X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=xen-hvm.c;h=98ea44fdf34af0900e1f722870833d07e550a6e3;hb=0517cc9863bd4753be56d47da1a568538069e19f;hp=0d0994011191110cb48f61f96f9182ec65b98e3d;hpb=f2426947decc96bde4f9ea50097dac66a0a48acc;p=mirror_qemu.git diff --git a/xen-hvm.c b/xen-hvm.c index 0d09940111..98ea44fdf3 100644 --- a/xen-hvm.c +++ b/xen-hvm.c @@ -8,15 +8,18 @@ * GNU GPL, version 2 or (at your option) any later version. */ -#include +#include "qemu/osdep.h" +#include "cpu.h" #include "hw/pci/pci.h" #include "hw/i386/pc.h" +#include "hw/i386/apic-msidef.h" #include "hw/xen/xen_common.h" #include "hw/xen/xen_backend.h" #include "qmp-commands.h" #include "sysemu/char.h" +#include "qemu/error-report.h" #include "qemu/range.h" #include "sysemu/xen-mapcache.h" #include "trace.h" @@ -41,17 +44,29 @@ static MemoryRegion *framebuffer; static bool xen_in_migration; /* Compatibility with older version */ -#if __XEN_LATEST_INTERFACE_VERSION__ < 0x0003020a -static inline uint32_t xen_vcpu_eport(shared_iopage_t *shared_page, int i) -{ - return shared_page->vcpu_iodata[i].vp_eport; -} -static inline ioreq_t *xen_vcpu_ioreq(shared_iopage_t *shared_page, int vcpu) -{ - return &shared_page->vcpu_iodata[vcpu].vp_ioreq; -} -# define FMT_ioreq_size PRIx64 -#else + +/* This allows QEMU to build on a system that has Xen 4.5 or earlier + * installed. This here (not in hw/xen/xen_common.h) because xen/hvm/ioreq.h + * needs to be included before this block and hw/xen/xen_common.h needs to + * be included before xen/hvm/ioreq.h + */ +#ifndef IOREQ_TYPE_VMWARE_PORT +#define IOREQ_TYPE_VMWARE_PORT 3 +struct vmware_regs { + uint32_t esi; + uint32_t edi; + uint32_t ebx; + uint32_t ecx; + uint32_t edx; +}; +typedef struct vmware_regs vmware_regs_t; + +struct shared_vmport_iopage { + struct vmware_regs vcpu_vmport_regs[1]; +}; +typedef struct shared_vmport_iopage shared_vmport_iopage_t; +#endif + static inline uint32_t xen_vcpu_eport(shared_iopage_t *shared_page, int i) { return shared_page->vcpu_ioreq[i].vp_eport; @@ -60,11 +75,6 @@ static inline ioreq_t *xen_vcpu_ioreq(shared_iopage_t *shared_page, int vcpu) { return &shared_page->vcpu_ioreq[vcpu]; } -# define FMT_ioreq_size "u" -#endif -#ifndef HVM_PARAM_BUFIOREQ_EVTCHN -#define HVM_PARAM_BUFIOREQ_EVTCHN 26 -#endif #define BUFFER_IO_MAX_DELAY 100 @@ -78,20 +88,25 @@ typedef struct XenPhysmap { } XenPhysmap; typedef struct XenIOState { + ioservid_t ioservid; shared_iopage_t *shared_page; + shared_vmport_iopage_t *shared_vmport_page; buffered_iopage_t *buffered_io_page; QEMUTimer *buffered_io_timer; + CPUState **cpu_by_vcpu_id; /* the evtchn port for polling the notification, */ evtchn_port_t *ioreq_local_port; /* evtchn local port for buffered io */ evtchn_port_t bufioreq_local_port; /* the evtchn fd for polling */ - XenEvtchn xce_handle; + xenevtchn_handle *xce_handle; /* which vcpu we are serving */ int send_vcpu; struct xs_handle *xenstore; MemoryListener memory_listener; + MemoryListener io_listener; + DeviceListener device_listener; QLIST_HEAD(, XenPhysmap) physmap; hwaddr free_phys_offset; const XenPhysmap *log_for_dirtybit; @@ -131,9 +146,17 @@ void xen_piix_pci_write_config_client(uint32_t address, uint32_t val, int len) } } +int xen_is_pirq_msi(uint32_t msi_data) +{ + /* If vector is 0, the msi is remapped into a pirq, passed as + * dest_id. + */ + return ((msi_data & MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT) == 0; +} + void xen_hvm_inject_msi(uint64_t addr, uint32_t data) { - xen_xc_hvm_inject_msi(xen_xc, xen_domid, addr, data); + xc_hvm_inject_msi(xen_xc, xen_domid, addr, data); } static void xen_suspend_notifier(Notifier *notifier, void *data) @@ -155,8 +178,7 @@ qemu_irq *xen_interrupt_controller_init(void) /* Memory Ops */ -static void xen_ram_init(ram_addr_t *below_4g_mem_size, - ram_addr_t *above_4g_mem_size, +static void xen_ram_init(PCMachineState *pcms, ram_addr_t ram_size, MemoryRegion **ram_memory_p) { MemoryRegion *sysmem = get_system_memory(); @@ -173,22 +195,23 @@ static void xen_ram_init(ram_addr_t *below_4g_mem_size, } if (ram_size >= user_lowmem) { - *above_4g_mem_size = ram_size - user_lowmem; - *below_4g_mem_size = user_lowmem; + pcms->above_4g_mem_size = ram_size - user_lowmem; + pcms->below_4g_mem_size = user_lowmem; } else { - *above_4g_mem_size = 0; - *below_4g_mem_size = ram_size; + pcms->above_4g_mem_size = 0; + pcms->below_4g_mem_size = ram_size; } - if (!*above_4g_mem_size) { + if (!pcms->above_4g_mem_size) { block_len = ram_size; } else { /* * Xen does not allocate the memory continuously, it keeps a * hole of the size computed above or passed in. */ - block_len = (1ULL << 32) + *above_4g_mem_size; + block_len = (1ULL << 32) + pcms->above_4g_mem_size; } - memory_region_init_ram(&ram_memory, NULL, "xen.ram", block_len); + memory_region_init_ram(&ram_memory, NULL, "xen.ram", block_len, + &error_fatal); *ram_memory_p = &ram_memory; vmstate_register_ram_global(&ram_memory); @@ -203,17 +226,18 @@ static void xen_ram_init(ram_addr_t *below_4g_mem_size, */ memory_region_init_alias(&ram_lo, NULL, "xen.ram.lo", &ram_memory, 0xc0000, - *below_4g_mem_size - 0xc0000); + pcms->below_4g_mem_size - 0xc0000); memory_region_add_subregion(sysmem, 0xc0000, &ram_lo); - if (*above_4g_mem_size > 0) { + if (pcms->above_4g_mem_size > 0) { memory_region_init_alias(&ram_hi, NULL, "xen.ram.hi", &ram_memory, 0x100000000ULL, - *above_4g_mem_size); + pcms->above_4g_mem_size); memory_region_add_subregion(sysmem, 0x100000000ULL, &ram_hi); } } -void xen_ram_alloc(ram_addr_t ram_addr, ram_addr_t size, MemoryRegion *mr) +void xen_ram_alloc(ram_addr_t ram_addr, ram_addr_t size, MemoryRegion *mr, + Error **errp) { unsigned long nr_pfn; xen_pfn_t *pfn_list; @@ -241,7 +265,8 @@ void xen_ram_alloc(ram_addr_t ram_addr, ram_addr_t size, MemoryRegion *mr) } if (xc_domain_populate_physmap_exact(xen_xc, xen_domid, nr_pfn, 0, 0, pfn_list)) { - hw_error("xen: failed to populate ram at " RAM_ADDR_FMT, ram_addr); + error_setg(errp, "xen: failed to populate ram at " RAM_ADDR_FMT, + ram_addr); } g_free(pfn_list); @@ -278,7 +303,6 @@ static hwaddr xen_phys_offset_to_gaddr(hwaddr start_addr, return start_addr; } -#if CONFIG_XEN_CTRL_INTERFACE_VERSION >= 340 static int xen_add_to_physmap(XenIOState *state, hwaddr start_addr, ram_addr_t size, @@ -319,10 +343,10 @@ go_physmap: unsigned long idx = pfn + i; xen_pfn_t gpfn = start_gpfn + i; - rc = xc_domain_add_to_physmap(xen_xc, xen_domid, XENMAPSPACE_gmfn, idx, gpfn); + rc = xen_xc_domain_add_to_physmap(xen_xc, xen_domid, XENMAPSPACE_gmfn, idx, gpfn); if (rc) { DPRINTF("add_to_physmap MFN %"PRI_xen_pfn" to PFN %" - PRI_xen_pfn" failed: %d\n", idx, gpfn, rc); + PRI_xen_pfn" failed: %d (errno: %d)\n", idx, gpfn, rc, errno); return -rc; } } @@ -396,10 +420,10 @@ static int xen_remove_from_physmap(XenIOState *state, xen_pfn_t idx = start_addr + i; xen_pfn_t gpfn = phys_offset + i; - rc = xc_domain_add_to_physmap(xen_xc, xen_domid, XENMAPSPACE_gmfn, idx, gpfn); + rc = xen_xc_domain_add_to_physmap(xen_xc, xen_domid, XENMAPSPACE_gmfn, idx, gpfn); if (rc) { fprintf(stderr, "add_to_physmap MFN %"PRI_xen_pfn" to PFN %" - PRI_xen_pfn" failed: %d\n", idx, gpfn, rc); + PRI_xen_pfn" failed: %d (errno: %d)\n", idx, gpfn, rc, errno); return -rc; } } @@ -413,24 +437,6 @@ static int xen_remove_from_physmap(XenIOState *state, return 0; } -#else -static int xen_add_to_physmap(XenIOState *state, - hwaddr start_addr, - ram_addr_t size, - MemoryRegion *mr, - hwaddr offset_within_region) -{ - return -ENOSYS; -} - -static int xen_remove_from_physmap(XenIOState *state, - hwaddr start_addr, - ram_addr_t size) -{ - return -ENOSYS; -} -#endif - static void xen_set_memory(struct MemoryListener *listener, MemoryRegionSection *section, bool add) @@ -438,15 +444,26 @@ static void xen_set_memory(struct MemoryListener *listener, XenIOState *state = container_of(listener, XenIOState, memory_listener); hwaddr start_addr = section->offset_within_address_space; ram_addr_t size = int128_get64(section->size); - bool log_dirty = memory_region_is_logging(section->mr); + bool log_dirty = memory_region_is_logging(section->mr, DIRTY_MEMORY_VGA); hvmmem_type_t mem_type; + if (section->mr == &ram_memory) { + return; + } else { + if (add) { + xen_map_memory_section(xen_xc, xen_domid, state->ioservid, + section); + } else { + xen_unmap_memory_section(xen_xc, xen_domid, state->ioservid, + section); + } + } + if (!memory_region_is_ram(section->mr)) { return; } - if (!(section->mr != &ram_memory - && ( (log_dirty && add) || (!log_dirty && !add)))) { + if (log_dirty != add) { return; } @@ -489,13 +506,67 @@ static void xen_region_del(MemoryListener *listener, memory_region_unref(section->mr); } +static void xen_io_add(MemoryListener *listener, + MemoryRegionSection *section) +{ + XenIOState *state = container_of(listener, XenIOState, io_listener); + MemoryRegion *mr = section->mr; + + if (mr->ops == &unassigned_io_ops) { + return; + } + + memory_region_ref(mr); + + xen_map_io_section(xen_xc, xen_domid, state->ioservid, section); +} + +static void xen_io_del(MemoryListener *listener, + MemoryRegionSection *section) +{ + XenIOState *state = container_of(listener, XenIOState, io_listener); + MemoryRegion *mr = section->mr; + + if (mr->ops == &unassigned_io_ops) { + return; + } + + xen_unmap_io_section(xen_xc, xen_domid, state->ioservid, section); + + memory_region_unref(mr); +} + +static void xen_device_realize(DeviceListener *listener, + DeviceState *dev) +{ + XenIOState *state = container_of(listener, XenIOState, device_listener); + + if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + PCIDevice *pci_dev = PCI_DEVICE(dev); + + xen_map_pcidev(xen_xc, xen_domid, state->ioservid, pci_dev); + } +} + +static void xen_device_unrealize(DeviceListener *listener, + DeviceState *dev) +{ + XenIOState *state = container_of(listener, XenIOState, device_listener); + + if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + PCIDevice *pci_dev = PCI_DEVICE(dev); + + xen_unmap_pcidev(xen_xc, xen_domid, state->ioservid, pci_dev); + } +} + static void xen_sync_dirty_bitmap(XenIOState *state, hwaddr start_addr, ram_addr_t size) { hwaddr npages = size >> TARGET_PAGE_BITS; const int width = sizeof(unsigned long) * 8; - unsigned long bitmap[(npages + width - 1) / width]; + unsigned long bitmap[DIV_ROUND_UP(npages, width)]; int rc, i, j; const XenPhysmap *physmap = NULL; @@ -541,21 +612,27 @@ static void xen_sync_dirty_bitmap(XenIOState *state, } static void xen_log_start(MemoryListener *listener, - MemoryRegionSection *section) + MemoryRegionSection *section, + int old, int new) { XenIOState *state = container_of(listener, XenIOState, memory_listener); - xen_sync_dirty_bitmap(state, section->offset_within_address_space, - int128_get64(section->size)); + if (new & ~old & (1 << DIRTY_MEMORY_VGA)) { + xen_sync_dirty_bitmap(state, section->offset_within_address_space, + int128_get64(section->size)); + } } -static void xen_log_stop(MemoryListener *listener, MemoryRegionSection *section) +static void xen_log_stop(MemoryListener *listener, MemoryRegionSection *section, + int old, int new) { XenIOState *state = container_of(listener, XenIOState, memory_listener); - state->log_for_dirtybit = NULL; - /* Disable dirty bit tracking */ - xc_hvm_track_dirty_vram(xen_xc, xen_domid, 0, 0, NULL); + if (old & ~new & (1 << DIRTY_MEMORY_VGA)) { + state->log_for_dirtybit = NULL; + /* Disable dirty bit tracking */ + xc_hvm_track_dirty_vram(xen_xc, xen_domid, 0, 0, NULL); + } } static void xen_log_sync(MemoryListener *listener, MemoryRegionSection *section) @@ -589,6 +666,17 @@ static MemoryListener xen_memory_listener = { .priority = 10, }; +static MemoryListener xen_io_listener = { + .region_add = xen_io_add, + .region_del = xen_io_del, + .priority = 10, +}; + +static DeviceListener xen_device_listener = { + .realize = xen_device_realize, + .unrealize = xen_device_unrealize, +}; + /* get the ioreq packets from share mem */ static ioreq_t *cpu_get_ioreq_from_shared_memory(XenIOState *state, int vcpu) { @@ -597,7 +685,7 @@ static ioreq_t *cpu_get_ioreq_from_shared_memory(XenIOState *state, int vcpu) if (req->state != STATE_IOREQ_READY) { DPRINTF("I/O request not ready: " "%x, ptr: %x, port: %"PRIx64", " - "data: %"PRIx64", count: %" FMT_ioreq_size ", size: %" FMT_ioreq_size "\n", + "data: %"PRIx64", count: %u, size: %u\n", req->state, req->data_is_ptr, req->addr, req->data, req->count, req->size); return NULL; @@ -617,7 +705,7 @@ static ioreq_t *cpu_get_ioreq(XenIOState *state) int i; evtchn_port_t port; - port = xc_evtchn_pending(state->xce_handle); + port = xenevtchn_pending(state->xce_handle); if (port == state->bufioreq_local_port) { timer_mod(state->buffered_io_timer, BUFFER_IO_MAX_DELAY + qemu_clock_get_ms(QEMU_CLOCK_REALTIME)); @@ -636,7 +724,7 @@ static ioreq_t *cpu_get_ioreq(XenIOState *state) } /* unmask the wanted port again */ - xc_evtchn_unmask(state->xce_handle, port); + xenevtchn_unmask(state->xce_handle, port); /* get the io packet from shared memory */ state->send_vcpu = i; @@ -647,7 +735,7 @@ static ioreq_t *cpu_get_ioreq(XenIOState *state) return NULL; } -static uint32_t do_inp(pio_addr_t addr, unsigned long size) +static uint32_t do_inp(uint32_t addr, unsigned long size) { switch (size) { case 1: @@ -657,11 +745,11 @@ static uint32_t do_inp(pio_addr_t addr, unsigned long size) case 4: return cpu_inl(addr); default: - hw_error("inp: bad size: %04"FMT_pioaddr" %lx", addr, size); + hw_error("inp: bad size: %04x %lx", addr, size); } } -static void do_outp(pio_addr_t addr, +static void do_outp(uint32_t addr, unsigned long size, uint32_t val) { switch (size) { @@ -672,7 +760,7 @@ static void do_outp(pio_addr_t addr, case 4: return cpu_outl(addr, val); default: - hw_error("outp: bad size: %04"FMT_pioaddr" %lx", addr, size); + hw_error("outp: bad size: %04x %lx", addr, size); } } @@ -716,9 +804,14 @@ static void cpu_ioreq_pio(ioreq_t *req) { uint32_t i; + trace_cpu_ioreq_pio(req, req->dir, req->df, req->data_is_ptr, req->addr, + req->data, req->count, req->size); + if (req->dir == IOREQ_READ) { if (!req->data_is_ptr) { req->data = do_inp(req->addr, req->size); + trace_cpu_ioreq_pio_read_reg(req, req->data, req->addr, + req->size); } else { uint32_t tmp; @@ -729,6 +822,8 @@ static void cpu_ioreq_pio(ioreq_t *req) } } else if (req->dir == IOREQ_WRITE) { if (!req->data_is_ptr) { + trace_cpu_ioreq_pio_write_reg(req, req->data, req->addr, + req->size); do_outp(req->addr, req->size, req->data); } else { for (i = 0; i < req->count; i++) { @@ -745,6 +840,9 @@ static void cpu_ioreq_move(ioreq_t *req) { uint32_t i; + trace_cpu_ioreq_move(req, req->dir, req->df, req->data_is_ptr, req->addr, + req->data, req->count, req->size); + if (!req->data_is_ptr) { if (req->dir == IOREQ_READ) { for (i = 0; i < req->count; i++) { @@ -772,13 +870,63 @@ static void cpu_ioreq_move(ioreq_t *req) } } -static void handle_ioreq(ioreq_t *req) +static void regs_to_cpu(vmware_regs_t *vmport_regs, ioreq_t *req) { + X86CPU *cpu; + CPUX86State *env; + + cpu = X86_CPU(current_cpu); + env = &cpu->env; + env->regs[R_EAX] = req->data; + env->regs[R_EBX] = vmport_regs->ebx; + env->regs[R_ECX] = vmport_regs->ecx; + env->regs[R_EDX] = vmport_regs->edx; + env->regs[R_ESI] = vmport_regs->esi; + env->regs[R_EDI] = vmport_regs->edi; +} + +static void regs_from_cpu(vmware_regs_t *vmport_regs) +{ + X86CPU *cpu = X86_CPU(current_cpu); + CPUX86State *env = &cpu->env; + + vmport_regs->ebx = env->regs[R_EBX]; + vmport_regs->ecx = env->regs[R_ECX]; + vmport_regs->edx = env->regs[R_EDX]; + vmport_regs->esi = env->regs[R_ESI]; + vmport_regs->edi = env->regs[R_EDI]; +} + +static void handle_vmport_ioreq(XenIOState *state, ioreq_t *req) +{ + vmware_regs_t *vmport_regs; + + assert(state->shared_vmport_page); + vmport_regs = + &state->shared_vmport_page->vcpu_vmport_regs[state->send_vcpu]; + QEMU_BUILD_BUG_ON(sizeof(*req) < sizeof(*vmport_regs)); + + current_cpu = state->cpu_by_vcpu_id[state->send_vcpu]; + regs_to_cpu(vmport_regs, req); + cpu_ioreq_pio(req); + regs_from_cpu(vmport_regs); + current_cpu = NULL; +} + +static void handle_ioreq(XenIOState *state, ioreq_t *req) +{ + trace_handle_ioreq(req, req->type, req->dir, req->df, req->data_is_ptr, + req->addr, req->data, req->count, req->size); + if (!req->data_is_ptr && (req->dir == IOREQ_WRITE) && (req->size < sizeof (target_ulong))) { req->data &= ((target_ulong) 1 << (8 * req->size)) - 1; } + if (req->dir == IOREQ_WRITE) + trace_handle_ioreq_write(req, req->type, req->df, req->data_is_ptr, + req->addr, req->data, req->count, req->size); + switch (req->type) { case IOREQ_TYPE_PIO: cpu_ioreq_pio(req); @@ -786,31 +934,70 @@ static void handle_ioreq(ioreq_t *req) case IOREQ_TYPE_COPY: cpu_ioreq_move(req); break; + case IOREQ_TYPE_VMWARE_PORT: + handle_vmport_ioreq(state, req); + break; case IOREQ_TYPE_TIMEOFFSET: break; case IOREQ_TYPE_INVALIDATE: xen_invalidate_map_cache(); break; + case IOREQ_TYPE_PCI_CONFIG: { + uint32_t sbdf = req->addr >> 32; + uint32_t val; + + /* Fake a write to port 0xCF8 so that + * the config space access will target the + * correct device model. + */ + val = (1u << 31) | + ((req->addr & 0x0f00) << 16) | + ((sbdf & 0xffff) << 8) | + (req->addr & 0xfc); + do_outp(0xcf8, 4, val); + + /* Now issue the config space access via + * port 0xCFC + */ + req->addr = 0xcfc | (req->addr & 0x03); + cpu_ioreq_pio(req); + break; + } default: hw_error("Invalid ioreq type 0x%x\n", req->type); } + if (req->dir == IOREQ_READ) { + trace_handle_ioreq_read(req, req->type, req->df, req->data_is_ptr, + req->addr, req->data, req->count, req->size); + } } static int handle_buffered_iopage(XenIOState *state) { + buffered_iopage_t *buf_page = state->buffered_io_page; buf_ioreq_t *buf_req = NULL; ioreq_t req; int qw; - if (!state->buffered_io_page) { + if (!buf_page) { return 0; } memset(&req, 0x00, sizeof(req)); - while (state->buffered_io_page->read_pointer != state->buffered_io_page->write_pointer) { - buf_req = &state->buffered_io_page->buf_ioreq[ - state->buffered_io_page->read_pointer % IOREQ_BUFFER_SLOT_NUM]; + for (;;) { + uint32_t rdptr = buf_page->read_pointer, wrptr; + + xen_rmb(); + wrptr = buf_page->write_pointer; + xen_rmb(); + if (rdptr != buf_page->read_pointer) { + continue; + } + if (rdptr == wrptr) { + break; + } + buf_req = &buf_page->buf_ioreq[rdptr % IOREQ_BUFFER_SLOT_NUM]; req.size = 1UL << buf_req->size; req.count = 1; req.addr = buf_req->addr; @@ -822,15 +1009,14 @@ static int handle_buffered_iopage(XenIOState *state) req.data_is_ptr = 0; qw = (req.size == 8); if (qw) { - buf_req = &state->buffered_io_page->buf_ioreq[ - (state->buffered_io_page->read_pointer + 1) % IOREQ_BUFFER_SLOT_NUM]; + buf_req = &buf_page->buf_ioreq[(rdptr + 1) % + IOREQ_BUFFER_SLOT_NUM]; req.data |= ((uint64_t)buf_req->data) << 32; } - handle_ioreq(&req); + handle_ioreq(state, &req); - xen_mb(); - state->buffered_io_page->read_pointer += qw ? 2 : 1; + atomic_add(&buf_page->read_pointer, qw + 1); } return req.count; @@ -845,7 +1031,7 @@ static void handle_buffered_io(void *opaque) BUFFER_IO_MAX_DELAY + qemu_clock_get_ms(QEMU_CLOCK_REALTIME)); } else { timer_del(state->buffered_io_timer); - xc_evtchn_unmask(state->xce_handle, state->bufioreq_local_port); + xenevtchn_unmask(state->xce_handle, state->bufioreq_local_port); } } @@ -856,14 +1042,14 @@ static void cpu_handle_ioreq(void *opaque) handle_buffered_iopage(state); if (req) { - handle_ioreq(req); + handle_ioreq(state, req); if (req->state != STATE_IOREQ_INPROCESS) { fprintf(stderr, "Badness in I/O request ... not in service?!: " "%x, ptr: %x, port: %"PRIx64", " - "data: %"PRIx64", count: %" FMT_ioreq_size ", size: %" FMT_ioreq_size "\n", + "data: %"PRIx64", count: %u, size: %u, type: %u\n", req->state, req->data_is_ptr, req->addr, - req->data, req->count, req->size); + req->data, req->count, req->size, req->type); destroy_hvm_domain(false); return; } @@ -887,7 +1073,8 @@ static void cpu_handle_ioreq(void *opaque) } req->state = STATE_IORESP_READY; - xc_evtchn_notify(state->xce_handle, state->ioreq_local_port[state->send_vcpu]); + xenevtchn_notify(state->xce_handle, + state->ioreq_local_port[state->send_vcpu]); } } @@ -895,14 +1082,22 @@ static void xen_main_loop_prepare(XenIOState *state) { int evtchn_fd = -1; - if (state->xce_handle != XC_HANDLER_INITIAL_VALUE) { - evtchn_fd = xc_evtchn_fd(state->xce_handle); + if (state->xce_handle != NULL) { + evtchn_fd = xenevtchn_fd(state->xce_handle); } state->buffered_io_timer = timer_new_ms(QEMU_CLOCK_REALTIME, handle_buffered_io, state); if (evtchn_fd != -1) { + CPUState *cpu_state; + + DPRINTF("%s: Init cpu_by_vcpu_id\n", __func__); + CPU_FOREACH(cpu_state) { + DPRINTF("%s: cpu_by_vcpu_id[%d]=%p\n", + __func__, cpu_state->cpu_index, cpu_state); + state->cpu_by_vcpu_id[cpu_state->cpu_index] = cpu_state; + } qemu_set_fd_handler(evtchn_fd, cpu_handle_ioreq, NULL, state); } } @@ -911,17 +1106,22 @@ static void xen_main_loop_prepare(XenIOState *state) static void xen_hvm_change_state_handler(void *opaque, int running, RunState rstate) { - XenIOState *xstate = opaque; + XenIOState *state = opaque; + if (running) { - xen_main_loop_prepare(xstate); + xen_main_loop_prepare(state); } + + xen_set_ioreq_server_state(xen_xc, xen_domid, + state->ioservid, + (rstate == RUN_STATE_RUNNING)); } static void xen_exit_notifier(Notifier *n, void *data) { XenIOState *state = container_of(n, XenIOState, exit); - xc_evtchn_close(state->xce_handle); + xenevtchn_close(state->xce_handle); xs_daemon_close(state->xenstore); } @@ -978,28 +1178,32 @@ static void xen_wakeup_notifier(Notifier *notifier, void *data) xc_set_hvm_param(xen_xc, xen_domid, HVM_PARAM_ACPI_S_STATE, 0); } -int xen_hvm_init(ram_addr_t *below_4g_mem_size, ram_addr_t *above_4g_mem_size, - MemoryRegion **ram_memory) +void xen_hvm_init(PCMachineState *pcms, MemoryRegion **ram_memory) { int i, rc; - unsigned long ioreq_pfn; - unsigned long bufioreq_evtchn; + xen_pfn_t ioreq_pfn; + xen_pfn_t bufioreq_pfn; + evtchn_port_t bufioreq_evtchn; XenIOState *state; state = g_malloc0(sizeof (XenIOState)); - state->xce_handle = xen_xc_evtchn_open(NULL, 0); - if (state->xce_handle == XC_HANDLER_INITIAL_VALUE) { + state->xce_handle = xenevtchn_open(NULL, 0); + if (state->xce_handle == NULL) { perror("xen: event channel open"); - g_free(state); - return -errno; + goto err; } state->xenstore = xs_daemon_open(); if (state->xenstore == NULL) { perror("xen: xenstore open"); - g_free(state); - return -errno; + goto err; + } + + rc = xen_create_ioreq_server(xen_xc, xen_domid, &state->ioservid); + if (rc < 0) { + perror("xen: ioreq server create"); + goto err; } state->exit.notify = xen_exit_notifier; @@ -1011,53 +1215,87 @@ int xen_hvm_init(ram_addr_t *below_4g_mem_size, ram_addr_t *above_4g_mem_size, state->wakeup.notify = xen_wakeup_notifier; qemu_register_wakeup_notifier(&state->wakeup); - xc_get_hvm_param(xen_xc, xen_domid, HVM_PARAM_IOREQ_PFN, &ioreq_pfn); + rc = xen_get_ioreq_server_info(xen_xc, xen_domid, state->ioservid, + &ioreq_pfn, &bufioreq_pfn, + &bufioreq_evtchn); + if (rc < 0) { + error_report("failed to get ioreq server info: error %d handle=%p", + errno, xen_xc); + goto err; + } + DPRINTF("shared page at pfn %lx\n", ioreq_pfn); - state->shared_page = xc_map_foreign_range(xen_xc, xen_domid, XC_PAGE_SIZE, - PROT_READ|PROT_WRITE, ioreq_pfn); + DPRINTF("buffered io page at pfn %lx\n", bufioreq_pfn); + DPRINTF("buffered io evtchn is %x\n", bufioreq_evtchn); + + state->shared_page = xenforeignmemory_map(xen_fmem, xen_domid, + PROT_READ|PROT_WRITE, + 1, &ioreq_pfn, NULL); if (state->shared_page == NULL) { - hw_error("map shared IO page returned error %d handle=" XC_INTERFACE_FMT, - errno, xen_xc); + error_report("map shared IO page returned error %d handle=%p", + errno, xen_xc); + goto err; + } + + rc = xen_get_vmport_regs_pfn(xen_xc, xen_domid, &ioreq_pfn); + if (!rc) { + DPRINTF("shared vmport page at pfn %lx\n", ioreq_pfn); + state->shared_vmport_page = + xenforeignmemory_map(xen_fmem, xen_domid, PROT_READ|PROT_WRITE, + 1, &ioreq_pfn, NULL); + if (state->shared_vmport_page == NULL) { + error_report("map shared vmport IO page returned error %d handle=%p", + errno, xen_xc); + goto err; + } + } else if (rc != -ENOSYS) { + error_report("get vmport regs pfn returned error %d, rc=%d", + errno, rc); + goto err; } - xc_get_hvm_param(xen_xc, xen_domid, HVM_PARAM_BUFIOREQ_PFN, &ioreq_pfn); - DPRINTF("buffered io page at pfn %lx\n", ioreq_pfn); - state->buffered_io_page = xc_map_foreign_range(xen_xc, xen_domid, XC_PAGE_SIZE, - PROT_READ|PROT_WRITE, ioreq_pfn); + state->buffered_io_page = xenforeignmemory_map(xen_fmem, xen_domid, + PROT_READ|PROT_WRITE, + 1, &bufioreq_pfn, NULL); if (state->buffered_io_page == NULL) { - hw_error("map buffered IO page returned error %d", errno); + error_report("map buffered IO page returned error %d", errno); + goto err; + } + + /* Note: cpus is empty at this point in init */ + state->cpu_by_vcpu_id = g_malloc0(max_cpus * sizeof(CPUState *)); + + rc = xen_set_ioreq_server_state(xen_xc, xen_domid, state->ioservid, true); + if (rc < 0) { + error_report("failed to enable ioreq server info: error %d handle=%p", + errno, xen_xc); + goto err; } state->ioreq_local_port = g_malloc0(max_cpus * sizeof (evtchn_port_t)); /* FIXME: how about if we overflow the page here? */ for (i = 0; i < max_cpus; i++) { - rc = xc_evtchn_bind_interdomain(state->xce_handle, xen_domid, + rc = xenevtchn_bind_interdomain(state->xce_handle, xen_domid, xen_vcpu_eport(state->shared_page, i)); if (rc == -1) { - fprintf(stderr, "bind interdomain ioctl error %d\n", errno); - return -1; + error_report("shared evtchn %d bind error %d", i, errno); + goto err; } state->ioreq_local_port[i] = rc; } - rc = xc_get_hvm_param(xen_xc, xen_domid, HVM_PARAM_BUFIOREQ_EVTCHN, - &bufioreq_evtchn); - if (rc < 0) { - fprintf(stderr, "failed to get HVM_PARAM_BUFIOREQ_EVTCHN\n"); - return -1; - } - rc = xc_evtchn_bind_interdomain(state->xce_handle, xen_domid, - (uint32_t)bufioreq_evtchn); + rc = xenevtchn_bind_interdomain(state->xce_handle, xen_domid, + bufioreq_evtchn); if (rc == -1) { - fprintf(stderr, "bind interdomain ioctl error %d\n", errno); - return -1; + error_report("buffered evtchn bind error %d", errno); + goto err; } state->bufioreq_local_port = rc; /* Init RAM management */ xen_map_cache_init(xen_phys_offset_to_gaddr, state); - xen_ram_init(below_4g_mem_size, above_4g_mem_size, ram_size, ram_memory); + xen_ram_init(pcms, ram_size, ram_memory); qemu_add_vm_change_state_handler(xen_hvm_change_state_handler, state); @@ -1066,26 +1304,35 @@ int xen_hvm_init(ram_addr_t *below_4g_mem_size, ram_addr_t *above_4g_mem_size, memory_listener_register(&state->memory_listener, &address_space_memory); state->log_for_dirtybit = NULL; + state->io_listener = xen_io_listener; + memory_listener_register(&state->io_listener, &address_space_io); + + state->device_listener = xen_device_listener; + device_listener_register(&state->device_listener); + /* Initialize backend core & drivers */ if (xen_be_init() != 0) { - fprintf(stderr, "%s: xen backend core setup failed\n", __FUNCTION__); - exit(1); + error_report("xen backend core setup failed"); + goto err; } xen_be_register("console", &xen_console_ops); xen_be_register("vkbd", &xen_kbdmouse_ops); xen_be_register("qdisk", &xen_blkdev_ops); xen_read_physmap(state); + return; - return 0; +err: + error_report("xen hardware virtual machine initialisation failed"); + exit(1); } void destroy_hvm_domain(bool reboot) { - XenXC xc_handle; + xc_interface *xc_handle; int sts; - xc_handle = xen_xc_interface_open(0, 0, 0); - if (xc_handle == XC_HANDLER_INITIAL_VALUE) { + xc_handle = xc_interface_open(0, 0, 0); + if (xc_handle == NULL) { fprintf(stderr, "Cannot acquire xenctrl handle\n"); } else { sts = xc_domain_shutdown(xc_handle, xen_domid,