From 0ea2730bef0b764ce87f5d6859f9b1eac6069250 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Mon, 8 Jun 2015 09:25:25 -0600 Subject: hw/vfio/platform: vfio-platform skeleton Minimal VFIO platform implementation supporting register space user mapping but not IRQ assignment. Signed-off-by: Kim Phillips Signed-off-by: Eric Auger Tested-by: Vikram Sethi Signed-off-by: Alex Williamson --- hw/vfio/Makefile.objs | 1 + hw/vfio/platform.c | 287 ++++++++++++++++++++++++++++++++++++++++ include/hw/vfio/vfio-common.h | 1 + include/hw/vfio/vfio-platform.h | 44 ++++++ trace-events | 5 + 5 files changed, 338 insertions(+) create mode 100644 hw/vfio/platform.c create mode 100644 include/hw/vfio/vfio-platform.h diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs index e31f30e..c5c76fe 100644 --- a/hw/vfio/Makefile.objs +++ b/hw/vfio/Makefile.objs @@ -1,4 +1,5 @@ ifeq ($(CONFIG_LINUX), y) obj-$(CONFIG_SOFTMMU) += common.o obj-$(CONFIG_PCI) += pci.o +obj-$(CONFIG_SOFTMMU) += platform.o endif diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c new file mode 100644 index 0000000..569a675 --- /dev/null +++ b/hw/vfio/platform.c @@ -0,0 +1,287 @@ +/* + * vfio based device assignment support - platform devices + * + * Copyright Linaro Limited, 2014 + * + * Authors: + * Kim Phillips + * Eric Auger + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Based on vfio based PCI device assignment support: + * Copyright Red Hat, Inc. 2012 + */ + +#include +#include + +#include "hw/vfio/vfio-platform.h" +#include "qemu/error-report.h" +#include "qemu/range.h" +#include "sysemu/sysemu.h" +#include "exec/memory.h" +#include "hw/sysbus.h" +#include "trace.h" +#include "hw/platform-bus.h" + +/* VFIO skeleton */ + +static void vfio_platform_compute_needs_reset(VFIODevice *vbasedev) +{ + vbasedev->needs_reset = true; +} + +/* not implemented yet */ +static int vfio_platform_hot_reset_multi(VFIODevice *vbasedev) +{ + return -1; +} + +/** + * vfio_populate_device - Allocate and populate MMIO region + * structs according to driver returned information + * @vbasedev: the VFIO device handle + * + */ +static int vfio_populate_device(VFIODevice *vbasedev) +{ + int i, ret = -1; + VFIOPlatformDevice *vdev = + container_of(vbasedev, VFIOPlatformDevice, vbasedev); + + if (!(vbasedev->flags & VFIO_DEVICE_FLAGS_PLATFORM)) { + error_report("vfio: Um, this isn't a platform device"); + return ret; + } + + vdev->regions = g_malloc0_n(vbasedev->num_regions, + sizeof(VFIORegion *)); + + for (i = 0; i < vbasedev->num_regions; i++) { + struct vfio_region_info reg_info = { .argsz = sizeof(reg_info) }; + VFIORegion *ptr; + + vdev->regions[i] = g_malloc0(sizeof(VFIORegion)); + ptr = vdev->regions[i]; + reg_info.index = i; + ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, ®_info); + if (ret) { + error_report("vfio: Error getting region %d info: %m", i); + goto reg_error; + } + ptr->flags = reg_info.flags; + ptr->size = reg_info.size; + ptr->fd_offset = reg_info.offset; + ptr->nr = i; + ptr->vbasedev = vbasedev; + + trace_vfio_platform_populate_regions(ptr->nr, + (unsigned long)ptr->flags, + (unsigned long)ptr->size, + ptr->vbasedev->fd, + (unsigned long)ptr->fd_offset); + } + + return 0; +reg_error: + for (i = 0; i < vbasedev->num_regions; i++) { + g_free(vdev->regions[i]); + } + g_free(vdev->regions); + return ret; +} + +/* specialized functions for VFIO Platform devices */ +static VFIODeviceOps vfio_platform_ops = { + .vfio_compute_needs_reset = vfio_platform_compute_needs_reset, + .vfio_hot_reset_multi = vfio_platform_hot_reset_multi, +}; + +/** + * vfio_base_device_init - perform preliminary VFIO setup + * @vbasedev: the VFIO device handle + * + * Implement the VFIO command sequence that allows to discover + * assigned device resources: group extraction, device + * fd retrieval, resource query. + * Precondition: the device name must be initialized + */ +static int vfio_base_device_init(VFIODevice *vbasedev) +{ + VFIOGroup *group; + VFIODevice *vbasedev_iter; + char path[PATH_MAX], iommu_group_path[PATH_MAX], *group_name; + ssize_t len; + struct stat st; + int groupid; + int ret; + + /* name must be set prior to the call */ + if (!vbasedev->name || strchr(vbasedev->name, '/')) { + return -EINVAL; + } + + /* Check that the host device exists */ + g_snprintf(path, sizeof(path), "/sys/bus/platform/devices/%s/", + vbasedev->name); + + if (stat(path, &st) < 0) { + error_report("vfio: error: no such host device: %s", path); + return -errno; + } + + g_strlcat(path, "iommu_group", sizeof(path)); + len = readlink(path, iommu_group_path, sizeof(iommu_group_path)); + if (len < 0 || len >= sizeof(iommu_group_path)) { + error_report("vfio: error no iommu_group for device"); + return len < 0 ? -errno : -ENAMETOOLONG; + } + + iommu_group_path[len] = 0; + group_name = basename(iommu_group_path); + + if (sscanf(group_name, "%d", &groupid) != 1) { + error_report("vfio: error reading %s: %m", path); + return -errno; + } + + trace_vfio_platform_base_device_init(vbasedev->name, groupid); + + group = vfio_get_group(groupid, &address_space_memory); + if (!group) { + error_report("vfio: failed to get group %d", groupid); + return -ENOENT; + } + + g_snprintf(path, sizeof(path), "%s", vbasedev->name); + + QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { + if (strcmp(vbasedev_iter->name, vbasedev->name) == 0) { + error_report("vfio: error: device %s is already attached", path); + vfio_put_group(group); + return -EBUSY; + } + } + ret = vfio_get_device(group, path, vbasedev); + if (ret) { + error_report("vfio: failed to get device %s", path); + vfio_put_group(group); + return ret; + } + + ret = vfio_populate_device(vbasedev); + if (ret) { + error_report("vfio: failed to populate device %s", path); + vfio_put_group(group); + } + + return ret; +} + +/** + * vfio_map_region - initialize the 2 memory regions for a given + * MMIO region index + * @vdev: the VFIO platform device handle + * @nr: the index of the region + * + * Init the top memory region and the mmapped memory region beneath + * VFIOPlatformDevice is used since VFIODevice is not a QOM Object + * and could not be passed to memory region functions +*/ +static void vfio_map_region(VFIOPlatformDevice *vdev, int nr) +{ + VFIORegion *region = vdev->regions[nr]; + uint64_t size = region->size; + char name[64]; + + if (!size) { + return; + } + + g_snprintf(name, sizeof(name), "VFIO %s region %d", + vdev->vbasedev.name, nr); + + /* A "slow" read/write mapping underlies all regions */ + memory_region_init_io(®ion->mem, OBJECT(vdev), &vfio_region_ops, + region, name, size); + + g_strlcat(name, " mmap", sizeof(name)); + + if (vfio_mmap_region(OBJECT(vdev), region, ®ion->mem, + ®ion->mmap_mem, ®ion->mmap, size, 0, name)) { + error_report("%s unsupported. Performance may be slow", name); + } +} + +/** + * vfio_platform_realize - the device realize function + * @dev: device state pointer + * @errp: error + * + * initialize the device, its memory regions and IRQ structures + * IRQ are started separately + */ +static void vfio_platform_realize(DeviceState *dev, Error **errp) +{ + VFIOPlatformDevice *vdev = VFIO_PLATFORM_DEVICE(dev); + SysBusDevice *sbdev = SYS_BUS_DEVICE(dev); + VFIODevice *vbasedev = &vdev->vbasedev; + int i, ret; + + vbasedev->type = VFIO_DEVICE_TYPE_PLATFORM; + vbasedev->ops = &vfio_platform_ops; + + trace_vfio_platform_realize(vbasedev->name, vdev->compat); + + ret = vfio_base_device_init(vbasedev); + if (ret) { + error_setg(errp, "vfio: vfio_base_device_init failed for %s", + vbasedev->name); + return; + } + + for (i = 0; i < vbasedev->num_regions; i++) { + vfio_map_region(vdev, i); + sysbus_init_mmio(sbdev, &vdev->regions[i]->mem); + } +} + +static const VMStateDescription vfio_platform_vmstate = { + .name = TYPE_VFIO_PLATFORM, + .unmigratable = 1, +}; + +static Property vfio_platform_dev_properties[] = { + DEFINE_PROP_STRING("host", VFIOPlatformDevice, vbasedev.name), + DEFINE_PROP_BOOL("x-mmap", VFIOPlatformDevice, vbasedev.allow_mmap, true), + DEFINE_PROP_END_OF_LIST(), +}; + +static void vfio_platform_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = vfio_platform_realize; + dc->props = vfio_platform_dev_properties; + dc->vmsd = &vfio_platform_vmstate; + dc->desc = "VFIO-based platform device assignment"; + set_bit(DEVICE_CATEGORY_MISC, dc->categories); +} + +static const TypeInfo vfio_platform_dev_info = { + .name = TYPE_VFIO_PLATFORM, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(VFIOPlatformDevice), + .class_init = vfio_platform_class_init, + .class_size = sizeof(VFIOPlatformDeviceClass), + .abstract = true, +}; + +static void register_vfio_platform_dev_type(void) +{ + type_register_static(&vfio_platform_dev_info); +} + +type_init(register_vfio_platform_dev_type) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 0d1fb80..59a321d 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -42,6 +42,7 @@ enum { VFIO_DEVICE_TYPE_PCI = 0, + VFIO_DEVICE_TYPE_PLATFORM = 1, }; typedef struct VFIORegion { diff --git a/include/hw/vfio/vfio-platform.h b/include/hw/vfio/vfio-platform.h new file mode 100644 index 0000000..338f0c6 --- /dev/null +++ b/include/hw/vfio/vfio-platform.h @@ -0,0 +1,44 @@ +/* + * vfio based device assignment support - platform devices + * + * Copyright Linaro Limited, 2014 + * + * Authors: + * Kim Phillips + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Based on vfio based PCI device assignment support: + * Copyright Red Hat, Inc. 2012 + */ + +#ifndef HW_VFIO_VFIO_PLATFORM_H +#define HW_VFIO_VFIO_PLATFORM_H + +#include "hw/sysbus.h" +#include "hw/vfio/vfio-common.h" + +#define TYPE_VFIO_PLATFORM "vfio-platform" + +typedef struct VFIOPlatformDevice { + SysBusDevice sbdev; + VFIODevice vbasedev; /* not a QOM object */ + VFIORegion **regions; + char *compat; /* compatibility string */ +} VFIOPlatformDevice; + +typedef struct VFIOPlatformDeviceClass { + /*< private >*/ + SysBusDeviceClass parent_class; + /*< public >*/ +} VFIOPlatformDeviceClass; + +#define VFIO_PLATFORM_DEVICE(obj) \ + OBJECT_CHECK(VFIOPlatformDevice, (obj), TYPE_VFIO_PLATFORM) +#define VFIO_PLATFORM_DEVICE_CLASS(klass) \ + OBJECT_CLASS_CHECK(VFIOPlatformDeviceClass, (klass), TYPE_VFIO_PLATFORM) +#define VFIO_PLATFORM_DEVICE_GET_CLASS(obj) \ + OBJECT_GET_CLASS(VFIOPlatformDeviceClass, (obj), TYPE_VFIO_PLATFORM) + +#endif /*HW_VFIO_VFIO_PLATFORM_H*/ diff --git a/trace-events b/trace-events index a589650..e1a34ec 100644 --- a/trace-events +++ b/trace-events @@ -1564,6 +1564,11 @@ vfio_put_group(int fd) "close group->fd=%d" vfio_get_device(const char * name, unsigned int flags, unsigned int num_regions, unsigned int num_irqs) "Device %s flags: %u, regions: %u, irqs: %u" vfio_put_base_device(int fd) "close vdev->fd=%d" +# hw/vfio/platform.c +vfio_platform_populate_regions(int region_index, unsigned long flag, unsigned long size, int fd, unsigned long offset) "- region %d flags = 0x%lx, size = 0x%lx, fd= %d, offset = 0x%lx" +vfio_platform_base_device_init(char *name, int groupid) "%s belongs to group #%d" +vfio_platform_realize(char *name, char *compat) "vfio device %s, compat = %s" + #hw/acpi/memory_hotplug.c mhp_acpi_invalid_slot_selected(uint32_t slot) "0x%"PRIx32 mhp_acpi_ejecting_invalid_slot(uint32_t slot) "0x%"PRIx32 -- cgit v1.1 From 38559979bf0095a586f61bc9e028df36673f21a1 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Mon, 8 Jun 2015 09:25:26 -0600 Subject: hw/vfio/platform: add irq assignment This patch adds the code requested to assign interrupts to a guest. The interrupts are mediated through user handled eventfds only. Signed-off-by: Eric Auger Tested-by: Vikram Sethi Signed-off-by: Alex Williamson --- hw/vfio/platform.c | 331 +++++++++++++++++++++++++++++++++++++++- include/hw/vfio/vfio-platform.h | 31 ++++ trace-events | 7 + 3 files changed, 368 insertions(+), 1 deletion(-) diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c index 569a675..35266a8 100644 --- a/hw/vfio/platform.c +++ b/hw/vfio/platform.c @@ -22,10 +22,299 @@ #include "qemu/range.h" #include "sysemu/sysemu.h" #include "exec/memory.h" +#include "qemu/queue.h" #include "hw/sysbus.h" #include "trace.h" #include "hw/platform-bus.h" +/* + * Functions used whatever the injection method + */ + +/** + * vfio_init_intp - allocate, initialize the IRQ struct pointer + * and add it into the list of IRQs + * @vbasedev: the VFIO device handle + * @info: irq info struct retrieved from VFIO driver + */ +static VFIOINTp *vfio_init_intp(VFIODevice *vbasedev, + struct vfio_irq_info info) +{ + int ret; + VFIOPlatformDevice *vdev = + container_of(vbasedev, VFIOPlatformDevice, vbasedev); + SysBusDevice *sbdev = SYS_BUS_DEVICE(vdev); + VFIOINTp *intp; + + intp = g_malloc0(sizeof(*intp)); + intp->vdev = vdev; + intp->pin = info.index; + intp->flags = info.flags; + intp->state = VFIO_IRQ_INACTIVE; + + sysbus_init_irq(sbdev, &intp->qemuirq); + + /* Get an eventfd for trigger */ + ret = event_notifier_init(&intp->interrupt, 0); + if (ret) { + g_free(intp); + error_report("vfio: Error: trigger event_notifier_init failed "); + return NULL; + } + + QLIST_INSERT_HEAD(&vdev->intp_list, intp, next); + return intp; +} + +/** + * vfio_set_trigger_eventfd - set VFIO eventfd handling + * + * @intp: IRQ struct handle + * @handler: handler to be called on eventfd signaling + * + * Setup VFIO signaling and attach an optional user-side handler + * to the eventfd + */ +static int vfio_set_trigger_eventfd(VFIOINTp *intp, + eventfd_user_side_handler_t handler) +{ + VFIODevice *vbasedev = &intp->vdev->vbasedev; + struct vfio_irq_set *irq_set; + int argsz, ret; + int32_t *pfd; + + argsz = sizeof(*irq_set) + sizeof(*pfd); + irq_set = g_malloc0(argsz); + irq_set->argsz = argsz; + irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER; + irq_set->index = intp->pin; + irq_set->start = 0; + irq_set->count = 1; + pfd = (int32_t *)&irq_set->data; + *pfd = event_notifier_get_fd(&intp->interrupt); + qemu_set_fd_handler(*pfd, (IOHandler *)handler, NULL, intp); + ret = ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set); + g_free(irq_set); + if (ret < 0) { + error_report("vfio: Failed to set trigger eventfd: %m"); + qemu_set_fd_handler(*pfd, NULL, NULL, NULL); + } + return ret; +} + +/* + * Functions only used when eventfds are handled on user-side + * ie. without irqfd + */ + +/** + * vfio_mmap_set_enabled - enable/disable the fast path mode + * @vdev: the VFIO platform device + * @enabled: the target mmap state + * + * enabled = true ~ fast path = MMIO region is mmaped (no KVM TRAP); + * enabled = false ~ slow path = MMIO region is trapped and region callbacks + * are called; slow path enables to trap the device IRQ status register reset +*/ + +static void vfio_mmap_set_enabled(VFIOPlatformDevice *vdev, bool enabled) +{ + int i; + + trace_vfio_platform_mmap_set_enabled(enabled); + + for (i = 0; i < vdev->vbasedev.num_regions; i++) { + VFIORegion *region = vdev->regions[i]; + + memory_region_set_enabled(®ion->mmap_mem, enabled); + } +} + +/** + * vfio_intp_mmap_enable - timer function, restores the fast path + * if there is no more active IRQ + * @opaque: actually points to the VFIO platform device + * + * Called on mmap timer timout, this function checks whether the + * IRQ is still active and if not, restores the fast path. + * by construction a single eventfd is handled at a time. + * if the IRQ is still active, the timer is re-programmed. + */ +static void vfio_intp_mmap_enable(void *opaque) +{ + VFIOINTp *tmp; + VFIOPlatformDevice *vdev = (VFIOPlatformDevice *)opaque; + + qemu_mutex_lock(&vdev->intp_mutex); + QLIST_FOREACH(tmp, &vdev->intp_list, next) { + if (tmp->state == VFIO_IRQ_ACTIVE) { + trace_vfio_platform_intp_mmap_enable(tmp->pin); + /* re-program the timer to check active status later */ + timer_mod(vdev->mmap_timer, + qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + + vdev->mmap_timeout); + qemu_mutex_unlock(&vdev->intp_mutex); + return; + } + } + vfio_mmap_set_enabled(vdev, true); + qemu_mutex_unlock(&vdev->intp_mutex); +} + +/** + * vfio_intp_inject_pending_lockheld - Injects a pending IRQ + * @opaque: opaque pointer, in practice the VFIOINTp handle + * + * The function is called on a previous IRQ completion, from + * vfio_platform_eoi, while the intp_mutex is locked. + * Also in such situation, the slow path already is set and + * the mmap timer was already programmed. + */ +static void vfio_intp_inject_pending_lockheld(VFIOINTp *intp) +{ + trace_vfio_platform_intp_inject_pending_lockheld(intp->pin, + event_notifier_get_fd(&intp->interrupt)); + + intp->state = VFIO_IRQ_ACTIVE; + + /* trigger the virtual IRQ */ + qemu_set_irq(intp->qemuirq, 1); +} + +/** + * vfio_intp_interrupt - The user-side eventfd handler + * @opaque: opaque pointer which in practice is the VFIOINTp handle + * + * the function is entered in event handler context: + * the vIRQ is injected into the guest if there is no other active + * or pending IRQ. + */ +static void vfio_intp_interrupt(VFIOINTp *intp) +{ + int ret; + VFIOINTp *tmp; + VFIOPlatformDevice *vdev = intp->vdev; + bool delay_handling = false; + + qemu_mutex_lock(&vdev->intp_mutex); + if (intp->state == VFIO_IRQ_INACTIVE) { + QLIST_FOREACH(tmp, &vdev->intp_list, next) { + if (tmp->state == VFIO_IRQ_ACTIVE || + tmp->state == VFIO_IRQ_PENDING) { + delay_handling = true; + break; + } + } + } + if (delay_handling) { + /* + * the new IRQ gets a pending status and is pushed in + * the pending queue + */ + intp->state = VFIO_IRQ_PENDING; + trace_vfio_intp_interrupt_set_pending(intp->pin); + QSIMPLEQ_INSERT_TAIL(&vdev->pending_intp_queue, + intp, pqnext); + ret = event_notifier_test_and_clear(&intp->interrupt); + qemu_mutex_unlock(&vdev->intp_mutex); + return; + } + + trace_vfio_platform_intp_interrupt(intp->pin, + event_notifier_get_fd(&intp->interrupt)); + + ret = event_notifier_test_and_clear(&intp->interrupt); + if (!ret) { + error_report("Error when clearing fd=%d (ret = %d)\n", + event_notifier_get_fd(&intp->interrupt), ret); + } + + intp->state = VFIO_IRQ_ACTIVE; + + /* sets slow path */ + vfio_mmap_set_enabled(vdev, false); + + /* trigger the virtual IRQ */ + qemu_set_irq(intp->qemuirq, 1); + + /* + * Schedule the mmap timer which will restore fastpath when no IRQ + * is active anymore + */ + if (vdev->mmap_timeout) { + timer_mod(vdev->mmap_timer, + qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + + vdev->mmap_timeout); + } + qemu_mutex_unlock(&vdev->intp_mutex); +} + +/** + * vfio_platform_eoi - IRQ completion routine + * @vbasedev: the VFIO device handle + * + * De-asserts the active virtual IRQ and unmasks the physical IRQ + * (effective for level sensitive IRQ auto-masked by the VFIO driver). + * Then it handles next pending IRQ if any. + * eoi function is called on the first access to any MMIO region + * after an IRQ was triggered, trapped since slow path was set. + * It is assumed this access corresponds to the IRQ status + * register reset. With such a mechanism, a single IRQ can be + * handled at a time since there is no way to know which IRQ + * was completed by the guest (we would need additional details + * about the IRQ status register mask). + */ +static void vfio_platform_eoi(VFIODevice *vbasedev) +{ + VFIOINTp *intp; + VFIOPlatformDevice *vdev = + container_of(vbasedev, VFIOPlatformDevice, vbasedev); + + qemu_mutex_lock(&vdev->intp_mutex); + QLIST_FOREACH(intp, &vdev->intp_list, next) { + if (intp->state == VFIO_IRQ_ACTIVE) { + trace_vfio_platform_eoi(intp->pin, + event_notifier_get_fd(&intp->interrupt)); + intp->state = VFIO_IRQ_INACTIVE; + + /* deassert the virtual IRQ */ + qemu_set_irq(intp->qemuirq, 0); + + if (intp->flags & VFIO_IRQ_INFO_AUTOMASKED) { + /* unmasks the physical level-sensitive IRQ */ + vfio_unmask_single_irqindex(vbasedev, intp->pin); + } + + /* a single IRQ can be active at a time */ + break; + } + } + /* in case there are pending IRQs, handle the first one */ + if (!QSIMPLEQ_EMPTY(&vdev->pending_intp_queue)) { + intp = QSIMPLEQ_FIRST(&vdev->pending_intp_queue); + vfio_intp_inject_pending_lockheld(intp); + QSIMPLEQ_REMOVE_HEAD(&vdev->pending_intp_queue, pqnext); + } + qemu_mutex_unlock(&vdev->intp_mutex); +} + +/** + * vfio_start_eventfd_injection - starts the virtual IRQ injection using + * user-side handled eventfds + * @intp: the IRQ struct pointer + */ + +static int vfio_start_eventfd_injection(VFIOINTp *intp) +{ + int ret; + + ret = vfio_set_trigger_eventfd(intp, vfio_intp_interrupt); + if (ret) { + error_report("vfio: Error: Failed to pass IRQ fd to the driver: %m"); + } + return ret; +} + /* VFIO skeleton */ static void vfio_platform_compute_needs_reset(VFIODevice *vbasedev) @@ -41,12 +330,13 @@ static int vfio_platform_hot_reset_multi(VFIODevice *vbasedev) /** * vfio_populate_device - Allocate and populate MMIO region - * structs according to driver returned information + * and IRQ structs according to driver returned information * @vbasedev: the VFIO device handle * */ static int vfio_populate_device(VFIODevice *vbasedev) { + VFIOINTp *intp, *tmp; int i, ret = -1; VFIOPlatformDevice *vdev = container_of(vbasedev, VFIOPlatformDevice, vbasedev); @@ -84,7 +374,38 @@ static int vfio_populate_device(VFIODevice *vbasedev) (unsigned long)ptr->fd_offset); } + vdev->mmap_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL, + vfio_intp_mmap_enable, vdev); + + QSIMPLEQ_INIT(&vdev->pending_intp_queue); + + for (i = 0; i < vbasedev->num_irqs; i++) { + struct vfio_irq_info irq = { .argsz = sizeof(irq) }; + + irq.index = i; + ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_IRQ_INFO, &irq); + if (ret) { + error_printf("vfio: error getting device %s irq info", + vbasedev->name); + goto irq_err; + } else { + trace_vfio_platform_populate_interrupts(irq.index, + irq.count, + irq.flags); + intp = vfio_init_intp(vbasedev, irq); + if (!intp) { + error_report("vfio: Error installing IRQ %d up", i); + goto irq_err; + } + } + } return 0; +irq_err: + timer_del(vdev->mmap_timer); + QLIST_FOREACH_SAFE(intp, &vdev->intp_list, next, tmp) { + QLIST_REMOVE(intp, next); + g_free(intp); + } reg_error: for (i = 0; i < vbasedev->num_regions; i++) { g_free(vdev->regions[i]); @@ -97,6 +418,7 @@ reg_error: static VFIODeviceOps vfio_platform_ops = { .vfio_compute_needs_reset = vfio_platform_compute_needs_reset, .vfio_hot_reset_multi = vfio_platform_hot_reset_multi, + .vfio_eoi = vfio_platform_eoi, }; /** @@ -228,6 +550,7 @@ static void vfio_platform_realize(DeviceState *dev, Error **errp) VFIOPlatformDevice *vdev = VFIO_PLATFORM_DEVICE(dev); SysBusDevice *sbdev = SYS_BUS_DEVICE(dev); VFIODevice *vbasedev = &vdev->vbasedev; + VFIOINTp *intp; int i, ret; vbasedev->type = VFIO_DEVICE_TYPE_PLATFORM; @@ -246,6 +569,10 @@ static void vfio_platform_realize(DeviceState *dev, Error **errp) vfio_map_region(vdev, i); sysbus_init_mmio(sbdev, &vdev->regions[i]->mem); } + + QLIST_FOREACH(intp, &vdev->intp_list, next) { + vfio_start_eventfd_injection(intp); + } } static const VMStateDescription vfio_platform_vmstate = { @@ -256,6 +583,8 @@ static const VMStateDescription vfio_platform_vmstate = { static Property vfio_platform_dev_properties[] = { DEFINE_PROP_STRING("host", VFIOPlatformDevice, vbasedev.name), DEFINE_PROP_BOOL("x-mmap", VFIOPlatformDevice, vbasedev.allow_mmap, true), + DEFINE_PROP_UINT32("mmap-timeout-ms", VFIOPlatformDevice, + mmap_timeout, 1100), DEFINE_PROP_END_OF_LIST(), }; diff --git a/include/hw/vfio/vfio-platform.h b/include/hw/vfio/vfio-platform.h index 338f0c6..26b2ad6 100644 --- a/include/hw/vfio/vfio-platform.h +++ b/include/hw/vfio/vfio-platform.h @@ -18,14 +18,45 @@ #include "hw/sysbus.h" #include "hw/vfio/vfio-common.h" +#include "qemu/event_notifier.h" +#include "qemu/queue.h" +#include "hw/irq.h" #define TYPE_VFIO_PLATFORM "vfio-platform" +enum { + VFIO_IRQ_INACTIVE = 0, + VFIO_IRQ_PENDING = 1, + VFIO_IRQ_ACTIVE = 2, + /* VFIO_IRQ_ACTIVE_AND_PENDING cannot happen with VFIO */ +}; + +typedef struct VFIOINTp { + QLIST_ENTRY(VFIOINTp) next; /* entry for IRQ list */ + QSIMPLEQ_ENTRY(VFIOINTp) pqnext; /* entry for pending IRQ queue */ + EventNotifier interrupt; /* eventfd triggered on interrupt */ + EventNotifier unmask; /* eventfd for unmask on QEMU bypass */ + qemu_irq qemuirq; + struct VFIOPlatformDevice *vdev; /* back pointer to device */ + int state; /* inactive, pending, active */ + uint8_t pin; /* index */ + uint32_t flags; /* IRQ info flags */ +} VFIOINTp; + +/* function type for user side eventfd handler */ +typedef void (*eventfd_user_side_handler_t)(VFIOINTp *intp); + typedef struct VFIOPlatformDevice { SysBusDevice sbdev; VFIODevice vbasedev; /* not a QOM object */ VFIORegion **regions; + QLIST_HEAD(, VFIOINTp) intp_list; /* list of IRQs */ + /* queue of pending IRQs */ + QSIMPLEQ_HEAD(pending_intp_queue, VFIOINTp) pending_intp_queue; char *compat; /* compatibility string */ + uint32_t mmap_timeout; /* delay to re-enable mmaps after interrupt */ + QEMUTimer *mmap_timer; /* allows fast-path resume after IRQ hit */ + QemuMutex intp_mutex; /* protect the intp_list IRQ state */ } VFIOPlatformDevice; typedef struct VFIOPlatformDeviceClass { diff --git a/trace-events b/trace-events index e1a34ec..7af9f19 100644 --- a/trace-events +++ b/trace-events @@ -1568,6 +1568,13 @@ vfio_put_base_device(int fd) "close vdev->fd=%d" vfio_platform_populate_regions(int region_index, unsigned long flag, unsigned long size, int fd, unsigned long offset) "- region %d flags = 0x%lx, size = 0x%lx, fd= %d, offset = 0x%lx" vfio_platform_base_device_init(char *name, int groupid) "%s belongs to group #%d" vfio_platform_realize(char *name, char *compat) "vfio device %s, compat = %s" +vfio_platform_eoi(int pin, int fd) "EOI IRQ pin %d (fd=%d)" +vfio_platform_mmap_set_enabled(bool enabled) "fast path = %d" +vfio_platform_intp_mmap_enable(int pin) "IRQ #%d still active, stay in slow path" +vfio_platform_intp_interrupt(int pin, int fd) "Inject IRQ #%d (fd = %d)" +vfio_platform_intp_inject_pending_lockheld(int pin, int fd) "Inject pending IRQ #%d (fd = %d)" +vfio_platform_populate_interrupts(int pin, int count, int flags) "- IRQ index %d: count %d, flags=0x%x" +vfio_intp_interrupt_set_pending(int index) "irq %d is set PENDING" #hw/acpi/memory_hotplug.c mhp_acpi_invalid_slot_selected(uint32_t slot) "0x%"PRIx32 -- cgit v1.1 From 7a8d15d7702444be715b6ae32574659483c0c158 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Tue, 9 Jun 2015 09:00:07 +0100 Subject: hw/vfio/platform: calxeda xgmac device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The platform device class has become abstract. This patch introduces a calxeda xgmac device that derives from it. Signed-off-by: Eric Auger Reviewed-by: Alex BennĂ©e Signed-off-by: Alex Williamson --- hw/vfio/Makefile.objs | 1 + hw/vfio/calxeda-xgmac.c | 55 ++++++++++++++++++++++++++++++++++++ include/hw/vfio/vfio-calxeda-xgmac.h | 46 ++++++++++++++++++++++++++++++ 3 files changed, 102 insertions(+) create mode 100644 hw/vfio/calxeda-xgmac.c create mode 100644 include/hw/vfio/vfio-calxeda-xgmac.h diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs index c5c76fe..d540c9d 100644 --- a/hw/vfio/Makefile.objs +++ b/hw/vfio/Makefile.objs @@ -2,4 +2,5 @@ ifeq ($(CONFIG_LINUX), y) obj-$(CONFIG_SOFTMMU) += common.o obj-$(CONFIG_PCI) += pci.o obj-$(CONFIG_SOFTMMU) += platform.o +obj-$(CONFIG_SOFTMMU) += calxeda-xgmac.o endif diff --git a/hw/vfio/calxeda-xgmac.c b/hw/vfio/calxeda-xgmac.c new file mode 100644 index 0000000..eb914f0 --- /dev/null +++ b/hw/vfio/calxeda-xgmac.c @@ -0,0 +1,55 @@ +/* + * calxeda xgmac VFIO device + * + * Copyright Linaro Limited, 2014 + * + * Authors: + * Eric Auger + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "hw/vfio/vfio-calxeda-xgmac.h" + +static void calxeda_xgmac_realize(DeviceState *dev, Error **errp) +{ + VFIOPlatformDevice *vdev = VFIO_PLATFORM_DEVICE(dev); + VFIOCalxedaXgmacDeviceClass *k = VFIO_CALXEDA_XGMAC_DEVICE_GET_CLASS(dev); + + vdev->compat = g_strdup("calxeda,hb-xgmac"); + + k->parent_realize(dev, errp); +} + +static const VMStateDescription vfio_platform_calxeda_xgmac_vmstate = { + .name = TYPE_VFIO_CALXEDA_XGMAC, + .unmigratable = 1, +}; + +static void vfio_calxeda_xgmac_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VFIOCalxedaXgmacDeviceClass *vcxc = + VFIO_CALXEDA_XGMAC_DEVICE_CLASS(klass); + vcxc->parent_realize = dc->realize; + dc->realize = calxeda_xgmac_realize; + dc->desc = "VFIO Calxeda XGMAC"; + dc->vmsd = &vfio_platform_calxeda_xgmac_vmstate; +} + +static const TypeInfo vfio_calxeda_xgmac_dev_info = { + .name = TYPE_VFIO_CALXEDA_XGMAC, + .parent = TYPE_VFIO_PLATFORM, + .instance_size = sizeof(VFIOCalxedaXgmacDevice), + .class_init = vfio_calxeda_xgmac_class_init, + .class_size = sizeof(VFIOCalxedaXgmacDeviceClass), +}; + +static void register_calxeda_xgmac_dev_type(void) +{ + type_register_static(&vfio_calxeda_xgmac_dev_info); +} + +type_init(register_calxeda_xgmac_dev_type) diff --git a/include/hw/vfio/vfio-calxeda-xgmac.h b/include/hw/vfio/vfio-calxeda-xgmac.h new file mode 100644 index 0000000..f994775 --- /dev/null +++ b/include/hw/vfio/vfio-calxeda-xgmac.h @@ -0,0 +1,46 @@ +/* + * VFIO calxeda xgmac device + * + * Copyright Linaro Limited, 2014 + * + * Authors: + * Eric Auger + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#ifndef HW_VFIO_VFIO_CALXEDA_XGMAC_H +#define HW_VFIO_VFIO_CALXEDA_XGMAC_H + +#include "hw/vfio/vfio-platform.h" + +#define TYPE_VFIO_CALXEDA_XGMAC "vfio-calxeda-xgmac" + +/** + * This device exposes: + * - a single MMIO region corresponding to its register space + * - 3 IRQS (main and 2 power related IRQs) + */ +typedef struct VFIOCalxedaXgmacDevice { + VFIOPlatformDevice vdev; +} VFIOCalxedaXgmacDevice; + +typedef struct VFIOCalxedaXgmacDeviceClass { + /*< private >*/ + VFIOPlatformDeviceClass parent_class; + /*< public >*/ + DeviceRealize parent_realize; +} VFIOCalxedaXgmacDeviceClass; + +#define VFIO_CALXEDA_XGMAC_DEVICE(obj) \ + OBJECT_CHECK(VFIOCalxedaXgmacDevice, (obj), TYPE_VFIO_CALXEDA_XGMAC) +#define VFIO_CALXEDA_XGMAC_DEVICE_CLASS(klass) \ + OBJECT_CLASS_CHECK(VFIOCalxedaXgmacDeviceClass, (klass), \ + TYPE_VFIO_CALXEDA_XGMAC) +#define VFIO_CALXEDA_XGMAC_DEVICE_GET_CLASS(obj) \ + OBJECT_GET_CLASS(VFIOCalxedaXgmacDeviceClass, (obj), \ + TYPE_VFIO_CALXEDA_XGMAC) + +#endif -- cgit v1.1