diff options
37 files changed, 924 insertions, 227 deletions
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml index 6a0d311cf4..1c46392b2f 100644 --- a/.gitlab-ci.yml +++ b/.gitlab-ci.yml @@ -27,9 +27,9 @@ include: - cd build - if test -n "$TARGETS"; then - ../configure --enable-werror --disable-docs ${LD_JOBS:+--meson=internal} $CONFIGURE_ARGS --target-list="$TARGETS" ; + ../configure --enable-werror --disable-docs ${LD_JOBS:+--meson=git} $CONFIGURE_ARGS --target-list="$TARGETS" ; else - ../configure --enable-werror --disable-docs ${LD_JOBS:+--meson=internal} $CONFIGURE_ARGS ; + ../configure --enable-werror --disable-docs ${LD_JOBS:+--meson=git} $CONFIGURE_ARGS ; fi || { cat config.log meson-logs/meson-log.txt && exit 1; } - if test -n "$LD_JOBS"; then @@ -48,9 +48,11 @@ Makefile: .git-submodule-status .PHONY: git-submodule-update git-submodule-update: +ifneq ($(GIT_SUBMODULES_ACTION),ignore) $(call quiet-command, \ (GIT="$(GIT)" "$(SRC_PATH)/scripts/git-submodule.sh" $(GIT_SUBMODULES_ACTION) $(GIT_SUBMODULES)), \ "GIT","$(GIT_SUBMODULES)") +endif # 0. ensure the build tree is okay diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index 4e0168e88b..c7ec538850 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -15,6 +15,7 @@ #include "qemu/osdep.h" #include <sys/ioctl.h> +#include <poll.h> #include <linux/kvm.h> @@ -78,6 +79,25 @@ struct KVMParkedVcpu { QLIST_ENTRY(KVMParkedVcpu) node; }; +enum KVMDirtyRingReaperState { + KVM_DIRTY_RING_REAPER_NONE = 0, + /* The reaper is sleeping */ + KVM_DIRTY_RING_REAPER_WAIT, + /* The reaper is reaping for dirty pages */ + KVM_DIRTY_RING_REAPER_REAPING, +}; + +/* + * KVM reaper instance, responsible for collecting the KVM dirty bits + * via the dirty ring. + */ +struct KVMDirtyRingReaper { + /* The reaper thread */ + QemuThread reaper_thr; + volatile uint64_t reaper_iteration; /* iteration number of reaper thr */ + volatile enum KVMDirtyRingReaperState reaper_state; /* reap thr state */ +}; + struct KVMState { AccelState parent_obj; @@ -126,6 +146,9 @@ struct KVMState KVMMemoryListener *ml; AddressSpace *as; } *as; + uint64_t kvm_dirty_ring_bytes; /* Size of the per-vcpu dirty ring */ + uint32_t kvm_dirty_ring_size; /* Number of dirty GFNs per ring */ + struct KVMDirtyRingReaper reaper; }; KVMState *kvm_state; @@ -172,8 +195,12 @@ typedef struct KVMResampleFd KVMResampleFd; static QLIST_HEAD(, KVMResampleFd) kvm_resample_fd_list = QLIST_HEAD_INITIALIZER(kvm_resample_fd_list); -#define kvm_slots_lock(kml) qemu_mutex_lock(&(kml)->slots_lock) -#define kvm_slots_unlock(kml) qemu_mutex_unlock(&(kml)->slots_lock) +static QemuMutex kml_slots_lock; + +#define kvm_slots_lock() qemu_mutex_lock(&kml_slots_lock) +#define kvm_slots_unlock() qemu_mutex_unlock(&kml_slots_lock) + +static void kvm_slot_init_dirty_bitmap(KVMSlot *mem); static inline void kvm_resample_fd_remove(int gsi) { @@ -239,9 +266,9 @@ bool kvm_has_free_slot(MachineState *ms) bool result; KVMMemoryListener *kml = &s->memory_listener; - kvm_slots_lock(kml); + kvm_slots_lock(); result = !!kvm_get_free_slot(kml); - kvm_slots_unlock(kml); + kvm_slots_unlock(); return result; } @@ -307,7 +334,7 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram, KVMMemoryListener *kml = &s->memory_listener; int i, ret = 0; - kvm_slots_lock(kml); + kvm_slots_lock(); for (i = 0; i < s->nr_slots; i++) { KVMSlot *mem = &kml->slots[i]; @@ -317,7 +344,7 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram, break; } } - kvm_slots_unlock(kml); + kvm_slots_unlock(); return ret; } @@ -383,6 +410,13 @@ static int do_kvm_destroy_vcpu(CPUState *cpu) goto err; } + if (cpu->kvm_dirty_gfns) { + ret = munmap(cpu->kvm_dirty_gfns, s->kvm_dirty_ring_size); + if (ret < 0) { + goto err; + } + } + vcpu = g_malloc0(sizeof(*vcpu)); vcpu->vcpu_id = kvm_arch_vcpu_id(cpu); vcpu->kvm_fd = cpu->kvm_fd; @@ -459,6 +493,19 @@ int kvm_init_vcpu(CPUState *cpu, Error **errp) (void *)cpu->kvm_run + s->coalesced_mmio * PAGE_SIZE; } + if (s->kvm_dirty_ring_size) { + /* Use MAP_SHARED to share pages with the kernel */ + cpu->kvm_dirty_gfns = mmap(NULL, s->kvm_dirty_ring_size, + PROT_READ | PROT_WRITE, MAP_SHARED, + cpu->kvm_fd, + PAGE_SIZE * KVM_DIRTY_LOG_PAGE_OFFSET); + if (cpu->kvm_dirty_gfns == MAP_FAILED) { + ret = -errno; + DPRINTF("mmap'ing vcpu dirty gfns failed: %d\n", ret); + goto err; + } + } + ret = kvm_arch_init_vcpu(cpu); if (ret < 0) { error_setg_errno(errp, -ret, @@ -498,6 +545,7 @@ static int kvm_slot_update_flags(KVMMemoryListener *kml, KVMSlot *mem, return 0; } + kvm_slot_init_dirty_bitmap(mem); return kvm_set_user_memory_region(kml, mem, false); } @@ -513,7 +561,7 @@ static int kvm_section_update_flags(KVMMemoryListener *kml, return 0; } - kvm_slots_lock(kml); + kvm_slots_lock(); while (size && !ret) { slot_size = MIN(kvm_max_slot_size, size); @@ -529,7 +577,7 @@ static int kvm_section_update_flags(KVMMemoryListener *kml, } out: - kvm_slots_unlock(kml); + kvm_slots_unlock(); return ret; } @@ -568,22 +616,28 @@ static void kvm_log_stop(MemoryListener *listener, } /* get kvm's dirty pages bitmap and update qemu's */ -static int kvm_get_dirty_pages_log_range(MemoryRegionSection *section, - unsigned long *bitmap) +static void kvm_slot_sync_dirty_pages(KVMSlot *slot) { - ram_addr_t start = section->offset_within_region + - memory_region_get_ram_addr(section->mr); - ram_addr_t pages = int128_get64(section->size) / qemu_real_host_page_size; + ram_addr_t start = slot->ram_start_offset; + ram_addr_t pages = slot->memory_size / qemu_real_host_page_size; - cpu_physical_memory_set_dirty_lebitmap(bitmap, start, pages); - return 0; + cpu_physical_memory_set_dirty_lebitmap(slot->dirty_bmap, start, pages); +} + +static void kvm_slot_reset_dirty_pages(KVMSlot *slot) +{ + memset(slot->dirty_bmap, 0, slot->dirty_bmap_size); } #define ALIGN(x, y) (((x)+(y)-1) & ~((y)-1)) /* Allocate the dirty bitmap for a slot */ -static void kvm_memslot_init_dirty_bitmap(KVMSlot *mem) +static void kvm_slot_init_dirty_bitmap(KVMSlot *mem) { + if (!(mem->flags & KVM_MEM_LOG_DIRTY_PAGES) || mem->dirty_bmap) { + return; + } + /* * XXX bad kernel interface alert * For dirty bitmap, kernel allocates array of size aligned to @@ -604,6 +658,196 @@ static void kvm_memslot_init_dirty_bitmap(KVMSlot *mem) hwaddr bitmap_size = ALIGN(mem->memory_size / qemu_real_host_page_size, /*HOST_LONG_BITS*/ 64) / 8; mem->dirty_bmap = g_malloc0(bitmap_size); + mem->dirty_bmap_size = bitmap_size; +} + +/* + * Sync dirty bitmap from kernel to KVMSlot.dirty_bmap, return true if + * succeeded, false otherwise + */ +static bool kvm_slot_get_dirty_log(KVMState *s, KVMSlot *slot) +{ + struct kvm_dirty_log d = {}; + int ret; + + d.dirty_bitmap = slot->dirty_bmap; + d.slot = slot->slot | (slot->as_id << 16); + ret = kvm_vm_ioctl(s, KVM_GET_DIRTY_LOG, &d); + + if (ret == -ENOENT) { + /* kernel does not have dirty bitmap in this slot */ + ret = 0; + } + if (ret) { + error_report_once("%s: KVM_GET_DIRTY_LOG failed with %d", + __func__, ret); + } + return ret == 0; +} + +/* Should be with all slots_lock held for the address spaces. */ +static void kvm_dirty_ring_mark_page(KVMState *s, uint32_t as_id, + uint32_t slot_id, uint64_t offset) +{ + KVMMemoryListener *kml; + KVMSlot *mem; + + if (as_id >= s->nr_as) { + return; + } + + kml = s->as[as_id].ml; + mem = &kml->slots[slot_id]; + + if (!mem->memory_size || offset >= + (mem->memory_size / qemu_real_host_page_size)) { + return; + } + + set_bit(offset, mem->dirty_bmap); +} + +static bool dirty_gfn_is_dirtied(struct kvm_dirty_gfn *gfn) +{ + return gfn->flags == KVM_DIRTY_GFN_F_DIRTY; +} + +static void dirty_gfn_set_collected(struct kvm_dirty_gfn *gfn) +{ + gfn->flags = KVM_DIRTY_GFN_F_RESET; +} + +/* + * Should be with all slots_lock held for the address spaces. It returns the + * dirty page we've collected on this dirty ring. + */ +static uint32_t kvm_dirty_ring_reap_one(KVMState *s, CPUState *cpu) +{ + struct kvm_dirty_gfn *dirty_gfns = cpu->kvm_dirty_gfns, *cur; + uint32_t ring_size = s->kvm_dirty_ring_size; + uint32_t count = 0, fetch = cpu->kvm_fetch_index; + + assert(dirty_gfns && ring_size); + trace_kvm_dirty_ring_reap_vcpu(cpu->cpu_index); + + while (true) { + cur = &dirty_gfns[fetch % ring_size]; + if (!dirty_gfn_is_dirtied(cur)) { + break; + } + kvm_dirty_ring_mark_page(s, cur->slot >> 16, cur->slot & 0xffff, + cur->offset); + dirty_gfn_set_collected(cur); + trace_kvm_dirty_ring_page(cpu->cpu_index, fetch, cur->offset); + fetch++; + count++; + } + cpu->kvm_fetch_index = fetch; + + return count; +} + +/* Must be with slots_lock held */ +static uint64_t kvm_dirty_ring_reap_locked(KVMState *s) +{ + int ret; + CPUState *cpu; + uint64_t total = 0; + int64_t stamp; + + stamp = get_clock(); + + CPU_FOREACH(cpu) { + total += kvm_dirty_ring_reap_one(s, cpu); + } + + if (total) { + ret = kvm_vm_ioctl(s, KVM_RESET_DIRTY_RINGS); + assert(ret == total); + } + + stamp = get_clock() - stamp; + + if (total) { + trace_kvm_dirty_ring_reap(total, stamp / 1000); + } + + return total; +} + +/* + * Currently for simplicity, we must hold BQL before calling this. We can + * consider to drop the BQL if we're clear with all the race conditions. + */ +static uint64_t kvm_dirty_ring_reap(KVMState *s) +{ + uint64_t total; + + /* + * We need to lock all kvm slots for all address spaces here, + * because: + * + * (1) We need to mark dirty for dirty bitmaps in multiple slots + * and for tons of pages, so it's better to take the lock here + * once rather than once per page. And more importantly, + * + * (2) We must _NOT_ publish dirty bits to the other threads + * (e.g., the migration thread) via the kvm memory slot dirty + * bitmaps before correctly re-protect those dirtied pages. + * Otherwise we can have potential risk of data corruption if + * the page data is read in the other thread before we do + * reset below. + */ + kvm_slots_lock(); + total = kvm_dirty_ring_reap_locked(s); + kvm_slots_unlock(); + + return total; +} + +static void do_kvm_cpu_synchronize_kick(CPUState *cpu, run_on_cpu_data arg) +{ + /* No need to do anything */ +} + +/* + * Kick all vcpus out in a synchronized way. When returned, we + * guarantee that every vcpu has been kicked and at least returned to + * userspace once. + */ +static void kvm_cpu_synchronize_kick_all(void) +{ + CPUState *cpu; + + CPU_FOREACH(cpu) { + run_on_cpu(cpu, do_kvm_cpu_synchronize_kick, RUN_ON_CPU_NULL); + } +} + +/* + * Flush all the existing dirty pages to the KVM slot buffers. When + * this call returns, we guarantee that all the touched dirty pages + * before calling this function have been put into the per-kvmslot + * dirty bitmap. + * + * This function must be called with BQL held. + */ +static void kvm_dirty_ring_flush(void) +{ + trace_kvm_dirty_ring_flush(0); + /* + * The function needs to be serialized. Since this function + * should always be with BQL held, serialization is guaranteed. + * However, let's be sure of it. + */ + assert(qemu_mutex_iothread_locked()); + /* + * First make sure to flush the hardware buffers by kicking all + * vcpus out in a synchronous way. + */ + kvm_cpu_synchronize_kick_all(); + kvm_dirty_ring_reap(kvm_state); + trace_kvm_dirty_ring_flush(1); } /** @@ -617,53 +861,28 @@ static void kvm_memslot_init_dirty_bitmap(KVMSlot *mem) * @kml: the KVM memory listener object * @section: the memory section to sync the dirty bitmap with */ -static int kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml, - MemoryRegionSection *section) +static void kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml, + MemoryRegionSection *section) { KVMState *s = kvm_state; - struct kvm_dirty_log d = {}; KVMSlot *mem; hwaddr start_addr, size; - hwaddr slot_size, slot_offset = 0; - int ret = 0; + hwaddr slot_size; size = kvm_align_section(section, &start_addr); while (size) { - MemoryRegionSection subsection = *section; - slot_size = MIN(kvm_max_slot_size, size); mem = kvm_lookup_matching_slot(kml, start_addr, slot_size); if (!mem) { /* We don't have a slot if we want to trap every access. */ - goto out; - } - - if (!mem->dirty_bmap) { - /* Allocate on the first log_sync, once and for all */ - kvm_memslot_init_dirty_bitmap(mem); + return; } - - d.dirty_bitmap = mem->dirty_bmap; - d.slot = mem->slot | (kml->as_id << 16); - ret = kvm_vm_ioctl(s, KVM_GET_DIRTY_LOG, &d); - if (ret == -ENOENT) { - /* kernel does not have dirty bitmap in this slot */ - ret = 0; - } else if (ret < 0) { - error_report("ioctl KVM_GET_DIRTY_LOG failed: %d", errno); - goto out; - } else { - subsection.offset_within_region += slot_offset; - subsection.size = int128_make64(slot_size); - kvm_get_dirty_pages_log_range(&subsection, d.dirty_bitmap); + if (kvm_slot_get_dirty_log(s, mem)) { + kvm_slot_sync_dirty_pages(mem); } - - slot_offset += slot_size; start_addr += slot_size; size -= slot_size; } -out: - return ret; } /* Alignment requirement for KVM_CLEAR_DIRTY_LOG - 64 pages */ @@ -810,7 +1029,7 @@ static int kvm_physical_log_clear(KVMMemoryListener *kml, return ret; } - kvm_slots_lock(kml); + kvm_slots_lock(); for (i = 0; i < s->nr_slots; i++) { mem = &kml->slots[i]; @@ -836,7 +1055,7 @@ static int kvm_physical_log_clear(KVMMemoryListener *kml, } } - kvm_slots_unlock(kml); + kvm_slots_unlock(); return ret; } @@ -1119,7 +1338,8 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, int err; MemoryRegion *mr = section->mr; bool writeable = !mr->readonly && !mr->rom_device; - hwaddr start_addr, size, slot_size; + hwaddr start_addr, size, slot_size, mr_offset; + ram_addr_t ram_start_offset; void *ram; if (!memory_region_is_ram(mr)) { @@ -1137,11 +1357,15 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, return; } - /* use aligned delta to align the ram address */ - ram = memory_region_get_ram_ptr(mr) + section->offset_within_region + - (start_addr - section->offset_within_address_space); + /* The offset of the kvmslot within the memory region */ + mr_offset = section->offset_within_region + start_addr - + section->offset_within_address_space; - kvm_slots_lock(kml); + /* use aligned delta to align the ram address and offset */ + ram = memory_region_get_ram_ptr(mr) + mr_offset; + ram_start_offset = memory_region_get_ram_addr(mr) + mr_offset; + + kvm_slots_lock(); if (!add) { do { @@ -1151,7 +1375,25 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, goto out; } if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { - kvm_physical_sync_dirty_bitmap(kml, section); + /* + * NOTE: We should be aware of the fact that here we're only + * doing a best effort to sync dirty bits. No matter whether + * we're using dirty log or dirty ring, we ignored two facts: + * + * (1) dirty bits can reside in hardware buffers (PML) + * + * (2) after we collected dirty bits here, pages can be dirtied + * again before we do the final KVM_SET_USER_MEMORY_REGION to + * remove the slot. + * + * Not easy. Let's cross the fingers until it's fixed. + */ + if (kvm_state->kvm_dirty_ring_size) { + kvm_dirty_ring_reap_locked(kvm_state); + } else { + kvm_slot_get_dirty_log(kvm_state, mem); + } + kvm_slot_sync_dirty_pages(mem); } /* unregister the slot */ @@ -1175,18 +1417,13 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, do { slot_size = MIN(kvm_max_slot_size, size); mem = kvm_alloc_slot(kml); + mem->as_id = kml->as_id; mem->memory_size = slot_size; mem->start_addr = start_addr; + mem->ram_start_offset = ram_start_offset; mem->ram = ram; mem->flags = kvm_mem_flags(mr); - - if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { - /* - * Reallocate the bmap; it means it doesn't disappear in - * middle of a migrate. - */ - kvm_memslot_init_dirty_bitmap(mem); - } + kvm_slot_init_dirty_bitmap(mem); err = kvm_set_user_memory_region(kml, mem, true); if (err) { fprintf(stderr, "%s: error registering slot: %s\n", __func__, @@ -1194,12 +1431,58 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, abort(); } start_addr += slot_size; + ram_start_offset += slot_size; ram += slot_size; size -= slot_size; } while (size); out: - kvm_slots_unlock(kml); + kvm_slots_unlock(); +} + +static void *kvm_dirty_ring_reaper_thread(void *data) +{ + KVMState *s = data; + struct KVMDirtyRingReaper *r = &s->reaper; + + rcu_register_thread(); + + trace_kvm_dirty_ring_reaper("init"); + + while (true) { + r->reaper_state = KVM_DIRTY_RING_REAPER_WAIT; + trace_kvm_dirty_ring_reaper("wait"); + /* + * TODO: provide a smarter timeout rather than a constant? + */ + sleep(1); + + trace_kvm_dirty_ring_reaper("wakeup"); + r->reaper_state = KVM_DIRTY_RING_REAPER_REAPING; + + qemu_mutex_lock_iothread(); + kvm_dirty_ring_reap(s); + qemu_mutex_unlock_iothread(); + + r->reaper_iteration++; + } + + trace_kvm_dirty_ring_reaper("exit"); + + rcu_unregister_thread(); + + return NULL; +} + +static int kvm_dirty_ring_reaper_init(KVMState *s) +{ + struct KVMDirtyRingReaper *r = &s->reaper; + + qemu_thread_create(&r->reaper_thr, "kvm-reaper", + kvm_dirty_ring_reaper_thread, + s, QEMU_THREAD_JOINABLE); + + return 0; } static void kvm_region_add(MemoryListener *listener, @@ -1224,14 +1507,40 @@ static void kvm_log_sync(MemoryListener *listener, MemoryRegionSection *section) { KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener); - int r; - kvm_slots_lock(kml); - r = kvm_physical_sync_dirty_bitmap(kml, section); - kvm_slots_unlock(kml); - if (r < 0) { - abort(); + kvm_slots_lock(); + kvm_physical_sync_dirty_bitmap(kml, section); + kvm_slots_unlock(); +} + +static void kvm_log_sync_global(MemoryListener *l) +{ + KVMMemoryListener *kml = container_of(l, KVMMemoryListener, listener); + KVMState *s = kvm_state; + KVMSlot *mem; + int i; + + /* Flush all kernel dirty addresses into KVMSlot dirty bitmap */ + kvm_dirty_ring_flush(); + + /* + * TODO: make this faster when nr_slots is big while there are + * only a few used slots (small VMs). + */ + kvm_slots_lock(); + for (i = 0; i < s->nr_slots; i++) { + mem = &kml->slots[i]; + if (mem->memory_size && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { + kvm_slot_sync_dirty_pages(mem); + /* + * This is not needed by KVM_GET_DIRTY_LOG because the + * ioctl will unconditionally overwrite the whole region. + * However kvm dirty ring has no such side effect. + */ + kvm_slot_reset_dirty_pages(mem); + } } + kvm_slots_unlock(); } static void kvm_log_clear(MemoryListener *listener, @@ -1328,7 +1637,6 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, { int i; - qemu_mutex_init(&kml->slots_lock); kml->slots = g_malloc0(s->nr_slots * sizeof(KVMSlot)); kml->as_id = as_id; @@ -1340,10 +1648,15 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, kml->listener.region_del = kvm_region_del; kml->listener.log_start = kvm_log_start; kml->listener.log_stop = kvm_log_stop; - kml->listener.log_sync = kvm_log_sync; - kml->listener.log_clear = kvm_log_clear; kml->listener.priority = 10; + if (s->kvm_dirty_ring_size) { + kml->listener.log_sync_global = kvm_log_sync_global; + } else { + kml->listener.log_sync = kvm_log_sync; + kml->listener.log_clear = kvm_log_clear; + } + memory_listener_register(&kml->listener, as); for (i = 0; i < s->nr_as; ++i) { @@ -2001,6 +2314,8 @@ static int kvm_init(MachineState *ms) int type = 0; uint64_t dirty_log_manual_caps; + qemu_mutex_init(&kml_slots_lock); + s = KVM_STATE(ms->accelerator); /* @@ -2017,7 +2332,6 @@ static int kvm_init(MachineState *ms) QTAILQ_INIT(&s->kvm_sw_breakpoints); #endif QLIST_INIT(&s->kvm_parked_vcpus); - s->vmfd = -1; s->fd = qemu_open_old("/dev/kvm", O_RDWR); if (s->fd == -1) { fprintf(stderr, "Could not access KVM kernel module: %m\n"); @@ -2125,20 +2439,70 @@ static int kvm_init(MachineState *ms) s->coalesced_pio = s->coalesced_mmio && kvm_check_extension(s, KVM_CAP_COALESCED_PIO); - dirty_log_manual_caps = - kvm_check_extension(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); - dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | - KVM_DIRTY_LOG_INITIALLY_SET); - s->manual_dirty_log_protect = dirty_log_manual_caps; - if (dirty_log_manual_caps) { - ret = kvm_vm_enable_cap(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, 0, - dirty_log_manual_caps); - if (ret) { - warn_report("Trying to enable capability %"PRIu64" of " - "KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 but failed. " - "Falling back to the legacy mode. ", - dirty_log_manual_caps); - s->manual_dirty_log_protect = 0; + /* + * Enable KVM dirty ring if supported, otherwise fall back to + * dirty logging mode + */ + if (s->kvm_dirty_ring_size > 0) { + uint64_t ring_bytes; + + ring_bytes = s->kvm_dirty_ring_size * sizeof(struct kvm_dirty_gfn); + + /* Read the max supported pages */ + ret = kvm_vm_check_extension(s, KVM_CAP_DIRTY_LOG_RING); + if (ret > 0) { + if (ring_bytes > ret) { + error_report("KVM dirty ring size %" PRIu32 " too big " + "(maximum is %ld). Please use a smaller value.", + s->kvm_dirty_ring_size, + (long)ret / sizeof(struct kvm_dirty_gfn)); + ret = -EINVAL; + goto err; + } + + ret = kvm_vm_enable_cap(s, KVM_CAP_DIRTY_LOG_RING, 0, ring_bytes); + if (ret) { + error_report("Enabling of KVM dirty ring failed: %s. " + "Suggested mininum value is 1024.", strerror(-ret)); + goto err; + } + + s->kvm_dirty_ring_bytes = ring_bytes; + } else { + warn_report("KVM dirty ring not available, using bitmap method"); + s->kvm_dirty_ring_size = 0; + } + } + + /* + * KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is not needed when dirty ring is + * enabled. More importantly, KVM_DIRTY_LOG_INITIALLY_SET will assume no + * page is wr-protected initially, which is against how kvm dirty ring is + * usage - kvm dirty ring requires all pages are wr-protected at the very + * beginning. Enabling this feature for dirty ring causes data corruption. + * + * TODO: Without KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 and kvm clear dirty log, + * we may expect a higher stall time when starting the migration. In the + * future we can enable KVM_CLEAR_DIRTY_LOG to work with dirty ring too: + * instead of clearing dirty bit, it can be a way to explicitly wr-protect + * guest pages. + */ + if (!s->kvm_dirty_ring_size) { + dirty_log_manual_caps = + kvm_check_extension(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); + s->manual_dirty_log_protect = dirty_log_manual_caps; + if (dirty_log_manual_caps) { + ret = kvm_vm_enable_cap(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, 0, + dirty_log_manual_caps); + if (ret) { + warn_report("Trying to enable capability %"PRIu64" of " + "KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 but failed. " + "Falling back to the legacy mode. ", + dirty_log_manual_caps); + s->manual_dirty_log_protect = 0; + } } } @@ -2224,6 +2588,14 @@ static int kvm_init(MachineState *ms) ret = ram_block_discard_disable(true); assert(!ret); } + + if (s->kvm_dirty_ring_size) { + ret = kvm_dirty_ring_reaper_init(s); + if (ret) { + goto err; + } + } + return 0; err: @@ -2536,6 +2908,17 @@ int kvm_cpu_exec(CPUState *cpu) case KVM_EXIT_INTERNAL_ERROR: ret = kvm_handle_internal_error(cpu, run); break; + case KVM_EXIT_DIRTY_RING_FULL: + /* + * We shouldn't continue if the dirty ring of this vcpu is + * still full. Got kicked by KVM_RESET_DIRTY_RINGS. + */ + trace_kvm_dirty_ring_full(cpu->cpu_index); + qemu_mutex_lock_iothread(); + kvm_dirty_ring_reap(kvm_state); + qemu_mutex_unlock_iothread(); + ret = 0; + break; case KVM_EXIT_SYSTEM_EVENT: switch (run->system_event.type) { case KVM_SYSTEM_EVENT_SHUTDOWN: @@ -3112,6 +3495,11 @@ static void kvm_set_kvm_shadow_mem(Object *obj, Visitor *v, KVMState *s = KVM_STATE(obj); int64_t value; + if (s->fd != -1) { + error_setg(errp, "Cannot set properties after the accelerator has been initialized"); + return; + } + if (!visit_type_int(v, name, &value, errp)) { return; } @@ -3126,6 +3514,11 @@ static void kvm_set_kernel_irqchip(Object *obj, Visitor *v, KVMState *s = KVM_STATE(obj); OnOffSplit mode; + if (s->fd != -1) { + error_setg(errp, "Cannot set properties after the accelerator has been initialized"); + return; + } + if (!visit_type_OnOffSplit(v, name, &mode, errp)) { return; } @@ -3168,13 +3561,53 @@ bool kvm_kernel_irqchip_split(void) return kvm_state->kernel_irqchip_split == ON_OFF_AUTO_ON; } +static void kvm_get_dirty_ring_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + KVMState *s = KVM_STATE(obj); + uint32_t value = s->kvm_dirty_ring_size; + + visit_type_uint32(v, name, &value, errp); +} + +static void kvm_set_dirty_ring_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + KVMState *s = KVM_STATE(obj); + Error *error = NULL; + uint32_t value; + + if (s->fd != -1) { + error_setg(errp, "Cannot set properties after the accelerator has been initialized"); + return; + } + + visit_type_uint32(v, name, &value, &error); + if (error) { + error_propagate(errp, error); + return; + } + if (value & (value - 1)) { + error_setg(errp, "dirty-ring-size must be a power of two."); + return; + } + + s->kvm_dirty_ring_size = value; +} + static void kvm_accel_instance_init(Object *obj) { KVMState *s = KVM_STATE(obj); + s->fd = -1; + s->vmfd = -1; s->kvm_shadow_mem = -1; s->kernel_irqchip_allowed = true; s->kernel_irqchip_split = ON_OFF_AUTO_AUTO; + /* KVM dirty ring is by default off */ + s->kvm_dirty_ring_size = 0; } static void kvm_accel_class_init(ObjectClass *oc, void *data) @@ -3196,6 +3629,12 @@ static void kvm_accel_class_init(ObjectClass *oc, void *data) NULL, NULL); object_class_property_set_description(oc, "kvm-shadow-mem", "KVM shadow MMU size"); + + object_class_property_add(oc, "dirty-ring-size", "uint32", + kvm_get_dirty_ring_size, kvm_set_dirty_ring_size, + NULL, NULL); + object_class_property_set_description(oc, "dirty-ring-size", + "Size of KVM dirty page ring buffer (default: 0, i.e. use bitmap)"); } static const TypeInfo kvm_accel_type = { diff --git a/accel/kvm/trace-events b/accel/kvm/trace-events index e15ae8980d..72a01320a1 100644 --- a/accel/kvm/trace-events +++ b/accel/kvm/trace-events @@ -18,4 +18,11 @@ kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint32_t val, bool assign, uint32_t kvm_set_user_memory(uint32_t slot, uint32_t flags, uint64_t guest_phys_addr, uint64_t memory_size, uint64_t userspace_addr, int ret) "Slot#%d flags=0x%x gpa=0x%"PRIx64 " size=0x%"PRIx64 " ua=0x%"PRIx64 " ret=%d" kvm_clear_dirty_log(uint32_t slot, uint64_t start, uint32_t size) "slot#%"PRId32" start 0x%"PRIx64" size 0x%"PRIx32 kvm_resample_fd_notify(int gsi) "gsi %d" +kvm_dirty_ring_full(int id) "vcpu %d" +kvm_dirty_ring_reap_vcpu(int id) "vcpu %d" +kvm_dirty_ring_page(int vcpu, uint32_t slot, uint64_t offset) "vcpu %d fetch %"PRIu32" offset 0x%"PRIx64 +kvm_dirty_ring_reaper(const char *s) "%s" +kvm_dirty_ring_reap(uint64_t count, int64_t t) "reaped %"PRIu64" pages (took %"PRIi64" us)" +kvm_dirty_ring_reaper_kick(const char *reason) "%s" +kvm_dirty_ring_flush(int finished) "%d" diff --git a/block/replication.c b/block/replication.c index 97be7ef4de..52163f2d1f 100644 --- a/block/replication.c +++ b/block/replication.c @@ -22,7 +22,7 @@ #include "sysemu/block-backend.h" #include "qapi/error.h" #include "qapi/qmp/qdict.h" -#include "replication.h" +#include "block/replication.h" typedef enum { BLOCK_REPLICATION_NONE, /* block replication is not started */ @@ -256,31 +256,11 @@ gdb_bin=$(command -v "gdb-multiarch" || command -v "gdb") if test -e "$source_path/.git" then git_submodules_action="update" - git_submodules="ui/keycodemapdb" - git_submodules="$git_submodules tests/fp/berkeley-testfloat-3" - git_submodules="$git_submodules tests/fp/berkeley-softfloat-3" else git_submodules_action="ignore" - git_submodules="" - - if ! test -f "$source_path/ui/keycodemapdb/README" - then - echo - echo "ERROR: missing file $source_path/ui/keycodemapdb/README" - echo - echo "This is not a GIT checkout but module content appears to" - echo "be missing. Do not use 'git archive' or GitHub download links" - echo "to acquire QEMU source archives. Non-GIT builds are only" - echo "supported with source archives linked from:" - echo - echo " https://www.qemu.org/download/#source" - echo - echo "Developers working with GIT can use scripts/archive-source.sh" - echo "if they need to create valid source archives." - echo - exit 1 - fi fi + +git_submodules="ui/keycodemapdb" git="git" # Don't accept a target_list environment variable. @@ -1593,6 +1573,28 @@ case $git_submodules_action in fi ;; ignore) + if ! test -f "$source_path/ui/keycodemapdb/README" + then + echo + echo "ERROR: missing GIT submodules" + echo + if test -e "$source_path/.git"; then + echo "--with-git-submodules=ignore specified but submodules were not" + echo "checked out. Please initialize and update submodules." + else + echo "This is not a GIT checkout but module content appears to" + echo "be missing. Do not use 'git archive' or GitHub download links" + echo "to acquire QEMU source archives. Non-GIT builds are only" + echo "supported with source archives linked from:" + echo + echo " https://www.qemu.org/download/#source" + echo + echo "Developers working with GIT can use scripts/archive-source.sh" + echo "if they need to create valid source archives." + fi + echo + exit 1 + fi ;; *) echo "ERROR: invalid --with-git-submodules= value '$git_submodules_action'" @@ -2281,6 +2283,11 @@ if test "$solaris" = "yes" ; then fi fi +if test "$tcg" = "enabled"; then + git_submodules="$git_submodules tests/fp/berkeley-testfloat-3" + git_submodules="$git_submodules tests/fp/berkeley-softfloat-3" +fi + if test -z "${target_list+xxx}" ; then default_targets=yes for target in $default_target_list; do @@ -3620,9 +3627,7 @@ fi case "$fdt" in auto | enabled | internal) # Simpler to always update submodule, even if not needed. - if test "$git_submodules_action" != "ignore"; then - git_submodules="${git_submodules} dtc" - fi + git_submodules="${git_submodules} dtc" ;; esac @@ -4344,9 +4349,7 @@ fi case "$capstone" in auto | enabled | internal) # Simpler to always update submodule, even if not needed. - if test "$git_submodules_action" != "ignore"; then - git_submodules="${git_submodules} capstone" - fi + git_submodules="${git_submodules} capstone" ;; esac @@ -5276,9 +5279,7 @@ fi case "$slirp" in auto | enabled | internal) # Simpler to always update submodule, even if not needed. - if test "$git_submodules_action" != "ignore"; then - git_submodules="${git_submodules} slirp" - fi + git_submodules="${git_submodules} slirp" ;; esac @@ -5470,9 +5471,7 @@ if test "$cpu" = "s390x" ; then roms="$roms s390-ccw" # SLOF is required for building the s390-ccw firmware on s390x, # since it is using the libnet code from SLOF for network booting. - if test "$git_submodules_action" != "ignore"; then - git_submodules="${git_submodules} roms/SLOF" - fi + git_submodules="${git_submodules} roms/SLOF" fi fi @@ -6504,10 +6503,14 @@ fi # Create list of config switches that should be poisoned in common code... # but filter out CONFIG_TCG and CONFIG_USER_ONLY which are special. -sed -n -e '/CONFIG_TCG/d' -e '/CONFIG_USER_ONLY/d' \ - -e '/^#define / { s///; s/ .*//; s/^/#pragma GCC poison /p; }' \ - *-config-devices.h *-config-target.h | \ - sort -u > config-poison.h +target_configs_h=$(ls *-config-devices.h *-config-target.h 2>/dev/null) +if test -n "$target_configs_h" ; then + sed -n -e '/CONFIG_TCG/d' -e '/CONFIG_USER_ONLY/d' \ + -e '/^#define / { s///; s/ .*//; s/^/#pragma GCC poison /p; }' \ + $target_configs_h | sort -u > config-poison.h +else + :> config-poison.h +fi # Save the configure command line for later reuse. cat <<EOD >config.status diff --git a/default-configs/devices/ppc64-softmmu.mak b/default-configs/devices/ppc64-softmmu.mak index ae0841fa3a..cca52665d9 100644 --- a/default-configs/devices/ppc64-softmmu.mak +++ b/default-configs/devices/ppc64-softmmu.mak @@ -8,4 +8,3 @@ CONFIG_POWERNV=y # For pSeries CONFIG_PSERIES=y -CONFIG_NVDIMM=y diff --git a/hmp-commands.hx b/hmp-commands.hx index 5ee9cfd520..2d21fe5ad4 100644 --- a/hmp-commands.hx +++ b/hmp-commands.hx @@ -1297,6 +1297,7 @@ ERST .help = "create QOM object", .cmd = hmp_object_add, .command_completion = object_add_completion, + .flags = "p", }, SRST @@ -1311,6 +1312,7 @@ ERST .help = "destroy QOM object", .cmd = hmp_object_del, .command_completion = object_del_completion, + .flags = "p", }, SRST diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index b887f6a5b1..67723d9ea6 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -6,6 +6,7 @@ config ARM_VIRT imply VFIO_PLATFORM imply VFIO_XGMAC imply TPM_TIS_SYSBUS + imply NVDIMM select ARM_GIC select ACPI select ARM_SMMUV3 diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig index 7f91f30877..66838fa397 100644 --- a/hw/i386/Kconfig +++ b/hw/i386/Kconfig @@ -23,6 +23,7 @@ config PC imply TPM_TIS_ISA imply VGA_PCI imply VIRTIO_VGA + imply NVDIMM select FDC select I8259 select I8254 diff --git a/hw/mem/Kconfig b/hw/mem/Kconfig index a0ef2cf648..8b19fdc49f 100644 --- a/hw/mem/Kconfig +++ b/hw/mem/Kconfig @@ -7,6 +7,4 @@ config MEM_DEVICE config NVDIMM bool - default y - depends on (PC || PSERIES || ARM_VIRT) select MEM_DEVICE diff --git a/hw/ppc/Kconfig b/hw/ppc/Kconfig index e51e0e5e5a..66e0b15d9e 100644 --- a/hw/ppc/Kconfig +++ b/hw/ppc/Kconfig @@ -3,6 +3,7 @@ config PSERIES imply PCI_DEVICES imply TEST_DEVICES imply VIRTIO_VGA + imply NVDIMM select DIMM select PCI select SPAPR_VSCSI diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c index 3580e7ee61..e8a547dbb7 100644 --- a/hw/scsi/scsi-disk.c +++ b/hw/scsi/scsi-disk.c @@ -1582,6 +1582,7 @@ invalid_field: scsi_check_condition(r, SENSE_CODE(INVALID_FIELD)); } +/* sector_num and nb_sectors expected to be in qdev blocksize */ static inline bool check_lba_range(SCSIDiskState *s, uint64_t sector_num, uint32_t nb_sectors) { @@ -1614,11 +1615,12 @@ static void scsi_unmap_complete_noio(UnmapCBData *data, int ret) assert(r->req.aiocb == NULL); if (data->count > 0) { - r->sector = ldq_be_p(&data->inbuf[0]) - * (s->qdev.blocksize / BDRV_SECTOR_SIZE); - r->sector_count = (ldl_be_p(&data->inbuf[8]) & 0xffffffffULL) - * (s->qdev.blocksize / BDRV_SECTOR_SIZE); - if (!check_lba_range(s, r->sector, r->sector_count)) { + uint64_t sector_num = ldq_be_p(&data->inbuf[0]); + uint32_t nb_sectors = ldl_be_p(&data->inbuf[8]) & 0xffffffffULL; + r->sector = sector_num * (s->qdev.blocksize / BDRV_SECTOR_SIZE); + r->sector_count = nb_sectors * (s->qdev.blocksize / BDRV_SECTOR_SIZE); + + if (!check_lba_range(s, sector_num, nb_sectors)) { block_acct_invalid(blk_get_stats(s->qdev.conf.blk), BLOCK_ACCT_UNMAP); scsi_check_condition(r, SENSE_CODE(LBA_OUT_OF_RANGE)); diff --git a/replication.h b/include/block/replication.h index d49fc22cb9..21931b4f0c 100644 --- a/replication.h +++ b/include/block/replication.h @@ -23,7 +23,7 @@ typedef struct ReplicationOps ReplicationOps; typedef struct ReplicationState ReplicationState; /** - * SECTION:replication.h + * SECTION:block/replication.h * @title:Base Replication System * @short_description: interfaces for handling replication * @@ -32,7 +32,7 @@ typedef struct ReplicationState ReplicationState; * <example> * <title>How to use replication interfaces</title> * <programlisting> - * #include "replication.h" + * #include "block/replication.h" * * typedef struct BDRVReplicationState { * ReplicationState *rs; diff --git a/include/exec/memory.h b/include/exec/memory.h index c8b9088924..e38b7e3dce 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -617,6 +617,18 @@ struct MemoryListener { void (*log_sync)(MemoryListener *listener, MemoryRegionSection *section); /** + * @log_sync_global: + * + * This is the global version of @log_sync when the listener does + * not have a way to synchronize the log with finer granularity. + * When the listener registers with @log_sync_global defined, then + * its @log_sync must be NULL. Vice versa. + * + * @listener: The #MemoryListener. + */ + void (*log_sync_global)(MemoryListener *listener); + + /** * @log_clear: * * Called before reading the dirty memory bitmap for a diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index d45f78290e..753ca90668 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -329,6 +329,10 @@ struct qemu_work_item; * @ignore_memory_transaction_failures: Cached copy of the MachineState * flag of the same name: allows the board to suppress calling of the * CPU do_transaction_failed hook function. + * @kvm_dirty_gfns: Points to the KVM dirty ring for this CPU when KVM dirty + * ring is enabled. + * @kvm_fetch_index: Keeps the index that we last fetched from the per-vCPU + * dirty ring structure. * * State of one CPU core or thread. */ @@ -400,9 +404,12 @@ struct CPUState { */ uintptr_t mem_io_pc; + /* Only used in KVM */ int kvm_fd; struct KVMState *kvm_state; struct kvm_run *kvm_run; + struct kvm_dirty_gfn *kvm_dirty_gfns; + uint32_t kvm_fetch_index; /* Used for events with 'vcpu' and *without* the 'disabled' properties */ DECLARE_BITMAP(trace_dstate_delayed, CPU_TRACE_DSTATE_MAX_EVENTS); diff --git a/include/qemu/config-file.h b/include/qemu/config-file.h index 8d3e53ae4d..0500b3668d 100644 --- a/include/qemu/config-file.h +++ b/include/qemu/config-file.h @@ -1,7 +1,7 @@ #ifndef QEMU_CONFIG_FILE_H #define QEMU_CONFIG_FILE_H - +void qemu_load_module_for_opts(const char *group); QemuOptsList *qemu_find_opts(const char *group); QemuOptsList *qemu_find_opts_err(const char *group, Error **errp); QemuOpts *qemu_find_opts_singleton(const char *group); diff --git a/qemu-options.h b/include/qemu/qemu-options.h index b4ee63cd60..4a62c83c45 100644 --- a/qemu-options.h +++ b/include/qemu/qemu-options.h @@ -29,8 +29,13 @@ #define QEMU_OPTIONS_H enum { -#define QEMU_OPTIONS_GENERATE_ENUM -#include "qemu-options-wrapper.h" + +#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask) \ + opt_enum, +#define DEFHEADING(text) +#define ARCHHEADING(text, arch_mask) + +#include "qemu-options.def" }; #endif diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h index ccb8869f01..c788452cd9 100644 --- a/include/sysemu/kvm_int.h +++ b/include/sysemu/kvm_int.h @@ -23,12 +23,15 @@ typedef struct KVMSlot int old_flags; /* Dirty bitmap cache for the slot */ unsigned long *dirty_bmap; + unsigned long dirty_bmap_size; + /* Cache of the address space ID */ + int as_id; + /* Cache of the offset in ram address space */ + ram_addr_t ram_start_offset; } KVMSlot; typedef struct KVMMemoryListener { MemoryListener listener; - /* Protects the slots and all inside them */ - QemuMutex slots_lock; KVMSlot *slots; int as_id; } KVMMemoryListener; diff --git a/meson.build b/meson.build index 632b380738..20d7035e44 100644 --- a/meson.build +++ b/meson.build @@ -2145,6 +2145,7 @@ common_all = common_ss.apply(config_all, strict: false) common_all = static_library('common', build_by_default: false, sources: common_all.sources() + genh, + implicit_include_directories: false, dependencies: common_all.dependencies(), name_suffix: 'fa') diff --git a/migration/colo.c b/migration/colo.c index de27662cab..e498fdb125 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -28,7 +28,7 @@ #include "migration/failover.h" #include "migration/ram.h" #ifdef CONFIG_REPLICATION -#include "replication.h" +#include "block/replication.h" #endif #include "net/colo-compare.h" #include "net/colo.h" diff --git a/os-posix.c b/os-posix.c index a6846f51c1..ae6c9f2a5e 100644 --- a/os-posix.c +++ b/os-posix.c @@ -32,7 +32,7 @@ #include "qemu-common.h" /* Needed early for CONFIG_BSD etc. */ #include "net/slirp.h" -#include "qemu-options.h" +#include "qemu/qemu-options.h" #include "qemu/error-report.h" #include "qemu/log.h" #include "sysemu/runstate.h" diff --git a/os-win32.c b/os-win32.c index fd1137bab1..e31c921983 100644 --- a/os-win32.c +++ b/os-win32.c @@ -27,7 +27,6 @@ #include <windows.h> #include <mmsystem.h> #include "qemu-common.h" -#include "qemu-options.h" #include "sysemu/runstate.h" static BOOL WINAPI qemu_ctrl_handler(DWORD type) diff --git a/qapi/qom.json b/qapi/qom.json index 40d70c434a..f7ef30f940 100644 --- a/qapi/qom.json +++ b/qapi/qom.json @@ -645,6 +645,21 @@ 'data': { 'path': 'str' } } ## +# @QtestProperties: +# +# Properties for qtest objects. +# +# @chardev: the chardev to be used to receive qtest commands on. +# +# @log: the path to a log file +# +# Since: 6.0 +## +{ 'struct': 'QtestProperties', + 'data': { 'chardev': 'str', + '*log': 'str' } } + +## # @RemoteObjectProperties: # # Properties for x-remote-object objects. @@ -769,6 +784,7 @@ 'memory-backend-ram', 'pef-guest', 'pr-manager-helper', + 'qtest', 'rng-builtin', 'rng-egd', 'rng-random', @@ -825,6 +841,7 @@ 'if': 'defined(CONFIG_LINUX)' }, 'memory-backend-ram': 'MemoryBackendProperties', 'pr-manager-helper': 'PrManagerHelperProperties', + 'qtest': 'QtestProperties', 'rng-builtin': 'RngProperties', 'rng-egd': 'RngEgdProperties', 'rng-random': 'RngRandomProperties', @@ -857,7 +874,8 @@ # <- { "return": {} } # ## -{ 'command': 'object-add', 'data': 'ObjectOptions', 'boxed': true } +{ 'command': 'object-add', 'data': 'ObjectOptions', 'boxed': true, + 'allow-preconfig': true } ## # @object-del: @@ -877,4 +895,5 @@ # <- { "return": {} } # ## -{ 'command': 'object-del', 'data': {'id': 'str'} } +{ 'command': 'object-del', 'data': {'id': 'str'}, + 'allow-preconfig': true } diff --git a/qemu-options-wrapper.h b/qemu-options-wrapper.h deleted file mode 100644 index 6f548e3922..0000000000 --- a/qemu-options-wrapper.h +++ /dev/null @@ -1,40 +0,0 @@ - -#if defined(QEMU_OPTIONS_GENERATE_ENUM) - -#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask) \ - opt_enum, -#define DEFHEADING(text) -#define ARCHHEADING(text, arch_mask) - -#elif defined(QEMU_OPTIONS_GENERATE_HELP) - -#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask) \ - if ((arch_mask) & arch_type) \ - fputs(opt_help, stdout); - -#define ARCHHEADING(text, arch_mask) \ - if ((arch_mask) & arch_type) \ - puts(stringify(text)); - -#define DEFHEADING(text) ARCHHEADING(text, QEMU_ARCH_ALL) - -#elif defined(QEMU_OPTIONS_GENERATE_OPTIONS) - -#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask) \ - { option, opt_arg, opt_enum, arch_mask }, -#define DEFHEADING(text) -#define ARCHHEADING(text, arch_mask) - -#else -#error "qemu-options-wrapper.h included with no option defined" -#endif - -#include "qemu-options.def" - -#undef DEF -#undef DEFHEADING -#undef ARCHHEADING - -#undef QEMU_OPTIONS_GENERATE_ENUM -#undef QEMU_OPTIONS_GENERATE_HELP -#undef QEMU_OPTIONS_GENERATE_OPTIONS diff --git a/qemu-options.hx b/qemu-options.hx index e22fb94d99..14258784b3 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -141,6 +141,7 @@ DEF("accel", HAS_ARG, QEMU_OPTION_accel, " kvm-shadow-mem=size of KVM shadow MMU in bytes\n" " split-wx=on|off (enable TCG split w^x mapping)\n" " tb-size=n (TCG translation block cache size)\n" + " dirty-ring-size=n (KVM dirty ring GFN count, default 0)\n" " thread=single|multi (enable multi-threaded TCG)\n", QEMU_ARCH_ALL) SRST ``-accel name[,prop=value[,...]]`` @@ -181,6 +182,17 @@ SRST where both the back-end and front-ends support it and no incompatible TCG features have been enabled (e.g. icount/replay). + + ``dirty-ring-size=n`` + When the KVM accelerator is used, it controls the size of the per-vCPU + dirty page ring buffer (number of entries for each vCPU). It should + be a value that is power of two, and it should be 1024 or bigger (but + still less than the maximum value that the kernel supports). 4096 + could be a good initial value if you have no idea which is the best. + Set this value to 0 to disable the feature. By default, this feature + is disabled (dirty-ring-size=0). When enabled, KVM will instead + record dirty pages in a bitmap. + ERST DEF("smp", HAS_ARG, QEMU_OPTION_smp, @@ -3787,8 +3799,11 @@ DEF("mon", HAS_ARG, QEMU_OPTION_mon, \ "-mon [chardev=]name[,mode=readline|control][,pretty[=on|off]]\n", QEMU_ARCH_ALL) SRST ``-mon [chardev=]name[,mode=readline|control][,pretty[=on|off]]`` - Setup monitor on chardev name. ``pretty`` is only valid when - ``mode=control``, turning on JSON pretty printing to ease + Setup monitor on chardev name. ``mode=control`` configures + a QMP monitor (a JSON RPC-style protocol) and it is not the + same as HMP, the human monitor that has a "(qemu)" prompt. + ``pretty`` is only valid when ``mode=control``, + turning on JSON pretty printing to ease human reading and debugging. ERST @@ -5264,3 +5279,7 @@ ERST HXCOMM This is the last statement. Insert new options before this line! + +#undef DEF +#undef DEFHEADING +#undef ARCHHEADING diff --git a/replication.c b/replication.c index be3a42f9c9..4acd3f8004 100644 --- a/replication.c +++ b/replication.c @@ -14,7 +14,7 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "replication.h" +#include "block/replication.h" static QLIST_HEAD(, ReplicationState) replication_states; diff --git a/softmmu/memory.c b/softmmu/memory.c index 3bb533c0bc..c19b0be6b1 100644 --- a/softmmu/memory.c +++ b/softmmu/memory.c @@ -2055,6 +2055,10 @@ void memory_region_set_dirty(MemoryRegion *mr, hwaddr addr, memory_region_get_dirty_log_mask(mr)); } +/* + * If memory region `mr' is NULL, do global sync. Otherwise, sync + * dirty bitmap for the specified memory region. + */ static void memory_region_sync_dirty_bitmap(MemoryRegion *mr) { MemoryListener *listener; @@ -2068,18 +2072,24 @@ static void memory_region_sync_dirty_bitmap(MemoryRegion *mr) * address space once. */ QTAILQ_FOREACH(listener, &memory_listeners, link) { - if (!listener->log_sync) { - continue; - } - as = listener->address_space; - view = address_space_get_flatview(as); - FOR_EACH_FLAT_RANGE(fr, view) { - if (fr->dirty_log_mask && (!mr || fr->mr == mr)) { - MemoryRegionSection mrs = section_from_flat_range(fr, view); - listener->log_sync(listener, &mrs); + if (listener->log_sync) { + as = listener->address_space; + view = address_space_get_flatview(as); + FOR_EACH_FLAT_RANGE(fr, view) { + if (fr->dirty_log_mask && (!mr || fr->mr == mr)) { + MemoryRegionSection mrs = section_from_flat_range(fr, view); + listener->log_sync(listener, &mrs); + } } + flatview_unref(view); + } else if (listener->log_sync_global) { + /* + * No matter whether MR is specified, what we can do here + * is to do a global sync, because we are not capable to + * sync in a finer granularity. + */ + listener->log_sync_global(listener); } - flatview_unref(view); } } @@ -2767,6 +2777,9 @@ void memory_listener_register(MemoryListener *listener, AddressSpace *as) { MemoryListener *other = NULL; + /* Only one of them can be defined for a listener */ + assert(!(listener->log_sync && listener->log_sync_global)); + listener->address_space = as; if (QTAILQ_EMPTY(&memory_listeners) || listener->priority >= QTAILQ_LAST(&memory_listeners)->priority) { diff --git a/softmmu/qtest.c b/softmmu/qtest.c index 130c366615..72751e1fd8 100644 --- a/softmmu/qtest.c +++ b/softmmu/qtest.c @@ -27,6 +27,8 @@ #include "qemu/error-report.h" #include "qemu/module.h" #include "qemu/cutils.h" +#include "qapi/qmp/qerror.h" +#include "qom/object_interfaces.h" #include CONFIG_DEVICES #ifdef CONFIG_PSERIES #include "hw/ppc/spapr_rtas.h" @@ -34,11 +36,25 @@ #define MAX_IRQ 256 +#define TYPE_QTEST "qtest" + +OBJECT_DECLARE_SIMPLE_TYPE(QTest, QTEST) + +struct QTest { + Object parent; + + bool has_machine_link; + char *chr_name; + Chardev *chr; + CharBackend qtest_chr; + char *log; +}; + bool qtest_allowed; static DeviceState *irq_intercept_dev; static FILE *qtest_log_fp; -static CharBackend qtest_chr; +static QTest *qtest; static GString *inbuf; static int irq_levels[MAX_IRQ]; static qemu_timeval start_time; @@ -320,7 +336,7 @@ static void qtest_irq_handler(void *opaque, int n, int level) qemu_set_irq(old_irq, level); if (irq_levels[n] != level) { - CharBackend *chr = &qtest_chr; + CharBackend *chr = &qtest->qtest_chr; irq_levels[n] = level; qtest_send_prefix(chr); qtest_sendf(chr, "IRQ %s %d\n", @@ -849,18 +865,39 @@ static void qtest_event(void *opaque, QEMUChrEvent event) break; } } + void qtest_server_init(const char *qtest_chrdev, const char *qtest_log, Error **errp) { + ERRP_GUARD(); Chardev *chr; + Object *qtest; chr = qemu_chr_new("qtest", qtest_chrdev, NULL); - if (chr == NULL) { error_setg(errp, "Failed to initialize device for qtest: \"%s\"", qtest_chrdev); return; } + qtest = object_new(TYPE_QTEST); + object_property_set_str(qtest, "chardev", "qtest", &error_abort); + if (qtest_log) { + object_property_set_str(qtest, "log", qtest_log, &error_abort); + } + object_property_add_child(qdev_get_machine(), "qtest", qtest); + user_creatable_complete(USER_CREATABLE(qtest), errp); + if (*errp) { + object_unparent(qtest); + } + object_unref(OBJECT(chr)); + object_unref(qtest); +} + +static bool qtest_server_start(QTest *q, Error **errp) +{ + Chardev *chr = q->chr; + const char *qtest_log = q->log; + if (qtest_log) { if (strcmp(qtest_log, "none") != 0) { qtest_log_fp = fopen(qtest_log, "w+"); @@ -869,16 +906,20 @@ void qtest_server_init(const char *qtest_chrdev, const char *qtest_log, Error ** qtest_log_fp = stderr; } - qemu_chr_fe_init(&qtest_chr, chr, errp); - qemu_chr_fe_set_handlers(&qtest_chr, qtest_can_read, qtest_read, - qtest_event, NULL, &qtest_chr, NULL, true); - qemu_chr_fe_set_echo(&qtest_chr, true); + if (!qemu_chr_fe_init(&q->qtest_chr, chr, errp)) { + return false; + } + qemu_chr_fe_set_handlers(&q->qtest_chr, qtest_can_read, qtest_read, + qtest_event, NULL, &q->qtest_chr, NULL, true); + qemu_chr_fe_set_echo(&q->qtest_chr, true); inbuf = g_string_new(""); if (!qtest_server_send) { - qtest_server_set_send_handler(qtest_server_char_be_send, &qtest_chr); + qtest_server_set_send_handler(qtest_server_char_be_send, &q->qtest_chr); } + qtest = q; + return true; } void qtest_server_set_send_handler(void (*send)(void*, const char*), @@ -890,7 +931,7 @@ void qtest_server_set_send_handler(void (*send)(void*, const char*), bool qtest_driver(void) { - return qtest_chr.chr != NULL; + return qtest && qtest->qtest_chr.chr != NULL; } void qtest_server_inproc_recv(void *dummy, const char *buf) @@ -905,3 +946,129 @@ void qtest_server_inproc_recv(void *dummy, const char *buf) g_string_truncate(gstr, 0); } } + +static void qtest_complete(UserCreatable *uc, Error **errp) +{ + QTest *q = QTEST(uc); + if (qtest) { + error_setg(errp, "Only one instance of qtest can be created"); + return; + } + if (!q->chr_name) { + error_setg(errp, "No backend specified"); + return; + } + + if (OBJECT(uc)->parent != qdev_get_machine()) { + q->has_machine_link = true; + object_property_add_const_link(qdev_get_machine(), "qtest", OBJECT(uc)); + } else { + /* -qtest was used. */ + } + + qtest_server_start(q, errp); +} + +static void qtest_unparent(Object *obj) +{ + QTest *q = QTEST(obj); + + if (qtest == q) { + qemu_chr_fe_disconnect(&q->qtest_chr); + assert(!qtest_opened); + qemu_chr_fe_deinit(&q->qtest_chr, false); + if (qtest_log_fp) { + fclose(qtest_log_fp); + qtest_log_fp = NULL; + } + qtest = NULL; + } + + if (q->has_machine_link) { + object_property_del(qdev_get_machine(), "qtest"); + q->has_machine_link = false; + } +} + +static void qtest_set_log(Object *obj, const char *value, Error **errp) +{ + QTest *q = QTEST(obj); + + if (qtest == q) { + error_setg(errp, QERR_PERMISSION_DENIED); + } else { + g_free(q->log); + q->log = g_strdup(value); + } +} + +static char *qtest_get_log(Object *obj, Error **errp) +{ + QTest *q = QTEST(obj); + + return g_strdup(q->log); +} + +static void qtest_set_chardev(Object *obj, const char *value, Error **errp) +{ + QTest *q = QTEST(obj); + Chardev *chr; + + if (qtest == q) { + error_setg(errp, QERR_PERMISSION_DENIED); + return; + } + + chr = qemu_chr_find(value); + if (!chr) { + error_setg(errp, "Cannot find character device '%s'", value); + return; + } + + g_free(q->chr_name); + q->chr_name = g_strdup(value); + + if (q->chr) { + object_unref(q->chr); + } + q->chr = chr; + object_ref(chr); +} + +static char *qtest_get_chardev(Object *obj, Error **errp) +{ + QTest *q = QTEST(obj); + + return g_strdup(q->chr_name); +} + +static void qtest_class_init(ObjectClass *oc, void *data) +{ + UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc); + + oc->unparent = qtest_unparent; + ucc->complete = qtest_complete; + + object_class_property_add_str(oc, "chardev", + qtest_get_chardev, qtest_set_chardev); + object_class_property_add_str(oc, "log", + qtest_get_log, qtest_set_log); +} + +static const TypeInfo qtest_info = { + .name = TYPE_QTEST, + .parent = TYPE_OBJECT, + .class_init = qtest_class_init, + .instance_size = sizeof(QTest), + .interfaces = (InterfaceInfo[]) { + { TYPE_USER_CREATABLE }, + { } + } +}; + +static void register_types(void) +{ + type_register_static(&qtest_info); +} + +type_init(register_types); diff --git a/softmmu/vl.c b/softmmu/vl.c index 93e78469bc..6054f6f0b9 100644 --- a/softmmu/vl.c +++ b/softmmu/vl.c @@ -88,7 +88,7 @@ #include "qapi/qobject-input-visitor.h" #include "qemu/option.h" #include "qemu/config-file.h" -#include "qemu-options.h" +#include "qemu/qemu-options.h" #include "qemu/main-loop.h" #ifdef CONFIG_VIRTFS #include "fsdev/qemu-fsdev.h" @@ -854,8 +854,17 @@ static void help(int exitcode) "'disk_image' is a raw hard disk image for IDE hard disk 0\n\n", error_get_progname()); -#define QEMU_OPTIONS_GENERATE_HELP -#include "qemu-options-wrapper.h" +#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask) \ + if ((arch_mask) & arch_type) \ + fputs(opt_help, stdout); + +#define ARCHHEADING(text, arch_mask) \ + if ((arch_mask) & arch_type) \ + puts(stringify(text)); + +#define DEFHEADING(text) ARCHHEADING(text, QEMU_ARCH_ALL) + +#include "qemu-options.def" printf("\nDuring emulation, the following keys are useful:\n" "ctrl-alt-f toggle full screen\n" @@ -880,8 +889,13 @@ typedef struct QEMUOption { static const QEMUOption qemu_options[] = { { "h", 0, QEMU_OPTION_h, QEMU_ARCH_ALL }, -#define QEMU_OPTIONS_GENERATE_OPTIONS -#include "qemu-options-wrapper.h" + +#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask) \ + { option, opt_arg, opt_enum, arch_mask }, +#define DEFHEADING(text) +#define ARCHHEADING(text, arch_mask) + +#include "qemu-options.def" { NULL }, }; @@ -1758,8 +1772,9 @@ static bool object_create_early(const char *type) * add one, state the reason in a comment! */ - /* Reason: rng-egd property "chardev" */ - if (g_str_equal(type, "rng-egd")) { + /* Reason: property "chardev" */ + if (g_str_equal(type, "rng-egd") || + g_str_equal(type, "qtest")) { return false; } @@ -2024,8 +2039,6 @@ static void set_memory_options(MachineClass *mc) exit(EXIT_FAILURE); } - /* store value for the future use */ - qemu_opt_set_number(opts, "size", ram_size, &error_abort); maxram_size = ram_size; if (qemu_opt_get(opts, "maxmem")) { @@ -2614,6 +2627,23 @@ void qmp_x_exit_preconfig(Error **errp) } } +#ifdef CONFIG_MODULES +void qemu_load_module_for_opts(const char *group) +{ + static bool spice_tried; + if (g_str_equal(group, "spice") && !spice_tried) { + ui_module_load_one("spice-core"); + spice_tried = true; + } + + static bool iscsi_tried; + if (g_str_equal(group, "iscsi") && !iscsi_tried) { + block_module_load_one("iscsi"); + iscsi_tried = true; + } +} +#endif + void qemu_init(int argc, char **argv, char **envp) { QemuOpts *opts; @@ -3374,10 +3404,6 @@ void qemu_init(int argc, char **argv, char **envp) case QEMU_OPTION_spice: olist = qemu_find_opts_err("spice", NULL); if (!olist) { - ui_module_load_one("spice-core"); - olist = qemu_find_opts("spice"); - } - if (!olist) { error_report("spice support is disabled"); exit(1); } diff --git a/stubs/meson.build b/stubs/meson.build index 3faef16892..f3f979c3fe 100644 --- a/stubs/meson.build +++ b/stubs/meson.build @@ -22,6 +22,7 @@ stub_ss.add(files('isa-bus.c')) stub_ss.add(files('is-daemonized.c')) stub_ss.add(when: 'CONFIG_LINUX_AIO', if_true: files('linux-aio.c')) stub_ss.add(files('migr-blocker.c')) +stub_ss.add(files('module-opts.c')) stub_ss.add(files('monitor.c')) stub_ss.add(files('monitor-core.c')) stub_ss.add(files('pci-bus.c')) diff --git a/stubs/module-opts.c b/stubs/module-opts.c new file mode 100644 index 0000000000..a7d0e4ad6e --- /dev/null +++ b/stubs/module-opts.c @@ -0,0 +1,6 @@ +#include "qemu/osdep.h" +#include "qemu/config-file.h" + +void qemu_load_module_for_opts(const char *group) +{ +} diff --git a/target/i386/cpu.c b/target/i386/cpu.c index c496bfa1c2..9e211ac2ce 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -940,7 +940,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { .type = CPUID_FEATURE_WORD, .feat_names = { NULL, NULL, NULL, NULL, - NULL, "avx512-bf16", NULL, NULL, + "avx-vnni", "avx512-bf16", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, @@ -3194,7 +3194,7 @@ static X86CPUDefinition builtin_x86_defs[] = { MSR_ARCH_CAP_SKIP_L1DFL_VMENTRY | MSR_ARCH_CAP_MDS_NO | MSR_ARCH_CAP_PSCHANGE_MC_NO | MSR_ARCH_CAP_TAA_NO, .features[FEAT_7_1_EAX] = - CPUID_7_1_EAX_AVX512_BF16, + CPUID_7_1_EAX_AVX_VNNI | CPUID_7_1_EAX_AVX512_BF16, /* * Missing: XSAVES (not supported by some Linux versions, * including v4.1 to v4.12). diff --git a/target/i386/cpu.h b/target/i386/cpu.h index e6836393f7..da72aa5228 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -817,6 +817,8 @@ typedef uint64_t FeatureWordArray[FEATURE_WORDS]; /* Speculative Store Bypass Disable */ #define CPUID_7_0_EDX_SPEC_CTRL_SSBD (1U << 31) +/* AVX VNNI Instruction */ +#define CPUID_7_1_EAX_AVX_VNNI (1U << 4) /* AVX512 BFloat16 Instruction */ #define CPUID_7_1_EAX_AVX512_BF16 (1U << 5) diff --git a/tests/qtest/fuzz/fuzz.c b/tests/qtest/fuzz/fuzz.c index 04b70e114b..5f77c84983 100644 --- a/tests/qtest/fuzz/fuzz.c +++ b/tests/qtest/fuzz/fuzz.c @@ -16,6 +16,7 @@ #include <wordexp.h> #include "qemu/datadir.h" +#include "sysemu/sysemu.h" #include "sysemu/qtest.h" #include "sysemu/runstate.h" #include "qemu/main-loop.h" diff --git a/tests/unit/test-replication.c b/tests/unit/test-replication.c index b067240add..afff908d77 100644 --- a/tests/unit/test-replication.c +++ b/tests/unit/test-replication.c @@ -14,7 +14,7 @@ #include "qapi/qmp/qdict.h" #include "qemu/option.h" #include "qemu/main-loop.h" -#include "replication.h" +#include "block/replication.h" #include "block/block_int.h" #include "block/qdict.h" #include "sysemu/block-backend.h" diff --git a/util/qemu-config.c b/util/qemu-config.c index 670bd6ebca..34974c4b47 100644 --- a/util/qemu-config.c +++ b/util/qemu-config.c @@ -16,6 +16,7 @@ static QemuOptsList *find_list(QemuOptsList **lists, const char *group, { int i; + qemu_load_module_for_opts(group); for (i = 0; lists[i] != NULL; i++) { if (strcmp(lists[i]->name, group) == 0) break; |