VMChangeStateEntry *e, *next; + int ret = 0; trace_vm_state_notify(running, state, RunState_str(state)); @@ -393,7 +398,17 @@ void vm_state_notify(bool running, RunState state) } QTAILQ_FOREACH_SAFE(e, &vm_change_state_head, entries, next) { - e->cb(e->opaque, running, state); + if (e->cb) { + e->cb(e->opaque, running, state); + } else if (e->cb_ret) { + /* + * Here ignore the return value of cb_ret because + * we only care about the stopping the device during + * the VM live migration to indicate whether the + * connection between qemu and backend is normal. + */ + e->cb_ret(e->opaque, running, state); + } } } else { QTAILQ_FOREACH_REVERSE_SAFE(e, &vm_change_state_head, entries, next) { @@ -403,9 +418,19 @@ void vm_state_notify(bool running, RunState state) } QTAILQ_FOREACH_REVERSE_SAFE(e, &vm_change_state_head, entries, next) { - e->cb(e->opaque, running, state); + if (e->cb) { + e->cb(e->opaque, running, state); + } else if (e->cb_ret) { + /* + * We should execute all registered callbacks even if + * one of them returns failure, otherwise, some cleanup + * work of the device will be skipped. + */ + ret |= e->cb_ret(e->opaque, running, state); + } } } + return ret; } static ShutdownCause reset_requested; @@ -565,6 +590,58 @@ static void qemu_system_wakeup(void) } } +static char *tdx_parse_panic_message(char *message) +{ + bool printable = false; + char *buf = NULL; + int len = 0, i; + + /* + * Although message is defined as a json string, we shouldn't + * unconditionally treat it as is because the guest generated it and + * it's not necessarily trustable. + */ + if (message) { + /* The caller guarantees the NULL-terminated string. */ + len = strlen(message); + + printable = len > 0; + for (i = 0; i < len; i++) { + if (!(0x20 <= message[i] && message[i] <= 0x7e)) { + printable = false; + break; + } + } + } + + if (len == 0) { + buf = g_malloc(1); + buf[0] = '\0'; + } else { + if (!printable) { + /* 3 = length of "%02x " */ + buf = g_malloc(len * 3); + for (i = 0; i < len; i++) { + if (message[i] == '\0') { + break; + } else { + sprintf(buf + 3 * i, "%02x ", message[i]); + } + } + if (i > 0) { + /* replace the last ' '(space) to NULL */ + buf[i * 3 - 1] = '\0'; + } else { + buf[0] = '\0'; + } + } else { + buf = g_strdup(message); + } + } + + return buf; +} + void qemu_system_guest_panicked(GuestPanicInformation *info) { qemu_log_mask(LOG_GUEST_ERROR, "Guest crashed"); @@ -606,7 +683,20 @@ void qemu_system_guest_panicked(GuestPanicInformation *info) S390CrashReason_str(info->u.s390.reason), info->u.s390.psw_mask, info->u.s390.psw_addr); + } else if (info->type == GUEST_PANIC_INFORMATION_TYPE_TDX) { + char *message = tdx_parse_panic_message(info->u.tdx.message); + qemu_log_mask(LOG_GUEST_ERROR, + "\nTDX guest reports fatal error." + " error code: 0x%" PRIx32 " error message:\"%s\"\n", + info->u.tdx.error_code, message); + g_free(message); + if (info->u.tdx.gpa != -1ull) { + qemu_log_mask(LOG_GUEST_ERROR, "Additional error information " + "can be found at gpa page: 0x%" PRIx64 "\n", + info->u.tdx.gpa); + } } + qapi_free_GuestPanicInformation(info); } } diff --git a/system/trace-events b/system/trace-events index be12ebf..82856e4 100644 --- a/system/trace-events +++ b/system/trace-events @@ -52,3 +52,6 @@ dirtylimit_state_finalize(void) dirtylimit_throttle_pct(int cpu_index, uint64_t pct, int64_t time_us) "CPU[%d] throttle percent: %" PRIu64 ", throttle adjust time %"PRIi64 " us" dirtylimit_set_vcpu(int cpu_index, uint64_t quota) "CPU[%d] set dirty page rate limit %"PRIu64 dirtylimit_vcpu_execute(int cpu_index, int64_t sleep_time_us) "CPU[%d] sleep %"PRIi64 " us" + +# ram-block-attributes.c +ram_block_attributes_state_change(uint64_t offset, uint64_t size, const char *from, const char *to) "offset 0x%"PRIx64" size 0x%"PRIx64" from '%s' to '%s'" diff --git a/system/vl.c b/system/vl.c index 520956f..3b7057e 100644 --- a/system/vl.c +++ b/system/vl.c @@ -27,6 +27,7 @@ #include "qemu/datadir.h" #include "qemu/units.h" #include "qemu/module.h" +#include "qemu/target-info.h" #include "exec/cpu-common.h" #include "exec/page-vary.h" #include "hw/qdev-properties.h" @@ -767,7 +768,7 @@ static QemuOptsList qemu_smp_opts = { }, }; -#if defined(CONFIG_POSIX) +#if defined(CONFIG_POSIX) && !defined(EMSCRIPTEN) static QemuOptsList qemu_run_with_opts = { .name = "run-with", .head = QTAILQ_HEAD_INITIALIZER(qemu_run_with_opts.head), @@ -1191,10 +1192,7 @@ static int parse_fw_cfg(void *opaque, QemuOpts *opts, Error **errp) return -1; } } - /* For legacy, keep user files in a specific global order. */ - fw_cfg_set_order_override(fw_cfg, FW_CFG_ORDER_OVERRIDE_USER); fw_cfg_add_file(fw_cfg, name, buf, size); - fw_cfg_reset_order_override(fw_cfg); return 0; } @@ -1564,7 +1562,7 @@ static void machine_help_func(const QDict *qdict) GSList *el; const char *type = qdict_get_try_str(qdict, "type"); - machines = object_class_get_list(TYPE_MACHINE, false); + machines = object_class_get_list(target_machine_typename(), false); if (type) { ObjectClass *machine_class = OBJECT_CLASS(find_machine(type, machines)); if (machine_class) { @@ -2744,7 +2742,6 @@ static void qemu_create_cli_devices(void) } /* init generic devices */ - rom_set_order_override(FW_CFG_ORDER_OVERRIDE_DEVICE); qemu_opts_foreach(qemu_find_opts("device"), device_init_func, NULL, &error_fatal); QTAILQ_FOREACH(opt, &device_opts, next) { @@ -2755,7 +2752,6 @@ static void qemu_create_cli_devices(void) assert(ret_data == NULL); /* error_fatal aborts */ loc_pop(&opt->loc); } - rom_reset_order_override(); } static bool qemu_machine_creation_done(Error **errp) @@ -3678,7 +3674,7 @@ void qemu_init(int argc, char **argv) case QEMU_OPTION_nouserconfig: /* Nothing to be parsed here. Especially, do not error out below. */ break; -#if defined(CONFIG_POSIX) +#if defined(CONFIG_POSIX) && !defined(EMSCRIPTEN) case QEMU_OPTION_daemonize: os_set_daemonize(true); break; |