X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?p=kvmfornfv.git;a=blobdiff_plain;f=qemu%2Fxen-hvm.c;h=039680a6d905bd19a792330f1bcd50c127fd1f21;hp=040846236c93849091f5514d0282c5250f547afd;hb=437fd90c0250dee670290f9b714253671a990160;hpb=5bbd6fe9b8bab2a93e548c5a53b032d1939eec05 diff --git a/qemu/xen-hvm.c b/qemu/xen-hvm.c index 040846236..039680a6d 100644 --- a/qemu/xen-hvm.c +++ b/qemu/xen-hvm.c @@ -8,15 +8,18 @@ * GNU GPL, version 2 or (at your option) any later version. */ +#include "qemu/osdep.h" #include #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" @@ -64,17 +67,6 @@ struct shared_vmport_iopage { typedef struct shared_vmport_iopage shared_vmport_iopage_t; #endif -#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 static inline uint32_t xen_vcpu_eport(shared_iopage_t *shared_page, int i) { return shared_page->vcpu_ioreq[i].vp_eport; @@ -83,8 +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 #define BUFFER_IO_MAX_DELAY 100 @@ -109,7 +99,7 @@ typedef struct XenIOState { /* 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; @@ -156,9 +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) @@ -180,8 +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(); @@ -198,23 +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, - &error_abort); + &error_fatal); *ram_memory_p = &ram_memory; vmstate_register_ram_global(&ram_memory); @@ -229,17 +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; @@ -267,7 +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); @@ -304,7 +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, @@ -345,10 +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; } } @@ -422,10 +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; } } @@ -439,24 +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) @@ -695,7 +675,7 @@ 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; @@ -715,7 +695,7 @@ 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)); @@ -734,7 +714,7 @@ 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; @@ -814,9 +794,14 @@ 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; @@ -827,6 +812,8 @@ 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++) { @@ -843,6 +830,9 @@ 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++) { @@ -915,11 +905,18 @@ static void handle_vmport_ioreq(XenIOState *state, ioreq_t *req) 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); @@ -959,23 +956,38 @@ static void handle_ioreq(XenIOState *state, ioreq_t *req) 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; @@ -987,15 +999,14 @@ 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(state, &req); - xen_mb(); - state->buffered_io_page->read_pointer += qw ? 2 : 1; + atomic_add(&buf_page->read_pointer, qw + 1); } return req.count; @@ -1010,7 +1021,7 @@ 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); } } @@ -1026,9 +1037,7 @@ static void cpu_handle_ioreq(void *opaque) 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 - ", type: %"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->type); destroy_hvm_domain(false); @@ -1054,7 +1063,8 @@ 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]); } } @@ -1062,8 +1072,8 @@ 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, @@ -1101,7 +1111,7 @@ 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); } @@ -1158,9 +1168,7 @@ static void xen_wakeup_notifier(Notifier *notifier, void *data) xc_set_hvm_param(xen_xc, xen_domid, HVM_PARAM_ACPI_S_STATE, 0); } -/* return 0 means OK, or -1 means critical issue -- will exit(1) */ -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; xen_pfn_t ioreq_pfn; @@ -1170,22 +1178,22 @@ int xen_hvm_init(ram_addr_t *below_4g_mem_size, ram_addr_t *above_4g_mem_size, 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"); - return -1; + goto err; } state->xenstore = xs_daemon_open(); if (state->xenstore == NULL) { perror("xen: xenstore open"); - return -1; + goto err; } rc = xen_create_ioreq_server(xen_xc, xen_domid, &state->ioservid); if (rc < 0) { perror("xen: ioreq server create"); - return -1; + goto err; } state->exit.notify = xen_exit_notifier; @@ -1201,41 +1209,47 @@ int xen_hvm_init(ram_addr_t *below_4g_mem_size, ram_addr_t *above_4g_mem_size, &ioreq_pfn, &bufioreq_pfn, &bufioreq_evtchn); if (rc < 0) { - hw_error("failed to get ioreq server info: error %d handle=" XC_INTERFACE_FMT, - errno, xen_xc); + 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); DPRINTF("buffered io page at pfn %lx\n", bufioreq_pfn); DPRINTF("buffered io evtchn is %x\n", bufioreq_evtchn); - state->shared_page = xc_map_foreign_range(xen_xc, xen_domid, XC_PAGE_SIZE, - PROT_READ|PROT_WRITE, ioreq_pfn); + 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 = - xc_map_foreign_range(xen_xc, xen_domid, XC_PAGE_SIZE, - PROT_READ|PROT_WRITE, ioreq_pfn); + xenforeignmemory_map(xen_fmem, xen_domid, PROT_READ|PROT_WRITE, + 1, &ioreq_pfn, NULL); if (state->shared_vmport_page == NULL) { - hw_error("map shared vmport IO page returned error %d handle=" - XC_INTERFACE_FMT, errno, xen_xc); + error_report("map shared vmport IO page returned error %d handle=%p", + errno, xen_xc); + goto err; } } else if (rc != -ENOSYS) { - hw_error("get vmport regs pfn returned error %d, rc=%d", errno, rc); + error_report("get vmport regs pfn returned error %d, rc=%d", + errno, rc); + goto err; } - state->buffered_io_page = xc_map_foreign_range(xen_xc, xen_domid, - XC_PAGE_SIZE, + state->buffered_io_page = xenforeignmemory_map(xen_fmem, xen_domid, PROT_READ|PROT_WRITE, - bufioreq_pfn); + 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 */ @@ -1243,34 +1257,35 @@ int xen_hvm_init(ram_addr_t *below_4g_mem_size, ram_addr_t *above_4g_mem_size, rc = xen_set_ioreq_server_state(xen_xc, xen_domid, state->ioservid, true); if (rc < 0) { - hw_error("failed to enable ioreq server info: error %d handle=" XC_INTERFACE_FMT, - errno, xen_xc); + 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, "shared evtchn %d bind error %d\n", i, errno); - return -1; + error_report("shared evtchn %d bind error %d", i, errno); + goto err; } state->ioreq_local_port[i] = rc; } - rc = xc_evtchn_bind_interdomain(state->xce_handle, xen_domid, + rc = xenevtchn_bind_interdomain(state->xce_handle, xen_domid, bufioreq_evtchn); if (rc == -1) { - fprintf(stderr, "buffered evtchn bind 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); @@ -1287,24 +1302,27 @@ int xen_hvm_init(ram_addr_t *below_4g_mem_size, ram_addr_t *above_4g_mem_size, /* Initialize backend core & drivers */ if (xen_be_init() != 0) { - fprintf(stderr, "%s: xen backend core setup failed\n", __FUNCTION__); - return -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,