diff options
Diffstat (limited to 'hw')
169 files changed, 6784 insertions, 2262 deletions
diff --git a/hw/9pfs/9p.c b/hw/9pfs/9p.c index faebd91f5f..06b6e7ec66 100644 --- a/hw/9pfs/9p.c +++ b/hw/9pfs/9p.c @@ -47,7 +47,7 @@ ssize_t pdu_marshal(V9fsPDU *pdu, size_t offset, const char *fmt, ...) va_list ap; va_start(ap, fmt); - ret = virtio_pdu_vmarshal(pdu, offset, fmt, ap); + ret = pdu->s->transport->pdu_vmarshal(pdu, offset, fmt, ap); va_end(ap); return ret; @@ -59,7 +59,7 @@ ssize_t pdu_unmarshal(V9fsPDU *pdu, size_t offset, const char *fmt, ...) va_list ap; va_start(ap, fmt); - ret = virtio_pdu_vunmarshal(pdu, offset, fmt, ap); + ret = pdu->s->transport->pdu_vunmarshal(pdu, offset, fmt, ap); va_end(ap); return ret; @@ -67,7 +67,7 @@ ssize_t pdu_unmarshal(V9fsPDU *pdu, size_t offset, const char *fmt, ...) static void pdu_push_and_notify(V9fsPDU *pdu) { - virtio_9p_push_and_notify(pdu); + pdu->s->transport->push_and_notify(pdu); } static int omode_to_uflags(int8_t mode) @@ -979,6 +979,7 @@ static void coroutine_fn v9fs_attach(void *opaque) size_t offset = 7; V9fsQID qid; ssize_t err; + Error *local_err = NULL; v9fs_string_init(&uname); v9fs_string_init(&aname); @@ -1007,26 +1008,36 @@ static void coroutine_fn v9fs_attach(void *opaque) clunk_fid(s, fid); goto out; } - err = pdu_marshal(pdu, offset, "Q", &qid); - if (err < 0) { - clunk_fid(s, fid); - goto out; - } - err += offset; - memcpy(&s->root_qid, &qid, sizeof(qid)); - trace_v9fs_attach_return(pdu->tag, pdu->id, - qid.type, qid.version, qid.path); + /* * disable migration if we haven't done already. * attach could get called multiple times for the same export. */ if (!s->migration_blocker) { - s->root_fid = fid; error_setg(&s->migration_blocker, "Migration is disabled when VirtFS export path '%s' is mounted in the guest using mount_tag '%s'", s->ctx.fs_root ? s->ctx.fs_root : "NULL", s->tag); - migrate_add_blocker(s->migration_blocker); + err = migrate_add_blocker(s->migration_blocker, &local_err); + if (local_err) { + error_free(local_err); + error_free(s->migration_blocker); + s->migration_blocker = NULL; + clunk_fid(s, fid); + goto out; + } + s->root_fid = fid; + } + + err = pdu_marshal(pdu, offset, "Q", &qid); + if (err < 0) { + clunk_fid(s, fid); + goto out; } + err += offset; + + memcpy(&s->root_qid, &qid, sizeof(qid)); + trace_v9fs_attach_return(pdu->tag, pdu->id, + qid.type, qid.version, qid.path); out: put_fid(pdu, fidp); out_nofid: @@ -1633,14 +1644,43 @@ out_nofid: pdu_complete(pdu, err); } +/* + * Create a QEMUIOVector for a sub-region of PDU iovecs + * + * @qiov: uninitialized QEMUIOVector + * @skip: number of bytes to skip from beginning of PDU + * @size: number of bytes to include + * @is_write: true - write, false - read + * + * The resulting QEMUIOVector has heap-allocated iovecs and must be cleaned up + * with qemu_iovec_destroy(). + */ +static void v9fs_init_qiov_from_pdu(QEMUIOVector *qiov, V9fsPDU *pdu, + size_t skip, size_t size, + bool is_write) +{ + QEMUIOVector elem; + struct iovec *iov; + unsigned int niov; + + if (is_write) { + pdu->s->transport->init_out_iov_from_pdu(pdu, &iov, &niov); + } else { + pdu->s->transport->init_in_iov_from_pdu(pdu, &iov, &niov, size); + } + + qemu_iovec_init_external(&elem, iov, niov); + qemu_iovec_init(qiov, niov); + qemu_iovec_concat(qiov, &elem, skip, size); +} + static int v9fs_xattr_read(V9fsState *s, V9fsPDU *pdu, V9fsFidState *fidp, uint64_t off, uint32_t max_count) { ssize_t err; size_t offset = 7; uint64_t read_count; - V9fsVirtioState *v = container_of(s, V9fsVirtioState, state); - VirtQueueElement *elem = v->elems[pdu->idx]; + QEMUIOVector qiov_full; if (fidp->fs.xattr.len < off) { read_count = 0; @@ -1656,9 +1696,11 @@ static int v9fs_xattr_read(V9fsState *s, V9fsPDU *pdu, V9fsFidState *fidp, } offset += err; - err = v9fs_pack(elem->in_sg, elem->in_num, offset, + v9fs_init_qiov_from_pdu(&qiov_full, pdu, 0, read_count, false); + err = v9fs_pack(qiov_full.iov, qiov_full.niov, offset, ((char *)fidp->fs.xattr.value) + off, read_count); + qemu_iovec_destroy(&qiov_full); if (err < 0) { return err; } @@ -1732,32 +1774,6 @@ static int coroutine_fn v9fs_do_readdir_with_stat(V9fsPDU *pdu, return count; } -/* - * Create a QEMUIOVector for a sub-region of PDU iovecs - * - * @qiov: uninitialized QEMUIOVector - * @skip: number of bytes to skip from beginning of PDU - * @size: number of bytes to include - * @is_write: true - write, false - read - * - * The resulting QEMUIOVector has heap-allocated iovecs and must be cleaned up - * with qemu_iovec_destroy(). - */ -static void v9fs_init_qiov_from_pdu(QEMUIOVector *qiov, V9fsPDU *pdu, - size_t skip, size_t size, - bool is_write) -{ - QEMUIOVector elem; - struct iovec *iov; - unsigned int niov; - - virtio_init_iov_from_pdu(pdu, &iov, &niov, is_write); - - qemu_iovec_init_external(&elem, iov, niov); - qemu_iovec_init(qiov, niov); - qemu_iovec_concat(qiov, &elem, skip, size); -} - static void coroutine_fn v9fs_read(void *opaque) { int32_t fid; @@ -3440,7 +3456,6 @@ void pdu_submit(V9fsPDU *pdu) /* Returns 0 on success, 1 on failure. */ int v9fs_device_realize_common(V9fsState *s, Error **errp) { - V9fsVirtioState *v = container_of(s, V9fsVirtioState, state); int i, len; struct stat stat; FsDriverEntry *fse; @@ -3451,9 +3466,9 @@ int v9fs_device_realize_common(V9fsState *s, Error **errp) QLIST_INIT(&s->free_list); QLIST_INIT(&s->active_list); for (i = 0; i < (MAX_REQ - 1); i++) { - QLIST_INSERT_HEAD(&s->free_list, &v->pdus[i], next); - v->pdus[i].s = s; - v->pdus[i].idx = i; + QLIST_INSERT_HEAD(&s->free_list, &s->pdus[i], next); + s->pdus[i].s = s; + s->pdus[i].idx = i; } v9fs_path_init(&path); @@ -3521,7 +3536,7 @@ int v9fs_device_realize_common(V9fsState *s, Error **errp) rc = 0; out: if (rc) { - if (s->ops->cleanup && s->ctx.private) { + if (s->ops && s->ops->cleanup && s->ctx.private) { s->ops->cleanup(&s->ctx); } g_free(s->tag); diff --git a/hw/9pfs/9p.h b/hw/9pfs/9p.h index 3976b7fe3d..b7e836251e 100644 --- a/hw/9pfs/9p.h +++ b/hw/9pfs/9p.h @@ -99,8 +99,8 @@ enum p9_proto_version { V9FS_PROTO_2000L = 0x02, }; -#define P9_NOTAG (u16)(~0) -#define P9_NOFID (u32)(~0) +#define P9_NOTAG UINT16_MAX +#define P9_NOFID UINT32_MAX #define P9_MAXWELEM 16 #define FID_REFERENCED 0x1 @@ -229,6 +229,8 @@ typedef struct V9fsState char *tag; enum p9_proto_version proto_version; int32_t msize; + V9fsPDU pdus[MAX_REQ]; + const struct V9fsTransport *transport; /* * lock ensuring atomic path update * on rename. @@ -342,4 +344,24 @@ void pdu_free(V9fsPDU *pdu); void pdu_submit(V9fsPDU *pdu); void v9fs_reset(V9fsState *s); +struct V9fsTransport { + ssize_t (*pdu_vmarshal)(V9fsPDU *pdu, size_t offset, const char *fmt, + va_list ap); + ssize_t (*pdu_vunmarshal)(V9fsPDU *pdu, size_t offset, const char *fmt, + va_list ap); + void (*init_in_iov_from_pdu)(V9fsPDU *pdu, struct iovec **piov, + unsigned int *pniov, size_t size); + void (*init_out_iov_from_pdu)(V9fsPDU *pdu, struct iovec **piov, + unsigned int *pniov); + void (*push_and_notify)(V9fsPDU *pdu); +}; + +static inline int v9fs_register_transport(V9fsState *s, + const struct V9fsTransport *t) +{ + assert(!s->transport); + s->transport = t; + return 0; +} + #endif diff --git a/hw/9pfs/virtio-9p-device.c b/hw/9pfs/virtio-9p-device.c index 1782e4a227..27a4a32f5c 100644 --- a/hw/9pfs/virtio-9p-device.c +++ b/hw/9pfs/virtio-9p-device.c @@ -20,7 +20,9 @@ #include "hw/virtio/virtio-access.h" #include "qemu/iov.h" -void virtio_9p_push_and_notify(V9fsPDU *pdu) +static const struct V9fsTransport virtio_9p_transport; + +static void virtio_9p_push_and_notify(V9fsPDU *pdu) { V9fsState *s = pdu->s; V9fsVirtioState *v = container_of(s, V9fsVirtioState, state); @@ -126,6 +128,7 @@ static void virtio_9p_device_realize(DeviceState *dev, Error **errp) v->config_size = sizeof(struct virtio_9p_config) + strlen(s->fsconf.tag); virtio_init(vdev, "virtio-9p", VIRTIO_ID_9P, v->config_size); v->vq = virtio_add_queue(vdev, MAX_REQ, handle_9p_output); + v9fs_register_transport(s, &virtio_9p_transport); out: return; @@ -148,8 +151,8 @@ static void virtio_9p_reset(VirtIODevice *vdev) v9fs_reset(&v->state); } -ssize_t virtio_pdu_vmarshal(V9fsPDU *pdu, size_t offset, - const char *fmt, va_list ap) +static ssize_t virtio_pdu_vmarshal(V9fsPDU *pdu, size_t offset, + const char *fmt, va_list ap) { V9fsState *s = pdu->s; V9fsVirtioState *v = container_of(s, V9fsVirtioState, state); @@ -158,8 +161,8 @@ ssize_t virtio_pdu_vmarshal(V9fsPDU *pdu, size_t offset, return v9fs_iov_vmarshal(elem->in_sg, elem->in_num, offset, 1, fmt, ap); } -ssize_t virtio_pdu_vunmarshal(V9fsPDU *pdu, size_t offset, - const char *fmt, va_list ap) +static ssize_t virtio_pdu_vunmarshal(V9fsPDU *pdu, size_t offset, + const char *fmt, va_list ap) { V9fsState *s = pdu->s; V9fsVirtioState *v = container_of(s, V9fsVirtioState, state); @@ -168,22 +171,37 @@ ssize_t virtio_pdu_vunmarshal(V9fsPDU *pdu, size_t offset, return v9fs_iov_vunmarshal(elem->out_sg, elem->out_num, offset, 1, fmt, ap); } -void virtio_init_iov_from_pdu(V9fsPDU *pdu, struct iovec **piov, - unsigned int *pniov, bool is_write) +/* The size parameter is used by other transports. Do not drop it. */ +static void virtio_init_in_iov_from_pdu(V9fsPDU *pdu, struct iovec **piov, + unsigned int *pniov, size_t size) { V9fsState *s = pdu->s; V9fsVirtioState *v = container_of(s, V9fsVirtioState, state); VirtQueueElement *elem = v->elems[pdu->idx]; - if (is_write) { - *piov = elem->out_sg; - *pniov = elem->out_num; - } else { - *piov = elem->in_sg; - *pniov = elem->in_num; - } + *piov = elem->in_sg; + *pniov = elem->in_num; } +static void virtio_init_out_iov_from_pdu(V9fsPDU *pdu, struct iovec **piov, + unsigned int *pniov) +{ + V9fsState *s = pdu->s; + V9fsVirtioState *v = container_of(s, V9fsVirtioState, state); + VirtQueueElement *elem = v->elems[pdu->idx]; + + *piov = elem->out_sg; + *pniov = elem->out_num; +} + +static const struct V9fsTransport virtio_9p_transport = { + .pdu_vmarshal = virtio_pdu_vmarshal, + .pdu_vunmarshal = virtio_pdu_vunmarshal, + .init_in_iov_from_pdu = virtio_init_in_iov_from_pdu, + .init_out_iov_from_pdu = virtio_init_out_iov_from_pdu, + .push_and_notify = virtio_9p_push_and_notify, +}; + /* virtio-9p device */ static const VMStateDescription vmstate_virtio_9p = { diff --git a/hw/9pfs/virtio-9p.h b/hw/9pfs/virtio-9p.h index 25c47c7cb6..e763da2c02 100644 --- a/hw/9pfs/virtio-9p.h +++ b/hw/9pfs/virtio-9p.h @@ -10,20 +10,10 @@ typedef struct V9fsVirtioState VirtIODevice parent_obj; VirtQueue *vq; size_t config_size; - V9fsPDU pdus[MAX_REQ]; VirtQueueElement *elems[MAX_REQ]; V9fsState state; } V9fsVirtioState; -void virtio_9p_push_and_notify(V9fsPDU *pdu); - -ssize_t virtio_pdu_vmarshal(V9fsPDU *pdu, size_t offset, - const char *fmt, va_list ap); -ssize_t virtio_pdu_vunmarshal(V9fsPDU *pdu, size_t offset, - const char *fmt, va_list ap); -void virtio_init_iov_from_pdu(V9fsPDU *pdu, struct iovec **piov, - unsigned int *pniov, bool is_write); - #define TYPE_VIRTIO_9P "virtio-9p-device" #define VIRTIO_9P(obj) \ OBJECT_CHECK(V9fsVirtioState, (obj), TYPE_VIRTIO_9P) diff --git a/hw/Makefile.objs b/hw/Makefile.objs index 0ffd281145..a2c61f6b09 100644 --- a/hw/Makefile.objs +++ b/hw/Makefile.objs @@ -1,5 +1,5 @@ devices-dirs-$(call land, $(CONFIG_VIRTIO),$(call land,$(CONFIG_VIRTFS),$(CONFIG_PCI))) += 9pfs/ -devices-dirs-$(CONFIG_ACPI) += acpi/ +devices-dirs-$(CONFIG_SOFTMMU) += acpi/ devices-dirs-$(CONFIG_SOFTMMU) += adc/ devices-dirs-$(CONFIG_SOFTMMU) += audio/ devices-dirs-$(CONFIG_SOFTMMU) += block/ @@ -29,11 +29,11 @@ devices-dirs-$(CONFIG_SOFTMMU) += timer/ devices-dirs-$(CONFIG_TPM) += tpm/ devices-dirs-$(CONFIG_SOFTMMU) += usb/ devices-dirs-$(CONFIG_SOFTMMU) += vfio/ -devices-dirs-$(CONFIG_VIRTIO) += virtio/ +devices-dirs-$(CONFIG_SOFTMMU) += virtio/ devices-dirs-$(CONFIG_SOFTMMU) += watchdog/ devices-dirs-$(CONFIG_SOFTMMU) += xen/ devices-dirs-$(CONFIG_MEM_HOTPLUG) += mem/ -devices-dirs-$(CONFIG_SMBIOS) += smbios/ +devices-dirs-$(CONFIG_SOFTMMU) += smbios/ devices-dirs-y += core/ common-obj-y += $(devices-dirs-y) obj-y += $(devices-dirs-y) diff --git a/hw/acpi/Makefile.objs b/hw/acpi/Makefile.objs index 489e63bb75..6acf79860a 100644 --- a/hw/acpi/Makefile.objs +++ b/hw/acpi/Makefile.objs @@ -1,10 +1,19 @@ +ifeq ($(CONFIG_ACPI),y) common-obj-$(CONFIG_ACPI_X86) += core.o piix4.o pcihp.o common-obj-$(CONFIG_ACPI_X86_ICH) += ich9.o tco.o common-obj-$(CONFIG_ACPI_CPU_HOTPLUG) += cpu_hotplug.o -common-obj-$(CONFIG_ACPI_MEMORY_HOTPLUG) += memory_hotplug.o memory_hotplug_acpi_table.o +common-obj-$(CONFIG_ACPI_MEMORY_HOTPLUG) += memory_hotplug.o common-obj-$(CONFIG_ACPI_CPU_HOTPLUG) += cpu.o common-obj-$(CONFIG_ACPI_NVDIMM) += nvdimm.o -common-obj-$(CONFIG_ACPI) += acpi_interface.o -common-obj-$(CONFIG_ACPI) += bios-linker-loader.o -common-obj-$(CONFIG_ACPI) += aml-build.o -common-obj-$(call land,$(CONFIG_ACPI),$(CONFIG_IPMI)) += ipmi.o +common-obj-$(call lnot,$(CONFIG_ACPI_X86)) += acpi-stub.o + +common-obj-y += acpi_interface.o +common-obj-y += bios-linker-loader.o +common-obj-y += aml-build.o + +common-obj-$(CONFIG_IPMI) += ipmi.o +common-obj-$(call lnot,$(CONFIG_IPMI)) += ipmi-stub.o +else +common-obj-y += acpi-stub.o +endif +common-obj-$(CONFIG_ALL) += acpi-stub.o ipmi-stub.o diff --git a/hw/acpi/acpi-stub.c b/hw/acpi/acpi-stub.c new file mode 100644 index 0000000000..26bd22f7ec --- /dev/null +++ b/hw/acpi/acpi-stub.c @@ -0,0 +1,29 @@ +/* + * ACPI stubs for platforms that don't support ACPI. + * + * Copyright (c) 2006 Fabrice Bellard + * Copyright (c) 2016 Red Hat, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qapi/qmp/qerror.h" +#include "qmp-commands.h" +#include "hw/acpi/acpi.h" + +void acpi_table_add(const QemuOpts *opts, Error **errp) +{ + error_setg(errp, QERR_UNSUPPORTED); +} diff --git a/hw/acpi/cpu.c b/hw/acpi/cpu.c index 5ac89fefaf..6017ca04bf 100644 --- a/hw/acpi/cpu.c +++ b/hw/acpi/cpu.c @@ -190,7 +190,7 @@ void cpu_hotplug_hw_init(MemoryRegion *as, Object *owner, { MachineState *machine = MACHINE(qdev_get_machine()); MachineClass *mc = MACHINE_GET_CLASS(machine); - CPUArchIdList *id_list; + const CPUArchIdList *id_list; int i; assert(mc->possible_cpu_arch_ids); @@ -201,7 +201,6 @@ void cpu_hotplug_hw_init(MemoryRegion *as, Object *owner, state->devs[i].cpu = id_list->cpus[i].cpu; state->devs[i].arch_id = id_list->cpus[i].arch_id; } - g_free(id_list); memory_region_init_io(&state->ctrl_reg, owner, &cpu_hotplug_ops, state, "acpi-mem-hotplug", ACPI_CPU_HOTPLUG_REG_LEN); memory_region_add_subregion(as, base_addr, &state->ctrl_reg); @@ -325,7 +324,7 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, Aml *one = aml_int(1); Aml *sb_scope = aml_scope("_SB"); MachineClass *mc = MACHINE_GET_CLASS(machine); - CPUArchIdList *arch_ids = mc->possible_cpu_arch_ids(machine); + const CPUArchIdList *arch_ids = mc->possible_cpu_arch_ids(machine); char *cphp_res_path = g_strdup_printf("%s." CPUHP_RES_DEVICE, res_root); Object *obj = object_resolve_path_type("", TYPE_ACPI_DEVICE_IF, NULL); AcpiDeviceIfClass *adevc = ACPI_DEVICE_IF_GET_CLASS(obj); @@ -574,5 +573,4 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, aml_append(table, method); g_free(cphp_res_path); - g_free(arch_ids); } diff --git a/hw/acpi/cpu_hotplug.c b/hw/acpi/cpu_hotplug.c index f15a2402fc..5243918125 100644 --- a/hw/acpi/cpu_hotplug.c +++ b/hw/acpi/cpu_hotplug.c @@ -128,7 +128,7 @@ void build_legacy_cpu_hotplug_aml(Aml *ctx, MachineState *machine, Aml *zero = aml_int(0); Aml *one = aml_int(1); MachineClass *mc = MACHINE_GET_CLASS(machine); - CPUArchIdList *apic_ids = mc->possible_cpu_arch_ids(machine); + const CPUArchIdList *apic_ids = mc->possible_cpu_arch_ids(machine); PCMachineState *pcms = PC_MACHINE(machine); /* @@ -329,8 +329,6 @@ void build_legacy_cpu_hotplug_aml(Aml *ctx, MachineState *machine, apic_idx = apic_id + 1; } aml_append(sb_scope, aml_name_decl(CPU_ON_BITMAP, pkg)); - g_free(apic_ids); - aml_append(ctx, sb_scope); method = aml_method("\\_GPE._E02", 0, AML_NOTSERIALIZED); diff --git a/hw/acpi/ich9.c b/hw/acpi/ich9.c index 830c475127..5c279bbaca 100644 --- a/hw/acpi/ich9.c +++ b/hw/acpi/ich9.c @@ -306,7 +306,8 @@ void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm, if (pm->acpi_memory_hotplug.is_enabled) { acpi_memory_hotplug_init(pci_address_space_io(lpc_pci), OBJECT(lpc_pci), - &pm->acpi_memory_hotplug); + &pm->acpi_memory_hotplug, + ACPI_MEMORY_HOTPLUG_BASE); } } diff --git a/hw/acpi/ipmi-stub.c b/hw/acpi/ipmi-stub.c new file mode 100644 index 0000000000..98b6dcee0d --- /dev/null +++ b/hw/acpi/ipmi-stub.c @@ -0,0 +1,14 @@ +/* + * IPMI ACPI firmware handling + * + * Copyright (c) 2015,2016 Corey Minyard, MontaVista Software, LLC + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "hw/acpi/ipmi.h" + +void build_acpi_ipmi_devices(Aml *table, BusState *bus) +{ +} diff --git a/hw/acpi/memory_hotplug.c b/hw/acpi/memory_hotplug.c index ec4e64b361..210073d283 100644 --- a/hw/acpi/memory_hotplug.c +++ b/hw/acpi/memory_hotplug.c @@ -7,6 +7,34 @@ #include "trace.h" #include "qapi-event.h" +#define MEMORY_SLOTS_NUMBER "MDNR" +#define MEMORY_HOTPLUG_IO_REGION "HPMR" +#define MEMORY_SLOT_ADDR_LOW "MRBL" +#define MEMORY_SLOT_ADDR_HIGH "MRBH" +#define MEMORY_SLOT_SIZE_LOW "MRLL" +#define MEMORY_SLOT_SIZE_HIGH "MRLH" +#define MEMORY_SLOT_PROXIMITY "MPX" +#define MEMORY_SLOT_ENABLED "MES" +#define MEMORY_SLOT_INSERT_EVENT "MINS" +#define MEMORY_SLOT_REMOVE_EVENT "MRMV" +#define MEMORY_SLOT_EJECT "MEJ" +#define MEMORY_SLOT_SLECTOR "MSEL" +#define MEMORY_SLOT_OST_EVENT "MOEV" +#define MEMORY_SLOT_OST_STATUS "MOSC" +#define MEMORY_SLOT_LOCK "MLCK" +#define MEMORY_SLOT_STATUS_METHOD "MRST" +#define MEMORY_SLOT_CRS_METHOD "MCRS" +#define MEMORY_SLOT_OST_METHOD "MOST" +#define MEMORY_SLOT_PROXIMITY_METHOD "MPXM" +#define MEMORY_SLOT_EJECT_METHOD "MEJ0" +#define MEMORY_SLOT_NOTIFY_METHOD "MTFY" +#define MEMORY_SLOT_SCAN_METHOD "MSCN" +#define MEMORY_HOTPLUG_DEVICE "MHPD" +#define MEMORY_HOTPLUG_IO_LEN 24 +#define MEMORY_DEVICES_CONTAINER "\\_SB.MHPC" + +static uint16_t memhp_io_base; + static ACPIOSTInfo *acpi_memory_device_status(int slot, MemStatus *mdev) { ACPIOSTInfo *info = g_new0(ACPIOSTInfo, 1); @@ -178,7 +206,7 @@ static const MemoryRegionOps acpi_memory_hotplug_ops = { }; void acpi_memory_hotplug_init(MemoryRegion *as, Object *owner, - MemHotplugState *state) + MemHotplugState *state, uint16_t io_base) { MachineState *machine = MACHINE(qdev_get_machine()); @@ -187,10 +215,12 @@ void acpi_memory_hotplug_init(MemoryRegion *as, Object *owner, return; } + assert(!memhp_io_base); + memhp_io_base = io_base; state->devs = g_malloc0(sizeof(*state->devs) * state->dev_count); memory_region_init_io(&state->io, owner, &acpi_memory_hotplug_ops, state, - "acpi-mem-hotplug", ACPI_MEMORY_HOTPLUG_IO_LEN); - memory_region_add_subregion(as, ACPI_MEMORY_HOTPLUG_BASE, &state->io); + "acpi-mem-hotplug", MEMORY_HOTPLUG_IO_LEN); + memory_region_add_subregion(as, memhp_io_base, &state->io); } /** @@ -306,3 +336,387 @@ const VMStateDescription vmstate_memory_hotplug = { VMSTATE_END_OF_LIST() } }; + +void build_memory_hotplug_aml(Aml *table, uint32_t nr_mem, + const char *res_root, + const char *event_handler_method) +{ + int i; + Aml *ifctx; + Aml *method; + Aml *dev_container; + Aml *mem_ctrl_dev; + char *mhp_res_path; + + if (!memhp_io_base) { + return; + } + + mhp_res_path = g_strdup_printf("%s." MEMORY_HOTPLUG_DEVICE, res_root); + mem_ctrl_dev = aml_device("%s", mhp_res_path); + { + Aml *crs; + + aml_append(mem_ctrl_dev, aml_name_decl("_HID", aml_string("PNP0A06"))); + aml_append(mem_ctrl_dev, + aml_name_decl("_UID", aml_string("Memory hotplug resources"))); + + crs = aml_resource_template(); + aml_append(crs, + aml_io(AML_DECODE16, memhp_io_base, memhp_io_base, 0, + MEMORY_HOTPLUG_IO_LEN) + ); + aml_append(mem_ctrl_dev, aml_name_decl("_CRS", crs)); + + aml_append(mem_ctrl_dev, aml_operation_region( + MEMORY_HOTPLUG_IO_REGION, AML_SYSTEM_IO, + aml_int(memhp_io_base), MEMORY_HOTPLUG_IO_LEN) + ); + + } + aml_append(table, mem_ctrl_dev); + + dev_container = aml_device(MEMORY_DEVICES_CONTAINER); + { + Aml *field; + Aml *one = aml_int(1); + Aml *zero = aml_int(0); + Aml *ret_val = aml_local(0); + Aml *slot_arg0 = aml_arg(0); + Aml *slots_nr = aml_name(MEMORY_SLOTS_NUMBER); + Aml *ctrl_lock = aml_name(MEMORY_SLOT_LOCK); + Aml *slot_selector = aml_name(MEMORY_SLOT_SLECTOR); + char *mmio_path = g_strdup_printf("%s." MEMORY_HOTPLUG_IO_REGION, + mhp_res_path); + + aml_append(dev_container, aml_name_decl("_HID", aml_string("PNP0A06"))); + aml_append(dev_container, + aml_name_decl("_UID", aml_string("DIMM devices"))); + + assert(nr_mem <= ACPI_MAX_RAM_SLOTS); + aml_append(dev_container, + aml_name_decl(MEMORY_SLOTS_NUMBER, aml_int(nr_mem)) + ); + + field = aml_field(mmio_path, AML_DWORD_ACC, + AML_NOLOCK, AML_PRESERVE); + aml_append(field, /* read only */ + aml_named_field(MEMORY_SLOT_ADDR_LOW, 32)); + aml_append(field, /* read only */ + aml_named_field(MEMORY_SLOT_ADDR_HIGH, 32)); + aml_append(field, /* read only */ + aml_named_field(MEMORY_SLOT_SIZE_LOW, 32)); + aml_append(field, /* read only */ + aml_named_field(MEMORY_SLOT_SIZE_HIGH, 32)); + aml_append(field, /* read only */ + aml_named_field(MEMORY_SLOT_PROXIMITY, 32)); + aml_append(dev_container, field); + + field = aml_field(mmio_path, AML_BYTE_ACC, + AML_NOLOCK, AML_WRITE_AS_ZEROS); + aml_append(field, aml_reserved_field(160 /* bits, Offset(20) */)); + aml_append(field, /* 1 if enabled, read only */ + aml_named_field(MEMORY_SLOT_ENABLED, 1)); + aml_append(field, + /*(read) 1 if has a insert event. (write) 1 to clear event */ + aml_named_field(MEMORY_SLOT_INSERT_EVENT, 1)); + aml_append(field, + /* (read) 1 if has a remove event. (write) 1 to clear event */ + aml_named_field(MEMORY_SLOT_REMOVE_EVENT, 1)); + aml_append(field, + /* initiates device eject, write only */ + aml_named_field(MEMORY_SLOT_EJECT, 1)); + aml_append(dev_container, field); + + field = aml_field(mmio_path, AML_DWORD_ACC, + AML_NOLOCK, AML_PRESERVE); + aml_append(field, /* DIMM selector, write only */ + aml_named_field(MEMORY_SLOT_SLECTOR, 32)); + aml_append(field, /* _OST event code, write only */ + aml_named_field(MEMORY_SLOT_OST_EVENT, 32)); + aml_append(field, /* _OST status code, write only */ + aml_named_field(MEMORY_SLOT_OST_STATUS, 32)); + aml_append(dev_container, field); + g_free(mmio_path); + + method = aml_method("_STA", 0, AML_NOTSERIALIZED); + ifctx = aml_if(aml_equal(slots_nr, zero)); + { + aml_append(ifctx, aml_return(zero)); + } + aml_append(method, ifctx); + /* present, functioning, decoding, not shown in UI */ + aml_append(method, aml_return(aml_int(0xB))); + aml_append(dev_container, method); + + aml_append(dev_container, aml_mutex(MEMORY_SLOT_LOCK, 0)); + + method = aml_method(MEMORY_SLOT_SCAN_METHOD, 0, AML_NOTSERIALIZED); + { + Aml *else_ctx; + Aml *while_ctx; + Aml *idx = aml_local(0); + Aml *eject_req = aml_int(3); + Aml *dev_chk = aml_int(1); + + ifctx = aml_if(aml_equal(slots_nr, zero)); + { + aml_append(ifctx, aml_return(zero)); + } + aml_append(method, ifctx); + + aml_append(method, aml_store(zero, idx)); + aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); + /* build AML that: + * loops over all slots and Notifies DIMMs with + * Device Check or Eject Request notifications if + * slot has corresponding status bit set and clears + * slot status. + */ + while_ctx = aml_while(aml_lless(idx, slots_nr)); + { + Aml *ins_evt = aml_name(MEMORY_SLOT_INSERT_EVENT); + Aml *rm_evt = aml_name(MEMORY_SLOT_REMOVE_EVENT); + + aml_append(while_ctx, aml_store(idx, slot_selector)); + ifctx = aml_if(aml_equal(ins_evt, one)); + { + aml_append(ifctx, + aml_call2(MEMORY_SLOT_NOTIFY_METHOD, + idx, dev_chk)); + aml_append(ifctx, aml_store(one, ins_evt)); + } + aml_append(while_ctx, ifctx); + + else_ctx = aml_else(); + ifctx = aml_if(aml_equal(rm_evt, one)); + { + aml_append(ifctx, + aml_call2(MEMORY_SLOT_NOTIFY_METHOD, + idx, eject_req)); + aml_append(ifctx, aml_store(one, rm_evt)); + } + aml_append(else_ctx, ifctx); + aml_append(while_ctx, else_ctx); + + aml_append(while_ctx, aml_add(idx, one, idx)); + } + aml_append(method, while_ctx); + aml_append(method, aml_release(ctrl_lock)); + aml_append(method, aml_return(one)); + } + aml_append(dev_container, method); + + method = aml_method(MEMORY_SLOT_STATUS_METHOD, 1, AML_NOTSERIALIZED); + { + Aml *slot_enabled = aml_name(MEMORY_SLOT_ENABLED); + + aml_append(method, aml_store(zero, ret_val)); + aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); + aml_append(method, + aml_store(aml_to_integer(slot_arg0), slot_selector)); + + ifctx = aml_if(aml_equal(slot_enabled, one)); + { + aml_append(ifctx, aml_store(aml_int(0xF), ret_val)); + } + aml_append(method, ifctx); + + aml_append(method, aml_release(ctrl_lock)); + aml_append(method, aml_return(ret_val)); + } + aml_append(dev_container, method); + + method = aml_method(MEMORY_SLOT_CRS_METHOD, 1, AML_SERIALIZED); + { + Aml *mr64 = aml_name("MR64"); + Aml *mr32 = aml_name("MR32"); + Aml *crs_tmpl = aml_resource_template(); + Aml *minl = aml_name("MINL"); + Aml *minh = aml_name("MINH"); + Aml *maxl = aml_name("MAXL"); + Aml *maxh = aml_name("MAXH"); + Aml *lenl = aml_name("LENL"); + Aml *lenh = aml_name("LENH"); + + aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); + aml_append(method, aml_store(aml_to_integer(slot_arg0), + slot_selector)); + + aml_append(crs_tmpl, + aml_qword_memory(AML_POS_DECODE, AML_MIN_FIXED, AML_MAX_FIXED, + AML_CACHEABLE, AML_READ_WRITE, + 0, 0x0, 0xFFFFFFFFFFFFFFFEULL, 0, + 0xFFFFFFFFFFFFFFFFULL)); + aml_append(method, aml_name_decl("MR64", crs_tmpl)); + aml_append(method, + aml_create_dword_field(mr64, aml_int(14), "MINL")); + aml_append(method, + aml_create_dword_field(mr64, aml_int(18), "MINH")); + aml_append(method, + aml_create_dword_field(mr64, aml_int(38), "LENL")); + aml_append(method, + aml_create_dword_field(mr64, aml_int(42), "LENH")); + aml_append(method, + aml_create_dword_field(mr64, aml_int(22), "MAXL")); + aml_append(method, + aml_create_dword_field(mr64, aml_int(26), "MAXH")); + + aml_append(method, + aml_store(aml_name(MEMORY_SLOT_ADDR_HIGH), minh)); + aml_append(method, + aml_store(aml_name(MEMORY_SLOT_ADDR_LOW), minl)); + aml_append(method, + aml_store(aml_name(MEMORY_SLOT_SIZE_HIGH), lenh)); + aml_append(method, + aml_store(aml_name(MEMORY_SLOT_SIZE_LOW), lenl)); + + /* 64-bit math: MAX = MIN + LEN - 1 */ + aml_append(method, aml_add(minl, lenl, maxl)); + aml_append(method, aml_add(minh, lenh, maxh)); + ifctx = aml_if(aml_lless(maxl, minl)); + { + aml_append(ifctx, aml_add(maxh, one, maxh)); + } + aml_append(method, ifctx); + ifctx = aml_if(aml_lless(maxl, one)); + { + aml_append(ifctx, aml_subtract(maxh, one, maxh)); + } + aml_append(method, ifctx); + aml_append(method, aml_subtract(maxl, one, maxl)); + + /* return 32-bit _CRS if addr/size is in low mem */ + /* TODO: remove it since all hotplugged DIMMs are in high mem */ + ifctx = aml_if(aml_equal(maxh, zero)); + { + crs_tmpl = aml_resource_template(); + aml_append(crs_tmpl, + aml_dword_memory(AML_POS_DECODE, AML_MIN_FIXED, + AML_MAX_FIXED, AML_CACHEABLE, + AML_READ_WRITE, + 0, 0x0, 0xFFFFFFFE, 0, + 0xFFFFFFFF)); + aml_append(ifctx, aml_name_decl("MR32", crs_tmpl)); + aml_append(ifctx, + aml_create_dword_field(mr32, aml_int(10), "MIN")); + aml_append(ifctx, + aml_create_dword_field(mr32, aml_int(14), "MAX")); + aml_append(ifctx, + aml_create_dword_field(mr32, aml_int(22), "LEN")); + aml_append(ifctx, aml_store(minl, aml_name("MIN"))); + aml_append(ifctx, aml_store(maxl, aml_name("MAX"))); + aml_append(ifctx, aml_store(lenl, aml_name("LEN"))); + + aml_append(ifctx, aml_release(ctrl_lock)); + aml_append(ifctx, aml_return(mr32)); + } + aml_append(method, ifctx); + + aml_append(method, aml_release(ctrl_lock)); + aml_append(method, aml_return(mr64)); + } + aml_append(dev_container, method); + + method = aml_method(MEMORY_SLOT_PROXIMITY_METHOD, 1, + AML_NOTSERIALIZED); + { + Aml *proximity = aml_name(MEMORY_SLOT_PROXIMITY); + + aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); + aml_append(method, aml_store(aml_to_integer(slot_arg0), + slot_selector)); + aml_append(method, aml_store(proximity, ret_val)); + aml_append(method, aml_release(ctrl_lock)); + aml_append(method, aml_return(ret_val)); + } + aml_append(dev_container, method); + + method = aml_method(MEMORY_SLOT_OST_METHOD, 4, AML_NOTSERIALIZED); + { + Aml *ost_evt = aml_name(MEMORY_SLOT_OST_EVENT); + Aml *ost_status = aml_name(MEMORY_SLOT_OST_STATUS); + + aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); + aml_append(method, aml_store(aml_to_integer(slot_arg0), + slot_selector)); + aml_append(method, aml_store(aml_arg(1), ost_evt)); + aml_append(method, aml_store(aml_arg(2), ost_status)); + aml_append(method, aml_release(ctrl_lock)); + } + aml_append(dev_container, method); + + method = aml_method(MEMORY_SLOT_EJECT_METHOD, 2, AML_NOTSERIALIZED); + { + Aml *eject = aml_name(MEMORY_SLOT_EJECT); + + aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); + aml_append(method, aml_store(aml_to_integer(slot_arg0), + slot_selector)); + aml_append(method, aml_store(one, eject)); + aml_append(method, aml_release(ctrl_lock)); + } + aml_append(dev_container, method); + + /* build memory devices */ + for (i = 0; i < nr_mem; i++) { + Aml *dev; + const char *s; + + dev = aml_device("MP%02X", i); + aml_append(dev, aml_name_decl("_UID", aml_string("0x%02X", i))); + aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0C80"))); + + method = aml_method("_CRS", 0, AML_NOTSERIALIZED); + s = MEMORY_SLOT_CRS_METHOD; + aml_append(method, aml_return(aml_call1(s, aml_name("_UID")))); + aml_append(dev, method); + + method = aml_method("_STA", 0, AML_NOTSERIALIZED); + s = MEMORY_SLOT_STATUS_METHOD; + aml_append(method, aml_return(aml_call1(s, aml_name("_UID")))); + aml_append(dev, method); + + method = aml_method("_PXM", 0, AML_NOTSERIALIZED); + s = MEMORY_SLOT_PROXIMITY_METHOD; + aml_append(method, aml_return(aml_call1(s, aml_name("_UID")))); + aml_append(dev, method); + + method = aml_method("_OST", 3, AML_NOTSERIALIZED); + s = MEMORY_SLOT_OST_METHOD; + aml_append(method, aml_return(aml_call4( + s, aml_name("_UID"), aml_arg(0), aml_arg(1), aml_arg(2) + ))); + aml_append(dev, method); + + method = aml_method("_EJ0", 1, AML_NOTSERIALIZED); + s = MEMORY_SLOT_EJECT_METHOD; + aml_append(method, aml_return(aml_call2( + s, aml_name("_UID"), aml_arg(0)))); + aml_append(dev, method); + + aml_append(dev_container, dev); + } + + /* build Method(MEMORY_SLOT_NOTIFY_METHOD, 2) { + * If (LEqual(Arg0, 0x00)) {Notify(MP00, Arg1)} ... } + */ + method = aml_method(MEMORY_SLOT_NOTIFY_METHOD, 2, AML_NOTSERIALIZED); + for (i = 0; i < nr_mem; i++) { + ifctx = aml_if(aml_equal(aml_arg(0), aml_int(i))); + aml_append(ifctx, + aml_notify(aml_name("MP%.02X", i), aml_arg(1)) + ); + aml_append(method, ifctx); + } + aml_append(dev_container, method); + } + aml_append(table, dev_container); + + method = aml_method(event_handler_method, 0, AML_NOTSERIALIZED); + aml_append(method, + aml_call0(MEMORY_DEVICES_CONTAINER "." MEMORY_SLOT_SCAN_METHOD)); + aml_append(table, method); + + g_free(mhp_res_path); +} diff --git a/hw/acpi/memory_hotplug_acpi_table.c b/hw/acpi/memory_hotplug_acpi_table.c deleted file mode 100644 index c75660215d..0000000000 --- a/hw/acpi/memory_hotplug_acpi_table.c +++ /dev/null @@ -1,262 +0,0 @@ -/* - * Memory hotplug AML code of DSDT ACPI table - * - * Copyright (C) 2015 Red Hat Inc - * - * Author: Igor Mammedov <imammedo@redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - */ - -#include "qemu/osdep.h" -#include "hw/acpi/memory_hotplug.h" -#include "include/hw/acpi/pc-hotplug.h" -#include "hw/boards.h" - -void build_memory_hotplug_aml(Aml *ctx, uint32_t nr_mem, - uint16_t io_base, uint16_t io_len) -{ - Aml *ifctx; - Aml *method; - Aml *pci_scope; - Aml *mem_ctrl_dev; - - /* scope for memory hotplug controller device node */ - pci_scope = aml_scope("_SB.PCI0"); - mem_ctrl_dev = aml_device(MEMORY_HOTPLUG_DEVICE); - { - Aml *one = aml_int(1); - Aml *zero = aml_int(0); - Aml *ret_val = aml_local(0); - Aml *slot_arg0 = aml_arg(0); - Aml *slots_nr = aml_name(MEMORY_SLOTS_NUMBER); - Aml *ctrl_lock = aml_name(MEMORY_SLOT_LOCK); - Aml *slot_selector = aml_name(MEMORY_SLOT_SLECTOR); - - aml_append(mem_ctrl_dev, aml_name_decl("_HID", aml_string("PNP0A06"))); - aml_append(mem_ctrl_dev, - aml_name_decl("_UID", aml_string("Memory hotplug resources"))); - - method = aml_method("_STA", 0, AML_NOTSERIALIZED); - ifctx = aml_if(aml_equal(slots_nr, zero)); - { - aml_append(ifctx, aml_return(zero)); - } - aml_append(method, ifctx); - /* present, functioning, decoding, not shown in UI */ - aml_append(method, aml_return(aml_int(0xB))); - aml_append(mem_ctrl_dev, method); - - aml_append(mem_ctrl_dev, aml_mutex(MEMORY_SLOT_LOCK, 0)); - - method = aml_method(MEMORY_SLOT_SCAN_METHOD, 0, AML_NOTSERIALIZED); - { - Aml *else_ctx; - Aml *while_ctx; - Aml *idx = aml_local(0); - Aml *eject_req = aml_int(3); - Aml *dev_chk = aml_int(1); - - ifctx = aml_if(aml_equal(slots_nr, zero)); - { - aml_append(ifctx, aml_return(zero)); - } - aml_append(method, ifctx); - - aml_append(method, aml_store(zero, idx)); - aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); - /* build AML that: - * loops over all slots and Notifies DIMMs with - * Device Check or Eject Request notifications if - * slot has corresponding status bit set and clears - * slot status. - */ - while_ctx = aml_while(aml_lless(idx, slots_nr)); - { - Aml *ins_evt = aml_name(MEMORY_SLOT_INSERT_EVENT); - Aml *rm_evt = aml_name(MEMORY_SLOT_REMOVE_EVENT); - - aml_append(while_ctx, aml_store(idx, slot_selector)); - ifctx = aml_if(aml_equal(ins_evt, one)); - { - aml_append(ifctx, - aml_call2(MEMORY_SLOT_NOTIFY_METHOD, - idx, dev_chk)); - aml_append(ifctx, aml_store(one, ins_evt)); - } - aml_append(while_ctx, ifctx); - - else_ctx = aml_else(); - ifctx = aml_if(aml_equal(rm_evt, one)); - { - aml_append(ifctx, - aml_call2(MEMORY_SLOT_NOTIFY_METHOD, - idx, eject_req)); - aml_append(ifctx, aml_store(one, rm_evt)); - } - aml_append(else_ctx, ifctx); - aml_append(while_ctx, else_ctx); - - aml_append(while_ctx, aml_add(idx, one, idx)); - } - aml_append(method, while_ctx); - aml_append(method, aml_release(ctrl_lock)); - aml_append(method, aml_return(one)); - } - aml_append(mem_ctrl_dev, method); - - method = aml_method(MEMORY_SLOT_STATUS_METHOD, 1, AML_NOTSERIALIZED); - { - Aml *slot_enabled = aml_name(MEMORY_SLOT_ENABLED); - - aml_append(method, aml_store(zero, ret_val)); - aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); - aml_append(method, - aml_store(aml_to_integer(slot_arg0), slot_selector)); - - ifctx = aml_if(aml_equal(slot_enabled, one)); - { - aml_append(ifctx, aml_store(aml_int(0xF), ret_val)); - } - aml_append(method, ifctx); - - aml_append(method, aml_release(ctrl_lock)); - aml_append(method, aml_return(ret_val)); - } - aml_append(mem_ctrl_dev, method); - - method = aml_method(MEMORY_SLOT_CRS_METHOD, 1, AML_SERIALIZED); - { - Aml *mr64 = aml_name("MR64"); - Aml *mr32 = aml_name("MR32"); - Aml *crs_tmpl = aml_resource_template(); - Aml *minl = aml_name("MINL"); - Aml *minh = aml_name("MINH"); - Aml *maxl = aml_name("MAXL"); - Aml *maxh = aml_name("MAXH"); - Aml *lenl = aml_name("LENL"); - Aml *lenh = aml_name("LENH"); - - aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); - aml_append(method, aml_store(aml_to_integer(slot_arg0), - slot_selector)); - - aml_append(crs_tmpl, - aml_qword_memory(AML_POS_DECODE, AML_MIN_FIXED, AML_MAX_FIXED, - AML_CACHEABLE, AML_READ_WRITE, - 0, 0x0, 0xFFFFFFFFFFFFFFFEULL, 0, - 0xFFFFFFFFFFFFFFFFULL)); - aml_append(method, aml_name_decl("MR64", crs_tmpl)); - aml_append(method, - aml_create_dword_field(mr64, aml_int(14), "MINL")); - aml_append(method, - aml_create_dword_field(mr64, aml_int(18), "MINH")); - aml_append(method, - aml_create_dword_field(mr64, aml_int(38), "LENL")); - aml_append(method, - aml_create_dword_field(mr64, aml_int(42), "LENH")); - aml_append(method, - aml_create_dword_field(mr64, aml_int(22), "MAXL")); - aml_append(method, - aml_create_dword_field(mr64, aml_int(26), "MAXH")); - - aml_append(method, - aml_store(aml_name(MEMORY_SLOT_ADDR_HIGH), minh)); - aml_append(method, - aml_store(aml_name(MEMORY_SLOT_ADDR_LOW), minl)); - aml_append(method, - aml_store(aml_name(MEMORY_SLOT_SIZE_HIGH), lenh)); - aml_append(method, - aml_store(aml_name(MEMORY_SLOT_SIZE_LOW), lenl)); - - /* 64-bit math: MAX = MIN + LEN - 1 */ - aml_append(method, aml_add(minl, lenl, maxl)); - aml_append(method, aml_add(minh, lenh, maxh)); - ifctx = aml_if(aml_lless(maxl, minl)); - { - aml_append(ifctx, aml_add(maxh, one, maxh)); - } - aml_append(method, ifctx); - ifctx = aml_if(aml_lless(maxl, one)); - { - aml_append(ifctx, aml_subtract(maxh, one, maxh)); - } - aml_append(method, ifctx); - aml_append(method, aml_subtract(maxl, one, maxl)); - - /* return 32-bit _CRS if addr/size is in low mem */ - /* TODO: remove it since all hotplugged DIMMs are in high mem */ - ifctx = aml_if(aml_equal(maxh, zero)); - { - crs_tmpl = aml_resource_template(); - aml_append(crs_tmpl, - aml_dword_memory(AML_POS_DECODE, AML_MIN_FIXED, - AML_MAX_FIXED, AML_CACHEABLE, - AML_READ_WRITE, - 0, 0x0, 0xFFFFFFFE, 0, - 0xFFFFFFFF)); - aml_append(ifctx, aml_name_decl("MR32", crs_tmpl)); - aml_append(ifctx, - aml_create_dword_field(mr32, aml_int(10), "MIN")); - aml_append(ifctx, - aml_create_dword_field(mr32, aml_int(14), "MAX")); - aml_append(ifctx, - aml_create_dword_field(mr32, aml_int(22), "LEN")); - aml_append(ifctx, aml_store(minl, aml_name("MIN"))); - aml_append(ifctx, aml_store(maxl, aml_name("MAX"))); - aml_append(ifctx, aml_store(lenl, aml_name("LEN"))); - - aml_append(ifctx, aml_release(ctrl_lock)); - aml_append(ifctx, aml_return(mr32)); - } - aml_append(method, ifctx); - - aml_append(method, aml_release(ctrl_lock)); - aml_append(method, aml_return(mr64)); - } - aml_append(mem_ctrl_dev, method); - - method = aml_method(MEMORY_SLOT_PROXIMITY_METHOD, 1, - AML_NOTSERIALIZED); - { - Aml *proximity = aml_name(MEMORY_SLOT_PROXIMITY); - - aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); - aml_append(method, aml_store(aml_to_integer(slot_arg0), - slot_selector)); - aml_append(method, aml_store(proximity, ret_val)); - aml_append(method, aml_release(ctrl_lock)); - aml_append(method, aml_return(ret_val)); - } - aml_append(mem_ctrl_dev, method); - - method = aml_method(MEMORY_SLOT_OST_METHOD, 4, AML_NOTSERIALIZED); - { - Aml *ost_evt = aml_name(MEMORY_SLOT_OST_EVENT); - Aml *ost_status = aml_name(MEMORY_SLOT_OST_STATUS); - - aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); - aml_append(method, aml_store(aml_to_integer(slot_arg0), - slot_selector)); - aml_append(method, aml_store(aml_arg(1), ost_evt)); - aml_append(method, aml_store(aml_arg(2), ost_status)); - aml_append(method, aml_release(ctrl_lock)); - } - aml_append(mem_ctrl_dev, method); - - method = aml_method(MEMORY_SLOT_EJECT_METHOD, 2, AML_NOTSERIALIZED); - { - Aml *eject = aml_name(MEMORY_SLOT_EJECT); - - aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); - aml_append(method, aml_store(aml_to_integer(slot_arg0), - slot_selector)); - aml_append(method, aml_store(one, eject)); - aml_append(method, aml_release(ctrl_lock)); - } - aml_append(mem_ctrl_dev, method); - } - aml_append(pci_scope, mem_ctrl_dev); - aml_append(ctx, pci_scope); -} diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c index 17d36bd595..6d99fe407c 100644 --- a/hw/acpi/piix4.c +++ b/hw/acpi/piix4.c @@ -644,7 +644,8 @@ static void piix4_acpi_system_hot_add_init(MemoryRegion *parent, PIIX4_CPU_HOTPLUG_IO_BASE); if (s->acpi_memory_hotplug.is_enabled) { - acpi_memory_hotplug_init(parent, OBJECT(s), &s->acpi_memory_hotplug); + acpi_memory_hotplug_init(parent, OBJECT(s), &s->acpi_memory_hotplug, + ACPI_MEMORY_HOTPLUG_BASE); } } diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index c7206fda6d..a92c2f1c36 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -20,6 +20,8 @@ #include "qemu/log.h" #include "sysemu/block-backend.h" #include "sysemu/blockdev.h" +#include "hw/loader.h" +#include "qemu/error-report.h" static struct arm_boot_info aspeed_board_binfo = { .board_id = -1, /* device-tree-only board */ @@ -34,13 +36,18 @@ typedef struct AspeedBoardState { typedef struct AspeedBoardConfig { const char *soc_name; uint32_t hw_strap1; + const char *fmc_model; + const char *spi_model; + uint32_t num_cs; } AspeedBoardConfig; enum { PALMETTO_BMC, AST2500_EVB, + ROMULUS_BMC, }; +/* Palmetto hardware value: 0x120CE416 */ #define PALMETTO_BMC_HW_STRAP1 ( \ SCU_AST2400_HW_STRAP_DRAM_SIZE(DRAM_SIZE_256MB) | \ SCU_AST2400_HW_STRAP_DRAM_CONFIG(2 /* DDR3 with CL=6, CWL=5 */) | \ @@ -54,6 +61,7 @@ enum { SCU_HW_STRAP_VGA_SIZE_SET(VGA_16M_DRAM) | \ SCU_AST2400_HW_STRAP_BOOT_MODE(AST2400_SPI_BOOT)) +/* AST2500 evb hardware value: 0xF100C2E6 */ #define AST2500_EVB_HW_STRAP1 (( \ AST2500_HW_STRAP1_DEFAULTS | \ SCU_AST2500_HW_STRAP_SPI_AUTOFETCH_ENABLE | \ @@ -64,11 +72,62 @@ enum { SCU_HW_STRAP_MAC0_RGMII) & \ ~SCU_HW_STRAP_2ND_BOOT_WDT) +/* Romulus hardware value: 0xF10AD206 */ +#define ROMULUS_BMC_HW_STRAP1 ( \ + AST2500_HW_STRAP1_DEFAULTS | \ + SCU_AST2500_HW_STRAP_SPI_AUTOFETCH_ENABLE | \ + SCU_AST2500_HW_STRAP_GPIO_STRAP_ENABLE | \ + SCU_AST2500_HW_STRAP_UART_DEBUG | \ + SCU_AST2500_HW_STRAP_DDR4_ENABLE | \ + SCU_AST2500_HW_STRAP_ACPI_ENABLE | \ + SCU_HW_STRAP_SPI_MODE(SCU_HW_STRAP_SPI_MASTER)) + static const AspeedBoardConfig aspeed_boards[] = { - [PALMETTO_BMC] = { "ast2400-a0", PALMETTO_BMC_HW_STRAP1 }, - [AST2500_EVB] = { "ast2500-a1", AST2500_EVB_HW_STRAP1 }, + [PALMETTO_BMC] = { + .soc_name = "ast2400-a1", + .hw_strap1 = PALMETTO_BMC_HW_STRAP1, + .fmc_model = "n25q256a", + .spi_model = "mx25l25635e", + .num_cs = 1, + }, + [AST2500_EVB] = { + .soc_name = "ast2500-a1", + .hw_strap1 = AST2500_EVB_HW_STRAP1, + .fmc_model = "n25q256a", + .spi_model = "mx25l25635e", + .num_cs = 1, + }, + [ROMULUS_BMC] = { + .soc_name = "ast2500-a1", + .hw_strap1 = ROMULUS_BMC_HW_STRAP1, + .fmc_model = "n25q256a", + .spi_model = "mx66l1g45g", + .num_cs = 2, + }, }; +#define FIRMWARE_ADDR 0x0 + +static void write_boot_rom(DriveInfo *dinfo, hwaddr addr, size_t rom_size, + Error **errp) +{ + BlockBackend *blk = blk_by_legacy_dinfo(dinfo); + uint8_t *storage; + + if (rom_size > blk_getlength(blk)) { + rom_size = blk_getlength(blk); + } + + storage = g_new0(uint8_t, rom_size); + if (blk_pread(blk, 0, storage, rom_size) < 0) { + error_setg(errp, "failed to read the initial flash content"); + return; + } + + rom_add_blob_fixed("aspeed.boot_rom", storage, rom_size, addr); + g_free(storage); +} + static void aspeed_board_init_flashes(AspeedSMCState *s, const char *flashtype, Error **errp) { @@ -100,6 +159,7 @@ static void aspeed_board_init(MachineState *machine, { AspeedBoardState *bmc; AspeedSoCClass *sc; + DriveInfo *drive0 = drive_get(IF_MTD, 0, 0); bmc = g_new0(AspeedBoardState, 1); object_initialize(&bmc->soc, (sizeof(bmc->soc)), cfg->soc_name); @@ -112,6 +172,8 @@ static void aspeed_board_init(MachineState *machine, &error_abort); object_property_set_int(OBJECT(&bmc->soc), cfg->hw_strap1, "hw-strap1", &error_abort); + object_property_set_int(OBJECT(&bmc->soc), cfg->num_cs, "num-cs", + &error_abort); object_property_set_bool(OBJECT(&bmc->soc), true, "realized", &error_abort); @@ -128,8 +190,24 @@ static void aspeed_board_init(MachineState *machine, object_property_add_const_link(OBJECT(&bmc->soc), "ram", OBJECT(&bmc->ram), &error_abort); - aspeed_board_init_flashes(&bmc->soc.fmc, "n25q256a", &error_abort); - aspeed_board_init_flashes(&bmc->soc.spi[0], "mx25l25635e", &error_abort); + aspeed_board_init_flashes(&bmc->soc.fmc, cfg->fmc_model, &error_abort); + aspeed_board_init_flashes(&bmc->soc.spi[0], cfg->spi_model, &error_abort); + + /* Install first FMC flash content as a boot rom. */ + if (drive0) { + AspeedSMCFlash *fl = &bmc->soc.fmc.flashes[0]; + MemoryRegion *boot_rom = g_new(MemoryRegion, 1); + + /* + * create a ROM region using the default mapping window size of + * the flash module. + */ + memory_region_init_rom(boot_rom, OBJECT(bmc), "aspeed.boot_rom", + fl->size, &error_abort); + memory_region_add_subregion(get_system_memory(), FIRMWARE_ADDR, + boot_rom); + write_boot_rom(drive0, FIRMWARE_ADDR, fl->size, &error_abort); + } aspeed_board_binfo.kernel_filename = machine->kernel_filename; aspeed_board_binfo.initrd_filename = machine->initrd_filename; @@ -188,10 +266,35 @@ static const TypeInfo ast2500_evb_type = { .class_init = ast2500_evb_class_init, }; +static void romulus_bmc_init(MachineState *machine) +{ + aspeed_board_init(machine, &aspeed_boards[ROMULUS_BMC]); +} + +static void romulus_bmc_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + + mc->desc = "OpenPOWER Romulus BMC (ARM1176)"; + mc->init = romulus_bmc_init; + mc->max_cpus = 1; + mc->no_sdcard = 1; + mc->no_floppy = 1; + mc->no_cdrom = 1; + mc->no_parallel = 1; +} + +static const TypeInfo romulus_bmc_type = { + .name = MACHINE_TYPE_NAME("romulus-bmc"), + .parent = TYPE_MACHINE, + .class_init = romulus_bmc_class_init, +}; + static void aspeed_machine_init(void) { type_register_static(&palmetto_bmc_type); type_register_static(&ast2500_evb_type); + type_register_static(&romulus_bmc_type); } type_init(aspeed_machine_init) diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c index e14f5c217e..b3e7f07b61 100644 --- a/hw/arm/aspeed_soc.c +++ b/hw/arm/aspeed_soc.c @@ -29,6 +29,7 @@ #define ASPEED_SOC_VIC_BASE 0x1E6C0000 #define ASPEED_SOC_SDMC_BASE 0x1E6E0000 #define ASPEED_SOC_SCU_BASE 0x1E6E2000 +#define ASPEED_SOC_SRAM_BASE 0x1E720000 #define ASPEED_SOC_TIMER_BASE 0x1E782000 #define ASPEED_SOC_I2C_BASE 0x1E78A000 @@ -47,15 +48,47 @@ static const char *aspeed_soc_ast2500_typenames[] = { "aspeed.smc.ast2500-spi1", "aspeed.smc.ast2500-spi2" }; static const AspeedSoCInfo aspeed_socs[] = { - { "ast2400-a0", "arm926", AST2400_A0_SILICON_REV, AST2400_SDRAM_BASE, - 1, aspeed_soc_ast2400_spi_bases, - "aspeed.smc.fmc", aspeed_soc_ast2400_typenames }, - { "ast2400", "arm926", AST2400_A0_SILICON_REV, AST2400_SDRAM_BASE, - 1, aspeed_soc_ast2400_spi_bases, - "aspeed.smc.fmc", aspeed_soc_ast2400_typenames }, - { "ast2500-a1", "arm1176", AST2500_A1_SILICON_REV, AST2500_SDRAM_BASE, - 2, aspeed_soc_ast2500_spi_bases, - "aspeed.smc.ast2500-fmc", aspeed_soc_ast2500_typenames }, + { + .name = "ast2400-a0", + .cpu_model = "arm926", + .silicon_rev = AST2400_A0_SILICON_REV, + .sdram_base = AST2400_SDRAM_BASE, + .sram_size = 0x8000, + .spis_num = 1, + .spi_bases = aspeed_soc_ast2400_spi_bases, + .fmc_typename = "aspeed.smc.fmc", + .spi_typename = aspeed_soc_ast2400_typenames, + }, { + .name = "ast2400-a1", + .cpu_model = "arm926", + .silicon_rev = AST2400_A1_SILICON_REV, + .sdram_base = AST2400_SDRAM_BASE, + .sram_size = 0x8000, + .spis_num = 1, + .spi_bases = aspeed_soc_ast2400_spi_bases, + .fmc_typename = "aspeed.smc.fmc", + .spi_typename = aspeed_soc_ast2400_typenames, + }, { + .name = "ast2400", + .cpu_model = "arm926", + .silicon_rev = AST2400_A0_SILICON_REV, + .sdram_base = AST2400_SDRAM_BASE, + .sram_size = 0x8000, + .spis_num = 1, + .spi_bases = aspeed_soc_ast2400_spi_bases, + .fmc_typename = "aspeed.smc.fmc", + .spi_typename = aspeed_soc_ast2400_typenames, + }, { + .name = "ast2500-a1", + .cpu_model = "arm1176", + .silicon_rev = AST2500_A1_SILICON_REV, + .sdram_base = AST2500_SDRAM_BASE, + .sram_size = 0x9000, + .spis_num = 2, + .spi_bases = aspeed_soc_ast2500_spi_bases, + .fmc_typename = "aspeed.smc.ast2500-fmc", + .spi_typename = aspeed_soc_ast2500_typenames, + }, }; /* @@ -87,9 +120,13 @@ static void aspeed_soc_init(Object *obj) { AspeedSoCState *s = ASPEED_SOC(obj); AspeedSoCClass *sc = ASPEED_SOC_GET_CLASS(s); + char *cpu_typename; int i; - s->cpu = cpu_arm_init(sc->info->cpu_model); + cpu_typename = g_strdup_printf("%s-" TYPE_ARM_CPU, sc->info->cpu_model); + object_initialize(&s->cpu, sizeof(s->cpu), cpu_typename); + object_property_add_child(obj, "cpu", OBJECT(&s->cpu), NULL); + g_free(cpu_typename); object_initialize(&s->vic, sizeof(s->vic), TYPE_ASPEED_VIC); object_property_add_child(obj, "vic", OBJECT(&s->vic), NULL); @@ -116,11 +153,13 @@ static void aspeed_soc_init(Object *obj) object_initialize(&s->fmc, sizeof(s->fmc), sc->info->fmc_typename); object_property_add_child(obj, "fmc", OBJECT(&s->fmc), NULL); qdev_set_parent_bus(DEVICE(&s->fmc), sysbus_get_default()); + object_property_add_alias(obj, "num-cs", OBJECT(&s->fmc), "num-cs", + &error_abort); for (i = 0; i < sc->info->spis_num; i++) { object_initialize(&s->spi[i], sizeof(s->spi[i]), sc->info->spi_typename[i]); - object_property_add_child(obj, "spi", OBJECT(&s->spi[i]), NULL); + object_property_add_child(obj, "spi[*]", OBJECT(&s->spi[i]), NULL); qdev_set_parent_bus(DEVICE(&s->spi[i]), sysbus_get_default()); } @@ -146,6 +185,24 @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) memory_region_add_subregion_overlap(get_system_memory(), ASPEED_SOC_IOMEM_BASE, &s->iomem, -1); + /* CPU */ + object_property_set_bool(OBJECT(&s->cpu), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + + /* SRAM */ + memory_region_init_ram(&s->sram, OBJECT(dev), "aspeed.sram", + sc->info->sram_size, &err); + if (err) { + error_propagate(errp, err); + return; + } + vmstate_register_ram_global(&s->sram); + memory_region_add_subregion(get_system_memory(), ASPEED_SOC_SRAM_BASE, + &s->sram); + /* VIC */ object_property_set_bool(OBJECT(&s->vic), true, "realized", &err); if (err) { @@ -154,9 +211,9 @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) } sysbus_mmio_map(SYS_BUS_DEVICE(&s->vic), 0, ASPEED_SOC_VIC_BASE); sysbus_connect_irq(SYS_BUS_DEVICE(&s->vic), 0, - qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ)); + qdev_get_gpio_in(DEVICE(&s->cpu), ARM_CPU_IRQ)); sysbus_connect_irq(SYS_BUS_DEVICE(&s->vic), 1, - qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_FIQ)); + qdev_get_gpio_in(DEVICE(&s->cpu), ARM_CPU_FIQ)); /* Timer */ object_property_set_bool(OBJECT(&s->timerctrl), true, "realized", &err); @@ -195,10 +252,8 @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c), 0, qdev_get_gpio_in(DEVICE(&s->vic), 12)); - /* FMC */ - object_property_set_int(OBJECT(&s->fmc), 1, "num-cs", &err); - object_property_set_bool(OBJECT(&s->fmc), true, "realized", &local_err); - error_propagate(&err, local_err); + /* FMC, The number of CS is set at the board level */ + object_property_set_bool(OBJECT(&s->fmc), true, "realized", &err); if (err) { error_propagate(errp, err); return; @@ -240,12 +295,6 @@ static void aspeed_soc_class_init(ObjectClass *oc, void *data) sc->info = (AspeedSoCInfo *) data; dc->realize = aspeed_soc_realize; - - /* - * Reason: creates an ARM CPU, thus use after free(), see - * arm_cpu_class_init() - */ - dc->cannot_destroy_with_object_finalize_yet = true; } static const TypeInfo aspeed_soc_type_info = { diff --git a/hw/arm/imx25_pdk.c b/hw/arm/imx25_pdk.c index 025b60843e..44e741fde3 100644 --- a/hw/arm/imx25_pdk.c +++ b/hw/arm/imx25_pdk.c @@ -139,7 +139,7 @@ static void imx25_pdk_init(MachineState *machine) * of simple qtest. See "make check" for details. */ i2c_create_slave((I2CBus *)qdev_get_child_bus(DEVICE(&s->soc.i2c[0]), - "i2c"), + "i2c-bus.0"), "ds1338", 0x68); } } diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index 21ea1d6210..d31b4577f0 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -1258,7 +1258,7 @@ static void pxa2xx_i2c_update(PXA2xxI2CState *s) } /* These are only stubs now. */ -static void pxa2xx_i2c_event(I2CSlave *i2c, enum i2c_event event) +static int pxa2xx_i2c_event(I2CSlave *i2c, enum i2c_event event) { PXA2xxI2CSlaveState *slave = PXA2XX_I2C_SLAVE(i2c); PXA2xxI2CState *s = slave->host; @@ -1280,6 +1280,8 @@ static void pxa2xx_i2c_event(I2CSlave *i2c, enum i2c_event event) break; } pxa2xx_i2c_update(s); + + return 0; } static int pxa2xx_i2c_rx(I2CSlave *i2c) @@ -1449,17 +1451,10 @@ static const VMStateDescription vmstate_pxa2xx_i2c = { } }; -static int pxa2xx_i2c_slave_init(I2CSlave *i2c) -{ - /* Nothing to do. */ - return 0; -} - static void pxa2xx_i2c_slave_class_init(ObjectClass *klass, void *data) { I2CSlaveClass *k = I2C_SLAVE_CLASS(klass); - k->init = pxa2xx_i2c_slave_init; k->event = pxa2xx_i2c_event; k->recv = pxa2xx_i2c_rx; k->send = pxa2xx_i2c_tx; @@ -2070,7 +2065,7 @@ PXA2xxState *pxa270_init(MemoryRegion *address_space, } if (!revision) revision = "pxa270"; - + s->cpu = cpu_arm_init(revision); if (s->cpu == NULL) { fprintf(stderr, "Unable to find CPU definition\n"); diff --git a/hw/arm/tosa.c b/hw/arm/tosa.c index 1ee12f49b3..c3db996930 100644 --- a/hw/arm/tosa.c +++ b/hw/arm/tosa.c @@ -172,7 +172,7 @@ static int tosa_dac_send(I2CSlave *i2c, uint8_t data) return 0; } -static void tosa_dac_event(I2CSlave *i2c, enum i2c_event event) +static int tosa_dac_event(I2CSlave *i2c, enum i2c_event event) { TosaDACState *s = TOSA_DAC(i2c); @@ -194,6 +194,8 @@ static void tosa_dac_event(I2CSlave *i2c, enum i2c_event event) default: break; } + + return 0; } static int tosa_dac_recv(I2CSlave *s) @@ -202,12 +204,6 @@ static int tosa_dac_recv(I2CSlave *s) return -1; } -static int tosa_dac_init(I2CSlave *i2c) -{ - /* Nothing to do. */ - return 0; -} - static void tosa_tg_init(PXA2xxState *cpu) { I2CBus *bus = pxa2xx_i2c_bus(cpu->i2c[0]); @@ -275,7 +271,6 @@ static void tosa_dac_class_init(ObjectClass *klass, void *data) { I2CSlaveClass *k = I2C_SLAVE_CLASS(klass); - k->init = tosa_dac_init; k->event = tosa_dac_event; k->recv = tosa_dac_recv; k->send = tosa_dac_send; diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index 7102686882..07a10aca40 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -29,7 +29,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu-common.h" -#include "hw/arm/virt-acpi-build.h" #include "qemu/bitmap.h" #include "trace.h" #include "qom/cpu.h" @@ -43,6 +42,7 @@ #include "hw/acpi/aml-build.h" #include "hw/pci/pcie_host.h" #include "hw/pci/pci.h" +#include "hw/arm/virt.h" #include "sysemu/numa.h" #include "kvm_arm.h" @@ -310,6 +310,13 @@ static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap, Aml *dev_rp0 = aml_device("%s", "RP0"); aml_append(dev_rp0, aml_name_decl("_ADR", aml_int(0))); aml_append(dev, dev_rp0); + + Aml *dev_res0 = aml_device("%s", "RES0"); + aml_append(dev_res0, aml_name_decl("_HID", aml_string("PNP0C02"))); + crs = aml_resource_template(); + aml_append(crs, aml_memory32_fixed(base_ecam, size_ecam, AML_READ_WRITE)); + aml_append(dev_res0, aml_name_decl("_CRS", crs)); + aml_append(dev, dev_res0); aml_append(scope, dev); } @@ -384,7 +391,7 @@ build_rsdp(GArray *rsdp_table, BIOSLinker *linker, unsigned rsdt_tbl_offset) } static void -build_iort(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) +build_iort(GArray *table_data, BIOSLinker *linker) { int iort_start = table_data->len; AcpiIortIdMapping *idmap; @@ -439,11 +446,11 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) } static void -build_spcr(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) +build_spcr(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) { AcpiSerialPortConsoleRedirection *spcr; - const MemMapEntry *uart_memmap = &guest_info->memmap[VIRT_UART]; - int irq = guest_info->irqmap[VIRT_UART] + ARM_SPI_BASE; + const MemMapEntry *uart_memmap = &vms->memmap[VIRT_UART]; + int irq = vms->irqmap[VIRT_UART] + ARM_SPI_BASE; spcr = acpi_data_push(table_data, sizeof(*spcr)); @@ -472,16 +479,16 @@ build_spcr(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) } static void -build_srat(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) +build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) { AcpiSystemResourceAffinityTable *srat; AcpiSratProcessorGiccAffinity *core; AcpiSratMemoryAffinity *numamem; int i, j, srat_start; uint64_t mem_base; - uint32_t *cpu_node = g_malloc0(guest_info->smp_cpus * sizeof(uint32_t)); + uint32_t *cpu_node = g_malloc0(vms->smp_cpus * sizeof(uint32_t)); - for (i = 0; i < guest_info->smp_cpus; i++) { + for (i = 0; i < vms->smp_cpus; i++) { j = numa_get_node_for_cpu(i); if (j < nb_numa_nodes) { cpu_node[i] = j; @@ -492,7 +499,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) srat = acpi_data_push(table_data, sizeof(*srat)); srat->reserved1 = cpu_to_le32(1); - for (i = 0; i < guest_info->smp_cpus; ++i) { + for (i = 0; i < vms->smp_cpus; ++i) { core = acpi_data_push(table_data, sizeof(*core)); core->type = ACPI_SRAT_PROCESSOR_GICC; core->length = sizeof(*core); @@ -502,7 +509,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) } g_free(cpu_node); - mem_base = guest_info->memmap[VIRT_MEM].base; + mem_base = vms->memmap[VIRT_MEM].base; for (i = 0; i < nb_numa_nodes; ++i) { numamem = acpi_data_push(table_data, sizeof(*numamem)); build_srat_memory(numamem, mem_base, numa_info[i].node_mem, i, @@ -515,10 +522,10 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) } static void -build_mcfg(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) +build_mcfg(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) { AcpiTableMcfg *mcfg; - const MemMapEntry *memmap = guest_info->memmap; + const MemMapEntry *memmap = vms->memmap; int len = sizeof(*mcfg) + sizeof(mcfg->allocation[0]); mcfg = acpi_data_push(table_data, len); @@ -535,24 +542,33 @@ build_mcfg(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) /* GTDT */ static void -build_gtdt(GArray *table_data, BIOSLinker *linker) +build_gtdt(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) { + VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms); int gtdt_start = table_data->len; AcpiGenericTimerTable *gtdt; + uint32_t irqflags; + + if (vmc->claim_edge_triggered_timers) { + irqflags = ACPI_GTDT_INTERRUPT_MODE_EDGE; + } else { + irqflags = ACPI_GTDT_INTERRUPT_MODE_LEVEL; + } gtdt = acpi_data_push(table_data, sizeof *gtdt); /* The interrupt values are the same with the device tree when adding 16 */ - gtdt->secure_el1_interrupt = ARCH_TIMER_S_EL1_IRQ + 16; - gtdt->secure_el1_flags = ACPI_EDGE_SENSITIVE; + gtdt->secure_el1_interrupt = cpu_to_le32(ARCH_TIMER_S_EL1_IRQ + 16); + gtdt->secure_el1_flags = cpu_to_le32(irqflags); - gtdt->non_secure_el1_interrupt = ARCH_TIMER_NS_EL1_IRQ + 16; - gtdt->non_secure_el1_flags = ACPI_EDGE_SENSITIVE | ACPI_GTDT_ALWAYS_ON; + gtdt->non_secure_el1_interrupt = cpu_to_le32(ARCH_TIMER_NS_EL1_IRQ + 16); + gtdt->non_secure_el1_flags = cpu_to_le32(irqflags | + ACPI_GTDT_CAP_ALWAYS_ON); - gtdt->virtual_timer_interrupt = ARCH_TIMER_VIRT_IRQ + 16; - gtdt->virtual_timer_flags = ACPI_EDGE_SENSITIVE; + gtdt->virtual_timer_interrupt = cpu_to_le32(ARCH_TIMER_VIRT_IRQ + 16); + gtdt->virtual_timer_flags = cpu_to_le32(irqflags); - gtdt->non_secure_el2_interrupt = ARCH_TIMER_NS_EL2_IRQ + 16; - gtdt->non_secure_el2_flags = ACPI_EDGE_SENSITIVE; + gtdt->non_secure_el2_interrupt = cpu_to_le32(ARCH_TIMER_NS_EL2_IRQ + 16); + gtdt->non_secure_el2_flags = cpu_to_le32(irqflags); build_header(linker, table_data, (void *)(table_data->data + gtdt_start), "GTDT", @@ -561,11 +577,12 @@ build_gtdt(GArray *table_data, BIOSLinker *linker) /* MADT */ static void -build_madt(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) +build_madt(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) { + VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms); int madt_start = table_data->len; - const MemMapEntry *memmap = guest_info->memmap; - const int *irqmap = guest_info->irqmap; + const MemMapEntry *memmap = vms->memmap; + const int *irqmap = vms->irqmap; AcpiMultipleApicTable *madt; AcpiMadtGenericDistributor *gicd; AcpiMadtGenericMsiFrame *gic_msi; @@ -576,30 +593,33 @@ build_madt(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) gicd = acpi_data_push(table_data, sizeof *gicd); gicd->type = ACPI_APIC_GENERIC_DISTRIBUTOR; gicd->length = sizeof(*gicd); - gicd->base_address = memmap[VIRT_GIC_DIST].base; - gicd->version = guest_info->gic_version; + gicd->base_address = cpu_to_le64(memmap[VIRT_GIC_DIST].base); + gicd->version = vms->gic_version; - for (i = 0; i < guest_info->smp_cpus; i++) { - AcpiMadtGenericInterrupt *gicc = acpi_data_push(table_data, - sizeof *gicc); + for (i = 0; i < vms->smp_cpus; i++) { + AcpiMadtGenericCpuInterface *gicc = acpi_data_push(table_data, + sizeof(*gicc)); ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(i)); - gicc->type = ACPI_APIC_GENERIC_INTERRUPT; + gicc->type = ACPI_APIC_GENERIC_CPU_INTERFACE; gicc->length = sizeof(*gicc); - if (guest_info->gic_version == 2) { - gicc->base_address = memmap[VIRT_GIC_CPU].base; + if (vms->gic_version == 2) { + gicc->base_address = cpu_to_le64(memmap[VIRT_GIC_CPU].base); } - gicc->cpu_interface_number = i; - gicc->arm_mpidr = armcpu->mp_affinity; - gicc->uid = i; - gicc->flags = cpu_to_le32(ACPI_GICC_ENABLED); + gicc->cpu_interface_number = cpu_to_le32(i); + gicc->arm_mpidr = cpu_to_le64(armcpu->mp_affinity); + gicc->uid = cpu_to_le32(i); + gicc->flags = cpu_to_le32(ACPI_MADT_GICC_ENABLED); if (arm_feature(&armcpu->env, ARM_FEATURE_PMU)) { gicc->performance_interrupt = cpu_to_le32(PPI(VIRTUAL_PMU_IRQ)); } + if (vms->virt && vms->gic_version == 3) { + gicc->vgic_interrupt = cpu_to_le32(PPI(ARCH_GICV3_MAINT_IRQ)); + } } - if (guest_info->gic_version == 3) { + if (vms->gic_version == 3) { AcpiMadtGenericTranslator *gic_its; AcpiMadtGenericRedistributor *gicr = acpi_data_push(table_data, sizeof *gicr); @@ -609,7 +629,7 @@ build_madt(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) gicr->base_address = cpu_to_le64(memmap[VIRT_GIC_REDIST].base); gicr->range_length = cpu_to_le32(memmap[VIRT_GIC_REDIST].size); - if (its_class_name() && !guest_info->no_its) { + if (its_class_name() && !vmc->no_its) { gic_its = acpi_data_push(table_data, sizeof *gic_its); gic_its->type = ACPI_APIC_GENERIC_TRANSLATOR; gic_its->length = sizeof(*gic_its); @@ -633,16 +653,30 @@ build_madt(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) } /* FADT */ -static void -build_fadt(GArray *table_data, BIOSLinker *linker, unsigned dsdt_tbl_offset) +static void build_fadt(GArray *table_data, BIOSLinker *linker, + VirtMachineState *vms, unsigned dsdt_tbl_offset) { AcpiFadtDescriptorRev5_1 *fadt = acpi_data_push(table_data, sizeof(*fadt)); unsigned dsdt_entry_offset = (char *)&fadt->dsdt - table_data->data; + uint16_t bootflags; + + switch (vms->psci_conduit) { + case QEMU_PSCI_CONDUIT_DISABLED: + bootflags = 0; + break; + case QEMU_PSCI_CONDUIT_HVC: + bootflags = ACPI_FADT_ARM_PSCI_COMPLIANT | ACPI_FADT_ARM_PSCI_USE_HVC; + break; + case QEMU_PSCI_CONDUIT_SMC: + bootflags = ACPI_FADT_ARM_PSCI_COMPLIANT; + break; + default: + g_assert_not_reached(); + } - /* Hardware Reduced = 1 and use PSCI 0.2+ and with HVC */ + /* Hardware Reduced = 1 and use PSCI 0.2+ */ fadt->flags = cpu_to_le32(1 << ACPI_FADT_F_HW_REDUCED_ACPI); - fadt->arm_boot_flags = cpu_to_le16((1 << ACPI_FADT_ARM_USE_PSCI_G_0_2) | - (1 << ACPI_FADT_ARM_PSCI_USE_HVC)); + fadt->arm_boot_flags = cpu_to_le16(bootflags); /* ACPI v5.1 (fadt->revision.fadt->minor_revision) */ fadt->minor_revision = 0x1; @@ -658,11 +692,11 @@ build_fadt(GArray *table_data, BIOSLinker *linker, unsigned dsdt_tbl_offset) /* DSDT */ static void -build_dsdt(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) +build_dsdt(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) { Aml *scope, *dsdt; - const MemMapEntry *memmap = guest_info->memmap; - const int *irqmap = guest_info->irqmap; + const MemMapEntry *memmap = vms->memmap; + const int *irqmap = vms->irqmap; dsdt = init_aml_allocator(); /* Reserve space for header */ @@ -674,7 +708,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) * the RTC ACPI device at all when using UEFI. */ scope = aml_scope("\\_SB"); - acpi_dsdt_add_cpus(scope, guest_info->smp_cpus); + acpi_dsdt_add_cpus(scope, vms->smp_cpus); acpi_dsdt_add_uart(scope, &memmap[VIRT_UART], (irqmap[VIRT_UART] + ARM_SPI_BASE)); acpi_dsdt_add_flash(scope, &memmap[VIRT_FLASH]); @@ -682,7 +716,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, VirtGuestInfo *guest_info) acpi_dsdt_add_virtio(scope, &memmap[VIRT_MMIO], (irqmap[VIRT_MMIO] + ARM_SPI_BASE), NUM_VIRTIO_TRANSPORTS); acpi_dsdt_add_pci(scope, memmap, (irqmap[VIRT_PCIE] + ARM_SPI_BASE), - guest_info->use_highmem); + vms->highmem); acpi_dsdt_add_gpio(scope, &memmap[VIRT_GPIO], (irqmap[VIRT_GPIO] + ARM_SPI_BASE)); acpi_dsdt_add_power_button(scope); @@ -705,12 +739,12 @@ struct AcpiBuildState { MemoryRegion *linker_mr; /* Is table patched? */ bool patched; - VirtGuestInfo *guest_info; } AcpiBuildState; static -void virt_acpi_build(VirtGuestInfo *guest_info, AcpiBuildTables *tables) +void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) { + VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms); GArray *table_offsets; unsigned dsdt, rsdt; GArray *tables_blob = tables->table_data; @@ -724,32 +758,32 @@ void virt_acpi_build(VirtGuestInfo *guest_info, AcpiBuildTables *tables) /* DSDT is pointed to by FADT */ dsdt = tables_blob->len; - build_dsdt(tables_blob, tables->linker, guest_info); + build_dsdt(tables_blob, tables->linker, vms); /* FADT MADT GTDT MCFG SPCR pointed to by RSDT */ acpi_add_table(table_offsets, tables_blob); - build_fadt(tables_blob, tables->linker, dsdt); + build_fadt(tables_blob, tables->linker, vms, dsdt); acpi_add_table(table_offsets, tables_blob); - build_madt(tables_blob, tables->linker, guest_info); + build_madt(tables_blob, tables->linker, vms); acpi_add_table(table_offsets, tables_blob); - build_gtdt(tables_blob, tables->linker); + build_gtdt(tables_blob, tables->linker, vms); acpi_add_table(table_offsets, tables_blob); - build_mcfg(tables_blob, tables->linker, guest_info); + build_mcfg(tables_blob, tables->linker, vms); acpi_add_table(table_offsets, tables_blob); - build_spcr(tables_blob, tables->linker, guest_info); + build_spcr(tables_blob, tables->linker, vms); if (nb_numa_nodes > 0) { acpi_add_table(table_offsets, tables_blob); - build_srat(tables_blob, tables->linker, guest_info); + build_srat(tables_blob, tables->linker, vms); } - if (its_class_name() && !guest_info->no_its) { + if (its_class_name() && !vmc->no_its) { acpi_add_table(table_offsets, tables_blob); - build_iort(tables_blob, tables->linker, guest_info); + build_iort(tables_blob, tables->linker); } /* RSDT is pointed to by RSDP */ @@ -788,13 +822,12 @@ static void virt_acpi_build_update(void *build_opaque) acpi_build_tables_init(&tables); - virt_acpi_build(build_state->guest_info, &tables); + virt_acpi_build(VIRT_MACHINE(qdev_get_machine()), &tables); acpi_ram_update(build_state->table_mr, tables.table_data); acpi_ram_update(build_state->rsdp_mr, tables.rsdp); acpi_ram_update(build_state->linker_mr, tables.linker->cmd_blob); - acpi_build_tables_cleanup(&tables, true); } @@ -809,7 +842,7 @@ static MemoryRegion *acpi_add_rom_blob(AcpiBuildState *build_state, uint64_t max_size) { return rom_add_blob(name, blob->data, acpi_data_len(blob), max_size, -1, - name, virt_acpi_build_update, build_state, NULL); + name, virt_acpi_build_update, build_state, NULL, true); } static const VMStateDescription vmstate_virt_acpi_build = { @@ -822,12 +855,12 @@ static const VMStateDescription vmstate_virt_acpi_build = { }, }; -void virt_acpi_setup(VirtGuestInfo *guest_info) +void virt_acpi_setup(VirtMachineState *vms) { AcpiBuildTables tables; AcpiBuildState *build_state; - if (!guest_info->fw_cfg) { + if (!vms->fw_cfg) { trace_virt_acpi_setup(); return; } @@ -838,10 +871,9 @@ void virt_acpi_setup(VirtGuestInfo *guest_info) } build_state = g_malloc0(sizeof *build_state); - build_state->guest_info = guest_info; acpi_build_tables_init(&tables); - virt_acpi_build(build_state->guest_info, &tables); + virt_acpi_build(vms, &tables); /* Now expose it all to Guest */ build_state->table_mr = acpi_add_rom_blob(build_state, tables.table_data, @@ -853,8 +885,8 @@ void virt_acpi_setup(VirtGuestInfo *guest_info) acpi_add_rom_blob(build_state, tables.linker->cmd_blob, "etc/table-loader", 0); - fw_cfg_add_file(guest_info->fw_cfg, ACPI_BUILD_TPMLOG_FILE, - tables.tcpalog->data, acpi_data_len(tables.tcpalog)); + fw_cfg_add_file(vms->fw_cfg, ACPI_BUILD_TPMLOG_FILE, tables.tcpalog->data, + acpi_data_len(tables.tcpalog)); build_state->rsdp_mr = acpi_add_rom_blob(build_state, tables.rsdp, ACPI_BUILD_RSDP_FILE, 0); diff --git a/hw/arm/virt.c b/hw/arm/virt.c index d04e4acbd9..6c9e8985bf 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -41,14 +41,12 @@ #include "sysemu/numa.h" #include "sysemu/sysemu.h" #include "sysemu/kvm.h" -#include "hw/boards.h" #include "hw/compat.h" #include "hw/loader.h" #include "exec/address-spaces.h" #include "qemu/bitops.h" #include "qemu/error-report.h" #include "hw/pci-host/gpex.h" -#include "hw/arm/virt-acpi-build.h" #include "hw/arm/sysbus-fdt.h" #include "hw/platform-bus.h" #include "hw/arm/fdt.h" @@ -59,51 +57,6 @@ #include "qapi/visitor.h" #include "standard-headers/linux/input.h" -/* Number of external interrupt lines to configure the GIC with */ -#define NUM_IRQS 256 - -#define PLATFORM_BUS_NUM_IRQS 64 - -static ARMPlatformBusSystemParams platform_bus_params; - -typedef struct VirtBoardInfo { - struct arm_boot_info bootinfo; - const char *cpu_model; - const MemMapEntry *memmap; - const int *irqmap; - int smp_cpus; - void *fdt; - int fdt_size; - uint32_t clock_phandle; - uint32_t gic_phandle; - uint32_t msi_phandle; - bool using_psci; -} VirtBoardInfo; - -typedef struct { - MachineClass parent; - VirtBoardInfo *daughterboard; - bool disallow_affinity_adjustment; - bool no_its; - bool no_pmu; -} VirtMachineClass; - -typedef struct { - MachineState parent; - bool secure; - bool highmem; - int32_t gic_version; -} VirtMachineState; - -#define TYPE_VIRT_MACHINE MACHINE_TYPE_NAME("virt") -#define VIRT_MACHINE(obj) \ - OBJECT_CHECK(VirtMachineState, (obj), TYPE_VIRT_MACHINE) -#define VIRT_MACHINE_GET_CLASS(obj) \ - OBJECT_GET_CLASS(VirtMachineClass, obj, TYPE_VIRT_MACHINE) -#define VIRT_MACHINE_CLASS(klass) \ - OBJECT_CLASS_CHECK(VirtMachineClass, klass, TYPE_VIRT_MACHINE) - - #define DEFINE_VIRT_MACHINE_LATEST(major, minor, latest) \ static void virt_##major##_##minor##_class_init(ObjectClass *oc, \ void *data) \ @@ -133,6 +86,13 @@ typedef struct { DEFINE_VIRT_MACHINE_LATEST(major, minor, false) +/* Number of external interrupt lines to configure the GIC with */ +#define NUM_IRQS 256 + +#define PLATFORM_BUS_NUM_IRQS 64 + +static ARMPlatformBusSystemParams platform_bus_params; + /* RAM limit in GB. Since VIRT_MEM starts at the 1GB mark, this means * RAM can go up to the 256GB mark, leaving 256GB of the physical * address space unallocated and free for future use between 256G and 512G. @@ -202,51 +162,35 @@ static const int a15irqmap[] = { [VIRT_PLATFORM_BUS] = 112, /* ...to 112 + PLATFORM_BUS_NUM_IRQS -1 */ }; -static VirtBoardInfo machines[] = { - { - .cpu_model = "cortex-a15", - .memmap = a15memmap, - .irqmap = a15irqmap, - }, - { - .cpu_model = "cortex-a53", - .memmap = a15memmap, - .irqmap = a15irqmap, - }, - { - .cpu_model = "cortex-a57", - .memmap = a15memmap, - .irqmap = a15irqmap, - }, - { - .cpu_model = "host", - .memmap = a15memmap, - .irqmap = a15irqmap, - }, +static const char *valid_cpus[] = { + "cortex-a15", + "cortex-a53", + "cortex-a57", + "host", }; -static VirtBoardInfo *find_machine_info(const char *cpu) +static bool cpuname_valid(const char *cpu) { int i; - for (i = 0; i < ARRAY_SIZE(machines); i++) { - if (strcmp(cpu, machines[i].cpu_model) == 0) { - return &machines[i]; + for (i = 0; i < ARRAY_SIZE(valid_cpus); i++) { + if (strcmp(cpu, valid_cpus[i]) == 0) { + return true; } } - return NULL; + return false; } -static void create_fdt(VirtBoardInfo *vbi) +static void create_fdt(VirtMachineState *vms) { - void *fdt = create_device_tree(&vbi->fdt_size); + void *fdt = create_device_tree(&vms->fdt_size); if (!fdt) { error_report("create_device_tree() failed"); exit(1); } - vbi->fdt = fdt; + vms->fdt = fdt; /* Header */ qemu_fdt_setprop_string(fdt, "/", "compatible", "linux,dummy-virt"); @@ -266,28 +210,38 @@ static void create_fdt(VirtBoardInfo *vbi) * optional but in practice if you omit them the kernel refuses to * probe for the device. */ - vbi->clock_phandle = qemu_fdt_alloc_phandle(fdt); + vms->clock_phandle = qemu_fdt_alloc_phandle(fdt); qemu_fdt_add_subnode(fdt, "/apb-pclk"); qemu_fdt_setprop_string(fdt, "/apb-pclk", "compatible", "fixed-clock"); qemu_fdt_setprop_cell(fdt, "/apb-pclk", "#clock-cells", 0x0); qemu_fdt_setprop_cell(fdt, "/apb-pclk", "clock-frequency", 24000000); qemu_fdt_setprop_string(fdt, "/apb-pclk", "clock-output-names", "clk24mhz"); - qemu_fdt_setprop_cell(fdt, "/apb-pclk", "phandle", vbi->clock_phandle); + qemu_fdt_setprop_cell(fdt, "/apb-pclk", "phandle", vms->clock_phandle); } -static void fdt_add_psci_node(const VirtBoardInfo *vbi) +static void fdt_add_psci_node(const VirtMachineState *vms) { uint32_t cpu_suspend_fn; uint32_t cpu_off_fn; uint32_t cpu_on_fn; uint32_t migrate_fn; - void *fdt = vbi->fdt; + void *fdt = vms->fdt; ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(0)); + const char *psci_method; - if (!vbi->using_psci) { + switch (vms->psci_conduit) { + case QEMU_PSCI_CONDUIT_DISABLED: return; + case QEMU_PSCI_CONDUIT_HVC: + psci_method = "hvc"; + break; + case QEMU_PSCI_CONDUIT_SMC: + psci_method = "smc"; + break; + default: + g_assert_not_reached(); } qemu_fdt_add_subnode(fdt, "/psci"); @@ -319,7 +273,7 @@ static void fdt_add_psci_node(const VirtBoardInfo *vbi) * However, the device tree binding uses 'method' instead, so that is * what we should use here. */ - qemu_fdt_setprop_string(fdt, "/psci", "method", "hvc"); + qemu_fdt_setprop_string(fdt, "/psci", "method", psci_method); qemu_fdt_setprop_cell(fdt, "/psci", "cpu_suspend", cpu_suspend_fn); qemu_fdt_setprop_cell(fdt, "/psci", "cpu_off", cpu_off_fn); @@ -327,41 +281,60 @@ static void fdt_add_psci_node(const VirtBoardInfo *vbi) qemu_fdt_setprop_cell(fdt, "/psci", "migrate", migrate_fn); } -static void fdt_add_timer_nodes(const VirtBoardInfo *vbi, int gictype) +static void fdt_add_timer_nodes(const VirtMachineState *vms) { - /* Note that on A15 h/w these interrupts are level-triggered, - * but for the GIC implementation provided by both QEMU and KVM - * they are edge-triggered. + /* On real hardware these interrupts are level-triggered. + * On KVM they were edge-triggered before host kernel version 4.4, + * and level-triggered afterwards. + * On emulated QEMU they are level-triggered. + * + * Getting the DTB info about them wrong is awkward for some + * guest kernels: + * pre-4.8 ignore the DT and leave the interrupt configured + * with whatever the GIC reset value (or the bootloader) left it at + * 4.8 before rc6 honour the incorrect data by programming it back + * into the GIC, causing problems + * 4.8rc6 and later ignore the DT and always write "level triggered" + * into the GIC + * + * For backwards-compatibility, virt-2.8 and earlier will continue + * to say these are edge-triggered, but later machines will report + * the correct information. */ ARMCPU *armcpu; - uint32_t irqflags = GIC_FDT_IRQ_FLAGS_EDGE_LO_HI; + VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms); + uint32_t irqflags = GIC_FDT_IRQ_FLAGS_LEVEL_HI; + + if (vmc->claim_edge_triggered_timers) { + irqflags = GIC_FDT_IRQ_FLAGS_EDGE_LO_HI; + } - if (gictype == 2) { + if (vms->gic_version == 2) { irqflags = deposit32(irqflags, GIC_FDT_IRQ_PPI_CPU_START, GIC_FDT_IRQ_PPI_CPU_WIDTH, - (1 << vbi->smp_cpus) - 1); + (1 << vms->smp_cpus) - 1); } - qemu_fdt_add_subnode(vbi->fdt, "/timer"); + qemu_fdt_add_subnode(vms->fdt, "/timer"); armcpu = ARM_CPU(qemu_get_cpu(0)); if (arm_feature(&armcpu->env, ARM_FEATURE_V8)) { const char compat[] = "arm,armv8-timer\0arm,armv7-timer"; - qemu_fdt_setprop(vbi->fdt, "/timer", "compatible", + qemu_fdt_setprop(vms->fdt, "/timer", "compatible", compat, sizeof(compat)); } else { - qemu_fdt_setprop_string(vbi->fdt, "/timer", "compatible", + qemu_fdt_setprop_string(vms->fdt, "/timer", "compatible", "arm,armv7-timer"); } - qemu_fdt_setprop(vbi->fdt, "/timer", "always-on", NULL, 0); - qemu_fdt_setprop_cells(vbi->fdt, "/timer", "interrupts", + qemu_fdt_setprop(vms->fdt, "/timer", "always-on", NULL, 0); + qemu_fdt_setprop_cells(vms->fdt, "/timer", "interrupts", GIC_FDT_IRQ_TYPE_PPI, ARCH_TIMER_S_EL1_IRQ, irqflags, GIC_FDT_IRQ_TYPE_PPI, ARCH_TIMER_NS_EL1_IRQ, irqflags, GIC_FDT_IRQ_TYPE_PPI, ARCH_TIMER_VIRT_IRQ, irqflags, GIC_FDT_IRQ_TYPE_PPI, ARCH_TIMER_NS_EL2_IRQ, irqflags); } -static void fdt_add_cpu_nodes(const VirtBoardInfo *vbi) +static void fdt_add_cpu_nodes(const VirtMachineState *vms) { int cpu; int addr_cells = 1; @@ -380,7 +353,7 @@ static void fdt_add_cpu_nodes(const VirtBoardInfo *vbi) * The simplest way to go is to examine affinity IDs of all our CPUs. If * at least one of them has Aff3 populated, we set #address-cells to 2. */ - for (cpu = 0; cpu < vbi->smp_cpus; cpu++) { + for (cpu = 0; cpu < vms->smp_cpus; cpu++) { ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(cpu)); if (armcpu->mp_affinity & ARM_AFF3_MASK) { @@ -389,101 +362,107 @@ static void fdt_add_cpu_nodes(const VirtBoardInfo *vbi) } } - qemu_fdt_add_subnode(vbi->fdt, "/cpus"); - qemu_fdt_setprop_cell(vbi->fdt, "/cpus", "#address-cells", addr_cells); - qemu_fdt_setprop_cell(vbi->fdt, "/cpus", "#size-cells", 0x0); + qemu_fdt_add_subnode(vms->fdt, "/cpus"); + qemu_fdt_setprop_cell(vms->fdt, "/cpus", "#address-cells", addr_cells); + qemu_fdt_setprop_cell(vms->fdt, "/cpus", "#size-cells", 0x0); - for (cpu = vbi->smp_cpus - 1; cpu >= 0; cpu--) { + for (cpu = vms->smp_cpus - 1; cpu >= 0; cpu--) { char *nodename = g_strdup_printf("/cpus/cpu@%d", cpu); ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(cpu)); - qemu_fdt_add_subnode(vbi->fdt, nodename); - qemu_fdt_setprop_string(vbi->fdt, nodename, "device_type", "cpu"); - qemu_fdt_setprop_string(vbi->fdt, nodename, "compatible", + qemu_fdt_add_subnode(vms->fdt, nodename); + qemu_fdt_setprop_string(vms->fdt, nodename, "device_type", "cpu"); + qemu_fdt_setprop_string(vms->fdt, nodename, "compatible", armcpu->dtb_compatible); - if (vbi->using_psci && vbi->smp_cpus > 1) { - qemu_fdt_setprop_string(vbi->fdt, nodename, + if (vms->psci_conduit != QEMU_PSCI_CONDUIT_DISABLED + && vms->smp_cpus > 1) { + qemu_fdt_setprop_string(vms->fdt, nodename, "enable-method", "psci"); } if (addr_cells == 2) { - qemu_fdt_setprop_u64(vbi->fdt, nodename, "reg", + qemu_fdt_setprop_u64(vms->fdt, nodename, "reg", armcpu->mp_affinity); } else { - qemu_fdt_setprop_cell(vbi->fdt, nodename, "reg", + qemu_fdt_setprop_cell(vms->fdt, nodename, "reg", armcpu->mp_affinity); } i = numa_get_node_for_cpu(cpu); if (i < nb_numa_nodes) { - qemu_fdt_setprop_cell(vbi->fdt, nodename, "numa-node-id", i); + qemu_fdt_setprop_cell(vms->fdt, nodename, "numa-node-id", i); } g_free(nodename); } } -static void fdt_add_its_gic_node(VirtBoardInfo *vbi) +static void fdt_add_its_gic_node(VirtMachineState *vms) { - vbi->msi_phandle = qemu_fdt_alloc_phandle(vbi->fdt); - qemu_fdt_add_subnode(vbi->fdt, "/intc/its"); - qemu_fdt_setprop_string(vbi->fdt, "/intc/its", "compatible", + vms->msi_phandle = qemu_fdt_alloc_phandle(vms->fdt); + qemu_fdt_add_subnode(vms->fdt, "/intc/its"); + qemu_fdt_setprop_string(vms->fdt, "/intc/its", "compatible", "arm,gic-v3-its"); - qemu_fdt_setprop(vbi->fdt, "/intc/its", "msi-controller", NULL, 0); - qemu_fdt_setprop_sized_cells(vbi->fdt, "/intc/its", "reg", - 2, vbi->memmap[VIRT_GIC_ITS].base, - 2, vbi->memmap[VIRT_GIC_ITS].size); - qemu_fdt_setprop_cell(vbi->fdt, "/intc/its", "phandle", vbi->msi_phandle); + qemu_fdt_setprop(vms->fdt, "/intc/its", "msi-controller", NULL, 0); + qemu_fdt_setprop_sized_cells(vms->fdt, "/intc/its", "reg", + 2, vms->memmap[VIRT_GIC_ITS].base, + 2, vms->memmap[VIRT_GIC_ITS].size); + qemu_fdt_setprop_cell(vms->fdt, "/intc/its", "phandle", vms->msi_phandle); } -static void fdt_add_v2m_gic_node(VirtBoardInfo *vbi) +static void fdt_add_v2m_gic_node(VirtMachineState *vms) { - vbi->msi_phandle = qemu_fdt_alloc_phandle(vbi->fdt); - qemu_fdt_add_subnode(vbi->fdt, "/intc/v2m"); - qemu_fdt_setprop_string(vbi->fdt, "/intc/v2m", "compatible", + vms->msi_phandle = qemu_fdt_alloc_phandle(vms->fdt); + qemu_fdt_add_subnode(vms->fdt, "/intc/v2m"); + qemu_fdt_setprop_string(vms->fdt, "/intc/v2m", "compatible", "arm,gic-v2m-frame"); - qemu_fdt_setprop(vbi->fdt, "/intc/v2m", "msi-controller", NULL, 0); - qemu_fdt_setprop_sized_cells(vbi->fdt, "/intc/v2m", "reg", - 2, vbi->memmap[VIRT_GIC_V2M].base, - 2, vbi->memmap[VIRT_GIC_V2M].size); - qemu_fdt_setprop_cell(vbi->fdt, "/intc/v2m", "phandle", vbi->msi_phandle); + qemu_fdt_setprop(vms->fdt, "/intc/v2m", "msi-controller", NULL, 0); + qemu_fdt_setprop_sized_cells(vms->fdt, "/intc/v2m", "reg", + 2, vms->memmap[VIRT_GIC_V2M].base, + 2, vms->memmap[VIRT_GIC_V2M].size); + qemu_fdt_setprop_cell(vms->fdt, "/intc/v2m", "phandle", vms->msi_phandle); } -static void fdt_add_gic_node(VirtBoardInfo *vbi, int type) +static void fdt_add_gic_node(VirtMachineState *vms) { - vbi->gic_phandle = qemu_fdt_alloc_phandle(vbi->fdt); - qemu_fdt_setprop_cell(vbi->fdt, "/", "interrupt-parent", vbi->gic_phandle); - - qemu_fdt_add_subnode(vbi->fdt, "/intc"); - qemu_fdt_setprop_cell(vbi->fdt, "/intc", "#interrupt-cells", 3); - qemu_fdt_setprop(vbi->fdt, "/intc", "interrupt-controller", NULL, 0); - qemu_fdt_setprop_cell(vbi->fdt, "/intc", "#address-cells", 0x2); - qemu_fdt_setprop_cell(vbi->fdt, "/intc", "#size-cells", 0x2); - qemu_fdt_setprop(vbi->fdt, "/intc", "ranges", NULL, 0); - if (type == 3) { - qemu_fdt_setprop_string(vbi->fdt, "/intc", "compatible", + vms->gic_phandle = qemu_fdt_alloc_phandle(vms->fdt); + qemu_fdt_setprop_cell(vms->fdt, "/", "interrupt-parent", vms->gic_phandle); + + qemu_fdt_add_subnode(vms->fdt, "/intc"); + qemu_fdt_setprop_cell(vms->fdt, "/intc", "#interrupt-cells", 3); + qemu_fdt_setprop(vms->fdt, "/intc", "interrupt-controller", NULL, 0); + qemu_fdt_setprop_cell(vms->fdt, "/intc", "#address-cells", 0x2); + qemu_fdt_setprop_cell(vms->fdt, "/intc", "#size-cells", 0x2); + qemu_fdt_setprop(vms->fdt, "/intc", "ranges", NULL, 0); + if (vms->gic_version == 3) { + qemu_fdt_setprop_string(vms->fdt, "/intc", "compatible", "arm,gic-v3"); - qemu_fdt_setprop_sized_cells(vbi->fdt, "/intc", "reg", - 2, vbi->memmap[VIRT_GIC_DIST].base, - 2, vbi->memmap[VIRT_GIC_DIST].size, - 2, vbi->memmap[VIRT_GIC_REDIST].base, - 2, vbi->memmap[VIRT_GIC_REDIST].size); + qemu_fdt_setprop_sized_cells(vms->fdt, "/intc", "reg", + 2, vms->memmap[VIRT_GIC_DIST].base, + 2, vms->memmap[VIRT_GIC_DIST].size, + 2, vms->memmap[VIRT_GIC_REDIST].base, + 2, vms->memmap[VIRT_GIC_REDIST].size); + if (vms->virt) { + qemu_fdt_setprop_cells(vms->fdt, "/intc", "interrupts", + GIC_FDT_IRQ_TYPE_PPI, ARCH_GICV3_MAINT_IRQ, + GIC_FDT_IRQ_FLAGS_LEVEL_HI); + } } else { /* 'cortex-a15-gic' means 'GIC v2' */ - qemu_fdt_setprop_string(vbi->fdt, "/intc", "compatible", + qemu_fdt_setprop_string(vms->fdt, "/intc", "compatible", "arm,cortex-a15-gic"); - qemu_fdt_setprop_sized_cells(vbi->fdt, "/intc", "reg", - 2, vbi->memmap[VIRT_GIC_DIST].base, - 2, vbi->memmap[VIRT_GIC_DIST].size, - 2, vbi->memmap[VIRT_GIC_CPU].base, - 2, vbi->memmap[VIRT_GIC_CPU].size); + qemu_fdt_setprop_sized_cells(vms->fdt, "/intc", "reg", + 2, vms->memmap[VIRT_GIC_DIST].base, + 2, vms->memmap[VIRT_GIC_DIST].size, + 2, vms->memmap[VIRT_GIC_CPU].base, + 2, vms->memmap[VIRT_GIC_CPU].size); } - qemu_fdt_setprop_cell(vbi->fdt, "/intc", "phandle", vbi->gic_phandle); + qemu_fdt_setprop_cell(vms->fdt, "/intc", "phandle", vms->gic_phandle); } -static void fdt_add_pmu_nodes(const VirtBoardInfo *vbi, int gictype) +static void fdt_add_pmu_nodes(const VirtMachineState *vms) { CPUState *cpu; ARMCPU *armcpu; @@ -497,24 +476,24 @@ static void fdt_add_pmu_nodes(const VirtBoardInfo *vbi, int gictype) } } - if (gictype == 2) { + if (vms->gic_version == 2) { irqflags = deposit32(irqflags, GIC_FDT_IRQ_PPI_CPU_START, GIC_FDT_IRQ_PPI_CPU_WIDTH, - (1 << vbi->smp_cpus) - 1); + (1 << vms->smp_cpus) - 1); } armcpu = ARM_CPU(qemu_get_cpu(0)); - qemu_fdt_add_subnode(vbi->fdt, "/pmu"); + qemu_fdt_add_subnode(vms->fdt, "/pmu"); if (arm_feature(&armcpu->env, ARM_FEATURE_V8)) { const char compat[] = "arm,armv8-pmuv3"; - qemu_fdt_setprop(vbi->fdt, "/pmu", "compatible", + qemu_fdt_setprop(vms->fdt, "/pmu", "compatible", compat, sizeof(compat)); - qemu_fdt_setprop_cells(vbi->fdt, "/pmu", "interrupts", + qemu_fdt_setprop_cells(vms->fdt, "/pmu", "interrupts", GIC_FDT_IRQ_TYPE_PPI, VIRTUAL_PMU_IRQ, irqflags); } } -static void create_its(VirtBoardInfo *vbi, DeviceState *gicdev) +static void create_its(VirtMachineState *vms, DeviceState *gicdev) { const char *itsclass = its_class_name(); DeviceState *dev; @@ -529,19 +508,19 @@ static void create_its(VirtBoardInfo *vbi, DeviceState *gicdev) object_property_set_link(OBJECT(dev), OBJECT(gicdev), "parent-gicv3", &error_abort); qdev_init_nofail(dev); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, vbi->memmap[VIRT_GIC_ITS].base); + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, vms->memmap[VIRT_GIC_ITS].base); - fdt_add_its_gic_node(vbi); + fdt_add_its_gic_node(vms); } -static void create_v2m(VirtBoardInfo *vbi, qemu_irq *pic) +static void create_v2m(VirtMachineState *vms, qemu_irq *pic) { int i; - int irq = vbi->irqmap[VIRT_GIC_V2M]; + int irq = vms->irqmap[VIRT_GIC_V2M]; DeviceState *dev; dev = qdev_create(NULL, "arm-gicv2m"); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, vbi->memmap[VIRT_GIC_V2M].base); + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, vms->memmap[VIRT_GIC_V2M].base); qdev_prop_set_uint32(dev, "base-spi", irq); qdev_prop_set_uint32(dev, "num-spi", NUM_GICV2M_SPIS); qdev_init_nofail(dev); @@ -550,17 +529,17 @@ static void create_v2m(VirtBoardInfo *vbi, qemu_irq *pic) sysbus_connect_irq(SYS_BUS_DEVICE(dev), i, pic[irq + i]); } - fdt_add_v2m_gic_node(vbi); + fdt_add_v2m_gic_node(vms); } -static void create_gic(VirtBoardInfo *vbi, qemu_irq *pic, int type, - bool secure, bool no_its) +static void create_gic(VirtMachineState *vms, qemu_irq *pic) { /* We create a standalone GIC */ + VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms); DeviceState *gicdev; SysBusDevice *gicbusdev; const char *gictype; - int i; + int type = vms->gic_version, i; gictype = (type == 3) ? gicv3_class_name() : gic_class_name(); @@ -572,20 +551,20 @@ static void create_gic(VirtBoardInfo *vbi, qemu_irq *pic, int type, */ qdev_prop_set_uint32(gicdev, "num-irq", NUM_IRQS + 32); if (!kvm_irqchip_in_kernel()) { - qdev_prop_set_bit(gicdev, "has-security-extensions", secure); + qdev_prop_set_bit(gicdev, "has-security-extensions", vms->secure); } qdev_init_nofail(gicdev); gicbusdev = SYS_BUS_DEVICE(gicdev); - sysbus_mmio_map(gicbusdev, 0, vbi->memmap[VIRT_GIC_DIST].base); + sysbus_mmio_map(gicbusdev, 0, vms->memmap[VIRT_GIC_DIST].base); if (type == 3) { - sysbus_mmio_map(gicbusdev, 1, vbi->memmap[VIRT_GIC_REDIST].base); + sysbus_mmio_map(gicbusdev, 1, vms->memmap[VIRT_GIC_REDIST].base); } else { - sysbus_mmio_map(gicbusdev, 1, vbi->memmap[VIRT_GIC_CPU].base); + sysbus_mmio_map(gicbusdev, 1, vms->memmap[VIRT_GIC_CPU].base); } - /* Wire the outputs from each CPU's generic timer to the - * appropriate GIC PPI inputs, and the GIC's IRQ output to - * the CPU's IRQ input. + /* Wire the outputs from each CPU's generic timer and the GICv3 + * maintenance interrupt signal to the appropriate GIC PPI inputs, + * and the GIC's IRQ/FIQ/VIRQ/VFIQ interrupt outputs to the CPU's inputs. */ for (i = 0; i < smp_cpus; i++) { DeviceState *cpudev = DEVICE(qemu_get_cpu(i)); @@ -607,31 +586,39 @@ static void create_gic(VirtBoardInfo *vbi, qemu_irq *pic, int type, ppibase + timer_irq[irq])); } + qdev_connect_gpio_out_named(cpudev, "gicv3-maintenance-interrupt", 0, + qdev_get_gpio_in(gicdev, ppibase + + ARCH_GICV3_MAINT_IRQ)); + sysbus_connect_irq(gicbusdev, i, qdev_get_gpio_in(cpudev, ARM_CPU_IRQ)); sysbus_connect_irq(gicbusdev, i + smp_cpus, qdev_get_gpio_in(cpudev, ARM_CPU_FIQ)); + sysbus_connect_irq(gicbusdev, i + 2 * smp_cpus, + qdev_get_gpio_in(cpudev, ARM_CPU_VIRQ)); + sysbus_connect_irq(gicbusdev, i + 3 * smp_cpus, + qdev_get_gpio_in(cpudev, ARM_CPU_VFIQ)); } for (i = 0; i < NUM_IRQS; i++) { pic[i] = qdev_get_gpio_in(gicdev, i); } - fdt_add_gic_node(vbi, type); + fdt_add_gic_node(vms); - if (type == 3 && !no_its) { - create_its(vbi, gicdev); + if (type == 3 && !vmc->no_its) { + create_its(vms, gicdev); } else if (type == 2) { - create_v2m(vbi, pic); + create_v2m(vms, pic); } } -static void create_uart(const VirtBoardInfo *vbi, qemu_irq *pic, int uart, +static void create_uart(const VirtMachineState *vms, qemu_irq *pic, int uart, MemoryRegion *mem, CharDriverState *chr) { char *nodename; - hwaddr base = vbi->memmap[uart].base; - hwaddr size = vbi->memmap[uart].size; - int irq = vbi->irqmap[uart]; + hwaddr base = vms->memmap[uart].base; + hwaddr size = vms->memmap[uart].size; + int irq = vms->irqmap[uart]; const char compat[] = "arm,pl011\0arm,primecell"; const char clocknames[] = "uartclk\0apb_pclk"; DeviceState *dev = qdev_create(NULL, "pl011"); @@ -644,51 +631,51 @@ static void create_uart(const VirtBoardInfo *vbi, qemu_irq *pic, int uart, sysbus_connect_irq(s, 0, pic[irq]); nodename = g_strdup_printf("/pl011@%" PRIx64, base); - qemu_fdt_add_subnode(vbi->fdt, nodename); + qemu_fdt_add_subnode(vms->fdt, nodename); /* Note that we can't use setprop_string because of the embedded NUL */ - qemu_fdt_setprop(vbi->fdt, nodename, "compatible", + qemu_fdt_setprop(vms->fdt, nodename, "compatible", compat, sizeof(compat)); - qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg", + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, base, 2, size); - qemu_fdt_setprop_cells(vbi->fdt, nodename, "interrupts", + qemu_fdt_setprop_cells(vms->fdt, nodename, "interrupts", GIC_FDT_IRQ_TYPE_SPI, irq, GIC_FDT_IRQ_FLAGS_LEVEL_HI); - qemu_fdt_setprop_cells(vbi->fdt, nodename, "clocks", - vbi->clock_phandle, vbi->clock_phandle); - qemu_fdt_setprop(vbi->fdt, nodename, "clock-names", + qemu_fdt_setprop_cells(vms->fdt, nodename, "clocks", + vms->clock_phandle, vms->clock_phandle); + qemu_fdt_setprop(vms->fdt, nodename, "clock-names", clocknames, sizeof(clocknames)); if (uart == VIRT_UART) { - qemu_fdt_setprop_string(vbi->fdt, "/chosen", "stdout-path", nodename); + qemu_fdt_setprop_string(vms->fdt, "/chosen", "stdout-path", nodename); } else { /* Mark as not usable by the normal world */ - qemu_fdt_setprop_string(vbi->fdt, nodename, "status", "disabled"); - qemu_fdt_setprop_string(vbi->fdt, nodename, "secure-status", "okay"); + qemu_fdt_setprop_string(vms->fdt, nodename, "status", "disabled"); + qemu_fdt_setprop_string(vms->fdt, nodename, "secure-status", "okay"); } g_free(nodename); } -static void create_rtc(const VirtBoardInfo *vbi, qemu_irq *pic) +static void create_rtc(const VirtMachineState *vms, qemu_irq *pic) { char *nodename; - hwaddr base = vbi->memmap[VIRT_RTC].base; - hwaddr size = vbi->memmap[VIRT_RTC].size; - int irq = vbi->irqmap[VIRT_RTC]; + hwaddr base = vms->memmap[VIRT_RTC].base; + hwaddr size = vms->memmap[VIRT_RTC].size; + int irq = vms->irqmap[VIRT_RTC]; const char compat[] = "arm,pl031\0arm,primecell"; sysbus_create_simple("pl031", base, pic[irq]); nodename = g_strdup_printf("/pl031@%" PRIx64, base); - qemu_fdt_add_subnode(vbi->fdt, nodename); - qemu_fdt_setprop(vbi->fdt, nodename, "compatible", compat, sizeof(compat)); - qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg", + qemu_fdt_add_subnode(vms->fdt, nodename); + qemu_fdt_setprop(vms->fdt, nodename, "compatible", compat, sizeof(compat)); + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, base, 2, size); - qemu_fdt_setprop_cells(vbi->fdt, nodename, "interrupts", + qemu_fdt_setprop_cells(vms->fdt, nodename, "interrupts", GIC_FDT_IRQ_TYPE_SPI, irq, GIC_FDT_IRQ_FLAGS_LEVEL_HI); - qemu_fdt_setprop_cell(vbi->fdt, nodename, "clocks", vbi->clock_phandle); - qemu_fdt_setprop_string(vbi->fdt, nodename, "clock-names", "apb_pclk"); + qemu_fdt_setprop_cell(vms->fdt, nodename, "clocks", vms->clock_phandle); + qemu_fdt_setprop_string(vms->fdt, nodename, "clock-names", "apb_pclk"); g_free(nodename); } @@ -703,45 +690,45 @@ static Notifier virt_system_powerdown_notifier = { .notify = virt_powerdown_req }; -static void create_gpio(const VirtBoardInfo *vbi, qemu_irq *pic) +static void create_gpio(const VirtMachineState *vms, qemu_irq *pic) { char *nodename; DeviceState *pl061_dev; - hwaddr base = vbi->memmap[VIRT_GPIO].base; - hwaddr size = vbi->memmap[VIRT_GPIO].size; - int irq = vbi->irqmap[VIRT_GPIO]; + hwaddr base = vms->memmap[VIRT_GPIO].base; + hwaddr size = vms->memmap[VIRT_GPIO].size; + int irq = vms->irqmap[VIRT_GPIO]; const char compat[] = "arm,pl061\0arm,primecell"; pl061_dev = sysbus_create_simple("pl061", base, pic[irq]); - uint32_t phandle = qemu_fdt_alloc_phandle(vbi->fdt); + uint32_t phandle = qemu_fdt_alloc_phandle(vms->fdt); nodename = g_strdup_printf("/pl061@%" PRIx64, base); - qemu_fdt_add_subnode(vbi->fdt, nodename); - qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg", + qemu_fdt_add_subnode(vms->fdt, nodename); + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, base, 2, size); - qemu_fdt_setprop(vbi->fdt, nodename, "compatible", compat, sizeof(compat)); - qemu_fdt_setprop_cell(vbi->fdt, nodename, "#gpio-cells", 2); - qemu_fdt_setprop(vbi->fdt, nodename, "gpio-controller", NULL, 0); - qemu_fdt_setprop_cells(vbi->fdt, nodename, "interrupts", + qemu_fdt_setprop(vms->fdt, nodename, "compatible", compat, sizeof(compat)); + qemu_fdt_setprop_cell(vms->fdt, nodename, "#gpio-cells", 2); + qemu_fdt_setprop(vms->fdt, nodename, "gpio-controller", NULL, 0); + qemu_fdt_setprop_cells(vms->fdt, nodename, "interrupts", GIC_FDT_IRQ_TYPE_SPI, irq, GIC_FDT_IRQ_FLAGS_LEVEL_HI); - qemu_fdt_setprop_cell(vbi->fdt, nodename, "clocks", vbi->clock_phandle); - qemu_fdt_setprop_string(vbi->fdt, nodename, "clock-names", "apb_pclk"); - qemu_fdt_setprop_cell(vbi->fdt, nodename, "phandle", phandle); + qemu_fdt_setprop_cell(vms->fdt, nodename, "clocks", vms->clock_phandle); + qemu_fdt_setprop_string(vms->fdt, nodename, "clock-names", "apb_pclk"); + qemu_fdt_setprop_cell(vms->fdt, nodename, "phandle", phandle); gpio_key_dev = sysbus_create_simple("gpio-key", -1, qdev_get_gpio_in(pl061_dev, 3)); - qemu_fdt_add_subnode(vbi->fdt, "/gpio-keys"); - qemu_fdt_setprop_string(vbi->fdt, "/gpio-keys", "compatible", "gpio-keys"); - qemu_fdt_setprop_cell(vbi->fdt, "/gpio-keys", "#size-cells", 0); - qemu_fdt_setprop_cell(vbi->fdt, "/gpio-keys", "#address-cells", 1); + qemu_fdt_add_subnode(vms->fdt, "/gpio-keys"); + qemu_fdt_setprop_string(vms->fdt, "/gpio-keys", "compatible", "gpio-keys"); + qemu_fdt_setprop_cell(vms->fdt, "/gpio-keys", "#size-cells", 0); + qemu_fdt_setprop_cell(vms->fdt, "/gpio-keys", "#address-cells", 1); - qemu_fdt_add_subnode(vbi->fdt, "/gpio-keys/poweroff"); - qemu_fdt_setprop_string(vbi->fdt, "/gpio-keys/poweroff", + qemu_fdt_add_subnode(vms->fdt, "/gpio-keys/poweroff"); + qemu_fdt_setprop_string(vms->fdt, "/gpio-keys/poweroff", "label", "GPIO Key Poweroff"); - qemu_fdt_setprop_cell(vbi->fdt, "/gpio-keys/poweroff", "linux,code", + qemu_fdt_setprop_cell(vms->fdt, "/gpio-keys/poweroff", "linux,code", KEY_POWER); - qemu_fdt_setprop_cells(vbi->fdt, "/gpio-keys/poweroff", + qemu_fdt_setprop_cells(vms->fdt, "/gpio-keys/poweroff", "gpios", phandle, 3, 0); /* connect powerdown request */ @@ -750,10 +737,10 @@ static void create_gpio(const VirtBoardInfo *vbi, qemu_irq *pic) g_free(nodename); } -static void create_virtio_devices(const VirtBoardInfo *vbi, qemu_irq *pic) +static void create_virtio_devices(const VirtMachineState *vms, qemu_irq *pic) { int i; - hwaddr size = vbi->memmap[VIRT_MMIO].size; + hwaddr size = vms->memmap[VIRT_MMIO].size; /* We create the transports in forwards order. Since qbus_realize() * prepends (not appends) new child buses, the incrementing loop below will @@ -783,8 +770,8 @@ static void create_virtio_devices(const VirtBoardInfo *vbi, qemu_irq *pic) * of disks users must use UUIDs or similar mechanisms. */ for (i = 0; i < NUM_VIRTIO_TRANSPORTS; i++) { - int irq = vbi->irqmap[VIRT_MMIO] + i; - hwaddr base = vbi->memmap[VIRT_MMIO].base + i * size; + int irq = vms->irqmap[VIRT_MMIO] + i; + hwaddr base = vms->memmap[VIRT_MMIO].base + i * size; sysbus_create_simple("virtio-mmio", base, pic[irq]); } @@ -798,16 +785,16 @@ static void create_virtio_devices(const VirtBoardInfo *vbi, qemu_irq *pic) */ for (i = NUM_VIRTIO_TRANSPORTS - 1; i >= 0; i--) { char *nodename; - int irq = vbi->irqmap[VIRT_MMIO] + i; - hwaddr base = vbi->memmap[VIRT_MMIO].base + i * size; + int irq = vms->irqmap[VIRT_MMIO] + i; + hwaddr base = vms->memmap[VIRT_MMIO].base + i * size; nodename = g_strdup_printf("/virtio_mmio@%" PRIx64, base); - qemu_fdt_add_subnode(vbi->fdt, nodename); - qemu_fdt_setprop_string(vbi->fdt, nodename, + qemu_fdt_add_subnode(vms->fdt, nodename); + qemu_fdt_setprop_string(vms->fdt, nodename, "compatible", "virtio,mmio"); - qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg", + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, base, 2, size); - qemu_fdt_setprop_cells(vbi->fdt, nodename, "interrupts", + qemu_fdt_setprop_cells(vms->fdt, nodename, "interrupts", GIC_FDT_IRQ_TYPE_SPI, irq, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI); g_free(nodename); @@ -870,7 +857,7 @@ static void create_one_flash(const char *name, hwaddr flashbase, } } -static void create_flash(const VirtBoardInfo *vbi, +static void create_flash(const VirtMachineState *vms, MemoryRegion *sysmem, MemoryRegion *secure_sysmem) { @@ -882,8 +869,8 @@ static void create_flash(const VirtBoardInfo *vbi, * If sysmem == secure_sysmem this means there is no separate Secure * address space and both flash devices are generally visible. */ - hwaddr flashsize = vbi->memmap[VIRT_FLASH].size / 2; - hwaddr flashbase = vbi->memmap[VIRT_FLASH].base; + hwaddr flashsize = vms->memmap[VIRT_FLASH].size / 2; + hwaddr flashbase = vms->memmap[VIRT_FLASH].base; char *nodename; create_one_flash("virt.flash0", flashbase, flashsize, @@ -894,41 +881,41 @@ static void create_flash(const VirtBoardInfo *vbi, if (sysmem == secure_sysmem) { /* Report both flash devices as a single node in the DT */ nodename = g_strdup_printf("/flash@%" PRIx64, flashbase); - qemu_fdt_add_subnode(vbi->fdt, nodename); - qemu_fdt_setprop_string(vbi->fdt, nodename, "compatible", "cfi-flash"); - qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg", + qemu_fdt_add_subnode(vms->fdt, nodename); + qemu_fdt_setprop_string(vms->fdt, nodename, "compatible", "cfi-flash"); + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, flashbase, 2, flashsize, 2, flashbase + flashsize, 2, flashsize); - qemu_fdt_setprop_cell(vbi->fdt, nodename, "bank-width", 4); + qemu_fdt_setprop_cell(vms->fdt, nodename, "bank-width", 4); g_free(nodename); } else { /* Report the devices as separate nodes so we can mark one as * only visible to the secure world. */ nodename = g_strdup_printf("/secflash@%" PRIx64, flashbase); - qemu_fdt_add_subnode(vbi->fdt, nodename); - qemu_fdt_setprop_string(vbi->fdt, nodename, "compatible", "cfi-flash"); - qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg", + qemu_fdt_add_subnode(vms->fdt, nodename); + qemu_fdt_setprop_string(vms->fdt, nodename, "compatible", "cfi-flash"); + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, flashbase, 2, flashsize); - qemu_fdt_setprop_cell(vbi->fdt, nodename, "bank-width", 4); - qemu_fdt_setprop_string(vbi->fdt, nodename, "status", "disabled"); - qemu_fdt_setprop_string(vbi->fdt, nodename, "secure-status", "okay"); + qemu_fdt_setprop_cell(vms->fdt, nodename, "bank-width", 4); + qemu_fdt_setprop_string(vms->fdt, nodename, "status", "disabled"); + qemu_fdt_setprop_string(vms->fdt, nodename, "secure-status", "okay"); g_free(nodename); nodename = g_strdup_printf("/flash@%" PRIx64, flashbase); - qemu_fdt_add_subnode(vbi->fdt, nodename); - qemu_fdt_setprop_string(vbi->fdt, nodename, "compatible", "cfi-flash"); - qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg", + qemu_fdt_add_subnode(vms->fdt, nodename); + qemu_fdt_setprop_string(vms->fdt, nodename, "compatible", "cfi-flash"); + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, flashbase + flashsize, 2, flashsize); - qemu_fdt_setprop_cell(vbi->fdt, nodename, "bank-width", 4); + qemu_fdt_setprop_cell(vms->fdt, nodename, "bank-width", 4); g_free(nodename); } } -static void create_fw_cfg(const VirtBoardInfo *vbi, AddressSpace *as) +static FWCfgState *create_fw_cfg(const VirtMachineState *vms, AddressSpace *as) { - hwaddr base = vbi->memmap[VIRT_FW_CFG].base; - hwaddr size = vbi->memmap[VIRT_FW_CFG].size; + hwaddr base = vms->memmap[VIRT_FW_CFG].base; + hwaddr size = vms->memmap[VIRT_FW_CFG].size; FWCfgState *fw_cfg; char *nodename; @@ -936,15 +923,17 @@ static void create_fw_cfg(const VirtBoardInfo *vbi, AddressSpace *as) fw_cfg_add_i16(fw_cfg, FW_CFG_NB_CPUS, (uint16_t)smp_cpus); nodename = g_strdup_printf("/fw-cfg@%" PRIx64, base); - qemu_fdt_add_subnode(vbi->fdt, nodename); - qemu_fdt_setprop_string(vbi->fdt, nodename, + qemu_fdt_add_subnode(vms->fdt, nodename); + qemu_fdt_setprop_string(vms->fdt, nodename, "compatible", "qemu,fw-cfg-mmio"); - qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg", + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, base, 2, size); g_free(nodename); + return fw_cfg; } -static void create_pcie_irq_map(const VirtBoardInfo *vbi, uint32_t gic_phandle, +static void create_pcie_irq_map(const VirtMachineState *vms, + uint32_t gic_phandle, int first_irq, const char *nodename) { int devfn, pin; @@ -971,28 +960,27 @@ static void create_pcie_irq_map(const VirtBoardInfo *vbi, uint32_t gic_phandle, } } - qemu_fdt_setprop(vbi->fdt, nodename, "interrupt-map", + qemu_fdt_setprop(vms->fdt, nodename, "interrupt-map", full_irq_map, sizeof(full_irq_map)); - qemu_fdt_setprop_cells(vbi->fdt, nodename, "interrupt-map-mask", + qemu_fdt_setprop_cells(vms->fdt, nodename, "interrupt-map-mask", 0x1800, 0, 0, /* devfn (PCI_SLOT(3)) */ 0x7 /* PCI irq */); } -static void create_pcie(const VirtBoardInfo *vbi, qemu_irq *pic, - bool use_highmem) +static void create_pcie(const VirtMachineState *vms, qemu_irq *pic) { - hwaddr base_mmio = vbi->memmap[VIRT_PCIE_MMIO].base; - hwaddr size_mmio = vbi->memmap[VIRT_PCIE_MMIO].size; - hwaddr base_mmio_high = vbi->memmap[VIRT_PCIE_MMIO_HIGH].base; - hwaddr size_mmio_high = vbi->memmap[VIRT_PCIE_MMIO_HIGH].size; - hwaddr base_pio = vbi->memmap[VIRT_PCIE_PIO].base; - hwaddr size_pio = vbi->memmap[VIRT_PCIE_PIO].size; - hwaddr base_ecam = vbi->memmap[VIRT_PCIE_ECAM].base; - hwaddr size_ecam = vbi->memmap[VIRT_PCIE_ECAM].size; + hwaddr base_mmio = vms->memmap[VIRT_PCIE_MMIO].base; + hwaddr size_mmio = vms->memmap[VIRT_PCIE_MMIO].size; + hwaddr base_mmio_high = vms->memmap[VIRT_PCIE_MMIO_HIGH].base; + hwaddr size_mmio_high = vms->memmap[VIRT_PCIE_MMIO_HIGH].size; + hwaddr base_pio = vms->memmap[VIRT_PCIE_PIO].base; + hwaddr size_pio = vms->memmap[VIRT_PCIE_PIO].size; + hwaddr base_ecam = vms->memmap[VIRT_PCIE_ECAM].base; + hwaddr size_ecam = vms->memmap[VIRT_PCIE_ECAM].size; hwaddr base = base_mmio; int nr_pcie_buses = size_ecam / PCIE_MMCFG_SIZE_MIN; - int irq = vbi->irqmap[VIRT_PCIE]; + int irq = vms->irqmap[VIRT_PCIE]; MemoryRegion *mmio_alias; MemoryRegion *mmio_reg; MemoryRegion *ecam_alias; @@ -1023,7 +1011,7 @@ static void create_pcie(const VirtBoardInfo *vbi, qemu_irq *pic, mmio_reg, base_mmio, size_mmio); memory_region_add_subregion(get_system_memory(), base_mmio, mmio_alias); - if (use_highmem) { + if (vms->highmem) { /* Map high MMIO space */ MemoryRegion *high_mmio_alias = g_new0(MemoryRegion, 1); @@ -1054,26 +1042,26 @@ static void create_pcie(const VirtBoardInfo *vbi, qemu_irq *pic, } nodename = g_strdup_printf("/pcie@%" PRIx64, base); - qemu_fdt_add_subnode(vbi->fdt, nodename); - qemu_fdt_setprop_string(vbi->fdt, nodename, + qemu_fdt_add_subnode(vms->fdt, nodename); + qemu_fdt_setprop_string(vms->fdt, nodename, "compatible", "pci-host-ecam-generic"); - qemu_fdt_setprop_string(vbi->fdt, nodename, "device_type", "pci"); - qemu_fdt_setprop_cell(vbi->fdt, nodename, "#address-cells", 3); - qemu_fdt_setprop_cell(vbi->fdt, nodename, "#size-cells", 2); - qemu_fdt_setprop_cells(vbi->fdt, nodename, "bus-range", 0, + qemu_fdt_setprop_string(vms->fdt, nodename, "device_type", "pci"); + qemu_fdt_setprop_cell(vms->fdt, nodename, "#address-cells", 3); + qemu_fdt_setprop_cell(vms->fdt, nodename, "#size-cells", 2); + qemu_fdt_setprop_cells(vms->fdt, nodename, "bus-range", 0, nr_pcie_buses - 1); - qemu_fdt_setprop(vbi->fdt, nodename, "dma-coherent", NULL, 0); + qemu_fdt_setprop(vms->fdt, nodename, "dma-coherent", NULL, 0); - if (vbi->msi_phandle) { - qemu_fdt_setprop_cells(vbi->fdt, nodename, "msi-parent", - vbi->msi_phandle); + if (vms->msi_phandle) { + qemu_fdt_setprop_cells(vms->fdt, nodename, "msi-parent", + vms->msi_phandle); } - qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg", + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, base_ecam, 2, size_ecam); - if (use_highmem) { - qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "ranges", + if (vms->highmem) { + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "ranges", 1, FDT_PCI_RANGE_IOPORT, 2, 0, 2, base_pio, 2, size_pio, 1, FDT_PCI_RANGE_MMIO, 2, base_mmio, @@ -1082,20 +1070,20 @@ static void create_pcie(const VirtBoardInfo *vbi, qemu_irq *pic, 2, base_mmio_high, 2, base_mmio_high, 2, size_mmio_high); } else { - qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "ranges", + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "ranges", 1, FDT_PCI_RANGE_IOPORT, 2, 0, 2, base_pio, 2, size_pio, 1, FDT_PCI_RANGE_MMIO, 2, base_mmio, 2, base_mmio, 2, size_mmio); } - qemu_fdt_setprop_cell(vbi->fdt, nodename, "#interrupt-cells", 1); - create_pcie_irq_map(vbi, vbi->gic_phandle, irq, nodename); + qemu_fdt_setprop_cell(vms->fdt, nodename, "#interrupt-cells", 1); + create_pcie_irq_map(vms, vms->gic_phandle, irq, nodename); g_free(nodename); } -static void create_platform_bus(VirtBoardInfo *vbi, qemu_irq *pic) +static void create_platform_bus(VirtMachineState *vms, qemu_irq *pic) { DeviceState *dev; SysBusDevice *s; @@ -1103,13 +1091,13 @@ static void create_platform_bus(VirtBoardInfo *vbi, qemu_irq *pic) ARMPlatformBusFDTParams *fdt_params = g_new(ARMPlatformBusFDTParams, 1); MemoryRegion *sysmem = get_system_memory(); - platform_bus_params.platform_bus_base = vbi->memmap[VIRT_PLATFORM_BUS].base; - platform_bus_params.platform_bus_size = vbi->memmap[VIRT_PLATFORM_BUS].size; - platform_bus_params.platform_bus_first_irq = vbi->irqmap[VIRT_PLATFORM_BUS]; + platform_bus_params.platform_bus_base = vms->memmap[VIRT_PLATFORM_BUS].base; + platform_bus_params.platform_bus_size = vms->memmap[VIRT_PLATFORM_BUS].size; + platform_bus_params.platform_bus_first_irq = vms->irqmap[VIRT_PLATFORM_BUS]; platform_bus_params.platform_bus_num_irqs = PLATFORM_BUS_NUM_IRQS; fdt_params->system_params = &platform_bus_params; - fdt_params->binfo = &vbi->bootinfo; + fdt_params->binfo = &vms->bootinfo; fdt_params->intc = "/intc"; /* * register a machine init done notifier that creates the device tree @@ -1136,43 +1124,44 @@ static void create_platform_bus(VirtBoardInfo *vbi, qemu_irq *pic) sysbus_mmio_get_region(s, 0)); } -static void create_secure_ram(VirtBoardInfo *vbi, MemoryRegion *secure_sysmem) +static void create_secure_ram(VirtMachineState *vms, + MemoryRegion *secure_sysmem) { MemoryRegion *secram = g_new(MemoryRegion, 1); char *nodename; - hwaddr base = vbi->memmap[VIRT_SECURE_MEM].base; - hwaddr size = vbi->memmap[VIRT_SECURE_MEM].size; + hwaddr base = vms->memmap[VIRT_SECURE_MEM].base; + hwaddr size = vms->memmap[VIRT_SECURE_MEM].size; memory_region_init_ram(secram, NULL, "virt.secure-ram", size, &error_fatal); vmstate_register_ram_global(secram); memory_region_add_subregion(secure_sysmem, base, secram); nodename = g_strdup_printf("/secram@%" PRIx64, base); - qemu_fdt_add_subnode(vbi->fdt, nodename); - qemu_fdt_setprop_string(vbi->fdt, nodename, "device_type", "memory"); - qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg", 2, base, 2, size); - qemu_fdt_setprop_string(vbi->fdt, nodename, "status", "disabled"); - qemu_fdt_setprop_string(vbi->fdt, nodename, "secure-status", "okay"); + qemu_fdt_add_subnode(vms->fdt, nodename); + qemu_fdt_setprop_string(vms->fdt, nodename, "device_type", "memory"); + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, base, 2, size); + qemu_fdt_setprop_string(vms->fdt, nodename, "status", "disabled"); + qemu_fdt_setprop_string(vms->fdt, nodename, "secure-status", "okay"); g_free(nodename); } static void *machvirt_dtb(const struct arm_boot_info *binfo, int *fdt_size) { - const VirtBoardInfo *board = (const VirtBoardInfo *)binfo; + const VirtMachineState *board = container_of(binfo, VirtMachineState, + bootinfo); *fdt_size = board->fdt_size; return board->fdt; } -static void virt_build_smbios(VirtGuestInfo *guest_info) +static void virt_build_smbios(VirtMachineState *vms) { - FWCfgState *fw_cfg = guest_info->fw_cfg; uint8_t *smbios_tables, *smbios_anchor; size_t smbios_tables_len, smbios_anchor_len; const char *product = "QEMU Virtual Machine"; - if (!fw_cfg) { + if (!vms->fw_cfg) { return; } @@ -1187,20 +1176,21 @@ static void virt_build_smbios(VirtGuestInfo *guest_info) &smbios_anchor, &smbios_anchor_len); if (smbios_anchor) { - fw_cfg_add_file(fw_cfg, "etc/smbios/smbios-tables", + fw_cfg_add_file(vms->fw_cfg, "etc/smbios/smbios-tables", smbios_tables, smbios_tables_len); - fw_cfg_add_file(fw_cfg, "etc/smbios/smbios-anchor", + fw_cfg_add_file(vms->fw_cfg, "etc/smbios/smbios-anchor", smbios_anchor, smbios_anchor_len); } } static -void virt_guest_info_machine_done(Notifier *notifier, void *data) +void virt_machine_done(Notifier *notifier, void *data) { - VirtGuestInfoState *guest_info_state = container_of(notifier, - VirtGuestInfoState, machine_done); - virt_acpi_setup(&guest_info_state->info); - virt_build_smbios(&guest_info_state->info); + VirtMachineState *vms = container_of(notifier, VirtMachineState, + machine_done); + + virt_acpi_setup(vms); + virt_build_smbios(vms); } static void machvirt_init(MachineState *machine) @@ -1210,13 +1200,9 @@ static void machvirt_init(MachineState *machine) qemu_irq pic[NUM_IRQS]; MemoryRegion *sysmem = get_system_memory(); MemoryRegion *secure_sysmem = NULL; - int gic_version = vms->gic_version; int n, virt_max_cpus; MemoryRegion *ram = g_new(MemoryRegion, 1); const char *cpu_model = machine->cpu_model; - VirtBoardInfo *vbi; - VirtGuestInfoState *guest_info_state = g_malloc0(sizeof *guest_info_state); - VirtGuestInfo *guest_info = &guest_info_state->info; char **cpustr; ObjectClass *oc; const char *typename; @@ -1232,14 +1218,14 @@ static void machvirt_init(MachineState *machine) /* We can probe only here because during property set * KVM is not available yet */ - if (!gic_version) { + if (!vms->gic_version) { if (!kvm_enabled()) { error_report("gic-version=host requires KVM"); exit(1); } - gic_version = kvm_arm_vgic_probe(); - if (!gic_version) { + vms->gic_version = kvm_arm_vgic_probe(); + if (!vms->gic_version) { error_report("Unable to determine GIC version supported by host"); exit(1); } @@ -1248,9 +1234,7 @@ static void machvirt_init(MachineState *machine) /* Separate the actual CPU model name from any appended features */ cpustr = g_strsplit(cpu_model, ",", 2); - vbi = find_machine_info(cpustr[0]); - - if (!vbi) { + if (!cpuname_valid(cpustr[0])) { error_report("mach-virt: CPU %s not supported", cpustr[0]); exit(1); } @@ -1260,15 +1244,24 @@ static void machvirt_init(MachineState *machine) * so it doesn't get in the way. Instead of starting secondary * CPUs in PSCI powerdown state we will start them all running and * let the boot ROM sort them out. - * The usual case is that we do use QEMU's PSCI implementation. + * The usual case is that we do use QEMU's PSCI implementation; + * if the guest has EL2 then we will use SMC as the conduit, + * and otherwise we will use HVC (for backwards compatibility and + * because if we're using KVM then we must use HVC). */ - vbi->using_psci = !(vms->secure && firmware_loaded); + if (vms->secure && firmware_loaded) { + vms->psci_conduit = QEMU_PSCI_CONDUIT_DISABLED; + } else if (vms->virt) { + vms->psci_conduit = QEMU_PSCI_CONDUIT_SMC; + } else { + vms->psci_conduit = QEMU_PSCI_CONDUIT_HVC; + } /* The maximum number of CPUs depends on the GIC version, or on how * many redistributors we can fit into the memory map. */ - if (gic_version == 3) { - virt_max_cpus = vbi->memmap[VIRT_GIC_REDIST].size / 0x20000; + if (vms->gic_version == 3) { + virt_max_cpus = vms->memmap[VIRT_GIC_REDIST].size / 0x20000; clustersz = GICV3_TARGETLIST_BITS; } else { virt_max_cpus = GIC_NCPU; @@ -1282,13 +1275,19 @@ static void machvirt_init(MachineState *machine) exit(1); } - vbi->smp_cpus = smp_cpus; + vms->smp_cpus = smp_cpus; - if (machine->ram_size > vbi->memmap[VIRT_MEM].size) { + if (machine->ram_size > vms->memmap[VIRT_MEM].size) { error_report("mach-virt: cannot model more than %dGB RAM", RAMLIMIT_GB); exit(1); } + if (vms->virt && kvm_enabled()) { + error_report("mach-virt: KVM does not support providing " + "Virtualization extensions to the guest CPU"); + exit(1); + } + if (vms->secure) { if (kvm_enabled()) { error_report("mach-virt: KVM does not support Security extensions"); @@ -1306,7 +1305,7 @@ static void machvirt_init(MachineState *machine) memory_region_add_subregion_overlap(secure_sysmem, 0, sysmem, -1); } - create_fdt(vbi); + create_fdt(vms); oc = cpu_class_by_name(TYPE_ARM_CPU, cpustr[0]); if (!oc) { @@ -1345,8 +1344,12 @@ static void machvirt_init(MachineState *machine) object_property_set_bool(cpuobj, false, "has_el3", NULL); } - if (vbi->using_psci) { - object_property_set_int(cpuobj, QEMU_PSCI_CONDUIT_HVC, + if (!vms->virt && object_property_find(cpuobj, "has_el2", NULL)) { + object_property_set_bool(cpuobj, false, "has_el2", NULL); + } + + if (vms->psci_conduit != QEMU_PSCI_CONDUIT_DISABLED) { + object_property_set_int(cpuobj, vms->psci_conduit, "psci-conduit", NULL); /* Secondary CPUs start in PSCI powered-down state */ @@ -1361,7 +1364,7 @@ static void machvirt_init(MachineState *machine) } if (object_property_find(cpuobj, "reset-cbar", NULL)) { - object_property_set_int(cpuobj, vbi->memmap[VIRT_CPUPERIPHS].base, + object_property_set_int(cpuobj, vms->memmap[VIRT_CPUPERIPHS].base, "reset-cbar", &error_abort); } @@ -1374,62 +1377,55 @@ static void machvirt_init(MachineState *machine) object_property_set_bool(cpuobj, true, "realized", NULL); } - fdt_add_timer_nodes(vbi, gic_version); - fdt_add_cpu_nodes(vbi); - fdt_add_psci_node(vbi); + fdt_add_timer_nodes(vms); + fdt_add_cpu_nodes(vms); + fdt_add_psci_node(vms); memory_region_allocate_system_memory(ram, NULL, "mach-virt.ram", machine->ram_size); - memory_region_add_subregion(sysmem, vbi->memmap[VIRT_MEM].base, ram); + memory_region_add_subregion(sysmem, vms->memmap[VIRT_MEM].base, ram); - create_flash(vbi, sysmem, secure_sysmem ? secure_sysmem : sysmem); + create_flash(vms, sysmem, secure_sysmem ? secure_sysmem : sysmem); - create_gic(vbi, pic, gic_version, vms->secure, vmc->no_its); + create_gic(vms, pic); - fdt_add_pmu_nodes(vbi, gic_version); + fdt_add_pmu_nodes(vms); - create_uart(vbi, pic, VIRT_UART, sysmem, serial_hds[0]); + create_uart(vms, pic, VIRT_UART, sysmem, serial_hds[0]); if (vms->secure) { - create_secure_ram(vbi, secure_sysmem); - create_uart(vbi, pic, VIRT_SECURE_UART, secure_sysmem, serial_hds[1]); + create_secure_ram(vms, secure_sysmem); + create_uart(vms, pic, VIRT_SECURE_UART, secure_sysmem, serial_hds[1]); } - create_rtc(vbi, pic); + create_rtc(vms, pic); - create_pcie(vbi, pic, vms->highmem); + create_pcie(vms, pic); - create_gpio(vbi, pic); + create_gpio(vms, pic); /* Create mmio transports, so the user can create virtio backends * (which will be automatically plugged in to the transports). If * no backend is created the transport will just sit harmlessly idle. */ - create_virtio_devices(vbi, pic); - - create_fw_cfg(vbi, &address_space_memory); - rom_set_fw(fw_cfg_find()); - - guest_info->smp_cpus = smp_cpus; - guest_info->fw_cfg = fw_cfg_find(); - guest_info->memmap = vbi->memmap; - guest_info->irqmap = vbi->irqmap; - guest_info->use_highmem = vms->highmem; - guest_info->gic_version = gic_version; - guest_info->no_its = vmc->no_its; - guest_info_state->machine_done.notify = virt_guest_info_machine_done; - qemu_add_machine_init_done_notifier(&guest_info_state->machine_done); - - vbi->bootinfo.ram_size = machine->ram_size; - vbi->bootinfo.kernel_filename = machine->kernel_filename; - vbi->bootinfo.kernel_cmdline = machine->kernel_cmdline; - vbi->bootinfo.initrd_filename = machine->initrd_filename; - vbi->bootinfo.nb_cpus = smp_cpus; - vbi->bootinfo.board_id = -1; - vbi->bootinfo.loader_start = vbi->memmap[VIRT_MEM].base; - vbi->bootinfo.get_dtb = machvirt_dtb; - vbi->bootinfo.firmware_loaded = firmware_loaded; - arm_load_kernel(ARM_CPU(first_cpu), &vbi->bootinfo); + create_virtio_devices(vms, pic); + + vms->fw_cfg = create_fw_cfg(vms, &address_space_memory); + rom_set_fw(vms->fw_cfg); + + vms->machine_done.notify = virt_machine_done; + qemu_add_machine_init_done_notifier(&vms->machine_done); + + vms->bootinfo.ram_size = machine->ram_size; + vms->bootinfo.kernel_filename = machine->kernel_filename; + vms->bootinfo.kernel_cmdline = machine->kernel_cmdline; + vms->bootinfo.initrd_filename = machine->initrd_filename; + vms->bootinfo.nb_cpus = smp_cpus; + vms->bootinfo.board_id = -1; + vms->bootinfo.loader_start = vms->memmap[VIRT_MEM].base; + vms->bootinfo.get_dtb = machvirt_dtb; + vms->bootinfo.firmware_loaded = firmware_loaded; + arm_load_kernel(ARM_CPU(first_cpu), &vms->bootinfo); /* * arm_load_kernel machine init done notifier registration must @@ -1437,7 +1433,7 @@ static void machvirt_init(MachineState *machine) * another notifier is registered which adds platform bus nodes. * Notifiers are executed in registration reverse order. */ - create_platform_bus(vbi, pic); + create_platform_bus(vms, pic); } static bool virt_get_secure(Object *obj, Error **errp) @@ -1454,6 +1450,20 @@ static void virt_set_secure(Object *obj, bool value, Error **errp) vms->secure = value; } +static bool virt_get_virt(Object *obj, Error **errp) +{ + VirtMachineState *vms = VIRT_MACHINE(obj); + + return vms->virt; +} + +static void virt_set_virt(Object *obj, bool value, Error **errp) +{ + VirtMachineState *vms = VIRT_MACHINE(obj); + + vms->virt = value; +} + static bool virt_get_highmem(Object *obj, Error **errp) { VirtMachineState *vms = VIRT_MACHINE(obj); @@ -1525,7 +1535,7 @@ static void machvirt_machine_init(void) } type_init(machvirt_machine_init); -static void virt_2_8_instance_init(Object *obj) +static void virt_2_9_instance_init(Object *obj) { VirtMachineState *vms = VIRT_MACHINE(obj); @@ -1541,6 +1551,16 @@ static void virt_2_8_instance_init(Object *obj) "Security Extensions (TrustZone)", NULL); + /* EL2 is also disabled by default, for similar reasons */ + vms->virt = false; + object_property_add_bool(obj, "virtualization", virt_get_virt, + virt_set_virt, NULL); + object_property_set_description(obj, "virtualization", + "Set on/off to enable/disable emulating a " + "guest CPU which implements the ARM " + "Virtualization Extensions", + NULL); + /* High memory is enabled by default */ vms->highmem = true; object_property_add_bool(obj, "highmem", virt_get_highmem, @@ -1556,12 +1576,36 @@ static void virt_2_8_instance_init(Object *obj) object_property_set_description(obj, "gic-version", "Set GIC version. " "Valid values are 2, 3 and host", NULL); + + vms->memmap = a15memmap; + vms->irqmap = a15irqmap; +} + +static void virt_machine_2_9_options(MachineClass *mc) +{ +} +DEFINE_VIRT_MACHINE_AS_LATEST(2, 9) + +#define VIRT_COMPAT_2_8 \ + HW_COMPAT_2_8 + +static void virt_2_8_instance_init(Object *obj) +{ + virt_2_9_instance_init(obj); } static void virt_machine_2_8_options(MachineClass *mc) { + VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc)); + + virt_machine_2_9_options(mc); + SET_MACHINE_COMPAT(mc, VIRT_COMPAT_2_8); + /* For 2.8 and earlier we falsely claimed in the DT that + * our timers were edge-triggered, not level-triggered. + */ + vmc->claim_edge_triggered_timers = true; } -DEFINE_VIRT_MACHINE_AS_LATEST(2, 8) +DEFINE_VIRT_MACHINE(2, 8) #define VIRT_COMPAT_2_7 \ HW_COMPAT_2_7 diff --git a/hw/arm/xlnx-zynqmp.c b/hw/arm/xlnx-zynqmp.c index 0d86ba35ae..bc4e66b862 100644 --- a/hw/arm/xlnx-zynqmp.c +++ b/hw/arm/xlnx-zynqmp.c @@ -258,6 +258,8 @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp) object_property_set_bool(OBJECT(&s->apu_cpu[i]), s->secure, "has_el3", NULL); + object_property_set_bool(OBJECT(&s->apu_cpu[i]), + false, "has_el2", NULL); object_property_set_int(OBJECT(&s->apu_cpu[i]), GIC_BASE_ADDR, "reset-cbar", &error_abort); object_property_set_bool(OBJECT(&s->apu_cpu[i]), true, "realized", diff --git a/hw/arm/z2.c b/hw/arm/z2.c index 68a92f3184..1607cbdb03 100644 --- a/hw/arm/z2.c +++ b/hw/arm/z2.c @@ -220,7 +220,7 @@ static int aer915_send(I2CSlave *i2c, uint8_t data) return 0; } -static void aer915_event(I2CSlave *i2c, enum i2c_event event) +static int aer915_event(I2CSlave *i2c, enum i2c_event event) { AER915State *s = AER915(i2c); @@ -238,6 +238,8 @@ static void aer915_event(I2CSlave *i2c, enum i2c_event event) default: break; } + + return 0; } static int aer915_recv(I2CSlave *slave) @@ -263,12 +265,6 @@ static int aer915_recv(I2CSlave *slave) return retval; } -static int aer915_init(I2CSlave *i2c) -{ - /* Nothing to do. */ - return 0; -} - static VMStateDescription vmstate_aer915_state = { .name = "aer915", .version_id = 1, @@ -285,7 +281,6 @@ static void aer915_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); I2CSlaveClass *k = I2C_SLAVE_CLASS(klass); - k->init = aer915_init; k->event = aer915_event; k->recv = aer915_recv; k->send = aer915_send; diff --git a/hw/audio/ac97.c b/hw/audio/ac97.c index cbd959e0bd..c30657501c 100644 --- a/hw/audio/ac97.c +++ b/hw/audio/ac97.c @@ -1387,6 +1387,16 @@ static void ac97_realize(PCIDevice *dev, Error **errp) ac97_on_reset (&s->dev.qdev); } +static void ac97_exit(PCIDevice *dev) +{ + AC97LinkState *s = DO_UPCAST(AC97LinkState, dev, dev); + + AUD_close_in(&s->card, s->voice_pi); + AUD_close_out(&s->card, s->voice_po); + AUD_close_in(&s->card, s->voice_mc); + AUD_remove_card(&s->card); +} + static int ac97_init (PCIBus *bus) { pci_create_simple (bus, -1, "AC97"); @@ -1404,6 +1414,7 @@ static void ac97_class_init (ObjectClass *klass, void *data) PCIDeviceClass *k = PCI_DEVICE_CLASS (klass); k->realize = ac97_realize; + k->exit = ac97_exit; k->vendor_id = PCI_VENDOR_ID_INTEL; k->device_id = PCI_DEVICE_ID_INTEL_82801AA_5; k->revision = 0x01; diff --git a/hw/audio/es1370.c b/hw/audio/es1370.c index 8449b5f436..fe64c1ac37 100644 --- a/hw/audio/es1370.c +++ b/hw/audio/es1370.c @@ -1010,9 +1010,9 @@ static const VMStateDescription vmstate_es1370 = { } }; -static void es1370_on_reset (void *opaque) +static void es1370_on_reset(DeviceState *dev) { - ES1370State *s = opaque; + ES1370State *s = container_of(dev, ES1370State, dev.qdev); es1370_reset (s); } @@ -1035,12 +1035,24 @@ static void es1370_realize(PCIDevice *dev, Error **errp) memory_region_init_io (&s->io, OBJECT(s), &es1370_io_ops, s, "es1370", 256); pci_register_bar (&s->dev, 0, PCI_BASE_ADDRESS_SPACE_IO, &s->io); - qemu_register_reset (es1370_on_reset, s); AUD_register_card ("es1370", &s->card); es1370_reset (s); } +static void es1370_exit(PCIDevice *dev) +{ + ES1370State *s = ES1370(dev); + int i; + + for (i = 0; i < 2; ++i) { + AUD_close_out(&s->card, s->dac_voice[i]); + } + + AUD_close_in(&s->card, s->adc_voice); + AUD_remove_card(&s->card); +} + static int es1370_init (PCIBus *bus) { pci_create_simple (bus, -1, TYPE_ES1370); @@ -1053,6 +1065,7 @@ static void es1370_class_init (ObjectClass *klass, void *data) PCIDeviceClass *k = PCI_DEVICE_CLASS (klass); k->realize = es1370_realize; + k->exit = es1370_exit; k->vendor_id = PCI_VENDOR_ID_ENSONIQ; k->device_id = PCI_DEVICE_ID_ENSONIQ_ES1370; k->class_id = PCI_CLASS_MULTIMEDIA_AUDIO; @@ -1061,6 +1074,7 @@ static void es1370_class_init (ObjectClass *klass, void *data) set_bit(DEVICE_CATEGORY_SOUND, dc->categories); dc->desc = "ENSONIQ AudioPCI ES1370"; dc->vmsd = &vmstate_es1370; + dc->reset = es1370_on_reset; } static const TypeInfo es1370_info = { diff --git a/hw/audio/marvell_88w8618.c b/hw/audio/marvell_88w8618.c index a6ca1806be..511b004287 100644 --- a/hw/audio/marvell_88w8618.c +++ b/hw/audio/marvell_88w8618.c @@ -241,19 +241,23 @@ static const MemoryRegionOps mv88w8618_audio_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -static int mv88w8618_audio_init(SysBusDevice *dev) +static void mv88w8618_audio_init(Object *obj) { + SysBusDevice *dev = SYS_BUS_DEVICE(obj); mv88w8618_audio_state *s = MV88W8618_AUDIO(dev); sysbus_init_irq(dev, &s->irq); - wm8750_data_req_set(s->wm, mv88w8618_audio_callback, s); - - memory_region_init_io(&s->iomem, OBJECT(s), &mv88w8618_audio_ops, s, + memory_region_init_io(&s->iomem, obj, &mv88w8618_audio_ops, s, "audio", MP_AUDIO_SIZE); sysbus_init_mmio(dev, &s->iomem); +} - return 0; +static void mv88w8618_audio_realize(DeviceState *dev, Error **errp) +{ + mv88w8618_audio_state *s = MV88W8618_AUDIO(dev); + + wm8750_data_req_set(s->wm, mv88w8618_audio_callback, s); } static const VMStateDescription mv88w8618_audio_vmsd = { @@ -282,9 +286,8 @@ static Property mv88w8618_audio_properties[] = { static void mv88w8618_audio_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); - SysBusDeviceClass *k = SYS_BUS_DEVICE_CLASS(klass); - k->init = mv88w8618_audio_init; + dc->realize = mv88w8618_audio_realize; dc->reset = mv88w8618_audio_reset; dc->vmsd = &mv88w8618_audio_vmsd; dc->props = mv88w8618_audio_properties; @@ -296,6 +299,7 @@ static const TypeInfo mv88w8618_audio_info = { .name = TYPE_MV88W8618_AUDIO, .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(mv88w8618_audio_state), + .instance_init = mv88w8618_audio_init, .class_init = mv88w8618_audio_class_init, }; diff --git a/hw/audio/pl041.c b/hw/audio/pl041.c index 6e9c104011..c8cc503236 100644 --- a/hw/audio/pl041.c +++ b/hw/audio/pl041.c @@ -521,12 +521,23 @@ static const MemoryRegionOps pl041_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -static int pl041_init(SysBusDevice *dev) +static void pl041_init(Object *obj) { + SysBusDevice *dev = SYS_BUS_DEVICE(obj); PL041State *s = PL041(dev); DBG_L1("pl041_init 0x%08x\n", (uint32_t)s); + /* Connect the device to the sysbus */ + memory_region_init_io(&s->iomem, obj, &pl041_ops, s, "pl041", 0x1000); + sysbus_init_mmio(dev, &s->iomem); + sysbus_init_irq(dev, &s->irq); +} + +static void pl041_realize(DeviceState *dev, Error **errp) +{ + PL041State *s = PL041(dev); + /* Check the device properties */ switch (s->fifo_depth) { case 8: @@ -545,18 +556,10 @@ static int pl041_init(SysBusDevice *dev) qemu_log_mask(LOG_UNIMP, "pl041: unsupported non-compact fifo depth [%i]\n", s->fifo_depth); - return -1; } - /* Connect the device to the sysbus */ - memory_region_init_io(&s->iomem, OBJECT(s), &pl041_ops, s, "pl041", 0x1000); - sysbus_init_mmio(dev, &s->iomem); - sysbus_init_irq(dev, &s->irq); - /* Init the codec */ lm4549_init(&s->codec, &pl041_request_data, (void *)s); - - return 0; } static const VMStateDescription vmstate_pl041_regfile = { @@ -627,9 +630,8 @@ static Property pl041_device_properties[] = { static void pl041_device_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); - SysBusDeviceClass *k = SYS_BUS_DEVICE_CLASS(klass); - k->init = pl041_init; + dc->realize = pl041_realize; set_bit(DEVICE_CATEGORY_SOUND, dc->categories); dc->reset = pl041_device_reset; dc->vmsd = &vmstate_pl041; @@ -640,6 +642,7 @@ static const TypeInfo pl041_device_info = { .name = TYPE_PL041, .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(PL041State), + .instance_init = pl041_init, .class_init = pl041_device_class_init, }; diff --git a/hw/audio/wm8750.c b/hw/audio/wm8750.c index 0c6500e96a..f8b5bebfc2 100644 --- a/hw/audio/wm8750.c +++ b/hw/audio/wm8750.c @@ -303,7 +303,7 @@ static void wm8750_reset(I2CSlave *i2c) s->i2c_len = 0; } -static void wm8750_event(I2CSlave *i2c, enum i2c_event event) +static int wm8750_event(I2CSlave *i2c, enum i2c_event event) { WM8750State *s = WM8750(i2c); @@ -321,6 +321,8 @@ static void wm8750_event(I2CSlave *i2c, enum i2c_event event) default: break; } + + return 0; } #define WM8750_LINVOL 0x00 diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c index d29ff4cb4f..2d6eb46a04 100644 --- a/hw/block/m25p80.c +++ b/hw/block/m25p80.c @@ -28,6 +28,7 @@ #include "hw/ssi/ssi.h" #include "qemu/bitops.h" #include "qemu/log.h" +#include "qemu/error-report.h" #include "qapi/error.h" #ifndef M25P80_ERR_DEBUG @@ -73,6 +74,12 @@ typedef struct FlashPartInfo { uint32_t n_sectors; uint32_t page_size; uint16_t flags; + /* + * Big sized spi nor are often stacked devices, thus sometime + * replace chip erase with die erase. + * This field inform how many die is in the chip. + */ + uint8_t die_cnt; } FlashPartInfo; /* adapted from linux */ @@ -90,7 +97,8 @@ typedef struct FlashPartInfo { .sector_size = (_sector_size),\ .n_sectors = (_n_sectors),\ .page_size = 256,\ - .flags = (_flags), + .flags = (_flags),\ + .die_cnt = 0 #define INFO6(_part_name, _jedec_id, _ext_id, _sector_size, _n_sectors, _flags)\ .part_name = _part_name,\ @@ -107,6 +115,24 @@ typedef struct FlashPartInfo { .n_sectors = (_n_sectors),\ .page_size = 256,\ .flags = (_flags),\ + .die_cnt = 0 + +#define INFO_STACKED(_part_name, _jedec_id, _ext_id, _sector_size, _n_sectors,\ + _flags, _die_cnt)\ + .part_name = _part_name,\ + .id = {\ + ((_jedec_id) >> 16) & 0xff,\ + ((_jedec_id) >> 8) & 0xff,\ + (_jedec_id) & 0xff,\ + ((_ext_id) >> 8) & 0xff,\ + (_ext_id) & 0xff,\ + },\ + .id_len = (!(_jedec_id) ? 0 : (3 + ((_ext_id) ? 2 : 0))),\ + .sector_size = (_sector_size),\ + .n_sectors = (_n_sectors),\ + .page_size = 256,\ + .flags = (_flags),\ + .die_cnt = _die_cnt #define JEDEC_NUMONYX 0x20 #define JEDEC_WINBOND 0xEF @@ -121,7 +147,7 @@ typedef struct FlashPartInfo { #define CFG_DUMMY_CLK_LEN 4 #define NVCFG_DUMMY_CLK_POS 12 #define VCFG_DUMMY_CLK_POS 4 -#define EVCFG_OUT_DRIVER_STRENGHT_DEF 7 +#define EVCFG_OUT_DRIVER_STRENGTH_DEF 7 #define EVCFG_VPP_ACCELERATOR (1 << 3) #define EVCFG_RESET_HOLD_ENABLED (1 << 4) #define NVCFG_DUAL_IO_MASK (1 << 2) @@ -203,6 +229,7 @@ static const FlashPartInfo known_devices[] = { { INFO("mx25l25655e", 0xc22619, 0, 64 << 10, 512, 0) }, { INFO("mx66u51235f", 0xc2253a, 0, 64 << 10, 1024, ER_4K | ER_32K) }, { INFO("mx66u1g45g", 0xc2253b, 0, 64 << 10, 2048, ER_4K | ER_32K) }, + { INFO("mx66l1g45g", 0xc2201b, 0, 64 << 10, 2048, ER_4K | ER_32K) }, /* Micron */ { INFO("n25q032a11", 0x20bb16, 0, 64 << 10, 64, ER_4K) }, @@ -216,8 +243,10 @@ static const FlashPartInfo known_devices[] = { { INFO("n25q128", 0x20ba18, 0, 64 << 10, 256, 0) }, { INFO("n25q256a", 0x20ba19, 0, 64 << 10, 512, ER_4K) }, { INFO("n25q512a", 0x20ba20, 0, 64 << 10, 1024, ER_4K) }, - { INFO("mt25ql01g", 0x20ba21, 0, 64 << 10, 2048, ER_4K) }, - { INFO("mt25qu01g", 0x20bb21, 0, 64 << 10, 2048, ER_4K) }, + { INFO_STACKED("n25q00", 0x20ba21, 0x1000, 64 << 10, 2048, ER_4K, 4) }, + { INFO_STACKED("n25q00a", 0x20bb21, 0x1000, 64 << 10, 2048, ER_4K, 4) }, + { INFO_STACKED("mt25ql01g", 0x20ba21, 0x1040, 64 << 10, 2048, ER_4K, 2) }, + { INFO_STACKED("mt25qu01g", 0x20bb21, 0x1040, 64 << 10, 2048, ER_4K, 2) }, /* Spansion -- single (large) sector size only, at least * for the chips listed here (without boot sectors). @@ -325,6 +354,7 @@ typedef enum { PP4_4 = 0x3e, DPP = 0xa2, QPP = 0x32, + QPP_4 = 0x34, ERASE_4K = 0x20, ERASE4_4K = 0x21, @@ -357,6 +387,8 @@ typedef enum { REVCR = 0x65, WEVCR = 0x61, + + DIE_ERASE = 0xC4, } FlashCMD; typedef enum { @@ -376,6 +408,8 @@ typedef enum { MAN_GENERIC, } Manufacturer; +#define M25P80_INTERNAL_DATA_BUFFER_SZ 16 + typedef struct Flash { SSISlave parent_obj; @@ -386,7 +420,7 @@ typedef struct Flash { int page_size; uint8_t state; - uint8_t data[16]; + uint8_t data[M25P80_INTERNAL_DATA_BUFFER_SZ]; uint32_t len; uint32_t pos; uint8_t needed_bytes; @@ -512,6 +546,16 @@ static void flash_erase(Flash *s, int offset, FlashCMD cmd) case BULK_ERASE: len = s->size; break; + case DIE_ERASE: + if (s->pi->die_cnt) { + len = s->size / s->pi->die_cnt; + offset = offset & (~(len - 1)); + } else { + qemu_log_mask(LOG_GUEST_ERROR, "M25P80: die erase is not supported" + " by device\n"); + return; + } + break; default: abort(); } @@ -573,6 +617,7 @@ static inline int get_addr_length(Flash *s) switch (s->cmd_in_progress) { case PP4: case PP4_4: + case QPP_4: case READ4: case QIOR4: case ERASE4_4K: @@ -606,6 +651,7 @@ static void complete_collecting_data(Flash *s) switch (s->cmd_in_progress) { case DPP: case QPP: + case QPP_4: case PP: case PP4: case PP4_4: @@ -631,6 +677,7 @@ static void complete_collecting_data(Flash *s) case ERASE4_32K: case ERASE_SECTOR: case ERASE4_SECTOR: + case DIE_ERASE: flash_erase(s, s->cur_addr, s->cmd_in_progress); break; case WRSR: @@ -700,7 +747,7 @@ static void reset_memory(Flash *s) ); s->enh_volatile_cfg = 0; - s->enh_volatile_cfg |= EVCFG_OUT_DRIVER_STRENGHT_DEF; + s->enh_volatile_cfg |= EVCFG_OUT_DRIVER_STRENGTH_DEF; s->enh_volatile_cfg |= EVCFG_VPP_ACCELERATOR; s->enh_volatile_cfg |= EVCFG_RESET_HOLD_ENABLED; if (s->nonvolatile_cfg & NVCFG_DUAL_IO_MASK) { @@ -873,9 +920,11 @@ static void decode_new_cmd(Flash *s, uint32_t value) case READ4: case DPP: case QPP: + case QPP_4: case PP: case PP4: case PP4_4: + case DIE_ERASE: s->needed_bytes = get_addr_length(s); s->pos = 0; s->len = 0; @@ -1114,6 +1163,17 @@ static uint32_t m25p80_transfer8(SSISlave *ss, uint32_t tx) case STATE_COLLECTING_DATA: case STATE_COLLECTING_VAR_LEN_DATA: + + if (s->len >= M25P80_INTERNAL_DATA_BUFFER_SZ) { + qemu_log_mask(LOG_GUEST_ERROR, + "M25P80: Write overrun internal data buffer. " + "SPI controller (QEMU emulator or guest driver) " + "is misbehaving\n"); + s->len = s->pos = 0; + s->state = STATE_IDLE; + break; + } + s->data[s->len] = (uint8_t)tx; s->len++; @@ -1123,6 +1183,17 @@ static uint32_t m25p80_transfer8(SSISlave *ss, uint32_t tx) break; case STATE_READING_DATA: + + if (s->pos >= M25P80_INTERNAL_DATA_BUFFER_SZ) { + qemu_log_mask(LOG_GUEST_ERROR, + "M25P80: Read overrun internal data buffer. " + "SPI controller (QEMU emulator or guest driver) " + "is misbehaving\n"); + s->len = s->pos = 0; + s->state = STATE_IDLE; + break; + } + r = s->data[s->pos]; s->pos++; if (s->pos == s->len) { @@ -1195,7 +1266,7 @@ static const VMStateDescription vmstate_m25p80 = { .pre_save = m25p80_pre_save, .fields = (VMStateField[]) { VMSTATE_UINT8(state, Flash), - VMSTATE_UINT8_ARRAY(data, Flash, 16), + VMSTATE_UINT8_ARRAY(data, Flash, M25P80_INTERNAL_DATA_BUFFER_SZ), VMSTATE_UINT32(len, Flash), VMSTATE_UINT32(pos, Flash), VMSTATE_UINT8(needed_bytes, Flash), diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index 0c5fd27593..702eda863e 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -588,13 +588,19 @@ void virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq) blk_io_plug(s->blk); - while ((req = virtio_blk_get_request(s, vq))) { - if (virtio_blk_handle_request(req, &mrb)) { - virtqueue_detach_element(req->vq, &req->elem, 0); - virtio_blk_free_request(req); - break; + do { + virtio_queue_set_notification(vq, 0); + + while ((req = virtio_blk_get_request(s, vq))) { + if (virtio_blk_handle_request(req, &mrb)) { + virtqueue_detach_element(req->vq, &req->elem, 0); + virtio_blk_free_request(req); + break; + } } - } + + virtio_queue_set_notification(vq, 1); + } while (!virtio_queue_empty(vq)); if (mrb.num_reqs) { virtio_blk_submit_multireq(s->blk, &mrb); @@ -857,7 +863,7 @@ static int virtio_blk_load_device(VirtIODevice *vdev, QEMUFile *f, } } - req = qemu_get_virtqueue_element(f, sizeof(VirtIOBlockReq)); + req = qemu_get_virtqueue_element(vdev, f, sizeof(VirtIOBlockReq)); virtio_blk_init_request(s, virtio_get_queue(vdev, vq_idx), req); req->next = s->rq; s->rq = req; diff --git a/hw/char/cadence_uart.c b/hw/char/cadence_uart.c index 0215d6518d..4dcee571c0 100644 --- a/hw/char/cadence_uart.c +++ b/hw/char/cadence_uart.c @@ -138,9 +138,10 @@ static void fifo_trigger_update(void *opaque) { CadenceUARTState *s = opaque; - s->r[R_CISR] |= UART_INTR_TIMEOUT; - - uart_update_status(s); + if (s->r[R_RTOR]) { + s->r[R_CISR] |= UART_INTR_TIMEOUT; + uart_update_status(s); + } } static void uart_rx_reset(CadenceUARTState *s) @@ -502,6 +503,13 @@ static int cadence_uart_post_load(void *opaque, int version_id) { CadenceUARTState *s = opaque; + /* Ensure these two aren't invalid numbers */ + if (s->r[R_BRGR] < 1 || s->r[R_BRGR] & ~0xFFFF || + s->r[R_BDIV] <= 3 || s->r[R_BDIV] & ~0xFF) { + /* Value is invalid, abort */ + return 1; + } + uart_parameters_setup(s); uart_update_status(s); return 0; diff --git a/hw/char/exynos4210_uart.c b/hw/char/exynos4210_uart.c index 571c324004..820d1abeb9 100644 --- a/hw/char/exynos4210_uart.c +++ b/hw/char/exynos4210_uart.c @@ -629,22 +629,26 @@ DeviceState *exynos4210_uart_create(hwaddr addr, return dev; } -static int exynos4210_uart_init(SysBusDevice *dev) +static void exynos4210_uart_init(Object *obj) { + SysBusDevice *dev = SYS_BUS_DEVICE(obj); Exynos4210UartState *s = EXYNOS4210_UART(dev); /* memory mapping */ - memory_region_init_io(&s->iomem, OBJECT(s), &exynos4210_uart_ops, s, + memory_region_init_io(&s->iomem, obj, &exynos4210_uart_ops, s, "exynos4210.uart", EXYNOS4210_UART_REGS_MEM_SIZE); sysbus_init_mmio(dev, &s->iomem); sysbus_init_irq(dev, &s->irq); +} + +static void exynos4210_uart_realize(DeviceState *dev, Error **errp) +{ + Exynos4210UartState *s = EXYNOS4210_UART(dev); qemu_chr_fe_set_handlers(&s->chr, exynos4210_uart_can_receive, exynos4210_uart_receive, exynos4210_uart_event, s, NULL, true); - - return 0; } static Property exynos4210_uart_properties[] = { @@ -658,9 +662,8 @@ static Property exynos4210_uart_properties[] = { static void exynos4210_uart_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); - SysBusDeviceClass *k = SYS_BUS_DEVICE_CLASS(klass); - k->init = exynos4210_uart_init; + dc->realize = exynos4210_uart_realize; dc->reset = exynos4210_uart_reset; dc->props = exynos4210_uart_properties; dc->vmsd = &vmstate_exynos4210_uart; @@ -670,6 +673,7 @@ static const TypeInfo exynos4210_uart_info = { .name = TYPE_EXYNOS4210_UART, .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(Exynos4210UartState), + .instance_init = exynos4210_uart_init, .class_init = exynos4210_uart_class_init, }; diff --git a/hw/char/serial.c b/hw/char/serial.c index ffbacd8227..67b18eda12 100644 --- a/hw/char/serial.c +++ b/hw/char/serial.c @@ -906,6 +906,16 @@ void serial_realize_core(SerialState *s, Error **errp) void serial_exit_core(SerialState *s) { qemu_chr_fe_deinit(&s->chr); + + timer_del(s->modem_status_poll); + timer_free(s->modem_status_poll); + + timer_del(s->fifo_timeout_timer); + timer_free(s->fifo_timeout_timer); + + fifo8_destroy(&s->recv_fifo); + fifo8_destroy(&s->xmit_fifo); + qemu_unregister_reset(serial_reset, s); } diff --git a/hw/char/virtio-serial-bus.c b/hw/char/virtio-serial-bus.c index 7975c2cda1..d544cd91c0 100644 --- a/hw/char/virtio-serial-bus.c +++ b/hw/char/virtio-serial-bus.c @@ -732,6 +732,7 @@ static void virtio_serial_post_load_timer_cb(void *opaque) static int fetch_active_ports_list(QEMUFile *f, VirtIOSerial *s, uint32_t nr_active_ports) { + VirtIODevice *vdev = VIRTIO_DEVICE(s); uint32_t i; s->post_load = g_malloc0(sizeof(*s->post_load)); @@ -765,7 +766,7 @@ static int fetch_active_ports_list(QEMUFile *f, qemu_get_be64s(f, &port->iov_offset); port->elem = - qemu_get_virtqueue_element(f, sizeof(VirtQueueElement)); + qemu_get_virtqueue_element(vdev, f, sizeof(VirtQueueElement)); /* * Port was throttled on source machine. Let's diff --git a/hw/core/Makefile.objs b/hw/core/Makefile.objs index a4c94e522d..7f8c9dc659 100644 --- a/hw/core/Makefile.objs +++ b/hw/core/Makefile.objs @@ -1,6 +1,6 @@ # core qdev-related obj files, also used by *-user: common-obj-y += qdev.o qdev-properties.o -common-obj-y += bus.o +common-obj-y += bus.o reset.o common-obj-y += fw-path-provider.o # irq.o needed for qdev GPIO handling: common-obj-y += irq.o @@ -12,7 +12,6 @@ common-obj-$(CONFIG_XILINX_AXI) += stream.o common-obj-$(CONFIG_PTIMER) += ptimer.o common-obj-$(CONFIG_SOFTMMU) += sysbus.o common-obj-$(CONFIG_SOFTMMU) += machine.o -common-obj-$(CONFIG_SOFTMMU) += null-machine.o common-obj-$(CONFIG_SOFTMMU) += loader.o common-obj-$(CONFIG_SOFTMMU) += qdev-properties-system.o common-obj-$(CONFIG_SOFTMMU) += register.o @@ -20,3 +19,4 @@ common-obj-$(CONFIG_SOFTMMU) += or-irq.o common-obj-$(CONFIG_PLATFORM_BUS) += platform-bus.o obj-$(CONFIG_SOFTMMU) += generic-loader.o +obj-$(CONFIG_SOFTMMU) += null-machine.o diff --git a/hw/core/generic-loader.c b/hw/core/generic-loader.c index 208f549dff..58f1f02902 100644 --- a/hw/core/generic-loader.c +++ b/hw/core/generic-loader.c @@ -27,7 +27,7 @@ * this it needs a backend to manage the datas, the same as other * memory-related devices. In this case as the backend is so trivial we * have merged it with the frontend instead of creating and maintaining a - * seperate backend. + * separate backend. */ #include "qemu/osdep.h" @@ -79,7 +79,7 @@ static void generic_loader_realize(DeviceState *dev, Error **errp) "loading memory values"); return; } else if (!s->data_len) { - /* We cant' check for !data here as a value of 0 is still valid. */ + /* We can't check for !data here as a value of 0 is still valid. */ error_setg(errp, "Both data and data-len must be specified"); return; } else if (s->data_len > 8) { diff --git a/hw/core/loader.c b/hw/core/loader.c index 45742494e6..ee5abd6eb7 100644 --- a/hw/core/loader.c +++ b/hw/core/loader.c @@ -853,7 +853,7 @@ static void fw_cfg_resized(const char *id, uint64_t length, void *host) } } -static void *rom_set_mr(Rom *rom, Object *owner, const char *name) +static void *rom_set_mr(Rom *rom, Object *owner, const char *name, bool ro) { void *data; @@ -862,7 +862,7 @@ static void *rom_set_mr(Rom *rom, Object *owner, const char *name) rom->datasize, rom->romsize, fw_cfg_resized, &error_fatal); - memory_region_set_readonly(rom->mr, true); + memory_region_set_readonly(rom->mr, ro); vmstate_register_ram_global(rom->mr); data = memory_region_get_ram_ptr(rom->mr); @@ -942,7 +942,7 @@ int rom_add_file(const char *file, const char *fw_dir, snprintf(devpath, sizeof(devpath), "/rom@%s", fw_file_name); if ((!option_rom || mc->option_rom_has_mr) && mc->rom_file_has_mr) { - data = rom_set_mr(rom, OBJECT(fw_cfg), devpath); + data = rom_set_mr(rom, OBJECT(fw_cfg), devpath, true); } else { data = rom->data; } @@ -979,7 +979,7 @@ err: MemoryRegion *rom_add_blob(const char *name, const void *blob, size_t len, size_t max_len, hwaddr addr, const char *fw_file_name, FWCfgReadCallback fw_callback, void *callback_opaque, - AddressSpace *as) + AddressSpace *as, bool read_only) { MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); Rom *rom; @@ -998,10 +998,14 @@ MemoryRegion *rom_add_blob(const char *name, const void *blob, size_t len, char devpath[100]; void *data; - snprintf(devpath, sizeof(devpath), "/rom@%s", fw_file_name); + if (read_only) { + snprintf(devpath, sizeof(devpath), "/rom@%s", fw_file_name); + } else { + snprintf(devpath, sizeof(devpath), "/ram@%s", fw_file_name); + } if (mc->rom_file_has_mr) { - data = rom_set_mr(rom, OBJECT(fw_cfg), devpath); + data = rom_set_mr(rom, OBJECT(fw_cfg), devpath, read_only); mr = rom->mr; } else { data = rom->data; @@ -1009,7 +1013,7 @@ MemoryRegion *rom_add_blob(const char *name, const void *blob, size_t len, fw_cfg_add_file_callback(fw_cfg, fw_file_name, fw_callback, callback_opaque, - data, rom->datasize); + data, rom->datasize, read_only); } return mr; } diff --git a/hw/core/null-machine.c b/hw/core/null-machine.c index 0351ba7828..27c8369b57 100644 --- a/hw/core/null-machine.c +++ b/hw/core/null-machine.c @@ -13,18 +13,41 @@ #include "qemu/osdep.h" #include "qemu-common.h" +#include "qemu/error-report.h" #include "hw/hw.h" #include "hw/boards.h" +#include "sysemu/sysemu.h" +#include "exec/address-spaces.h" +#include "cpu.h" -static void machine_none_init(MachineState *machine) +static void machine_none_init(MachineState *mch) { + CPUState *cpu = NULL; + + /* Initialize CPU (if a model has been specified) */ + if (mch->cpu_model) { + cpu = cpu_init(mch->cpu_model); + if (!cpu) { + error_report("Unable to initialize CPU"); + exit(1); + } + } + + /* RAM at address zero */ + if (mch->ram_size) { + MemoryRegion *ram = g_new(MemoryRegion, 1); + + memory_region_allocate_system_memory(ram, NULL, "ram", mch->ram_size); + memory_region_add_subregion(get_system_memory(), 0, ram); + } } static void machine_none_machine_init(MachineClass *mc) { mc->desc = "empty machine"; mc->init = machine_none_init; - mc->max_cpus = 0; + mc->max_cpus = 1; + mc->default_ram_size = 0; } DEFINE_MACHINE("none", machine_none_machine_init) diff --git a/hw/core/qdev-properties.c b/hw/core/qdev-properties.c index 2a82768067..6ab4265eb4 100644 --- a/hw/core/qdev-properties.c +++ b/hw/core/qdev-properties.c @@ -711,7 +711,7 @@ static void get_pci_host_devaddr(Object *obj, Visitor *v, const char *name, /* * Catch "invalid" device reference from vfio-pci and allow the - * default buffer representing the non-existant device to be used. + * default buffer representing the non-existent device to be used. */ if (~addr->domain || ~addr->bus || ~addr->slot || ~addr->function) { rc = snprintf(buffer, sizeof(buffer), "%04x:%02x:%02x.%0d", diff --git a/hw/core/reset.c b/hw/core/reset.c new file mode 100644 index 0000000000..84c8869371 --- /dev/null +++ b/hw/core/reset.c @@ -0,0 +1,72 @@ +/* + * Reset handlers. + * + * Copyright (c) 2003-2008 Fabrice Bellard + * Copyright (c) 2016 Red Hat, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qemu/queue.h" +#include "sysemu/reset.h" + +/* reset/shutdown handler */ + +typedef struct QEMUResetEntry { + QTAILQ_ENTRY(QEMUResetEntry) entry; + QEMUResetHandler *func; + void *opaque; +} QEMUResetEntry; + +static QTAILQ_HEAD(reset_handlers, QEMUResetEntry) reset_handlers = + QTAILQ_HEAD_INITIALIZER(reset_handlers); + +void qemu_register_reset(QEMUResetHandler *func, void *opaque) +{ + QEMUResetEntry *re = g_malloc0(sizeof(QEMUResetEntry)); + + re->func = func; + re->opaque = opaque; + QTAILQ_INSERT_TAIL(&reset_handlers, re, entry); +} + +void qemu_unregister_reset(QEMUResetHandler *func, void *opaque) +{ + QEMUResetEntry *re; + + QTAILQ_FOREACH(re, &reset_handlers, entry) { + if (re->func == func && re->opaque == opaque) { + QTAILQ_REMOVE(&reset_handlers, re, entry); + g_free(re); + return; + } + } +} + +void qemu_devices_reset(void) +{ + QEMUResetEntry *re, *nre; + + /* reset all devices */ + QTAILQ_FOREACH_SAFE(re, &reset_handlers, entry, nre) { + re->func(re->opaque); + } +} + diff --git a/hw/display/cirrus_vga.c b/hw/display/cirrus_vga.c index bdb092ee9d..379910db2d 100644 --- a/hw/display/cirrus_vga.c +++ b/hw/display/cirrus_vga.c @@ -294,7 +294,7 @@ static bool blit_region_is_unsafe(struct CirrusVGAState *s, return false; } -static bool blit_is_unsafe(struct CirrusVGAState *s) +static bool blit_is_unsafe(struct CirrusVGAState *s, bool dst_only) { /* should be the case, see cirrus_bitblt_start */ assert(s->cirrus_blt_width > 0); @@ -308,6 +308,9 @@ static bool blit_is_unsafe(struct CirrusVGAState *s) s->cirrus_blt_dstaddr & s->cirrus_addr_mask)) { return true; } + if (dst_only) { + return false; + } if (blit_region_is_unsafe(s, s->cirrus_blt_srcpitch, s->cirrus_blt_srcaddr & s->cirrus_addr_mask)) { return true; @@ -673,7 +676,7 @@ static int cirrus_bitblt_common_patterncopy(CirrusVGAState * s, dst = s->vga.vram_ptr + (s->cirrus_blt_dstaddr & s->cirrus_addr_mask); - if (blit_is_unsafe(s)) + if (blit_is_unsafe(s, false)) return 0; (*s->cirrus_rop) (s, dst, src, @@ -691,7 +694,7 @@ static int cirrus_bitblt_solidfill(CirrusVGAState *s, int blt_rop) { cirrus_fill_t rop_func; - if (blit_is_unsafe(s)) { + if (blit_is_unsafe(s, true)) { return 0; } rop_func = cirrus_fill[rop_to_index[blt_rop]][s->cirrus_blt_pixelwidth - 1]; @@ -795,7 +798,7 @@ static int cirrus_do_copy(CirrusVGAState *s, int dst, int src, int w, int h) static int cirrus_bitblt_videotovideo_copy(CirrusVGAState * s) { - if (blit_is_unsafe(s)) + if (blit_is_unsafe(s, false)) return 0; return cirrus_do_copy(s, s->cirrus_blt_dstaddr - s->vga.start_addr, diff --git a/hw/display/framebuffer.c b/hw/display/framebuffer.c index df51358e72..25aa46c8c7 100644 --- a/hw/display/framebuffer.c +++ b/hw/display/framebuffer.c @@ -78,7 +78,7 @@ void framebuffer_update_display( i = *first_row; *first_row = -1; - src_len = src_width * rows; + src_len = (hwaddr)src_width * rows; mem = mem_section->mr; if (!mem) { diff --git a/hw/display/milkymist-tmu2.c b/hw/display/milkymist-tmu2.c index 5c666f9b24..920374b985 100644 --- a/hw/display/milkymist-tmu2.c +++ b/hw/display/milkymist-tmu2.c @@ -257,7 +257,7 @@ static void tmu2_start(MilkymistTMU2State *s) glColor4f(m, m, m, (float)(s->regs[R_ALPHA] + 1) / 64.0f); /* Read the QEMU dest. framebuffer into the OpenGL framebuffer */ - fb_len = 2 * s->regs[R_DSTHRES] * s->regs[R_DSTVRES]; + fb_len = 2ULL * s->regs[R_DSTHRES] * s->regs[R_DSTVRES]; fb = cpu_physical_memory_map(s->regs[R_DSTFBUF], &fb_len, 0); if (fb == NULL) { glDeleteTextures(1, &texture); diff --git a/hw/display/ssd0303.c b/hw/display/ssd0303.c index d3017563f3..68a80b9d64 100644 --- a/hw/display/ssd0303.c +++ b/hw/display/ssd0303.c @@ -179,7 +179,7 @@ static int ssd0303_send(I2CSlave *i2c, uint8_t data) return 0; } -static void ssd0303_event(I2CSlave *i2c, enum i2c_event event) +static int ssd0303_event(I2CSlave *i2c, enum i2c_event event) { ssd0303_state *s = SSD0303(i2c); @@ -193,6 +193,8 @@ static void ssd0303_event(I2CSlave *i2c, enum i2c_event event) /* Nothing to do. */ break; } + + return 0; } static void ssd0303_update_display(void *opaque) diff --git a/hw/display/virtio-gpu-3d.c b/hw/display/virtio-gpu-3d.c index 23f39de94d..f96a0c2e59 100644 --- a/hw/display/virtio-gpu-3d.c +++ b/hw/display/virtio-gpu-3d.c @@ -291,8 +291,11 @@ static void virgl_resource_attach_backing(VirtIOGPU *g, return; } - virgl_renderer_resource_attach_iov(att_rb.resource_id, - res_iovs, att_rb.nr_entries); + ret = virgl_renderer_resource_attach_iov(att_rb.resource_id, + res_iovs, att_rb.nr_entries); + + if (ret != 0) + virtio_gpu_cleanup_mapping_iov(res_iovs, att_rb.nr_entries); } static void virgl_resource_detach_backing(VirtIOGPU *g, @@ -371,8 +374,12 @@ static void virgl_cmd_get_capset(VirtIOGPU *g, virgl_renderer_get_cap_set(gc.capset_id, &max_ver, &max_size); - resp = g_malloc(sizeof(*resp) + max_size); + if (!max_size) { + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; + return; + } + resp = g_malloc0(sizeof(*resp) + max_size); resp->hdr.type = VIRTIO_GPU_RESP_OK_CAPSET; virgl_renderer_fill_caps(gc.capset_id, gc.capset_version, diff --git a/hw/display/virtio-gpu.c b/hw/display/virtio-gpu.c index 5f32e1aae9..444ca064c1 100644 --- a/hw/display/virtio-gpu.c +++ b/hw/display/virtio-gpu.c @@ -28,6 +28,8 @@ static struct virtio_gpu_simple_resource* virtio_gpu_find_resource(VirtIOGPU *g, uint32_t resource_id); +static void virtio_gpu_cleanup_mapping(struct virtio_gpu_simple_resource *res); + #ifdef CONFIG_VIRGL #include <virglrenderer.h> #define VIRGL(_g, _virgl, _simple, ...) \ @@ -338,10 +340,14 @@ static void virtio_gpu_resource_create_2d(VirtIOGPU *g, cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; return; } - res->image = pixman_image_create_bits(pformat, - c2d.width, - c2d.height, - NULL, 0); + + res->hostmem = PIXMAN_FORMAT_BPP(pformat) * c2d.width * c2d.height; + if (res->hostmem + g->hostmem < g->conf.max_hostmem) { + res->image = pixman_image_create_bits(pformat, + c2d.width, + c2d.height, + NULL, 0); + } if (!res->image) { qemu_log_mask(LOG_GUEST_ERROR, @@ -353,13 +359,16 @@ static void virtio_gpu_resource_create_2d(VirtIOGPU *g, } QTAILQ_INSERT_HEAD(&g->reslist, res, next); + g->hostmem += res->hostmem; } static void virtio_gpu_resource_destroy(VirtIOGPU *g, struct virtio_gpu_simple_resource *res) { pixman_image_unref(res->image); + virtio_gpu_cleanup_mapping(res); QTAILQ_REMOVE(&g->reslist, res, next); + g->hostmem -= res->hostmem; g_free(res); } @@ -705,6 +714,11 @@ virtio_gpu_resource_attach_backing(VirtIOGPU *g, return; } + if (res->iov) { + cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; + return; + } + ret = virtio_gpu_create_mapping_iov(&ab, cmd, &res->addrs, &res->iov); if (ret != 0) { cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; @@ -989,7 +1003,8 @@ static const VMStateDescription vmstate_virtio_gpu_scanouts = { }, }; -static void virtio_gpu_save(QEMUFile *f, void *opaque, size_t size) +static int virtio_gpu_save(QEMUFile *f, void *opaque, size_t size, + VMStateField *field, QJSON *vmdesc) { VirtIOGPU *g = opaque; struct virtio_gpu_simple_resource *res; @@ -1014,9 +1029,12 @@ static void virtio_gpu_save(QEMUFile *f, void *opaque, size_t size) qemu_put_be32(f, 0); /* end of list */ vmstate_save_state(f, &vmstate_virtio_gpu_scanouts, g, NULL); + + return 0; } -static int virtio_gpu_load(QEMUFile *f, void *opaque, size_t size) +static int virtio_gpu_load(QEMUFile *f, void *opaque, size_t size, + VMStateField *field) { VirtIOGPU *g = opaque; struct virtio_gpu_simple_resource *res; @@ -1024,6 +1042,8 @@ static int virtio_gpu_load(QEMUFile *f, void *opaque, size_t size) uint32_t resource_id, pformat; int i; + g->hostmem = 0; + resource_id = qemu_get_be32(f); while (resource_id != 0) { res = g_new0(struct virtio_gpu_simple_resource, 1); @@ -1036,15 +1056,19 @@ static int virtio_gpu_load(QEMUFile *f, void *opaque, size_t size) /* allocate */ pformat = get_pixman_format(res->format); if (!pformat) { + g_free(res); return -EINVAL; } res->image = pixman_image_create_bits(pformat, res->width, res->height, NULL, 0); if (!res->image) { + g_free(res); return -EINVAL; } + res->hostmem = PIXMAN_FORMAT_BPP(pformat) * res->width * res->height; + res->addrs = g_new(uint64_t, res->iov_cnt); res->iov = g_new(struct iovec, res->iov_cnt); @@ -1062,11 +1086,22 @@ static int virtio_gpu_load(QEMUFile *f, void *opaque, size_t size) res->iov[i].iov_base = cpu_physical_memory_map(res->addrs[i], &len, 1); if (!res->iov[i].iov_base || len != res->iov[i].iov_len) { + /* Clean up the half-a-mapping we just created... */ + if (res->iov[i].iov_base) { + cpu_physical_memory_unmap(res->iov[i].iov_base, + len, 0, 0); + } + /* ...and the mappings for previous loop iterations */ + res->iov_cnt = i; + virtio_gpu_cleanup_mapping(res); + pixman_image_unref(res->image); + g_free(res); return -EINVAL; } } QTAILQ_INSERT_HEAD(&g->reslist, res, next); + g->hostmem += res->hostmem; resource_id = qemu_get_be32(f); } @@ -1101,6 +1136,7 @@ static void virtio_gpu_device_realize(DeviceState *qdev, Error **errp) VirtIODevice *vdev = VIRTIO_DEVICE(qdev); VirtIOGPU *g = VIRTIO_GPU(qdev); bool have_virgl; + Error *local_err = NULL; int i; if (g->conf.max_outputs > VIRTIO_GPU_MAX_SCANOUTS) { @@ -1108,14 +1144,6 @@ static void virtio_gpu_device_realize(DeviceState *qdev, Error **errp) return; } - g->config_size = sizeof(struct virtio_gpu_config); - g->virtio_config.num_scanouts = g->conf.max_outputs; - virtio_init(VIRTIO_DEVICE(g), "virtio-gpu", VIRTIO_ID_GPU, - g->config_size); - - g->req_state[0].width = 1024; - g->req_state[0].height = 768; - g->use_virgl_renderer = false; #if !defined(CONFIG_VIRGL) || defined(HOST_WORDS_BIGENDIAN) have_virgl = false; @@ -1127,6 +1155,24 @@ static void virtio_gpu_device_realize(DeviceState *qdev, Error **errp) } if (virtio_gpu_virgl_enabled(g->conf)) { + error_setg(&g->migration_blocker, "virgl is not yet migratable"); + migrate_add_blocker(g->migration_blocker, &local_err); + if (local_err) { + error_propagate(errp, local_err); + error_free(g->migration_blocker); + return; + } + } + + g->config_size = sizeof(struct virtio_gpu_config); + g->virtio_config.num_scanouts = g->conf.max_outputs; + virtio_init(VIRTIO_DEVICE(g), "virtio-gpu", VIRTIO_ID_GPU, + g->config_size); + + g->req_state[0].width = 1024; + g->req_state[0].height = 768; + + if (virtio_gpu_virgl_enabled(g->conf)) { /* use larger control queue in 3d mode */ g->ctrl_vq = virtio_add_queue(vdev, 256, virtio_gpu_handle_ctrl_cb); g->cursor_vq = virtio_add_queue(vdev, 16, virtio_gpu_handle_cursor_cb); @@ -1152,11 +1198,6 @@ static void virtio_gpu_device_realize(DeviceState *qdev, Error **errp) dpy_gfx_replace_surface(g->scanout[i].con, NULL); } } - - if (virtio_gpu_virgl_enabled(g->conf)) { - error_setg(&g->migration_blocker, "virgl is not yet migratable"); - migrate_add_blocker(g->migration_blocker); - } } static void virtio_gpu_device_unrealize(DeviceState *qdev, Error **errp) @@ -1241,6 +1282,8 @@ static const VMStateDescription vmstate_virtio_gpu = { static Property virtio_gpu_properties[] = { DEFINE_PROP_UINT32("max_outputs", VirtIOGPU, conf.max_outputs, 1), + DEFINE_PROP_SIZE("max_hostmem", VirtIOGPU, conf.max_hostmem, + 256 * 1024 * 1024), #ifdef CONFIG_VIRGL DEFINE_PROP_BIT("virgl", VirtIOGPU, conf.flags, VIRTIO_GPU_FLAG_VIRGL_ENABLED, true), @@ -1266,6 +1309,7 @@ static void virtio_gpu_class_init(ObjectClass *klass, void *data) dc->props = virtio_gpu_properties; dc->vmsd = &vmstate_virtio_gpu; + dc->hotpluggable = false; } static const TypeInfo virtio_gpu_info = { diff --git a/hw/display/xlnx_dp.c b/hw/display/xlnx_dp.c index f43eb09304..f7b7b80c68 100644 --- a/hw/display/xlnx_dp.c +++ b/hw/display/xlnx_dp.c @@ -555,7 +555,7 @@ static void xlnx_dp_recreate_surface(XlnxDPState *s) if ((width != 0) && (height != 0)) { /* * As dpy_gfx_replace_surface calls qemu_free_displaysurface on the - * surface we need to be carefull and don't free the surface associated + * surface we need to be careful and don't free the surface associated * to the console or double free will happen. */ if (s->bout_plane.surface != current_console_surface) { @@ -1160,7 +1160,7 @@ static void xlnx_dp_update_display(void *opaque) */ if (!xlnx_dpdma_start_operation(s->dpdma, 3, false)) { /* - * An error occured don't do anything with the data.. + * An error occurred don't do anything with the data.. * Trigger an underflow interrupt. */ s->core_registers[DP_INT_STATUS] |= (1 << 21); diff --git a/hw/gpio/max7310.c b/hw/gpio/max7310.c index 1bd5eaf911..f82e3e6555 100644 --- a/hw/gpio/max7310.c +++ b/hw/gpio/max7310.c @@ -129,7 +129,7 @@ static int max7310_tx(I2CSlave *i2c, uint8_t data) return 0; } -static void max7310_event(I2CSlave *i2c, enum i2c_event event) +static int max7310_event(I2CSlave *i2c, enum i2c_event event) { MAX7310State *s = MAX7310(i2c); s->len = 0; @@ -147,6 +147,8 @@ static void max7310_event(I2CSlave *i2c, enum i2c_event event) default: break; } + + return 0; } static const VMStateDescription vmstate_max7310 = { diff --git a/hw/i2c/core.c b/hw/i2c/core.c index abd4c4cddb..2c1234cdff 100644 --- a/hw/i2c/core.c +++ b/hw/i2c/core.c @@ -88,18 +88,26 @@ int i2c_bus_busy(I2CBus *bus) return !QLIST_EMPTY(&bus->current_devs); } +/* TODO: Make this handle multiple masters. */ /* - * Returns non-zero if the address is not valid. If this is called - * again without an intervening i2c_end_transfer(), like in the SMBus - * case where the operation is switched from write to read, this - * function will not rescan the bus and thus cannot fail. + * Start or continue an i2c transaction. When this is called for the + * first time or after an i2c_end_transfer(), if it returns an error + * the bus transaction is terminated (or really never started). If + * this is called after another i2c_start_transfer() without an + * intervening i2c_end_transfer(), and it returns an error, the + * transaction will not be terminated. The caller must do it. + * + * This corresponds with the way real hardware works. The SMBus + * protocol uses a start transfer to switch from write to read mode + * without releasing the bus. If that fails, the bus is still + * in a transaction. */ -/* TODO: Make this handle multiple masters. */ int i2c_start_transfer(I2CBus *bus, uint8_t address, int recv) { BusChild *kid; I2CSlaveClass *sc; I2CNode *node; + bool bus_scanned = false; if (address == I2C_BROADCAST) { /* @@ -130,6 +138,7 @@ int i2c_start_transfer(I2CBus *bus, uint8_t address, int recv) } } } + bus_scanned = true; } if (QLIST_EMPTY(&bus->current_devs)) { @@ -137,11 +146,21 @@ int i2c_start_transfer(I2CBus *bus, uint8_t address, int recv) } QLIST_FOREACH(node, &bus->current_devs, next) { + int rv; + sc = I2C_SLAVE_GET_CLASS(node->elt); /* If the bus is already busy, assume this is a repeated start condition. */ + if (sc->event) { - sc->event(node->elt, recv ? I2C_START_RECV : I2C_START_SEND); + rv = sc->event(node->elt, recv ? I2C_START_RECV : I2C_START_SEND); + if (rv && !bus->broadcast) { + if (bus_scanned) { + /* First call, terminate the transfer. */ + i2c_end_transfer(bus); + } + return rv; + } } } return 0; @@ -260,7 +279,11 @@ static int i2c_slave_qdev_init(DeviceState *dev) I2CSlave *s = I2C_SLAVE(dev); I2CSlaveClass *sc = I2C_SLAVE_GET_CLASS(s); - return sc->init(s); + if (sc->init) { + return sc->init(s); + } + + return 0; } DeviceState *i2c_create_slave(I2CBus *bus, const char *name, uint8_t addr) diff --git a/hw/i2c/i2c-ddc.c b/hw/i2c/i2c-ddc.c index 1227212934..66899d7233 100644 --- a/hw/i2c/i2c-ddc.c +++ b/hw/i2c/i2c-ddc.c @@ -230,13 +230,15 @@ static void i2c_ddc_reset(DeviceState *ds) s->reg = 0; } -static void i2c_ddc_event(I2CSlave *i2c, enum i2c_event event) +static int i2c_ddc_event(I2CSlave *i2c, enum i2c_event event) { I2CDDCState *s = I2CDDC(i2c); if (event == I2C_START_SEND) { s->firstbyte = true; } + + return 0; } static int i2c_ddc_rx(I2CSlave *i2c) diff --git a/hw/i2c/imx_i2c.c b/hw/i2c/imx_i2c.c index 37e5a62ce7..6c81b98ebd 100644 --- a/hw/i2c/imx_i2c.c +++ b/hw/i2c/imx_i2c.c @@ -310,7 +310,7 @@ static void imx_i2c_realize(DeviceState *dev, Error **errp) IMX_I2C_MEM_SIZE); sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq); - s->bus = i2c_init_bus(DEVICE(dev), "i2c"); + s->bus = i2c_init_bus(DEVICE(dev), NULL); } static void imx_i2c_class_init(ObjectClass *klass, void *data) diff --git a/hw/i2c/smbus.c b/hw/i2c/smbus.c index 5b4dd3eba4..2d1b79a689 100644 --- a/hw/i2c/smbus.c +++ b/hw/i2c/smbus.c @@ -67,7 +67,7 @@ static void smbus_do_write(SMBusDevice *dev) } } -static void smbus_i2c_event(I2CSlave *s, enum i2c_event event) +static int smbus_i2c_event(I2CSlave *s, enum i2c_event event) { SMBusDevice *dev = SMBUS_DEVICE(s); @@ -148,6 +148,8 @@ static void smbus_i2c_event(I2CSlave *s, enum i2c_event event) break; } } + + return 0; } static int smbus_i2c_recv(I2CSlave *s) @@ -249,7 +251,8 @@ int smbus_read_byte(I2CBus *bus, uint8_t addr, uint8_t command) } i2c_send(bus, command); if (i2c_start_transfer(bus, addr, 1)) { - assert(0); + i2c_end_transfer(bus); + return -1; } data = i2c_recv(bus); i2c_nack(bus); @@ -276,7 +279,8 @@ int smbus_read_word(I2CBus *bus, uint8_t addr, uint8_t command) } i2c_send(bus, command); if (i2c_start_transfer(bus, addr, 1)) { - assert(0); + i2c_end_transfer(bus); + return -1; } data = i2c_recv(bus); data |= i2c_recv(bus) << 8; @@ -307,7 +311,8 @@ int smbus_read_block(I2CBus *bus, uint8_t addr, uint8_t command, uint8_t *data) } i2c_send(bus, command); if (i2c_start_transfer(bus, addr, 1)) { - assert(0); + i2c_end_transfer(bus); + return -1; } len = i2c_recv(bus); if (len > 32) { diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 42ecf619d5..1c928abb28 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -101,8 +101,6 @@ typedef struct AcpiPmInfo { uint32_t gpe0_blk_len; uint32_t io_base; uint16_t cpu_hp_io_base; - uint16_t mem_hp_io_base; - uint16_t mem_hp_io_len; uint16_t pcihp_io_base; uint16_t pcihp_io_len; } AcpiPmInfo; @@ -148,9 +146,6 @@ static void acpi_get_pm_info(AcpiPmInfo *pm) } assert(obj); - pm->mem_hp_io_base = ACPI_MEMORY_HOTPLUG_BASE; - pm->mem_hp_io_len = ACPI_MEMORY_HOTPLUG_IO_LEN; - /* Fill in optional s3/s4 related properties */ o = object_property_get_qobject(obj, ACPI_PM_PROP_S3_DISABLED, NULL); if (o) { @@ -337,7 +332,7 @@ build_fadt(GArray *table_data, BIOSLinker *linker, AcpiPmInfo *pm, } void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid, - CPUArchIdList *apic_ids, GArray *entry) + const CPUArchIdList *apic_ids, GArray *entry) { uint32_t apic_id = apic_ids->cpus[uid].arch_id; @@ -378,7 +373,7 @@ static void build_madt(GArray *table_data, BIOSLinker *linker, PCMachineState *pcms) { MachineClass *mc = MACHINE_GET_CLASS(pcms); - CPUArchIdList *apic_ids = mc->possible_cpu_arch_ids(MACHINE(pcms)); + const CPUArchIdList *apic_ids = mc->possible_cpu_arch_ids(MACHINE(pcms)); int madt_start = table_data->len; AcpiDeviceIfClass *adevc = ACPI_DEVICE_IF_GET_CLASS(pcms->acpi_dev); AcpiDeviceIf *adev = ACPI_DEVICE_IF(pcms->acpi_dev); @@ -399,7 +394,6 @@ build_madt(GArray *table_data, BIOSLinker *linker, PCMachineState *pcms) x2apic_mode = true; } } - g_free(apic_ids); io_apic = acpi_data_push(table_data, sizeof *io_apic); io_apic->type = ACPI_APIC_IO; @@ -1038,130 +1032,6 @@ static Aml *build_crs(PCIHostState *host, CrsRangeSet *range_set) return crs; } -static void build_memory_devices(Aml *sb_scope, int nr_mem, - uint16_t io_base, uint16_t io_len) -{ - int i; - Aml *scope; - Aml *crs; - Aml *field; - Aml *dev; - Aml *method; - Aml *ifctx; - - /* build memory devices */ - assert(nr_mem <= ACPI_MAX_RAM_SLOTS); - scope = aml_scope("\\_SB.PCI0." MEMORY_HOTPLUG_DEVICE); - aml_append(scope, - aml_name_decl(MEMORY_SLOTS_NUMBER, aml_int(nr_mem)) - ); - - crs = aml_resource_template(); - aml_append(crs, - aml_io(AML_DECODE16, io_base, io_base, 0, io_len) - ); - aml_append(scope, aml_name_decl("_CRS", crs)); - - aml_append(scope, aml_operation_region( - MEMORY_HOTPLUG_IO_REGION, AML_SYSTEM_IO, - aml_int(io_base), io_len) - ); - - field = aml_field(MEMORY_HOTPLUG_IO_REGION, AML_DWORD_ACC, - AML_NOLOCK, AML_PRESERVE); - aml_append(field, /* read only */ - aml_named_field(MEMORY_SLOT_ADDR_LOW, 32)); - aml_append(field, /* read only */ - aml_named_field(MEMORY_SLOT_ADDR_HIGH, 32)); - aml_append(field, /* read only */ - aml_named_field(MEMORY_SLOT_SIZE_LOW, 32)); - aml_append(field, /* read only */ - aml_named_field(MEMORY_SLOT_SIZE_HIGH, 32)); - aml_append(field, /* read only */ - aml_named_field(MEMORY_SLOT_PROXIMITY, 32)); - aml_append(scope, field); - - field = aml_field(MEMORY_HOTPLUG_IO_REGION, AML_BYTE_ACC, - AML_NOLOCK, AML_WRITE_AS_ZEROS); - aml_append(field, aml_reserved_field(160 /* bits, Offset(20) */)); - aml_append(field, /* 1 if enabled, read only */ - aml_named_field(MEMORY_SLOT_ENABLED, 1)); - aml_append(field, - /*(read) 1 if has a insert event. (write) 1 to clear event */ - aml_named_field(MEMORY_SLOT_INSERT_EVENT, 1)); - aml_append(field, - /* (read) 1 if has a remove event. (write) 1 to clear event */ - aml_named_field(MEMORY_SLOT_REMOVE_EVENT, 1)); - aml_append(field, - /* initiates device eject, write only */ - aml_named_field(MEMORY_SLOT_EJECT, 1)); - aml_append(scope, field); - - field = aml_field(MEMORY_HOTPLUG_IO_REGION, AML_DWORD_ACC, - AML_NOLOCK, AML_PRESERVE); - aml_append(field, /* DIMM selector, write only */ - aml_named_field(MEMORY_SLOT_SLECTOR, 32)); - aml_append(field, /* _OST event code, write only */ - aml_named_field(MEMORY_SLOT_OST_EVENT, 32)); - aml_append(field, /* _OST status code, write only */ - aml_named_field(MEMORY_SLOT_OST_STATUS, 32)); - aml_append(scope, field); - aml_append(sb_scope, scope); - - for (i = 0; i < nr_mem; i++) { - #define BASEPATH "\\_SB.PCI0." MEMORY_HOTPLUG_DEVICE "." - const char *s; - - dev = aml_device("MP%02X", i); - aml_append(dev, aml_name_decl("_UID", aml_string("0x%02X", i))); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0C80"))); - - method = aml_method("_CRS", 0, AML_NOTSERIALIZED); - s = BASEPATH MEMORY_SLOT_CRS_METHOD; - aml_append(method, aml_return(aml_call1(s, aml_name("_UID")))); - aml_append(dev, method); - - method = aml_method("_STA", 0, AML_NOTSERIALIZED); - s = BASEPATH MEMORY_SLOT_STATUS_METHOD; - aml_append(method, aml_return(aml_call1(s, aml_name("_UID")))); - aml_append(dev, method); - - method = aml_method("_PXM", 0, AML_NOTSERIALIZED); - s = BASEPATH MEMORY_SLOT_PROXIMITY_METHOD; - aml_append(method, aml_return(aml_call1(s, aml_name("_UID")))); - aml_append(dev, method); - - method = aml_method("_OST", 3, AML_NOTSERIALIZED); - s = BASEPATH MEMORY_SLOT_OST_METHOD; - - aml_append(method, aml_return(aml_call4( - s, aml_name("_UID"), aml_arg(0), aml_arg(1), aml_arg(2) - ))); - aml_append(dev, method); - - method = aml_method("_EJ0", 1, AML_NOTSERIALIZED); - s = BASEPATH MEMORY_SLOT_EJECT_METHOD; - aml_append(method, aml_return(aml_call2( - s, aml_name("_UID"), aml_arg(0)))); - aml_append(dev, method); - - aml_append(sb_scope, dev); - } - - /* build Method(MEMORY_SLOT_NOTIFY_METHOD, 2) { - * If (LEqual(Arg0, 0x00)) {Notify(MP00, Arg1)} ... } - */ - method = aml_method(MEMORY_SLOT_NOTIFY_METHOD, 2, AML_NOTSERIALIZED); - for (i = 0; i < nr_mem; i++) { - ifctx = aml_if(aml_equal(aml_arg(0), aml_int(i))); - aml_append(ifctx, - aml_notify(aml_name("MP%.02X", i), aml_arg(1)) - ); - aml_append(method, ifctx); - } - aml_append(sb_scope, method); -} - static void build_hpet_aml(Aml *table) { Aml *crs; @@ -2049,8 +1919,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, build_cpus_aml(dsdt, machine, opts, pm->cpu_hp_io_base, "\\_SB.PCI0", "\\_GPE._E02"); } - build_memory_hotplug_aml(dsdt, nr_mem, pm->mem_hp_io_base, - pm->mem_hp_io_len); + build_memory_hotplug_aml(dsdt, nr_mem, "\\_SB.PCI0", "\\_GPE._E03"); scope = aml_scope("_GPE"); { @@ -2065,10 +1934,6 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, aml_append(scope, method); } - method = aml_method("_E03", 0, AML_NOTSERIALIZED); - aml_append(method, aml_call0(MEMORY_HOTPLUG_HANDLER_PATH)); - aml_append(scope, method); - if (pcms->acpi_nvdimm_state.is_enabled) { method = aml_method("_E04", 0, AML_NOTSERIALIZED); aml_append(method, aml_notify(aml_name("\\_SB.NVDR"), @@ -2321,45 +2186,40 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, sb_scope = aml_scope("\\_SB"); { - build_memory_devices(sb_scope, nr_mem, pm->mem_hp_io_base, - pm->mem_hp_io_len); + Object *pci_host; + PCIBus *bus = NULL; - { - Object *pci_host; - PCIBus *bus = NULL; + pci_host = acpi_get_i386_pci_host(); + if (pci_host) { + bus = PCI_HOST_BRIDGE(pci_host)->bus; + } - pci_host = acpi_get_i386_pci_host(); - if (pci_host) { - bus = PCI_HOST_BRIDGE(pci_host)->bus; + if (bus) { + Aml *scope = aml_scope("PCI0"); + /* Scan all PCI buses. Generate tables to support hotplug. */ + build_append_pci_bus_devices(scope, bus, pm->pcihp_bridge_en); + + if (misc->tpm_version != TPM_VERSION_UNSPEC) { + dev = aml_device("ISA.TPM"); + aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0C31"))); + aml_append(dev, aml_name_decl("_STA", aml_int(0xF))); + crs = aml_resource_template(); + aml_append(crs, aml_memory32_fixed(TPM_TIS_ADDR_BASE, + TPM_TIS_ADDR_SIZE, AML_READ_WRITE)); + /* + FIXME: TPM_TIS_IRQ=5 conflicts with PNP0C0F irqs, + Rewrite to take IRQ from TPM device model and + fix default IRQ value there to use some unused IRQ + */ + /* aml_append(crs, aml_irq_no_flags(TPM_TIS_IRQ)); */ + aml_append(dev, aml_name_decl("_CRS", crs)); + aml_append(scope, dev); } - if (bus) { - Aml *scope = aml_scope("PCI0"); - /* Scan all PCI buses. Generate tables to support hotplug. */ - build_append_pci_bus_devices(scope, bus, pm->pcihp_bridge_en); - - if (misc->tpm_version != TPM_VERSION_UNSPEC) { - dev = aml_device("ISA.TPM"); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0C31"))); - aml_append(dev, aml_name_decl("_STA", aml_int(0xF))); - crs = aml_resource_template(); - aml_append(crs, aml_memory32_fixed(TPM_TIS_ADDR_BASE, - TPM_TIS_ADDR_SIZE, AML_READ_WRITE)); - /* - FIXME: TPM_TIS_IRQ=5 conflicts with PNP0C0F irqs, - Rewrite to take IRQ from TPM device model and - fix default IRQ value there to use some unused IRQ - */ - /* aml_append(crs, aml_irq_no_flags(TPM_TIS_IRQ)); */ - aml_append(dev, aml_name_decl("_CRS", crs)); - aml_append(scope, dev); - } - - aml_append(sb_scope, scope); - } + aml_append(sb_scope, scope); } - aml_append(dsdt, sb_scope); } + aml_append(dsdt, sb_scope); /* copy AML table into ACPI tables blob and patch header there */ g_array_append_vals(table_data, dsdt->buf->data, dsdt->buf->len); @@ -2433,7 +2293,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) int srat_start, numa_start, slots; uint64_t mem_len, mem_base, next_base; MachineClass *mc = MACHINE_GET_CLASS(machine); - CPUArchIdList *apic_ids = mc->possible_cpu_arch_ids(machine); + const CPUArchIdList *apic_ids = mc->possible_cpu_arch_ids(machine); PCMachineState *pcms = PC_MACHINE(machine); ram_addr_t hotplugabble_address_space_size = object_property_get_int(OBJECT(pcms), PC_MACHINE_MEMHP_REGION_SIZE, @@ -2532,7 +2392,6 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) (void *)(table_data->data + srat_start), "SRAT", table_data->len - srat_start, 1, NULL, NULL); - g_free(apic_ids); } static void @@ -2575,6 +2434,7 @@ build_dmar_q35(GArray *table_data, BIOSLinker *linker) AcpiTableDmar *dmar; AcpiDmarHardwareUnit *drhd; + AcpiDmarRootPortATS *atsr; uint8_t dmar_flags = 0; X86IOMMUState *iommu = x86_iommu_get_default(); AcpiDmarDeviceScope *scope = NULL; @@ -2608,6 +2468,14 @@ build_dmar_q35(GArray *table_data, BIOSLinker *linker) scope->path[0].device = PCI_SLOT(Q35_PSEUDO_DEVFN_IOAPIC); scope->path[0].function = PCI_FUNC(Q35_PSEUDO_DEVFN_IOAPIC); + if (iommu->dt_supported) { + atsr = acpi_data_push(table_data, sizeof(*atsr)); + atsr->type = cpu_to_le16(ACPI_DMAR_TYPE_ATSR); + atsr->length = cpu_to_le16(sizeof(*atsr)); + atsr->flags = ACPI_DMAR_ATSR_ALL_PORTS; + atsr->pci_segment = cpu_to_le16(0); + } + build_header(linker, table_data, (void *)(table_data->data + dmar_start), "DMAR", table_data->len - dmar_start, 1, NULL, NULL); } @@ -2936,7 +2804,7 @@ static MemoryRegion *acpi_add_rom_blob(AcpiBuildState *build_state, uint64_t max_size) { return rom_add_blob(name, blob->data, acpi_data_len(blob), max_size, -1, - name, acpi_build_update, build_state, NULL); + name, acpi_build_update, build_state, NULL, true); } static const VMStateDescription vmstate_acpi_build = { @@ -3002,7 +2870,7 @@ void acpi_setup(void) build_state->rsdp = g_memdup(tables.rsdp->data, rsdp_size); fw_cfg_add_file_callback(pcms->fw_cfg, ACPI_BUILD_RSDP_FILE, acpi_build_update, build_state, - build_state->rsdp, rsdp_size); + build_state->rsdp, rsdp_size, true); build_state->rsdp_mr = NULL; } else { build_state->rsdp = NULL; diff --git a/hw/i386/amd_iommu.c b/hw/i386/amd_iommu.c index 47b79d9112..e0732ccaf1 100644 --- a/hw/i386/amd_iommu.c +++ b/hw/i386/amd_iommu.c @@ -562,7 +562,7 @@ static void amdvi_mmio_trace(hwaddr addr, unsigned size) trace_amdvi_mmio_read(amdvi_mmio_high[index], addr, size, addr & ~0x07); } else { index = index >= AMDVI_MMIO_REGS_LOW ? AMDVI_MMIO_REGS_LOW : index; - trace_amdvi_mmio_read(amdvi_mmio_high[index], addr, size, addr & ~0x07); + trace_amdvi_mmio_read(amdvi_mmio_low[index], addr, size, addr & ~0x07); } } diff --git a/hw/i386/amd_iommu.h b/hw/i386/amd_iommu.h index 884926e9e7..0d3dc6a9f2 100644 --- a/hw/i386/amd_iommu.h +++ b/hw/i386/amd_iommu.h @@ -49,8 +49,8 @@ #define AMDVI_CAPAB_INIT_TYPE (3 << 16) /* No. of used MMIO registers */ -#define AMDVI_MMIO_REGS_HIGH 8 -#define AMDVI_MMIO_REGS_LOW 7 +#define AMDVI_MMIO_REGS_HIGH 7 +#define AMDVI_MMIO_REGS_LOW 8 /* MMIO registers */ #define AMDVI_MMIO_DEVICE_TABLE 0x0000 diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index 5f3e35123d..ec62239aba 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -738,11 +738,18 @@ static int vtd_dev_to_context_entry(IntelIOMMUState *s, uint8_t bus_num, "context-entry hi 0x%"PRIx64 " lo 0x%"PRIx64, ce->hi, ce->lo); return -VTD_FR_CONTEXT_ENTRY_INV; - } else if (ce->lo & VTD_CONTEXT_ENTRY_TT) { - VTD_DPRINTF(GENERAL, "error: unsupported Translation Type in " - "context-entry hi 0x%"PRIx64 " lo 0x%"PRIx64, - ce->hi, ce->lo); - return -VTD_FR_CONTEXT_ENTRY_INV; + } else { + switch (ce->lo & VTD_CONTEXT_ENTRY_TT) { + case VTD_CONTEXT_TT_MULTI_LEVEL: + /* fall through */ + case VTD_CONTEXT_TT_DEV_IOTLB: + break; + default: + VTD_DPRINTF(GENERAL, "error: unsupported Translation Type in " + "context-entry hi 0x%"PRIx64 " lo 0x%"PRIx64, + ce->hi, ce->lo); + return -VTD_FR_CONTEXT_ENTRY_INV; + } } return 0; } @@ -1438,7 +1445,61 @@ static bool vtd_process_inv_iec_desc(IntelIOMMUState *s, vtd_iec_notify_all(s, !inv_desc->iec.granularity, inv_desc->iec.index, inv_desc->iec.index_mask); + return true; +} +static bool vtd_process_device_iotlb_desc(IntelIOMMUState *s, + VTDInvDesc *inv_desc) +{ + VTDAddressSpace *vtd_dev_as; + IOMMUTLBEntry entry; + struct VTDBus *vtd_bus; + hwaddr addr; + uint64_t sz; + uint16_t sid; + uint8_t devfn; + bool size; + uint8_t bus_num; + + addr = VTD_INV_DESC_DEVICE_IOTLB_ADDR(inv_desc->hi); + sid = VTD_INV_DESC_DEVICE_IOTLB_SID(inv_desc->lo); + devfn = sid & 0xff; + bus_num = sid >> 8; + size = VTD_INV_DESC_DEVICE_IOTLB_SIZE(inv_desc->hi); + + if ((inv_desc->lo & VTD_INV_DESC_DEVICE_IOTLB_RSVD_LO) || + (inv_desc->hi & VTD_INV_DESC_DEVICE_IOTLB_RSVD_HI)) { + VTD_DPRINTF(GENERAL, "error: non-zero reserved field in Device " + "IOTLB Invalidate Descriptor hi 0x%"PRIx64 " lo 0x%"PRIx64, + inv_desc->hi, inv_desc->lo); + return false; + } + + vtd_bus = vtd_find_as_from_bus_num(s, bus_num); + if (!vtd_bus) { + goto done; + } + + vtd_dev_as = vtd_bus->dev_as[devfn]; + if (!vtd_dev_as) { + goto done; + } + + if (size) { + sz = 1 << (ctz64(~(addr | (VTD_PAGE_MASK_4K - 1))) + 1); + addr &= ~(sz - 1); + } else { + sz = VTD_PAGE_SIZE; + } + + entry.target_as = &vtd_dev_as->as; + entry.addr_mask = sz - 1; + entry.iova = addr; + entry.perm = IOMMU_NONE; + entry.translated_addr = 0; + memory_region_notify_iommu(entry.target_as->root, entry); + +done: return true; } @@ -1490,6 +1551,14 @@ static bool vtd_process_inv_desc(IntelIOMMUState *s) } break; + case VTD_INV_DESC_DEVICE: + VTD_DPRINTF(INV, "Device IOTLB Invalidation Descriptor hi 0x%"PRIx64 + " lo 0x%"PRIx64, inv_desc.hi, inv_desc.lo); + if (!vtd_process_device_iotlb_desc(s, &inv_desc)) { + return false; + } + break; + default: VTD_DPRINTF(GENERAL, "error: unkonw Invalidation Descriptor type " "hi 0x%"PRIx64 " lo 0x%"PRIx64 " type %"PRIu8, @@ -1996,7 +2065,27 @@ static void vtd_iommu_notify_flag_changed(MemoryRegion *iommu, static const VMStateDescription vtd_vmstate = { .name = "iommu-intel", - .unmigratable = 1, + .version_id = 1, + .minimum_version_id = 1, + .priority = MIG_PRI_IOMMU, + .fields = (VMStateField[]) { + VMSTATE_UINT64(root, IntelIOMMUState), + VMSTATE_UINT64(intr_root, IntelIOMMUState), + VMSTATE_UINT64(iq, IntelIOMMUState), + VMSTATE_UINT32(intr_size, IntelIOMMUState), + VMSTATE_UINT16(iq_head, IntelIOMMUState), + VMSTATE_UINT16(iq_tail, IntelIOMMUState), + VMSTATE_UINT16(iq_size, IntelIOMMUState), + VMSTATE_UINT16(next_frcd_reg, IntelIOMMUState), + VMSTATE_UINT8_ARRAY(csr, IntelIOMMUState, DMAR_REG_SIZE), + VMSTATE_UINT8(iq_last_desc_type, IntelIOMMUState), + VMSTATE_BOOL(root_extended, IntelIOMMUState), + VMSTATE_BOOL(dmar_enabled, IntelIOMMUState), + VMSTATE_BOOL(qi_enabled, IntelIOMMUState), + VMSTATE_BOOL(intr_enabled, IntelIOMMUState), + VMSTATE_BOOL(intr_eime, IntelIOMMUState), + VMSTATE_END_OF_LIST() + } }; static const MemoryRegionOps vtd_mem_ops = { @@ -2324,19 +2413,22 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus, int devfn) uintptr_t key = (uintptr_t)bus; VTDBus *vtd_bus = g_hash_table_lookup(s->vtd_as_by_busptr, &key); VTDAddressSpace *vtd_dev_as; + char name[128]; if (!vtd_bus) { + uintptr_t *new_key = g_malloc(sizeof(*new_key)); + *new_key = (uintptr_t)bus; /* No corresponding free() */ vtd_bus = g_malloc0(sizeof(VTDBus) + sizeof(VTDAddressSpace *) * \ X86_IOMMU_PCI_DEVFN_MAX); vtd_bus->bus = bus; - key = (uintptr_t)bus; - g_hash_table_insert(s->vtd_as_by_busptr, &key, vtd_bus); + g_hash_table_insert(s->vtd_as_by_busptr, new_key, vtd_bus); } vtd_dev_as = vtd_bus->dev_as[devfn]; if (!vtd_dev_as) { + snprintf(name, sizeof(name), "intel_iommu_devfn_%d", devfn); vtd_bus->dev_as[devfn] = vtd_dev_as = g_malloc0(sizeof(VTDAddressSpace)); vtd_dev_as->bus = bus; @@ -2351,7 +2443,7 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus, int devfn) memory_region_add_subregion(&vtd_dev_as->iommu, VTD_INTERRUPT_ADDR_FIRST, &vtd_dev_as->iommu_ir); address_space_init(&vtd_dev_as->as, - &vtd_dev_as->iommu, "intel_iommu"); + &vtd_dev_as->iommu, name); } return vtd_dev_as; } @@ -2392,6 +2484,10 @@ static void vtd_init(IntelIOMMUState *s) assert(s->intr_eim != ON_OFF_AUTO_AUTO); } + if (x86_iommu->dt_supported) { + s->ecap |= VTD_ECAP_DT; + } + vtd_reset_context_cache(s); vtd_reset_iotlb(s); diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h index 11abfa2233..356f188b73 100644 --- a/hw/i386/intel_iommu_internal.h +++ b/hw/i386/intel_iommu_internal.h @@ -183,6 +183,7 @@ /* (offset >> 4) << 8 */ #define VTD_ECAP_IRO (DMAR_IOTLB_REG_OFFSET << 4) #define VTD_ECAP_QI (1ULL << 1) +#define VTD_ECAP_DT (1ULL << 2) /* Interrupt Remapping support */ #define VTD_ECAP_IR (1ULL << 3) #define VTD_ECAP_EIM (1ULL << 4) @@ -326,6 +327,7 @@ typedef union VTDInvDesc VTDInvDesc; #define VTD_INV_DESC_TYPE 0xf #define VTD_INV_DESC_CC 0x1 /* Context-cache Invalidate Desc */ #define VTD_INV_DESC_IOTLB 0x2 +#define VTD_INV_DESC_DEVICE 0x3 #define VTD_INV_DESC_IEC 0x4 /* Interrupt Entry Cache Invalidate Descriptor */ #define VTD_INV_DESC_WAIT 0x5 /* Invalidation Wait Descriptor */ @@ -361,6 +363,13 @@ typedef union VTDInvDesc VTDInvDesc; #define VTD_INV_DESC_IOTLB_RSVD_LO 0xffffffff0000ff00ULL #define VTD_INV_DESC_IOTLB_RSVD_HI 0xf80ULL +/* Mask for Device IOTLB Invalidate Descriptor */ +#define VTD_INV_DESC_DEVICE_IOTLB_ADDR(val) ((val) & 0xfffffffffffff000ULL) +#define VTD_INV_DESC_DEVICE_IOTLB_SIZE(val) ((val) & 0x1) +#define VTD_INV_DESC_DEVICE_IOTLB_SID(val) (((val) >> 32) & 0xFFFFULL) +#define VTD_INV_DESC_DEVICE_IOTLB_RSVD_HI 0xffeULL +#define VTD_INV_DESC_DEVICE_IOTLB_RSVD_LO 0xffff0000ffe0fff8 + /* Information about page-selective IOTLB invalidate */ struct VTDIOTLBPageInvInfo { uint16_t domain_id; @@ -399,8 +408,8 @@ typedef struct VTDRootEntry VTDRootEntry; #define VTD_CONTEXT_ENTRY_FPD (1ULL << 1) /* Fault Processing Disable */ #define VTD_CONTEXT_ENTRY_TT (3ULL << 2) /* Translation Type */ #define VTD_CONTEXT_TT_MULTI_LEVEL 0 -#define VTD_CONTEXT_TT_DEV_IOTLB 1 -#define VTD_CONTEXT_TT_PASS_THROUGH 2 +#define VTD_CONTEXT_TT_DEV_IOTLB (1ULL << 2) +#define VTD_CONTEXT_TT_PASS_THROUGH (2ULL << 2) /* Second Level Page Translation Pointer*/ #define VTD_CONTEXT_ENTRY_SLPTPTR (~0xfffULL) #define VTD_CONTEXT_ENTRY_RSVD_LO (0xff0ULL | ~VTD_HAW_MASK) diff --git a/hw/i386/kvm/apic.c b/hw/i386/kvm/apic.c index df5180b1e0..1df6d26816 100644 --- a/hw/i386/kvm/apic.c +++ b/hw/i386/kvm/apic.c @@ -14,6 +14,7 @@ #include "cpu.h" #include "hw/i386/apic_internal.h" #include "hw/pci/msi.h" +#include "sysemu/hw_accel.h" #include "sysemu/kvm.h" #include "target/i386/kvm_i386.h" diff --git a/hw/i386/kvmvapic.c b/hw/i386/kvmvapic.c index b30d1b90c6..702e281dc8 100644 --- a/hw/i386/kvmvapic.c +++ b/hw/i386/kvmvapic.c @@ -14,6 +14,7 @@ #include "exec/exec-all.h" #include "sysemu/sysemu.h" #include "sysemu/cpus.h" +#include "sysemu/hw_accel.h" #include "sysemu/kvm.h" #include "hw/i386/apic_internal.h" #include "hw/sysbus.h" @@ -534,7 +535,6 @@ static int patch_hypercalls(VAPICROMState *s) uint8_t alternates[2]; const uint8_t *pattern; const uint8_t *patch; - int patches = 0; off_t pos; uint8_t *rom; @@ -565,11 +565,6 @@ static int patch_hypercalls(VAPICROMState *s) } g_free(rom); - - if (patches != 0 && patches != 2) { - return -1; - } - return 0; } diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 25e8586b48..706e2330ac 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -701,16 +701,20 @@ static uint32_t x86_cpu_apic_id_from_index(unsigned int cpu_index) } } -static void pc_build_smbios(FWCfgState *fw_cfg) +static void pc_build_smbios(PCMachineState *pcms) { uint8_t *smbios_tables, *smbios_anchor; size_t smbios_tables_len, smbios_anchor_len; struct smbios_phys_mem_area *mem_array; unsigned i, array_count; + X86CPU *cpu = X86_CPU(pcms->possible_cpus->cpus[0].cpu); + + /* tell smbios about cpuid version and features */ + smbios_set_cpuid(cpu->env.cpuid_version, cpu->env.features[FEAT_1_EDX]); smbios_tables = smbios_get_table_legacy(&smbios_tables_len); if (smbios_tables) { - fw_cfg_add_bytes(fw_cfg, FW_CFG_SMBIOS_ENTRIES, + fw_cfg_add_bytes(pcms->fw_cfg, FW_CFG_SMBIOS_ENTRIES, smbios_tables, smbios_tables_len); } @@ -731,9 +735,9 @@ static void pc_build_smbios(FWCfgState *fw_cfg) g_free(mem_array); if (smbios_anchor) { - fw_cfg_add_file(fw_cfg, "etc/smbios/smbios-tables", + fw_cfg_add_file(pcms->fw_cfg, "etc/smbios/smbios-tables", smbios_tables, smbios_tables_len); - fw_cfg_add_file(fw_cfg, "etc/smbios/smbios-anchor", + fw_cfg_add_file(pcms->fw_cfg, "etc/smbios/smbios-anchor", smbios_anchor, smbios_anchor_len); } } @@ -1088,28 +1092,24 @@ void pc_acpi_smi_interrupt(void *opaque, int irq, int level) } } -static X86CPU *pc_new_cpu(const char *typename, int64_t apic_id, - Error **errp) +static void pc_new_cpu(const char *typename, int64_t apic_id, Error **errp) { - X86CPU *cpu = NULL; + Object *cpu = NULL; Error *local_err = NULL; - cpu = X86_CPU(object_new(typename)); + cpu = object_new(typename); - object_property_set_int(OBJECT(cpu), apic_id, "apic-id", &local_err); - object_property_set_bool(OBJECT(cpu), true, "realized", &local_err); + object_property_set_int(cpu, apic_id, "apic-id", &local_err); + object_property_set_bool(cpu, true, "realized", &local_err); + object_unref(cpu); if (local_err) { error_propagate(errp, local_err); - object_unref(OBJECT(cpu)); - cpu = NULL; } - return cpu; } void pc_hot_add_cpu(const int64_t id, Error **errp) { - X86CPU *cpu; ObjectClass *oc; PCMachineState *pcms = PC_MACHINE(qdev_get_machine()); int64_t apic_id = x86_cpu_apic_id_from_index(id); @@ -1129,12 +1129,11 @@ void pc_hot_add_cpu(const int64_t id, Error **errp) assert(pcms->possible_cpus->cpus[0].cpu); /* BSP is always present */ oc = OBJECT_CLASS(CPU_GET_CLASS(pcms->possible_cpus->cpus[0].cpu)); - cpu = pc_new_cpu(object_class_get_name(oc), apic_id, &local_err); + pc_new_cpu(object_class_get_name(oc), apic_id, &local_err); if (local_err) { error_propagate(errp, local_err); return; } - object_unref(OBJECT(cpu)); } void pc_cpus_init(PCMachineState *pcms) @@ -1144,7 +1143,6 @@ void pc_cpus_init(PCMachineState *pcms) ObjectClass *oc; const char *typename; gchar **model_pieces; - X86CPU *cpu = NULL; MachineState *machine = MACHINE(pcms); /* init CPUs */ @@ -1186,14 +1184,9 @@ void pc_cpus_init(PCMachineState *pcms) pcms->possible_cpus->cpus[i].arch_id = x86_cpu_apic_id_from_index(i); pcms->possible_cpus->len++; if (i < smp_cpus) { - cpu = pc_new_cpu(typename, x86_cpu_apic_id_from_index(i), - &error_fatal); - object_unref(OBJECT(cpu)); + pc_new_cpu(typename, x86_cpu_apic_id_from_index(i), &error_fatal); } } - - /* tell smbios about cpuid version and features */ - smbios_set_cpuid(cpu->env.cpuid_version, cpu->env.features[FEAT_1_EDX]); } static void pc_build_feature_control_file(PCMachineState *pcms) @@ -1266,7 +1259,7 @@ void pc_machine_done(Notifier *notifier, void *data) acpi_setup(); if (pcms->fw_cfg) { - pc_build_smbios(pcms->fw_cfg); + pc_build_smbios(pcms); pc_build_feature_control_file(pcms); /* update FW_CFG_NB_CPUS to account for -device added CPUs */ fw_cfg_modify_i16(pcms->fw_cfg, FW_CFG_NB_CPUS, pcms->boot_cpus); @@ -1784,7 +1777,7 @@ static int pc_apic_cmp(const void *a, const void *b) /* returns pointer to CPUArchId descriptor that matches CPU's apic_id * in pcms->possible_cpus->cpus, if pcms->possible_cpus->cpus has no - * entry correponding to CPU's apic_id returns NULL. + * entry corresponding to CPU's apic_id returns NULL. */ static CPUArchId *pc_find_cpu_slot(PCMachineState *pcms, CPUState *cpu, int *idx) @@ -1820,8 +1813,10 @@ static void pc_cpu_plug(HotplugHandler *hotplug_dev, /* increment the number of CPUs */ pcms->boot_cpus++; - if (dev->hotplugged) { + if (pcms->rtc) { rtc_set_cpus_count(pcms->rtc, pcms->boot_cpus); + } + if (pcms->fw_cfg) { fw_cfg_modify_i16(pcms->fw_cfg, FW_CFG_NB_CPUS, pcms->boot_cpus); } @@ -2245,15 +2240,11 @@ static unsigned pc_cpu_index_to_socket_id(unsigned cpu_index) return topo.pkg_id; } -static CPUArchIdList *pc_possible_cpu_arch_ids(MachineState *machine) +static const CPUArchIdList *pc_possible_cpu_arch_ids(MachineState *machine) { PCMachineState *pcms = PC_MACHINE(machine); - int len = sizeof(CPUArchIdList) + - sizeof(CPUArchId) * (pcms->possible_cpus->len); - CPUArchIdList *list = g_malloc(len); - - memcpy(list, pcms->possible_cpus, len); - return list; + assert(pcms->possible_cpus); + return pcms->possible_cpus; } static HotpluggableCPUList *pc_query_hotpluggable_cpus(MachineState *machine) diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 5e1adbe53c..9f102aa388 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -437,13 +437,24 @@ static void pc_i440fx_machine_options(MachineClass *m) m->default_display = "std"; } -static void pc_i440fx_2_8_machine_options(MachineClass *m) +static void pc_i440fx_2_9_machine_options(MachineClass *m) { pc_i440fx_machine_options(m); m->alias = "pc"; m->is_default = 1; } +DEFINE_I440FX_MACHINE(v2_9, "pc-i440fx-2.9", NULL, + pc_i440fx_2_9_machine_options); + +static void pc_i440fx_2_8_machine_options(MachineClass *m) +{ + pc_i440fx_2_9_machine_options(m); + m->is_default = 0; + m->alias = NULL; + SET_MACHINE_COMPAT(m, PC_COMPAT_2_8); +} + DEFINE_I440FX_MACHINE(v2_8, "pc-i440fx-2.8", NULL, pc_i440fx_2_8_machine_options); @@ -451,8 +462,6 @@ DEFINE_I440FX_MACHINE(v2_8, "pc-i440fx-2.8", NULL, static void pc_i440fx_2_7_machine_options(MachineClass *m) { pc_i440fx_2_8_machine_options(m); - m->is_default = 0; - m->alias = NULL; SET_MACHINE_COMPAT(m, PC_COMPAT_2_7); } diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index d042fe0843..dd792a8547 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -301,19 +301,28 @@ static void pc_q35_machine_options(MachineClass *m) m->max_cpus = 288; } -static void pc_q35_2_8_machine_options(MachineClass *m) +static void pc_q35_2_9_machine_options(MachineClass *m) { pc_q35_machine_options(m); m->alias = "q35"; } +DEFINE_Q35_MACHINE(v2_9, "pc-q35-2.9", NULL, + pc_q35_2_9_machine_options); + +static void pc_q35_2_8_machine_options(MachineClass *m) +{ + pc_q35_2_9_machine_options(m); + m->alias = NULL; + SET_MACHINE_COMPAT(m, PC_COMPAT_2_8); +} + DEFINE_Q35_MACHINE(v2_8, "pc-q35-2.8", NULL, pc_q35_2_8_machine_options); static void pc_q35_2_7_machine_options(MachineClass *m) { pc_q35_2_8_machine_options(m); - m->alias = NULL; m->max_cpus = 255; SET_MACHINE_COMPAT(m, PC_COMPAT_2_7); } diff --git a/hw/i386/pci-assign-load-rom.c b/hw/i386/pci-assign-load-rom.c index 0d8e4b2826..fd59076e7a 100644 --- a/hw/i386/pci-assign-load-rom.c +++ b/hw/i386/pci-assign-load-rom.c @@ -39,19 +39,19 @@ void *pci_assign_dev_load_option_rom(PCIDevice *dev, struct Object *owner, "/sys/bus/pci/devices/%04x:%02x:%02x.%01x/rom", domain, bus, slot, function); - if (stat(rom_file, &st)) { - if (errno != ENOENT) { - error_report("pci-assign: Invalid ROM."); - } - return NULL; - } - /* Write "1" to the ROM file to enable it */ fp = fopen(rom_file, "r+"); if (fp == NULL) { - error_report("pci-assign: Cannot open %s: %s", rom_file, strerror(errno)); + if (errno != ENOENT) { + error_report("pci-assign: Cannot open %s: %s", rom_file, strerror(errno)); + } return NULL; } + if (fstat(fileno(fp), &st) == -1) { + error_report("pci-assign: Cannot stat %s: %s", rom_file, strerror(errno)); + goto close_rom; + } + val = 1; if (fwrite(&val, 1, 1, fp) != 1) { goto close_rom; diff --git a/hw/i386/x86-iommu.c b/hw/i386/x86-iommu.c index 2278af7c32..23dcd3f039 100644 --- a/hw/i386/x86-iommu.c +++ b/hw/i386/x86-iommu.c @@ -106,6 +106,18 @@ static void x86_iommu_intremap_prop_set(Object *o, bool value, Error **errp) s->intr_supported = value; } +static bool x86_iommu_device_iotlb_prop_get(Object *o, Error **errp) +{ + X86IOMMUState *s = X86_IOMMU_DEVICE(o); + return s->dt_supported; +} + +static void x86_iommu_device_iotlb_prop_set(Object *o, bool value, Error **errp) +{ + X86IOMMUState *s = X86_IOMMU_DEVICE(o); + s->dt_supported = value; +} + static void x86_iommu_instance_init(Object *o) { X86IOMMUState *s = X86_IOMMU_DEVICE(o); @@ -114,6 +126,11 @@ static void x86_iommu_instance_init(Object *o) s->intr_supported = false; object_property_add_bool(o, "intremap", x86_iommu_intremap_prop_get, x86_iommu_intremap_prop_set, NULL); + s->dt_supported = false; + object_property_add_bool(o, "device-iotlb", + x86_iommu_device_iotlb_prop_get, + x86_iommu_device_iotlb_prop_set, + NULL); } static const TypeInfo x86_iommu_info = { diff --git a/hw/input/lm832x.c b/hw/input/lm832x.c index 539682cac8..2340523da0 100644 --- a/hw/input/lm832x.c +++ b/hw/input/lm832x.c @@ -383,7 +383,7 @@ static void lm_kbd_write(LM823KbdState *s, int reg, int byte, uint8_t value) } } -static void lm_i2c_event(I2CSlave *i2c, enum i2c_event event) +static int lm_i2c_event(I2CSlave *i2c, enum i2c_event event) { LM823KbdState *s = LM8323(i2c); @@ -397,6 +397,8 @@ static void lm_i2c_event(I2CSlave *i2c, enum i2c_event event) default: break; } + + return 0; } static int lm_i2c_rx(I2CSlave *i2c) diff --git a/hw/input/ps2.c b/hw/input/ps2.c index 0d14de08a6..8485a4edaf 100644 --- a/hw/input/ps2.c +++ b/hw/input/ps2.c @@ -252,6 +252,9 @@ static const uint16_t qcode_to_keycode_set1[Q_KEY_CODE__MAX] = { [Q_KEY_CODE_ASTERISK] = 0x37, [Q_KEY_CODE_LESS] = 0x56, [Q_KEY_CODE_RO] = 0x73, + [Q_KEY_CODE_HIRAGANA] = 0x70, + [Q_KEY_CODE_HENKAN] = 0x79, + [Q_KEY_CODE_YEN] = 0x7d, [Q_KEY_CODE_KP_COMMA] = 0x7e, }; @@ -394,6 +397,9 @@ static const uint16_t qcode_to_keycode_set2[Q_KEY_CODE__MAX] = { [Q_KEY_CODE_LESS] = 0x61, [Q_KEY_CODE_SYSRQ] = 0x7f, [Q_KEY_CODE_RO] = 0x51, + [Q_KEY_CODE_HIRAGANA] = 0x13, + [Q_KEY_CODE_HENKAN] = 0x64, + [Q_KEY_CODE_YEN] = 0x6a, [Q_KEY_CODE_KP_COMMA] = 0x6d, }; @@ -504,6 +510,10 @@ static const uint16_t qcode_to_keycode_set3[Q_KEY_CODE__MAX] = { [Q_KEY_CODE_COMMA] = 0x41, [Q_KEY_CODE_DOT] = 0x49, [Q_KEY_CODE_SLASH] = 0x4a, + + [Q_KEY_CODE_HIRAGANA] = 0x87, + [Q_KEY_CODE_HENKAN] = 0x86, + [Q_KEY_CODE_YEN] = 0x5d, }; static uint8_t translate_table[256] = { diff --git a/hw/intc/Makefile.objs b/hw/intc/Makefile.objs index 2f44a2da26..8948106ac4 100644 --- a/hw/intc/Makefile.objs +++ b/hw/intc/Makefile.objs @@ -41,3 +41,4 @@ obj-$(CONFIG_S390_FLIC_KVM) += s390_flic_kvm.o obj-$(CONFIG_ASPEED_SOC) += aspeed_vic.o obj-$(CONFIG_ARM_GIC) += arm_gicv3_cpuif.o obj-$(CONFIG_MIPS_CPS) += mips_gic.o +obj-$(CONFIG_NIOS2) += nios2_iic.o diff --git a/hw/intc/apic_common.c b/hw/intc/apic_common.c index d78c885509..3945dfd7b9 100644 --- a/hw/intc/apic_common.c +++ b/hw/intc/apic_common.c @@ -26,6 +26,7 @@ #include "hw/i386/apic.h" #include "hw/i386/apic_internal.h" #include "trace.h" +#include "sysemu/hax.h" #include "sysemu/kvm.h" #include "hw/qdev.h" #include "hw/sysbus.h" @@ -316,7 +317,7 @@ static void apic_common_realize(DeviceState *dev, Error **errp) /* Note: We need at least 1M to map the VAPIC option ROM */ if (!vapic && s->vapic_control & VAPIC_ENABLE_MASK && - ram_size >= 1024 * 1024) { + !hax_enabled() && ram_size >= 1024 * 1024) { vapic = sysbus_create_simple("kvmvapic", -1, NULL); } s->vapic = vapic; diff --git a/hw/intc/arm_gic_common.c b/hw/intc/arm_gic_common.c index 0a1f56af19..4a8df44fb1 100644 --- a/hw/intc/arm_gic_common.c +++ b/hw/intc/arm_gic_common.c @@ -110,6 +110,12 @@ void gic_init_irqs_and_mmio(GICState *s, qemu_irq_handler handler, for (i = 0; i < s->num_cpu; i++) { sysbus_init_irq(sbd, &s->parent_fiq[i]); } + for (i = 0; i < s->num_cpu; i++) { + sysbus_init_irq(sbd, &s->parent_virq[i]); + } + for (i = 0; i < s->num_cpu; i++) { + sysbus_init_irq(sbd, &s->parent_vfiq[i]); + } /* Distributor */ memory_region_init_io(&s->iomem, OBJECT(s), ops, s, "gic_dist", 0x1000); diff --git a/hw/intc/arm_gic_kvm.c b/hw/intc/arm_gic_kvm.c index 11729ee902..ec952ece93 100644 --- a/hw/intc/arm_gic_kvm.c +++ b/hw/intc/arm_gic_kvm.c @@ -510,6 +510,17 @@ static void kvm_arm_gic_realize(DeviceState *dev, Error **errp) return; } + if (!kvm_arm_gic_can_save_restore(s)) { + error_setg(&s->migration_blocker, "This operating system kernel does " + "not support vGICv2 migration"); + migrate_add_blocker(s->migration_blocker, &local_err); + if (local_err) { + error_propagate(errp, local_err); + error_free(s->migration_blocker); + return; + } + } + gic_init_irqs_and_mmio(s, kvm_arm_gicv2_set_irq, NULL); for (i = 0; i < s->num_irq - GIC_INTERNAL; i++) { @@ -558,12 +569,6 @@ static void kvm_arm_gic_realize(DeviceState *dev, Error **errp) KVM_VGIC_V2_ADDR_TYPE_CPU, s->dev_fd); - if (!kvm_arm_gic_can_save_restore(s)) { - error_setg(&s->migration_blocker, "This operating system kernel does " - "not support vGICv2 migration"); - migrate_add_blocker(s->migration_blocker); - } - if (kvm_has_gsi_routing()) { /* set up irq routing */ kvm_init_irq_routing(kvm_state); diff --git a/hw/intc/arm_gicv3.c b/hw/intc/arm_gicv3.c index 8a6c647219..f0c967b304 100644 --- a/hw/intc/arm_gicv3.c +++ b/hw/intc/arm_gicv3.c @@ -54,6 +54,7 @@ static uint32_t gicd_int_pending(GICv3State *s, int irq) * + the PENDING latch is set OR it is level triggered and the input is 1 * + its ENABLE bit is set * + the GICD enable bit for its group is set + * + its ACTIVE bit is not set (otherwise it would be Active+Pending) * Conveniently we can bulk-calculate this with bitwise operations. */ uint32_t pend, grpmask; @@ -63,9 +64,11 @@ static uint32_t gicd_int_pending(GICv3State *s, int irq) uint32_t group = *gic_bmp_ptr32(s->group, irq); uint32_t grpmod = *gic_bmp_ptr32(s->grpmod, irq); uint32_t enable = *gic_bmp_ptr32(s->enabled, irq); + uint32_t active = *gic_bmp_ptr32(s->active, irq); pend = pending | (~edge_trigger & level); pend &= enable; + pend &= ~active; if (s->gicd_ctlr & GICD_CTLR_DS) { grpmod = 0; @@ -96,12 +99,14 @@ static uint32_t gicr_int_pending(GICv3CPUState *cs) * + the PENDING latch is set OR it is level triggered and the input is 1 * + its ENABLE bit is set * + the GICD enable bit for its group is set + * + its ACTIVE bit is not set (otherwise it would be Active+Pending) * Conveniently we can bulk-calculate this with bitwise operations. */ uint32_t pend, grpmask, grpmod; pend = cs->gicr_ipendr0 | (~cs->edge_trigger & cs->level); pend &= cs->gicr_ienabler0; + pend &= ~cs->gicr_iactiver0; if (cs->gic->gicd_ctlr & GICD_CTLR_DS) { grpmod = 0; diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index 0f8c4b86e0..16b9b0f7eb 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -49,6 +49,27 @@ static int gicv3_post_load(void *opaque, int version_id) return 0; } +static bool virt_state_needed(void *opaque) +{ + GICv3CPUState *cs = opaque; + + return cs->num_list_regs != 0; +} + +static const VMStateDescription vmstate_gicv3_cpu_virt = { + .name = "arm_gicv3_cpu/virt", + .version_id = 1, + .minimum_version_id = 1, + .needed = virt_state_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT64_2DARRAY(ich_apr, GICv3CPUState, 3, 4), + VMSTATE_UINT64(ich_hcr_el2, GICv3CPUState), + VMSTATE_UINT64_ARRAY(ich_lr_el2, GICv3CPUState, GICV3_LR_MAX), + VMSTATE_UINT64(ich_vmcr_el2, GICv3CPUState), + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_gicv3_cpu = { .name = "arm_gicv3_cpu", .version_id = 1, @@ -75,6 +96,10 @@ static const VMStateDescription vmstate_gicv3_cpu = { VMSTATE_UINT64_ARRAY(icc_igrpen, GICv3CPUState, 3), VMSTATE_UINT64(icc_ctlr_el3, GICv3CPUState), VMSTATE_END_OF_LIST() + }, + .subsections = (const VMStateDescription * []) { + &vmstate_gicv3_cpu_virt, + NULL } }; @@ -126,6 +151,12 @@ void gicv3_init_irqs_and_mmio(GICv3State *s, qemu_irq_handler handler, for (i = 0; i < s->num_cpu; i++) { sysbus_init_irq(sbd, &s->cpu[i].parent_fiq); } + for (i = 0; i < s->num_cpu; i++) { + sysbus_init_irq(sbd, &s->cpu[i].parent_virq); + } + for (i = 0; i < s->num_cpu; i++) { + sysbus_init_irq(sbd, &s->cpu[i].parent_vfiq); + } memory_region_init_io(&s->iomem_dist, OBJECT(s), ops, s, "gicv3_dist", 0x10000); @@ -204,7 +235,8 @@ static void arm_gicv3_common_realize(DeviceState *dev, Error **errp) /* The CPU mp-affinity property is in MPIDR register format; squash * the affinity bytes into 32 bits as the GICR_TYPER has them. */ - cpu_affid = (cpu_affid & 0xFF00000000ULL >> 8) | (cpu_affid & 0xFFFFFF); + cpu_affid = ((cpu_affid & 0xFF00000000ULL) >> 8) | + (cpu_affid & 0xFFFFFF); s->cpu[i].gicr_typer = (cpu_affid << 32) | (1 << 24) | (i << 8) | diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index bca30c49da..a9ee7fddf9 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -13,6 +13,7 @@ */ #include "qemu/osdep.h" +#include "qemu/bitops.h" #include "trace.h" #include "gicv3_internal.h" #include "cpu.h" @@ -36,6 +37,610 @@ static bool gicv3_use_ns_bank(CPUARMState *env) return !arm_is_secure_below_el3(env); } +/* The minimum BPR for the virtual interface is a configurable property */ +static inline int icv_min_vbpr(GICv3CPUState *cs) +{ + return 7 - cs->vprebits; +} + +/* Simple accessor functions for LR fields */ +static uint32_t ich_lr_vintid(uint64_t lr) +{ + return extract64(lr, ICH_LR_EL2_VINTID_SHIFT, ICH_LR_EL2_VINTID_LENGTH); +} + +static uint32_t ich_lr_pintid(uint64_t lr) +{ + return extract64(lr, ICH_LR_EL2_PINTID_SHIFT, ICH_LR_EL2_PINTID_LENGTH); +} + +static uint32_t ich_lr_prio(uint64_t lr) +{ + return extract64(lr, ICH_LR_EL2_PRIORITY_SHIFT, ICH_LR_EL2_PRIORITY_LENGTH); +} + +static int ich_lr_state(uint64_t lr) +{ + return extract64(lr, ICH_LR_EL2_STATE_SHIFT, ICH_LR_EL2_STATE_LENGTH); +} + +static bool icv_access(CPUARMState *env, int hcr_flags) +{ + /* Return true if this ICC_ register access should really be + * directed to an ICV_ access. hcr_flags is a mask of + * HCR_EL2 bits to check: we treat this as an ICV_ access + * if we are in NS EL1 and at least one of the specified + * HCR_EL2 bits is set. + * + * ICV registers fall into four categories: + * * access if NS EL1 and HCR_EL2.FMO == 1: + * all ICV regs with '0' in their name + * * access if NS EL1 and HCR_EL2.IMO == 1: + * all ICV regs with '1' in their name + * * access if NS EL1 and either IMO or FMO == 1: + * CTLR, DIR, PMR, RPR + */ + return (env->cp15.hcr_el2 & hcr_flags) && arm_current_el(env) == 1 + && !arm_is_secure_below_el3(env); +} + +static int read_vbpr(GICv3CPUState *cs, int grp) +{ + /* Read VBPR value out of the VMCR field (caller must handle + * VCBPR effects if required) + */ + if (grp == GICV3_G0) { + return extract64(cs->ich_vmcr_el2, ICH_VMCR_EL2_VBPR0_SHIFT, + ICH_VMCR_EL2_VBPR0_LENGTH); + } else { + return extract64(cs->ich_vmcr_el2, ICH_VMCR_EL2_VBPR1_SHIFT, + ICH_VMCR_EL2_VBPR1_LENGTH); + } +} + +static void write_vbpr(GICv3CPUState *cs, int grp, int value) +{ + /* Write new VBPR1 value, handling the "writing a value less than + * the minimum sets it to the minimum" semantics. + */ + int min = icv_min_vbpr(cs); + + if (grp != GICV3_G0) { + min++; + } + + value = MAX(value, min); + + if (grp == GICV3_G0) { + cs->ich_vmcr_el2 = deposit64(cs->ich_vmcr_el2, ICH_VMCR_EL2_VBPR0_SHIFT, + ICH_VMCR_EL2_VBPR0_LENGTH, value); + } else { + cs->ich_vmcr_el2 = deposit64(cs->ich_vmcr_el2, ICH_VMCR_EL2_VBPR1_SHIFT, + ICH_VMCR_EL2_VBPR1_LENGTH, value); + } +} + +static uint32_t icv_fullprio_mask(GICv3CPUState *cs) +{ + /* Return a mask word which clears the unimplemented priority bits + * from a priority value for a virtual interrupt. (Not to be confused + * with the group priority, whose mask depends on the value of VBPR + * for the interrupt group.) + */ + return ~0U << (8 - cs->vpribits); +} + +static int ich_highest_active_virt_prio(GICv3CPUState *cs) +{ + /* Calculate the current running priority based on the set bits + * in the ICH Active Priority Registers. + */ + int i; + int aprmax = 1 << (cs->vprebits - 5); + + assert(aprmax <= ARRAY_SIZE(cs->ich_apr[0])); + + for (i = 0; i < aprmax; i++) { + uint32_t apr = cs->ich_apr[GICV3_G0][i] | + cs->ich_apr[GICV3_G1NS][i]; + + if (!apr) { + continue; + } + return (i * 32 + ctz32(apr)) << (icv_min_vbpr(cs) + 1); + } + /* No current active interrupts: return idle priority */ + return 0xff; +} + +static int hppvi_index(GICv3CPUState *cs) +{ + /* Return the list register index of the highest priority pending + * virtual interrupt, as per the HighestPriorityVirtualInterrupt + * pseudocode. If no pending virtual interrupts, return -1. + */ + int idx = -1; + int i; + /* Note that a list register entry with a priority of 0xff will + * never be reported by this function; this is the architecturally + * correct behaviour. + */ + int prio = 0xff; + + if (!(cs->ich_vmcr_el2 & (ICH_VMCR_EL2_VENG0 | ICH_VMCR_EL2_VENG1))) { + /* Both groups disabled, definitely nothing to do */ + return idx; + } + + for (i = 0; i < cs->num_list_regs; i++) { + uint64_t lr = cs->ich_lr_el2[i]; + int thisprio; + + if (ich_lr_state(lr) != ICH_LR_EL2_STATE_PENDING) { + /* Not Pending */ + continue; + } + + /* Ignore interrupts if relevant group enable not set */ + if (lr & ICH_LR_EL2_GROUP) { + if (!(cs->ich_vmcr_el2 & ICH_VMCR_EL2_VENG1)) { + continue; + } + } else { + if (!(cs->ich_vmcr_el2 & ICH_VMCR_EL2_VENG0)) { + continue; + } + } + + thisprio = ich_lr_prio(lr); + + if (thisprio < prio) { + prio = thisprio; + idx = i; + } + } + + return idx; +} + +static uint32_t icv_gprio_mask(GICv3CPUState *cs, int group) +{ + /* Return a mask word which clears the subpriority bits from + * a priority value for a virtual interrupt in the specified group. + * This depends on the VBPR value: + * a BPR of 0 means the group priority bits are [7:1]; + * a BPR of 1 means they are [7:2], and so on down to + * a BPR of 7 meaning no group priority bits at all. + * Which BPR to use depends on the group of the interrupt and + * the current ICH_VMCR_EL2.VCBPR settings. + */ + if (group == GICV3_G1NS && cs->ich_vmcr_el2 & ICH_VMCR_EL2_VCBPR) { + group = GICV3_G0; + } + + return ~0U << (read_vbpr(cs, group) + 1); +} + +static bool icv_hppi_can_preempt(GICv3CPUState *cs, uint64_t lr) +{ + /* Return true if we can signal this virtual interrupt defined by + * the given list register value; see the pseudocode functions + * CanSignalVirtualInterrupt and CanSignalVirtualInt. + * Compare also icc_hppi_can_preempt() which is the non-virtual + * equivalent of these checks. + */ + int grp; + uint32_t mask, prio, rprio, vpmr; + + if (!(cs->ich_hcr_el2 & ICH_HCR_EL2_EN)) { + /* Virtual interface disabled */ + return false; + } + + /* We don't need to check that this LR is in Pending state because + * that has already been done in hppvi_index(). + */ + + prio = ich_lr_prio(lr); + vpmr = extract64(cs->ich_vmcr_el2, ICH_VMCR_EL2_VPMR_SHIFT, + ICH_VMCR_EL2_VPMR_LENGTH); + + if (prio >= vpmr) { + /* Priority mask masks this interrupt */ + return false; + } + + rprio = ich_highest_active_virt_prio(cs); + if (rprio == 0xff) { + /* No running interrupt so we can preempt */ + return true; + } + + grp = (lr & ICH_LR_EL2_GROUP) ? GICV3_G1NS : GICV3_G0; + + mask = icv_gprio_mask(cs, grp); + + /* We only preempt a running interrupt if the pending interrupt's + * group priority is sufficient (the subpriorities are not considered). + */ + if ((prio & mask) < (rprio & mask)) { + return true; + } + + return false; +} + +static uint32_t eoi_maintenance_interrupt_state(GICv3CPUState *cs, + uint32_t *misr) +{ + /* Return a set of bits indicating the EOI maintenance interrupt status + * for each list register. The EOI maintenance interrupt status is + * 1 if LR.State == 0 && LR.HW == 0 && LR.EOI == 1 + * (see the GICv3 spec for the ICH_EISR_EL2 register). + * If misr is not NULL then we should also collect the information + * about the MISR.EOI, MISR.NP and MISR.U bits. + */ + uint32_t value = 0; + int validcount = 0; + bool seenpending = false; + int i; + + for (i = 0; i < cs->num_list_regs; i++) { + uint64_t lr = cs->ich_lr_el2[i]; + + if ((lr & (ICH_LR_EL2_STATE_MASK | ICH_LR_EL2_HW | ICH_LR_EL2_EOI)) + == ICH_LR_EL2_EOI) { + value |= (1 << i); + } + if ((lr & ICH_LR_EL2_STATE_MASK)) { + validcount++; + } + if (ich_lr_state(lr) == ICH_LR_EL2_STATE_PENDING) { + seenpending = true; + } + } + + if (misr) { + if (validcount < 2 && (cs->ich_hcr_el2 & ICH_HCR_EL2_UIE)) { + *misr |= ICH_MISR_EL2_U; + } + if (!seenpending && (cs->ich_hcr_el2 & ICH_HCR_EL2_NPIE)) { + *misr |= ICH_MISR_EL2_NP; + } + if (value) { + *misr |= ICH_MISR_EL2_EOI; + } + } + return value; +} + +static uint32_t maintenance_interrupt_state(GICv3CPUState *cs) +{ + /* Return a set of bits indicating the maintenance interrupt status + * (as seen in the ICH_MISR_EL2 register). + */ + uint32_t value = 0; + + /* Scan list registers and fill in the U, NP and EOI bits */ + eoi_maintenance_interrupt_state(cs, &value); + + if (cs->ich_hcr_el2 & (ICH_HCR_EL2_LRENPIE | ICH_HCR_EL2_EOICOUNT_MASK)) { + value |= ICH_MISR_EL2_LRENP; + } + + if ((cs->ich_hcr_el2 & ICH_HCR_EL2_VGRP0EIE) && + (cs->ich_vmcr_el2 & ICH_VMCR_EL2_VENG0)) { + value |= ICH_MISR_EL2_VGRP0E; + } + + if ((cs->ich_hcr_el2 & ICH_HCR_EL2_VGRP0DIE) && + !(cs->ich_vmcr_el2 & ICH_VMCR_EL2_VENG1)) { + value |= ICH_MISR_EL2_VGRP0D; + } + if ((cs->ich_hcr_el2 & ICH_HCR_EL2_VGRP1EIE) && + (cs->ich_vmcr_el2 & ICH_VMCR_EL2_VENG1)) { + value |= ICH_MISR_EL2_VGRP1E; + } + + if ((cs->ich_hcr_el2 & ICH_HCR_EL2_VGRP1DIE) && + !(cs->ich_vmcr_el2 & ICH_VMCR_EL2_VENG1)) { + value |= ICH_MISR_EL2_VGRP1D; + } + + return value; +} + +static void gicv3_cpuif_virt_update(GICv3CPUState *cs) +{ + /* Tell the CPU about any pending virtual interrupts or + * maintenance interrupts, following a change to the state + * of the CPU interface relevant to virtual interrupts. + * + * CAUTION: this function will call qemu_set_irq() on the + * CPU maintenance IRQ line, which is typically wired up + * to the GIC as a per-CPU interrupt. This means that it + * will recursively call back into the GIC code via + * gicv3_redist_set_irq() and thus into the CPU interface code's + * gicv3_cpuif_update(). It is therefore important that this + * function is only called as the final action of a CPU interface + * register write implementation, after all the GIC state + * fields have been updated. gicv3_cpuif_update() also must + * not cause this function to be called, but that happens + * naturally as a result of there being no architectural + * linkage between the physical and virtual GIC logic. + */ + int idx; + int irqlevel = 0; + int fiqlevel = 0; + int maintlevel = 0; + + idx = hppvi_index(cs); + trace_gicv3_cpuif_virt_update(gicv3_redist_affid(cs), idx); + if (idx >= 0) { + uint64_t lr = cs->ich_lr_el2[idx]; + + if (icv_hppi_can_preempt(cs, lr)) { + /* Virtual interrupts are simple: G0 are always FIQ, and G1 IRQ */ + if (lr & ICH_LR_EL2_GROUP) { + irqlevel = 1; + } else { + fiqlevel = 1; + } + } + } + + if (cs->ich_hcr_el2 & ICH_HCR_EL2_EN) { + maintlevel = maintenance_interrupt_state(cs); + } + + trace_gicv3_cpuif_virt_set_irqs(gicv3_redist_affid(cs), fiqlevel, + irqlevel, maintlevel); + + qemu_set_irq(cs->parent_vfiq, fiqlevel); + qemu_set_irq(cs->parent_virq, irqlevel); + qemu_set_irq(cs->maintenance_irq, maintlevel); +} + +static uint64_t icv_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + int regno = ri->opc2 & 3; + int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1NS; + uint64_t value = cs->ich_apr[grp][regno]; + + trace_gicv3_icv_ap_read(ri->crm & 1, regno, gicv3_redist_affid(cs), value); + return value; +} + +static void icv_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + int regno = ri->opc2 & 3; + int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1NS; + + trace_gicv3_icv_ap_write(ri->crm & 1, regno, gicv3_redist_affid(cs), value); + + cs->ich_apr[grp][regno] = value & 0xFFFFFFFFU; + + gicv3_cpuif_virt_update(cs); + return; +} + +static uint64_t icv_bpr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + int grp = (ri->crm == 8) ? GICV3_G0 : GICV3_G1NS; + uint64_t bpr; + bool satinc = false; + + if (grp == GICV3_G1NS && (cs->ich_vmcr_el2 & ICH_VMCR_EL2_VCBPR)) { + /* reads return bpr0 + 1 saturated to 7, writes ignored */ + grp = GICV3_G0; + satinc = true; + } + + bpr = read_vbpr(cs, grp); + + if (satinc) { + bpr++; + bpr = MIN(bpr, 7); + } + + trace_gicv3_icv_bpr_read(ri->crm == 8 ? 0 : 1, gicv3_redist_affid(cs), bpr); + + return bpr; +} + +static void icv_bpr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + int grp = (ri->crm == 8) ? GICV3_G0 : GICV3_G1NS; + + trace_gicv3_icv_bpr_write(ri->crm == 8 ? 0 : 1, + gicv3_redist_affid(cs), value); + + if (grp == GICV3_G1NS && (cs->ich_vmcr_el2 & ICH_VMCR_EL2_VCBPR)) { + /* reads return bpr0 + 1 saturated to 7, writes ignored */ + return; + } + + write_vbpr(cs, grp, value); + + gicv3_cpuif_virt_update(cs); +} + +static uint64_t icv_pmr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + uint64_t value; + + value = extract64(cs->ich_vmcr_el2, ICH_VMCR_EL2_VPMR_SHIFT, + ICH_VMCR_EL2_VPMR_LENGTH); + + trace_gicv3_icv_pmr_read(gicv3_redist_affid(cs), value); + return value; +} + +static void icv_pmr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + + trace_gicv3_icv_pmr_write(gicv3_redist_affid(cs), value); + + value &= icv_fullprio_mask(cs); + + cs->ich_vmcr_el2 = deposit64(cs->ich_vmcr_el2, ICH_VMCR_EL2_VPMR_SHIFT, + ICH_VMCR_EL2_VPMR_LENGTH, value); + + gicv3_cpuif_virt_update(cs); +} + +static uint64_t icv_igrpen_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + int enbit; + uint64_t value; + + enbit = ri->opc2 & 1 ? ICH_VMCR_EL2_VENG1_SHIFT : ICH_VMCR_EL2_VENG0_SHIFT; + value = extract64(cs->ich_vmcr_el2, enbit, 1); + + trace_gicv3_icv_igrpen_read(ri->opc2 & 1 ? 1 : 0, + gicv3_redist_affid(cs), value); + return value; +} + +static void icv_igrpen_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + int enbit; + + trace_gicv3_icv_igrpen_write(ri->opc2 & 1 ? 1 : 0, + gicv3_redist_affid(cs), value); + + enbit = ri->opc2 & 1 ? ICH_VMCR_EL2_VENG1_SHIFT : ICH_VMCR_EL2_VENG0_SHIFT; + + cs->ich_vmcr_el2 = deposit64(cs->ich_vmcr_el2, enbit, 1, value); + gicv3_cpuif_virt_update(cs); +} + +static uint64_t icv_ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + uint64_t value; + + /* Note that the fixed fields here (A3V, SEIS, IDbits, PRIbits) + * should match the ones reported in ich_vtr_read(). + */ + value = ICC_CTLR_EL1_A3V | (1 << ICC_CTLR_EL1_IDBITS_SHIFT) | + (7 << ICC_CTLR_EL1_PRIBITS_SHIFT); + + if (cs->ich_vmcr_el2 & ICH_VMCR_EL2_VEOIM) { + value |= ICC_CTLR_EL1_EOIMODE; + } + + if (cs->ich_vmcr_el2 & ICH_VMCR_EL2_VCBPR) { + value |= ICC_CTLR_EL1_CBPR; + } + + trace_gicv3_icv_ctlr_read(gicv3_redist_affid(cs), value); + return value; +} + +static void icv_ctlr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + + trace_gicv3_icv_ctlr_write(gicv3_redist_affid(cs), value); + + cs->ich_vmcr_el2 = deposit64(cs->ich_vmcr_el2, ICH_VMCR_EL2_VCBPR_SHIFT, + 1, value & ICC_CTLR_EL1_CBPR ? 1 : 0); + cs->ich_vmcr_el2 = deposit64(cs->ich_vmcr_el2, ICH_VMCR_EL2_VEOIM_SHIFT, + 1, value & ICC_CTLR_EL1_EOIMODE ? 1 : 0); + + gicv3_cpuif_virt_update(cs); +} + +static uint64_t icv_rpr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + int prio = ich_highest_active_virt_prio(cs); + + trace_gicv3_icv_rpr_read(gicv3_redist_affid(cs), prio); + return prio; +} + +static uint64_t icv_hppir_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + int grp = ri->crm == 8 ? GICV3_G0 : GICV3_G1NS; + int idx = hppvi_index(cs); + uint64_t value = INTID_SPURIOUS; + + if (idx >= 0) { + uint64_t lr = cs->ich_lr_el2[idx]; + int thisgrp = (lr & ICH_LR_EL2_GROUP) ? GICV3_G1NS : GICV3_G0; + + if (grp == thisgrp) { + value = ich_lr_vintid(lr); + } + } + + trace_gicv3_icv_hppir_read(grp, gicv3_redist_affid(cs), value); + return value; +} + +static void icv_activate_irq(GICv3CPUState *cs, int idx, int grp) +{ + /* Activate the interrupt in the specified list register + * by moving it from Pending to Active state, and update the + * Active Priority Registers. + */ + uint32_t mask = icv_gprio_mask(cs, grp); + int prio = ich_lr_prio(cs->ich_lr_el2[idx]) & mask; + int aprbit = prio >> (8 - cs->vprebits); + int regno = aprbit / 32; + int regbit = aprbit % 32; + + cs->ich_lr_el2[idx] &= ~ICH_LR_EL2_STATE_PENDING_BIT; + cs->ich_lr_el2[idx] |= ICH_LR_EL2_STATE_ACTIVE_BIT; + cs->ich_apr[grp][regno] |= (1 << regbit); +} + +static uint64_t icv_iar_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + int grp = ri->crm == 8 ? GICV3_G0 : GICV3_G1NS; + int idx = hppvi_index(cs); + uint64_t intid = INTID_SPURIOUS; + + if (idx >= 0) { + uint64_t lr = cs->ich_lr_el2[idx]; + int thisgrp = (lr & ICH_LR_EL2_GROUP) ? GICV3_G1NS : GICV3_G0; + + if (thisgrp == grp && icv_hppi_can_preempt(cs, lr)) { + intid = ich_lr_vintid(lr); + if (intid < INTID_SECURE) { + icv_activate_irq(cs, idx, grp); + } else { + /* Interrupt goes from Pending to Invalid */ + cs->ich_lr_el2[idx] &= ~ICH_LR_EL2_STATE_PENDING_BIT; + /* We will now return the (bogus) ID from the list register, + * as per the pseudocode. + */ + } + } + } + + trace_gicv3_icv_iar_read(ri->crm == 8 ? 0 : 1, + gicv3_redist_affid(cs), intid); + return intid; +} + static int icc_highest_active_prio(GICv3CPUState *cs) { /* Calculate the current running priority based on the set bits @@ -177,6 +782,10 @@ static uint64_t icc_pmr_read(CPUARMState *env, const ARMCPRegInfo *ri) GICv3CPUState *cs = icc_cs_from_env(env); uint32_t value = cs->icc_pmr_el1; + if (icv_access(env, HCR_FMO | HCR_IMO)) { + return icv_pmr_read(env, ri); + } + if (arm_feature(env, ARM_FEATURE_EL3) && !arm_is_secure(env) && (env->cp15.scr_el3 & SCR_FIQ)) { /* NS access and Group 0 is inaccessible to NS: return the @@ -200,6 +809,10 @@ static void icc_pmr_write(CPUARMState *env, const ARMCPRegInfo *ri, { GICv3CPUState *cs = icc_cs_from_env(env); + if (icv_access(env, HCR_FMO | HCR_IMO)) { + return icv_pmr_write(env, ri, value); + } + trace_gicv3_icc_pmr_write(gicv3_redist_affid(cs), value); value &= 0xff; @@ -321,6 +934,10 @@ static uint64_t icc_iar0_read(CPUARMState *env, const ARMCPRegInfo *ri) GICv3CPUState *cs = icc_cs_from_env(env); uint64_t intid; + if (icv_access(env, HCR_FMO)) { + return icv_iar_read(env, ri); + } + if (!icc_hppi_can_preempt(cs)) { intid = INTID_SPURIOUS; } else { @@ -340,6 +957,10 @@ static uint64_t icc_iar1_read(CPUARMState *env, const ARMCPRegInfo *ri) GICv3CPUState *cs = icc_cs_from_env(env); uint64_t intid; + if (icv_access(env, HCR_IMO)) { + return icv_iar_read(env, ri); + } + if (!icc_hppi_can_preempt(cs)) { intid = INTID_SPURIOUS; } else { @@ -446,6 +1067,190 @@ static void icc_deactivate_irq(GICv3CPUState *cs, int irq) } } +static bool icv_eoi_split(CPUARMState *env, GICv3CPUState *cs) +{ + /* Return true if we should split priority drop and interrupt + * deactivation, ie whether the virtual EOIMode bit is set. + */ + return cs->ich_vmcr_el2 & ICH_VMCR_EL2_VEOIM; +} + +static int icv_find_active(GICv3CPUState *cs, int irq) +{ + /* Given an interrupt number for an active interrupt, return the index + * of the corresponding list register, or -1 if there is no match. + * Corresponds to FindActiveVirtualInterrupt pseudocode. + */ + int i; + + for (i = 0; i < cs->num_list_regs; i++) { + uint64_t lr = cs->ich_lr_el2[i]; + + if ((lr & ICH_LR_EL2_STATE_ACTIVE_BIT) && ich_lr_vintid(lr) == irq) { + return i; + } + } + + return -1; +} + +static void icv_deactivate_irq(GICv3CPUState *cs, int idx) +{ + /* Deactivate the interrupt in the specified list register index */ + uint64_t lr = cs->ich_lr_el2[idx]; + + if (lr & ICH_LR_EL2_HW) { + /* Deactivate the associated physical interrupt */ + int pirq = ich_lr_pintid(lr); + + if (pirq < INTID_SECURE) { + icc_deactivate_irq(cs, pirq); + } + } + + /* Clear the 'active' part of the state, so ActivePending->Pending + * and Active->Invalid. + */ + lr &= ~ICH_LR_EL2_STATE_ACTIVE_BIT; + cs->ich_lr_el2[idx] = lr; +} + +static void icv_increment_eoicount(GICv3CPUState *cs) +{ + /* Increment the EOICOUNT field in ICH_HCR_EL2 */ + int eoicount = extract64(cs->ich_hcr_el2, ICH_HCR_EL2_EOICOUNT_SHIFT, + ICH_HCR_EL2_EOICOUNT_LENGTH); + + cs->ich_hcr_el2 = deposit64(cs->ich_hcr_el2, ICH_HCR_EL2_EOICOUNT_SHIFT, + ICH_HCR_EL2_EOICOUNT_LENGTH, eoicount + 1); +} + +static int icv_drop_prio(GICv3CPUState *cs) +{ + /* Drop the priority of the currently active virtual interrupt + * (favouring group 0 if there is a set active bit at + * the same priority for both group 0 and group 1). + * Return the priority value for the bit we just cleared, + * or 0xff if no bits were set in the AP registers at all. + * Note that though the ich_apr[] are uint64_t only the low + * 32 bits are actually relevant. + */ + int i; + int aprmax = 1 << (cs->vprebits - 5); + + assert(aprmax <= ARRAY_SIZE(cs->ich_apr[0])); + + for (i = 0; i < aprmax; i++) { + uint64_t *papr0 = &cs->ich_apr[GICV3_G0][i]; + uint64_t *papr1 = &cs->ich_apr[GICV3_G1NS][i]; + int apr0count, apr1count; + + if (!*papr0 && !*papr1) { + continue; + } + + /* We can't just use the bit-twiddling hack icc_drop_prio() does + * because we need to return the bit number we cleared so + * it can be compared against the list register's priority field. + */ + apr0count = ctz32(*papr0); + apr1count = ctz32(*papr1); + + if (apr0count <= apr1count) { + *papr0 &= *papr0 - 1; + return (apr0count + i * 32) << (icv_min_vbpr(cs) + 1); + } else { + *papr1 &= *papr1 - 1; + return (apr1count + i * 32) << (icv_min_vbpr(cs) + 1); + } + } + return 0xff; +} + +static void icv_dir_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Deactivate interrupt */ + GICv3CPUState *cs = icc_cs_from_env(env); + int idx; + int irq = value & 0xffffff; + + trace_gicv3_icv_dir_write(gicv3_redist_affid(cs), value); + + if (irq >= cs->gic->num_irq) { + /* Also catches special interrupt numbers and LPIs */ + return; + } + + if (!icv_eoi_split(env, cs)) { + return; + } + + idx = icv_find_active(cs, irq); + + if (idx < 0) { + /* No list register matching this, so increment the EOI count + * (might trigger a maintenance interrupt) + */ + icv_increment_eoicount(cs); + } else { + icv_deactivate_irq(cs, idx); + } + + gicv3_cpuif_virt_update(cs); +} + +static void icv_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* End of Interrupt */ + GICv3CPUState *cs = icc_cs_from_env(env); + int irq = value & 0xffffff; + int grp = ri->crm == 8 ? GICV3_G0 : GICV3_G1NS; + int idx, dropprio; + + trace_gicv3_icv_eoir_write(ri->crm == 8 ? 0 : 1, + gicv3_redist_affid(cs), value); + + if (irq >= cs->gic->num_irq) { + /* Also catches special interrupt numbers and LPIs */ + return; + } + + /* We implement the IMPDEF choice of "drop priority before doing + * error checks" (because that lets us avoid scanning the AP + * registers twice). + */ + dropprio = icv_drop_prio(cs); + if (dropprio == 0xff) { + /* No active interrupt. It is CONSTRAINED UNPREDICTABLE + * whether the list registers are checked in this + * situation; we choose not to. + */ + return; + } + + idx = icv_find_active(cs, irq); + + if (idx < 0) { + /* No valid list register corresponding to EOI ID */ + icv_increment_eoicount(cs); + } else { + uint64_t lr = cs->ich_lr_el2[idx]; + int thisgrp = (lr & ICH_LR_EL2_GROUP) ? GICV3_G1NS : GICV3_G0; + int lr_gprio = ich_lr_prio(lr) & icv_gprio_mask(cs, grp); + + if (thisgrp == grp && lr_gprio == dropprio) { + if (!icv_eoi_split(env, cs)) { + /* Priority drop and deactivate not split: deactivate irq now */ + icv_deactivate_irq(cs, idx); + } + } + } + + gicv3_cpuif_virt_update(cs); +} + static void icc_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -454,6 +1259,11 @@ static void icc_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, int irq = value & 0xffffff; int grp; + if (icv_access(env, ri->crm == 8 ? HCR_FMO : HCR_IMO)) { + icv_eoir_write(env, ri, value); + return; + } + trace_gicv3_icc_eoir_write(ri->crm == 8 ? 0 : 1, gicv3_redist_affid(cs), value); @@ -496,8 +1306,13 @@ static void icc_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, static uint64_t icc_hppir0_read(CPUARMState *env, const ARMCPRegInfo *ri) { GICv3CPUState *cs = icc_cs_from_env(env); - uint64_t value = icc_hppir0_value(cs, env); + uint64_t value; + if (icv_access(env, HCR_FMO)) { + return icv_hppir_read(env, ri); + } + + value = icc_hppir0_value(cs, env); trace_gicv3_icc_hppir0_read(gicv3_redist_affid(cs), value); return value; } @@ -505,8 +1320,13 @@ static uint64_t icc_hppir0_read(CPUARMState *env, const ARMCPRegInfo *ri) static uint64_t icc_hppir1_read(CPUARMState *env, const ARMCPRegInfo *ri) { GICv3CPUState *cs = icc_cs_from_env(env); - uint64_t value = icc_hppir1_value(cs, env); + uint64_t value; + + if (icv_access(env, HCR_IMO)) { + return icv_hppir_read(env, ri); + } + value = icc_hppir1_value(cs, env); trace_gicv3_icc_hppir1_read(gicv3_redist_affid(cs), value); return value; } @@ -518,6 +1338,10 @@ static uint64_t icc_bpr_read(CPUARMState *env, const ARMCPRegInfo *ri) bool satinc = false; uint64_t bpr; + if (icv_access(env, grp == GICV3_G0 ? HCR_FMO : HCR_IMO)) { + return icv_bpr_read(env, ri); + } + if (grp == GICV3_G1 && gicv3_use_ns_bank(env)) { grp = GICV3_G1NS; } @@ -554,6 +1378,11 @@ static void icc_bpr_write(CPUARMState *env, const ARMCPRegInfo *ri, GICv3CPUState *cs = icc_cs_from_env(env); int grp = (ri->crm == 8) ? GICV3_G0 : GICV3_G1; + if (icv_access(env, grp == GICV3_G0 ? HCR_FMO : HCR_IMO)) { + icv_bpr_write(env, ri, value); + return; + } + trace_gicv3_icc_bpr_write(ri->crm == 8 ? 0 : 1, gicv3_redist_affid(cs), value); @@ -587,6 +1416,10 @@ static uint64_t icc_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) int regno = ri->opc2 & 3; int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1; + if (icv_access(env, grp == GICV3_G0 ? HCR_FMO : HCR_IMO)) { + return icv_ap_read(env, ri); + } + if (grp == GICV3_G1 && gicv3_use_ns_bank(env)) { grp = GICV3_G1NS; } @@ -605,6 +1438,11 @@ static void icc_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, int regno = ri->opc2 & 3; int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1; + if (icv_access(env, grp == GICV3_G0 ? HCR_FMO : HCR_IMO)) { + icv_ap_write(env, ri, value); + return; + } + trace_gicv3_icc_ap_write(ri->crm & 1, regno, gicv3_redist_affid(cs), value); if (grp == GICV3_G1 && gicv3_use_ns_bank(env)) { @@ -633,6 +1471,11 @@ static void icc_dir_write(CPUARMState *env, const ARMCPRegInfo *ri, bool irq_is_secure, single_sec_state, irq_is_grp0; bool route_fiq_to_el3, route_irq_to_el3, route_fiq_to_el2, route_irq_to_el2; + if (icv_access(env, HCR_FMO | HCR_IMO)) { + icv_dir_write(env, ri, value); + return; + } + trace_gicv3_icc_dir_write(gicv3_redist_affid(cs), value); if (irq >= cs->gic->num_irq) { @@ -704,7 +1547,13 @@ static void icc_dir_write(CPUARMState *env, const ARMCPRegInfo *ri, static uint64_t icc_rpr_read(CPUARMState *env, const ARMCPRegInfo *ri) { GICv3CPUState *cs = icc_cs_from_env(env); - int prio = icc_highest_active_prio(cs); + int prio; + + if (icv_access(env, HCR_FMO | HCR_IMO)) { + return icv_rpr_read(env, ri); + } + + prio = icc_highest_active_prio(cs); if (arm_feature(env, ARM_FEATURE_EL3) && !arm_is_secure(env) && (env->cp15.scr_el3 & SCR_FIQ)) { @@ -817,6 +1666,10 @@ static uint64_t icc_igrpen_read(CPUARMState *env, const ARMCPRegInfo *ri) int grp = ri->opc2 & 1 ? GICV3_G1 : GICV3_G0; uint64_t value; + if (icv_access(env, grp == GICV3_G0 ? HCR_FMO : HCR_IMO)) { + return icv_igrpen_read(env, ri); + } + if (grp == GICV3_G1 && gicv3_use_ns_bank(env)) { grp = GICV3_G1NS; } @@ -833,6 +1686,11 @@ static void icc_igrpen_write(CPUARMState *env, const ARMCPRegInfo *ri, GICv3CPUState *cs = icc_cs_from_env(env); int grp = ri->opc2 & 1 ? GICV3_G1 : GICV3_G0; + if (icv_access(env, grp == GICV3_G0 ? HCR_FMO : HCR_IMO)) { + icv_igrpen_write(env, ri, value); + return; + } + trace_gicv3_icc_igrpen_write(ri->opc2 & 1 ? 1 : 0, gicv3_redist_affid(cs), value); @@ -874,6 +1732,10 @@ static uint64_t icc_ctlr_el1_read(CPUARMState *env, const ARMCPRegInfo *ri) int bank = gicv3_use_ns_bank(env) ? GICV3_NS : GICV3_S; uint64_t value; + if (icv_access(env, HCR_FMO | HCR_IMO)) { + return icv_ctlr_read(env, ri); + } + value = cs->icc_ctlr_el1[bank]; trace_gicv3_icc_ctlr_read(gicv3_redist_affid(cs), value); return value; @@ -886,6 +1748,11 @@ static void icc_ctlr_el1_write(CPUARMState *env, const ARMCPRegInfo *ri, int bank = gicv3_use_ns_bank(env) ? GICV3_NS : GICV3_S; uint64_t mask; + if (icv_access(env, HCR_FMO | HCR_IMO)) { + icv_ctlr_write(env, ri, value); + return; + } + trace_gicv3_icc_ctlr_write(gicv3_redist_affid(cs), value); /* Only CBPR and EOIMODE can be RW; @@ -966,9 +1833,17 @@ static CPAccessResult gicv3_irqfiq_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { CPAccessResult r = CP_ACCESS_OK; + GICv3CPUState *cs = icc_cs_from_env(env); + int el = arm_current_el(env); + + if ((cs->ich_hcr_el2 & ICH_HCR_EL2_TC) && + el == 1 && !arm_is_secure_below_el3(env)) { + /* Takes priority over a possible EL3 trap */ + return CP_ACCESS_TRAP_EL2; + } if ((env->cp15.scr_el3 & (SCR_FIQ | SCR_IRQ)) == (SCR_FIQ | SCR_IRQ)) { - switch (arm_current_el(env)) { + switch (el) { case 1: if (arm_is_secure_below_el3(env) || ((env->cp15.hcr_el2 & (HCR_IMO | HCR_FMO)) == 0)) { @@ -994,13 +1869,47 @@ static CPAccessResult gicv3_irqfiq_access(CPUARMState *env, return r; } +static CPAccessResult gicv3_dir_access(CPUARMState *env, + const ARMCPRegInfo *ri, bool isread) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + + if ((cs->ich_hcr_el2 & ICH_HCR_EL2_TDIR) && + arm_current_el(env) == 1 && !arm_is_secure_below_el3(env)) { + /* Takes priority over a possible EL3 trap */ + return CP_ACCESS_TRAP_EL2; + } + + return gicv3_irqfiq_access(env, ri, isread); +} + +static CPAccessResult gicv3_sgi_access(CPUARMState *env, + const ARMCPRegInfo *ri, bool isread) +{ + if ((env->cp15.hcr_el2 & (HCR_IMO | HCR_FMO)) && + arm_current_el(env) == 1 && !arm_is_secure_below_el3(env)) { + /* Takes priority over a possible EL3 trap */ + return CP_ACCESS_TRAP_EL2; + } + + return gicv3_irqfiq_access(env, ri, isread); +} + static CPAccessResult gicv3_fiq_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { CPAccessResult r = CP_ACCESS_OK; + GICv3CPUState *cs = icc_cs_from_env(env); + int el = arm_current_el(env); + + if ((cs->ich_hcr_el2 & ICH_HCR_EL2_TALL0) && + el == 1 && !arm_is_secure_below_el3(env)) { + /* Takes priority over a possible EL3 trap */ + return CP_ACCESS_TRAP_EL2; + } if (env->cp15.scr_el3 & SCR_FIQ) { - switch (arm_current_el(env)) { + switch (el) { case 1: if (arm_is_secure_below_el3(env) || ((env->cp15.hcr_el2 & HCR_FMO) == 0)) { @@ -1030,9 +1939,17 @@ static CPAccessResult gicv3_irq_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { CPAccessResult r = CP_ACCESS_OK; + GICv3CPUState *cs = icc_cs_from_env(env); + int el = arm_current_el(env); + + if ((cs->ich_hcr_el2 & ICH_HCR_EL2_TALL1) && + el == 1 && !arm_is_secure_below_el3(env)) { + /* Takes priority over a possible EL3 trap */ + return CP_ACCESS_TRAP_EL2; + } if (env->cp15.scr_el3 & SCR_IRQ) { - switch (arm_current_el(env)) { + switch (el) { case 1: if (arm_is_secure_below_el3(env) || ((env->cp15.hcr_el2 & HCR_IMO) == 0)) { @@ -1081,6 +1998,13 @@ static void icc_reset(CPUARMState *env, const ARMCPRegInfo *ri) cs->icc_ctlr_el3 = ICC_CTLR_EL3_NDS | ICC_CTLR_EL3_A3V | (1 << ICC_CTLR_EL3_IDBITS_SHIFT) | (7 << ICC_CTLR_EL3_PRIBITS_SHIFT); + + memset(cs->ich_apr, 0, sizeof(cs->ich_apr)); + cs->ich_hcr_el2 = 0; + memset(cs->ich_lr_el2, 0, sizeof(cs->ich_lr_el2)); + cs->ich_vmcr_el2 = ICH_VMCR_EL2_VFIQEN | + (icv_min_vbpr(cs) << ICH_VMCR_EL2_VBPR1_SHIFT) | + (icv_min_vbpr(cs) << ICH_VMCR_EL2_VBPR0_SHIFT); } static const ARMCPRegInfo gicv3_cpuif_reginfo[] = { @@ -1118,35 +2042,35 @@ static const ARMCPRegInfo gicv3_cpuif_reginfo[] = { .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 8, .opc2 = 3, .type = ARM_CP_IO | ARM_CP_NO_RAW, .access = PL1_RW, .accessfn = gicv3_fiq_access, - .fieldoffset = offsetof(GICv3CPUState, icc_bpr[GICV3_G0]), + .readfn = icc_bpr_read, .writefn = icc_bpr_write, }, { .name = "ICC_AP0R0_EL1", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 8, .opc2 = 4, .type = ARM_CP_IO | ARM_CP_NO_RAW, .access = PL1_RW, .accessfn = gicv3_fiq_access, - .fieldoffset = offsetof(GICv3CPUState, icc_apr[GICV3_G0][0]), + .readfn = icc_ap_read, .writefn = icc_ap_write, }, { .name = "ICC_AP0R1_EL1", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 8, .opc2 = 5, .type = ARM_CP_IO | ARM_CP_NO_RAW, .access = PL1_RW, .accessfn = gicv3_fiq_access, - .fieldoffset = offsetof(GICv3CPUState, icc_apr[GICV3_G0][1]), + .readfn = icc_ap_read, .writefn = icc_ap_write, }, { .name = "ICC_AP0R2_EL1", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 8, .opc2 = 6, .type = ARM_CP_IO | ARM_CP_NO_RAW, .access = PL1_RW, .accessfn = gicv3_fiq_access, - .fieldoffset = offsetof(GICv3CPUState, icc_apr[GICV3_G0][2]), + .readfn = icc_ap_read, .writefn = icc_ap_write, }, { .name = "ICC_AP0R3_EL1", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 8, .opc2 = 7, .type = ARM_CP_IO | ARM_CP_NO_RAW, .access = PL1_RW, .accessfn = gicv3_fiq_access, - .fieldoffset = offsetof(GICv3CPUState, icc_apr[GICV3_G0][3]), + .readfn = icc_ap_read, .writefn = icc_ap_write, }, /* All the ICC_AP1R*_EL1 registers are banked */ @@ -1181,7 +2105,7 @@ static const ARMCPRegInfo gicv3_cpuif_reginfo[] = { { .name = "ICC_DIR_EL1", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 11, .opc2 = 1, .type = ARM_CP_IO | ARM_CP_NO_RAW, - .access = PL1_W, .accessfn = gicv3_irqfiq_access, + .access = PL1_W, .accessfn = gicv3_dir_access, .writefn = icc_dir_write, }, { .name = "ICC_RPR_EL1", .state = ARM_CP_STATE_BOTH, @@ -1193,37 +2117,37 @@ static const ARMCPRegInfo gicv3_cpuif_reginfo[] = { { .name = "ICC_SGI1R_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 11, .opc2 = 5, .type = ARM_CP_IO | ARM_CP_NO_RAW, - .access = PL1_W, .accessfn = gicv3_irqfiq_access, + .access = PL1_W, .accessfn = gicv3_sgi_access, .writefn = icc_sgi1r_write, }, { .name = "ICC_SGI1R", .cp = 15, .opc1 = 0, .crm = 12, .type = ARM_CP_64BIT | ARM_CP_IO | ARM_CP_NO_RAW, - .access = PL1_W, .accessfn = gicv3_irqfiq_access, + .access = PL1_W, .accessfn = gicv3_sgi_access, .writefn = icc_sgi1r_write, }, { .name = "ICC_ASGI1R_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 11, .opc2 = 6, .type = ARM_CP_IO | ARM_CP_NO_RAW, - .access = PL1_W, .accessfn = gicv3_irqfiq_access, + .access = PL1_W, .accessfn = gicv3_sgi_access, .writefn = icc_asgi1r_write, }, { .name = "ICC_ASGI1R", .cp = 15, .opc1 = 1, .crm = 12, .type = ARM_CP_64BIT | ARM_CP_IO | ARM_CP_NO_RAW, - .access = PL1_W, .accessfn = gicv3_irqfiq_access, + .access = PL1_W, .accessfn = gicv3_sgi_access, .writefn = icc_asgi1r_write, }, { .name = "ICC_SGI0R_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 11, .opc2 = 7, .type = ARM_CP_IO | ARM_CP_NO_RAW, - .access = PL1_W, .accessfn = gicv3_irqfiq_access, + .access = PL1_W, .accessfn = gicv3_sgi_access, .writefn = icc_sgi0r_write, }, { .name = "ICC_SGI0R", .cp = 15, .opc1 = 2, .crm = 12, .type = ARM_CP_64BIT | ARM_CP_IO | ARM_CP_NO_RAW, - .access = PL1_W, .accessfn = gicv3_irqfiq_access, + .access = PL1_W, .accessfn = gicv3_sgi_access, .writefn = icc_sgi0r_write, }, { .name = "ICC_IAR1_EL1", .state = ARM_CP_STATE_BOTH, @@ -1275,7 +2199,7 @@ static const ARMCPRegInfo gicv3_cpuif_reginfo[] = { .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 12, .opc2 = 6, .type = ARM_CP_IO | ARM_CP_NO_RAW, .access = PL1_RW, .accessfn = gicv3_fiq_access, - .fieldoffset = offsetof(GICv3CPUState, icc_igrpen[GICV3_G0]), + .readfn = icc_igrpen_read, .writefn = icc_igrpen_write, }, /* This register is banked */ @@ -1299,7 +2223,6 @@ static const ARMCPRegInfo gicv3_cpuif_reginfo[] = { .opc0 = 3, .opc1 = 6, .crn = 12, .crm = 12, .opc2 = 4, .type = ARM_CP_IO | ARM_CP_NO_RAW, .access = PL3_RW, - .fieldoffset = offsetof(GICv3CPUState, icc_ctlr_el3), .readfn = icc_ctlr_el3_read, .writefn = icc_ctlr_el3_write, }, @@ -1322,6 +2245,306 @@ static const ARMCPRegInfo gicv3_cpuif_reginfo[] = { REGINFO_SENTINEL }; +static uint64_t ich_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + int regno = ri->opc2 & 3; + int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1NS; + uint64_t value; + + value = cs->ich_apr[grp][regno]; + trace_gicv3_ich_ap_read(ri->crm & 1, regno, gicv3_redist_affid(cs), value); + return value; +} + +static void ich_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + int regno = ri->opc2 & 3; + int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1NS; + + trace_gicv3_ich_ap_write(ri->crm & 1, regno, gicv3_redist_affid(cs), value); + + cs->ich_apr[grp][regno] = value & 0xFFFFFFFFU; + gicv3_cpuif_virt_update(cs); +} + +static uint64_t ich_hcr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + uint64_t value = cs->ich_hcr_el2; + + trace_gicv3_ich_hcr_read(gicv3_redist_affid(cs), value); + return value; +} + +static void ich_hcr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + + trace_gicv3_ich_hcr_write(gicv3_redist_affid(cs), value); + + value &= ICH_HCR_EL2_EN | ICH_HCR_EL2_UIE | ICH_HCR_EL2_LRENPIE | + ICH_HCR_EL2_NPIE | ICH_HCR_EL2_VGRP0EIE | ICH_HCR_EL2_VGRP0DIE | + ICH_HCR_EL2_VGRP1EIE | ICH_HCR_EL2_VGRP1DIE | ICH_HCR_EL2_TC | + ICH_HCR_EL2_TALL0 | ICH_HCR_EL2_TALL1 | ICH_HCR_EL2_TSEI | + ICH_HCR_EL2_TDIR | ICH_HCR_EL2_EOICOUNT_MASK; + + cs->ich_hcr_el2 = value; + gicv3_cpuif_virt_update(cs); +} + +static uint64_t ich_vmcr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + uint64_t value = cs->ich_vmcr_el2; + + trace_gicv3_ich_vmcr_read(gicv3_redist_affid(cs), value); + return value; +} + +static void ich_vmcr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + + trace_gicv3_ich_vmcr_write(gicv3_redist_affid(cs), value); + + value &= ICH_VMCR_EL2_VENG0 | ICH_VMCR_EL2_VENG1 | ICH_VMCR_EL2_VCBPR | + ICH_VMCR_EL2_VEOIM | ICH_VMCR_EL2_VBPR1_MASK | + ICH_VMCR_EL2_VBPR0_MASK | ICH_VMCR_EL2_VPMR_MASK; + value |= ICH_VMCR_EL2_VFIQEN; + + cs->ich_vmcr_el2 = value; + /* Enforce "writing BPRs to less than minimum sets them to the minimum" + * by reading and writing back the fields. + */ + write_vbpr(cs, GICV3_G1, read_vbpr(cs, GICV3_G0)); + write_vbpr(cs, GICV3_G1, read_vbpr(cs, GICV3_G1)); + + gicv3_cpuif_virt_update(cs); +} + +static uint64_t ich_lr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + int regno = ri->opc2 | ((ri->crm & 1) << 3); + uint64_t value; + + /* This read function handles all of: + * 64-bit reads of the whole LR + * 32-bit reads of the low half of the LR + * 32-bit reads of the high half of the LR + */ + if (ri->state == ARM_CP_STATE_AA32) { + if (ri->crm >= 14) { + value = extract64(cs->ich_lr_el2[regno], 32, 32); + trace_gicv3_ich_lrc_read(regno, gicv3_redist_affid(cs), value); + } else { + value = extract64(cs->ich_lr_el2[regno], 0, 32); + trace_gicv3_ich_lr32_read(regno, gicv3_redist_affid(cs), value); + } + } else { + value = cs->ich_lr_el2[regno]; + trace_gicv3_ich_lr_read(regno, gicv3_redist_affid(cs), value); + } + + return value; +} + +static void ich_lr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + int regno = ri->opc2 | ((ri->crm & 1) << 3); + + /* This write function handles all of: + * 64-bit writes to the whole LR + * 32-bit writes to the low half of the LR + * 32-bit writes to the high half of the LR + */ + if (ri->state == ARM_CP_STATE_AA32) { + if (ri->crm >= 14) { + trace_gicv3_ich_lrc_write(regno, gicv3_redist_affid(cs), value); + value = deposit64(cs->ich_lr_el2[regno], 32, 32, value); + } else { + trace_gicv3_ich_lr32_write(regno, gicv3_redist_affid(cs), value); + value = deposit64(cs->ich_lr_el2[regno], 0, 32, value); + } + } else { + trace_gicv3_ich_lr_write(regno, gicv3_redist_affid(cs), value); + } + + /* Enforce RES0 bits in priority field */ + if (cs->vpribits < 8) { + value = deposit64(value, ICH_LR_EL2_PRIORITY_SHIFT, + 8 - cs->vpribits, 0); + } + + cs->ich_lr_el2[regno] = value; + gicv3_cpuif_virt_update(cs); +} + +static uint64_t ich_vtr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + uint64_t value; + + value = ((cs->num_list_regs - 1) << ICH_VTR_EL2_LISTREGS_SHIFT) + | ICH_VTR_EL2_TDS | ICH_VTR_EL2_NV4 | ICH_VTR_EL2_A3V + | (1 << ICH_VTR_EL2_IDBITS_SHIFT) + | ((cs->vprebits - 1) << ICH_VTR_EL2_PREBITS_SHIFT) + | ((cs->vpribits - 1) << ICH_VTR_EL2_PRIBITS_SHIFT); + + trace_gicv3_ich_vtr_read(gicv3_redist_affid(cs), value); + return value; +} + +static uint64_t ich_misr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + uint64_t value = maintenance_interrupt_state(cs); + + trace_gicv3_ich_misr_read(gicv3_redist_affid(cs), value); + return value; +} + +static uint64_t ich_eisr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + uint64_t value = eoi_maintenance_interrupt_state(cs, NULL); + + trace_gicv3_ich_eisr_read(gicv3_redist_affid(cs), value); + return value; +} + +static uint64_t ich_elrsr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + uint64_t value = 0; + int i; + + for (i = 0; i < cs->num_list_regs; i++) { + uint64_t lr = cs->ich_lr_el2[i]; + + if ((lr & ICH_LR_EL2_STATE_MASK) == 0 && + ((lr & ICH_LR_EL2_HW) == 1 || (lr & ICH_LR_EL2_EOI) == 0)) { + value |= (1 << i); + } + } + + trace_gicv3_ich_elrsr_read(gicv3_redist_affid(cs), value); + return value; +} + +static const ARMCPRegInfo gicv3_cpuif_hcr_reginfo[] = { + { .name = "ICH_AP0R0_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 8, .opc2 = 0, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_RW, + .readfn = ich_ap_read, + .writefn = ich_ap_write, + }, + { .name = "ICH_AP1R0_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 9, .opc2 = 0, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_RW, + .readfn = ich_ap_read, + .writefn = ich_ap_write, + }, + { .name = "ICH_HCR_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 11, .opc2 = 0, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_RW, + .readfn = ich_hcr_read, + .writefn = ich_hcr_write, + }, + { .name = "ICH_VTR_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 11, .opc2 = 1, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_R, + .readfn = ich_vtr_read, + }, + { .name = "ICH_MISR_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 11, .opc2 = 2, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_R, + .readfn = ich_misr_read, + }, + { .name = "ICH_EISR_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 11, .opc2 = 3, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_R, + .readfn = ich_eisr_read, + }, + { .name = "ICH_ELRSR_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 11, .opc2 = 5, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_R, + .readfn = ich_elrsr_read, + }, + { .name = "ICH_VMCR_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 11, .opc2 = 7, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_RW, + .readfn = ich_vmcr_read, + .writefn = ich_vmcr_write, + }, + REGINFO_SENTINEL +}; + +static const ARMCPRegInfo gicv3_cpuif_ich_apxr1_reginfo[] = { + { .name = "ICH_AP0R1_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 8, .opc2 = 1, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_RW, + .readfn = ich_ap_read, + .writefn = ich_ap_write, + }, + { .name = "ICH_AP1R1_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 9, .opc2 = 1, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_RW, + .readfn = ich_ap_read, + .writefn = ich_ap_write, + }, + REGINFO_SENTINEL +}; + +static const ARMCPRegInfo gicv3_cpuif_ich_apxr23_reginfo[] = { + { .name = "ICH_AP0R2_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 8, .opc2 = 2, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_RW, + .readfn = ich_ap_read, + .writefn = ich_ap_write, + }, + { .name = "ICH_AP0R3_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 8, .opc2 = 3, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_RW, + .readfn = ich_ap_read, + .writefn = ich_ap_write, + }, + { .name = "ICH_AP1R2_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 9, .opc2 = 2, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_RW, + .readfn = ich_ap_read, + .writefn = ich_ap_write, + }, + { .name = "ICH_AP1R3_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 9, .opc2 = 3, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_RW, + .readfn = ich_ap_read, + .writefn = ich_ap_write, + }, + REGINFO_SENTINEL +}; + static void gicv3_cpuif_el_change_hook(ARMCPU *cpu, void *opaque) { GICv3CPUState *cs = opaque; @@ -1350,6 +2573,59 @@ void gicv3_init_cpuif(GICv3State *s) * to need to register anyway. */ define_arm_cp_regs(cpu, gicv3_cpuif_reginfo); + if (arm_feature(&cpu->env, ARM_FEATURE_EL2) + && cpu->gic_num_lrs) { + int j; + + cs->maintenance_irq = cpu->gicv3_maintenance_interrupt; + + cs->num_list_regs = cpu->gic_num_lrs; + cs->vpribits = cpu->gic_vpribits; + cs->vprebits = cpu->gic_vprebits; + + /* Check against architectural constraints: getting these + * wrong would be a bug in the CPU code defining these, + * and the implementation relies on them holding. + */ + g_assert(cs->vprebits <= cs->vpribits); + g_assert(cs->vprebits >= 5 && cs->vprebits <= 7); + g_assert(cs->vpribits >= 5 && cs->vpribits <= 8); + + define_arm_cp_regs(cpu, gicv3_cpuif_hcr_reginfo); + + for (j = 0; j < cs->num_list_regs; j++) { + /* Note that the AArch64 LRs are 64-bit; the AArch32 LRs + * are split into two cp15 regs, LR (the low part, with the + * same encoding as the AArch64 LR) and LRC (the high part). + */ + ARMCPRegInfo lr_regset[] = { + { .name = "ICH_LRn_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, + .crm = 12 + (j >> 3), .opc2 = j & 7, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_RW, + .readfn = ich_lr_read, + .writefn = ich_lr_write, + }, + { .name = "ICH_LRCn_EL2", .state = ARM_CP_STATE_AA32, + .cp = 15, .opc1 = 4, .crn = 12, + .crm = 14 + (j >> 3), .opc2 = j & 7, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL2_RW, + .readfn = ich_lr_read, + .writefn = ich_lr_write, + }, + REGINFO_SENTINEL + }; + define_arm_cp_regs(cpu, lr_regset); + } + if (cs->vprebits >= 6) { + define_arm_cp_regs(cpu, gicv3_cpuif_ich_apxr1_reginfo); + } + if (cs->vprebits == 7) { + define_arm_cp_regs(cpu, gicv3_cpuif_ich_apxr23_reginfo); + } + } arm_register_el_change_hook(cpu, gicv3_cpuif_el_change_hook, cs); } } diff --git a/hw/intc/arm_gicv3_its_kvm.c b/hw/intc/arm_gicv3_its_kvm.c index fc246e0cb5..bd4f3aafc6 100644 --- a/hw/intc/arm_gicv3_its_kvm.c +++ b/hw/intc/arm_gicv3_its_kvm.c @@ -56,6 +56,19 @@ static int kvm_its_send_msi(GICv3ITSState *s, uint32_t value, uint16_t devid) static void kvm_arm_its_realize(DeviceState *dev, Error **errp) { GICv3ITSState *s = ARM_GICV3_ITS_COMMON(dev); + Error *local_err = NULL; + + /* + * Block migration of a KVM GICv3 ITS device: the API for saving and + * restoring the state in the kernel is not yet available + */ + error_setg(&s->migration_blocker, "vITS migration is not implemented"); + migrate_add_blocker(s->migration_blocker, &local_err); + if (local_err) { + error_propagate(errp, local_err); + error_free(s->migration_blocker); + return; + } s->dev_fd = kvm_create_device(kvm_state, KVM_DEV_TYPE_ARM_VGIC_ITS, false); if (s->dev_fd < 0) { @@ -73,13 +86,6 @@ static void kvm_arm_its_realize(DeviceState *dev, Error **errp) gicv3_its_init_mmio(s, NULL); - /* - * Block migration of a KVM GICv3 ITS device: the API for saving and - * restoring the state in the kernel is not yet available - */ - error_setg(&s->migration_blocker, "vITS migration is not implemented"); - migrate_add_blocker(s->migration_blocker); - kvm_msi_use_devid = true; kvm_gsi_direct_mapping = false; kvm_msi_via_irqfd_allowed = kvm_irqfds_enabled(); diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c index 199a439ccf..d69dc47370 100644 --- a/hw/intc/arm_gicv3_kvm.c +++ b/hw/intc/arm_gicv3_kvm.c @@ -103,6 +103,18 @@ static void kvm_arm_gicv3_realize(DeviceState *dev, Error **errp) gicv3_init_irqs_and_mmio(s, kvm_arm_gicv3_set_irq, NULL); + /* Block migration of a KVM GICv3 device: the API for saving and restoring + * the state in the kernel is not yet finalised in the kernel or + * implemented in QEMU. + */ + error_setg(&s->migration_blocker, "vGICv3 migration is not implemented"); + migrate_add_blocker(s->migration_blocker, &local_err); + if (local_err) { + error_propagate(errp, local_err); + error_free(s->migration_blocker); + return; + } + /* Try to create the device via the device control API */ s->dev_fd = kvm_create_device(kvm_state, KVM_DEV_TYPE_ARM_VGIC_V3, false); if (s->dev_fd < 0) { @@ -122,13 +134,6 @@ static void kvm_arm_gicv3_realize(DeviceState *dev, Error **errp) kvm_arm_register_device(&s->iomem_redist, -1, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_REDIST, s->dev_fd); - /* Block migration of a KVM GICv3 device: the API for saving and restoring - * the state in the kernel is not yet finalised in the kernel or - * implemented in QEMU. - */ - error_setg(&s->migration_blocker, "vGICv3 migration is not implemented"); - migrate_add_blocker(s->migration_blocker); - if (kvm_has_gsi_routing()) { /* set up irq routing */ kvm_init_irq_routing(kvm_state); diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index 8f3567edaa..aeb801d133 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -159,6 +159,85 @@ #define ICC_CTLR_EL3_A3V (1U << 15) #define ICC_CTLR_EL3_NDS (1U << 17) +#define ICH_VMCR_EL2_VENG0_SHIFT 0 +#define ICH_VMCR_EL2_VENG0 (1U << ICH_VMCR_EL2_VENG0_SHIFT) +#define ICH_VMCR_EL2_VENG1_SHIFT 1 +#define ICH_VMCR_EL2_VENG1 (1U << ICH_VMCR_EL2_VENG1_SHIFT) +#define ICH_VMCR_EL2_VACKCTL (1U << 2) +#define ICH_VMCR_EL2_VFIQEN (1U << 3) +#define ICH_VMCR_EL2_VCBPR_SHIFT 4 +#define ICH_VMCR_EL2_VCBPR (1U << ICH_VMCR_EL2_VCBPR_SHIFT) +#define ICH_VMCR_EL2_VEOIM_SHIFT 9 +#define ICH_VMCR_EL2_VEOIM (1U << ICH_VMCR_EL2_VEOIM_SHIFT) +#define ICH_VMCR_EL2_VBPR1_SHIFT 18 +#define ICH_VMCR_EL2_VBPR1_LENGTH 3 +#define ICH_VMCR_EL2_VBPR1_MASK (0x7U << ICH_VMCR_EL2_VBPR1_SHIFT) +#define ICH_VMCR_EL2_VBPR0_SHIFT 21 +#define ICH_VMCR_EL2_VBPR0_LENGTH 3 +#define ICH_VMCR_EL2_VBPR0_MASK (0x7U << ICH_VMCR_EL2_VBPR0_SHIFT) +#define ICH_VMCR_EL2_VPMR_SHIFT 24 +#define ICH_VMCR_EL2_VPMR_LENGTH 8 +#define ICH_VMCR_EL2_VPMR_MASK (0xffU << ICH_VMCR_EL2_VPMR_SHIFT) + +#define ICH_HCR_EL2_EN (1U << 0) +#define ICH_HCR_EL2_UIE (1U << 1) +#define ICH_HCR_EL2_LRENPIE (1U << 2) +#define ICH_HCR_EL2_NPIE (1U << 3) +#define ICH_HCR_EL2_VGRP0EIE (1U << 4) +#define ICH_HCR_EL2_VGRP0DIE (1U << 5) +#define ICH_HCR_EL2_VGRP1EIE (1U << 6) +#define ICH_HCR_EL2_VGRP1DIE (1U << 7) +#define ICH_HCR_EL2_TC (1U << 10) +#define ICH_HCR_EL2_TALL0 (1U << 11) +#define ICH_HCR_EL2_TALL1 (1U << 12) +#define ICH_HCR_EL2_TSEI (1U << 13) +#define ICH_HCR_EL2_TDIR (1U << 14) +#define ICH_HCR_EL2_EOICOUNT_SHIFT 27 +#define ICH_HCR_EL2_EOICOUNT_LENGTH 5 +#define ICH_HCR_EL2_EOICOUNT_MASK (0x1fU << ICH_HCR_EL2_EOICOUNT_SHIFT) + +#define ICH_LR_EL2_VINTID_SHIFT 0 +#define ICH_LR_EL2_VINTID_LENGTH 32 +#define ICH_LR_EL2_VINTID_MASK (0xffffffffULL << ICH_LR_EL2_VINTID_SHIFT) +#define ICH_LR_EL2_PINTID_SHIFT 32 +#define ICH_LR_EL2_PINTID_LENGTH 10 +#define ICH_LR_EL2_PINTID_MASK (0x3ffULL << ICH_LR_EL2_PINTID_SHIFT) +/* Note that EOI shares with the top bit of the pINTID field */ +#define ICH_LR_EL2_EOI (1ULL << 41) +#define ICH_LR_EL2_PRIORITY_SHIFT 48 +#define ICH_LR_EL2_PRIORITY_LENGTH 8 +#define ICH_LR_EL2_PRIORITY_MASK (0xffULL << ICH_LR_EL2_PRIORITY_SHIFT) +#define ICH_LR_EL2_GROUP (1ULL << 60) +#define ICH_LR_EL2_HW (1ULL << 61) +#define ICH_LR_EL2_STATE_SHIFT 62 +#define ICH_LR_EL2_STATE_LENGTH 2 +#define ICH_LR_EL2_STATE_MASK (3ULL << ICH_LR_EL2_STATE_SHIFT) +/* values for the state field: */ +#define ICH_LR_EL2_STATE_INVALID 0 +#define ICH_LR_EL2_STATE_PENDING 1 +#define ICH_LR_EL2_STATE_ACTIVE 2 +#define ICH_LR_EL2_STATE_ACTIVE_PENDING 3 +#define ICH_LR_EL2_STATE_PENDING_BIT (1ULL << ICH_LR_EL2_STATE_SHIFT) +#define ICH_LR_EL2_STATE_ACTIVE_BIT (2ULL << ICH_LR_EL2_STATE_SHIFT) + +#define ICH_MISR_EL2_EOI (1U << 0) +#define ICH_MISR_EL2_U (1U << 1) +#define ICH_MISR_EL2_LRENP (1U << 2) +#define ICH_MISR_EL2_NP (1U << 3) +#define ICH_MISR_EL2_VGRP0E (1U << 4) +#define ICH_MISR_EL2_VGRP0D (1U << 5) +#define ICH_MISR_EL2_VGRP1E (1U << 6) +#define ICH_MISR_EL2_VGRP1D (1U << 7) + +#define ICH_VTR_EL2_LISTREGS_SHIFT 0 +#define ICH_VTR_EL2_TDS (1U << 19) +#define ICH_VTR_EL2_NV4 (1U << 20) +#define ICH_VTR_EL2_A3V (1U << 21) +#define ICH_VTR_EL2_SEIS (1U << 22) +#define ICH_VTR_EL2_IDBITS_SHIFT 23 +#define ICH_VTR_EL2_PREBITS_SHIFT 26 +#define ICH_VTR_EL2_PRIBITS_SHIFT 29 + /* Special interrupt IDs */ #define INTID_SECURE 1020 #define INTID_NONSECURE 1021 diff --git a/hw/intc/ioapic.c b/hw/intc/ioapic.c index ea7ea0bce8..9047b8950a 100644 --- a/hw/intc/ioapic.c +++ b/hw/intc/ioapic.c @@ -33,6 +33,7 @@ #include "target/i386/cpu.h" #include "hw/i386/apic-msidef.h" #include "hw/i386/x86-iommu.h" +#include "trace.h" //#define DEBUG_IOAPIC @@ -115,6 +116,7 @@ static void ioapic_service(IOAPICCommonState *s) s->irr &= ~mask; } else { coalesce = s->ioredtbl[i] & IOAPIC_LVT_REMOTE_IRR; + trace_ioapic_set_remote_irr(i); s->ioredtbl[i] |= IOAPIC_LVT_REMOTE_IRR; } @@ -220,6 +222,8 @@ void ioapic_eoi_broadcast(int vector) uint64_t entry; int i, n; + trace_ioapic_eoi_broadcast(vector); + for (i = 0; i < MAX_IOAPICS; i++) { s = ioapics[i]; if (!s) { @@ -229,6 +233,7 @@ void ioapic_eoi_broadcast(int vector) entry = s->ioredtbl[n]; if ((entry & IOAPIC_LVT_REMOTE_IRR) && (entry & IOAPIC_VECTOR_MASK) == vector) { + trace_ioapic_clear_remote_irr(n, vector); s->ioredtbl[n] = entry & ~IOAPIC_LVT_REMOTE_IRR; if (!(entry & IOAPIC_LVT_MASKED) && (s->irr & (1 << n))) { ioapic_service(s); @@ -256,7 +261,9 @@ ioapic_mem_read(void *opaque, hwaddr addr, unsigned int size) int index; uint32_t val = 0; - switch (addr & 0xff) { + addr &= 0xff; + + switch (addr) { case IOAPIC_IOREGSEL: val = s->ioregsel; break; @@ -286,6 +293,9 @@ ioapic_mem_read(void *opaque, hwaddr addr, unsigned int size) DPRINTF("read: %08x = %08x\n", s->ioregsel, val); break; } + + trace_ioapic_mem_read(addr, size, val); + return val; } @@ -324,7 +334,10 @@ ioapic_mem_write(void *opaque, hwaddr addr, uint64_t val, IOAPICCommonState *s = opaque; int index; - switch (addr & 0xff) { + addr &= 0xff; + trace_ioapic_mem_write(addr, size, val); + + switch (addr) { case IOAPIC_IOREGSEL: s->ioregsel = val; break; @@ -426,6 +439,11 @@ static void ioapic_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); k->realize = ioapic_realize; + /* + * If APIC is in kernel, we need to update the kernel cache after + * migration, otherwise first 24 gsi routes will be invalid. + */ + k->post_load = ioapic_update_kvm_routes; dc->reset = ioapic_reset_common; dc->props = ioapic_properties; } diff --git a/hw/intc/ioapic_common.c b/hw/intc/ioapic_common.c index 1b7ec5ec20..97c4f9c2df 100644 --- a/hw/intc/ioapic_common.c +++ b/hw/intc/ioapic_common.c @@ -58,7 +58,8 @@ void ioapic_print_redtbl(Monitor *mon, IOAPICCommonState *s) uint32_t remote_irr = 0; int i; - monitor_printf(mon, "ioapic id=0x%02x sel=0x%02x", s->id, s->ioregsel); + monitor_printf(mon, "ioapic ver=0x%x id=0x%02x sel=0x%02x", + s->version, s->id, s->ioregsel); if (s->ioregsel) { monitor_printf(mon, " (redir[%u])\n", (s->ioregsel - IOAPIC_REG_REDTBL_BASE) >> 1); diff --git a/hw/intc/nios2_iic.c b/hw/intc/nios2_iic.c new file mode 100644 index 0000000000..818ab1b315 --- /dev/null +++ b/hw/intc/nios2_iic.c @@ -0,0 +1,103 @@ +/* + * QEMU Altera Internal Interrupt Controller. + * + * Copyright (c) 2012 Chris Wulff <crwulff@gmail.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/lgpl-2.1.html> + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qapi/error.h" + +#include "hw/sysbus.h" +#include "cpu.h" + +#define TYPE_ALTERA_IIC "altera,iic" +#define ALTERA_IIC(obj) \ + OBJECT_CHECK(AlteraIIC, (obj), TYPE_ALTERA_IIC) + +typedef struct AlteraIIC { + SysBusDevice parent_obj; + void *cpu; + qemu_irq parent_irq; +} AlteraIIC; + +static void update_irq(AlteraIIC *pv) +{ + CPUNios2State *env = &((Nios2CPU *)(pv->cpu))->env; + + qemu_set_irq(pv->parent_irq, + env->regs[CR_IPENDING] & env->regs[CR_IENABLE]); +} + +static void irq_handler(void *opaque, int irq, int level) +{ + AlteraIIC *pv = opaque; + CPUNios2State *env = &((Nios2CPU *)(pv->cpu))->env; + + env->regs[CR_IPENDING] &= ~(1 << irq); + env->regs[CR_IPENDING] |= !!level << irq; + + update_irq(pv); +} + +static void altera_iic_init(Object *obj) +{ + AlteraIIC *pv = ALTERA_IIC(obj); + + qdev_init_gpio_in(DEVICE(pv), irq_handler, 32); + sysbus_init_irq(SYS_BUS_DEVICE(obj), &pv->parent_irq); +} + +static Property altera_iic_properties[] = { + DEFINE_PROP_PTR("cpu", AlteraIIC, cpu), + DEFINE_PROP_END_OF_LIST(), +}; + +static void altera_iic_realize(DeviceState *dev, Error **errp) +{ + struct AlteraIIC *pv = ALTERA_IIC(dev); + + if (!pv->cpu) { + error_setg(errp, "altera,iic: CPU not connected"); + return; + } +} + +static void altera_iic_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->props = altera_iic_properties; + /* Reason: pointer property "cpu" */ + dc->cannot_instantiate_with_device_add_yet = true; + dc->realize = altera_iic_realize; +} + +static TypeInfo altera_iic_info = { + .name = "altera,iic", + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(AlteraIIC), + .instance_init = altera_iic_init, + .class_init = altera_iic_class_init, +}; + +static void altera_iic_register(void) +{ + type_register_static(&altera_iic_info); +} + +type_init(altera_iic_register) diff --git a/hw/intc/s390_flic_kvm.c b/hw/intc/s390_flic_kvm.c index 21ac2e2dcd..da8e4dfab6 100644 --- a/hw/intc/s390_flic_kvm.c +++ b/hw/intc/s390_flic_kvm.c @@ -201,7 +201,7 @@ static int kvm_s390_register_io_adapter(S390FLICState *fs, uint32_t id, .addr = (uint64_t)&adapter, }; - if (!kvm_check_extension(kvm_state, KVM_CAP_IRQ_ROUTING)) { + if (!kvm_gsi_routing_enabled()) { /* nothing to do */ return 0; } @@ -226,7 +226,7 @@ static int kvm_s390_io_adapter_map(S390FLICState *fs, uint32_t id, KVMS390FLICState *flic = KVM_S390_FLIC(fs); int r; - if (!kvm_check_extension(kvm_state, KVM_CAP_IRQ_ROUTING)) { + if (!kvm_gsi_routing_enabled()) { /* nothing to do */ return 0; } @@ -286,7 +286,8 @@ static void kvm_s390_release_adapter_routes(S390FLICState *fs, * increase until buffer is sufficient or maxium size is * reached */ -static void kvm_flic_save(QEMUFile *f, void *opaque, size_t size) +static int kvm_flic_save(QEMUFile *f, void *opaque, size_t size, + VMStateField *field, QJSON *vmdesc) { KVMS390FLICState *flic = opaque; int len = FLIC_SAVE_INITIAL_SIZE; @@ -319,6 +320,8 @@ static void kvm_flic_save(QEMUFile *f, void *opaque, size_t size) count * sizeof(struct kvm_s390_irq)); } g_free(buf); + + return 0; } /** @@ -331,7 +334,8 @@ static void kvm_flic_save(QEMUFile *f, void *opaque, size_t size) * Note: Do nothing when no interrupts where stored * in QEMUFile */ -static int kvm_flic_load(QEMUFile *f, void *opaque, size_t size) +static int kvm_flic_load(QEMUFile *f, void *opaque, size_t size, + VMStateField *field) { uint64_t len = 0; uint64_t count = 0; diff --git a/hw/intc/trace-events b/hw/intc/trace-events index 340f617761..92a6171692 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -14,6 +14,13 @@ apic_deliver_irq(uint8_t dest, uint8_t dest_mode, uint8_t delivery_mode, uint8_t apic_mem_readl(uint64_t addr, uint32_t val) "%"PRIx64" = %08x" apic_mem_writel(uint64_t addr, uint32_t val) "%"PRIx64" = %08x" +# hw/intc/ioapic.c +ioapic_set_remote_irr(int n) "set remote irr for pin %d" +ioapic_clear_remote_irr(int n, int vector) "clear remote irr for pin %d vector %d" +ioapic_eoi_broadcast(int vector) "EOI broadcast for vector %d" +ioapic_mem_read(uint8_t addr, uint8_t size, uint32_t val) "ioapic mem read addr 0x%"PRIx8" size 0x%"PRIx8" retval 0x%"PRIx32 +ioapic_mem_write(uint8_t addr, uint8_t size, uint32_t val) "ioapic mem write addr 0x%"PRIx8" size 0x%"PRIx8" val 0x%"PRIx32 + # hw/intc/slavio_intctl.c slavio_intctl_mem_readl(uint32_t cpu, uint64_t addr, uint32_t ret) "read cpu %d reg 0x%"PRIx64" = %x" slavio_intctl_mem_writel(uint32_t cpu, uint64_t addr, uint32_t val) "write cpu %d reg 0x%"PRIx64" = %x" @@ -107,6 +114,39 @@ gicv3_icc_hppir0_read(uint32_t cpu, uint64_t val) "GICv3 ICC_HPPIR0 read cpu %x gicv3_icc_hppir1_read(uint32_t cpu, uint64_t val) "GICv3 ICC_HPPIR1 read cpu %x value 0x%" PRIx64 gicv3_icc_dir_write(uint32_t cpu, uint64_t val) "GICv3 ICC_DIR write cpu %x value 0x%" PRIx64 gicv3_icc_rpr_read(uint32_t cpu, uint64_t val) "GICv3 ICC_RPR read cpu %x value 0x%" PRIx64 +gicv3_ich_ap_read(int grp, int regno, uint32_t cpu, uint64_t val) "GICv3 ICH_AP%dR%d read cpu %x value 0x%" PRIx64 +gicv3_ich_ap_write(int grp, int regno, uint32_t cpu, uint64_t val) "GICv3 ICH_AP%dR%d write cpu %x value 0x%" PRIx64 +gicv3_ich_hcr_read(uint32_t cpu, uint64_t val) "GICv3 ICH_HCR_EL2 read cpu %x value 0x%" PRIx64 +gicv3_ich_hcr_write(uint32_t cpu, uint64_t val) "GICv3 ICH_HCR_EL2 write cpu %x value 0x%" PRIx64 +gicv3_ich_vmcr_read(uint32_t cpu, uint64_t val) "GICv3 ICH_VMCR_EL2 read cpu %x value 0x%" PRIx64 +gicv3_ich_vmcr_write(uint32_t cpu, uint64_t val) "GICv3 ICH_VMCR_EL2 write cpu %x value 0x%" PRIx64 +gicv3_ich_lr_read(int regno, uint32_t cpu, uint64_t val) "GICv3 ICH_LR%d_EL2 read cpu %x value 0x%" PRIx64 +gicv3_ich_lr32_read(int regno, uint32_t cpu, uint32_t val) "GICv3 ICH_LR%d read cpu %x value 0x%" PRIx32 +gicv3_ich_lrc_read(int regno, uint32_t cpu, uint32_t val) "GICv3 ICH_LRC%d read cpu %x value 0x%" PRIx32 +gicv3_ich_lr_write(int regno, uint32_t cpu, uint64_t val) "GICv3 ICH_LR%d_EL2 write cpu %x value 0x%" PRIx64 +gicv3_ich_lr32_write(int regno, uint32_t cpu, uint32_t val) "GICv3 ICH_LR%d write cpu %x value 0x%" PRIx32 +gicv3_ich_lrc_write(int regno, uint32_t cpu, uint32_t val) "GICv3 ICH_LRC%d write cpu %x value 0x%" PRIx32 +gicv3_ich_vtr_read(uint32_t cpu, uint64_t val) "GICv3 ICH_VTR read cpu %x value 0x%" PRIx64 +gicv3_ich_misr_read(uint32_t cpu, uint64_t val) "GICv3 ICH_MISR read cpu %x value 0x%" PRIx64 +gicv3_ich_eisr_read(uint32_t cpu, uint64_t val) "GICv3 ICH_EISR read cpu %x value 0x%" PRIx64 +gicv3_ich_elrsr_read(uint32_t cpu, uint64_t val) "GICv3 ICH_ELRSR read cpu %x value 0x%" PRIx64 +gicv3_icv_ap_read(int grp, int regno, uint32_t cpu, uint64_t val) "GICv3 ICV_AP%dR%d read cpu %x value 0x%" PRIx64 +gicv3_icv_ap_write(int grp, int regno, uint32_t cpu, uint64_t val) "GICv3 ICV_AP%dR%d write cpu %x value 0x%" PRIx64 +gicv3_icv_bpr_read(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_BPR%d read cpu %x value 0x%" PRIx64 +gicv3_icv_bpr_write(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_BPR%d write cpu %x value 0x%" PRIx64 +gicv3_icv_pmr_read(uint32_t cpu, uint64_t val) "GICv3 ICV_PMR read cpu %x value 0x%" PRIx64 +gicv3_icv_pmr_write(uint32_t cpu, uint64_t val) "GICv3 ICV_PMR write cpu %x value 0x%" PRIx64 +gicv3_icv_igrpen_read(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_IGRPEN%d read cpu %x value 0x%" PRIx64 +gicv3_icv_igrpen_write(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_IGRPEN%d write cpu %x value 0x%" PRIx64 +gicv3_icv_ctlr_read(uint32_t cpu, uint64_t val) "GICv3 ICV_CTLR read cpu %x value 0x%" PRIx64 +gicv3_icv_ctlr_write(uint32_t cpu, uint64_t val) "GICv3 ICV_CTLR write cpu %x value 0x%" PRIx64 +gicv3_icv_rpr_read(uint32_t cpu, uint64_t val) "GICv3 ICV_RPR read cpu %x value 0x%" PRIx64 +gicv3_icv_hppir_read(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_HPPIR%d read cpu %x value 0x%" PRIx64 +gicv3_icv_dir_write(uint32_t cpu, uint64_t val) "GICv3 ICV_DIR write cpu %x value 0x%" PRIx64 +gicv3_icv_iar_read(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_IAR%d read cpu %x value 0x%" PRIx64 +gicv3_icv_eoir_write(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_EOIR%d write cpu %x value 0x%" PRIx64 +gicv3_cpuif_virt_update(uint32_t cpuid, int idx) "GICv3 CPU i/f %x virt HPPI update LR index %d" +gicv3_cpuif_virt_set_irqs(uint32_t cpuid, int fiqlevel, int irqlevel, int maintlevel) "GICv3 CPU i/f %x virt HPPI update: setting FIQ %d IRQ %d maintenance-irq %d" # hw/intc/arm_gicv3_dist.c gicv3_dist_read(uint64_t offset, uint64_t data, unsigned size, bool secure) "GICv3 distributor read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u secure %d" diff --git a/hw/isa/isa-bus.c b/hw/isa/isa-bus.c index 9d07b118c0..0ffbc8dd28 100644 --- a/hw/isa/isa-bus.c +++ b/hw/isa/isa-bus.c @@ -219,6 +219,7 @@ static void isabus_bridge_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); dc->fw_name = "isa"; } diff --git a/hw/lm32/lm32_hwsetup.h b/hw/lm32/lm32_hwsetup.h index 23e18784df..a01f6bc5df 100644 --- a/hw/lm32/lm32_hwsetup.h +++ b/hw/lm32/lm32_hwsetup.h @@ -75,7 +75,7 @@ static inline void hwsetup_create_rom(HWSetup *hw, hwaddr base) { rom_add_blob("hwsetup", hw->data, TARGET_PAGE_SIZE, - TARGET_PAGE_SIZE, base, NULL, NULL, NULL, NULL); + TARGET_PAGE_SIZE, base, NULL, NULL, NULL, NULL, true); } static inline void hwsetup_add_u8(HWSetup *hw, uint8_t u) diff --git a/hw/m68k/mcf5208.c b/hw/m68k/mcf5208.c index 3438314c35..bad1d332ed 100644 --- a/hw/m68k/mcf5208.c +++ b/hw/m68k/mcf5208.c @@ -11,6 +11,7 @@ #include "cpu.h" #include "hw/hw.h" #include "hw/m68k/mcf.h" +#include "hw/m68k/mcf_fec.h" #include "qemu/timer.h" #include "hw/ptimer.h" #include "sysemu/sysemu.h" @@ -18,6 +19,7 @@ #include "net/net.h" #include "hw/boards.h" #include "hw/loader.h" +#include "hw/sysbus.h" #include "elf.h" #include "exec/address-spaces.h" @@ -192,6 +194,26 @@ static void mcf5208_sys_init(MemoryRegion *address_space, qemu_irq *pic) } } +static void mcf_fec_init(MemoryRegion *sysmem, NICInfo *nd, hwaddr base, + qemu_irq *irqs) +{ + DeviceState *dev; + SysBusDevice *s; + int i; + + qemu_check_nic_model(nd, TYPE_MCF_FEC_NET); + dev = qdev_create(NULL, TYPE_MCF_FEC_NET); + qdev_set_nic_properties(dev, nd); + qdev_init_nofail(dev); + + s = SYS_BUS_DEVICE(dev); + for (i = 0; i < FEC_NUM_IRQ; i++) { + sysbus_connect_irq(s, i, irqs[i]); + } + + memory_region_add_subregion(sysmem, base, sysbus_mmio_get_region(s, 0)); +} + static void mcf5208evb_init(MachineState *machine) { ram_addr_t ram_size = machine->ram_size; @@ -243,9 +265,10 @@ static void mcf5208evb_init(MachineState *machine) fprintf(stderr, "Too many NICs\n"); exit(1); } - if (nd_table[0].used) + if (nd_table[0].used) { mcf_fec_init(address_space_mem, &nd_table[0], 0xfc030000, pic + 36); + } /* 0xfc000000 SCM. */ /* 0xfc004000 XBS. */ diff --git a/hw/misc/aspeed_scu.c b/hw/misc/aspeed_scu.c index b1f3e6f6b8..95022d3607 100644 --- a/hw/misc/aspeed_scu.c +++ b/hw/misc/aspeed_scu.c @@ -86,7 +86,7 @@ #define BMC_DEV_ID TO_REG(0x1A4) #define PROT_KEY_UNLOCK 0x1688A8A8 -#define SCU_IO_REGION_SIZE 0x20000 +#define SCU_IO_REGION_SIZE 0x1000 static const uint32_t ast2400_a0_resets[ASPEED_SCU_NR_REGS] = { [SYS_RST_CTRL] = 0xFFCFFEDCU, @@ -231,6 +231,7 @@ static void aspeed_scu_reset(DeviceState *dev) switch (s->silicon_rev) { case AST2400_A0_SILICON_REV: + case AST2400_A1_SILICON_REV: reset = ast2400_a0_resets; break; case AST2500_A0_SILICON_REV: @@ -249,6 +250,7 @@ static void aspeed_scu_reset(DeviceState *dev) static uint32_t aspeed_silicon_revs[] = { AST2400_A0_SILICON_REV, + AST2400_A1_SILICON_REV, AST2500_A0_SILICON_REV, AST2500_A1_SILICON_REV, }; diff --git a/hw/misc/aspeed_sdmc.c b/hw/misc/aspeed_sdmc.c index 8830dc084c..5f3ac0b6f6 100644 --- a/hw/misc/aspeed_sdmc.c +++ b/hw/misc/aspeed_sdmc.c @@ -119,6 +119,7 @@ static void aspeed_sdmc_write(void *opaque, hwaddr addr, uint64_t data, /* Make sure readonly bits are kept */ switch (s->silicon_rev) { case AST2400_A0_SILICON_REV: + case AST2400_A1_SILICON_REV: data &= ~ASPEED_SDMC_READONLY_MASK; break; case AST2500_A0_SILICON_REV: @@ -193,6 +194,7 @@ static void aspeed_sdmc_reset(DeviceState *dev) /* Set ram size bit and defaults values */ switch (s->silicon_rev) { case AST2400_A0_SILICON_REV: + case AST2400_A1_SILICON_REV: s->regs[R_CONF] |= ASPEED_SDMC_VGA_COMPAT | ASPEED_SDMC_DRAM_SIZE(s->ram_bits); @@ -224,6 +226,7 @@ static void aspeed_sdmc_realize(DeviceState *dev, Error **errp) switch (s->silicon_rev) { case AST2400_A0_SILICON_REV: + case AST2400_A1_SILICON_REV: s->ram_bits = ast2400_rambits(s); break; case AST2500_A0_SILICON_REV: diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c index abeaf3da08..fd14d7a07e 100644 --- a/hw/misc/ivshmem.c +++ b/hw/misc/ivshmem.c @@ -840,6 +840,7 @@ static void ivshmem_common_realize(PCIDevice *dev, Error **errp) uint8_t *pci_conf; uint8_t attr = PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_PREFETCH; + Error *local_err = NULL; /* IRQFD requires MSI */ if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD) && @@ -903,9 +904,6 @@ static void ivshmem_common_realize(PCIDevice *dev, Error **errp) } } - vmstate_register_ram(s->ivshmem_bar2, DEVICE(s)); - pci_register_bar(PCI_DEVICE(s), 2, attr, s->ivshmem_bar2); - if (s->master == ON_OFF_AUTO_AUTO) { s->master = s->vm_id == 0 ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF; } @@ -913,8 +911,16 @@ static void ivshmem_common_realize(PCIDevice *dev, Error **errp) if (!ivshmem_is_master(s)) { error_setg(&s->migration_blocker, "Migration is disabled when using feature 'peer mode' in device 'ivshmem'"); - migrate_add_blocker(s->migration_blocker); + migrate_add_blocker(s->migration_blocker, &local_err); + if (local_err) { + error_propagate(errp, local_err); + error_free(s->migration_blocker); + return; + } } + + vmstate_register_ram(s->ivshmem_bar2, DEVICE(s)); + pci_register_bar(PCI_DEVICE(s), 2, attr, s->ivshmem_bar2); } static void ivshmem_exit(PCIDevice *dev) diff --git a/hw/misc/tmp105.c b/hw/misc/tmp105.c index f5c2472b5b..04e83787d4 100644 --- a/hw/misc/tmp105.c +++ b/hw/misc/tmp105.c @@ -176,7 +176,7 @@ static int tmp105_tx(I2CSlave *i2c, uint8_t data) return 0; } -static void tmp105_event(I2CSlave *i2c, enum i2c_event event) +static int tmp105_event(I2CSlave *i2c, enum i2c_event event) { TMP105State *s = TMP105(i2c); @@ -185,6 +185,7 @@ static void tmp105_event(I2CSlave *i2c, enum i2c_event event) } s->len = 0; + return 0; } static int tmp105_post_load(void *opaque, int version_id) diff --git a/hw/misc/vmport.c b/hw/misc/vmport.c index c763811a9f..be40930b8b 100644 --- a/hw/misc/vmport.c +++ b/hw/misc/vmport.c @@ -25,7 +25,7 @@ #include "hw/hw.h" #include "hw/isa/isa.h" #include "hw/i386/pc.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" #include "hw/qdev.h" //#define VMPORT_DEBUG diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index 7915732f74..e99d4544a2 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -896,7 +896,7 @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) DB_PRINT("config bufsize: %d packet size: %ld\n", rxbufsize, size); - /* Find which queue we are targetting */ + /* Find which queue we are targeting */ q = get_queue_from_screen(s, rxbuf_ptr, rxbufsize); while (bytes_to_copy) { diff --git a/hw/net/dp8393x.c b/hw/net/dp8393x.c index 17f0338d1c..efa33ad40a 100644 --- a/hw/net/dp8393x.c +++ b/hw/net/dp8393x.c @@ -174,6 +174,52 @@ typedef struct dp8393xState { AddressSpace as; } dp8393xState; +/* Accessor functions for values which are formed by + * concatenating two 16 bit device registers. By putting these + * in their own functions with a uint32_t return type we avoid the + * pitfall of implicit sign extension where ((x << 16) | y) is a + * signed 32 bit integer that might get sign-extended to a 64 bit integer. + */ +static uint32_t dp8393x_cdp(dp8393xState *s) +{ + return (s->regs[SONIC_URRA] << 16) | s->regs[SONIC_CDP]; +} + +static uint32_t dp8393x_crba(dp8393xState *s) +{ + return (s->regs[SONIC_CRBA1] << 16) | s->regs[SONIC_CRBA0]; +} + +static uint32_t dp8393x_crda(dp8393xState *s) +{ + return (s->regs[SONIC_URDA] << 16) | s->regs[SONIC_CRDA]; +} + +static uint32_t dp8393x_rbwc(dp8393xState *s) +{ + return (s->regs[SONIC_RBWC1] << 16) | s->regs[SONIC_RBWC0]; +} + +static uint32_t dp8393x_rrp(dp8393xState *s) +{ + return (s->regs[SONIC_URRA] << 16) | s->regs[SONIC_RRP]; +} + +static uint32_t dp8393x_tsa(dp8393xState *s) +{ + return (s->regs[SONIC_TSA1] << 16) | s->regs[SONIC_TSA0]; +} + +static uint32_t dp8393x_ttda(dp8393xState *s) +{ + return (s->regs[SONIC_UTDA] << 16) | s->regs[SONIC_TTDA]; +} + +static uint32_t dp8393x_wt(dp8393xState *s) +{ + return s->regs[SONIC_WT1] << 16 | s->regs[SONIC_WT0]; +} + static void dp8393x_update_irq(dp8393xState *s) { int level = (s->regs[SONIC_IMR] & s->regs[SONIC_ISR]) ? 1 : 0; @@ -203,8 +249,7 @@ static void dp8393x_do_load_cam(dp8393xState *s) while (s->regs[SONIC_CDC] & 0x1f) { /* Fill current entry */ - address_space_rw(&s->as, - (s->regs[SONIC_URRA] << 16) | s->regs[SONIC_CDP], + address_space_rw(&s->as, dp8393x_cdp(s), MEMTXATTRS_UNSPECIFIED, (uint8_t *)data, size, 0); s->cam[index][0] = data[1 * width] & 0xff; s->cam[index][1] = data[1 * width] >> 8; @@ -222,8 +267,7 @@ static void dp8393x_do_load_cam(dp8393xState *s) } /* Read CAM enable */ - address_space_rw(&s->as, - (s->regs[SONIC_URRA] << 16) | s->regs[SONIC_CDP], + address_space_rw(&s->as, dp8393x_cdp(s), MEMTXATTRS_UNSPECIFIED, (uint8_t *)data, size, 0); s->regs[SONIC_CE] = data[0 * width]; DPRINTF("load cam done. cam enable mask 0x%04x\n", s->regs[SONIC_CE]); @@ -242,8 +286,7 @@ static void dp8393x_do_read_rra(dp8393xState *s) /* Read memory */ width = (s->regs[SONIC_DCR] & SONIC_DCR_DW) ? 2 : 1; size = sizeof(uint16_t) * 4 * width; - address_space_rw(&s->as, - (s->regs[SONIC_URRA] << 16) | s->regs[SONIC_RRP], + address_space_rw(&s->as, dp8393x_rrp(s), MEMTXATTRS_UNSPECIFIED, (uint8_t *)data, size, 0); /* Update SONIC registers */ @@ -292,7 +335,7 @@ static void dp8393x_set_next_tick(dp8393xState *s) return; } - ticks = s->regs[SONIC_WT1] << 16 | s->regs[SONIC_WT0]; + ticks = dp8393x_wt(s); s->wt_last_update = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); delay = NANOSECONDS_PER_SECOND * ticks / 5000000; timer_mod(s->watchdog, s->wt_last_update + delay); @@ -309,7 +352,7 @@ static void dp8393x_update_wt_regs(dp8393xState *s) } elapsed = s->wt_last_update - qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - val = s->regs[SONIC_WT1] << 16 | s->regs[SONIC_WT0]; + val = dp8393x_wt(s); val -= elapsed / 5000000; s->regs[SONIC_WT1] = (val >> 16) & 0xffff; s->regs[SONIC_WT0] = (val >> 0) & 0xffff; @@ -356,12 +399,11 @@ static void dp8393x_do_transmit_packets(dp8393xState *s) while (1) { /* Read memory */ - DPRINTF("Transmit packet at %08x\n", - (s->regs[SONIC_UTDA] << 16) | s->regs[SONIC_CTDA]); size = sizeof(uint16_t) * 6 * width; s->regs[SONIC_TTDA] = s->regs[SONIC_CTDA]; + DPRINTF("Transmit packet at %08x\n", dp8393x_ttda(s)); address_space_rw(&s->as, - ((s->regs[SONIC_UTDA] << 16) | s->regs[SONIC_TTDA]) + sizeof(uint16_t) * width, + dp8393x_ttda(s) + sizeof(uint16_t) * width, MEMTXATTRS_UNSPECIFIED, (uint8_t *)data, size, 0); tx_len = 0; @@ -386,8 +428,7 @@ static void dp8393x_do_transmit_packets(dp8393xState *s) if (tx_len + len > sizeof(s->tx_buffer)) { len = sizeof(s->tx_buffer) - tx_len; } - address_space_rw(&s->as, - (s->regs[SONIC_TSA1] << 16) | s->regs[SONIC_TSA0], + address_space_rw(&s->as, dp8393x_tsa(s), MEMTXATTRS_UNSPECIFIED, &s->tx_buffer[tx_len], len, 0); tx_len += len; @@ -396,7 +437,7 @@ static void dp8393x_do_transmit_packets(dp8393xState *s) /* Read next fragment details */ size = sizeof(uint16_t) * 3 * width; address_space_rw(&s->as, - ((s->regs[SONIC_UTDA] << 16) | s->regs[SONIC_TTDA]) + sizeof(uint16_t) * (4 + 3 * i) * width, + dp8393x_ttda(s) + sizeof(uint16_t) * (4 + 3 * i) * width, MEMTXATTRS_UNSPECIFIED, (uint8_t *)data, size, 0); s->regs[SONIC_TSA0] = data[0 * width]; s->regs[SONIC_TSA1] = data[1 * width]; @@ -430,14 +471,16 @@ static void dp8393x_do_transmit_packets(dp8393xState *s) data[0 * width] = s->regs[SONIC_TCR] & 0x0fff; /* status */ size = sizeof(uint16_t) * width; address_space_rw(&s->as, - (s->regs[SONIC_UTDA] << 16) | s->regs[SONIC_TTDA], + dp8393x_ttda(s), MEMTXATTRS_UNSPECIFIED, (uint8_t *)data, size, 1); if (!(s->regs[SONIC_CR] & SONIC_CR_HTX)) { /* Read footer of packet */ size = sizeof(uint16_t) * width; address_space_rw(&s->as, - ((s->regs[SONIC_UTDA] << 16) | s->regs[SONIC_TTDA]) + sizeof(uint16_t) * (4 + 3 * s->regs[SONIC_TFC]) * width, + dp8393x_ttda(s) + + sizeof(uint16_t) * + (4 + 3 * s->regs[SONIC_TFC]) * width, MEMTXATTRS_UNSPECIFIED, (uint8_t *)data, size, 0); s->regs[SONIC_CTDA] = data[0 * width] & ~0x1; if (data[0 * width] & 0x1) { @@ -700,7 +743,7 @@ static ssize_t dp8393x_receive(NetClientState *nc, const uint8_t * buf, if (s->regs[SONIC_LLFA] & 0x1) { /* Are we still in resource exhaustion? */ size = sizeof(uint16_t) * 1 * width; - address = ((s->regs[SONIC_URDA] << 16) | s->regs[SONIC_CRDA]) + sizeof(uint16_t) * 5 * width; + address = dp8393x_crda(s) + sizeof(uint16_t) * 5 * width; address_space_rw(&s->as, address, MEMTXATTRS_UNSPECIFIED, (uint8_t *)data, size, 0); if (data[0 * width] & 0x1) { @@ -719,8 +762,8 @@ static ssize_t dp8393x_receive(NetClientState *nc, const uint8_t * buf, checksum = cpu_to_le32(crc32(0, buf, rx_len)); /* Put packet into RBA */ - DPRINTF("Receive packet at %08x\n", (s->regs[SONIC_CRBA1] << 16) | s->regs[SONIC_CRBA0]); - address = (s->regs[SONIC_CRBA1] << 16) | s->regs[SONIC_CRBA0]; + DPRINTF("Receive packet at %08x\n", dp8393x_crba(s)); + address = dp8393x_crba(s); address_space_rw(&s->as, address, MEMTXATTRS_UNSPECIFIED, (uint8_t *)buf, rx_len, 1); address += rx_len; @@ -729,13 +772,13 @@ static ssize_t dp8393x_receive(NetClientState *nc, const uint8_t * buf, rx_len += 4; s->regs[SONIC_CRBA1] = address >> 16; s->regs[SONIC_CRBA0] = address & 0xffff; - available = (s->regs[SONIC_RBWC1] << 16) | s->regs[SONIC_RBWC0]; + available = dp8393x_rbwc(s); available -= rx_len / 2; s->regs[SONIC_RBWC1] = available >> 16; s->regs[SONIC_RBWC0] = available & 0xffff; /* Update status */ - if (((s->regs[SONIC_RBWC1] << 16) | s->regs[SONIC_RBWC0]) < s->regs[SONIC_EOBC]) { + if (dp8393x_rbwc(s) < s->regs[SONIC_EOBC]) { s->regs[SONIC_RCR] |= SONIC_RCR_LPKT; } s->regs[SONIC_RCR] |= packet_type; @@ -746,20 +789,19 @@ static ssize_t dp8393x_receive(NetClientState *nc, const uint8_t * buf, } /* Write status to memory */ - DPRINTF("Write status at %08x\n", (s->regs[SONIC_URDA] << 16) | s->regs[SONIC_CRDA]); + DPRINTF("Write status at %08x\n", dp8393x_crda(s)); data[0 * width] = s->regs[SONIC_RCR]; /* status */ data[1 * width] = rx_len; /* byte count */ data[2 * width] = s->regs[SONIC_TRBA0]; /* pkt_ptr0 */ data[3 * width] = s->regs[SONIC_TRBA1]; /* pkt_ptr1 */ data[4 * width] = s->regs[SONIC_RSC]; /* seq_no */ size = sizeof(uint16_t) * 5 * width; - address_space_rw(&s->as, (s->regs[SONIC_URDA] << 16) | s->regs[SONIC_CRDA], + address_space_rw(&s->as, dp8393x_crda(s), MEMTXATTRS_UNSPECIFIED, (uint8_t *)data, size, 1); /* Move to next descriptor */ size = sizeof(uint16_t) * width; - address_space_rw(&s->as, - ((s->regs[SONIC_URDA] << 16) | s->regs[SONIC_CRDA]) + sizeof(uint16_t) * 5 * width, + address_space_rw(&s->as, dp8393x_crda(s) + sizeof(uint16_t) * 5 * width, MEMTXATTRS_UNSPECIFIED, (uint8_t *)data, size, 0); s->regs[SONIC_LLFA] = data[0 * width]; if (s->regs[SONIC_LLFA] & 0x1) { @@ -767,8 +809,7 @@ static ssize_t dp8393x_receive(NetClientState *nc, const uint8_t * buf, s->regs[SONIC_ISR] |= SONIC_ISR_RDE; } else { data[0 * width] = 0; /* in_use */ - address_space_rw(&s->as, - ((s->regs[SONIC_URDA] << 16) | s->regs[SONIC_CRDA]) + sizeof(uint16_t) * 6 * width, + address_space_rw(&s->as, dp8393x_crda(s) + sizeof(uint16_t) * 6 * width, MEMTXATTRS_UNSPECIFIED, (uint8_t *)data, sizeof(uint16_t), 1); s->regs[SONIC_CRDA] = s->regs[SONIC_LLFA]; s->regs[SONIC_ISR] |= SONIC_ISR_PKTRX; diff --git a/hw/net/e1000e.c b/hw/net/e1000e.c index 4994e1ca00..0e9a25b7ab 100644 --- a/hw/net/e1000e.c +++ b/hw/net/e1000e.c @@ -472,7 +472,8 @@ static void e1000e_pci_realize(PCIDevice *pci_dev, Error **errp) hw_error("Failed to initialize PM capability"); } - if (pcie_aer_init(pci_dev, e1000e_aer_offset, PCI_ERR_SIZEOF) < 0) { + if (pcie_aer_init(pci_dev, PCI_ERR_VER, e1000e_aer_offset, + PCI_ERR_SIZEOF, NULL) < 0) { hw_error("Failed to initialize AER capability"); } @@ -592,7 +593,7 @@ static const VMStateDescription e1000e_vmstate = { .pre_save = e1000e_pre_save, .post_load = e1000e_post_load, .fields = (VMStateField[]) { - VMSTATE_PCIE_DEVICE(parent_obj, E1000EState), + VMSTATE_PCI_DEVICE(parent_obj, E1000EState), VMSTATE_MSIX(parent_obj, E1000EState), VMSTATE_UINT32(ioaddr, E1000EState), diff --git a/hw/net/fsl_etsec/rings.c b/hw/net/fsl_etsec/rings.c index 54c01275d4..d0f93eebfc 100644 --- a/hw/net/fsl_etsec/rings.c +++ b/hw/net/fsl_etsec/rings.c @@ -358,25 +358,24 @@ void etsec_walk_tx_ring(eTSEC *etsec, int ring_nbr) /* Save flags before BD update */ bd_flags = bd.flags; - if (bd_flags & BD_TX_READY) { - process_tx_bd(etsec, &bd); - - /* Write back BD after update */ - write_buffer_descriptor(etsec, bd_addr, &bd); + if (!(bd_flags & BD_TX_READY)) { + break; } + process_tx_bd(etsec, &bd); + /* Write back BD after update */ + write_buffer_descriptor(etsec, bd_addr, &bd); + /* Wrap or next BD */ if (bd_flags & BD_WRAP) { bd_addr = ring_base; } else { bd_addr += sizeof(eTSEC_rxtx_bd); } + } while (TRUE); - } while (bd_addr != ring_base); - - bd_addr = ring_base; - - /* Save the Buffer Descriptor Pointers to current bd */ + /* Save the Buffer Descriptor Pointers to last bd that was not + * succesfully closed */ etsec->regs[TBPTR0 + ring_nbr].value = bd_addr; /* Set transmit halt THLTx */ diff --git a/hw/net/mcf_fec.c b/hw/net/mcf_fec.c index 4025eb3b33..a3eca7e0f5 100644 --- a/hw/net/mcf_fec.c +++ b/hw/net/mcf_fec.c @@ -9,7 +9,9 @@ #include "hw/hw.h" #include "net/net.h" #include "hw/m68k/mcf.h" +#include "hw/m68k/mcf_fec.h" #include "hw/net/mii.h" +#include "hw/sysbus.h" /* For crc32 */ #include <zlib.h> #include "exec/address-spaces.h" @@ -27,9 +29,10 @@ do { printf("mcf_fec: " fmt , ## __VA_ARGS__); } while (0) #define FEC_MAX_FRAME_SIZE 2032 typedef struct { - MemoryRegion *sysmem; + SysBusDevice parent_obj; + MemoryRegion iomem; - qemu_irq *irq; + qemu_irq irq[FEC_NUM_IRQ]; NICState *nic; NICConf conf; uint32_t irq_state; @@ -68,7 +71,6 @@ typedef struct { #define FEC_RESET 1 /* Map interrupt flags onto IRQ lines. */ -#define FEC_NUM_IRQ 13 static const uint32_t mcf_fec_irq_map[FEC_NUM_IRQ] = { FEC_INT_TXF, FEC_INT_TXB, @@ -208,8 +210,10 @@ static void mcf_fec_enable_rx(mcf_fec_state *s) } } -static void mcf_fec_reset(mcf_fec_state *s) +static void mcf_fec_reset(DeviceState *dev) { + mcf_fec_state *s = MCF_FEC_NET(dev); + s->eir = 0; s->eimr = 0; s->rx_enabled = 0; @@ -330,7 +334,7 @@ static void mcf_fec_write(void *opaque, hwaddr addr, s->ecr = value; if (value & FEC_RESET) { DPRINTF("Reset\n"); - mcf_fec_reset(s); + mcf_fec_reset(opaque); } if ((s->ecr & FEC_EN) == 0) { s->rx_enabled = 0; @@ -513,24 +517,55 @@ static NetClientInfo net_mcf_fec_info = { .receive = mcf_fec_receive, }; -void mcf_fec_init(MemoryRegion *sysmem, NICInfo *nd, - hwaddr base, qemu_irq *irq) +static void mcf_fec_realize(DeviceState *dev, Error **errp) { - mcf_fec_state *s; + mcf_fec_state *s = MCF_FEC_NET(dev); + + s->nic = qemu_new_nic(&net_mcf_fec_info, &s->conf, + object_get_typename(OBJECT(dev)), dev->id, s); + qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a); +} - qemu_check_nic_model(nd, "mcf_fec"); +static void mcf_fec_instance_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + mcf_fec_state *s = MCF_FEC_NET(obj); + int i; + + memory_region_init_io(&s->iomem, obj, &mcf_fec_ops, s, "fec", 0x400); + sysbus_init_mmio(sbd, &s->iomem); + for (i = 0; i < FEC_NUM_IRQ; i++) { + sysbus_init_irq(sbd, &s->irq[i]); + } +} - s = (mcf_fec_state *)g_malloc0(sizeof(mcf_fec_state)); - s->sysmem = sysmem; - s->irq = irq; +static Property mcf_fec_properties[] = { + DEFINE_NIC_PROPERTIES(mcf_fec_state, conf), + DEFINE_PROP_END_OF_LIST(), +}; - memory_region_init_io(&s->iomem, NULL, &mcf_fec_ops, s, "fec", 0x400); - memory_region_add_subregion(sysmem, base, &s->iomem); +static void mcf_fec_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); - s->conf.macaddr = nd->macaddr; - s->conf.peers.ncs[0] = nd->netdev; + set_bit(DEVICE_CATEGORY_NETWORK, dc->categories); + dc->realize = mcf_fec_realize; + dc->desc = "MCF Fast Ethernet Controller network device"; + dc->reset = mcf_fec_reset; + dc->props = mcf_fec_properties; +} - s->nic = qemu_new_nic(&net_mcf_fec_info, &s->conf, nd->model, nd->name, s); +static const TypeInfo mcf_fec_info = { + .name = TYPE_MCF_FEC_NET, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(mcf_fec_state), + .instance_init = mcf_fec_instance_init, + .class_init = mcf_fec_class_init, +}; - qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a); +static void mcf_fec_register_types(void) +{ + type_register_static(&mcf_fec_info); } + +type_init(mcf_fec_register_types) diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c index f05e59c85f..671c7e48c6 100644 --- a/hw/net/rtl8139.c +++ b/hw/net/rtl8139.c @@ -1205,6 +1205,20 @@ static void rtl8139_reset_rxring(RTL8139State *s, uint32_t bufferSize) s->RxBufAddr = 0; } +static void rtl8139_reset_phy(RTL8139State *s) +{ + s->BasicModeStatus = 0x7809; + s->BasicModeStatus |= 0x0020; /* autonegotiation completed */ + /* preserve link state */ + s->BasicModeStatus |= qemu_get_queue(s->nic)->link_down ? 0 : 0x04; + + s->NWayAdvert = 0x05e1; /* all modes, full duplex */ + s->NWayLPAR = 0x05e1; /* all modes, full duplex */ + s->NWayExpansion = 0x0001; /* autonegotiation supported */ + + s->CSCR = CSCR_F_LINK_100 | CSCR_HEART_BIT | CSCR_LD; +} + static void rtl8139_reset(DeviceState *d) { RTL8139State *s = RTL8139(d); @@ -1256,25 +1270,14 @@ static void rtl8139_reset(DeviceState *d) s->Config3 = 0x1; /* fast back-to-back compatible */ s->Config5 = 0x0; - s->CSCR = CSCR_F_LINK_100 | CSCR_HEART_BIT | CSCR_LD; - s->CpCmd = 0x0; /* reset C+ mode */ s->cplus_enabled = 0; - // s->BasicModeCtrl = 0x3100; // 100Mbps, full duplex, autonegotiation // s->BasicModeCtrl = 0x2100; // 100Mbps, full duplex s->BasicModeCtrl = 0x1000; // autonegotiation - s->BasicModeStatus = 0x7809; - //s->BasicModeStatus |= 0x0040; /* UTP medium */ - s->BasicModeStatus |= 0x0020; /* autonegotiation completed */ - /* preserve link state */ - s->BasicModeStatus |= qemu_get_queue(s->nic)->link_down ? 0 : 0x04; - - s->NWayAdvert = 0x05e1; /* all modes, full duplex */ - s->NWayLPAR = 0x05e1; /* all modes, full duplex */ - s->NWayExpansion = 0x0001; /* autonegotiation supported */ + rtl8139_reset_phy(s); /* also reset timer and disable timer interrupt */ s->TCTR = 0; @@ -1469,7 +1472,7 @@ static void rtl8139_BasicModeCtrl_write(RTL8139State *s, uint32_t val) DPRINTF("BasicModeCtrl register write(w) val=0x%04x\n", val); /* mask unwritable bits */ - uint32_t mask = 0x4cff; + uint32_t mask = 0xccff; if (1 || !rtl8139_config_writable(s)) { @@ -1479,6 +1482,11 @@ static void rtl8139_BasicModeCtrl_write(RTL8139State *s, uint32_t val) mask |= 0x0100; } + if (val & 0x8000) { + /* Reset PHY */ + rtl8139_reset_phy(s); + } + val = SET_MASKED(val, mask, s->BasicModeCtrl); s->BasicModeCtrl = val; diff --git a/hw/net/spapr_llan.c b/hw/net/spapr_llan.c index 01ecb02773..058908d8d7 100644 --- a/hw/net/spapr_llan.c +++ b/hw/net/spapr_llan.c @@ -105,7 +105,7 @@ typedef struct VIOsPAPRVLANDevice { uint32_t add_buf_ptr, use_buf_ptr, rx_bufs; hwaddr rxq_ptr; QEMUTimer *rxp_timer; - uint32_t compat_flags; /* Compatability flags for migration */ + uint32_t compat_flags; /* Compatibility flags for migration */ RxBufPool *rx_pool[RX_MAX_POOLS]; /* Receive buffer descriptor pools */ } VIOsPAPRVLANDevice; @@ -559,7 +559,7 @@ static target_long spapr_vlan_add_rxbuf_to_pool(VIOsPAPRVLANDevice *dev, if (pool < 0) { /* * No matching pool found? Try to use a new one. If the guest used all - * pools before, but changed the size of one pool inbetween, we might + * pools before, but changed the size of one pool in the meantime, we might * need to recycle that pool here (if it's empty already). Thus scan * all buffer pools now, starting with the last (likely empty) one. */ diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index f2d49ad7e7..22874a9777 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -51,6 +51,8 @@ static const int kernel_feature_bits[] = { VIRTIO_RING_F_EVENT_IDX, VIRTIO_NET_F_MRG_RXBUF, VIRTIO_F_VERSION_1, + VIRTIO_NET_F_MTU, + VIRTIO_F_IOMMU_PLATFORM, VHOST_INVALID_FEATURE_BIT }; @@ -74,6 +76,7 @@ static const int user_feature_bits[] = { VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_MRG_RXBUF, + VIRTIO_NET_F_MTU, /* This bit implies RARP isn't sent by QEMU out of band */ VIRTIO_NET_F_GUEST_ANNOUNCE, @@ -435,6 +438,17 @@ int vhost_set_vring_enable(NetClientState *nc, int enable) return 0; } +int vhost_net_set_mtu(struct vhost_net *net, uint16_t mtu) +{ + const VhostOps *vhost_ops = net->dev.vhost_ops; + + if (!vhost_ops->vhost_net_set_mtu) { + return 0; + } + + return vhost_ops->vhost_net_set_mtu(&net->dev, mtu); +} + #else uint64_t vhost_net_get_max_queues(VHostNetState *net) { @@ -501,4 +515,9 @@ int vhost_set_vring_enable(NetClientState *nc, int enable) { return 0; } + +int vhost_net_set_mtu(struct vhost_net *net, uint16_t mtu) +{ + return 0; +} #endif diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 5009533cfa..7b3ad4a9f0 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -55,6 +55,8 @@ static VirtIOFeature feature_sizes[] = { .end = endof(struct virtio_net_config, status)}, {.flags = 1 << VIRTIO_NET_F_MQ, .end = endof(struct virtio_net_config, max_virtqueue_pairs)}, + {.flags = 1 << VIRTIO_NET_F_MTU, + .end = endof(struct virtio_net_config, mtu)}, {} }; @@ -81,6 +83,7 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) virtio_stw_p(vdev, &netcfg.status, n->status); virtio_stw_p(vdev, &netcfg.max_virtqueue_pairs, n->max_queues); + virtio_stw_p(vdev, &netcfg.mtu, n->net_conf.mtu); memcpy(netcfg.mac, n->mac, ETH_ALEN); memcpy(config, &netcfg, n->config_size); } @@ -152,6 +155,16 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) qemu_net_queue_purge(qnc->incoming_queue, qnc->peer); } + if (virtio_has_feature(vdev->guest_features, VIRTIO_NET_F_MTU)) { + r = vhost_net_set_mtu(get_vhost_net(nc->peer), n->net_conf.mtu); + if (r < 0) { + error_report("%uBytes MTU not supported by the backend", + n->net_conf.mtu); + + return; + } + } + n->vhost_started = 1; r = vhost_net_start(vdev, n->nic->ncs, queues); if (r < 0) { @@ -218,6 +231,14 @@ static void virtio_net_vnet_endian_status(VirtIONet *n, uint8_t status) } } +static void virtio_net_drop_tx_queue_data(VirtIODevice *vdev, VirtQueue *vq) +{ + unsigned int dropped = virtqueue_drop_all(vq); + if (dropped) { + virtio_notify(vdev, vq); + } +} + static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status) { VirtIONet *n = VIRTIO_NET(vdev); @@ -262,6 +283,14 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status) } else { qemu_bh_cancel(q->tx_bh); } + if ((n->status & VIRTIO_NET_S_LINK_UP) == 0 && + (queue_status & VIRTIO_CONFIG_S_DRIVER_OK)) { + /* if tx is waiting we are likely have some packets in tx queue + * and disabled notification */ + q->tx_waiting = 0; + virtio_queue_set_notification(q->tx_vq, 1); + virtio_net_drop_tx_queue_data(vdev, q->tx_vq); + } } } } @@ -1323,6 +1352,11 @@ static void virtio_net_handle_tx_timer(VirtIODevice *vdev, VirtQueue *vq) VirtIONet *n = VIRTIO_NET(vdev); VirtIONetQueue *q = &n->vqs[vq2q(virtio_get_queue_index(vq))]; + if (unlikely((n->status & VIRTIO_NET_S_LINK_UP) == 0)) { + virtio_net_drop_tx_queue_data(vdev, vq); + return; + } + /* This happens when device was stopped but VCPU wasn't. */ if (!vdev->vm_running) { q->tx_waiting = 1; @@ -1349,6 +1383,11 @@ static void virtio_net_handle_tx_bh(VirtIODevice *vdev, VirtQueue *vq) VirtIONet *n = VIRTIO_NET(vdev); VirtIONetQueue *q = &n->vqs[vq2q(virtio_get_queue_index(vq))]; + if (unlikely((n->status & VIRTIO_NET_S_LINK_UP) == 0)) { + virtio_net_drop_tx_queue_data(vdev, vq); + return; + } + if (unlikely(q->tx_waiting)) { return; } @@ -1695,6 +1734,7 @@ static void virtio_net_set_config_size(VirtIONet *n, uint64_t host_features) { int i, config_size = 0; virtio_add_feature(&host_features, VIRTIO_NET_F_MAC); + for (i = 0; feature_sizes[i].flags != 0; i++) { if (host_features & feature_sizes[i].flags) { config_size = MAX(feature_sizes[i].end, config_size); @@ -1724,6 +1764,10 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) NetClientState *nc; int i; + if (n->net_conf.mtu) { + n->host_features |= (0x1 << VIRTIO_NET_F_MTU); + } + virtio_net_set_config_size(n, n->host_features); virtio_init(vdev, "virtio-net", VIRTIO_ID_NET, n->config_size); @@ -1922,6 +1966,7 @@ static Property virtio_net_properties[] = { DEFINE_PROP_STRING("tx", VirtIONet, net_conf.tx), DEFINE_PROP_UINT16("rx_queue_size", VirtIONet, net_conf.rx_queue_size, VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE), + DEFINE_PROP_UINT16("host_mtu", VirtIONet, net_conf.mtu, 0), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/net/vmxnet3.c b/hw/net/vmxnet3.c index 92f6af9620..2cb2731e29 100644 --- a/hw/net/vmxnet3.c +++ b/hw/net/vmxnet3.c @@ -2451,7 +2451,8 @@ static void vmxnet3_put_tx_stats_to_file(QEMUFile *f, qemu_put_be64(f, tx_stat->pktsTxDiscard); } -static int vmxnet3_get_txq_descr(QEMUFile *f, void *pv, size_t size) +static int vmxnet3_get_txq_descr(QEMUFile *f, void *pv, size_t size, + VMStateField *field) { Vmxnet3TxqDescr *r = pv; @@ -2465,7 +2466,8 @@ static int vmxnet3_get_txq_descr(QEMUFile *f, void *pv, size_t size) return 0; } -static void vmxnet3_put_txq_descr(QEMUFile *f, void *pv, size_t size) +static int vmxnet3_put_txq_descr(QEMUFile *f, void *pv, size_t size, + VMStateField *field, QJSON *vmdesc) { Vmxnet3TxqDescr *r = pv; @@ -2474,6 +2476,8 @@ static void vmxnet3_put_txq_descr(QEMUFile *f, void *pv, size_t size) qemu_put_byte(f, r->intr_idx); qemu_put_be64(f, r->tx_stats_pa); vmxnet3_put_tx_stats_to_file(f, &r->txq_stats); + + return 0; } static const VMStateInfo txq_descr_info = { @@ -2512,7 +2516,8 @@ static void vmxnet3_put_rx_stats_to_file(QEMUFile *f, qemu_put_be64(f, rx_stat->pktsRxError); } -static int vmxnet3_get_rxq_descr(QEMUFile *f, void *pv, size_t size) +static int vmxnet3_get_rxq_descr(QEMUFile *f, void *pv, size_t size, + VMStateField *field) { Vmxnet3RxqDescr *r = pv; int i; @@ -2530,7 +2535,8 @@ static int vmxnet3_get_rxq_descr(QEMUFile *f, void *pv, size_t size) return 0; } -static void vmxnet3_put_rxq_descr(QEMUFile *f, void *pv, size_t size) +static int vmxnet3_put_rxq_descr(QEMUFile *f, void *pv, size_t size, + VMStateField *field, QJSON *vmdesc) { Vmxnet3RxqDescr *r = pv; int i; @@ -2543,6 +2549,8 @@ static void vmxnet3_put_rxq_descr(QEMUFile *f, void *pv, size_t size) qemu_put_byte(f, r->intr_idx); qemu_put_be64(f, r->rx_stats_pa); vmxnet3_put_rx_stats_to_file(f, &r->rxq_stats); + + return 0; } static int vmxnet3_post_load(void *opaque, int version_id) @@ -2575,7 +2583,8 @@ static const VMStateInfo rxq_descr_info = { .put = vmxnet3_put_rxq_descr }; -static int vmxnet3_get_int_state(QEMUFile *f, void *pv, size_t size) +static int vmxnet3_get_int_state(QEMUFile *f, void *pv, size_t size, + VMStateField *field) { Vmxnet3IntState *r = pv; @@ -2586,13 +2595,16 @@ static int vmxnet3_get_int_state(QEMUFile *f, void *pv, size_t size) return 0; } -static void vmxnet3_put_int_state(QEMUFile *f, void *pv, size_t size) +static int vmxnet3_put_int_state(QEMUFile *f, void *pv, size_t size, + VMStateField *field, QJSON *vmdesc) { Vmxnet3IntState *r = pv; qemu_put_byte(f, r->is_masked); qemu_put_byte(f, r->is_pending); qemu_put_byte(f, r->is_asserted); + + return 0; } static const VMStateInfo int_state_info = { @@ -2619,7 +2631,7 @@ static const VMStateDescription vmstate_vmxnet3_pcie_device = { .minimum_version_id = 1, .needed = vmxnet3_vmstate_need_pcie_device, .fields = (VMStateField[]) { - VMSTATE_PCIE_DEVICE(parent_obj, VMXNET3State), + VMSTATE_PCI_DEVICE(parent_obj, VMXNET3State), VMSTATE_END_OF_LIST() } }; diff --git a/hw/nios2/10m50_devboard.c b/hw/nios2/10m50_devboard.c new file mode 100644 index 0000000000..62e5738b65 --- /dev/null +++ b/hw/nios2/10m50_devboard.c @@ -0,0 +1,126 @@ +/* + * Altera 10M50 Nios2 GHRD + * + * Copyright (c) 2016 Marek Vasut <marek.vasut@gmail.com> + * + * Based on LabX device code + * + * Copyright (c) 2012 Chris Wulff <crwulff@gmail.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/lgpl-2.1.html> + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu-common.h" +#include "cpu.h" + +#include "hw/sysbus.h" +#include "hw/hw.h" +#include "hw/char/serial.h" +#include "sysemu/sysemu.h" +#include "hw/boards.h" +#include "exec/memory.h" +#include "exec/address-spaces.h" +#include "qemu/config-file.h" + +#include "boot.h" + +#define BINARY_DEVICE_TREE_FILE "10m50-devboard.dtb" + +static void nios2_10m50_ghrd_init(MachineState *machine) +{ + Nios2CPU *cpu; + DeviceState *dev; + MemoryRegion *address_space_mem = get_system_memory(); + MemoryRegion *phys_tcm = g_new(MemoryRegion, 1); + MemoryRegion *phys_tcm_alias = g_new(MemoryRegion, 1); + MemoryRegion *phys_ram = g_new(MemoryRegion, 1); + MemoryRegion *phys_ram_alias = g_new(MemoryRegion, 1); + ram_addr_t tcm_base = 0x0; + ram_addr_t tcm_size = 0x1000; /* 1 kiB, but QEMU limit is 4 kiB */ + ram_addr_t ram_base = 0x08000000; + ram_addr_t ram_size = 0x08000000; + qemu_irq *cpu_irq, irq[32]; + int i; + + /* Physical TCM (tb_ram_1k) with alias at 0xc0000000 */ + memory_region_init_ram(phys_tcm, NULL, "nios2.tcm", tcm_size, &error_abort); + memory_region_init_alias(phys_tcm_alias, NULL, "nios2.tcm.alias", + phys_tcm, 0, tcm_size); + vmstate_register_ram_global(phys_tcm); + memory_region_add_subregion(address_space_mem, tcm_base, phys_tcm); + memory_region_add_subregion(address_space_mem, 0xc0000000 + tcm_base, + phys_tcm_alias); + + /* Physical DRAM with alias at 0xc0000000 */ + memory_region_init_ram(phys_ram, NULL, "nios2.ram", ram_size, &error_abort); + memory_region_init_alias(phys_ram_alias, NULL, "nios2.ram.alias", + phys_ram, 0, ram_size); + vmstate_register_ram_global(phys_ram); + memory_region_add_subregion(address_space_mem, ram_base, phys_ram); + memory_region_add_subregion(address_space_mem, 0xc0000000 + ram_base, + phys_ram_alias); + + /* Create CPU -- FIXME */ + cpu = cpu_nios2_init("nios2"); + + /* Register: CPU interrupt controller (PIC) */ + cpu_irq = nios2_cpu_pic_init(cpu); + + /* Register: Internal Interrupt Controller (IIC) */ + dev = qdev_create(NULL, "altera,iic"); + qdev_prop_set_ptr(dev, "cpu", cpu); + qdev_init_nofail(dev); + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, cpu_irq[0]); + for (i = 0; i < 32; i++) { + irq[i] = qdev_get_gpio_in(dev, i); + } + + /* Register: Altera 16550 UART */ + serial_mm_init(address_space_mem, 0xf8001600, 2, irq[1], 115200, + serial_hds[0], DEVICE_NATIVE_ENDIAN); + + /* Register: Timer sys_clk_timer */ + dev = qdev_create(NULL, "ALTR.timer"); + qdev_prop_set_uint32(dev, "clock-frequency", 75 * 1000000); + qdev_init_nofail(dev); + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, 0xf8001440); + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, irq[0]); + + /* Register: Timer sys_clk_timer_1 */ + dev = qdev_create(NULL, "ALTR.timer"); + qdev_prop_set_uint32(dev, "clock-frequency", 75 * 1000000); + qdev_init_nofail(dev); + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, 0xe0000880); + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, irq[5]); + + /* Configure new exception vectors and reset CPU for it to take effect. */ + cpu->reset_addr = 0xd4000000; + cpu->exception_addr = 0xc8000120; + cpu->fast_tlb_miss_addr = 0xc0000100; + + nios2_load_kernel(cpu, ram_base, ram_size, machine->initrd_filename, + BINARY_DEVICE_TREE_FILE, NULL); +} + +static void nios2_10m50_ghrd_machine_init(struct MachineClass *mc) +{ + mc->desc = "Altera 10M50 GHRD Nios II design"; + mc->init = nios2_10m50_ghrd_init; + mc->is_default = 1; +} + +DEFINE_MACHINE("10m50-ghrd", nios2_10m50_ghrd_machine_init); diff --git a/hw/nios2/Makefile.objs b/hw/nios2/Makefile.objs new file mode 100644 index 0000000000..6b5c421760 --- /dev/null +++ b/hw/nios2/Makefile.objs @@ -0,0 +1 @@ +obj-y = boot.o cpu_pic.o 10m50_devboard.o diff --git a/hw/nios2/boot.c b/hw/nios2/boot.c new file mode 100644 index 0000000000..e0a9aff2f4 --- /dev/null +++ b/hw/nios2/boot.c @@ -0,0 +1,223 @@ +/* + * Nios2 kernel loader + * + * Copyright (c) 2016 Marek Vasut <marek.vasut@gmail.com> + * + * Based on microblaze kernel loader + * + * Copyright (c) 2012 Peter Crosthwaite <peter.crosthwaite@petalogix.com> + * Copyright (c) 2012 PetaLogix + * Copyright (c) 2009 Edgar E. Iglesias. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "cpu.h" +#include "qemu/option.h" +#include "qemu/config-file.h" +#include "qemu/error-report.h" +#include "qemu-common.h" +#include "sysemu/device_tree.h" +#include "sysemu/sysemu.h" +#include "hw/loader.h" +#include "elf.h" +#include "qemu/cutils.h" + +#include "boot.h" + +#define NIOS2_MAGIC 0x534f494e + +static struct nios2_boot_info { + void (*machine_cpu_reset)(Nios2CPU *); + uint32_t bootstrap_pc; + uint32_t cmdline; + uint32_t initrd_start; + uint32_t initrd_end; + uint32_t fdt; +} boot_info; + +static void main_cpu_reset(void *opaque) +{ + Nios2CPU *cpu = opaque; + CPUState *cs = CPU(cpu); + CPUNios2State *env = &cpu->env; + + cpu_reset(CPU(cpu)); + + env->regs[R_ARG0] = NIOS2_MAGIC; + env->regs[R_ARG1] = boot_info.initrd_start; + env->regs[R_ARG2] = boot_info.fdt; + env->regs[R_ARG3] = boot_info.cmdline; + + cpu_set_pc(cs, boot_info.bootstrap_pc); + if (boot_info.machine_cpu_reset) { + boot_info.machine_cpu_reset(cpu); + } +} + +static uint64_t translate_kernel_address(void *opaque, uint64_t addr) +{ + return addr - 0xc0000000LL; +} + +static int nios2_load_dtb(struct nios2_boot_info bi, const uint32_t ramsize, + const char *kernel_cmdline, const char *dtb_filename) +{ + int fdt_size; + void *fdt = NULL; + int r; + + if (dtb_filename) { + fdt = load_device_tree(dtb_filename, &fdt_size); + } + if (!fdt) { + return 0; + } + + if (kernel_cmdline) { + r = qemu_fdt_setprop_string(fdt, "/chosen", "bootargs", + kernel_cmdline); + if (r < 0) { + fprintf(stderr, "couldn't set /chosen/bootargs\n"); + } + } + + if (bi.initrd_start) { + qemu_fdt_setprop_cell(fdt, "/chosen", "linux,initrd-start", + translate_kernel_address(NULL, bi.initrd_start)); + + qemu_fdt_setprop_cell(fdt, "/chosen", "linux,initrd-end", + translate_kernel_address(NULL, bi.initrd_end)); + } + + cpu_physical_memory_write(bi.fdt, fdt, fdt_size); + return fdt_size; +} + +void nios2_load_kernel(Nios2CPU *cpu, hwaddr ddr_base, + uint32_t ramsize, + const char *initrd_filename, + const char *dtb_filename, + void (*machine_cpu_reset)(Nios2CPU *)) +{ + QemuOpts *machine_opts; + const char *kernel_filename; + const char *kernel_cmdline; + const char *dtb_arg; + char *filename = NULL; + + machine_opts = qemu_get_machine_opts(); + kernel_filename = qemu_opt_get(machine_opts, "kernel"); + kernel_cmdline = qemu_opt_get(machine_opts, "append"); + dtb_arg = qemu_opt_get(machine_opts, "dtb"); + /* default to pcbios dtb as passed by machine_init */ + if (!dtb_arg) { + filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, dtb_filename); + } + + boot_info.machine_cpu_reset = machine_cpu_reset; + qemu_register_reset(main_cpu_reset, cpu); + + if (kernel_filename) { + int kernel_size, fdt_size; + uint64_t entry, low, high; + uint32_t base32; + int big_endian = 0; + +#ifdef TARGET_WORDS_BIGENDIAN + big_endian = 1; +#endif + + /* Boots a kernel elf binary. */ + kernel_size = load_elf(kernel_filename, NULL, NULL, + &entry, &low, &high, + big_endian, EM_ALTERA_NIOS2, 0, 0); + base32 = entry; + if (base32 == 0xc0000000) { + kernel_size = load_elf(kernel_filename, translate_kernel_address, + NULL, &entry, NULL, NULL, + big_endian, EM_ALTERA_NIOS2, 0, 0); + } + + /* Always boot into physical ram. */ + boot_info.bootstrap_pc = ddr_base + 0xc0000000 + (entry & 0x07ffffff); + + /* If it wasn't an ELF image, try an u-boot image. */ + if (kernel_size < 0) { + hwaddr uentry, loadaddr; + + kernel_size = load_uimage(kernel_filename, &uentry, &loadaddr, 0, + NULL, NULL); + boot_info.bootstrap_pc = uentry; + high = loadaddr + kernel_size; + } + + /* Not an ELF image nor an u-boot image, try a RAW image. */ + if (kernel_size < 0) { + kernel_size = load_image_targphys(kernel_filename, ddr_base, + ram_size); + boot_info.bootstrap_pc = ddr_base; + high = ddr_base + kernel_size; + } + + high = ROUND_UP(high, 1024 * 1024); + + /* If initrd is available, it goes after the kernel, aligned to 1M. */ + if (initrd_filename) { + int initrd_size; + uint32_t initrd_offset; + + boot_info.initrd_start = high; + initrd_offset = boot_info.initrd_start - ddr_base; + + initrd_size = load_ramdisk(initrd_filename, + boot_info.initrd_start, + ram_size - initrd_offset); + if (initrd_size < 0) { + initrd_size = load_image_targphys(initrd_filename, + boot_info.initrd_start, + ram_size - initrd_offset); + } + if (initrd_size < 0) { + error_report("qemu: could not load initrd '%s'", + initrd_filename); + exit(EXIT_FAILURE); + } + high += initrd_size; + } + high = ROUND_UP(high, 4); + boot_info.initrd_end = high; + + /* Device tree must be placed right after initrd (if available) */ + boot_info.fdt = high; + fdt_size = nios2_load_dtb(boot_info, ram_size, kernel_cmdline, + /* Preference a -dtb argument */ + dtb_arg ? dtb_arg : filename); + high += fdt_size; + + /* Kernel command is at the end, 4k aligned. */ + boot_info.cmdline = ROUND_UP(high, 4096); + if (kernel_cmdline && strlen(kernel_cmdline)) { + pstrcpy_targphys("cmdline", boot_info.cmdline, 256, kernel_cmdline); + } + } + g_free(filename); +} diff --git a/hw/nios2/boot.h b/hw/nios2/boot.h new file mode 100644 index 0000000000..3116753818 --- /dev/null +++ b/hw/nios2/boot.h @@ -0,0 +1,11 @@ +#ifndef NIOS2_BOOT_H +#define NIOS2_BOOT_H + +#include "hw/hw.h" +#include "cpu.h" + +void nios2_load_kernel(Nios2CPU *cpu, hwaddr ddr_base, uint32_t ramsize, + const char *initrd_filename, const char *dtb_filename, + void (*machine_cpu_reset)(Nios2CPU *)); + +#endif /* NIOS2_BOOT_H */ diff --git a/hw/nios2/cpu_pic.c b/hw/nios2/cpu_pic.c new file mode 100644 index 0000000000..0f95987ef3 --- /dev/null +++ b/hw/nios2/cpu_pic.c @@ -0,0 +1,70 @@ +/* + * Altera Nios2 CPU PIC + * + * Copyright (c) 2016 Marek Vasut <marek.vasut@gmail.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/lgpl-2.1.html> + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu-common.h" +#include "cpu.h" + +#include "qemu/config-file.h" + +#include "boot.h" + +static void nios2_pic_cpu_handler(void *opaque, int irq, int level) +{ + Nios2CPU *cpu = opaque; + CPUNios2State *env = &cpu->env; + CPUState *cs = CPU(cpu); + int type = irq ? CPU_INTERRUPT_NMI : CPU_INTERRUPT_HARD; + + if (type == CPU_INTERRUPT_HARD) { + env->irq_pending = level; + + if (level && (env->regs[CR_STATUS] & CR_STATUS_PIE)) { + env->irq_pending = 0; + cpu_interrupt(cs, type); + } else if (!level) { + env->irq_pending = 0; + cpu_reset_interrupt(cs, type); + } + } else { + if (level) { + cpu_interrupt(cs, type); + } else { + cpu_reset_interrupt(cs, type); + } + } +} + +void nios2_check_interrupts(CPUNios2State *env) +{ + Nios2CPU *cpu = nios2_env_get_cpu(env); + CPUState *cs = CPU(cpu); + + if (env->irq_pending) { + env->irq_pending = 0; + cpu_interrupt(cs, CPU_INTERRUPT_HARD); + } +} + +qemu_irq *nios2_cpu_pic_init(Nios2CPU *cpu) +{ + return qemu_allocate_irqs(nios2_pic_cpu_handler, cpu, 2); +} diff --git a/hw/nvram/eeprom93xx.c b/hw/nvram/eeprom93xx.c index 2c16fc23df..848692abc0 100644 --- a/hw/nvram/eeprom93xx.c +++ b/hw/nvram/eeprom93xx.c @@ -94,18 +94,22 @@ struct _eeprom_t { This is a Big hack, but it is how the old state did it. */ -static int get_uint16_from_uint8(QEMUFile *f, void *pv, size_t size) +static int get_uint16_from_uint8(QEMUFile *f, void *pv, size_t size, + VMStateField *field) { uint16_t *v = pv; *v = qemu_get_ubyte(f); return 0; } -static void put_unused(QEMUFile *f, void *pv, size_t size) +static int put_unused(QEMUFile *f, void *pv, size_t size, VMStateField *field, + QJSON *vmdesc) { fprintf(stderr, "uint16_from_uint8 is used only for backwards compatibility.\n"); fprintf(stderr, "Never should be used to write a new state.\n"); exit(0); + + return 0; } static const VMStateInfo vmstate_hack_uint16_from_uint8 = { diff --git a/hw/nvram/fw_cfg.c b/hw/nvram/fw_cfg.c index 3ebecb2260..316fca9bc1 100644 --- a/hw/nvram/fw_cfg.c +++ b/hw/nvram/fw_cfg.c @@ -33,6 +33,9 @@ #include "qemu/error-report.h" #include "qemu/config-file.h" #include "qemu/cutils.h" +#include "qapi/error.h" + +#define FW_CFG_FILE_SLOTS_DFLT 0x20 #define FW_CFG_NAME "fw_cfg" #define FW_CFG_PATH "/machine/" FW_CFG_NAME @@ -54,11 +57,13 @@ #define FW_CFG_DMA_CTL_READ 0x02 #define FW_CFG_DMA_CTL_SKIP 0x04 #define FW_CFG_DMA_CTL_SELECT 0x08 +#define FW_CFG_DMA_CTL_WRITE 0x10 #define FW_CFG_DMA_SIGNATURE 0x51454d5520434647ULL /* "QEMU CFG" */ typedef struct FWCfgEntry { uint32_t len; + bool allow_write; uint8_t *data; void *callback_opaque; FWCfgReadCallback read_callback; @@ -69,8 +74,9 @@ struct FWCfgState { SysBusDevice parent_obj; /*< public >*/ - FWCfgEntry entries[2][FW_CFG_MAX_ENTRY]; - int entry_order[FW_CFG_MAX_ENTRY]; + uint16_t file_slots; + FWCfgEntry *entries[2]; + int *entry_order; FWCfgFiles *files; uint16_t cur_entry; uint32_t cur_offset; @@ -255,13 +261,24 @@ static void fw_cfg_write(FWCfgState *s, uint8_t value) /* nothing, write support removed in QEMU v2.4+ */ } +static inline uint16_t fw_cfg_file_slots(const FWCfgState *s) +{ + return s->file_slots; +} + +/* Note: this function returns an exclusive limit. */ +static inline uint32_t fw_cfg_max_entry(const FWCfgState *s) +{ + return FW_CFG_FILE_FIRST + fw_cfg_file_slots(s); +} + static int fw_cfg_select(FWCfgState *s, uint16_t key) { int arch, ret; FWCfgEntry *e; s->cur_offset = 0; - if ((key & FW_CFG_ENTRY_MASK) >= FW_CFG_MAX_ENTRY) { + if ((key & FW_CFG_ENTRY_MASK) >= fw_cfg_max_entry(s)) { s->cur_entry = FW_CFG_INVALID; ret = 0; } else { @@ -326,7 +343,7 @@ static void fw_cfg_dma_transfer(FWCfgState *s) FWCfgDmaAccess dma; int arch; FWCfgEntry *e; - int read; + int read = 0, write = 0; dma_addr_t dma_addr; /* Reset the address before the next access */ @@ -353,8 +370,13 @@ static void fw_cfg_dma_transfer(FWCfgState *s) if (dma.control & FW_CFG_DMA_CTL_READ) { read = 1; + write = 0; + } else if (dma.control & FW_CFG_DMA_CTL_WRITE) { + read = 0; + write = 1; } else if (dma.control & FW_CFG_DMA_CTL_SKIP) { read = 0; + write = 0; } else { dma.length = 0; } @@ -374,7 +396,9 @@ static void fw_cfg_dma_transfer(FWCfgState *s) dma.control |= FW_CFG_DMA_CTL_ERROR; } } - + if (write) { + dma.control |= FW_CFG_DMA_CTL_ERROR; + } } else { if (dma.length <= (e->len - s->cur_offset)) { len = dma.length; @@ -391,6 +415,14 @@ static void fw_cfg_dma_transfer(FWCfgState *s) dma.control |= FW_CFG_DMA_CTL_ERROR; } } + if (write) { + if (!e->allow_write || + len != dma.length || + dma_memory_read(s->dma_as, dma.address, + &e->data[s->cur_offset], len)) { + dma.control |= FW_CFG_DMA_CTL_ERROR; + } + } s->cur_offset += len; } @@ -523,17 +555,21 @@ static void fw_cfg_reset(DeviceState *d) Or we broke compatibility in the state, or we can't use struct tm */ -static int get_uint32_as_uint16(QEMUFile *f, void *pv, size_t size) +static int get_uint32_as_uint16(QEMUFile *f, void *pv, size_t size, + VMStateField *field) { uint32_t *v = pv; *v = qemu_get_be16(f); return 0; } -static void put_unused(QEMUFile *f, void *pv, size_t size) +static int put_unused(QEMUFile *f, void *pv, size_t size, VMStateField *field, + QJSON *vmdesc) { fprintf(stderr, "uint32_as_uint16 is only used for backward compatibility.\n"); fprintf(stderr, "This functions shouldn't be called.\n"); + + return 0; } static const VMStateInfo vmstate_hack_uint32_as_uint16 = { @@ -586,19 +622,21 @@ static const VMStateDescription vmstate_fw_cfg = { static void fw_cfg_add_bytes_read_callback(FWCfgState *s, uint16_t key, FWCfgReadCallback callback, void *callback_opaque, - void *data, size_t len) + void *data, size_t len, + bool read_only) { int arch = !!(key & FW_CFG_ARCH_LOCAL); key &= FW_CFG_ENTRY_MASK; - assert(key < FW_CFG_MAX_ENTRY && len < UINT32_MAX); + assert(key < fw_cfg_max_entry(s) && len < UINT32_MAX); assert(s->entries[arch][key].data == NULL); /* avoid key conflict */ s->entries[arch][key].data = data; s->entries[arch][key].len = (uint32_t)len; s->entries[arch][key].read_callback = callback; s->entries[arch][key].callback_opaque = callback_opaque; + s->entries[arch][key].allow_write = !read_only; } static void *fw_cfg_modify_bytes_read(FWCfgState *s, uint16_t key, @@ -609,20 +647,21 @@ static void *fw_cfg_modify_bytes_read(FWCfgState *s, uint16_t key, key &= FW_CFG_ENTRY_MASK; - assert(key < FW_CFG_MAX_ENTRY && len < UINT32_MAX); + assert(key < fw_cfg_max_entry(s) && len < UINT32_MAX); /* return the old data to the function caller, avoid memory leak */ ptr = s->entries[arch][key].data; s->entries[arch][key].data = data; s->entries[arch][key].len = len; s->entries[arch][key].callback_opaque = NULL; + s->entries[arch][key].allow_write = false; return ptr; } void fw_cfg_add_bytes(FWCfgState *s, uint16_t key, void *data, size_t len) { - fw_cfg_add_bytes_read_callback(s, key, NULL, NULL, data, len); + fw_cfg_add_bytes_read_callback(s, key, NULL, NULL, data, len, true); } void fw_cfg_add_string(FWCfgState *s, uint16_t key, const char *value) @@ -749,7 +788,7 @@ static int get_fw_cfg_order(FWCfgState *s, const char *name) void fw_cfg_add_file_callback(FWCfgState *s, const char *filename, FWCfgReadCallback callback, void *callback_opaque, - void *data, size_t len) + void *data, size_t len, bool read_only) { int i, index, count; size_t dsize; @@ -757,13 +796,13 @@ void fw_cfg_add_file_callback(FWCfgState *s, const char *filename, int order = 0; if (!s->files) { - dsize = sizeof(uint32_t) + sizeof(FWCfgFile) * FW_CFG_FILE_SLOTS; + dsize = sizeof(uint32_t) + sizeof(FWCfgFile) * fw_cfg_file_slots(s); s->files = g_malloc0(dsize); fw_cfg_add_bytes(s, FW_CFG_FILE_DIR, s->files, dsize); } count = be32_to_cpu(s->files->count); - assert(count < FW_CFG_FILE_SLOTS); + assert(count < fw_cfg_file_slots(s)); /* Find the insertion point. */ if (mc->legacy_fw_cfg_order) { @@ -811,7 +850,8 @@ void fw_cfg_add_file_callback(FWCfgState *s, const char *filename, } fw_cfg_add_bytes_read_callback(s, FW_CFG_FILE_FIRST + index, - callback, callback_opaque, data, len); + callback, callback_opaque, data, len, + read_only); s->files->f[index].size = cpu_to_be32(len); s->files->f[index].select = cpu_to_be16(FW_CFG_FILE_FIRST + index); @@ -824,7 +864,7 @@ void fw_cfg_add_file_callback(FWCfgState *s, const char *filename, void fw_cfg_add_file(FWCfgState *s, const char *filename, void *data, size_t len) { - fw_cfg_add_file_callback(s, filename, NULL, NULL, data, len); + fw_cfg_add_file_callback(s, filename, NULL, NULL, data, len, true); } void *fw_cfg_modify_file(FWCfgState *s, const char *filename, @@ -836,7 +876,7 @@ void *fw_cfg_modify_file(FWCfgState *s, const char *filename, assert(s->files); index = be32_to_cpu(s->files->count); - assert(index < FW_CFG_FILE_SLOTS); + assert(index < fw_cfg_file_slots(s)); for (i = 0; i < index; i++) { if (strcmp(filename, s->files->f[i].name) == 0) { @@ -847,7 +887,7 @@ void *fw_cfg_modify_file(FWCfgState *s, const char *filename, } } /* add new one */ - fw_cfg_add_file_callback(s, filename, NULL, NULL, data, len); + fw_cfg_add_file_callback(s, filename, NULL, NULL, data, len, true); return NULL; } @@ -993,12 +1033,38 @@ static const TypeInfo fw_cfg_info = { .class_init = fw_cfg_class_init, }; +static void fw_cfg_file_slots_allocate(FWCfgState *s, Error **errp) +{ + uint16_t file_slots_max; + + if (fw_cfg_file_slots(s) < FW_CFG_FILE_SLOTS_MIN) { + error_setg(errp, "\"file_slots\" must be at least 0x%x", + FW_CFG_FILE_SLOTS_MIN); + return; + } + + /* (UINT16_MAX & FW_CFG_ENTRY_MASK) is the highest inclusive selector value + * that we permit. The actual (exclusive) value coming from the + * configuration is (FW_CFG_FILE_FIRST + fw_cfg_file_slots(s)). */ + file_slots_max = (UINT16_MAX & FW_CFG_ENTRY_MASK) - FW_CFG_FILE_FIRST + 1; + if (fw_cfg_file_slots(s) > file_slots_max) { + error_setg(errp, "\"file_slots\" must not exceed 0x%" PRIx16, + file_slots_max); + return; + } + + s->entries[0] = g_new0(FWCfgEntry, fw_cfg_max_entry(s)); + s->entries[1] = g_new0(FWCfgEntry, fw_cfg_max_entry(s)); + s->entry_order = g_new0(int, fw_cfg_max_entry(s)); +} static Property fw_cfg_io_properties[] = { DEFINE_PROP_UINT32("iobase", FWCfgIoState, iobase, -1), DEFINE_PROP_UINT32("dma_iobase", FWCfgIoState, dma_iobase, -1), DEFINE_PROP_BOOL("dma_enabled", FWCfgIoState, parent_obj.dma_enabled, true), + DEFINE_PROP_UINT16("x-file-slots", FWCfgIoState, parent_obj.file_slots, + FW_CFG_FILE_SLOTS_DFLT), DEFINE_PROP_END_OF_LIST(), }; @@ -1006,6 +1072,13 @@ static void fw_cfg_io_realize(DeviceState *dev, Error **errp) { FWCfgIoState *s = FW_CFG_IO(dev); SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + Error *local_err = NULL; + + fw_cfg_file_slots_allocate(FW_CFG(s), &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } /* when using port i/o, the 8-bit data register ALWAYS overlaps * with half of the 16-bit control register. Hence, the total size @@ -1042,6 +1115,8 @@ static Property fw_cfg_mem_properties[] = { DEFINE_PROP_UINT32("data_width", FWCfgMemState, data_width, -1), DEFINE_PROP_BOOL("dma_enabled", FWCfgMemState, parent_obj.dma_enabled, true), + DEFINE_PROP_UINT16("x-file-slots", FWCfgMemState, parent_obj.file_slots, + FW_CFG_FILE_SLOTS_DFLT), DEFINE_PROP_END_OF_LIST(), }; @@ -1050,6 +1125,13 @@ static void fw_cfg_mem_realize(DeviceState *dev, Error **errp) FWCfgMemState *s = FW_CFG_MEM(dev); SysBusDevice *sbd = SYS_BUS_DEVICE(dev); const MemoryRegionOps *data_ops = &fw_cfg_data_mem_ops; + Error *local_err = NULL; + + fw_cfg_file_slots_allocate(FW_CFG(s), &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } memory_region_init_io(&s->ctl_iomem, OBJECT(s), &fw_cfg_ctl_mem_ops, FW_CFG(s), "fwcfg.ctl", FW_CFG_CTL_SIZE); diff --git a/hw/pci-bridge/ioh3420.c b/hw/pci-bridge/ioh3420.c index c8b5ac4207..0eef87a4f8 100644 --- a/hw/pci-bridge/ioh3420.c +++ b/hw/pci-bridge/ioh3420.c @@ -135,8 +135,10 @@ static int ioh3420_initfn(PCIDevice *d) goto err_pcie_cap; } - rc = pcie_aer_init(d, IOH_EP_AER_OFFSET, PCI_ERR_SIZEOF); + rc = pcie_aer_init(d, PCI_ERR_VER, IOH_EP_AER_OFFSET, + PCI_ERR_SIZEOF, &err); if (rc < 0) { + error_report_err(err); goto err; } pcie_aer_root_init(d); @@ -178,7 +180,7 @@ static const VMStateDescription vmstate_ioh3420 = { .minimum_version_id = 1, .post_load = pcie_cap_slot_post_load, .fields = (VMStateField[]) { - VMSTATE_PCIE_DEVICE(parent_obj.parent_obj.parent_obj, PCIESlot), + VMSTATE_PCI_DEVICE(parent_obj.parent_obj.parent_obj, PCIESlot), VMSTATE_STRUCT(parent_obj.parent_obj.parent_obj.exp.aer_log, PCIESlot, 0, vmstate_pcie_aer_log, PCIEAERLog), VMSTATE_END_OF_LIST() diff --git a/hw/pci-bridge/xio3130_downstream.c b/hw/pci-bridge/xio3130_downstream.c index cef6e1325e..cfe8a3657f 100644 --- a/hw/pci-bridge/xio3130_downstream.c +++ b/hw/pci-bridge/xio3130_downstream.c @@ -97,8 +97,10 @@ static int xio3130_downstream_initfn(PCIDevice *d) goto err_pcie_cap; } - rc = pcie_aer_init(d, XIO3130_AER_OFFSET, PCI_ERR_SIZEOF); + rc = pcie_aer_init(d, PCI_ERR_VER, XIO3130_AER_OFFSET, + PCI_ERR_SIZEOF, &err); if (rc < 0) { + error_report_err(err); goto err; } @@ -164,7 +166,7 @@ static const VMStateDescription vmstate_xio3130_downstream = { .minimum_version_id = 1, .post_load = pcie_cap_slot_post_load, .fields = (VMStateField[]) { - VMSTATE_PCIE_DEVICE(parent_obj.parent_obj.parent_obj, PCIESlot), + VMSTATE_PCI_DEVICE(parent_obj.parent_obj.parent_obj, PCIESlot), VMSTATE_STRUCT(parent_obj.parent_obj.parent_obj.exp.aer_log, PCIESlot, 0, vmstate_pcie_aer_log, PCIEAERLog), VMSTATE_END_OF_LIST() diff --git a/hw/pci-bridge/xio3130_upstream.c b/hw/pci-bridge/xio3130_upstream.c index 4ad0440aa1..401c78452b 100644 --- a/hw/pci-bridge/xio3130_upstream.c +++ b/hw/pci-bridge/xio3130_upstream.c @@ -85,8 +85,10 @@ static int xio3130_upstream_initfn(PCIDevice *d) pcie_cap_flr_init(d); pcie_cap_deverr_init(d); - rc = pcie_aer_init(d, XIO3130_AER_OFFSET, PCI_ERR_SIZEOF); + rc = pcie_aer_init(d, PCI_ERR_VER, XIO3130_AER_OFFSET, + PCI_ERR_SIZEOF, &err); if (rc < 0) { + error_report_err(err); goto err; } @@ -136,7 +138,7 @@ static const VMStateDescription vmstate_xio3130_upstream = { .version_id = 1, .minimum_version_id = 1, .fields = (VMStateField[]) { - VMSTATE_PCIE_DEVICE(parent_obj.parent_obj, PCIEPort), + VMSTATE_PCI_DEVICE(parent_obj.parent_obj, PCIEPort), VMSTATE_STRUCT(parent_obj.parent_obj.exp.aer_log, PCIEPort, 0, vmstate_pcie_aer_log, PCIEAERLog), VMSTATE_END_OF_LIST() diff --git a/hw/pci/msix.c b/hw/pci/msix.c index 0ec1cb14fc..ee1714d2cf 100644 --- a/hw/pci/msix.c +++ b/hw/pci/msix.c @@ -587,12 +587,16 @@ void msix_unset_vector_notifiers(PCIDevice *dev) dev->msix_vector_poll_notifier = NULL; } -static void put_msix_state(QEMUFile *f, void *pv, size_t size) +static int put_msix_state(QEMUFile *f, void *pv, size_t size, + VMStateField *field, QJSON *vmdesc) { msix_save(pv, f); + + return 0; } -static int get_msix_state(QEMUFile *f, void *pv, size_t size) +static int get_msix_state(QEMUFile *f, void *pv, size_t size, + VMStateField *field) { msix_load(pv, f); return 0; diff --git a/hw/pci/pci.c b/hw/pci/pci.c index 24fae1689d..47ca3af69a 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -445,7 +445,8 @@ int pci_bus_numa_node(PCIBus *bus) return PCI_BUS_GET_CLASS(bus)->numa_node(bus); } -static int get_pci_config_device(QEMUFile *f, void *pv, size_t size) +static int get_pci_config_device(QEMUFile *f, void *pv, size_t size, + VMStateField *field) { PCIDevice *s = container_of(pv, PCIDevice, config); PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(s); @@ -484,11 +485,14 @@ static int get_pci_config_device(QEMUFile *f, void *pv, size_t size) } /* just put buffer */ -static void put_pci_config_device(QEMUFile *f, void *pv, size_t size) +static int put_pci_config_device(QEMUFile *f, void *pv, size_t size, + VMStateField *field, QJSON *vmdesc) { const uint8_t **v = pv; assert(size == pci_config_size(container_of(pv, PCIDevice, config))); qemu_put_buffer(f, *v, size); + + return 0; } static VMStateInfo vmstate_info_pci_config = { @@ -497,7 +501,8 @@ static VMStateInfo vmstate_info_pci_config = { .put = put_pci_config_device, }; -static int get_pci_irq_state(QEMUFile *f, void *pv, size_t size) +static int get_pci_irq_state(QEMUFile *f, void *pv, size_t size, + VMStateField *field) { PCIDevice *s = container_of(pv, PCIDevice, irq_state); uint32_t irq_state[PCI_NUM_PINS]; @@ -518,7 +523,8 @@ static int get_pci_irq_state(QEMUFile *f, void *pv, size_t size) return 0; } -static void put_pci_irq_state(QEMUFile *f, void *pv, size_t size) +static int put_pci_irq_state(QEMUFile *f, void *pv, size_t size, + VMStateField *field, QJSON *vmdesc) { int i; PCIDevice *s = container_of(pv, PCIDevice, irq_state); @@ -526,6 +532,8 @@ static void put_pci_irq_state(QEMUFile *f, void *pv, size_t size) for (i = 0; i < PCI_NUM_PINS; ++i) { qemu_put_be32(f, pci_irq_state(s, i)); } + + return 0; } static VMStateInfo vmstate_info_pci_irq_state = { @@ -534,30 +542,29 @@ static VMStateInfo vmstate_info_pci_irq_state = { .put = put_pci_irq_state, }; +static bool migrate_is_pcie(void *opaque, int version_id) +{ + return pci_is_express((PCIDevice *)opaque); +} + +static bool migrate_is_not_pcie(void *opaque, int version_id) +{ + return !pci_is_express((PCIDevice *)opaque); +} + const VMStateDescription vmstate_pci_device = { .name = "PCIDevice", .version_id = 2, .minimum_version_id = 1, .fields = (VMStateField[]) { VMSTATE_INT32_POSITIVE_LE(version_id, PCIDevice), - VMSTATE_BUFFER_UNSAFE_INFO(config, PCIDevice, 0, - vmstate_info_pci_config, + VMSTATE_BUFFER_UNSAFE_INFO_TEST(config, PCIDevice, + migrate_is_not_pcie, + 0, vmstate_info_pci_config, PCI_CONFIG_SPACE_SIZE), - VMSTATE_BUFFER_UNSAFE_INFO(irq_state, PCIDevice, 2, - vmstate_info_pci_irq_state, - PCI_NUM_PINS * sizeof(int32_t)), - VMSTATE_END_OF_LIST() - } -}; - -const VMStateDescription vmstate_pcie_device = { - .name = "PCIEDevice", - .version_id = 2, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_INT32_POSITIVE_LE(version_id, PCIDevice), - VMSTATE_BUFFER_UNSAFE_INFO(config, PCIDevice, 0, - vmstate_info_pci_config, + VMSTATE_BUFFER_UNSAFE_INFO_TEST(config, PCIDevice, + migrate_is_pcie, + 0, vmstate_info_pci_config, PCIE_CONFIG_SPACE_SIZE), VMSTATE_BUFFER_UNSAFE_INFO(irq_state, PCIDevice, 2, vmstate_info_pci_irq_state, @@ -566,10 +573,6 @@ const VMStateDescription vmstate_pcie_device = { } }; -static inline const VMStateDescription *pci_get_vmstate(PCIDevice *s) -{ - return pci_is_express(s) ? &vmstate_pcie_device : &vmstate_pci_device; -} void pci_device_save(PCIDevice *s, QEMUFile *f) { @@ -578,7 +581,7 @@ void pci_device_save(PCIDevice *s, QEMUFile *f) * This makes us compatible with old devices * which never set or clear this bit. */ s->config[PCI_STATUS] &= ~PCI_STATUS_INTERRUPT; - vmstate_save_state(f, pci_get_vmstate(s), s, NULL); + vmstate_save_state(f, &vmstate_pci_device, s, NULL); /* Restore the interrupt status bit. */ pci_update_irq_status(s); } @@ -586,7 +589,7 @@ void pci_device_save(PCIDevice *s, QEMUFile *f) int pci_device_load(PCIDevice *s, QEMUFile *f) { int ret; - ret = vmstate_load_state(f, pci_get_vmstate(s), s, s->version_id); + ret = vmstate_load_state(f, &vmstate_pci_device, s, s->version_id); /* Restore the interrupt status bit. */ pci_update_irq_status(s); return ret; @@ -982,8 +985,8 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev, PCIBus *bus, pci_get_function_0(pci_dev)) { error_setg(errp, "PCI: slot %d function 0 already ocuppied by %s," " new func %s cannot be exposed to guest.", - PCI_SLOT(devfn), - bus->devices[PCI_DEVFN(PCI_SLOT(devfn), 0)]->name, + PCI_SLOT(pci_get_function_0(pci_dev)->devfn), + pci_get_function_0(pci_dev)->name, name); return NULL; @@ -1779,7 +1782,6 @@ PCIDevice *pci_nic_init_nofail(NICInfo *nd, PCIBus *rootbus, const char *default_devaddr) { const char *devaddr = nd->devaddr ? nd->devaddr : default_devaddr; - Error *err = NULL; PCIBus *bus; PCIDevice *pci_dev; DeviceState *dev; @@ -1805,13 +1807,7 @@ PCIDevice *pci_nic_init_nofail(NICInfo *nd, PCIBus *rootbus, pci_dev = pci_create(bus, devfn, pci_nic_names[i]); dev = &pci_dev->qdev; qdev_set_nic_properties(dev, nd); - - object_property_set_bool(OBJECT(dev), true, "realized", &err); - if (err) { - error_report_err(err); - object_unparent(OBJECT(dev)); - exit(1); - } + qdev_init_nofail(dev); return pci_dev; } diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c index 99cfb4561b..cbd4bb4f8c 100644 --- a/hw/pci/pcie.c +++ b/hw/pci/pcie.c @@ -656,7 +656,7 @@ static void pcie_ext_cap_set_next(PCIDevice *dev, uint16_t pos, uint16_t next) } /* - * caller must supply valid (offset, size) * such that the range shouldn't + * Caller must supply valid (offset, size) such that the range wouldn't * overlap with other capability or other registers. * This function doesn't check it. */ @@ -717,3 +717,18 @@ void pcie_dev_ser_num_init(PCIDevice *dev, uint16_t offset, uint64_t ser_num) PCI_EXT_CAP_DSN_SIZEOF); pci_set_quad(dev->config + offset + pci_dsn_cap, ser_num); } + +void pcie_ats_init(PCIDevice *dev, uint16_t offset) +{ + pcie_add_capability(dev, PCI_EXT_CAP_ID_ATS, 0x1, + offset, PCI_EXT_CAP_ATS_SIZEOF); + + dev->exp.ats_cap = offset; + + /* Invalidate Queue Depth 0, Page Aligned Request 0 */ + pci_set_word(dev->config + offset + PCI_ATS_CAP, 0); + /* STU 0, Disabled by default */ + pci_set_word(dev->config + offset + PCI_ATS_CTRL, 0); + + pci_set_word(dev->wmask + dev->exp.ats_cap + PCI_ATS_CTRL, 0x800f); +} diff --git a/hw/pci/pcie_aer.c b/hw/pci/pcie_aer.c index 048ce6a424..daf1f65427 100644 --- a/hw/pci/pcie_aer.c +++ b/hw/pci/pcie_aer.c @@ -29,6 +29,7 @@ #include "hw/pci/msi.h" #include "hw/pci/pci_bus.h" #include "hw/pci/pcie_regs.h" +#include "qapi/error.h" //#define DEBUG_PCIE #ifdef DEBUG_PCIE @@ -96,21 +97,17 @@ static void aer_log_clear_all_err(PCIEAERLog *aer_log) aer_log->log_num = 0; } -int pcie_aer_init(PCIDevice *dev, uint16_t offset, uint16_t size) +int pcie_aer_init(PCIDevice *dev, uint8_t cap_ver, uint16_t offset, + uint16_t size, Error **errp) { - PCIExpressDevice *exp; - - pcie_add_capability(dev, PCI_EXT_CAP_ID_ERR, PCI_ERR_VER, + pcie_add_capability(dev, PCI_EXT_CAP_ID_ERR, cap_ver, offset, size); - exp = &dev->exp; - exp->aer_cap = offset; + dev->exp.aer_cap = offset; - /* log_max is property */ - if (dev->exp.aer_log.log_max == PCIE_AER_LOG_MAX_UNSET) { - dev->exp.aer_log.log_max = PCIE_AER_LOG_MAX_DEFAULT; - } - /* clip down the value to avoid unreasobale memory usage */ + /* clip down the value to avoid unreasonable memory usage */ if (dev->exp.aer_log.log_max > PCIE_AER_LOG_MAX_LIMIT) { + error_setg(errp, "Invalid aer_log_max %d. The max number of aer log " + "is %d", dev->exp.aer_log.log_max, PCIE_AER_LOG_MAX_LIMIT); return -EINVAL; } dev->exp.aer_log.log = g_malloc0(sizeof dev->exp.aer_log.log[0] * diff --git a/hw/pci/shpc.c b/hw/pci/shpc.c index 3dcd472eba..42fafac91b 100644 --- a/hw/pci/shpc.c +++ b/hw/pci/shpc.c @@ -695,13 +695,16 @@ void shpc_cap_write_config(PCIDevice *d, uint32_t addr, uint32_t val, int l) shpc_cap_update_dword(d); } -static void shpc_save(QEMUFile *f, void *pv, size_t size) +static int shpc_save(QEMUFile *f, void *pv, size_t size, VMStateField *field, + QJSON *vmdesc) { PCIDevice *d = container_of(pv, PCIDevice, shpc); qemu_put_buffer(f, d->shpc->config, SHPC_SIZEOF(d)); + + return 0; } -static int shpc_load(QEMUFile *f, void *pv, size_t size) +static int shpc_load(QEMUFile *f, void *pv, size_t size, VMStateField *field) { PCIDevice *d = container_of(pv, PCIDevice, shpc); int ret = qemu_get_buffer(f, d->shpc->config, SHPC_SIZEOF(d)); diff --git a/hw/ppc/pnv_xscom.c b/hw/ppc/pnv_xscom.c index b82af4f086..38bc85f117 100644 --- a/hw/ppc/pnv_xscom.c +++ b/hw/ppc/pnv_xscom.c @@ -20,7 +20,7 @@ #include "qapi/error.h" #include "hw/hw.h" #include "qemu/log.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" #include "target/ppc/cpu.h" #include "hw/sysbus.h" diff --git a/hw/ppc/ppce500_spin.c b/hw/ppc/ppce500_spin.c index cf958a9e00..eb219abdff 100644 --- a/hw/ppc/ppce500_spin.c +++ b/hw/ppc/ppce500_spin.c @@ -29,9 +29,9 @@ #include "qemu/osdep.h" #include "hw/hw.h" -#include "sysemu/sysemu.h" #include "hw/sysbus.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" +#include "sysemu/sysemu.h" #include "e500.h" #define MAX_CPUS 32 diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index 208ef7b110..a642e663d4 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -36,7 +36,7 @@ #include "sysemu/device_tree.h" #include "sysemu/block-backend.h" #include "sysemu/cpus.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" #include "kvm_ppc.h" #include "migration/migration.h" #include "mmu-hash64.h" diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c index a0c44ee593..2de6377cca 100644 --- a/hw/ppc/spapr_drc.c +++ b/hw/ppc/spapr_drc.c @@ -59,7 +59,7 @@ static uint32_t set_isolation_state(sPAPRDRConnector *drc, trace_spapr_drc_set_isolation_state(get_index(drc), state); if (state == SPAPR_DR_ISOLATION_STATE_UNISOLATED) { - /* cannot unisolate a non-existant resource, and, or resources + /* cannot unisolate a non-existent resource, and, or resources * which are in an 'UNUSABLE' allocation state. (PAPR 2.7, 13.5.3.5) */ if (!drc->dev || diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c index 9a9bedf1bd..b2a8e48569 100644 --- a/hw/ppc/spapr_hcall.c +++ b/hw/ppc/spapr_hcall.c @@ -1,5 +1,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" +#include "sysemu/hw_accel.h" #include "sysemu/sysemu.h" #include "qemu/log.h" #include "cpu.h" @@ -9,7 +10,6 @@ #include "mmu-hash64.h" #include "cpu-models.h" #include "trace.h" -#include "sysemu/kvm.h" #include "kvm_ppc.h" #include "hw/ppc/spapr_ovec.h" diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c index 63f6248f1d..69b0291e8a 100644 --- a/hw/s390x/s390-pci-bus.c +++ b/hw/s390x/s390-pci-bus.c @@ -19,6 +19,7 @@ #include "s390-pci-bus.h" #include "s390-pci-inst.h" #include "hw/pci/pci_bus.h" +#include "hw/pci/pci_bridge.h" #include "hw/pci/msi.h" #include "qemu/error-report.h" @@ -31,7 +32,7 @@ do { } while (0) #endif -static S390pciState *s390_get_phb(void) +S390pciState *s390_get_phb(void) { static S390pciState *phb; @@ -91,35 +92,25 @@ int chsc_sei_nt2_have_event(void) return !QTAILQ_EMPTY(&s->pending_sei); } -S390PCIBusDevice *s390_pci_find_next_avail_dev(S390PCIBusDevice *pbdev) +S390PCIBusDevice *s390_pci_find_next_avail_dev(S390pciState *s, + S390PCIBusDevice *pbdev) { - int idx = 0; - S390PCIBusDevice *dev = NULL; - S390pciState *s = s390_get_phb(); - - if (pbdev) { - idx = (pbdev->fh & FH_MASK_INDEX) + 1; - } + S390PCIBusDevice *ret = pbdev ? QTAILQ_NEXT(pbdev, link) : + QTAILQ_FIRST(&s->zpci_devs); - for (; idx < PCI_SLOT_MAX; idx++) { - dev = s->pbdev[idx]; - if (dev && dev->state != ZPCI_FS_RESERVED) { - return dev; - } + while (ret && ret->state == ZPCI_FS_RESERVED) { + ret = QTAILQ_NEXT(ret, link); } - return NULL; + return ret; } -S390PCIBusDevice *s390_pci_find_dev_by_fid(uint32_t fid) +S390PCIBusDevice *s390_pci_find_dev_by_fid(S390pciState *s, uint32_t fid) { S390PCIBusDevice *pbdev; - int i; - S390pciState *s = s390_get_phb(); - for (i = 0; i < PCI_SLOT_MAX; i++) { - pbdev = s->pbdev[i]; - if (pbdev && pbdev->fid == fid) { + QTAILQ_FOREACH(pbdev, &s->zpci_devs, link) { + if (pbdev->fid == fid) { return pbdev; } } @@ -130,7 +121,8 @@ S390PCIBusDevice *s390_pci_find_dev_by_fid(uint32_t fid) void s390_pci_sclp_configure(SCCB *sccb) { PciCfgSccb *psccb = (PciCfgSccb *)sccb; - S390PCIBusDevice *pbdev = s390_pci_find_dev_by_fid(be32_to_cpu(psccb->aid)); + S390PCIBusDevice *pbdev = s390_pci_find_dev_by_fid(s390_get_phb(), + be32_to_cpu(psccb->aid)); uint16_t rc; if (be16_to_cpu(sccb->h.length) < 16) { @@ -162,7 +154,8 @@ out: void s390_pci_sclp_deconfigure(SCCB *sccb) { PciCfgSccb *psccb = (PciCfgSccb *)sccb; - S390PCIBusDevice *pbdev = s390_pci_find_dev_by_fid(be32_to_cpu(psccb->aid)); + S390PCIBusDevice *pbdev = s390_pci_find_dev_by_fid(s390_get_phb(), + be32_to_cpu(psccb->aid)); uint16_t rc; if (be16_to_cpu(sccb->h.length) < 16) { @@ -187,8 +180,8 @@ void s390_pci_sclp_deconfigure(SCCB *sccb) if (pbdev->summary_ind) { pci_dereg_irqs(pbdev); } - if (pbdev->iommu_enabled) { - pci_dereg_ioat(pbdev); + if (pbdev->iommu->enabled) { + pci_dereg_ioat(pbdev->iommu); } pbdev->state = ZPCI_FS_STANDBY; rc = SCLP_RC_NORMAL_COMPLETION; @@ -201,18 +194,11 @@ out: psccb->header.response_code = cpu_to_be16(rc); } -static S390PCIBusDevice *s390_pci_find_dev_by_uid(uint16_t uid) +static S390PCIBusDevice *s390_pci_find_dev_by_uid(S390pciState *s, uint16_t uid) { - int i; S390PCIBusDevice *pbdev; - S390pciState *s = s390_get_phb(); - - for (i = 0; i < PCI_SLOT_MAX; i++) { - pbdev = s->pbdev[i]; - if (!pbdev) { - continue; - } + QTAILQ_FOREACH(pbdev, &s->zpci_devs, link) { if (pbdev->uid == uid) { return pbdev; } @@ -221,22 +207,16 @@ static S390PCIBusDevice *s390_pci_find_dev_by_uid(uint16_t uid) return NULL; } -static S390PCIBusDevice *s390_pci_find_dev_by_target(const char *target) +static S390PCIBusDevice *s390_pci_find_dev_by_target(S390pciState *s, + const char *target) { - int i; S390PCIBusDevice *pbdev; - S390pciState *s = s390_get_phb(); if (!target) { return NULL; } - for (i = 0; i < PCI_SLOT_MAX; i++) { - pbdev = s->pbdev[i]; - if (!pbdev) { - continue; - } - + QTAILQ_FOREACH(pbdev, &s->zpci_devs, link) { if (!strcmp(pbdev->target, target)) { return pbdev; } @@ -245,19 +225,16 @@ static S390PCIBusDevice *s390_pci_find_dev_by_target(const char *target) return NULL; } -S390PCIBusDevice *s390_pci_find_dev_by_idx(uint32_t idx) +S390PCIBusDevice *s390_pci_find_dev_by_idx(S390pciState *s, uint32_t idx) { - S390pciState *s = s390_get_phb(); - - return s->pbdev[idx & FH_MASK_INDEX]; + return g_hash_table_lookup(s->zpci_table, &idx); } -S390PCIBusDevice *s390_pci_find_dev_by_fh(uint32_t fh) +S390PCIBusDevice *s390_pci_find_dev_by_fh(S390pciState *s, uint32_t fh) { - S390pciState *s = s390_get_phb(); - S390PCIBusDevice *pbdev; + uint32_t idx = FH_MASK_INDEX & fh; + S390PCIBusDevice *pbdev = s390_pci_find_dev_by_idx(s, idx); - pbdev = s->pbdev[fh & FH_MASK_INDEX]; if (pbdev && pbdev->fh == fh) { return pbdev; } @@ -377,12 +354,12 @@ out: return pte; } -static IOMMUTLBEntry s390_translate_iommu(MemoryRegion *iommu, hwaddr addr, +static IOMMUTLBEntry s390_translate_iommu(MemoryRegion *mr, hwaddr addr, bool is_write) { uint64_t pte; uint32_t flags; - S390PCIBusDevice *pbdev = container_of(iommu, S390PCIBusDevice, iommu_mr); + S390PCIIOMMU *iommu = container_of(mr, S390PCIIOMMU, iommu_mr); IOMMUTLBEntry ret = { .target_as = &address_space_memory, .iova = 0, @@ -391,10 +368,10 @@ static IOMMUTLBEntry s390_translate_iommu(MemoryRegion *iommu, hwaddr addr, .perm = IOMMU_NONE, }; - switch (pbdev->state) { + switch (iommu->pbdev->state) { case ZPCI_FS_ENABLED: case ZPCI_FS_BLOCKED: - if (!pbdev->iommu_enabled) { + if (!iommu->enabled) { return ret; } break; @@ -404,11 +381,11 @@ static IOMMUTLBEntry s390_translate_iommu(MemoryRegion *iommu, hwaddr addr, DPRINTF("iommu trans addr 0x%" PRIx64 "\n", addr); - if (addr < pbdev->pba || addr > pbdev->pal) { + if (addr < iommu->pba || addr > iommu->pal) { return ret; } - pte = s390_guest_io_table_walk(s390_pci_get_table_origin(pbdev->g_iota), + pte = s390_guest_io_table_walk(s390_pci_get_table_origin(iommu->g_iota), addr); if (!pte) { return ret; @@ -432,11 +409,48 @@ static const MemoryRegionIOMMUOps s390_iommu_ops = { .translate = s390_translate_iommu, }; +static S390PCIIOMMU *s390_pci_get_iommu(S390pciState *s, PCIBus *bus, + int devfn) +{ + uint64_t key = (uintptr_t)bus; + S390PCIIOMMUTable *table = g_hash_table_lookup(s->iommu_table, &key); + S390PCIIOMMU *iommu; + + if (!table) { + table = g_malloc0(sizeof(S390PCIIOMMUTable)); + table->key = key; + g_hash_table_insert(s->iommu_table, &table->key, table); + } + + iommu = table->iommu[PCI_SLOT(devfn)]; + if (!iommu) { + iommu = S390_PCI_IOMMU(object_new(TYPE_S390_PCI_IOMMU)); + + char *mr_name = g_strdup_printf("iommu-root-%02x:%02x.%01x", + pci_bus_num(bus), + PCI_SLOT(devfn), + PCI_FUNC(devfn)); + char *as_name = g_strdup_printf("iommu-pci-%02x:%02x.%01x", + pci_bus_num(bus), + PCI_SLOT(devfn), + PCI_FUNC(devfn)); + memory_region_init(&iommu->mr, OBJECT(iommu), mr_name, UINT64_MAX); + address_space_init(&iommu->as, &iommu->mr, as_name); + table->iommu[PCI_SLOT(devfn)] = iommu; + + g_free(mr_name); + g_free(as_name); + } + + return iommu; +} + static AddressSpace *s390_pci_dma_iommu(PCIBus *bus, void *opaque, int devfn) { S390pciState *s = opaque; + S390PCIIOMMU *iommu = s390_pci_get_iommu(s, bus, devfn); - return &s->iommu[PCI_SLOT(devfn)]->as; + return &iommu->as; } static uint8_t set_ind_atomic(uint64_t ind_loc, uint8_t to_be_set) @@ -503,34 +517,38 @@ static const MemoryRegionOps s390_msi_ctrl_ops = { .endianness = DEVICE_LITTLE_ENDIAN, }; -void s390_pci_iommu_enable(S390PCIBusDevice *pbdev) +void s390_pci_iommu_enable(S390PCIIOMMU *iommu) { - memory_region_init_iommu(&pbdev->iommu_mr, OBJECT(&pbdev->iommu->mr), - &s390_iommu_ops, "iommu-s390", pbdev->pal + 1); - memory_region_add_subregion(&pbdev->iommu->mr, 0, &pbdev->iommu_mr); - pbdev->iommu_enabled = true; + char *name = g_strdup_printf("iommu-s390-%04x", iommu->pbdev->uid); + memory_region_init_iommu(&iommu->iommu_mr, OBJECT(&iommu->mr), + &s390_iommu_ops, name, iommu->pal + 1); + iommu->enabled = true; + memory_region_add_subregion(&iommu->mr, 0, &iommu->iommu_mr); + g_free(name); } -void s390_pci_iommu_disable(S390PCIBusDevice *pbdev) +void s390_pci_iommu_disable(S390PCIIOMMU *iommu) { - memory_region_del_subregion(&pbdev->iommu->mr, &pbdev->iommu_mr); - object_unparent(OBJECT(&pbdev->iommu_mr)); - pbdev->iommu_enabled = false; + iommu->enabled = false; + memory_region_del_subregion(&iommu->mr, &iommu->iommu_mr); + object_unparent(OBJECT(&iommu->iommu_mr)); } -static void s390_pcihost_init_as(S390pciState *s) +static void s390_pci_iommu_free(S390pciState *s, PCIBus *bus, int32_t devfn) { - int i; - S390PCIIOMMU *iommu; + uint64_t key = (uintptr_t)bus; + S390PCIIOMMUTable *table = g_hash_table_lookup(s->iommu_table, &key); + S390PCIIOMMU *iommu = table ? table->iommu[PCI_SLOT(devfn)] : NULL; - for (i = 0; i < PCI_SLOT_MAX; i++) { - iommu = g_malloc0(sizeof(S390PCIIOMMU)); - memory_region_init(&iommu->mr, OBJECT(s), - "iommu-root-s390", UINT64_MAX); - address_space_init(&iommu->as, &iommu->mr, "iommu-pci"); - - s->iommu[i] = iommu; + if (!table || !iommu) { + return; } + + table->iommu[PCI_SLOT(devfn)] = NULL; + address_space_destroy(&iommu->as); + object_unparent(OBJECT(&iommu->mr)); + object_unparent(OBJECT(iommu)); + object_unref(OBJECT(iommu)); } static int s390_pcihost_init(SysBusDevice *dev) @@ -546,7 +564,6 @@ static int s390_pcihost_init(SysBusDevice *dev) s390_pci_set_irq, s390_pci_map_irq, NULL, get_system_memory(), get_system_io(), 0, 64, TYPE_PCI_BUS); - s390_pcihost_init_as(s); pci_setup_iommu(b, s390_pci_dma_iommu, s); bus = BUS(b); @@ -556,12 +573,18 @@ static int s390_pcihost_init(SysBusDevice *dev) s->bus = S390_PCI_BUS(qbus_create(TYPE_S390_PCI_BUS, DEVICE(s), NULL)); qbus_set_hotplug_handler(BUS(s->bus), DEVICE(s), NULL); + s->iommu_table = g_hash_table_new_full(g_int64_hash, g_int64_equal, + NULL, g_free); + s->zpci_table = g_hash_table_new_full(g_int_hash, g_int_equal, NULL, NULL); + s->bus_no = 0; QTAILQ_INIT(&s->pending_sei); + QTAILQ_INIT(&s->zpci_devs); return 0; } -static int s390_pci_setup_msix(S390PCIBusDevice *pbdev) +static int s390_pci_msix_init(S390PCIBusDevice *pbdev) { + char *name; uint8_t pos; uint16_t ctrl; uint32_t table, pba; @@ -569,7 +592,7 @@ static int s390_pci_setup_msix(S390PCIBusDevice *pbdev) pos = pci_find_capability(pbdev->pdev, PCI_CAP_ID_MSIX); if (!pos) { pbdev->msix.available = false; - return 0; + return -1; } ctrl = pci_host_config_read_common(pbdev->pdev, pos + PCI_MSIX_FLAGS, @@ -585,21 +608,15 @@ static int s390_pci_setup_msix(S390PCIBusDevice *pbdev) pbdev->msix.pba_offset = pba & ~PCI_MSIX_FLAGS_BIRMASK; pbdev->msix.entries = (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1; pbdev->msix.available = true; - return 0; -} - -static void s390_pci_msix_init(S390PCIBusDevice *pbdev) -{ - char *name; name = g_strdup_printf("msix-s390-%04x", pbdev->uid); - memory_region_init_io(&pbdev->msix_notify_mr, OBJECT(pbdev), &s390_msi_ctrl_ops, pbdev, name, PAGE_SIZE); memory_region_add_subregion(&pbdev->iommu->mr, ZPCI_MSI_ADDR, &pbdev->msix_notify_mr); - g_free(name); + + return 0; } static void s390_pci_msix_free(S390PCIBusDevice *pbdev) @@ -608,10 +625,10 @@ static void s390_pci_msix_free(S390PCIBusDevice *pbdev) object_unparent(OBJECT(&pbdev->msix_notify_mr)); } -static S390PCIBusDevice *s390_pci_device_new(const char *target) +static S390PCIBusDevice *s390_pci_device_new(S390pciState *s, + const char *target) { DeviceState *dev = NULL; - S390pciState *s = s390_get_phb(); dev = qdev_try_create(BUS(s->bus), TYPE_S390_PCI_DEVICE); if (!dev) { @@ -624,6 +641,24 @@ static S390PCIBusDevice *s390_pci_device_new(const char *target) return S390_PCI_DEVICE(dev); } +static bool s390_pci_alloc_idx(S390pciState *s, S390PCIBusDevice *pbdev) +{ + uint32_t idx; + + idx = s->next_idx; + while (s390_pci_find_dev_by_idx(s, idx)) { + idx = (idx + 1) & FH_MASK_INDEX; + if (idx == s->next_idx) { + return false; + } + } + + pbdev->idx = idx; + s->next_idx = (idx + 1) & FH_MASK_INDEX; + + return true; +} + static void s390_pcihost_hot_plug(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { @@ -631,7 +666,28 @@ static void s390_pcihost_hot_plug(HotplugHandler *hotplug_dev, S390PCIBusDevice *pbdev = NULL; S390pciState *s = s390_get_phb(); - if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_BRIDGE)) { + BusState *bus; + PCIBridge *pb = PCI_BRIDGE(dev); + PCIDevice *pdev = PCI_DEVICE(dev); + + pci_bridge_map_irq(pb, dev->id, s390_pci_map_irq); + pci_setup_iommu(&pb->sec_bus, s390_pci_dma_iommu, s); + + bus = BUS(&pb->sec_bus); + qbus_set_hotplug_handler(bus, DEVICE(s), errp); + + if (dev->hotplugged) { + pci_default_write_config(pdev, PCI_PRIMARY_BUS, s->bus_no, 1); + s->bus_no += 1; + pci_default_write_config(pdev, PCI_SECONDARY_BUS, s->bus_no, 1); + do { + pdev = pdev->bus->parent_dev; + pci_default_write_config(pdev, PCI_SUBORDINATE_BUS, + s->bus_no, 1); + } while (pdev->bus && pci_bus_num(pdev->bus)); + } + } else if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { pdev = PCI_DEVICE(dev); if (!dev->id) { @@ -643,9 +699,9 @@ static void s390_pcihost_hot_plug(HotplugHandler *hotplug_dev, PCI_FUNC(pdev->devfn)); } - pbdev = s390_pci_find_dev_by_target(dev->id); + pbdev = s390_pci_find_dev_by_target(s, dev->id); if (!pbdev) { - pbdev = s390_pci_device_new(dev->id); + pbdev = s390_pci_device_new(s, dev->id); if (!pbdev) { error_setg(errp, "create zpci device failed"); return; @@ -659,29 +715,30 @@ static void s390_pcihost_hot_plug(HotplugHandler *hotplug_dev, } pbdev->pdev = pdev; - pbdev->iommu = s->iommu[PCI_SLOT(pdev->devfn)]; + pbdev->iommu = s390_pci_get_iommu(s, pdev->bus, pdev->devfn); + pbdev->iommu->pbdev = pbdev; pbdev->state = ZPCI_FS_STANDBY; - s390_pci_msix_init(pbdev); - s390_pci_setup_msix(pbdev); + if (s390_pci_msix_init(pbdev)) { + error_setg(errp, "MSI-X support is mandatory " + "in the S390 architecture"); + return; + } if (dev->hotplugged) { s390_pci_generate_plug_event(HP_EVENT_RESERVED_TO_STANDBY, pbdev->fh, pbdev->fid); } } else if (object_dynamic_cast(OBJECT(dev), TYPE_S390_PCI_DEVICE)) { - int idx; - pbdev = S390_PCI_DEVICE(dev); - for (idx = 0; idx < PCI_SLOT_MAX; idx++) { - if (!s->pbdev[idx]) { - s->pbdev[idx] = pbdev; - pbdev->fh = idx; - return; - } - } - error_setg(errp, "no slot for plugging zpci device"); + if (!s390_pci_alloc_idx(s, pbdev)) { + error_setg(errp, "no slot for plugging zpci device"); + return; + } + pbdev->fh = pbdev->idx; + QTAILQ_INSERT_TAIL(&s->zpci_devs, pbdev, link); + g_hash_table_insert(s->zpci_table, &pbdev->idx, pbdev); } } @@ -692,8 +749,8 @@ static void s390_pcihost_timer_cb(void *opaque) if (pbdev->summary_ind) { pci_dereg_irqs(pbdev); } - if (pbdev->iommu_enabled) { - pci_dereg_ioat(pbdev); + if (pbdev->iommu->enabled) { + pci_dereg_ioat(pbdev->iommu); } pbdev->state = ZPCI_FS_STANDBY; @@ -705,17 +762,20 @@ static void s390_pcihost_timer_cb(void *opaque) static void s390_pcihost_hot_unplug(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { - int i; PCIDevice *pci_dev = NULL; + PCIBus *bus; + int32_t devfn; S390PCIBusDevice *pbdev = NULL; S390pciState *s = s390_get_phb(); - if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_BRIDGE)) { + error_setg(errp, "PCI bridge hot unplug currently not supported"); + return; + } else if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { pci_dev = PCI_DEVICE(dev); - for (i = 0 ; i < PCI_SLOT_MAX; i++) { - if (s->pbdev[i] && s->pbdev[i]->pdev == pci_dev) { - pbdev = s->pbdev[i]; + QTAILQ_FOREACH(pbdev, &s->zpci_devs, link) { + if (pbdev->pdev == pci_dev) { break; } } @@ -749,16 +809,58 @@ static void s390_pcihost_hot_unplug(HotplugHandler *hotplug_dev, s390_pci_generate_plug_event(HP_EVENT_STANDBY_TO_RESERVED, pbdev->fh, pbdev->fid); + bus = pci_dev->bus; + devfn = pci_dev->devfn; object_unparent(OBJECT(pci_dev)); s390_pci_msix_free(pbdev); + s390_pci_iommu_free(s, bus, devfn); pbdev->pdev = NULL; pbdev->state = ZPCI_FS_RESERVED; out: pbdev->fid = 0; - s->pbdev[pbdev->fh & FH_MASK_INDEX] = NULL; + QTAILQ_REMOVE(&s->zpci_devs, pbdev, link); + g_hash_table_remove(s->zpci_table, &pbdev->idx); object_unparent(OBJECT(pbdev)); } +static void s390_pci_enumerate_bridge(PCIBus *bus, PCIDevice *pdev, + void *opaque) +{ + S390pciState *s = opaque; + unsigned int primary = s->bus_no; + unsigned int subordinate = 0xff; + PCIBus *sec_bus = NULL; + + if ((pci_default_read_config(pdev, PCI_HEADER_TYPE, 1) != + PCI_HEADER_TYPE_BRIDGE)) { + return; + } + + (s->bus_no)++; + pci_default_write_config(pdev, PCI_PRIMARY_BUS, primary, 1); + pci_default_write_config(pdev, PCI_SECONDARY_BUS, s->bus_no, 1); + pci_default_write_config(pdev, PCI_SUBORDINATE_BUS, s->bus_no, 1); + + sec_bus = pci_bridge_get_sec_bus(PCI_BRIDGE(pdev)); + if (!sec_bus) { + return; + } + + pci_default_write_config(pdev, PCI_SUBORDINATE_BUS, subordinate, 1); + pci_for_each_device(sec_bus, pci_bus_num(sec_bus), + s390_pci_enumerate_bridge, s); + pci_default_write_config(pdev, PCI_SUBORDINATE_BUS, s->bus_no, 1); +} + +static void s390_pcihost_reset(DeviceState *dev) +{ + S390pciState *s = S390_PCI_HOST_BRIDGE(dev); + PCIBus *bus = s->parent_obj.bus; + + s->bus_no = 0; + pci_for_each_device(bus, pci_bus_num(bus), s390_pci_enumerate_bridge, s); +} + static void s390_pcihost_class_init(ObjectClass *klass, void *data) { SysBusDeviceClass *k = SYS_BUS_DEVICE_CLASS(klass); @@ -766,6 +868,7 @@ static void s390_pcihost_class_init(ObjectClass *klass, void *data) HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(klass); dc->cannot_instantiate_with_device_add_yet = true; + dc->reset = s390_pcihost_reset; k->init = s390_pcihost_init; hc->plug = s390_pcihost_hot_plug; hc->unplug = s390_pcihost_hot_unplug; @@ -789,13 +892,13 @@ static const TypeInfo s390_pcibus_info = { .instance_size = sizeof(S390PCIBus), }; -static uint16_t s390_pci_generate_uid(void) +static uint16_t s390_pci_generate_uid(S390pciState *s) { uint16_t uid = 0; do { uid++; - if (!s390_pci_find_dev_by_uid(uid)) { + if (!s390_pci_find_dev_by_uid(s, uid)) { return uid; } } while (uid < ZPCI_MAX_UID); @@ -803,12 +906,12 @@ static uint16_t s390_pci_generate_uid(void) return UID_UNDEFINED; } -static uint32_t s390_pci_generate_fid(Error **errp) +static uint32_t s390_pci_generate_fid(S390pciState *s, Error **errp) { uint32_t fid = 0; do { - if (!s390_pci_find_dev_by_fid(fid)) { + if (!s390_pci_find_dev_by_fid(s, fid)) { return fid; } } while (fid++ != ZPCI_MAX_FID); @@ -820,25 +923,26 @@ static uint32_t s390_pci_generate_fid(Error **errp) static void s390_pci_device_realize(DeviceState *dev, Error **errp) { S390PCIBusDevice *zpci = S390_PCI_DEVICE(dev); + S390pciState *s = s390_get_phb(); if (!zpci->target) { error_setg(errp, "target must be defined"); return; } - if (s390_pci_find_dev_by_target(zpci->target)) { + if (s390_pci_find_dev_by_target(s, zpci->target)) { error_setg(errp, "target %s already has an associated zpci device", zpci->target); return; } if (zpci->uid == UID_UNDEFINED) { - zpci->uid = s390_pci_generate_uid(); + zpci->uid = s390_pci_generate_uid(s); if (!zpci->uid) { error_setg(errp, "no free uid could be found"); return; } - } else if (s390_pci_find_dev_by_uid(zpci->uid)) { + } else if (s390_pci_find_dev_by_uid(s, zpci->uid)) { error_setg(errp, "uid %u already in use", zpci->uid); return; } @@ -846,12 +950,12 @@ static void s390_pci_device_realize(DeviceState *dev, Error **errp) if (!zpci->fid_defined) { Error *local_error = NULL; - zpci->fid = s390_pci_generate_fid(&local_error); + zpci->fid = s390_pci_generate_fid(s, &local_error); if (local_error) { error_propagate(errp, local_error); return; } - } else if (s390_pci_find_dev_by_fid(zpci->fid)) { + } else if (s390_pci_find_dev_by_fid(s, zpci->fid)) { error_setg(errp, "fid %u already in use", zpci->fid); return; } @@ -877,8 +981,8 @@ static void s390_pci_device_reset(DeviceState *dev) if (pbdev->summary_ind) { pci_dereg_irqs(pbdev); } - if (pbdev->iommu_enabled) { - pci_dereg_ioat(pbdev); + if (pbdev->iommu->enabled) { + pci_dereg_ioat(pbdev->iommu); } pbdev->fmb_addr = 0; @@ -944,11 +1048,18 @@ static const TypeInfo s390_pci_device_info = { .class_init = s390_pci_device_class_init, }; +static TypeInfo s390_pci_iommu_info = { + .name = TYPE_S390_PCI_IOMMU, + .parent = TYPE_OBJECT, + .instance_size = sizeof(S390PCIIOMMU), +}; + static void s390_pci_register_types(void) { type_register_static(&s390_pcihost_info); type_register_static(&s390_pcibus_info); type_register_static(&s390_pci_device_info); + type_register_static(&s390_pci_iommu_info); } type_init(s390_pci_register_types) diff --git a/hw/s390x/s390-pci-bus.h b/hw/s390x/s390-pci-bus.h index 7f2701301e..0aad9cc272 100644 --- a/hw/s390x/s390-pci-bus.h +++ b/hw/s390x/s390-pci-bus.h @@ -23,10 +23,11 @@ #define TYPE_S390_PCI_HOST_BRIDGE "s390-pcihost" #define TYPE_S390_PCI_BUS "s390-pcibus" #define TYPE_S390_PCI_DEVICE "zpci" +#define TYPE_S390_PCI_IOMMU "s390-pci-iommu" #define FH_MASK_ENABLE 0x80000000 #define FH_MASK_INSTANCE 0x7f000000 #define FH_MASK_SHM 0x00ff0000 -#define FH_MASK_INDEX 0x0000001f +#define FH_MASK_INDEX 0x0000ffff #define FH_SHM_VFIO 0x00010000 #define FH_SHM_EMUL 0x00020000 #define S390_PCIPT_ADAPTER 2 @@ -42,6 +43,8 @@ OBJECT_CHECK(S390PCIBus, (obj), TYPE_S390_PCI_BUS) #define S390_PCI_DEVICE(obj) \ OBJECT_CHECK(S390PCIBusDevice, (obj), TYPE_S390_PCI_DEVICE) +#define S390_PCI_IOMMU(obj) \ + OBJECT_CHECK(S390PCIIOMMU, (obj), TYPE_S390_PCI_IOMMU) #define HP_EVENT_TO_CONFIGURED 0x0301 #define HP_EVENT_RESERVED_TO_STANDBY 0x0302 @@ -180,8 +183,8 @@ enum ZpciIoatDtype { * may enter an error state * blocked: ignore all DMA and interrupts; transition back to enabled or from * error state via mpcifc - * error: an error occured; transition back to enabled via mpcifc - * permanent error: an unrecoverable error occured; transition to standby via + * error: an error occurred; transition back to enabled via mpcifc + * permanent error: an unrecoverable error occurred; transition to standby via * sclp deconfigure */ typedef enum { @@ -258,24 +261,34 @@ typedef struct S390MsixInfo { uint32_t pba_offset; } S390MsixInfo; +typedef struct S390PCIBusDevice S390PCIBusDevice; typedef struct S390PCIIOMMU { + Object parent_obj; + S390PCIBusDevice *pbdev; AddressSpace as; MemoryRegion mr; + MemoryRegion iommu_mr; + bool enabled; + uint64_t g_iota; + uint64_t pba; + uint64_t pal; } S390PCIIOMMU; +typedef struct S390PCIIOMMUTable { + uint64_t key; + S390PCIIOMMU *iommu[PCI_SLOT_MAX]; +} S390PCIIOMMUTable; + typedef struct S390PCIBusDevice { DeviceState qdev; PCIDevice *pdev; ZpciState state; - bool iommu_enabled; char *target; uint16_t uid; + uint32_t idx; uint32_t fh; uint32_t fid; bool fid_defined; - uint64_t g_iota; - uint64_t pba; - uint64_t pal; uint64_t fmb_addr; uint8_t isc; uint16_t noi; @@ -283,11 +296,11 @@ typedef struct S390PCIBusDevice { S390MsixInfo msix; AdapterRoutes routes; S390PCIIOMMU *iommu; - MemoryRegion iommu_mr; MemoryRegion msix_notify_mr; IndAddr *summary_ind; IndAddr *indicator; QEMUTimer *release_timer; + QTAILQ_ENTRY(S390PCIBusDevice) link; } S390PCIBusDevice; typedef struct S390PCIBus { @@ -296,23 +309,28 @@ typedef struct S390PCIBus { typedef struct S390pciState { PCIHostState parent_obj; + uint32_t next_idx; + int bus_no; S390PCIBus *bus; - S390PCIBusDevice *pbdev[PCI_SLOT_MAX]; - S390PCIIOMMU *iommu[PCI_SLOT_MAX]; + GHashTable *iommu_table; + GHashTable *zpci_table; QTAILQ_HEAD(, SeiContainer) pending_sei; + QTAILQ_HEAD(, S390PCIBusDevice) zpci_devs; } S390pciState; +S390pciState *s390_get_phb(void); int chsc_sei_nt2_get_event(void *res); int chsc_sei_nt2_have_event(void); void s390_pci_sclp_configure(SCCB *sccb); void s390_pci_sclp_deconfigure(SCCB *sccb); -void s390_pci_iommu_enable(S390PCIBusDevice *pbdev); -void s390_pci_iommu_disable(S390PCIBusDevice *pbdev); +void s390_pci_iommu_enable(S390PCIIOMMU *iommu); +void s390_pci_iommu_disable(S390PCIIOMMU *iommu); void s390_pci_generate_error_event(uint16_t pec, uint32_t fh, uint32_t fid, uint64_t faddr, uint32_t e); -S390PCIBusDevice *s390_pci_find_dev_by_idx(uint32_t idx); -S390PCIBusDevice *s390_pci_find_dev_by_fh(uint32_t fh); -S390PCIBusDevice *s390_pci_find_dev_by_fid(uint32_t fid); -S390PCIBusDevice *s390_pci_find_next_avail_dev(S390PCIBusDevice *pbdev); +S390PCIBusDevice *s390_pci_find_dev_by_idx(S390pciState *s, uint32_t idx); +S390PCIBusDevice *s390_pci_find_dev_by_fh(S390pciState *s, uint32_t fh); +S390PCIBusDevice *s390_pci_find_dev_by_fid(S390pciState *s, uint32_t fid); +S390PCIBusDevice *s390_pci_find_next_avail_dev(S390pciState *s, + S390PCIBusDevice *pbdev); #endif diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c index 0864d9be12..d2a8c0a083 100644 --- a/hw/s390x/s390-pci-inst.c +++ b/hw/s390x/s390-pci-inst.c @@ -18,6 +18,7 @@ #include "s390-pci-bus.h" #include "exec/memory-internal.h" #include "qemu/error-report.h" +#include "sysemu/hw_accel.h" /* #define DEBUG_S390PCI_INST */ #ifdef DEBUG_S390PCI_INST @@ -38,6 +39,7 @@ static void s390_set_status_code(CPUS390XState *env, static int list_pci(ClpReqRspListPci *rrb, uint8_t *cc) { S390PCIBusDevice *pbdev = NULL; + S390pciState *s = s390_get_phb(); uint32_t res_code, initial_l2, g_l2; int rc, i; uint64_t resume_token; @@ -65,14 +67,14 @@ static int list_pci(ClpReqRspListPci *rrb, uint8_t *cc) resume_token = ldq_p(&rrb->request.resume_token); if (resume_token) { - pbdev = s390_pci_find_dev_by_idx(resume_token); + pbdev = s390_pci_find_dev_by_idx(s, resume_token); if (!pbdev) { res_code = CLP_RC_LISTPCI_BADRT; rc = -EINVAL; goto out; } } else { - pbdev = s390_pci_find_next_avail_dev(NULL); + pbdev = s390_pci_find_next_avail_dev(s, NULL); } if (lduw_p(&rrb->response.hdr.len) < 48) { @@ -118,7 +120,7 @@ static int list_pci(ClpReqRspListPci *rrb, uint8_t *cc) lduw_p(&rrb->response.fh_list[i].device_id), ldl_p(&rrb->response.fh_list[i].fid), ldl_p(&rrb->response.fh_list[i].fh)); - pbdev = s390_pci_find_next_avail_dev(pbdev); + pbdev = s390_pci_find_next_avail_dev(s, pbdev); i++; } @@ -148,6 +150,7 @@ int clp_service_call(S390CPU *cpu, uint8_t r2) uint8_t buffer[4096 * 2]; uint8_t cc = 0; CPUS390XState *env = &cpu->env; + S390pciState *s = s390_get_phb(); int i; cpu_synchronize_state(CPU(cpu)); @@ -202,7 +205,7 @@ int clp_service_call(S390CPU *cpu, uint8_t r2) ClpReqSetPci *reqsetpci = (ClpReqSetPci *)reqh; ClpRspSetPci *ressetpci = (ClpRspSetPci *)resh; - pbdev = s390_pci_find_dev_by_fh(ldl_p(&reqsetpci->fh)); + pbdev = s390_pci_find_dev_by_fh(s, ldl_p(&reqsetpci->fh)); if (!pbdev) { stw_p(&ressetpci->hdr.rsp, CLP_RC_SETPCIFN_FH); goto out; @@ -253,7 +256,7 @@ int clp_service_call(S390CPU *cpu, uint8_t r2) ClpReqQueryPci *reqquery = (ClpReqQueryPci *)reqh; ClpRspQueryPci *resquery = (ClpRspQueryPci *)resh; - pbdev = s390_pci_find_dev_by_fh(ldl_p(&reqquery->fh)); + pbdev = s390_pci_find_dev_by_fh(s, ldl_p(&reqquery->fh)); if (!pbdev) { DPRINTF("query pci no pci dev\n"); stw_p(&resquery->hdr.rsp, CLP_RC_SETPCIFN_FH); @@ -338,7 +341,7 @@ int pcilg_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2) len = env->regs[r2] & 0xf; offset = env->regs[r2 + 1]; - pbdev = s390_pci_find_dev_by_fh(fh); + pbdev = s390_pci_find_dev_by_fh(s390_get_phb(), fh); if (!pbdev) { DPRINTF("pcilg no pci dev\n"); setcc(cpu, ZPCI_PCI_LS_INVAL_HANDLE); @@ -471,7 +474,7 @@ int pcistg_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2) len = env->regs[r2] & 0xf; offset = env->regs[r2 + 1]; - pbdev = s390_pci_find_dev_by_fh(fh); + pbdev = s390_pci_find_dev_by_fh(s390_get_phb(), fh); if (!pbdev) { DPRINTF("pcistg no pci dev\n"); setcc(cpu, ZPCI_PCI_LS_INVAL_HANDLE); @@ -555,6 +558,7 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2) CPUS390XState *env = &cpu->env; uint32_t fh; S390PCIBusDevice *pbdev; + S390PCIIOMMU *iommu; hwaddr start, end; IOMMUTLBEntry entry; MemoryRegion *mr; @@ -575,7 +579,7 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2) start = env->regs[r2]; end = start + env->regs[r2 + 1]; - pbdev = s390_pci_find_dev_by_fh(fh); + pbdev = s390_pci_find_dev_by_fh(s390_get_phb(), fh); if (!pbdev) { DPRINTF("rpcit no pci dev\n"); setcc(cpu, ZPCI_PCI_LS_INVAL_HANDLE); @@ -597,7 +601,8 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2) break; } - if (!pbdev->g_iota) { + iommu = pbdev->iommu; + if (!iommu->g_iota) { pbdev->state = ZPCI_FS_ERROR; setcc(cpu, ZPCI_PCI_LS_ERR); s390_set_status_code(env, r1, ZPCI_PCI_ST_INSUF_RES); @@ -606,7 +611,7 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2) goto out; } - if (end < pbdev->pba || start > pbdev->pal) { + if (end < iommu->pba || start > iommu->pal) { pbdev->state = ZPCI_FS_ERROR; setcc(cpu, ZPCI_PCI_LS_ERR); s390_set_status_code(env, r1, ZPCI_PCI_ST_INSUF_RES); @@ -615,7 +620,7 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2) goto out; } - mr = &pbdev->iommu_mr; + mr = &iommu->iommu_mr; while (start < end) { entry = mr->iommu_ops->translate(mr, start, 0); @@ -677,7 +682,7 @@ int pcistb_service_call(S390CPU *cpu, uint8_t r1, uint8_t r3, uint64_t gaddr, return 0; } - pbdev = s390_pci_find_dev_by_fh(fh); + pbdev = s390_pci_find_dev_by_fh(s390_get_phb(), fh); if (!pbdev) { DPRINTF("pcistb no pci dev fh 0x%x\n", fh); setcc(cpu, ZPCI_PCI_LS_INVAL_HANDLE); @@ -783,7 +788,7 @@ int pci_dereg_irqs(S390PCIBusDevice *pbdev) return 0; } -static int reg_ioat(CPUS390XState *env, S390PCIBusDevice *pbdev, ZpciFib fib) +static int reg_ioat(CPUS390XState *env, S390PCIIOMMU *iommu, ZpciFib fib) { uint64_t pba = ldq_p(&fib.pba); uint64_t pal = ldq_p(&fib.pal); @@ -803,21 +808,21 @@ static int reg_ioat(CPUS390XState *env, S390PCIBusDevice *pbdev, ZpciFib fib) return -EINVAL; } - pbdev->pba = pba; - pbdev->pal = pal; - pbdev->g_iota = g_iota; + iommu->pba = pba; + iommu->pal = pal; + iommu->g_iota = g_iota; - s390_pci_iommu_enable(pbdev); + s390_pci_iommu_enable(iommu); return 0; } -void pci_dereg_ioat(S390PCIBusDevice *pbdev) +void pci_dereg_ioat(S390PCIIOMMU *iommu) { - s390_pci_iommu_disable(pbdev); - pbdev->pba = 0; - pbdev->pal = 0; - pbdev->g_iota = 0; + s390_pci_iommu_disable(iommu); + iommu->pba = 0; + iommu->pal = 0; + iommu->g_iota = 0; } int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar) @@ -843,7 +848,7 @@ int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar) return 0; } - pbdev = s390_pci_find_dev_by_fh(fh); + pbdev = s390_pci_find_dev_by_fh(s390_get_phb(), fh); if (!pbdev) { DPRINTF("mpcifc no pci dev fh 0x%x\n", fh); setcc(cpu, ZPCI_PCI_LS_INVAL_HANDLE); @@ -892,10 +897,10 @@ int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar) if (dmaas != 0) { cc = ZPCI_PCI_LS_ERR; s390_set_status_code(env, r1, ZPCI_MOD_ST_DMAAS_INVAL); - } else if (pbdev->iommu_enabled) { + } else if (pbdev->iommu->enabled) { cc = ZPCI_PCI_LS_ERR; s390_set_status_code(env, r1, ZPCI_MOD_ST_SEQUENCE); - } else if (reg_ioat(env, pbdev, fib)) { + } else if (reg_ioat(env, pbdev->iommu, fib)) { cc = ZPCI_PCI_LS_ERR; s390_set_status_code(env, r1, ZPCI_MOD_ST_INSUF_RES); } @@ -904,23 +909,23 @@ int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar) if (dmaas != 0) { cc = ZPCI_PCI_LS_ERR; s390_set_status_code(env, r1, ZPCI_MOD_ST_DMAAS_INVAL); - } else if (!pbdev->iommu_enabled) { + } else if (!pbdev->iommu->enabled) { cc = ZPCI_PCI_LS_ERR; s390_set_status_code(env, r1, ZPCI_MOD_ST_SEQUENCE); } else { - pci_dereg_ioat(pbdev); + pci_dereg_ioat(pbdev->iommu); } break; case ZPCI_MOD_FC_REREG_IOAT: if (dmaas != 0) { cc = ZPCI_PCI_LS_ERR; s390_set_status_code(env, r1, ZPCI_MOD_ST_DMAAS_INVAL); - } else if (!pbdev->iommu_enabled) { + } else if (!pbdev->iommu->enabled) { cc = ZPCI_PCI_LS_ERR; s390_set_status_code(env, r1, ZPCI_MOD_ST_SEQUENCE); } else { - pci_dereg_ioat(pbdev); - if (reg_ioat(env, pbdev, fib)) { + pci_dereg_ioat(pbdev->iommu); + if (reg_ioat(env, pbdev->iommu, fib)) { cc = ZPCI_PCI_LS_ERR; s390_set_status_code(env, r1, ZPCI_MOD_ST_INSUF_RES); } @@ -988,7 +993,7 @@ int stpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar) return 0; } - pbdev = s390_pci_find_dev_by_idx(fh & FH_MASK_INDEX); + pbdev = s390_pci_find_dev_by_idx(s390_get_phb(), fh & FH_MASK_INDEX); if (!pbdev) { setcc(cpu, ZPCI_PCI_LS_INVAL_HANDLE); return 0; @@ -1015,7 +1020,7 @@ int stpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar) fib.fc |= 0x40; case ZPCI_FS_ENABLED: fib.fc |= 0x80; - if (pbdev->iommu_enabled) { + if (pbdev->iommu->enabled) { fib.fc |= 0x10; } if (!(fh & FH_MASK_ENABLE)) { @@ -1028,9 +1033,9 @@ int stpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar) return 0; } - stq_p(&fib.pba, pbdev->pba); - stq_p(&fib.pal, pbdev->pal); - stq_p(&fib.iota, pbdev->g_iota); + stq_p(&fib.pba, pbdev->iommu->pba); + stq_p(&fib.pal, pbdev->iommu->pal); + stq_p(&fib.iota, pbdev->iommu->g_iota); stq_p(&fib.aibv, pbdev->routes.adapter.ind_addr); stq_p(&fib.aisb, pbdev->routes.adapter.summary_addr); stq_p(&fib.fmb_addr, pbdev->fmb_addr); diff --git a/hw/s390x/s390-pci-inst.h b/hw/s390x/s390-pci-inst.h index 23f4bfa0ed..94a959f91c 100644 --- a/hw/s390x/s390-pci-inst.h +++ b/hw/s390x/s390-pci-inst.h @@ -292,7 +292,7 @@ typedef struct ZpciFib { } QEMU_PACKED ZpciFib; int pci_dereg_irqs(S390PCIBusDevice *pbdev); -void pci_dereg_ioat(S390PCIBusDevice *pbdev); +void pci_dereg_ioat(S390PCIIOMMU *iommu); int clp_service_call(S390CPU *cpu, uint8_t r2); int pcilg_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2); int pcistg_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2); diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index e340eab36b..e9a676797a 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -335,11 +335,13 @@ static const TypeInfo ccw_machine_info = { } \ type_init(ccw_machine_register_##suffix) +#define CCW_COMPAT_2_8 \ + HW_COMPAT_2_8 + #define CCW_COMPAT_2_7 \ HW_COMPAT_2_7 #define CCW_COMPAT_2_6 \ - CCW_COMPAT_2_7 \ HW_COMPAT_2_6 \ {\ .driver = TYPE_S390_IPL,\ @@ -352,7 +354,6 @@ static const TypeInfo ccw_machine_info = { }, #define CCW_COMPAT_2_5 \ - CCW_COMPAT_2_6 \ HW_COMPAT_2_5 #define CCW_COMPAT_2_4 \ @@ -395,14 +396,26 @@ static const TypeInfo ccw_machine_info = { .value = "0",\ }, +static void ccw_machine_2_9_instance_options(MachineState *machine) +{ +} + +static void ccw_machine_2_9_class_options(MachineClass *mc) +{ +} +DEFINE_CCW_MACHINE(2_9, "2.9", true); + static void ccw_machine_2_8_instance_options(MachineState *machine) { + ccw_machine_2_9_instance_options(machine); } static void ccw_machine_2_8_class_options(MachineClass *mc) { + ccw_machine_2_9_class_options(mc); + SET_MACHINE_COMPAT(mc, CCW_COMPAT_2_8); } -DEFINE_CCW_MACHINE(2_8, "2.8", true); +DEFINE_CCW_MACHINE(2_8, "2.8", false); static void ccw_machine_2_7_instance_options(MachineState *machine) { diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c index f5c1d98192..63c46373fb 100644 --- a/hw/s390x/virtio-ccw.c +++ b/hw/s390x/virtio-ccw.c @@ -149,7 +149,7 @@ static int virtio_ccw_set_vqs(SubchDev *sch, VqInfoBlock *info, } else { if (info) { /* virtio-1 allows changing the ring size. */ - if (virtio_queue_get_num(vdev, index) < num) { + if (virtio_queue_get_max_num(vdev, index) < num) { /* Fail if we exceed the maximum number. */ return -EINVAL; } @@ -1098,7 +1098,7 @@ static int virtio_ccw_set_guest_notifier(VirtioCcwDevice *dev, int n, * We do not support individual masking for channel devices, so we * need to manually trigger any guest masking callbacks here. */ - if (k->guest_notifier_mask) { + if (k->guest_notifier_mask && vdev->use_guest_notifier_mask) { k->guest_notifier_mask(vdev, n, false); } /* get lost events and re-inject */ @@ -1107,7 +1107,7 @@ static int virtio_ccw_set_guest_notifier(VirtioCcwDevice *dev, int n, event_notifier_set(notifier); } } else { - if (k->guest_notifier_mask) { + if (k->guest_notifier_mask && vdev->use_guest_notifier_mask) { k->guest_notifier_mask(vdev, n, true); } if (with_irqfd) { diff --git a/hw/scsi/megasas.c b/hw/scsi/megasas.c index 67fc1e7893..6aad7c9a06 100644 --- a/hw/scsi/megasas.c +++ b/hw/scsi/megasas.c @@ -683,14 +683,14 @@ static int megasas_map_dcmd(MegasasState *s, MegasasCmd *cmd) trace_megasas_dcmd_invalid_sge(cmd->index, cmd->frame->header.sge_count); cmd->iov_size = 0; - return -1; + return -EINVAL; } iov_pa = megasas_sgl_get_addr(cmd, &cmd->frame->dcmd.sgl); iov_size = megasas_sgl_get_len(cmd, &cmd->frame->dcmd.sgl); pci_dma_sglist_init(&cmd->qsg, PCI_DEVICE(s), 1); qemu_sglist_add(&cmd->qsg, iov_pa, iov_size); cmd->iov_size = iov_size; - return cmd->iov_size; + return 0; } static void megasas_finish_dcmd(MegasasCmd *cmd, uint32_t iov_size) @@ -1559,19 +1559,20 @@ static const struct dcmd_cmd_tbl_t { static int megasas_handle_dcmd(MegasasState *s, MegasasCmd *cmd) { - int opcode, len; + int opcode; int retval = 0; + size_t len; const struct dcmd_cmd_tbl_t *cmdptr = dcmd_cmd_tbl; opcode = le32_to_cpu(cmd->frame->dcmd.opcode); trace_megasas_handle_dcmd(cmd->index, opcode); - len = megasas_map_dcmd(s, cmd); - if (len < 0) { + if (megasas_map_dcmd(s, cmd) < 0) { return MFI_STAT_MEMORY_NOT_AVAILABLE; } while (cmdptr->opcode != -1 && cmdptr->opcode != opcode) { cmdptr++; } + len = cmd->iov_size; if (cmdptr->opcode == -1) { trace_megasas_dcmd_unhandled(cmd->index, opcode, len); retval = megasas_dcmd_dummy(s, cmd); @@ -2288,7 +2289,7 @@ static const VMStateDescription vmstate_megasas_gen2 = { .minimum_version_id = 0, .minimum_version_id_old = 0, .fields = (VMStateField[]) { - VMSTATE_PCIE_DEVICE(parent_obj, MegasasState), + VMSTATE_PCI_DEVICE(parent_obj, MegasasState), VMSTATE_MSIX(parent_obj, MegasasState), VMSTATE_INT32(fw_state, MegasasState), diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c index 297216dfcb..5940cb160c 100644 --- a/hw/scsi/scsi-bus.c +++ b/hw/scsi/scsi-bus.c @@ -1945,7 +1945,8 @@ SCSIDevice *scsi_device_find(SCSIBus *bus, int channel, int id, int lun) /* SCSI request list. For simplicity, pv points to the whole device */ -static void put_scsi_requests(QEMUFile *f, void *pv, size_t size) +static int put_scsi_requests(QEMUFile *f, void *pv, size_t size, + VMStateField *field, QJSON *vmdesc) { SCSIDevice *s = pv; SCSIBus *bus = DO_UPCAST(SCSIBus, qbus, s->qdev.parent_bus); @@ -1968,9 +1969,12 @@ static void put_scsi_requests(QEMUFile *f, void *pv, size_t size) } } qemu_put_sbyte(f, 0); + + return 0; } -static int get_scsi_requests(QEMUFile *f, void *pv, size_t size) +static int get_scsi_requests(QEMUFile *f, void *pv, size_t size, + VMStateField *field) { SCSIDevice *s = pv; SCSIBus *bus = DO_UPCAST(SCSIBus, qbus, s->qdev.parent_bus); diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c index bdd1e5f86c..cc06fe5f6c 100644 --- a/hw/scsi/scsi-disk.c +++ b/hw/scsi/scsi-disk.c @@ -2157,6 +2157,7 @@ static int32_t scsi_disk_dma_command(SCSIRequest *req, uint8_t *buf) DPRINTF("Write %s(sector %" PRId64 ", count %u)\n", (command & 0xe) == 0xe ? "And Verify " : "", r->req.cmd.lba, len); + /* fall through */ case VERIFY_10: case VERIFY_12: case VERIFY_16: @@ -2701,7 +2702,7 @@ static bool scsi_block_is_passthrough(SCSIDiskState *s, uint8_t *buf) * for the number of logical blocks specified in the length * field). For other modes, do not use scatter/gather operation. */ - if ((buf[1] & 6) != 2) { + if ((buf[1] & 6) == 2) { return false; } break; diff --git a/hw/scsi/vhost-scsi.c b/hw/scsi/vhost-scsi.c index 5b2694615f..c491ece1f2 100644 --- a/hw/scsi/vhost-scsi.c +++ b/hw/scsi/vhost-scsi.c @@ -238,8 +238,16 @@ static void vhost_scsi_realize(DeviceState *dev, Error **errp) vhost_dummy_handle_output); if (err != NULL) { error_propagate(errp, err); - close(vhostfd); - return; + goto close_fd; + } + + error_setg(&s->migration_blocker, + "vhost-scsi does not support migration"); + migrate_add_blocker(s->migration_blocker, &err); + if (err) { + error_propagate(errp, err); + error_free(s->migration_blocker); + goto close_fd; } s->dev.nvqs = VHOST_SCSI_VQ_NUM_FIXED + vs->conf.num_queues; @@ -252,7 +260,7 @@ static void vhost_scsi_realize(DeviceState *dev, Error **errp) if (ret < 0) { error_setg(errp, "vhost-scsi: vhost initialization failed: %s", strerror(-ret)); - return; + goto free_vqs; } /* At present, channel and lun both are 0 for bootable vhost-scsi disk */ @@ -261,9 +269,14 @@ static void vhost_scsi_realize(DeviceState *dev, Error **errp) /* Note: we can also get the minimum tpgt from kernel */ s->target = vs->conf.boot_tpgt; - error_setg(&s->migration_blocker, - "vhost-scsi does not support migration"); - migrate_add_blocker(s->migration_blocker); + return; + + free_vqs: + migrate_del_blocker(s->migration_blocker); + g_free(s->dev.vqs); + close_fd: + close(vhostfd); + return; } static void vhost_scsi_unrealize(DeviceState *dev, Error **errp) diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c index 34bba35d83..ce19efffc8 100644 --- a/hw/scsi/virtio-scsi.c +++ b/hw/scsi/virtio-scsi.c @@ -198,12 +198,14 @@ static void *virtio_scsi_load_request(QEMUFile *f, SCSIRequest *sreq) SCSIBus *bus = sreq->bus; VirtIOSCSI *s = container_of(bus, VirtIOSCSI, bus); VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s); + VirtIODevice *vdev = VIRTIO_DEVICE(s); VirtIOSCSIReq *req; uint32_t n; qemu_get_be32s(f, &n); assert(n < vs->conf.num_queues); - req = qemu_get_virtqueue_element(f, sizeof(VirtIOSCSIReq) + vs->cdb_size); + req = qemu_get_virtqueue_element(vdev, f, + sizeof(VirtIOSCSIReq) + vs->cdb_size); virtio_scsi_init_req(s, vs->cmd_vqs[n], req); if (virtio_scsi_parse_req(req, sizeof(VirtIOSCSICmdReq) + vs->cdb_size, @@ -592,26 +594,32 @@ static void virtio_scsi_handle_cmd_req_submit(VirtIOSCSI *s, VirtIOSCSIReq *req) void virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq) { VirtIOSCSIReq *req, *next; - int ret; + int ret = 0; QTAILQ_HEAD(, VirtIOSCSIReq) reqs = QTAILQ_HEAD_INITIALIZER(reqs); - while ((req = virtio_scsi_pop_req(s, vq))) { - ret = virtio_scsi_handle_cmd_req_prepare(s, req); - if (!ret) { - QTAILQ_INSERT_TAIL(&reqs, req, next); - } else if (ret == -EINVAL) { - /* The device is broken and shouldn't process any request */ - while (!QTAILQ_EMPTY(&reqs)) { - req = QTAILQ_FIRST(&reqs); - QTAILQ_REMOVE(&reqs, req, next); - blk_io_unplug(req->sreq->dev->conf.blk); - scsi_req_unref(req->sreq); - virtqueue_detach_element(req->vq, &req->elem, 0); - virtio_scsi_free_req(req); + do { + virtio_queue_set_notification(vq, 0); + + while ((req = virtio_scsi_pop_req(s, vq))) { + ret = virtio_scsi_handle_cmd_req_prepare(s, req); + if (!ret) { + QTAILQ_INSERT_TAIL(&reqs, req, next); + } else if (ret == -EINVAL) { + /* The device is broken and shouldn't process any request */ + while (!QTAILQ_EMPTY(&reqs)) { + req = QTAILQ_FIRST(&reqs); + QTAILQ_REMOVE(&reqs, req, next); + blk_io_unplug(req->sreq->dev->conf.blk); + scsi_req_unref(req->sreq); + virtqueue_detach_element(req->vq, &req->elem, 0); + virtio_scsi_free_req(req); + } } } - } + + virtio_queue_set_notification(vq, 1); + } while (ret != -EINVAL && !virtio_queue_empty(vq)); QTAILQ_FOREACH_SAFE(req, &reqs, next, next) { virtio_scsi_handle_cmd_req_submit(s, req); diff --git a/hw/scsi/vmw_pvscsi.c b/hw/scsi/vmw_pvscsi.c index a5ce7dea8e..75575461e2 100644 --- a/hw/scsi/vmw_pvscsi.c +++ b/hw/scsi/vmw_pvscsi.c @@ -1207,7 +1207,7 @@ static const VMStateDescription vmstate_pvscsi_pcie_device = { .name = "pvscsi/pcie", .needed = pvscsi_vmstate_need_pcie_device, .fields = (VMStateField[]) { - VMSTATE_PCIE_DEVICE(parent_obj, PVSCSIState), + VMSTATE_PCI_DEVICE(parent_obj, PVSCSIState), VMSTATE_END_OF_LIST() } }; diff --git a/hw/sh4/sh7750.c b/hw/sh4/sh7750.c index 3132d559d7..166e4bd947 100644 --- a/hw/sh4/sh7750.c +++ b/hw/sh4/sh7750.c @@ -417,7 +417,7 @@ static void sh7750_mem_writel(void *opaque, hwaddr addr, case SH7750_PTEH_A7: /* If asid changes, clear all registered tlb entries. */ if ((s->cpu->env.pteh & 0xff) != (mem_value & 0xff)) { - tlb_flush(CPU(s->cpu), 1); + tlb_flush(CPU(s->cpu)); } s->cpu->env.pteh = mem_value; return; diff --git a/hw/smbios/Makefile.objs b/hw/smbios/Makefile.objs index c3d3753602..23bb2bac07 100644 --- a/hw/smbios/Makefile.objs +++ b/hw/smbios/Makefile.objs @@ -1,2 +1,10 @@ -common-obj-$(CONFIG_SMBIOS) += smbios.o -common-obj-$(call land,$(CONFIG_SMBIOS),$(CONFIG_IPMI)) += smbios_type_38.o +ifeq ($(CONFIG_SMBIOS),y) +common-obj-y += smbios.o +common-obj-$(CONFIG_IPMI) += smbios_type_38.o +common-obj-$(call lnot,$(CONFIG_IPMI)) += smbios_type_38-stub.o +else +common-obj-y += smbios-stub.o +endif + +common-obj-$(CONFIG_ALL) += smbios-stub.o +common-obj-$(CONFIG_ALL) += smbios_type_38-stub.o diff --git a/hw/smbios/smbios-stub.c b/hw/smbios/smbios-stub.c new file mode 100644 index 0000000000..308739410f --- /dev/null +++ b/hw/smbios/smbios-stub.c @@ -0,0 +1,31 @@ +/* + * SMBIOS stubs for platforms that don't support SMBIOS. + * + * Copyright (c) 2010 Isaku Yamahata <yamahata at valinux co jp> + * VA Linux Systems Japan K.K. + * Copyright (c) 2016 Leif Lindholm <leif.lindholm@linaro.org> + * Linaro Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qapi/qmp/qerror.h" +#include "qmp-commands.h" +#include "hw/smbios/smbios.h" + +void smbios_entry_add(QemuOpts *opts, Error **errp) +{ + error_setg(errp, QERR_UNSUPPORTED); +} diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c index 3a96cededd..1a5437a07d 100644 --- a/hw/smbios/smbios.c +++ b/hw/smbios/smbios.c @@ -882,7 +882,7 @@ static void save_opt(const char **dest, QemuOpts *opts, const char *name) } } -void smbios_entry_add(QemuOpts *opts) +void smbios_entry_add(QemuOpts *opts, Error **errp) { const char *val; diff --git a/hw/smbios/smbios_type_38-stub.c b/hw/smbios/smbios_type_38-stub.c new file mode 100644 index 0000000000..9528c2c28e --- /dev/null +++ b/hw/smbios/smbios_type_38-stub.c @@ -0,0 +1,14 @@ +/* + * IPMI SMBIOS firmware handling + * + * Copyright (c) 2015,2016 Corey Minyard, MontaVista Software, LLC + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "hw/smbios/ipmi.h" + +void smbios_build_type_38_table(void) +{ +} diff --git a/hw/sparc64/Makefile.objs b/hw/sparc64/Makefile.objs index a84cfe3ec7..cf9de21133 100644 --- a/hw/sparc64/Makefile.objs +++ b/hw/sparc64/Makefile.objs @@ -1 +1,3 @@ +obj-y += sparc64.o obj-y += sun4u.o +obj-y += niagara.o
\ No newline at end of file diff --git a/hw/sparc64/niagara.c b/hw/sparc64/niagara.c new file mode 100644 index 0000000000..b55d4bb8d3 --- /dev/null +++ b/hw/sparc64/niagara.c @@ -0,0 +1,177 @@ +/* + * QEMU Sun4v/Niagara System Emulator + * + * Copyright (c) 2016 Artyom Tarasenko + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu-common.h" +#include "cpu.h" +#include "hw/hw.h" +#include "hw/boards.h" +#include "hw/char/serial.h" +#include "hw/empty_slot.h" +#include "hw/loader.h" +#include "hw/sparc/sparc64.h" +#include "hw/timer/sun4v-rtc.h" +#include "exec/address-spaces.h" +#include "sysemu/block-backend.h" + + +typedef struct NiagaraBoardState { + MemoryRegion hv_ram; + MemoryRegion partition_ram; + MemoryRegion nvram; + MemoryRegion md_rom; + MemoryRegion hv_rom; + MemoryRegion vdisk_ram; + MemoryRegion prom; +} NiagaraBoardState; + +#define NIAGARA_HV_RAM_BASE 0x100000ULL +#define NIAGARA_HV_RAM_SIZE 0x3f00000ULL /* 63 MiB */ + +#define NIAGARA_PARTITION_RAM_BASE 0x80000000ULL + +#define NIAGARA_UART_BASE 0x1f10000000ULL + +#define NIAGARA_NVRAM_BASE 0x1f11000000ULL +#define NIAGARA_NVRAM_SIZE 0x2000 + +#define NIAGARA_MD_ROM_BASE 0x1f12000000ULL +#define NIAGARA_MD_ROM_SIZE 0x2000 + +#define NIAGARA_HV_ROM_BASE 0x1f12080000ULL +#define NIAGARA_HV_ROM_SIZE 0x2000 + +#define NIAGARA_IOBBASE 0x9800000000ULL +#define NIAGARA_IOBSIZE 0x0100000000ULL + +#define NIAGARA_VDISK_BASE 0x1f40000000ULL +#define NIAGARA_RTC_BASE 0xfff0c1fff8ULL +#define NIAGARA_UART_BASE 0x1f10000000ULL + +/* Firmware layout + * + * |------------------| + * | openboot.bin | + * |------------------| PROM_ADDR + OBP_OFFSET + * | q.bin | + * |------------------| PROM_ADDR + Q_OFFSET + * | reset.bin | + * |------------------| PROM_ADDR + */ +#define NIAGARA_PROM_BASE 0xfff0000000ULL +#define NIAGARA_Q_OFFSET 0x10000ULL +#define NIAGARA_OBP_OFFSET 0x80000ULL +#define PROM_SIZE_MAX (4 * 1024 * 1024) + +/* Niagara hardware initialisation */ +static void niagara_init(MachineState *machine) +{ + NiagaraBoardState *s = g_new(NiagaraBoardState, 1); + DriveInfo *dinfo = drive_get_next(IF_PFLASH); + MemoryRegion *sysmem = get_system_memory(); + + /* init CPUs */ + sparc64_cpu_devinit(machine->cpu_model, "Sun UltraSparc T1", + NIAGARA_PROM_BASE); + /* set up devices */ + memory_region_allocate_system_memory(&s->hv_ram, NULL, "sun4v-hv.ram", + NIAGARA_HV_RAM_SIZE); + memory_region_add_subregion(sysmem, NIAGARA_HV_RAM_BASE, &s->hv_ram); + + memory_region_allocate_system_memory(&s->partition_ram, NULL, + "sun4v-partition.ram", + machine->ram_size); + memory_region_add_subregion(sysmem, NIAGARA_PARTITION_RAM_BASE, + &s->partition_ram); + + memory_region_allocate_system_memory(&s->nvram, NULL, + "sun4v.nvram", NIAGARA_NVRAM_SIZE); + memory_region_add_subregion(sysmem, NIAGARA_NVRAM_BASE, &s->nvram); + memory_region_allocate_system_memory(&s->md_rom, NULL, + "sun4v-md.rom", NIAGARA_MD_ROM_SIZE); + memory_region_add_subregion(sysmem, NIAGARA_MD_ROM_BASE, &s->md_rom); + memory_region_allocate_system_memory(&s->hv_rom, NULL, + "sun4v-hv.rom", NIAGARA_HV_ROM_SIZE); + memory_region_add_subregion(sysmem, NIAGARA_HV_ROM_BASE, &s->hv_rom); + memory_region_allocate_system_memory(&s->prom, NULL, + "sun4v.prom", PROM_SIZE_MAX); + memory_region_add_subregion(sysmem, NIAGARA_PROM_BASE, &s->prom); + + rom_add_file_fixed("nvram1", NIAGARA_NVRAM_BASE, -1); + rom_add_file_fixed("1up-md.bin", NIAGARA_MD_ROM_BASE, -1); + rom_add_file_fixed("1up-hv.bin", NIAGARA_HV_ROM_BASE, -1); + + rom_add_file_fixed("reset.bin", NIAGARA_PROM_BASE, -1); + rom_add_file_fixed("q.bin", NIAGARA_PROM_BASE + NIAGARA_Q_OFFSET, -1); + rom_add_file_fixed("openboot.bin", NIAGARA_PROM_BASE + NIAGARA_OBP_OFFSET, + -1); + + /* the virtual ramdisk is kind of initrd, but it resides + outside of the partition RAM */ + if (dinfo) { + BlockBackend *blk = blk_by_legacy_dinfo(dinfo); + int size = blk_getlength(blk); + if (size > 0) { + memory_region_allocate_system_memory(&s->vdisk_ram, NULL, + "sun4v_vdisk.ram", size); + memory_region_add_subregion(get_system_memory(), + NIAGARA_VDISK_BASE, &s->vdisk_ram); + dinfo->is_default = 1; + rom_add_file_fixed(blk_bs(blk)->filename, NIAGARA_VDISK_BASE, -1); + } else { + fprintf(stderr, "qemu: could not load ram disk '%s'\n", + blk_bs(blk)->filename); + exit(1); + } + } + serial_mm_init(sysmem, NIAGARA_UART_BASE, 0, NULL, 115200, + serial_hds[0], DEVICE_BIG_ENDIAN); + + empty_slot_init(NIAGARA_IOBBASE, NIAGARA_IOBSIZE); + sun4v_rtc_init(NIAGARA_RTC_BASE); +} + +static void niagara_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + + mc->desc = "Sun4v platform, Niagara"; + mc->init = niagara_init; + mc->max_cpus = 1; /* XXX for now */ + mc->default_boot_order = "c"; +} + +static const TypeInfo niagara_type = { + .name = MACHINE_TYPE_NAME("niagara"), + .parent = TYPE_MACHINE, + .class_init = niagara_class_init, +}; + +static void niagara_register_types(void) +{ + type_register_static(&niagara_type); +} + +type_init(niagara_register_types) diff --git a/hw/sparc64/sparc64.c b/hw/sparc64/sparc64.c new file mode 100644 index 0000000000..b3d219c769 --- /dev/null +++ b/hw/sparc64/sparc64.c @@ -0,0 +1,378 @@ +/* + * QEMU Sun4u/Sun4v System Emulator common routines + * + * Copyright (c) 2005 Fabrice Bellard + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + + +#include "qemu/osdep.h" +#include "cpu.h" +#include "hw/char/serial.h" +#include "hw/sparc/sparc64.h" +#include "qemu/timer.h" + + +//#define DEBUG_IRQ +//#define DEBUG_TIMER + +#ifdef DEBUG_IRQ +#define CPUIRQ_DPRINTF(fmt, ...) \ + do { printf("CPUIRQ: " fmt , ## __VA_ARGS__); } while (0) +#else +#define CPUIRQ_DPRINTF(fmt, ...) +#endif + +#ifdef DEBUG_TIMER +#define TIMER_DPRINTF(fmt, ...) \ + do { printf("TIMER: " fmt , ## __VA_ARGS__); } while (0) +#else +#define TIMER_DPRINTF(fmt, ...) +#endif + +#define TICK_MAX 0x7fffffffffffffffULL + +void cpu_check_irqs(CPUSPARCState *env) +{ + CPUState *cs; + uint32_t pil = env->pil_in | + (env->softint & ~(SOFTINT_TIMER | SOFTINT_STIMER)); + + /* TT_IVEC has a higher priority (16) than TT_EXTINT (31..17) */ + if (env->ivec_status & 0x20) { + return; + } + cs = CPU(sparc_env_get_cpu(env)); + /* check if TM or SM in SOFTINT are set + setting these also causes interrupt 14 */ + if (env->softint & (SOFTINT_TIMER | SOFTINT_STIMER)) { + pil |= 1 << 14; + } + + /* The bit corresponding to psrpil is (1<< psrpil), the next bit + is (2 << psrpil). */ + if (pil < (2 << env->psrpil)) { + if (cs->interrupt_request & CPU_INTERRUPT_HARD) { + CPUIRQ_DPRINTF("Reset CPU IRQ (current interrupt %x)\n", + env->interrupt_index); + env->interrupt_index = 0; + cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); + } + return; + } + + if (cpu_interrupts_enabled(env)) { + + unsigned int i; + + for (i = 15; i > env->psrpil; i--) { + if (pil & (1 << i)) { + int old_interrupt = env->interrupt_index; + int new_interrupt = TT_EXTINT | i; + + if (unlikely(env->tl > 0 && cpu_tsptr(env)->tt > new_interrupt + && ((cpu_tsptr(env)->tt & 0x1f0) == TT_EXTINT))) { + CPUIRQ_DPRINTF("Not setting CPU IRQ: TL=%d " + "current %x >= pending %x\n", + env->tl, cpu_tsptr(env)->tt, new_interrupt); + } else if (old_interrupt != new_interrupt) { + env->interrupt_index = new_interrupt; + CPUIRQ_DPRINTF("Set CPU IRQ %d old=%x new=%x\n", i, + old_interrupt, new_interrupt); + cpu_interrupt(cs, CPU_INTERRUPT_HARD); + } + break; + } + } + } else if (cs->interrupt_request & CPU_INTERRUPT_HARD) { + CPUIRQ_DPRINTF("Interrupts disabled, pil=%08x pil_in=%08x softint=%08x " + "current interrupt %x\n", + pil, env->pil_in, env->softint, env->interrupt_index); + env->interrupt_index = 0; + cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); + } +} + +static void cpu_kick_irq(SPARCCPU *cpu) +{ + CPUState *cs = CPU(cpu); + CPUSPARCState *env = &cpu->env; + + cs->halted = 0; + cpu_check_irqs(env); + qemu_cpu_kick(cs); +} + +void sparc64_cpu_set_ivec_irq(void *opaque, int irq, int level) +{ + SPARCCPU *cpu = opaque; + CPUSPARCState *env = &cpu->env; + CPUState *cs; + + if (level) { + if (!(env->ivec_status & 0x20)) { + CPUIRQ_DPRINTF("Raise IVEC IRQ %d\n", irq); + cs = CPU(cpu); + cs->halted = 0; + env->interrupt_index = TT_IVEC; + env->ivec_status |= 0x20; + env->ivec_data[0] = (0x1f << 6) | irq; + env->ivec_data[1] = 0; + env->ivec_data[2] = 0; + cpu_interrupt(cs, CPU_INTERRUPT_HARD); + } + } else { + if (env->ivec_status & 0x20) { + CPUIRQ_DPRINTF("Lower IVEC IRQ %d\n", irq); + cs = CPU(cpu); + env->ivec_status &= ~0x20; + cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); + } + } +} + +typedef struct ResetData { + SPARCCPU *cpu; + uint64_t prom_addr; +} ResetData; + +static CPUTimer *cpu_timer_create(const char *name, SPARCCPU *cpu, + QEMUBHFunc *cb, uint32_t frequency, + uint64_t disabled_mask, uint64_t npt_mask) +{ + CPUTimer *timer = g_malloc0(sizeof(CPUTimer)); + + timer->name = name; + timer->frequency = frequency; + timer->disabled_mask = disabled_mask; + timer->npt_mask = npt_mask; + + timer->disabled = 1; + timer->npt = 1; + timer->clock_offset = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + + timer->qtimer = timer_new_ns(QEMU_CLOCK_VIRTUAL, cb, cpu); + + return timer; +} + +static void cpu_timer_reset(CPUTimer *timer) +{ + timer->disabled = 1; + timer->clock_offset = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + + timer_del(timer->qtimer); +} + +static void main_cpu_reset(void *opaque) +{ + ResetData *s = (ResetData *)opaque; + CPUSPARCState *env = &s->cpu->env; + static unsigned int nr_resets; + + cpu_reset(CPU(s->cpu)); + + cpu_timer_reset(env->tick); + cpu_timer_reset(env->stick); + cpu_timer_reset(env->hstick); + + env->gregs[1] = 0; /* Memory start */ + env->gregs[2] = ram_size; /* Memory size */ + env->gregs[3] = 0; /* Machine description XXX */ + if (nr_resets++ == 0) { + /* Power on reset */ + env->pc = s->prom_addr + 0x20ULL; + } else { + env->pc = s->prom_addr + 0x40ULL; + } + env->npc = env->pc + 4; +} + +static void tick_irq(void *opaque) +{ + SPARCCPU *cpu = opaque; + CPUSPARCState *env = &cpu->env; + + CPUTimer *timer = env->tick; + + if (timer->disabled) { + CPUIRQ_DPRINTF("tick_irq: softint disabled\n"); + return; + } else { + CPUIRQ_DPRINTF("tick: fire\n"); + } + + env->softint |= SOFTINT_TIMER; + cpu_kick_irq(cpu); +} + +static void stick_irq(void *opaque) +{ + SPARCCPU *cpu = opaque; + CPUSPARCState *env = &cpu->env; + + CPUTimer *timer = env->stick; + + if (timer->disabled) { + CPUIRQ_DPRINTF("stick_irq: softint disabled\n"); + return; + } else { + CPUIRQ_DPRINTF("stick: fire\n"); + } + + env->softint |= SOFTINT_STIMER; + cpu_kick_irq(cpu); +} + +static void hstick_irq(void *opaque) +{ + SPARCCPU *cpu = opaque; + CPUSPARCState *env = &cpu->env; + + CPUTimer *timer = env->hstick; + + if (timer->disabled) { + CPUIRQ_DPRINTF("hstick_irq: softint disabled\n"); + return; + } else { + CPUIRQ_DPRINTF("hstick: fire\n"); + } + + env->softint |= SOFTINT_STIMER; + cpu_kick_irq(cpu); +} + +static int64_t cpu_to_timer_ticks(int64_t cpu_ticks, uint32_t frequency) +{ + return muldiv64(cpu_ticks, NANOSECONDS_PER_SECOND, frequency); +} + +static uint64_t timer_to_cpu_ticks(int64_t timer_ticks, uint32_t frequency) +{ + return muldiv64(timer_ticks, frequency, NANOSECONDS_PER_SECOND); +} + +void cpu_tick_set_count(CPUTimer *timer, uint64_t count) +{ + uint64_t real_count = count & ~timer->npt_mask; + uint64_t npt_bit = count & timer->npt_mask; + + int64_t vm_clock_offset = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - + cpu_to_timer_ticks(real_count, timer->frequency); + + TIMER_DPRINTF("%s set_count count=0x%016lx (npt %s) p=%p\n", + timer->name, real_count, + timer->npt ? "disabled" : "enabled", timer); + + timer->npt = npt_bit ? 1 : 0; + timer->clock_offset = vm_clock_offset; +} + +uint64_t cpu_tick_get_count(CPUTimer *timer) +{ + uint64_t real_count = timer_to_cpu_ticks( + qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - timer->clock_offset, + timer->frequency); + + TIMER_DPRINTF("%s get_count count=0x%016lx (npt %s) p=%p\n", + timer->name, real_count, + timer->npt ? "disabled" : "enabled", timer); + + if (timer->npt) { + real_count |= timer->npt_mask; + } + + return real_count; +} + +void cpu_tick_set_limit(CPUTimer *timer, uint64_t limit) +{ + int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + + uint64_t real_limit = limit & ~timer->disabled_mask; + timer->disabled = (limit & timer->disabled_mask) ? 1 : 0; + + int64_t expires = cpu_to_timer_ticks(real_limit, timer->frequency) + + timer->clock_offset; + + if (expires < now) { + expires = now + 1; + } + + TIMER_DPRINTF("%s set_limit limit=0x%016lx (%s) p=%p " + "called with limit=0x%016lx at 0x%016lx (delta=0x%016lx)\n", + timer->name, real_limit, + timer->disabled ? "disabled" : "enabled", + timer, limit, + timer_to_cpu_ticks(now - timer->clock_offset, + timer->frequency), + timer_to_cpu_ticks(expires - now, timer->frequency)); + + if (!real_limit) { + TIMER_DPRINTF("%s set_limit limit=ZERO - not starting timer\n", + timer->name); + timer_del(timer->qtimer); + } else if (timer->disabled) { + timer_del(timer->qtimer); + } else { + timer_mod(timer->qtimer, expires); + } +} + +SPARCCPU *sparc64_cpu_devinit(const char *cpu_model, + const char *default_cpu_model, uint64_t prom_addr) +{ + SPARCCPU *cpu; + CPUSPARCState *env; + ResetData *reset_info; + + uint32_t tick_frequency = 100 * 1000000; + uint32_t stick_frequency = 100 * 1000000; + uint32_t hstick_frequency = 100 * 1000000; + + if (cpu_model == NULL) { + cpu_model = default_cpu_model; + } + cpu = cpu_sparc_init(cpu_model); + if (cpu == NULL) { + fprintf(stderr, "Unable to find Sparc CPU definition\n"); + exit(1); + } + env = &cpu->env; + + env->tick = cpu_timer_create("tick", cpu, tick_irq, + tick_frequency, TICK_INT_DIS, + TICK_NPT_MASK); + + env->stick = cpu_timer_create("stick", cpu, stick_irq, + stick_frequency, TICK_INT_DIS, + TICK_NPT_MASK); + + env->hstick = cpu_timer_create("hstick", cpu, hstick_irq, + hstick_frequency, TICK_INT_DIS, + TICK_NPT_MASK); + + reset_info = g_malloc0(sizeof(ResetData)); + reset_info->cpu = cpu; + reset_info->prom_addr = prom_addr; + qemu_register_reset(main_cpu_reset, reset_info); + + return cpu; +} diff --git a/hw/sparc64/sun4u.c b/hw/sparc64/sun4u.c index 466331535b..d1a6bca873 100644 --- a/hw/sparc64/sun4u.c +++ b/hw/sparc64/sun4u.c @@ -38,25 +38,15 @@ #include "hw/boards.h" #include "hw/nvram/sun_nvram.h" #include "hw/nvram/chrp_nvram.h" +#include "hw/sparc/sparc64.h" #include "hw/nvram/fw_cfg.h" #include "hw/sysbus.h" #include "hw/ide.h" #include "hw/loader.h" #include "elf.h" -#include "sysemu/block-backend.h" -#include "exec/address-spaces.h" #include "qemu/cutils.h" -//#define DEBUG_IRQ //#define DEBUG_EBUS -//#define DEBUG_TIMER - -#ifdef DEBUG_IRQ -#define CPUIRQ_DPRINTF(fmt, ...) \ - do { printf("CPUIRQ: " fmt , ## __VA_ARGS__); } while (0) -#else -#define CPUIRQ_DPRINTF(fmt, ...) -#endif #ifdef DEBUG_EBUS #define EBUS_DPRINTF(fmt, ...) \ @@ -65,13 +55,6 @@ #define EBUS_DPRINTF(fmt, ...) #endif -#ifdef DEBUG_TIMER -#define TIMER_DPRINTF(fmt, ...) \ - do { printf("TIMER: " fmt , ## __VA_ARGS__); } while (0) -#else -#define TIMER_DPRINTF(fmt, ...) -#endif - #define KERNEL_LOAD_ADDR 0x00404000 #define CMDLINE_ADDR 0x003ff000 #define PROM_SIZE_MAX (4 * 1024 * 1024) @@ -89,8 +72,6 @@ #define IVEC_MAX 0x40 -#define TICK_MAX 0x7fffffffffffffffULL - struct hwdef { const char * const default_cpu_model; uint16_t machine_id; @@ -216,293 +197,11 @@ static uint64_t sun4u_load_kernel(const char *kernel_filename, return kernel_size; } -void cpu_check_irqs(CPUSPARCState *env) -{ - CPUState *cs; - uint32_t pil = env->pil_in | - (env->softint & ~(SOFTINT_TIMER | SOFTINT_STIMER)); - - /* TT_IVEC has a higher priority (16) than TT_EXTINT (31..17) */ - if (env->ivec_status & 0x20) { - return; - } - cs = CPU(sparc_env_get_cpu(env)); - /* check if TM or SM in SOFTINT are set - setting these also causes interrupt 14 */ - if (env->softint & (SOFTINT_TIMER | SOFTINT_STIMER)) { - pil |= 1 << 14; - } - - /* The bit corresponding to psrpil is (1<< psrpil), the next bit - is (2 << psrpil). */ - if (pil < (2 << env->psrpil)){ - if (cs->interrupt_request & CPU_INTERRUPT_HARD) { - CPUIRQ_DPRINTF("Reset CPU IRQ (current interrupt %x)\n", - env->interrupt_index); - env->interrupt_index = 0; - cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); - } - return; - } - - if (cpu_interrupts_enabled(env)) { - - unsigned int i; - - for (i = 15; i > env->psrpil; i--) { - if (pil & (1 << i)) { - int old_interrupt = env->interrupt_index; - int new_interrupt = TT_EXTINT | i; - - if (unlikely(env->tl > 0 && cpu_tsptr(env)->tt > new_interrupt - && ((cpu_tsptr(env)->tt & 0x1f0) == TT_EXTINT))) { - CPUIRQ_DPRINTF("Not setting CPU IRQ: TL=%d " - "current %x >= pending %x\n", - env->tl, cpu_tsptr(env)->tt, new_interrupt); - } else if (old_interrupt != new_interrupt) { - env->interrupt_index = new_interrupt; - CPUIRQ_DPRINTF("Set CPU IRQ %d old=%x new=%x\n", i, - old_interrupt, new_interrupt); - cpu_interrupt(cs, CPU_INTERRUPT_HARD); - } - break; - } - } - } else if (cs->interrupt_request & CPU_INTERRUPT_HARD) { - CPUIRQ_DPRINTF("Interrupts disabled, pil=%08x pil_in=%08x softint=%08x " - "current interrupt %x\n", - pil, env->pil_in, env->softint, env->interrupt_index); - env->interrupt_index = 0; - cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); - } -} - -static void cpu_kick_irq(SPARCCPU *cpu) -{ - CPUState *cs = CPU(cpu); - CPUSPARCState *env = &cpu->env; - - cs->halted = 0; - cpu_check_irqs(env); - qemu_cpu_kick(cs); -} - -static void cpu_set_ivec_irq(void *opaque, int irq, int level) -{ - SPARCCPU *cpu = opaque; - CPUSPARCState *env = &cpu->env; - CPUState *cs; - - if (level) { - if (!(env->ivec_status & 0x20)) { - CPUIRQ_DPRINTF("Raise IVEC IRQ %d\n", irq); - cs = CPU(cpu); - cs->halted = 0; - env->interrupt_index = TT_IVEC; - env->ivec_status |= 0x20; - env->ivec_data[0] = (0x1f << 6) | irq; - env->ivec_data[1] = 0; - env->ivec_data[2] = 0; - cpu_interrupt(cs, CPU_INTERRUPT_HARD); - } - } else { - if (env->ivec_status & 0x20) { - CPUIRQ_DPRINTF("Lower IVEC IRQ %d\n", irq); - cs = CPU(cpu); - env->ivec_status &= ~0x20; - cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); - } - } -} - typedef struct ResetData { SPARCCPU *cpu; uint64_t prom_addr; } ResetData; -static CPUTimer *cpu_timer_create(const char *name, SPARCCPU *cpu, - QEMUBHFunc *cb, uint32_t frequency, - uint64_t disabled_mask, uint64_t npt_mask) -{ - CPUTimer *timer = g_malloc0(sizeof (CPUTimer)); - - timer->name = name; - timer->frequency = frequency; - timer->disabled_mask = disabled_mask; - timer->npt_mask = npt_mask; - - timer->disabled = 1; - timer->npt = 1; - timer->clock_offset = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - - timer->qtimer = timer_new_ns(QEMU_CLOCK_VIRTUAL, cb, cpu); - - return timer; -} - -static void cpu_timer_reset(CPUTimer *timer) -{ - timer->disabled = 1; - timer->clock_offset = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - - timer_del(timer->qtimer); -} - -static void main_cpu_reset(void *opaque) -{ - ResetData *s = (ResetData *)opaque; - CPUSPARCState *env = &s->cpu->env; - static unsigned int nr_resets; - - cpu_reset(CPU(s->cpu)); - - cpu_timer_reset(env->tick); - cpu_timer_reset(env->stick); - cpu_timer_reset(env->hstick); - - env->gregs[1] = 0; // Memory start - env->gregs[2] = ram_size; // Memory size - env->gregs[3] = 0; // Machine description XXX - if (nr_resets++ == 0) { - /* Power on reset */ - env->pc = s->prom_addr + 0x20ULL; - } else { - env->pc = s->prom_addr + 0x40ULL; - } - env->npc = env->pc + 4; -} - -static void tick_irq(void *opaque) -{ - SPARCCPU *cpu = opaque; - CPUSPARCState *env = &cpu->env; - - CPUTimer* timer = env->tick; - - if (timer->disabled) { - CPUIRQ_DPRINTF("tick_irq: softint disabled\n"); - return; - } else { - CPUIRQ_DPRINTF("tick: fire\n"); - } - - env->softint |= SOFTINT_TIMER; - cpu_kick_irq(cpu); -} - -static void stick_irq(void *opaque) -{ - SPARCCPU *cpu = opaque; - CPUSPARCState *env = &cpu->env; - - CPUTimer* timer = env->stick; - - if (timer->disabled) { - CPUIRQ_DPRINTF("stick_irq: softint disabled\n"); - return; - } else { - CPUIRQ_DPRINTF("stick: fire\n"); - } - - env->softint |= SOFTINT_STIMER; - cpu_kick_irq(cpu); -} - -static void hstick_irq(void *opaque) -{ - SPARCCPU *cpu = opaque; - CPUSPARCState *env = &cpu->env; - - CPUTimer* timer = env->hstick; - - if (timer->disabled) { - CPUIRQ_DPRINTF("hstick_irq: softint disabled\n"); - return; - } else { - CPUIRQ_DPRINTF("hstick: fire\n"); - } - - env->softint |= SOFTINT_STIMER; - cpu_kick_irq(cpu); -} - -static int64_t cpu_to_timer_ticks(int64_t cpu_ticks, uint32_t frequency) -{ - return muldiv64(cpu_ticks, NANOSECONDS_PER_SECOND, frequency); -} - -static uint64_t timer_to_cpu_ticks(int64_t timer_ticks, uint32_t frequency) -{ - return muldiv64(timer_ticks, frequency, NANOSECONDS_PER_SECOND); -} - -void cpu_tick_set_count(CPUTimer *timer, uint64_t count) -{ - uint64_t real_count = count & ~timer->npt_mask; - uint64_t npt_bit = count & timer->npt_mask; - - int64_t vm_clock_offset = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - - cpu_to_timer_ticks(real_count, timer->frequency); - - TIMER_DPRINTF("%s set_count count=0x%016lx (npt %s) p=%p\n", - timer->name, real_count, - timer->npt ? "disabled" : "enabled", timer); - - timer->npt = npt_bit ? 1 : 0; - timer->clock_offset = vm_clock_offset; -} - -uint64_t cpu_tick_get_count(CPUTimer *timer) -{ - uint64_t real_count = timer_to_cpu_ticks( - qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - timer->clock_offset, - timer->frequency); - - TIMER_DPRINTF("%s get_count count=0x%016lx (npt %s) p=%p\n", - timer->name, real_count, - timer->npt ? "disabled" : "enabled", timer); - - if (timer->npt) { - real_count |= timer->npt_mask; - } - - return real_count; -} - -void cpu_tick_set_limit(CPUTimer *timer, uint64_t limit) -{ - int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - - uint64_t real_limit = limit & ~timer->disabled_mask; - timer->disabled = (limit & timer->disabled_mask) ? 1 : 0; - - int64_t expires = cpu_to_timer_ticks(real_limit, timer->frequency) + - timer->clock_offset; - - if (expires < now) { - expires = now + 1; - } - - TIMER_DPRINTF("%s set_limit limit=0x%016lx (%s) p=%p " - "called with limit=0x%016lx at 0x%016lx (delta=0x%016lx)\n", - timer->name, real_limit, - timer->disabled?"disabled":"enabled", - timer, limit, - timer_to_cpu_ticks(now - timer->clock_offset, - timer->frequency), - timer_to_cpu_ticks(expires - now, timer->frequency)); - - if (!real_limit) { - TIMER_DPRINTF("%s set_limit limit=ZERO - not starting timer\n", - timer->name); - timer_del(timer->qtimer); - } else if (timer->disabled) { - timer_del(timer->qtimer); - } else { - timer_mod(timer->qtimer, expires); - } -} - static void isa_irq_handler(void *opaque, int n, int level) { static const int isa_irq_to_ivec[16] = { @@ -723,46 +422,6 @@ static const TypeInfo ram_info = { .class_init = ram_class_init, }; -static SPARCCPU *cpu_devinit(const char *cpu_model, const struct hwdef *hwdef) -{ - SPARCCPU *cpu; - CPUSPARCState *env; - ResetData *reset_info; - - uint32_t tick_frequency = 100*1000000; - uint32_t stick_frequency = 100*1000000; - uint32_t hstick_frequency = 100*1000000; - - if (cpu_model == NULL) { - cpu_model = hwdef->default_cpu_model; - } - cpu = cpu_sparc_init(cpu_model); - if (cpu == NULL) { - fprintf(stderr, "Unable to find Sparc CPU definition\n"); - exit(1); - } - env = &cpu->env; - - env->tick = cpu_timer_create("tick", cpu, tick_irq, - tick_frequency, TICK_INT_DIS, - TICK_NPT_MASK); - - env->stick = cpu_timer_create("stick", cpu, stick_irq, - stick_frequency, TICK_INT_DIS, - TICK_NPT_MASK); - - env->hstick = cpu_timer_create("hstick", cpu, hstick_irq, - hstick_frequency, TICK_INT_DIS, - TICK_NPT_MASK); - - reset_info = g_malloc0(sizeof(ResetData)); - reset_info->cpu = cpu; - reset_info->prom_addr = hwdef->prom_addr; - qemu_register_reset(main_cpu_reset, reset_info); - - return cpu; -} - static void sun4uv_init(MemoryRegion *address_space_mem, MachineState *machine, const struct hwdef *hwdef) @@ -781,14 +440,15 @@ static void sun4uv_init(MemoryRegion *address_space_mem, FWCfgState *fw_cfg; /* init CPUs */ - cpu = cpu_devinit(machine->cpu_model, hwdef); + cpu = sparc64_cpu_devinit(machine->cpu_model, hwdef->default_cpu_model, + hwdef->prom_addr); /* set up devices */ ram_init(0, machine->ram_size); prom_init(hwdef->prom_addr, bios_name); - ivec_irqs = qemu_allocate_irqs(cpu_set_ivec_irq, cpu, IVEC_MAX); + ivec_irqs = qemu_allocate_irqs(sparc64_cpu_set_ivec_irq, cpu, IVEC_MAX); pci_bus = pci_apb_init(APB_SPECIAL_BASE, APB_MEM_BASE, ivec_irqs, &pci_bus2, &pci_bus3, &pbm_irqs); pci_vga_init(pci_bus); @@ -882,7 +542,6 @@ static void sun4uv_init(MemoryRegion *address_space_mem, enum { sun4u_id = 0, sun4v_id = 64, - niagara_id, }; static const struct hwdef hwdefs[] = { @@ -900,13 +559,6 @@ static const struct hwdef hwdefs[] = { .prom_addr = 0x1fff0000000ULL, .console_serial_base = 0, }, - /* Sun4v generic Niagara machine */ - { - .default_cpu_model = "Sun UltraSparc T1", - .machine_id = niagara_id, - .prom_addr = 0xfff0000000ULL, - .console_serial_base = 0xfff0c2c000ULL, - }, }; /* Sun4u hardware initialisation */ @@ -921,12 +573,6 @@ static void sun4v_init(MachineState *machine) sun4uv_init(get_system_memory(), machine, &hwdefs[1]); } -/* Niagara hardware initialisation */ -static void niagara_init(MachineState *machine) -{ - sun4uv_init(get_system_memory(), machine, &hwdefs[2]); -} - static void sun4u_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); @@ -960,22 +606,6 @@ static const TypeInfo sun4v_type = { .class_init = sun4v_class_init, }; -static void niagara_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Sun4v platform, Niagara"; - mc->init = niagara_init; - mc->max_cpus = 1; /* XXX for now */ - mc->default_boot_order = "c"; -} - -static const TypeInfo niagara_type = { - .name = MACHINE_TYPE_NAME("Niagara"), - .parent = TYPE_MACHINE, - .class_init = niagara_class_init, -}; - static void sun4u_register_types(void) { type_register_static(&ebus_info); @@ -984,7 +614,6 @@ static void sun4u_register_types(void) type_register_static(&sun4u_type); type_register_static(&sun4v_type); - type_register_static(&niagara_type); } type_init(sun4u_register_types) diff --git a/hw/ssi/aspeed_smc.c b/hw/ssi/aspeed_smc.c index 6e8403ebc2..ae1ad2dba6 100644 --- a/hw/ssi/aspeed_smc.c +++ b/hw/ssi/aspeed_smc.c @@ -39,11 +39,14 @@ #define CONF_ENABLE_W2 18 #define CONF_ENABLE_W1 17 #define CONF_ENABLE_W0 16 -#define CONF_FLASH_TYPE4 9 -#define CONF_FLASH_TYPE3 7 -#define CONF_FLASH_TYPE2 5 -#define CONF_FLASH_TYPE1 3 -#define CONF_FLASH_TYPE0 1 +#define CONF_FLASH_TYPE4 8 +#define CONF_FLASH_TYPE3 6 +#define CONF_FLASH_TYPE2 4 +#define CONF_FLASH_TYPE1 2 +#define CONF_FLASH_TYPE0 0 +#define CONF_FLASH_TYPE_NOR 0x0 +#define CONF_FLASH_TYPE_NAND 0x1 +#define CONF_FLASH_TYPE_SPI 0x2 /* CE Control Register */ #define R_CE_CTRL (0x04 / 4) @@ -66,6 +69,7 @@ #define R_CTRL0 (0x10 / 4) #define CTRL_CMD_SHIFT 16 #define CTRL_CMD_MASK 0xff +#define CTRL_AST2400_SPI_4BYTE (1 << 13) #define CTRL_CE_STOP_ACTIVE (1 << 2) #define CTRL_CMD_MODE_MASK 0x3 #define CTRL_READMODE 0x0 @@ -127,11 +131,17 @@ #define R_SPI_MISC_CTRL (0x10 / 4) #define R_SPI_TIMINGS (0x14 / 4) +#define ASPEED_SMC_R_SPI_MAX (0x20 / 4) +#define ASPEED_SMC_R_SMC_MAX (0x20 / 4) + #define ASPEED_SOC_SMC_FLASH_BASE 0x10000000 #define ASPEED_SOC_FMC_FLASH_BASE 0x20000000 #define ASPEED_SOC_SPI_FLASH_BASE 0x30000000 #define ASPEED_SOC_SPI2_FLASH_BASE 0x38000000 +/* Flash opcodes. */ +#define SPI_OP_READ 0x03 /* Read data bytes (low frequency) */ + /* * Default segments mapping addresses and size for each slave per * controller. These can be changed when board is initialized with the @@ -170,24 +180,85 @@ static const AspeedSegments aspeed_segments_ast2500_spi2[] = { }; static const AspeedSMCController controllers[] = { - { "aspeed.smc.smc", R_CONF, R_CE_CTRL, R_CTRL0, R_TIMINGS, - CONF_ENABLE_W0, 5, aspeed_segments_legacy, - ASPEED_SOC_SMC_FLASH_BASE, 0x6000000 }, - { "aspeed.smc.fmc", R_CONF, R_CE_CTRL, R_CTRL0, R_TIMINGS, - CONF_ENABLE_W0, 5, aspeed_segments_fmc, - ASPEED_SOC_FMC_FLASH_BASE, 0x10000000 }, - { "aspeed.smc.spi", R_SPI_CONF, 0xff, R_SPI_CTRL0, R_SPI_TIMINGS, - SPI_CONF_ENABLE_W0, 1, aspeed_segments_spi, - ASPEED_SOC_SPI_FLASH_BASE, 0x10000000 }, - { "aspeed.smc.ast2500-fmc", R_CONF, R_CE_CTRL, R_CTRL0, R_TIMINGS, - CONF_ENABLE_W0, 3, aspeed_segments_ast2500_fmc, - ASPEED_SOC_FMC_FLASH_BASE, 0x10000000 }, - { "aspeed.smc.ast2500-spi1", R_CONF, R_CE_CTRL, R_CTRL0, R_TIMINGS, - CONF_ENABLE_W0, 2, aspeed_segments_ast2500_spi1, - ASPEED_SOC_SPI_FLASH_BASE, 0x8000000 }, - { "aspeed.smc.ast2500-spi2", R_CONF, R_CE_CTRL, R_CTRL0, R_TIMINGS, - CONF_ENABLE_W0, 2, aspeed_segments_ast2500_spi2, - ASPEED_SOC_SPI2_FLASH_BASE, 0x8000000 }, + { + .name = "aspeed.smc.smc", + .r_conf = R_CONF, + .r_ce_ctrl = R_CE_CTRL, + .r_ctrl0 = R_CTRL0, + .r_timings = R_TIMINGS, + .conf_enable_w0 = CONF_ENABLE_W0, + .max_slaves = 5, + .segments = aspeed_segments_legacy, + .flash_window_base = ASPEED_SOC_SMC_FLASH_BASE, + .flash_window_size = 0x6000000, + .has_dma = false, + .nregs = ASPEED_SMC_R_SMC_MAX, + }, { + .name = "aspeed.smc.fmc", + .r_conf = R_CONF, + .r_ce_ctrl = R_CE_CTRL, + .r_ctrl0 = R_CTRL0, + .r_timings = R_TIMINGS, + .conf_enable_w0 = CONF_ENABLE_W0, + .max_slaves = 5, + .segments = aspeed_segments_fmc, + .flash_window_base = ASPEED_SOC_FMC_FLASH_BASE, + .flash_window_size = 0x10000000, + .has_dma = true, + .nregs = ASPEED_SMC_R_MAX, + }, { + .name = "aspeed.smc.spi", + .r_conf = R_SPI_CONF, + .r_ce_ctrl = 0xff, + .r_ctrl0 = R_SPI_CTRL0, + .r_timings = R_SPI_TIMINGS, + .conf_enable_w0 = SPI_CONF_ENABLE_W0, + .max_slaves = 1, + .segments = aspeed_segments_spi, + .flash_window_base = ASPEED_SOC_SPI_FLASH_BASE, + .flash_window_size = 0x10000000, + .has_dma = false, + .nregs = ASPEED_SMC_R_SPI_MAX, + }, { + .name = "aspeed.smc.ast2500-fmc", + .r_conf = R_CONF, + .r_ce_ctrl = R_CE_CTRL, + .r_ctrl0 = R_CTRL0, + .r_timings = R_TIMINGS, + .conf_enable_w0 = CONF_ENABLE_W0, + .max_slaves = 3, + .segments = aspeed_segments_ast2500_fmc, + .flash_window_base = ASPEED_SOC_FMC_FLASH_BASE, + .flash_window_size = 0x10000000, + .has_dma = true, + .nregs = ASPEED_SMC_R_MAX, + }, { + .name = "aspeed.smc.ast2500-spi1", + .r_conf = R_CONF, + .r_ce_ctrl = R_CE_CTRL, + .r_ctrl0 = R_CTRL0, + .r_timings = R_TIMINGS, + .conf_enable_w0 = CONF_ENABLE_W0, + .max_slaves = 2, + .segments = aspeed_segments_ast2500_spi1, + .flash_window_base = ASPEED_SOC_SPI_FLASH_BASE, + .flash_window_size = 0x8000000, + .has_dma = false, + .nregs = ASPEED_SMC_R_MAX, + }, { + .name = "aspeed.smc.ast2500-spi2", + .r_conf = R_CONF, + .r_ce_ctrl = R_CE_CTRL, + .r_ctrl0 = R_CTRL0, + .r_timings = R_TIMINGS, + .conf_enable_w0 = CONF_ENABLE_W0, + .max_slaves = 2, + .segments = aspeed_segments_ast2500_spi2, + .flash_window_base = ASPEED_SOC_SPI2_FLASH_BASE, + .flash_window_size = 0x8000000, + .has_dma = false, + .nregs = ASPEED_SMC_R_MAX, + }, }; /* @@ -253,7 +324,8 @@ static void aspeed_smc_flash_set_segment(AspeedSMCState *s, int cs, qemu_log_mask(LOG_GUEST_ERROR, "%s: Tried to change CS0 start address to 0x%" HWADDR_PRIx "\n", s->ctrl->name, seg.addr); - return; + seg.addr = s->ctrl->flash_window_base; + new = aspeed_smc_segment_to_reg(&seg); } /* @@ -267,8 +339,10 @@ static void aspeed_smc_flash_set_segment(AspeedSMCState *s, int cs, s->ctrl->segments[cs].size) { qemu_log_mask(LOG_GUEST_ERROR, "%s: Tried to change CS%d end address to 0x%" - HWADDR_PRIx "\n", s->ctrl->name, cs, seg.addr); - return; + HWADDR_PRIx "\n", s->ctrl->name, cs, seg.addr + seg.size); + seg.size = s->ctrl->segments[cs].addr + s->ctrl->segments[cs].size - + seg.addr; + new = aspeed_smc_segment_to_reg(&seg); } /* Keep the segment in the overall flash window */ @@ -281,16 +355,14 @@ static void aspeed_smc_flash_set_segment(AspeedSMCState *s, int cs, } /* Check start address vs. alignment */ - if (seg.addr % seg.size) { + if (seg.size && !QEMU_IS_ALIGNED(seg.addr, seg.size)) { qemu_log_mask(LOG_GUEST_ERROR, "%s: new segment for CS%d is not " "aligned : [ 0x%"HWADDR_PRIx" - 0x%"HWADDR_PRIx" ]\n", s->ctrl->name, cs, seg.addr, seg.addr + seg.size); } - /* And segments should not overlap */ - if (aspeed_smc_flash_overlap(s, &seg, cs)) { - return; - } + /* And segments should not overlap (in the specs) */ + aspeed_smc_flash_overlap(s, &seg, cs); /* All should be fine now to move the region */ memory_region_transaction_begin(); @@ -327,36 +399,137 @@ static const MemoryRegionOps aspeed_smc_flash_default_ops = { }, }; -static inline int aspeed_smc_flash_mode(const AspeedSMCState *s, int cs) +static inline int aspeed_smc_flash_mode(const AspeedSMCFlash *fl) +{ + const AspeedSMCState *s = fl->controller; + + return s->regs[s->r_ctrl0 + fl->id] & CTRL_CMD_MODE_MASK; +} + +static inline bool aspeed_smc_is_writable(const AspeedSMCFlash *fl) { - return s->regs[s->r_ctrl0 + cs] & CTRL_CMD_MODE_MASK; + const AspeedSMCState *s = fl->controller; + + return s->regs[s->r_conf] & (1 << (s->conf_enable_w0 + fl->id)); } -static inline bool aspeed_smc_is_usermode(const AspeedSMCState *s, int cs) +static inline int aspeed_smc_flash_cmd(const AspeedSMCFlash *fl) { - return aspeed_smc_flash_mode(s, cs) == CTRL_USERMODE; + const AspeedSMCState *s = fl->controller; + int cmd = (s->regs[s->r_ctrl0 + fl->id] >> CTRL_CMD_SHIFT) & CTRL_CMD_MASK; + + /* In read mode, the default SPI command is READ (0x3). In other + * modes, the command should necessarily be defined */ + if (aspeed_smc_flash_mode(fl) == CTRL_READMODE) { + cmd = SPI_OP_READ; + } + + if (!cmd) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: no command defined for mode %d\n", + __func__, aspeed_smc_flash_mode(fl)); + } + + return cmd; } -static inline bool aspeed_smc_is_writable(const AspeedSMCState *s, int cs) +static inline int aspeed_smc_flash_is_4byte(const AspeedSMCFlash *fl) { - return s->regs[s->r_conf] & (1 << (s->conf_enable_w0 + cs)); + const AspeedSMCState *s = fl->controller; + + if (s->ctrl->segments == aspeed_segments_spi) { + return s->regs[s->r_ctrl0] & CTRL_AST2400_SPI_4BYTE; + } else { + return s->regs[s->r_ce_ctrl] & (1 << (CTRL_EXTENDED0 + fl->id)); + } +} + +static inline bool aspeed_smc_is_ce_stop_active(const AspeedSMCFlash *fl) +{ + const AspeedSMCState *s = fl->controller; + + return s->regs[s->r_ctrl0 + fl->id] & CTRL_CE_STOP_ACTIVE; +} + +static void aspeed_smc_flash_select(AspeedSMCFlash *fl) +{ + AspeedSMCState *s = fl->controller; + + s->regs[s->r_ctrl0 + fl->id] &= ~CTRL_CE_STOP_ACTIVE; + qemu_set_irq(s->cs_lines[fl->id], aspeed_smc_is_ce_stop_active(fl)); +} + +static void aspeed_smc_flash_unselect(AspeedSMCFlash *fl) +{ + AspeedSMCState *s = fl->controller; + + s->regs[s->r_ctrl0 + fl->id] |= CTRL_CE_STOP_ACTIVE; + qemu_set_irq(s->cs_lines[fl->id], aspeed_smc_is_ce_stop_active(fl)); +} + +static uint32_t aspeed_smc_check_segment_addr(const AspeedSMCFlash *fl, + uint32_t addr) +{ + const AspeedSMCState *s = fl->controller; + AspeedSegments seg; + + aspeed_smc_reg_to_segment(s->regs[R_SEG_ADDR0 + fl->id], &seg); + if ((addr & (seg.size - 1)) != addr) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid address 0x%08x for CS%d segment : " + "[ 0x%"HWADDR_PRIx" - 0x%"HWADDR_PRIx" ]\n", + s->ctrl->name, addr, fl->id, seg.addr, + seg.addr + seg.size); + } + + addr &= seg.size - 1; + return addr; +} + +static void aspeed_smc_flash_send_addr(AspeedSMCFlash *fl, uint32_t addr) +{ + const AspeedSMCState *s = fl->controller; + uint8_t cmd = aspeed_smc_flash_cmd(fl); + + /* Flash access can not exceed CS segment */ + addr = aspeed_smc_check_segment_addr(fl, addr); + + ssi_transfer(s->spi, cmd); + + if (aspeed_smc_flash_is_4byte(fl)) { + ssi_transfer(s->spi, (addr >> 24) & 0xff); + } + ssi_transfer(s->spi, (addr >> 16) & 0xff); + ssi_transfer(s->spi, (addr >> 8) & 0xff); + ssi_transfer(s->spi, (addr & 0xff)); } static uint64_t aspeed_smc_flash_read(void *opaque, hwaddr addr, unsigned size) { AspeedSMCFlash *fl = opaque; - const AspeedSMCState *s = fl->controller; + AspeedSMCState *s = fl->controller; uint64_t ret = 0; int i; - if (aspeed_smc_is_usermode(s, fl->id)) { + switch (aspeed_smc_flash_mode(fl)) { + case CTRL_USERMODE: for (i = 0; i < size; i++) { ret |= ssi_transfer(s->spi, 0x0) << (8 * i); } - } else { - qemu_log_mask(LOG_UNIMP, "%s: usermode not implemented\n", - __func__); - ret = -1; + break; + case CTRL_READMODE: + case CTRL_FREADMODE: + aspeed_smc_flash_select(fl); + aspeed_smc_flash_send_addr(fl, addr); + + for (i = 0; i < size; i++) { + ret |= ssi_transfer(s->spi, 0x0) << (8 * i); + } + + aspeed_smc_flash_unselect(fl); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid flash mode %d\n", + __func__, aspeed_smc_flash_mode(fl)); } return ret; @@ -366,23 +539,34 @@ static void aspeed_smc_flash_write(void *opaque, hwaddr addr, uint64_t data, unsigned size) { AspeedSMCFlash *fl = opaque; - const AspeedSMCState *s = fl->controller; + AspeedSMCState *s = fl->controller; int i; - if (!aspeed_smc_is_writable(s, fl->id)) { + if (!aspeed_smc_is_writable(fl)) { qemu_log_mask(LOG_GUEST_ERROR, "%s: flash is not writable at 0x%" HWADDR_PRIx "\n", __func__, addr); return; } - if (!aspeed_smc_is_usermode(s, fl->id)) { - qemu_log_mask(LOG_UNIMP, "%s: usermode not implemented\n", - __func__); - return; - } + switch (aspeed_smc_flash_mode(fl)) { + case CTRL_USERMODE: + for (i = 0; i < size; i++) { + ssi_transfer(s->spi, (data >> (8 * i)) & 0xff); + } + break; + case CTRL_WRITEMODE: + aspeed_smc_flash_select(fl); + aspeed_smc_flash_send_addr(fl, addr); + + for (i = 0; i < size; i++) { + ssi_transfer(s->spi, (data >> (8 * i)) & 0xff); + } - for (i = 0; i < size; i++) { - ssi_transfer(s->spi, (data >> (8 * i)) & 0xff); + aspeed_smc_flash_unselect(fl); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid flash mode %d\n", + __func__, aspeed_smc_flash_mode(fl)); } } @@ -396,18 +580,11 @@ static const MemoryRegionOps aspeed_smc_flash_ops = { }, }; -static bool aspeed_smc_is_ce_stop_active(const AspeedSMCState *s, int cs) +static void aspeed_smc_flash_update_cs(AspeedSMCFlash *fl) { - return s->regs[s->r_ctrl0 + cs] & CTRL_CE_STOP_ACTIVE; -} - -static void aspeed_smc_update_cs(const AspeedSMCState *s) -{ - int i; + const AspeedSMCState *s = fl->controller; - for (i = 0; i < s->num_cs; ++i) { - qemu_set_irq(s->cs_lines[i], aspeed_smc_is_ce_stop_active(s, i)); - } + qemu_set_irq(s->cs_lines[fl->id], aspeed_smc_is_ce_stop_active(fl)); } static void aspeed_smc_reset(DeviceState *d) @@ -423,6 +600,7 @@ static void aspeed_smc_reset(DeviceState *d) /* Unselect all slaves */ for (i = 0; i < s->num_cs; ++i) { s->regs[s->r_ctrl0 + i] |= CTRL_CE_STOP_ACTIVE; + qemu_set_irq(s->cs_lines[i], true); } /* setup default segment register values for all */ @@ -431,7 +609,24 @@ static void aspeed_smc_reset(DeviceState *d) aspeed_smc_segment_to_reg(&s->ctrl->segments[i]); } - aspeed_smc_update_cs(s); + /* HW strapping for AST2500 FMC controllers */ + if (s->ctrl->segments == aspeed_segments_ast2500_fmc) { + /* flash type is fixed to SPI for CE0 and CE1 */ + s->regs[s->r_conf] |= (CONF_FLASH_TYPE_SPI << CONF_FLASH_TYPE0); + s->regs[s->r_conf] |= (CONF_FLASH_TYPE_SPI << CONF_FLASH_TYPE1); + + /* 4BYTE mode is autodetected for CE0. Let's force it to 1 for + * now */ + s->regs[s->r_ce_ctrl] |= (1 << (CTRL_EXTENDED0)); + } + + /* HW strapping for AST2400 FMC controllers (SCU70). Let's use the + * configuration of the palmetto-bmc machine */ + if (s->ctrl->segments == aspeed_segments_fmc) { + s->regs[s->r_conf] |= (CONF_FLASH_TYPE_SPI << CONF_FLASH_TYPE0); + + s->regs[s->r_ce_ctrl] |= (1 << (CTRL_EXTENDED0)); + } } static uint64_t aspeed_smc_read(void *opaque, hwaddr addr, unsigned int size) @@ -440,13 +635,6 @@ static uint64_t aspeed_smc_read(void *opaque, hwaddr addr, unsigned int size) addr >>= 2; - if (addr >= ARRAY_SIZE(s->regs)) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Out-of-bounds read at 0x%" HWADDR_PRIx "\n", - __func__, addr); - return 0; - } - if (addr == s->r_conf || addr == s->r_timings || addr == s->r_ce_ctrl || @@ -469,20 +657,14 @@ static void aspeed_smc_write(void *opaque, hwaddr addr, uint64_t data, addr >>= 2; - if (addr >= ARRAY_SIZE(s->regs)) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Out-of-bounds write at 0x%" HWADDR_PRIx "\n", - __func__, addr); - return; - } - if (addr == s->r_conf || addr == s->r_timings || addr == s->r_ce_ctrl) { s->regs[addr] = value; } else if (addr >= s->r_ctrl0 && addr < s->r_ctrl0 + s->num_cs) { + int cs = addr - s->r_ctrl0; s->regs[addr] = value; - aspeed_smc_update_cs(s); + aspeed_smc_flash_update_cs(&s->flashes[cs]); } else if (addr >= R_SEG_ADDR0 && addr < R_SEG_ADDR0 + s->ctrl->max_slaves) { int cs = addr - R_SEG_ADDR0; @@ -540,11 +722,9 @@ static void aspeed_smc_realize(DeviceState *dev, Error **errp) sysbus_init_irq(sbd, &s->cs_lines[i]); } - aspeed_smc_reset(dev); - /* The memory region for the controller registers */ memory_region_init_io(&s->mmio, OBJECT(s), &aspeed_smc_ops, s, - s->ctrl->name, ASPEED_SMC_R_MAX * 4); + s->ctrl->name, s->ctrl->nregs * 4); sysbus_init_mmio(sbd, &s->mmio); /* diff --git a/hw/ssi/imx_spi.c b/hw/ssi/imx_spi.c index e4e395fa67..b66505ca49 100644 --- a/hw/ssi/imx_spi.c +++ b/hw/ssi/imx_spi.c @@ -320,9 +320,6 @@ static void imx_spi_write(void *opaque, hwaddr offset, uint64_t value, TYPE_IMX_SPI, __func__); break; case ECSPI_TXDATA: - case ECSPI_MSGDATA: - /* Is there any difference between TXDATA and MSGDATA ? */ - /* I'll have to look in the linux driver */ if (!imx_spi_is_enabled(s)) { /* Ignore writes if device is disabled */ break; @@ -380,6 +377,14 @@ static void imx_spi_write(void *opaque, hwaddr offset, uint64_t value, } break; + case ECSPI_MSGDATA: + /* it is not clear from the spec what MSGDATA is for */ + /* Anyway it is not used by Linux driver */ + /* So for now we just ignore it */ + qemu_log_mask(LOG_UNIMP, + "[%s]%s: Trying to write to MSGDATA, ignoring\n", + TYPE_IMX_SPI, __func__); + break; default: s->regs[index] = value; diff --git a/hw/timer/Makefile.objs b/hw/timer/Makefile.objs index 7ba8c23c75..71994f2d88 100644 --- a/hw/timer/Makefile.objs +++ b/hw/timer/Makefile.objs @@ -18,6 +18,7 @@ common-obj-$(CONFIG_IMX) += imx_gpt.o common-obj-$(CONFIG_LM32) += lm32_timer.o common-obj-$(CONFIG_MILKYMIST) += milkymist-sysctl.o +obj-$(CONFIG_ALTERA_TIMER) += altera_timer.o obj-$(CONFIG_EXYNOS4) += exynos4210_mct.o obj-$(CONFIG_EXYNOS4) += exynos4210_pwm.o obj-$(CONFIG_EXYNOS4) += exynos4210_rtc.o @@ -34,3 +35,5 @@ obj-$(CONFIG_ALLWINNER_A10_PIT) += allwinner-a10-pit.o common-obj-$(CONFIG_STM32F2XX_TIMER) += stm32f2xx_timer.o common-obj-$(CONFIG_ASPEED_SOC) += aspeed_timer.o + +common-obj-$(CONFIG_SUN4V_RTC) += sun4v-rtc.o diff --git a/hw/timer/altera_timer.c b/hw/timer/altera_timer.c new file mode 100644 index 0000000000..6d4862661d --- /dev/null +++ b/hw/timer/altera_timer.c @@ -0,0 +1,237 @@ +/* + * QEMU model of the Altera timer. + * + * Copyright (c) 2012 Chris Wulff <crwulff@gmail.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see + * <http://www.gnu.org/licenses/lgpl-2.1.html> + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qapi/error.h" + +#include "hw/sysbus.h" +#include "sysemu/sysemu.h" +#include "hw/ptimer.h" + +#define R_STATUS 0 +#define R_CONTROL 1 +#define R_PERIODL 2 +#define R_PERIODH 3 +#define R_SNAPL 4 +#define R_SNAPH 5 +#define R_MAX 6 + +#define STATUS_TO 0x0001 +#define STATUS_RUN 0x0002 + +#define CONTROL_ITO 0x0001 +#define CONTROL_CONT 0x0002 +#define CONTROL_START 0x0004 +#define CONTROL_STOP 0x0008 + +#define TYPE_ALTERA_TIMER "ALTR.timer" +#define ALTERA_TIMER(obj) \ + OBJECT_CHECK(AlteraTimer, (obj), TYPE_ALTERA_TIMER) + +typedef struct AlteraTimer { + SysBusDevice busdev; + MemoryRegion mmio; + qemu_irq irq; + uint32_t freq_hz; + QEMUBH *bh; + ptimer_state *ptimer; + uint32_t regs[R_MAX]; +} AlteraTimer; + +static int timer_irq_state(AlteraTimer *t) +{ + bool irq = (t->regs[R_STATUS] & STATUS_TO) && + (t->regs[R_CONTROL] & CONTROL_ITO); + return irq; +} + +static uint64_t timer_read(void *opaque, hwaddr addr, + unsigned int size) +{ + AlteraTimer *t = opaque; + uint64_t r = 0; + + addr >>= 2; + + switch (addr) { + case R_CONTROL: + r = t->regs[R_CONTROL] & (CONTROL_ITO | CONTROL_CONT); + break; + + default: + if (addr < ARRAY_SIZE(t->regs)) { + r = t->regs[addr]; + } + break; + } + + return r; +} + +static void timer_write(void *opaque, hwaddr addr, + uint64_t value, unsigned int size) +{ + AlteraTimer *t = opaque; + uint64_t tvalue; + uint32_t count = 0; + int irqState = timer_irq_state(t); + + addr >>= 2; + + switch (addr) { + case R_STATUS: + /* The timeout bit is cleared by writing the status register. */ + t->regs[R_STATUS] &= ~STATUS_TO; + break; + + case R_CONTROL: + t->regs[R_CONTROL] = value & (CONTROL_ITO | CONTROL_CONT); + if ((value & CONTROL_START) && + !(t->regs[R_STATUS] & STATUS_RUN)) { + ptimer_run(t->ptimer, 1); + t->regs[R_STATUS] |= STATUS_RUN; + } + if ((value & CONTROL_STOP) && (t->regs[R_STATUS] & STATUS_RUN)) { + ptimer_stop(t->ptimer); + t->regs[R_STATUS] &= ~STATUS_RUN; + } + break; + + case R_PERIODL: + case R_PERIODH: + t->regs[addr] = value & 0xFFFF; + if (t->regs[R_STATUS] & STATUS_RUN) { + ptimer_stop(t->ptimer); + t->regs[R_STATUS] &= ~STATUS_RUN; + } + tvalue = (t->regs[R_PERIODH] << 16) | t->regs[R_PERIODL]; + ptimer_set_limit(t->ptimer, tvalue + 1, 1); + break; + + case R_SNAPL: + case R_SNAPH: + count = ptimer_get_count(t->ptimer); + t->regs[R_SNAPL] = count & 0xFFFF; + t->regs[R_SNAPH] = count >> 16; + break; + + default: + break; + } + + if (irqState != timer_irq_state(t)) { + qemu_set_irq(t->irq, timer_irq_state(t)); + } +} + +static const MemoryRegionOps timer_ops = { + .read = timer_read, + .write = timer_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 1, + .max_access_size = 4 + } +}; + +static void timer_hit(void *opaque) +{ + AlteraTimer *t = opaque; + const uint64_t tvalue = (t->regs[R_PERIODH] << 16) | t->regs[R_PERIODL]; + + t->regs[R_STATUS] |= STATUS_TO; + + ptimer_set_limit(t->ptimer, tvalue + 1, 1); + + if (!(t->regs[R_CONTROL] & CONTROL_CONT)) { + t->regs[R_STATUS] &= ~STATUS_RUN; + ptimer_set_count(t->ptimer, tvalue); + } else { + ptimer_run(t->ptimer, 1); + } + + qemu_set_irq(t->irq, timer_irq_state(t)); +} + +static void altera_timer_realize(DeviceState *dev, Error **errp) +{ + AlteraTimer *t = ALTERA_TIMER(dev); + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + + if (t->freq_hz == 0) { + error_setg(errp, "\"clock-frequency\" property must be provided."); + return; + } + + t->bh = qemu_bh_new(timer_hit, t); + t->ptimer = ptimer_init(t->bh, PTIMER_POLICY_DEFAULT); + ptimer_set_freq(t->ptimer, t->freq_hz); + + memory_region_init_io(&t->mmio, OBJECT(t), &timer_ops, t, + TYPE_ALTERA_TIMER, R_MAX * sizeof(uint32_t)); + sysbus_init_mmio(sbd, &t->mmio); +} + +static void altera_timer_init(Object *obj) +{ + AlteraTimer *t = ALTERA_TIMER(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + sysbus_init_irq(sbd, &t->irq); +} + +static void altera_timer_reset(DeviceState *dev) +{ + AlteraTimer *t = ALTERA_TIMER(dev); + + ptimer_stop(t->ptimer); + ptimer_set_limit(t->ptimer, 0xffffffff, 1); + memset(t->regs, 0, ARRAY_SIZE(t->regs)); +} + +static Property altera_timer_properties[] = { + DEFINE_PROP_UINT32("clock-frequency", AlteraTimer, freq_hz, 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static void altera_timer_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = altera_timer_realize; + dc->props = altera_timer_properties; + dc->reset = altera_timer_reset; +} + +static const TypeInfo altera_timer_info = { + .name = TYPE_ALTERA_TIMER, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(AlteraTimer), + .instance_init = altera_timer_init, + .class_init = altera_timer_class_init, +}; + +static void altera_timer_register(void) +{ + type_register_static(&altera_timer_info); +} + +type_init(altera_timer_register) diff --git a/hw/timer/ds1338.c b/hw/timer/ds1338.c index 0112949e23..3849b74a68 100644 --- a/hw/timer/ds1338.c +++ b/hw/timer/ds1338.c @@ -94,7 +94,7 @@ static void inc_regptr(DS1338State *s) } } -static void ds1338_event(I2CSlave *i2c, enum i2c_event event) +static int ds1338_event(I2CSlave *i2c, enum i2c_event event) { DS1338State *s = DS1338(i2c); @@ -113,6 +113,8 @@ static void ds1338_event(I2CSlave *i2c, enum i2c_event event) default: break; } + + return 0; } static int ds1338_recv(I2CSlave *i2c) @@ -198,11 +200,6 @@ static int ds1338_send(I2CSlave *i2c, uint8_t data) return 0; } -static int ds1338_init(I2CSlave *i2c) -{ - return 0; -} - static void ds1338_reset(DeviceState *dev) { DS1338State *s = DS1338(dev); @@ -220,7 +217,6 @@ static void ds1338_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); I2CSlaveClass *k = I2C_SLAVE_CLASS(klass); - k->init = ds1338_init; k->event = ds1338_event; k->recv = ds1338_recv; k->send = ds1338_send; diff --git a/hw/timer/mc146818rtc.c b/hw/timer/mc146818rtc.c index da209d02f0..637f8722a7 100644 --- a/hw/timer/mc146818rtc.c +++ b/hw/timer/mc146818rtc.c @@ -946,11 +946,23 @@ static Property mc146818rtc_properties[] = { DEFINE_PROP_END_OF_LIST(), }; +static void rtc_resetdev(DeviceState *d) +{ + RTCState *s = MC146818_RTC(d); + + /* Reason: VM do suspend self will set 0xfe + * Reset any values other than 0xfe(Guest suspend case) */ + if (s->cmos_data[0x0f] != 0xfe) { + s->cmos_data[0x0f] = 0x00; + } +} + static void rtc_class_initfn(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); dc->realize = rtc_realizefn; + dc->reset = rtc_resetdev; dc->vmsd = &vmstate_rtc; dc->props = mc146818rtc_properties; /* Reason: needs to be wired up by rtc_init() */ diff --git a/hw/timer/sun4v-rtc.c b/hw/timer/sun4v-rtc.c new file mode 100644 index 0000000000..310523225f --- /dev/null +++ b/hw/timer/sun4v-rtc.c @@ -0,0 +1,102 @@ +/* + * QEMU sun4v Real Time Clock device + * + * The sun4v_rtc device (sun4v tod clock) + * + * Copyright (c) 2016 Artyom Tarasenko + * + * This code is licensed under the GNU GPL v3 or (at your option) any later + * version. + */ + +#include "qemu/osdep.h" +#include "hw/hw.h" +#include "hw/sysbus.h" +#include "qemu/timer.h" +#include "hw/timer/sun4v-rtc.h" + +//#define DEBUG_SUN4V_RTC + +#ifdef DEBUG_SUN4V_RTC +#define DPRINTF(fmt, ...) \ + do { printf("sun4v_rtc: " fmt , ## __VA_ARGS__); } while (0) +#else +#define DPRINTF(fmt, ...) do {} while (0) +#endif + +#define TYPE_SUN4V_RTC "sun4v_rtc" +#define SUN4V_RTC(obj) OBJECT_CHECK(Sun4vRtc, (obj), TYPE_SUN4V_RTC) + +typedef struct Sun4vRtc { + SysBusDevice parent_obj; + + MemoryRegion iomem; +} Sun4vRtc; + +static uint64_t sun4v_rtc_read(void *opaque, hwaddr addr, + unsigned size) +{ + uint64_t val = get_clock_realtime() / NANOSECONDS_PER_SECOND; + if (!(addr & 4ULL)) { + /* accessing the high 32 bits */ + val >>= 32; + } + DPRINTF("read from " TARGET_FMT_plx " val %lx\n", addr, val); + return val; +} + +static void sun4v_rtc_write(void *opaque, hwaddr addr, + uint64_t val, unsigned size) +{ + DPRINTF("write 0x%x to " TARGET_FMT_plx "\n", (unsigned)val, addr); +} + +static const MemoryRegionOps sun4v_rtc_ops = { + .read = sun4v_rtc_read, + .write = sun4v_rtc_write, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +void sun4v_rtc_init(hwaddr addr) +{ + DeviceState *dev; + SysBusDevice *s; + + dev = qdev_create(NULL, TYPE_SUN4V_RTC); + s = SYS_BUS_DEVICE(dev); + + qdev_init_nofail(dev); + + sysbus_mmio_map(s, 0, addr); +} + +static int sun4v_rtc_init1(SysBusDevice *dev) +{ + Sun4vRtc *s = SUN4V_RTC(dev); + + memory_region_init_io(&s->iomem, OBJECT(s), &sun4v_rtc_ops, s, + "sun4v-rtc", 0x08ULL); + sysbus_init_mmio(dev, &s->iomem); + return 0; +} + +static void sun4v_rtc_class_init(ObjectClass *klass, void *data) +{ + SysBusDeviceClass *k = SYS_BUS_DEVICE_CLASS(klass); + + k->init = sun4v_rtc_init1; +} + +static const TypeInfo sun4v_rtc_info = { + .name = TYPE_SUN4V_RTC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(Sun4vRtc), + .class_init = sun4v_rtc_class_init, +}; + +static void sun4v_rtc_register_types(void) +{ + type_register_static(&sun4v_rtc_info); +} + +type_init(sun4v_rtc_register_types) diff --git a/hw/timer/twl92230.c b/hw/timer/twl92230.c index 7ba4e9a7c9..c0aa8ae3de 100644 --- a/hw/timer/twl92230.c +++ b/hw/timer/twl92230.c @@ -713,12 +713,14 @@ static void menelaus_write(void *opaque, uint8_t addr, uint8_t value) } } -static void menelaus_event(I2CSlave *i2c, enum i2c_event event) +static int menelaus_event(I2CSlave *i2c, enum i2c_event event) { MenelausState *s = TWL92230(i2c); if (event == I2C_START_SEND) s->firstbyte = 1; + + return 0; } static int menelaus_tx(I2CSlave *i2c, uint8_t data) @@ -747,17 +749,21 @@ static int menelaus_rx(I2CSlave *i2c) Or we broke compatibility in the state, or we can't use struct tm */ -static int get_int32_as_uint16(QEMUFile *f, void *pv, size_t size) +static int get_int32_as_uint16(QEMUFile *f, void *pv, size_t size, + VMStateField *field) { int *v = pv; *v = qemu_get_be16(f); return 0; } -static void put_int32_as_uint16(QEMUFile *f, void *pv, size_t size) +static int put_int32_as_uint16(QEMUFile *f, void *pv, size_t size, + VMStateField *field, QJSON *vmdesc) { int *v = pv; qemu_put_be16(f, *v); + + return 0; } static const VMStateInfo vmstate_hack_int32_as_uint16 = { diff --git a/hw/usb/bus.c b/hw/usb/bus.c index 25913ad488..1dcc35c8f8 100644 --- a/hw/usb/bus.c +++ b/hw/usb/bus.c @@ -8,6 +8,7 @@ #include "monitor/monitor.h" #include "trace.h" #include "qemu/cutils.h" +#include "migration/migration.h" static void usb_bus_dev_print(Monitor *mon, DeviceState *qdev, int indent); @@ -686,6 +687,8 @@ USBDevice *usbdevice_create(const char *cmdline) const char *params; int len; USBDevice *dev; + ObjectClass *klass; + DeviceClass *dc; params = strchr(cmdline,':'); if (params) { @@ -720,6 +723,22 @@ USBDevice *usbdevice_create(const char *cmdline) return NULL; } + klass = object_class_by_name(f->name); + if (klass == NULL) { + error_report("Device '%s' not found", f->name); + return NULL; + } + + dc = DEVICE_CLASS(klass); + + if (only_migratable) { + if (dc->vmsd->unmigratable) { + error_report("Device %s is not migratable, but --only-migratable " + "was specified", f->name); + return NULL; + } + } + if (f->usbdevice_init) { dev = f->usbdevice_init(bus, params); } else { diff --git a/hw/usb/ccid-card-emulated.c b/hw/usb/ccid-card-emulated.c index eceb5f3ee2..99627860a3 100644 --- a/hw/usb/ccid-card-emulated.c +++ b/hw/usb/ccid-card-emulated.c @@ -407,7 +407,7 @@ static int init_event_notifier(EmulatedState *card) DPRINTF(card, 2, "event notifier creation failed\n"); return -1; } - event_notifier_set_handler(&card->notifier, false, card_event_handler); + event_notifier_set_handler(&card->notifier, card_event_handler); return 0; } diff --git a/hw/usb/dev-mtp.c b/hw/usb/dev-mtp.c index 9cb0f50750..94c2e94f10 100644 --- a/hw/usb/dev-mtp.c +++ b/hw/usb/dev-mtp.c @@ -1093,7 +1093,7 @@ static MTPData *usb_mtp_get_object_prop_value(MTPState *s, MTPControl *c, } break; case PROP_PERSISTENT_UNIQUE_OBJECT_IDENTIFIER: - /* Should be persistant between sessions, + /* Should be persistent between sessions, * but using our objedt ID is "good enough" * for now */ usb_mtp_add_u64(d, 0x0000000000000000); @@ -1580,6 +1580,8 @@ static void usb_mtp_class_initfn(ObjectClass *klass, void *data) uc->handle_reset = usb_mtp_handle_reset; uc->handle_control = usb_mtp_handle_control; uc->handle_data = usb_mtp_handle_data; + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); + dc->desc = "USB Media Transfer Protocol device"; dc->fw_name = "mtp"; dc->vmsd = &vmstate_usb_mtp; dc->props = mtp_properties; diff --git a/hw/usb/hcd-xhci.c b/hw/usb/hcd-xhci.c index 4acf0c6dd8..e0b516987f 100644 --- a/hw/usb/hcd-xhci.c +++ b/hw/usb/hcd-xhci.c @@ -3894,7 +3894,7 @@ static const VMStateDescription vmstate_xhci = { .version_id = 1, .post_load = usb_xhci_post_load, .fields = (VMStateField[]) { - VMSTATE_PCIE_DEVICE(parent_obj, XHCIState), + VMSTATE_PCI_DEVICE(parent_obj, XHCIState), VMSTATE_MSIX(parent_obj, XHCIState), VMSTATE_STRUCT_VARRAY_UINT32(ports, XHCIState, numports, 1, diff --git a/hw/usb/redirect.c b/hw/usb/redirect.c index a65723781e..4a0ebbfb32 100644 --- a/hw/usb/redirect.c +++ b/hw/usb/redirect.c @@ -2165,7 +2165,8 @@ static int usbredir_post_load(void *priv, int version_id) } /* For usbredirparser migration */ -static void usbredir_put_parser(QEMUFile *f, void *priv, size_t unused) +static int usbredir_put_parser(QEMUFile *f, void *priv, size_t unused, + VMStateField *field, QJSON *vmdesc) { USBRedirDevice *dev = priv; uint8_t *data; @@ -2173,7 +2174,7 @@ static void usbredir_put_parser(QEMUFile *f, void *priv, size_t unused) if (dev->parser == NULL) { qemu_put_be32(f, 0); - return; + return 0; } usbredirparser_serialize(dev->parser, &data, &len); @@ -2183,9 +2184,12 @@ static void usbredir_put_parser(QEMUFile *f, void *priv, size_t unused) qemu_put_buffer(f, data, len); free(data); + + return 0; } -static int usbredir_get_parser(QEMUFile *f, void *priv, size_t unused) +static int usbredir_get_parser(QEMUFile *f, void *priv, size_t unused, + VMStateField *field) { USBRedirDevice *dev = priv; uint8_t *data; @@ -2228,7 +2232,8 @@ static const VMStateInfo usbredir_parser_vmstate_info = { /* For buffered packets (iso/irq) queue migration */ -static void usbredir_put_bufpq(QEMUFile *f, void *priv, size_t unused) +static int usbredir_put_bufpq(QEMUFile *f, void *priv, size_t unused, + VMStateField *field, QJSON *vmdesc) { struct endp_data *endp = priv; USBRedirDevice *dev = endp->dev; @@ -2246,9 +2251,12 @@ static void usbredir_put_bufpq(QEMUFile *f, void *priv, size_t unused) i++; } assert(i == endp->bufpq_size); + + return 0; } -static int usbredir_get_bufpq(QEMUFile *f, void *priv, size_t unused) +static int usbredir_get_bufpq(QEMUFile *f, void *priv, size_t unused, + VMStateField *field) { struct endp_data *endp = priv; USBRedirDevice *dev = endp->dev; @@ -2351,7 +2359,8 @@ static const VMStateDescription usbredir_ep_vmstate = { /* For PacketIdQueue migration */ -static void usbredir_put_packet_id_q(QEMUFile *f, void *priv, size_t unused) +static int usbredir_put_packet_id_q(QEMUFile *f, void *priv, size_t unused, + VMStateField *field, QJSON *vmdesc) { struct PacketIdQueue *q = priv; USBRedirDevice *dev = q->dev; @@ -2365,9 +2374,12 @@ static void usbredir_put_packet_id_q(QEMUFile *f, void *priv, size_t unused) remain--; } assert(remain == 0); + + return 0; } -static int usbredir_get_packet_id_q(QEMUFile *f, void *priv, size_t unused) +static int usbredir_get_packet_id_q(QEMUFile *f, void *priv, size_t unused, + VMStateField *field) { struct PacketIdQueue *q = priv; USBRedirDevice *dev = q->dev; diff --git a/hw/vfio/pci-quirks.c b/hw/vfio/pci-quirks.c index 811eecd1b4..6c771f778b 100644 --- a/hw/vfio/pci-quirks.c +++ b/hw/vfio/pci-quirks.c @@ -1171,7 +1171,7 @@ static int vfio_pci_igd_host_init(VFIOPCIDevice *vdev, * IGD LPC/ISA bridge support code. The vBIOS needs this, but we can't write * arbitrary values into just any bridge, so we must create our own. We try * to handle if the user has created it for us, which they might want to do - * to enable multifuction so we don't occupy the whole PCI slot. + * to enable multifunction so we don't occupy the whole PCI slot. */ static void vfio_pci_igd_lpc_bridge_realize(PCIDevice *pdev, Error **errp) { diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index d7dbe0e3e0..882d3a91b6 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -1881,8 +1881,8 @@ static void vfio_add_ext_cap(VFIOPCIDevice *vdev) * 0 is reserved for this since absence of capabilities is indicated by * 0 for the ID, version, AND next pointer. However, pcie_add_capability() * uses ID 0 as reserved for list management and will incorrectly match and - * assert if we attempt to pre-load the head of the chain with with this - * ID. Use ID 0xFFFF temporarily since it is also seems to be reserved in + * assert if we attempt to pre-load the head of the chain with this ID. + * Use ID 0xFFFF temporarily since it is also seems to be reserved in * part for identifying absence of capabilities in a root complex register * block. If the ID still exists after adding capabilities, switch back to * zero. We'll mark this entire first dword as emulated for this purpose. diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs index 95c4c30ea1..765d363c1f 100644 --- a/hw/virtio/Makefile.objs +++ b/hw/virtio/Makefile.objs @@ -1,3 +1,4 @@ +ifeq ($(CONFIG_VIRTIO),y) common-obj-y += virtio-rng.o common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o common-obj-y += virtio-bus.o @@ -5,7 +6,10 @@ common-obj-y += virtio-mmio.o obj-y += virtio.o virtio-balloon.o obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o - obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock.o obj-y += virtio-crypto.o obj-$(CONFIG_VIRTIO_PCI) += virtio-crypto-pci.o +endif + +common-obj-$(call lnot,$(CONFIG_LINUX)) += vhost-stub.o +common-obj-$(CONFIG_ALL) += vhost-stub.o diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index 7b6f55e70e..6926eedd3f 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -15,6 +15,8 @@ virtio_rng_pushed(void *rng, size_t len) "rng %p: %zd bytes pushed" virtio_rng_request(void *rng, size_t size, unsigned quota) "rng %p: %zd bytes requested, %u bytes quota left" # hw/virtio/virtio-balloon.c +# +virtio_balloon_bad_addr(uint64_t gpa) "%"PRIx64 virtio_balloon_handle_output(const char *name, uint64_t gpa) "section name: %s gpa: %"PRIx64 virtio_balloon_get_config(uint32_t num_pages, uint32_t actual) "num_pages: %d actual: %d" virtio_balloon_set_config(uint32_t actual, uint32_t oldactual) "actual: %d oldactual: %d" diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c index 272a5ec584..be927b891e 100644 --- a/hw/virtio/vhost-backend.c +++ b/hw/virtio/vhost-backend.c @@ -185,6 +185,102 @@ static int vhost_kernel_vsock_set_running(struct vhost_dev *dev, int start) } #endif /* CONFIG_VHOST_VSOCK */ +static void vhost_kernel_iotlb_read(void *opaque) +{ + struct vhost_dev *dev = opaque; + struct vhost_msg msg; + ssize_t len; + + while ((len = read((uintptr_t)dev->opaque, &msg, sizeof msg)) > 0) { + struct vhost_iotlb_msg *imsg = &msg.iotlb; + if (len < sizeof msg) { + error_report("Wrong vhost message len: %d", (int)len); + break; + } + if (msg.type != VHOST_IOTLB_MSG) { + error_report("Unknown vhost iotlb message type"); + break; + } + switch (imsg->type) { + case VHOST_IOTLB_MISS: + vhost_device_iotlb_miss(dev, imsg->iova, + imsg->perm != VHOST_ACCESS_RO); + break; + case VHOST_IOTLB_UPDATE: + case VHOST_IOTLB_INVALIDATE: + error_report("Unexpected IOTLB message type"); + break; + case VHOST_IOTLB_ACCESS_FAIL: + /* FIXME: report device iotlb error */ + break; + default: + break; + } + } +} + +static int vhost_kernel_update_device_iotlb(struct vhost_dev *dev, + uint64_t iova, uint64_t uaddr, + uint64_t len, + IOMMUAccessFlags perm) +{ + struct vhost_msg msg; + msg.type = VHOST_IOTLB_MSG; + msg.iotlb.iova = iova; + msg.iotlb.uaddr = uaddr; + msg.iotlb.size = len; + msg.iotlb.type = VHOST_IOTLB_UPDATE; + + switch (perm) { + case IOMMU_RO: + msg.iotlb.perm = VHOST_ACCESS_RO; + break; + case IOMMU_WO: + msg.iotlb.perm = VHOST_ACCESS_WO; + break; + case IOMMU_RW: + msg.iotlb.perm = VHOST_ACCESS_RW; + break; + default: + g_assert_not_reached(); + } + + if (write((uintptr_t)dev->opaque, &msg, sizeof msg) != sizeof msg) { + error_report("Fail to update device iotlb"); + return -EFAULT; + } + + return 0; +} + +static int vhost_kernel_invalidate_device_iotlb(struct vhost_dev *dev, + uint64_t iova, uint64_t len) +{ + struct vhost_msg msg; + + msg.type = VHOST_IOTLB_MSG; + msg.iotlb.iova = iova; + msg.iotlb.size = len; + msg.iotlb.type = VHOST_IOTLB_INVALIDATE; + + if (write((uintptr_t)dev->opaque, &msg, sizeof msg) != sizeof msg) { + error_report("Fail to invalidate device iotlb"); + return -EFAULT; + } + + return 0; +} + +static void vhost_kernel_set_iotlb_callback(struct vhost_dev *dev, + int enabled) +{ + if (enabled) + qemu_set_fd_handler((uintptr_t)dev->opaque, + vhost_kernel_iotlb_read, NULL, dev); + else + qemu_set_fd_handler((uintptr_t)dev->opaque, NULL, NULL, NULL); +} + static const VhostOps kernel_ops = { .backend_type = VHOST_BACKEND_TYPE_KERNEL, .vhost_backend_init = vhost_kernel_init, @@ -214,6 +310,9 @@ static const VhostOps kernel_ops = { .vhost_vsock_set_guest_cid = vhost_kernel_vsock_set_guest_cid, .vhost_vsock_set_running = vhost_kernel_vsock_set_running, #endif /* CONFIG_VHOST_VSOCK */ + .vhost_set_iotlb_callback = vhost_kernel_set_iotlb_callback, + .vhost_update_device_iotlb = vhost_kernel_update_device_iotlb, + .vhost_invalidate_device_iotlb = vhost_kernel_invalidate_device_iotlb, }; int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type) diff --git a/hw/virtio/vhost-stub.c b/hw/virtio/vhost-stub.c new file mode 100644 index 0000000000..2d76cdebdc --- /dev/null +++ b/hw/virtio/vhost-stub.c @@ -0,0 +1,7 @@ +#include "qemu/osdep.h" +#include "hw/virtio/vhost.h" + +bool vhost_has_free_slot(void) +{ + return true; +} diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 7ee92b32c5..9334a8ae22 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -32,6 +32,7 @@ enum VhostUserProtocolFeature { VHOST_USER_PROTOCOL_F_LOG_SHMFD = 1, VHOST_USER_PROTOCOL_F_RARP = 2, VHOST_USER_PROTOCOL_F_REPLY_ACK = 3, + VHOST_USER_PROTOCOL_F_NET_MTU = 4, VHOST_USER_PROTOCOL_F_MAX }; @@ -59,6 +60,7 @@ typedef enum VhostUserRequest { VHOST_USER_GET_QUEUE_NUM = 17, VHOST_USER_SET_VRING_ENABLE = 18, VHOST_USER_SEND_RARP = 19, + VHOST_USER_NET_SET_MTU = 20, VHOST_USER_MAX } VhostUserRequest; @@ -186,6 +188,7 @@ static bool vhost_user_one_time_request(VhostUserRequest request) case VHOST_USER_RESET_OWNER: case VHOST_USER_SET_MEM_TABLE: case VHOST_USER_GET_QUEUE_NUM: + case VHOST_USER_NET_SET_MTU: return true; default: return false; @@ -685,6 +688,36 @@ static bool vhost_user_can_merge(struct vhost_dev *dev, return mfd == rfd; } +static int vhost_user_net_set_mtu(struct vhost_dev *dev, uint16_t mtu) +{ + VhostUserMsg msg; + bool reply_supported = virtio_has_feature(dev->protocol_features, + VHOST_USER_PROTOCOL_F_REPLY_ACK); + + if (!(dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_NET_MTU))) { + return 0; + } + + msg.request = VHOST_USER_NET_SET_MTU; + msg.payload.u64 = mtu; + msg.size = sizeof(msg.payload.u64); + msg.flags = VHOST_USER_VERSION; + if (reply_supported) { + msg.flags |= VHOST_USER_NEED_REPLY_MASK; + } + + if (vhost_user_write(dev, &msg, NULL, 0) < 0) { + return -1; + } + + /* If reply_ack supported, slave has to ack specified MTU is valid */ + if (reply_supported) { + return process_message_reply(dev, msg.request); + } + + return 0; +} + const VhostOps user_ops = { .backend_type = VHOST_BACKEND_TYPE_USER, .vhost_backend_init = vhost_user_init, @@ -708,4 +741,5 @@ const VhostOps user_ops = { .vhost_requires_shm_log = vhost_user_requires_shm_log, .vhost_migration_done = vhost_user_migration_done, .vhost_backend_can_merge = vhost_user_can_merge, + .vhost_net_set_mtu = vhost_user_net_set_mtu, }; diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index f7f70237db..b124d97d7c 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -26,6 +26,7 @@ #include "hw/virtio/virtio-bus.h" #include "hw/virtio/virtio-access.h" #include "migration/migration.h" +#include "sysemu/dma.h" /* enabled until disconnected backend stabilizes */ #define _VHOST_DEBUG 1 @@ -421,8 +422,36 @@ static inline void vhost_dev_log_resize(struct vhost_dev *dev, uint64_t size) dev->log_size = size; } +static int vhost_dev_has_iommu(struct vhost_dev *dev) +{ + VirtIODevice *vdev = dev->vdev; + AddressSpace *dma_as = vdev->dma_as; + + return memory_region_is_iommu(dma_as->root) && + virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM); +} + +static void *vhost_memory_map(struct vhost_dev *dev, hwaddr addr, + hwaddr *plen, int is_write) +{ + if (!vhost_dev_has_iommu(dev)) { + return cpu_physical_memory_map(addr, plen, is_write); + } else { + return (void *)(uintptr_t)addr; + } +} + +static void vhost_memory_unmap(struct vhost_dev *dev, void *buffer, + hwaddr len, int is_write, + hwaddr access_len) +{ + if (!vhost_dev_has_iommu(dev)) { + cpu_physical_memory_unmap(buffer, len, is_write, access_len); + } +} -static int vhost_verify_ring_part_mapping(void *part, +static int vhost_verify_ring_part_mapping(struct vhost_dev *dev, + void *part, uint64_t part_addr, uint64_t part_size, uint64_t start_addr, @@ -436,14 +465,14 @@ static int vhost_verify_ring_part_mapping(void *part, return 0; } l = part_size; - p = cpu_physical_memory_map(part_addr, &l, 1); + p = vhost_memory_map(dev, part_addr, &l, 1); if (!p || l != part_size) { r = -ENOMEM; } if (p != part) { r = -EBUSY; } - cpu_physical_memory_unmap(p, l, 0, 0); + vhost_memory_unmap(dev, p, l, 0, 0); return r; } @@ -463,21 +492,21 @@ static int vhost_verify_ring_mappings(struct vhost_dev *dev, struct vhost_virtqueue *vq = dev->vqs + i; j = 0; - r = vhost_verify_ring_part_mapping(vq->desc, vq->desc_phys, + r = vhost_verify_ring_part_mapping(dev, vq->desc, vq->desc_phys, vq->desc_size, start_addr, size); if (!r) { break; } j++; - r = vhost_verify_ring_part_mapping(vq->avail, vq->avail_phys, + r = vhost_verify_ring_part_mapping(dev, vq->avail, vq->avail_phys, vq->avail_size, start_addr, size); if (!r) { break; } j++; - r = vhost_verify_ring_part_mapping(vq->used, vq->used_phys, + r = vhost_verify_ring_part_mapping(dev, vq->used, vq->used_phys, vq->used_size, start_addr, size); if (!r) { break; @@ -715,7 +744,8 @@ static int vhost_virtqueue_set_addr(struct vhost_dev *dev, return 0; } -static int vhost_dev_set_features(struct vhost_dev *dev, bool enable_log) +static int vhost_dev_set_features(struct vhost_dev *dev, + bool enable_log) { uint64_t features = dev->acked_features; int r; @@ -858,6 +888,56 @@ static int vhost_virtqueue_set_vring_endian_legacy(struct vhost_dev *dev, return -errno; } +static int vhost_memory_region_lookup(struct vhost_dev *hdev, + uint64_t gpa, uint64_t *uaddr, + uint64_t *len) +{ + int i; + + for (i = 0; i < hdev->mem->nregions; i++) { + struct vhost_memory_region *reg = hdev->mem->regions + i; + + if (gpa >= reg->guest_phys_addr && + reg->guest_phys_addr + reg->memory_size > gpa) { + *uaddr = reg->userspace_addr + gpa - reg->guest_phys_addr; + *len = reg->guest_phys_addr + reg->memory_size - gpa; + return 0; + } + } + + return -EFAULT; +} + +void vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write) +{ + IOMMUTLBEntry iotlb; + uint64_t uaddr, len; + + rcu_read_lock(); + + iotlb = address_space_get_iotlb_entry(dev->vdev->dma_as, + iova, write); + if (iotlb.target_as != NULL) { + if (vhost_memory_region_lookup(dev, iotlb.translated_addr, + &uaddr, &len)) { + error_report("Fail to lookup the translated address " + "%"PRIx64, iotlb.translated_addr); + goto out; + } + + len = MIN(iotlb.addr_mask + 1, len); + iova = iova & ~iotlb.addr_mask; + + if (dev->vhost_ops->vhost_update_device_iotlb(dev, iova, uaddr, + len, iotlb.perm)) { + error_report("Fail to update device iotlb"); + goto out; + } + } +out: + rcu_read_unlock(); +} + static int vhost_virtqueue_start(struct vhost_dev *dev, struct VirtIODevice *vdev, struct vhost_virtqueue *vq, @@ -903,21 +983,21 @@ static int vhost_virtqueue_start(struct vhost_dev *dev, vq->desc_size = s = l = virtio_queue_get_desc_size(vdev, idx); vq->desc_phys = a = virtio_queue_get_desc_addr(vdev, idx); - vq->desc = cpu_physical_memory_map(a, &l, 0); + vq->desc = vhost_memory_map(dev, a, &l, 0); if (!vq->desc || l != s) { r = -ENOMEM; goto fail_alloc_desc; } vq->avail_size = s = l = virtio_queue_get_avail_size(vdev, idx); vq->avail_phys = a = virtio_queue_get_avail_addr(vdev, idx); - vq->avail = cpu_physical_memory_map(a, &l, 0); + vq->avail = vhost_memory_map(dev, a, &l, 0); if (!vq->avail || l != s) { r = -ENOMEM; goto fail_alloc_avail; } vq->used_size = s = l = virtio_queue_get_used_size(vdev, idx); vq->used_phys = a = virtio_queue_get_used_addr(vdev, idx); - vq->used = cpu_physical_memory_map(a, &l, 1); + vq->used = vhost_memory_map(dev, a, &l, 1); if (!vq->used || l != s) { r = -ENOMEM; goto fail_alloc_used; @@ -963,14 +1043,14 @@ static int vhost_virtqueue_start(struct vhost_dev *dev, fail_vector: fail_kick: fail_alloc: - cpu_physical_memory_unmap(vq->used, virtio_queue_get_used_size(vdev, idx), - 0, 0); + vhost_memory_unmap(dev, vq->used, virtio_queue_get_used_size(vdev, idx), + 0, 0); fail_alloc_used: - cpu_physical_memory_unmap(vq->avail, virtio_queue_get_avail_size(vdev, idx), - 0, 0); + vhost_memory_unmap(dev, vq->avail, virtio_queue_get_avail_size(vdev, idx), + 0, 0); fail_alloc_avail: - cpu_physical_memory_unmap(vq->desc, virtio_queue_get_desc_size(vdev, idx), - 0, 0); + vhost_memory_unmap(dev, vq->desc, virtio_queue_get_desc_size(vdev, idx), + 0, 0); fail_alloc_desc: return r; } @@ -993,6 +1073,7 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev, virtio_queue_set_last_avail_idx(vdev, idx, state.num); } virtio_queue_invalidate_signalled_used(vdev, idx); + virtio_queue_update_used_idx(vdev, idx); /* In the cross-endian case, we need to reset the vring endianness to * native as legacy devices expect so by default. @@ -1003,12 +1084,12 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev, vhost_vq_index); } - cpu_physical_memory_unmap(vq->used, virtio_queue_get_used_size(vdev, idx), - 1, virtio_queue_get_used_size(vdev, idx)); - cpu_physical_memory_unmap(vq->avail, virtio_queue_get_avail_size(vdev, idx), - 0, virtio_queue_get_avail_size(vdev, idx)); - cpu_physical_memory_unmap(vq->desc, virtio_queue_get_desc_size(vdev, idx), - 0, virtio_queue_get_desc_size(vdev, idx)); + vhost_memory_unmap(dev, vq->used, virtio_queue_get_used_size(vdev, idx), + 1, virtio_queue_get_used_size(vdev, idx)); + vhost_memory_unmap(dev, vq->avail, virtio_queue_get_avail_size(vdev, idx), + 0, virtio_queue_get_avail_size(vdev, idx)); + vhost_memory_unmap(dev, vq->desc, virtio_queue_get_desc_size(vdev, idx), + 0, virtio_queue_get_desc_size(vdev, idx)); } static void vhost_eventfd_add(MemoryListener *listener, @@ -1065,6 +1146,9 @@ static int vhost_virtqueue_init(struct vhost_dev *dev, r = -errno; goto fail_call; } + + vq->dev = dev; + return 0; fail_call: event_notifier_cleanup(&vq->masked_notifier); @@ -1076,12 +1160,25 @@ static void vhost_virtqueue_cleanup(struct vhost_virtqueue *vq) event_notifier_cleanup(&vq->masked_notifier); } +static void vhost_iommu_unmap_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) +{ + struct vhost_dev *hdev = container_of(n, struct vhost_dev, n); + + if (hdev->vhost_ops->vhost_invalidate_device_iotlb(hdev, + iotlb->iova, + iotlb->addr_mask + 1)) { + error_report("Fail to invalidate device iotlb"); + } +} + int vhost_dev_init(struct vhost_dev *hdev, void *opaque, VhostBackendType backend_type, uint32_t busyloop_timeout) { uint64_t features; int i, r, n_initialized_vqs = 0; + Error *local_err = NULL; + hdev->vdev = NULL; hdev->migration_blocker = NULL; r = vhost_set_backend_type(hdev, backend_type); @@ -1146,6 +1243,9 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, .priority = 10 }; + hdev->n.notify = vhost_iommu_unmap_notify; + hdev->n.notifier_flags = IOMMU_NOTIFIER_UNMAP; + if (hdev->migration_blocker == NULL) { if (!(hdev->features & (0x1ULL << VHOST_F_LOG_ALL))) { error_setg(&hdev->migration_blocker, @@ -1157,7 +1257,12 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, } if (hdev->migration_blocker != NULL) { - migrate_add_blocker(hdev->migration_blocker); + r = migrate_add_blocker(hdev->migration_blocker, &local_err); + if (local_err) { + error_report_err(local_err); + error_free(hdev->migration_blocker); + goto fail_busyloop; + } } hdev->mem = g_malloc0(offsetof(struct vhost_memory, regions)); @@ -1341,11 +1446,18 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) assert(hdev->vhost_ops); hdev->started = true; + hdev->vdev = vdev; r = vhost_dev_set_features(hdev, hdev->log_enabled); if (r < 0) { goto fail_features; } + + if (vhost_dev_has_iommu(hdev)) { + memory_region_register_iommu_notifier(vdev->dma_as->root, + &hdev->n); + } + r = hdev->vhost_ops->vhost_set_mem_table(hdev, hdev->mem); if (r < 0) { VHOST_OPS_DEBUG("vhost_set_mem_table failed"); @@ -1379,6 +1491,16 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) } } + if (vhost_dev_has_iommu(hdev)) { + hdev->vhost_ops->vhost_set_iotlb_callback(hdev, true); + + /* Update used ring information for IOTLB to work correctly, + * vhost-kernel code requires for this.*/ + for (i = 0; i < hdev->nvqs; ++i) { + struct vhost_virtqueue *vq = hdev->vqs + i; + vhost_device_iotlb_miss(hdev, vq->used_phys, true); + } + } return 0; fail_log: vhost_log_put(hdev, false); @@ -1390,6 +1512,7 @@ fail_vq: hdev->vq_index + i); } i = hdev->nvqs; + fail_mem: fail_features: @@ -1412,8 +1535,14 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) hdev->vq_index + i); } + if (vhost_dev_has_iommu(hdev)) { + hdev->vhost_ops->vhost_set_iotlb_callback(hdev, false); + memory_region_unregister_iommu_notifier(vdev->dma_as->root, + &hdev->n); + } vhost_log_put(hdev, true); hdev->started = false; + hdev->vdev = NULL; } int vhost_net_set_backend(struct vhost_dev *hdev, diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c index 884570a57d..a705e0ec55 100644 --- a/hw/virtio/virtio-balloon.c +++ b/hw/virtio/virtio-balloon.c @@ -228,8 +228,13 @@ static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq) /* FIXME: remove get_system_memory(), but how? */ section = memory_region_find(get_system_memory(), pa, 1); - if (!int128_nz(section.size) || !memory_region_is_ram(section.mr)) + if (!int128_nz(section.size) || + !memory_region_is_ram(section.mr) || + memory_region_is_rom(section.mr) || + memory_region_is_romd(section.mr)) { + trace_virtio_balloon_bad_addr(pa); continue; + } trace_virtio_balloon_handle_output(memory_region_name(section.mr), pa); diff --git a/hw/virtio/virtio-bus.c b/hw/virtio/virtio-bus.c index d6c0c72bd2..a886011e75 100644 --- a/hw/virtio/virtio-bus.c +++ b/hw/virtio/virtio-bus.c @@ -28,6 +28,7 @@ #include "hw/qdev.h" #include "hw/virtio/virtio-bus.h" #include "hw/virtio/virtio.h" +#include "exec/address-spaces.h" /* #define DEBUG_VIRTIO_BUS */ @@ -46,6 +47,7 @@ void virtio_bus_device_plugged(VirtIODevice *vdev, Error **errp) VirtioBusState *bus = VIRTIO_BUS(qbus); VirtioBusClass *klass = VIRTIO_BUS_GET_CLASS(bus); VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev); + bool has_iommu = virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM); DPRINTF("%s: plug device.\n", qbus->name); @@ -61,6 +63,13 @@ void virtio_bus_device_plugged(VirtIODevice *vdev, Error **errp) if (klass->device_plugged != NULL) { klass->device_plugged(qbus->parent, errp); } + + if (klass->get_dma_as != NULL && has_iommu) { + virtio_add_feature(&vdev->host_features, VIRTIO_F_IOMMU_PLATFORM); + vdev->dma_as = klass->get_dma_as(qbus->parent); + } else { + vdev->dma_as = &address_space_memory; + } } /* Reset the virtio_bus */ diff --git a/hw/virtio/virtio-crypto-pci.c b/hw/virtio/virtio-crypto-pci.c index a1b09064c0..422aca3a98 100644 --- a/hw/virtio/virtio-crypto-pci.c +++ b/hw/virtio/virtio-crypto-pci.c @@ -31,6 +31,11 @@ static void virtio_crypto_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) VirtIOCryptoPCI *vcrypto = VIRTIO_CRYPTO_PCI(vpci_dev); DeviceState *vdev = DEVICE(&vcrypto->vdev); + if (vcrypto->vdev.conf.cryptodev == NULL) { + error_setg(errp, "'cryptodev' parameter expects a valid object"); + return; + } + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); virtio_pci_force_virtio_1(vpci_dev); object_property_set_bool(OBJECT(vdev), true, "realized", errp); @@ -48,7 +53,6 @@ static void virtio_crypto_pci_class_init(ObjectClass *klass, void *data) k->realize = virtio_crypto_pci_realize; set_bit(DEVICE_CATEGORY_MISC, dc->categories); dc->props = virtio_crypto_pci_properties; - dc->hotpluggable = false; pcidev_k->class_id = PCI_CLASS_OTHERS; } diff --git a/hw/virtio/virtio-crypto.c b/hw/virtio/virtio-crypto.c index 2f2467e859..0353eb6d5d 100644 --- a/hw/virtio/virtio-crypto.c +++ b/hw/virtio/virtio-crypto.c @@ -337,7 +337,18 @@ static void virtio_crypto_free_request(VirtIOCryptoReq *req) { if (req) { if (req->flags == CRYPTODEV_BACKEND_ALG_SYM) { - g_free(req->u.sym_op_info); + size_t max_len; + CryptoDevBackendSymOpInfo *op_info = req->u.sym_op_info; + + max_len = op_info->iv_len + + op_info->aad_len + + op_info->src_len + + op_info->dst_len + + op_info->digest_result_len; + + /* Zeroize and free request data structure */ + memset(op_info, 0, sizeof(*op_info) + max_len); + g_free(op_info); } g_free(req); } @@ -355,7 +366,7 @@ virtio_crypto_sym_input_data_helper(VirtIODevice *vdev, return; } - len = sym_op_info->dst_len; + len = sym_op_info->src_len; /* Save the cipher result */ s = iov_from_buf(req->in_iov, req->in_num, 0, sym_op_info->dst, len); if (s != len) { @@ -416,7 +427,7 @@ virtio_crypto_sym_op_helper(VirtIODevice *vdev, uint32_t hash_start_src_offset = 0, len_to_hash = 0; uint32_t cipher_start_src_offset = 0, len_to_cipher = 0; - size_t max_len, curr_size = 0; + uint64_t max_len, curr_size = 0; size_t s; /* Plain cipher */ @@ -441,7 +452,7 @@ virtio_crypto_sym_op_helper(VirtIODevice *vdev, return NULL; } - max_len = iv_len + aad_len + src_len + dst_len + hash_result_len; + max_len = (uint64_t)iv_len + aad_len + src_len + dst_len + hash_result_len; if (unlikely(max_len > vcrypto->conf.max_size)) { virtio_error(vdev, "virtio-crypto too big length"); return NULL; @@ -732,7 +743,7 @@ static void virtio_crypto_reset(VirtIODevice *vdev) VirtIOCrypto *vcrypto = VIRTIO_CRYPTO(vdev); /* multiqueue is disabled by default */ vcrypto->curr_queues = 1; - if (!vcrypto->cryptodev->ready) { + if (!cryptodev_backend_is_ready(vcrypto->cryptodev)) { vcrypto->status &= ~VIRTIO_CRYPTO_S_HW_READY; } else { vcrypto->status |= VIRTIO_CRYPTO_S_HW_READY; @@ -775,7 +786,7 @@ static void virtio_crypto_device_realize(DeviceState *dev, Error **errp) vcrypto->max_queues = MAX(vcrypto->cryptodev->conf.peers.queues, 1); if (vcrypto->max_queues + 1 > VIRTIO_QUEUE_MAX) { error_setg(errp, "Invalid number of queues (= %" PRIu32 "), " - "must be a postive integer less than %d.", + "must be a positive integer less than %d.", vcrypto->max_queues, VIRTIO_QUEUE_MAX); return; } @@ -792,13 +803,14 @@ static void virtio_crypto_device_realize(DeviceState *dev, Error **errp) } vcrypto->ctrl_vq = virtio_add_queue(vdev, 64, virtio_crypto_handle_ctrl); - if (!vcrypto->cryptodev->ready) { + if (!cryptodev_backend_is_ready(vcrypto->cryptodev)) { vcrypto->status &= ~VIRTIO_CRYPTO_S_HW_READY; } else { vcrypto->status |= VIRTIO_CRYPTO_S_HW_READY; } virtio_crypto_init_config(vdev); + cryptodev_backend_set_used(vcrypto->cryptodev, true); } static void virtio_crypto_device_unrealize(DeviceState *dev, Error **errp) @@ -818,6 +830,7 @@ static void virtio_crypto_device_unrealize(DeviceState *dev, Error **errp) g_free(vcrypto->vqs); virtio_cleanup(vdev); + cryptodev_backend_set_used(vcrypto->cryptodev, false); } static const VMStateDescription vmstate_virtio_crypto = { @@ -875,6 +888,20 @@ static void virtio_crypto_class_init(ObjectClass *klass, void *data) vdc->reset = virtio_crypto_reset; } +static void +virtio_crypto_check_cryptodev_is_used(Object *obj, const char *name, + Object *val, Error **errp) +{ + if (cryptodev_backend_is_used(CRYPTODEV_BACKEND(val))) { + char *path = object_get_canonical_path_component(val); + error_setg(errp, + "can't use already used cryptodev backend: %s", path); + g_free(path); + } else { + qdev_prop_allow_set_link_before_realize(obj, name, val, errp); + } +} + static void virtio_crypto_instance_init(Object *obj) { VirtIOCrypto *vcrypto = VIRTIO_CRYPTO(obj); @@ -888,7 +915,7 @@ static void virtio_crypto_instance_init(Object *obj) object_property_add_link(obj, "cryptodev", TYPE_CRYPTODEV_BACKEND, (Object **)&vcrypto->conf.cryptodev, - qdev_prop_allow_set_link_before_realize, + virtio_crypto_check_cryptodev_is_used, OBJ_PROP_LINK_UNREF_ON_RELEASE, NULL); } diff --git a/hw/virtio/virtio-mmio.c b/hw/virtio/virtio-mmio.c index 17412cb7b5..5807aa87fe 100644 --- a/hw/virtio/virtio-mmio.c +++ b/hw/virtio/virtio-mmio.c @@ -20,6 +20,7 @@ */ #include "qemu/osdep.h" +#include "standard-headers/linux/virtio_mmio.h" #include "hw/sysbus.h" #include "hw/virtio/virtio.h" #include "qemu/host-utils.h" @@ -52,28 +53,6 @@ do { printf("virtio_mmio: " fmt , ## __VA_ARGS__); } while (0) #define VIRTIO_MMIO(obj) \ OBJECT_CHECK(VirtIOMMIOProxy, (obj), TYPE_VIRTIO_MMIO) -/* Memory mapped register offsets */ -#define VIRTIO_MMIO_MAGIC 0x0 -#define VIRTIO_MMIO_VERSION 0x4 -#define VIRTIO_MMIO_DEVICEID 0x8 -#define VIRTIO_MMIO_VENDORID 0xc -#define VIRTIO_MMIO_HOSTFEATURES 0x10 -#define VIRTIO_MMIO_HOSTFEATURESSEL 0x14 -#define VIRTIO_MMIO_GUESTFEATURES 0x20 -#define VIRTIO_MMIO_GUESTFEATURESSEL 0x24 -#define VIRTIO_MMIO_GUESTPAGESIZE 0x28 -#define VIRTIO_MMIO_QUEUESEL 0x30 -#define VIRTIO_MMIO_QUEUENUMMAX 0x34 -#define VIRTIO_MMIO_QUEUENUM 0x38 -#define VIRTIO_MMIO_QUEUEALIGN 0x3c -#define VIRTIO_MMIO_QUEUEPFN 0x40 -#define VIRTIO_MMIO_QUEUENOTIFY 0x50 -#define VIRTIO_MMIO_INTERRUPTSTATUS 0x60 -#define VIRTIO_MMIO_INTERRUPTACK 0x64 -#define VIRTIO_MMIO_STATUS 0x70 -/* Device specific config space starts here */ -#define VIRTIO_MMIO_CONFIG 0x100 - #define VIRT_MAGIC 0x74726976 /* 'virt' */ #define VIRT_VERSION 1 #define VIRT_VENDOR 0x554D4551 /* 'QEMU' */ @@ -104,10 +83,10 @@ static int virtio_mmio_ioeventfd_assign(DeviceState *d, VirtIOMMIOProxy *proxy = VIRTIO_MMIO(d); if (assign) { - memory_region_add_eventfd(&proxy->iomem, VIRTIO_MMIO_QUEUENOTIFY, 4, + memory_region_add_eventfd(&proxy->iomem, VIRTIO_MMIO_QUEUE_NOTIFY, 4, true, n, notifier); } else { - memory_region_del_eventfd(&proxy->iomem, VIRTIO_MMIO_QUEUENOTIFY, 4, + memory_region_del_eventfd(&proxy->iomem, VIRTIO_MMIO_QUEUE_NOTIFY, 4, true, n, notifier); } return 0; @@ -140,11 +119,11 @@ static uint64_t virtio_mmio_read(void *opaque, hwaddr offset, unsigned size) * device ID of zero means no backend will claim it. */ switch (offset) { - case VIRTIO_MMIO_MAGIC: + case VIRTIO_MMIO_MAGIC_VALUE: return VIRT_MAGIC; case VIRTIO_MMIO_VERSION: return VIRT_VERSION; - case VIRTIO_MMIO_VENDORID: + case VIRTIO_MMIO_VENDOR_ID: return VIRT_VENDOR; default: return 0; @@ -169,40 +148,40 @@ static uint64_t virtio_mmio_read(void *opaque, hwaddr offset, unsigned size) return 0; } switch (offset) { - case VIRTIO_MMIO_MAGIC: + case VIRTIO_MMIO_MAGIC_VALUE: return VIRT_MAGIC; case VIRTIO_MMIO_VERSION: return VIRT_VERSION; - case VIRTIO_MMIO_DEVICEID: + case VIRTIO_MMIO_DEVICE_ID: return vdev->device_id; - case VIRTIO_MMIO_VENDORID: + case VIRTIO_MMIO_VENDOR_ID: return VIRT_VENDOR; - case VIRTIO_MMIO_HOSTFEATURES: + case VIRTIO_MMIO_DEVICE_FEATURES: if (proxy->host_features_sel) { return 0; } return vdev->host_features; - case VIRTIO_MMIO_QUEUENUMMAX: + case VIRTIO_MMIO_QUEUE_NUM_MAX: if (!virtio_queue_get_num(vdev, vdev->queue_sel)) { return 0; } return VIRTQUEUE_MAX_SIZE; - case VIRTIO_MMIO_QUEUEPFN: + case VIRTIO_MMIO_QUEUE_PFN: return virtio_queue_get_addr(vdev, vdev->queue_sel) >> proxy->guest_page_shift; - case VIRTIO_MMIO_INTERRUPTSTATUS: + case VIRTIO_MMIO_INTERRUPT_STATUS: return atomic_read(&vdev->isr); case VIRTIO_MMIO_STATUS: return vdev->status; - case VIRTIO_MMIO_HOSTFEATURESSEL: - case VIRTIO_MMIO_GUESTFEATURES: - case VIRTIO_MMIO_GUESTFEATURESSEL: - case VIRTIO_MMIO_GUESTPAGESIZE: - case VIRTIO_MMIO_QUEUESEL: - case VIRTIO_MMIO_QUEUENUM: - case VIRTIO_MMIO_QUEUEALIGN: - case VIRTIO_MMIO_QUEUENOTIFY: - case VIRTIO_MMIO_INTERRUPTACK: + case VIRTIO_MMIO_DEVICE_FEATURES_SEL: + case VIRTIO_MMIO_DRIVER_FEATURES: + case VIRTIO_MMIO_DRIVER_FEATURES_SEL: + case VIRTIO_MMIO_GUEST_PAGE_SIZE: + case VIRTIO_MMIO_QUEUE_SEL: + case VIRTIO_MMIO_QUEUE_NUM: + case VIRTIO_MMIO_QUEUE_ALIGN: + case VIRTIO_MMIO_QUEUE_NOTIFY: + case VIRTIO_MMIO_INTERRUPT_ACK: DPRINTF("read of write-only register\n"); return 0; default: @@ -251,18 +230,18 @@ static void virtio_mmio_write(void *opaque, hwaddr offset, uint64_t value, return; } switch (offset) { - case VIRTIO_MMIO_HOSTFEATURESSEL: + case VIRTIO_MMIO_DEVICE_FEATURES_SEL: proxy->host_features_sel = value; break; - case VIRTIO_MMIO_GUESTFEATURES: + case VIRTIO_MMIO_DRIVER_FEATURES: if (!proxy->guest_features_sel) { virtio_set_features(vdev, value); } break; - case VIRTIO_MMIO_GUESTFEATURESSEL: + case VIRTIO_MMIO_DRIVER_FEATURES_SEL: proxy->guest_features_sel = value; break; - case VIRTIO_MMIO_GUESTPAGESIZE: + case VIRTIO_MMIO_GUEST_PAGE_SIZE: proxy->guest_page_shift = ctz32(value); if (proxy->guest_page_shift > 31) { proxy->guest_page_shift = 0; @@ -270,22 +249,22 @@ static void virtio_mmio_write(void *opaque, hwaddr offset, uint64_t value, DPRINTF("guest page size %" PRIx64 " shift %d\n", value, proxy->guest_page_shift); break; - case VIRTIO_MMIO_QUEUESEL: + case VIRTIO_MMIO_QUEUE_SEL: if (value < VIRTIO_QUEUE_MAX) { vdev->queue_sel = value; } break; - case VIRTIO_MMIO_QUEUENUM: + case VIRTIO_MMIO_QUEUE_NUM: DPRINTF("mmio_queue write %d max %d\n", (int)value, VIRTQUEUE_MAX_SIZE); virtio_queue_set_num(vdev, vdev->queue_sel, value); /* Note: only call this function for legacy devices */ virtio_queue_update_rings(vdev, vdev->queue_sel); break; - case VIRTIO_MMIO_QUEUEALIGN: + case VIRTIO_MMIO_QUEUE_ALIGN: /* Note: this is only valid for legacy devices */ virtio_queue_set_align(vdev, vdev->queue_sel, value); break; - case VIRTIO_MMIO_QUEUEPFN: + case VIRTIO_MMIO_QUEUE_PFN: if (value == 0) { virtio_reset(vdev); } else { @@ -293,12 +272,12 @@ static void virtio_mmio_write(void *opaque, hwaddr offset, uint64_t value, value << proxy->guest_page_shift); } break; - case VIRTIO_MMIO_QUEUENOTIFY: + case VIRTIO_MMIO_QUEUE_NOTIFY: if (value < VIRTIO_QUEUE_MAX) { virtio_queue_notify(vdev, value); } break; - case VIRTIO_MMIO_INTERRUPTACK: + case VIRTIO_MMIO_INTERRUPT_ACK: atomic_and(&vdev->isr, ~value); virtio_update_irq(vdev); break; @@ -317,13 +296,13 @@ static void virtio_mmio_write(void *opaque, hwaddr offset, uint64_t value, virtio_reset(vdev); } break; - case VIRTIO_MMIO_MAGIC: + case VIRTIO_MMIO_MAGIC_VALUE: case VIRTIO_MMIO_VERSION: - case VIRTIO_MMIO_DEVICEID: - case VIRTIO_MMIO_VENDORID: - case VIRTIO_MMIO_HOSTFEATURES: - case VIRTIO_MMIO_QUEUENUMMAX: - case VIRTIO_MMIO_INTERRUPTSTATUS: + case VIRTIO_MMIO_DEVICE_ID: + case VIRTIO_MMIO_VENDOR_ID: + case VIRTIO_MMIO_DEVICE_FEATURES: + case VIRTIO_MMIO_QUEUE_NUM_MAX: + case VIRTIO_MMIO_INTERRUPT_STATUS: DPRINTF("write to readonly register\n"); break; @@ -402,7 +381,7 @@ static int virtio_mmio_set_guest_notifier(DeviceState *d, int n, bool assign, event_notifier_cleanup(notifier); } - if (vdc->guest_notifier_mask) { + if (vdc->guest_notifier_mask && vdev->use_guest_notifier_mask) { vdc->guest_notifier_mask(vdev, n, !assign); } diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index 21c2b9dbfc..b5af2a00f3 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -108,7 +108,8 @@ static bool virtio_pci_has_extra_state(DeviceState *d) return proxy->flags & VIRTIO_PCI_FLAG_MIGRATE_EXTRA; } -static int get_virtio_pci_modern_state(QEMUFile *f, void *pv, size_t size) +static int get_virtio_pci_modern_state(QEMUFile *f, void *pv, size_t size, + VMStateField *field) { VirtIOPCIProxy *proxy = pv; int i; @@ -137,7 +138,8 @@ static void virtio_pci_save_modern_queue_state(VirtIOPCIQueue *vq, qemu_put_be32(f, vq->used[1]); } -static void put_virtio_pci_modern_state(QEMUFile *f, void *pv, size_t size) +static int put_virtio_pci_modern_state(QEMUFile *f, void *pv, size_t size, + VMStateField *field, QJSON *vmdesc) { VirtIOPCIProxy *proxy = pv; int i; @@ -149,6 +151,8 @@ static void put_virtio_pci_modern_state(QEMUFile *f, void *pv, size_t size) for (i = 0; i < VIRTIO_QUEUE_MAX; i++) { virtio_pci_save_modern_queue_state(&proxy->vqs[i], f); } + + return 0; } static const VMStateInfo vmstate_info_virtio_pci_modern_state = { @@ -1144,6 +1148,14 @@ static int virtio_pci_query_nvectors(DeviceState *d) return proxy->nvectors; } +static AddressSpace *virtio_pci_get_dma_as(DeviceState *d) +{ + VirtIOPCIProxy *proxy = VIRTIO_PCI(d); + PCIDevice *dev = &proxy->pci_dev; + + return pci_get_address_space(dev); +} + static int virtio_pci_add_mem_cap(VirtIOPCIProxy *proxy, struct virtio_pci_cap *cap) { @@ -1308,7 +1320,6 @@ static void virtio_pci_common_write(void *opaque, hwaddr addr, virtio_queue_set_vector(vdev, vdev->queue_sel, val); break; case VIRTIO_PCI_COMMON_Q_ENABLE: - /* TODO: need a way to put num back on reset. */ virtio_queue_set_num(vdev, vdev->queue_sel, proxy->vqs[vdev->queue_sel].num); virtio_queue_set_rings(vdev, vdev->queue_sel, @@ -1601,6 +1612,11 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp) } if (legacy) { + if (virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM)) { + error_setg(errp, "VIRTIO_F_IOMMU_PLATFORM was supported by" + "neither legacy nor transitional device."); + return ; + } /* legacy and transitional */ pci_set_word(config + PCI_SUBSYSTEM_VENDOR_ID, pci_get_word(config + PCI_VENDOR_ID)); @@ -1802,6 +1818,11 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp) * PCI Power Management Interface Specification. */ pci_set_word(pci_dev->config + pos + PCI_PM_PMC, 0x3); + + if (proxy->flags & VIRTIO_PCI_FLAG_ATS) { + pcie_ats_init(pci_dev, 256); + } + } else { /* * make future invocations of pci_is_express() return false @@ -1855,6 +1876,8 @@ static Property virtio_pci_properties[] = { VIRTIO_PCI_FLAG_PAGE_PER_VQ_BIT, false), DEFINE_PROP_BOOL("x-ignore-backend-features", VirtIOPCIProxy, ignore_backend_features, false), + DEFINE_PROP_BIT("ats", VirtIOPCIProxy, flags, + VIRTIO_PCI_FLAG_ATS_BIT, false), DEFINE_PROP_END_OF_LIST(), }; @@ -2258,7 +2281,7 @@ static const TypeInfo virtio_serial_pci_info = { static Property virtio_net_properties[] = { DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, - VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, false), + VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true), DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 3), DEFINE_PROP_END_OF_LIST(), }; @@ -2520,6 +2543,7 @@ static void virtio_pci_bus_class_init(ObjectClass *klass, void *data) k->query_nvectors = virtio_pci_query_nvectors; k->ioeventfd_enabled = virtio_pci_ioeventfd_enabled; k->ioeventfd_assign = virtio_pci_ioeventfd_assign; + k->get_dma_as = virtio_pci_get_dma_as; } static const TypeInfo virtio_pci_bus_info = { diff --git a/hw/virtio/virtio-pci.h b/hw/virtio/virtio-pci.h index 5e078866c4..d00064cc0c 100644 --- a/hw/virtio/virtio-pci.h +++ b/hw/virtio/virtio-pci.h @@ -72,6 +72,7 @@ enum { VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT, VIRTIO_PCI_FLAG_DISABLE_PCIE_BIT, VIRTIO_PCI_FLAG_PAGE_PER_VQ_BIT, + VIRTIO_PCI_FLAG_ATS_BIT, }; /* Need to activate work-arounds for buggy guests at vmstate load. */ @@ -96,6 +97,9 @@ enum { #define VIRTIO_PCI_FLAG_PAGE_PER_VQ \ (1 << VIRTIO_PCI_FLAG_PAGE_PER_VQ_BIT) +/* address space translation service */ +#define VIRTIO_PCI_FLAG_ATS (1 << VIRTIO_PCI_FLAG_ATS_BIT) + typedef struct { MSIMessage msg; int virq; diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 1af2de2714..f292a53940 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -23,6 +23,7 @@ #include "hw/virtio/virtio-bus.h" #include "migration/migration.h" #include "hw/virtio/virtio-access.h" +#include "sysemu/dma.h" /* * The alignment to use between consumer and producer parts of vring. @@ -92,7 +93,7 @@ struct VirtQueue uint16_t queue_index; - int inuse; + unsigned int inuse; uint16_t vector; VirtIOHandleOutput handle_output; @@ -121,7 +122,7 @@ void virtio_queue_update_rings(VirtIODevice *vdev, int n) static void vring_desc_read(VirtIODevice *vdev, VRingDesc *desc, hwaddr desc_pa, int i) { - address_space_read(&address_space_memory, desc_pa + i * sizeof(VRingDesc), + address_space_read(vdev->dma_as, desc_pa + i * sizeof(VRingDesc), MEMTXATTRS_UNSPECIFIED, (void *)desc, sizeof(VRingDesc)); virtio_tswap64s(vdev, &desc->addr); virtio_tswap32s(vdev, &desc->len); @@ -163,7 +164,7 @@ static inline void vring_used_write(VirtQueue *vq, VRingUsedElem *uelem, virtio_tswap32s(vq->vdev, &uelem->id); virtio_tswap32s(vq->vdev, &uelem->len); pa = vq->vring.used + offsetof(VRingUsed, ring[i]); - address_space_write(&address_space_memory, pa, MEMTXATTRS_UNSPECIFIED, + address_space_write(vq->vdev->dma_as, pa, MEMTXATTRS_UNSPECIFIED, (void *)uelem, sizeof(VRingUsedElem)); } @@ -243,6 +244,7 @@ int virtio_queue_empty(VirtQueue *vq) static void virtqueue_unmap_sg(VirtQueue *vq, const VirtQueueElement *elem, unsigned int len) { + AddressSpace *dma_as = vq->vdev->dma_as; unsigned int offset; int i; @@ -250,17 +252,18 @@ static void virtqueue_unmap_sg(VirtQueue *vq, const VirtQueueElement *elem, for (i = 0; i < elem->in_num; i++) { size_t size = MIN(len - offset, elem->in_sg[i].iov_len); - cpu_physical_memory_unmap(elem->in_sg[i].iov_base, - elem->in_sg[i].iov_len, - 1, size); + dma_memory_unmap(dma_as, elem->in_sg[i].iov_base, + elem->in_sg[i].iov_len, + DMA_DIRECTION_FROM_DEVICE, size); offset += size; } for (i = 0; i < elem->out_num; i++) - cpu_physical_memory_unmap(elem->out_sg[i].iov_base, - elem->out_sg[i].iov_len, - 0, elem->out_sg[i].iov_len); + dma_memory_unmap(dma_as, elem->out_sg[i].iov_base, + elem->out_sg[i].iov_len, + DMA_DIRECTION_TO_DEVICE, + elem->out_sg[i].iov_len); } /* virtqueue_detach_element: @@ -554,7 +557,10 @@ static bool virtqueue_map_desc(VirtIODevice *vdev, unsigned int *p_num_sg, goto out; } - iov[num_sg].iov_base = cpu_physical_memory_map(pa, &len, is_write); + iov[num_sg].iov_base = dma_memory_map(vdev->dma_as, pa, &len, + is_write ? + DMA_DIRECTION_FROM_DEVICE : + DMA_DIRECTION_TO_DEVICE); if (!iov[num_sg].iov_base) { virtio_error(vdev, "virtio: bogus descriptor or out of resources"); goto out; @@ -591,28 +597,19 @@ static void virtqueue_undo_map_desc(unsigned int out_num, unsigned int in_num, } } -static void virtqueue_map_iovec(struct iovec *sg, hwaddr *addr, - unsigned int *num_sg, unsigned int max_size, +static void virtqueue_map_iovec(VirtIODevice *vdev, struct iovec *sg, + hwaddr *addr, unsigned int *num_sg, int is_write) { unsigned int i; hwaddr len; - /* Note: this function MUST validate input, some callers - * are passing in num_sg values received over the network. - */ - /* TODO: teach all callers that this can fail, and return failure instead - * of asserting here. - * When we do, we might be able to re-enable NDEBUG below. - */ -#ifdef NDEBUG -#error building with NDEBUG is not supported -#endif - assert(*num_sg <= max_size); - for (i = 0; i < *num_sg; i++) { len = sg[i].iov_len; - sg[i].iov_base = cpu_physical_memory_map(addr[i], &len, is_write); + sg[i].iov_base = dma_memory_map(vdev->dma_as, + addr[i], &len, is_write ? + DMA_DIRECTION_FROM_DEVICE : + DMA_DIRECTION_TO_DEVICE); if (!sg[i].iov_base) { error_report("virtio: error trying to map MMIO memory"); exit(1); @@ -624,12 +621,10 @@ static void virtqueue_map_iovec(struct iovec *sg, hwaddr *addr, } } -void virtqueue_map(VirtQueueElement *elem) +void virtqueue_map(VirtIODevice *vdev, VirtQueueElement *elem) { - virtqueue_map_iovec(elem->in_sg, elem->in_addr, &elem->in_num, - VIRTQUEUE_MAX_SIZE, 1); - virtqueue_map_iovec(elem->out_sg, elem->out_addr, &elem->out_num, - VIRTQUEUE_MAX_SIZE, 0); + virtqueue_map_iovec(vdev, elem->in_sg, elem->in_addr, &elem->in_num, 1); + virtqueue_map_iovec(vdev, elem->out_sg, elem->out_addr, &elem->out_num, 0); } static void *virtqueue_alloc_element(size_t sz, unsigned out_num, unsigned in_num) @@ -765,6 +760,44 @@ err_undo_map: return NULL; } +/* virtqueue_drop_all: + * @vq: The #VirtQueue + * Drops all queued buffers and indicates them to the guest + * as if they are done. Useful when buffers can not be + * processed but must be returned to the guest. + */ +unsigned int virtqueue_drop_all(VirtQueue *vq) +{ + unsigned int dropped = 0; + VirtQueueElement elem = {}; + VirtIODevice *vdev = vq->vdev; + bool fEventIdx = virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); + + if (unlikely(vdev->broken)) { + return 0; + } + + while (!virtio_queue_empty(vq) && vq->inuse < vq->vring.num) { + /* works similar to virtqueue_pop but does not map buffers + * and does not allocate any memory */ + smp_rmb(); + if (!virtqueue_get_head(vq, vq->last_avail_idx, &elem.index)) { + break; + } + vq->inuse++; + vq->last_avail_idx++; + if (fEventIdx) { + vring_set_avail_event(vq, vq->last_avail_idx); + } + /* immediately push the element, nothing to unmap + * as both in_num and out_num are set to 0 */ + virtqueue_push(vq, &elem, 0); + dropped++; + } + + return dropped; +} + /* Reading and writing a structure directly to QEMUFile is *awful*, but * it is what QEMU has always done by mistake. We can change it sooner * or later by bumping the version number of the affected vm states. @@ -782,7 +815,7 @@ typedef struct VirtQueueElementOld { struct iovec out_sg[VIRTQUEUE_MAX_SIZE]; } VirtQueueElementOld; -void *qemu_get_virtqueue_element(QEMUFile *f, size_t sz) +void *qemu_get_virtqueue_element(VirtIODevice *vdev, QEMUFile *f, size_t sz) { VirtQueueElement *elem; VirtQueueElementOld data; @@ -790,6 +823,16 @@ void *qemu_get_virtqueue_element(QEMUFile *f, size_t sz) qemu_get_buffer(f, (uint8_t *)&data, sizeof(VirtQueueElementOld)); + /* TODO: teach all callers that this can fail, and return failure instead + * of asserting here. + * When we do, we might be able to re-enable NDEBUG below. + */ +#ifdef NDEBUG +#error building with NDEBUG is not supported +#endif + assert(ARRAY_SIZE(data.in_addr) >= data.in_num); + assert(ARRAY_SIZE(data.out_addr) >= data.out_num); + elem = virtqueue_alloc_element(sz, data.out_num, data.in_num); elem->index = data.index; @@ -813,7 +856,7 @@ void *qemu_get_virtqueue_element(QEMUFile *f, size_t sz) elem->out_sg[i].iov_len = data.out_sg[i].iov_len; } - virtqueue_map(elem); + virtqueue_map(vdev, elem); return elem; } @@ -872,6 +915,11 @@ static int virtio_validate_features(VirtIODevice *vdev) { VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); + if (virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM) && + !virtio_vdev_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM)) { + return -EFAULT; + } + if (k->validate_features) { return k->validate_features(vdev); } else { @@ -1201,6 +1249,11 @@ int virtio_queue_get_num(VirtIODevice *vdev, int n) return vdev->vq[n].vring.num; } +int virtio_queue_get_max_num(VirtIODevice *vdev, int n) +{ + return vdev->vq[n].vring.num_default; +} + int virtio_get_num_queues(VirtIODevice *vdev) { int i; @@ -1502,7 +1555,8 @@ static const VMStateDescription vmstate_virtio_ringsize = { } }; -static int get_extra_state(QEMUFile *f, void *pv, size_t size) +static int get_extra_state(QEMUFile *f, void *pv, size_t size, + VMStateField *field) { VirtIODevice *vdev = pv; BusState *qbus = qdev_get_parent_bus(DEVICE(vdev)); @@ -1515,13 +1569,15 @@ static int get_extra_state(QEMUFile *f, void *pv, size_t size) } } -static void put_extra_state(QEMUFile *f, void *pv, size_t size) +static int put_extra_state(QEMUFile *f, void *pv, size_t size, + VMStateField *field, QJSON *vmdesc) { VirtIODevice *vdev = pv; BusState *qbus = qdev_get_parent_bus(DEVICE(vdev)); VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); k->save_extra_state(qbus->parent, f); + return 0; } static const VMStateInfo vmstate_info_extra_state = { @@ -1656,13 +1712,17 @@ void virtio_save(VirtIODevice *vdev, QEMUFile *f) } /* A wrapper for use as a VMState .put function */ -static void virtio_device_put(QEMUFile *f, void *opaque, size_t size) +static int virtio_device_put(QEMUFile *f, void *opaque, size_t size, + VMStateField *field, QJSON *vmdesc) { virtio_save(VIRTIO_DEVICE(opaque), f); + + return 0; } /* A wrapper for use as a VMState .get function */ -static int virtio_device_get(QEMUFile *f, void *opaque, size_t size) +static int virtio_device_get(QEMUFile *f, void *opaque, size_t size, + VMStateField *field) { VirtIODevice *vdev = VIRTIO_DEVICE(opaque); DeviceClass *dc = DEVICE_CLASS(VIRTIO_DEVICE_GET_CLASS(vdev)); @@ -1855,9 +1915,11 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id) /* * Some devices migrate VirtQueueElements that have been popped * from the avail ring but not yet returned to the used ring. + * Since max ring size < UINT16_MAX it's safe to use modulo + * UINT16_MAX + 1 subtraction. */ - vdev->vq[i].inuse = vdev->vq[i].last_avail_idx - - vdev->vq[i].used_idx; + vdev->vq[i].inuse = (uint16_t)(vdev->vq[i].last_avail_idx - + vdev->vq[i].used_idx); if (vdev->vq[i].inuse > vdev->vq[i].vring.num) { error_report("VQ %d size 0x%x < last_avail_idx 0x%x - " "used_idx 0x%x", @@ -1995,6 +2057,11 @@ void virtio_queue_set_last_avail_idx(VirtIODevice *vdev, int n, uint16_t idx) vdev->vq[n].shadow_avail_idx = idx; } +void virtio_queue_update_used_idx(VirtIODevice *vdev, int n) +{ + vdev->vq[n].used_idx = vring_used_idx(&vdev->vq[n]); +} + void virtio_queue_invalidate_signalled_used(VirtIODevice *vdev, int n) { vdev->vq[n].signalled_used_valid = false; @@ -2022,10 +2089,10 @@ void virtio_queue_set_guest_notifier_fd_handler(VirtQueue *vq, bool assign, bool with_irqfd) { if (assign && !with_irqfd) { - event_notifier_set_handler(&vq->guest_notifier, false, + event_notifier_set_handler(&vq->guest_notifier, virtio_queue_guest_notifier_read); } else { - event_notifier_set_handler(&vq->guest_notifier, false, NULL); + event_notifier_set_handler(&vq->guest_notifier, NULL); } if (!assign) { /* Test and clear notifier before closing it, @@ -2047,15 +2114,50 @@ static void virtio_queue_host_notifier_aio_read(EventNotifier *n) } } +static void virtio_queue_host_notifier_aio_poll_begin(EventNotifier *n) +{ + VirtQueue *vq = container_of(n, VirtQueue, host_notifier); + + virtio_queue_set_notification(vq, 0); +} + +static bool virtio_queue_host_notifier_aio_poll(void *opaque) +{ + EventNotifier *n = opaque; + VirtQueue *vq = container_of(n, VirtQueue, host_notifier); + + if (virtio_queue_empty(vq)) { + return false; + } + + virtio_queue_notify_aio_vq(vq); + + /* In case the handler function re-enabled notifications */ + virtio_queue_set_notification(vq, 0); + return true; +} + +static void virtio_queue_host_notifier_aio_poll_end(EventNotifier *n) +{ + VirtQueue *vq = container_of(n, VirtQueue, host_notifier); + + /* Caller polls once more after this to catch requests that race with us */ + virtio_queue_set_notification(vq, 1); +} + void virtio_queue_aio_set_host_notifier_handler(VirtQueue *vq, AioContext *ctx, VirtIOHandleOutput handle_output) { if (handle_output) { vq->handle_aio_output = handle_output; aio_set_event_notifier(ctx, &vq->host_notifier, true, - virtio_queue_host_notifier_aio_read); + virtio_queue_host_notifier_aio_read, + virtio_queue_host_notifier_aio_poll); + aio_set_event_notifier_poll(ctx, &vq->host_notifier, + virtio_queue_host_notifier_aio_poll_begin, + virtio_queue_host_notifier_aio_poll_end); } else { - aio_set_event_notifier(ctx, &vq->host_notifier, true, NULL); + aio_set_event_notifier(ctx, &vq->host_notifier, true, NULL, NULL); /* Test and clear notifier before after disabling event, * in case poll callback didn't have time to run. */ virtio_queue_host_notifier_aio_read(&vq->host_notifier); @@ -2162,7 +2264,7 @@ static int virtio_device_start_ioeventfd_impl(VirtIODevice *vdev) err = r; goto assign_error; } - event_notifier_set_handler(&vq->host_notifier, true, + event_notifier_set_handler(&vq->host_notifier, virtio_queue_host_notifier_read); } @@ -2183,7 +2285,7 @@ assign_error: continue; } - event_notifier_set_handler(&vq->host_notifier, true, NULL); + event_notifier_set_handler(&vq->host_notifier, NULL); r = virtio_bus_set_host_notifier(qbus, n, false); assert(r >= 0); } @@ -2209,7 +2311,7 @@ static void virtio_device_stop_ioeventfd_impl(VirtIODevice *vdev) if (!virtio_queue_get_num(vdev, n)) { continue; } - event_notifier_set_handler(&vq->host_notifier, true, NULL); + event_notifier_set_handler(&vq->host_notifier, NULL); r = virtio_bus_set_host_notifier(qbus, n, false); assert(r >= 0); } |
