From edcd69ab9a323b7ac7a86e1c44b6c9c46598391f Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Tue, 15 Jan 2019 12:19:57 +0000 Subject: iommu: Add virtio-iommu driver The virtio IOMMU is a para-virtualized device, allowing to send IOMMU requests such as map/unmap over virtio transport without emulating page tables. This implementation handles ATTACH, DETACH, MAP and UNMAP requests. The bulk of the code transforms calls coming from the IOMMU API into corresponding virtio requests. Mappings are kept in an interval tree instead of page tables. A little more work is required for modular and x86 support, so for the moment the driver depends on CONFIG_VIRTIO=y and CONFIG_ARM64. Tested-by: Bharat Bhushan Tested-by: Eric Auger Reviewed-by: Eric Auger Signed-off-by: Jean-Philippe Brucker Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_ids.h | 1 + include/uapi/linux/virtio_iommu.h | 106 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 107 insertions(+) create mode 100644 include/uapi/linux/virtio_iommu.h (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index 6d5c3b2d4f4d..cfe47c5d9a56 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -43,5 +43,6 @@ #define VIRTIO_ID_INPUT 18 /* virtio input */ #define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ #define VIRTIO_ID_CRYPTO 20 /* virtio crypto */ +#define VIRTIO_ID_IOMMU 23 /* virtio IOMMU */ #endif /* _LINUX_VIRTIO_IDS_H */ diff --git a/include/uapi/linux/virtio_iommu.h b/include/uapi/linux/virtio_iommu.h new file mode 100644 index 000000000000..5e5fd62689fb --- /dev/null +++ b/include/uapi/linux/virtio_iommu.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* + * Virtio-iommu definition v0.9 + * + * Copyright (C) 2018 Arm Ltd. + */ +#ifndef _UAPI_LINUX_VIRTIO_IOMMU_H +#define _UAPI_LINUX_VIRTIO_IOMMU_H + +#include + +/* Feature bits */ +#define VIRTIO_IOMMU_F_INPUT_RANGE 0 +#define VIRTIO_IOMMU_F_DOMAIN_BITS 1 +#define VIRTIO_IOMMU_F_MAP_UNMAP 2 +#define VIRTIO_IOMMU_F_BYPASS 3 + +struct virtio_iommu_range { + __u64 start; + __u64 end; +}; + +struct virtio_iommu_config { + /* Supported page sizes */ + __u64 page_size_mask; + /* Supported IOVA range */ + struct virtio_iommu_range input_range; + /* Max domain ID size */ + __u8 domain_bits; + __u8 padding[3]; + /* Probe buffer size */ + __u32 probe_size; +}; + +/* Request types */ +#define VIRTIO_IOMMU_T_ATTACH 0x01 +#define VIRTIO_IOMMU_T_DETACH 0x02 +#define VIRTIO_IOMMU_T_MAP 0x03 +#define VIRTIO_IOMMU_T_UNMAP 0x04 + +/* Status types */ +#define VIRTIO_IOMMU_S_OK 0x00 +#define VIRTIO_IOMMU_S_IOERR 0x01 +#define VIRTIO_IOMMU_S_UNSUPP 0x02 +#define VIRTIO_IOMMU_S_DEVERR 0x03 +#define VIRTIO_IOMMU_S_INVAL 0x04 +#define VIRTIO_IOMMU_S_RANGE 0x05 +#define VIRTIO_IOMMU_S_NOENT 0x06 +#define VIRTIO_IOMMU_S_FAULT 0x07 + +struct virtio_iommu_req_head { + __u8 type; + __u8 reserved[3]; +}; + +struct virtio_iommu_req_tail { + __u8 status; + __u8 reserved[3]; +}; + +struct virtio_iommu_req_attach { + struct virtio_iommu_req_head head; + __le32 domain; + __le32 endpoint; + __u8 reserved[8]; + struct virtio_iommu_req_tail tail; +}; + +struct virtio_iommu_req_detach { + struct virtio_iommu_req_head head; + __le32 domain; + __le32 endpoint; + __u8 reserved[8]; + struct virtio_iommu_req_tail tail; +}; + +#define VIRTIO_IOMMU_MAP_F_READ (1 << 0) +#define VIRTIO_IOMMU_MAP_F_WRITE (1 << 1) +#define VIRTIO_IOMMU_MAP_F_EXEC (1 << 2) +#define VIRTIO_IOMMU_MAP_F_MMIO (1 << 3) + +#define VIRTIO_IOMMU_MAP_F_MASK (VIRTIO_IOMMU_MAP_F_READ | \ + VIRTIO_IOMMU_MAP_F_WRITE | \ + VIRTIO_IOMMU_MAP_F_EXEC | \ + VIRTIO_IOMMU_MAP_F_MMIO) + +struct virtio_iommu_req_map { + struct virtio_iommu_req_head head; + __le32 domain; + __le64 virt_start; + __le64 virt_end; + __le64 phys_start; + __le32 flags; + struct virtio_iommu_req_tail tail; +}; + +struct virtio_iommu_req_unmap { + struct virtio_iommu_req_head head; + __le32 domain; + __le64 virt_start; + __le64 virt_end; + __u8 reserved[4]; + struct virtio_iommu_req_tail tail; +}; + +#endif -- cgit v1.2.3 From 2a5a314874450decec244923209ce6ba97e3ed93 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Tue, 15 Jan 2019 12:19:58 +0000 Subject: iommu/virtio: Add probe request When the device offers the probe feature, send a probe request for each device managed by the IOMMU. Extract RESV_MEM information. When we encounter a MSI doorbell region, set it up as a IOMMU_RESV_MSI region. This will tell other subsystems that there is no need to map the MSI doorbell in the virtio-iommu, because MSIs bypass it. Tested-by: Bharat Bhushan Tested-by: Eric Auger Reviewed-by: Eric Auger Signed-off-by: Jean-Philippe Brucker Signed-off-by: Michael S. Tsirkin --- drivers/iommu/virtio-iommu.c | 157 ++++++++++++++++++++++++++++++++++++-- include/uapi/linux/virtio_iommu.h | 36 +++++++++ 2 files changed, 187 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 6fa012cd727e..5e194493a531 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -46,6 +46,7 @@ struct viommu_dev { struct iommu_domain_geometry geometry; u64 pgsize_bitmap; u8 domain_bits; + u32 probe_size; }; struct viommu_mapping { @@ -67,8 +68,10 @@ struct viommu_domain { }; struct viommu_endpoint { + struct device *dev; struct viommu_dev *viommu; struct viommu_domain *vdomain; + struct list_head resv_regions; }; struct viommu_request { @@ -119,6 +122,9 @@ static off_t viommu_get_write_desc_offset(struct viommu_dev *viommu, { size_t tail_size = sizeof(struct virtio_iommu_req_tail); + if (req->type == VIRTIO_IOMMU_T_PROBE) + return len - viommu->probe_size - tail_size; + return len - tail_size; } @@ -393,6 +399,110 @@ static int viommu_replay_mappings(struct viommu_domain *vdomain) return ret; } +static int viommu_add_resv_mem(struct viommu_endpoint *vdev, + struct virtio_iommu_probe_resv_mem *mem, + size_t len) +{ + size_t size; + u64 start64, end64; + phys_addr_t start, end; + struct iommu_resv_region *region = NULL; + unsigned long prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO; + + start = start64 = le64_to_cpu(mem->start); + end = end64 = le64_to_cpu(mem->end); + size = end64 - start64 + 1; + + /* Catch any overflow, including the unlikely end64 - start64 + 1 = 0 */ + if (start != start64 || end != end64 || size < end64 - start64) + return -EOVERFLOW; + + if (len < sizeof(*mem)) + return -EINVAL; + + switch (mem->subtype) { + default: + dev_warn(vdev->dev, "unknown resv mem subtype 0x%x\n", + mem->subtype); + /* Fall-through */ + case VIRTIO_IOMMU_RESV_MEM_T_RESERVED: + region = iommu_alloc_resv_region(start, size, 0, + IOMMU_RESV_RESERVED); + break; + case VIRTIO_IOMMU_RESV_MEM_T_MSI: + region = iommu_alloc_resv_region(start, size, prot, + IOMMU_RESV_MSI); + break; + } + if (!region) + return -ENOMEM; + + list_add(&vdev->resv_regions, ®ion->list); + return 0; +} + +static int viommu_probe_endpoint(struct viommu_dev *viommu, struct device *dev) +{ + int ret; + u16 type, len; + size_t cur = 0; + size_t probe_len; + struct virtio_iommu_req_probe *probe; + struct virtio_iommu_probe_property *prop; + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + struct viommu_endpoint *vdev = fwspec->iommu_priv; + + if (!fwspec->num_ids) + return -EINVAL; + + probe_len = sizeof(*probe) + viommu->probe_size + + sizeof(struct virtio_iommu_req_tail); + probe = kzalloc(probe_len, GFP_KERNEL); + if (!probe) + return -ENOMEM; + + probe->head.type = VIRTIO_IOMMU_T_PROBE; + /* + * For now, assume that properties of an endpoint that outputs multiple + * IDs are consistent. Only probe the first one. + */ + probe->endpoint = cpu_to_le32(fwspec->ids[0]); + + ret = viommu_send_req_sync(viommu, probe, probe_len); + if (ret) + goto out_free; + + prop = (void *)probe->properties; + type = le16_to_cpu(prop->type) & VIRTIO_IOMMU_PROBE_T_MASK; + + while (type != VIRTIO_IOMMU_PROBE_T_NONE && + cur < viommu->probe_size) { + len = le16_to_cpu(prop->length) + sizeof(*prop); + + switch (type) { + case VIRTIO_IOMMU_PROBE_T_RESV_MEM: + ret = viommu_add_resv_mem(vdev, (void *)prop, len); + break; + default: + dev_err(dev, "unknown viommu prop 0x%x\n", type); + } + + if (ret) + dev_err(dev, "failed to parse viommu prop 0x%x\n", type); + + cur += len; + if (cur >= viommu->probe_size) + break; + + prop = (void *)probe->properties + cur; + type = le16_to_cpu(prop->type) & VIRTIO_IOMMU_PROBE_T_MASK; + } + +out_free: + kfree(probe); + return ret; +} + /* IOMMU API */ static struct iommu_domain *viommu_domain_alloc(unsigned type) @@ -614,15 +724,34 @@ static void viommu_iotlb_sync(struct iommu_domain *domain) static void viommu_get_resv_regions(struct device *dev, struct list_head *head) { - struct iommu_resv_region *region; + struct iommu_resv_region *entry, *new_entry, *msi = NULL; + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + struct viommu_endpoint *vdev = fwspec->iommu_priv; int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO; - region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH, prot, - IOMMU_RESV_SW_MSI); - if (!region) - return; + list_for_each_entry(entry, &vdev->resv_regions, list) { + if (entry->type == IOMMU_RESV_MSI) + msi = entry; + + new_entry = kmemdup(entry, sizeof(*entry), GFP_KERNEL); + if (!new_entry) + return; + list_add_tail(&new_entry->list, head); + } + + /* + * If the device didn't register any bypass MSI window, add a + * software-mapped region. + */ + if (!msi) { + msi = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH, + prot, IOMMU_RESV_SW_MSI); + if (!msi) + return; + + list_add_tail(&msi->list, head); + } - list_add_tail(®ion->list, head); iommu_dma_get_resv_regions(dev, head); } @@ -670,9 +799,18 @@ static int viommu_add_device(struct device *dev) if (!vdev) return -ENOMEM; + vdev->dev = dev; vdev->viommu = viommu; + INIT_LIST_HEAD(&vdev->resv_regions); fwspec->iommu_priv = vdev; + if (viommu->probe_size) { + /* Get additional information for this endpoint */ + ret = viommu_probe_endpoint(viommu, dev); + if (ret) + goto err_free_dev; + } + ret = iommu_device_link(&viommu->iommu, dev); if (ret) goto err_free_dev; @@ -694,6 +832,7 @@ static int viommu_add_device(struct device *dev) err_unlink_dev: iommu_device_unlink(&viommu->iommu, dev); err_free_dev: + viommu_put_resv_regions(dev, &vdev->resv_regions); kfree(vdev); return ret; @@ -711,6 +850,7 @@ static void viommu_remove_device(struct device *dev) iommu_group_remove_device(dev); iommu_device_unlink(&vdev->viommu->iommu, dev); + viommu_put_resv_regions(dev, &vdev->resv_regions); kfree(vdev); } @@ -810,6 +950,10 @@ static int viommu_probe(struct virtio_device *vdev) struct virtio_iommu_config, domain_bits, &viommu->domain_bits); + virtio_cread_feature(vdev, VIRTIO_IOMMU_F_PROBE, + struct virtio_iommu_config, probe_size, + &viommu->probe_size); + viommu->geometry = (struct iommu_domain_geometry) { .aperture_start = input_start, .aperture_end = input_end, @@ -891,6 +1035,7 @@ static unsigned int features[] = { VIRTIO_IOMMU_F_MAP_UNMAP, VIRTIO_IOMMU_F_DOMAIN_BITS, VIRTIO_IOMMU_F_INPUT_RANGE, + VIRTIO_IOMMU_F_PROBE, }; static struct virtio_device_id id_table[] = { diff --git a/include/uapi/linux/virtio_iommu.h b/include/uapi/linux/virtio_iommu.h index 5e5fd62689fb..ae6145cf5928 100644 --- a/include/uapi/linux/virtio_iommu.h +++ b/include/uapi/linux/virtio_iommu.h @@ -14,6 +14,7 @@ #define VIRTIO_IOMMU_F_DOMAIN_BITS 1 #define VIRTIO_IOMMU_F_MAP_UNMAP 2 #define VIRTIO_IOMMU_F_BYPASS 3 +#define VIRTIO_IOMMU_F_PROBE 4 struct virtio_iommu_range { __u64 start; @@ -37,6 +38,7 @@ struct virtio_iommu_config { #define VIRTIO_IOMMU_T_DETACH 0x02 #define VIRTIO_IOMMU_T_MAP 0x03 #define VIRTIO_IOMMU_T_UNMAP 0x04 +#define VIRTIO_IOMMU_T_PROBE 0x05 /* Status types */ #define VIRTIO_IOMMU_S_OK 0x00 @@ -103,4 +105,38 @@ struct virtio_iommu_req_unmap { struct virtio_iommu_req_tail tail; }; +#define VIRTIO_IOMMU_PROBE_T_NONE 0 +#define VIRTIO_IOMMU_PROBE_T_RESV_MEM 1 + +#define VIRTIO_IOMMU_PROBE_T_MASK 0xfff + +struct virtio_iommu_probe_property { + __le16 type; + __le16 length; +}; + +#define VIRTIO_IOMMU_RESV_MEM_T_RESERVED 0 +#define VIRTIO_IOMMU_RESV_MEM_T_MSI 1 + +struct virtio_iommu_probe_resv_mem { + struct virtio_iommu_probe_property head; + __u8 subtype; + __u8 reserved[3]; + __le64 start; + __le64 end; +}; + +struct virtio_iommu_req_probe { + struct virtio_iommu_req_head head; + __le32 endpoint; + __u8 reserved[64]; + + __u8 properties[]; + + /* + * Tail follows the variable-length properties array. No padding, + * property lengths are all aligned on 8 bytes. + */ +}; + #endif -- cgit v1.2.3 From 169a126c6e88a99578a309a9021f314b5d532c5f Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Tue, 15 Jan 2019 12:19:59 +0000 Subject: iommu/virtio: Add event queue The event queue offers a way for the device to report access faults from endpoints. It is implemented on virtqueue #1. Whenever the host needs to signal a fault, it fills one of the buffers offered by the guest and interrupts it. Tested-by: Bharat Bhushan Tested-by: Eric Auger Reviewed-by: Eric Auger Signed-off-by: Jean-Philippe Brucker Signed-off-by: Michael S. Tsirkin --- drivers/iommu/virtio-iommu.c | 115 +++++++++++++++++++++++++++++++++++--- include/uapi/linux/virtio_iommu.h | 19 +++++++ 2 files changed, 125 insertions(+), 9 deletions(-) (limited to 'include/uapi') diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 5e194493a531..4620dd221ffd 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -29,7 +29,8 @@ #define MSI_IOVA_LENGTH 0x100000 #define VIOMMU_REQUEST_VQ 0 -#define VIOMMU_NR_VQS 1 +#define VIOMMU_EVENT_VQ 1 +#define VIOMMU_NR_VQS 2 struct viommu_dev { struct iommu_device iommu; @@ -41,6 +42,7 @@ struct viommu_dev { struct virtqueue *vqs[VIOMMU_NR_VQS]; spinlock_t request_lock; struct list_head requests; + void *evts; /* Device configuration */ struct iommu_domain_geometry geometry; @@ -82,6 +84,15 @@ struct viommu_request { char buf[]; }; +#define VIOMMU_FAULT_RESV_MASK 0xffffff00 + +struct viommu_event { + union { + u32 head; + struct virtio_iommu_fault fault; + }; +}; + #define to_viommu_domain(domain) \ container_of(domain, struct viommu_domain, domain) @@ -503,6 +514,68 @@ out_free: return ret; } +static int viommu_fault_handler(struct viommu_dev *viommu, + struct virtio_iommu_fault *fault) +{ + char *reason_str; + + u8 reason = fault->reason; + u32 flags = le32_to_cpu(fault->flags); + u32 endpoint = le32_to_cpu(fault->endpoint); + u64 address = le64_to_cpu(fault->address); + + switch (reason) { + case VIRTIO_IOMMU_FAULT_R_DOMAIN: + reason_str = "domain"; + break; + case VIRTIO_IOMMU_FAULT_R_MAPPING: + reason_str = "page"; + break; + case VIRTIO_IOMMU_FAULT_R_UNKNOWN: + default: + reason_str = "unknown"; + break; + } + + /* TODO: find EP by ID and report_iommu_fault */ + if (flags & VIRTIO_IOMMU_FAULT_F_ADDRESS) + dev_err_ratelimited(viommu->dev, "%s fault from EP %u at %#llx [%s%s%s]\n", + reason_str, endpoint, address, + flags & VIRTIO_IOMMU_FAULT_F_READ ? "R" : "", + flags & VIRTIO_IOMMU_FAULT_F_WRITE ? "W" : "", + flags & VIRTIO_IOMMU_FAULT_F_EXEC ? "X" : ""); + else + dev_err_ratelimited(viommu->dev, "%s fault from EP %u\n", + reason_str, endpoint); + return 0; +} + +static void viommu_event_handler(struct virtqueue *vq) +{ + int ret; + unsigned int len; + struct scatterlist sg[1]; + struct viommu_event *evt; + struct viommu_dev *viommu = vq->vdev->priv; + + while ((evt = virtqueue_get_buf(vq, &len)) != NULL) { + if (len > sizeof(*evt)) { + dev_err(viommu->dev, + "invalid event buffer (len %u != %zu)\n", + len, sizeof(*evt)); + } else if (!(evt->head & VIOMMU_FAULT_RESV_MASK)) { + viommu_fault_handler(viommu, &evt->fault); + } + + sg_init_one(sg, evt, sizeof(*evt)); + ret = virtqueue_add_inbuf(vq, sg, 1, evt, GFP_ATOMIC); + if (ret) + dev_err(viommu->dev, "could not add event buffer\n"); + } + + virtqueue_kick(vq); +} + /* IOMMU API */ static struct iommu_domain *viommu_domain_alloc(unsigned type) @@ -886,16 +959,35 @@ static struct iommu_ops viommu_ops = { static int viommu_init_vqs(struct viommu_dev *viommu) { struct virtio_device *vdev = dev_to_virtio(viommu->dev); - const char *name = "request"; - void *ret; + const char *names[] = { "request", "event" }; + vq_callback_t *callbacks[] = { + NULL, /* No async requests */ + viommu_event_handler, + }; - ret = virtio_find_single_vq(vdev, NULL, name); - if (IS_ERR(ret)) { - dev_err(viommu->dev, "cannot find VQ\n"); - return PTR_ERR(ret); - } + return virtio_find_vqs(vdev, VIOMMU_NR_VQS, viommu->vqs, callbacks, + names, NULL); +} - viommu->vqs[VIOMMU_REQUEST_VQ] = ret; +static int viommu_fill_evtq(struct viommu_dev *viommu) +{ + int i, ret; + struct scatterlist sg[1]; + struct viommu_event *evts; + struct virtqueue *vq = viommu->vqs[VIOMMU_EVENT_VQ]; + size_t nr_evts = vq->num_free; + + viommu->evts = evts = devm_kmalloc_array(viommu->dev, nr_evts, + sizeof(*evts), GFP_KERNEL); + if (!evts) + return -ENOMEM; + + for (i = 0; i < nr_evts; i++) { + sg_init_one(sg, &evts[i], sizeof(*evts)); + ret = virtqueue_add_inbuf(vq, sg, 1, &evts[i], GFP_KERNEL); + if (ret) + return ret; + } return 0; } @@ -964,6 +1056,11 @@ static int viommu_probe(struct virtio_device *vdev) virtio_device_ready(vdev); + /* Populate the event queue with buffers */ + ret = viommu_fill_evtq(viommu); + if (ret) + goto err_free_vqs; + ret = iommu_device_sysfs_add(&viommu->iommu, dev, NULL, "%s", virtio_bus_name(vdev)); if (ret) diff --git a/include/uapi/linux/virtio_iommu.h b/include/uapi/linux/virtio_iommu.h index ae6145cf5928..ba1b460c9944 100644 --- a/include/uapi/linux/virtio_iommu.h +++ b/include/uapi/linux/virtio_iommu.h @@ -139,4 +139,23 @@ struct virtio_iommu_req_probe { */ }; +/* Fault types */ +#define VIRTIO_IOMMU_FAULT_R_UNKNOWN 0 +#define VIRTIO_IOMMU_FAULT_R_DOMAIN 1 +#define VIRTIO_IOMMU_FAULT_R_MAPPING 2 + +#define VIRTIO_IOMMU_FAULT_F_READ (1 << 0) +#define VIRTIO_IOMMU_FAULT_F_WRITE (1 << 1) +#define VIRTIO_IOMMU_FAULT_F_EXEC (1 << 2) +#define VIRTIO_IOMMU_FAULT_F_ADDRESS (1 << 8) + +struct virtio_iommu_fault { + __u8 reason; + __u8 reserved[3]; + __le32 flags; + __le32 endpoint; + __u8 reserved2[4]; + __le64 address; +}; + #endif -- cgit v1.2.3