diff options
Diffstat (limited to 'drivers/virtio/virtio_ring.c')
| -rw-r--r-- | drivers/virtio/virtio_ring.c | 439 |
1 files changed, 377 insertions, 62 deletions
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index e12e385..5c802d4 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -24,6 +24,8 @@ #include <linux/module.h> #include <linux/hrtimer.h> #include <linux/kmemleak.h> +#include <linux/dma-mapping.h> +#include <xen/xen.h> #ifdef DEBUG /* For development, we want to crash whenever the ring is screwed. */ @@ -54,6 +56,11 @@ #define END_USE(vq) #endif +struct vring_desc_state { + void *data; /* Data for callback. */ + struct vring_desc *indir_desc; /* Indirect descriptor, if any. */ +}; + struct vring_virtqueue { struct virtqueue vq; @@ -89,6 +96,11 @@ struct vring_virtqueue { /* How to notify other side. FIXME: commonalize hcalls! */ bool (*notify)(struct virtqueue *vq); + /* DMA, allocation, and size information */ + bool we_own_ring; + size_t queue_size_in_bytes; + dma_addr_t queue_dma_addr; + #ifdef DEBUG /* They're supposed to lock for us. */ unsigned int in_use; @@ -98,12 +110,120 @@ struct vring_virtqueue { ktime_t last_add_time; #endif - /* Tokens for callbacks. */ - void *data[]; + /* Per-descriptor state. */ + struct vring_desc_state desc_state[]; }; #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq) +/* + * The interaction between virtio and a possible IOMMU is a mess. + * + * On most systems with virtio, physical addresses match bus addresses, + * and it doesn't particularly matter whether we use the DMA API. + * + * On some systems, including Xen and any system with a physical device + * that speaks virtio behind a physical IOMMU, we must use the DMA API + * for virtio DMA to work at all. + * + * On other systems, including SPARC and PPC64, virtio-pci devices are + * enumerated as though they are behind an IOMMU, but the virtio host + * ignores the IOMMU, so we must either pretend that the IOMMU isn't + * there or somehow map everything as the identity. + * + * For the time being, we preserve historic behavior and bypass the DMA + * API. + */ + +static bool vring_use_dma_api(struct virtio_device *vdev) +{ + /* + * In theory, it's possible to have a buggy QEMU-supposed + * emulated Q35 IOMMU and Xen enabled at the same time. On + * such a configuration, virtio has never worked and will + * not work without an even larger kludge. Instead, enable + * the DMA API if we're a Xen guest, which at least allows + * all of the sensible Xen configurations to work correctly. + */ + if (xen_domain()) + return true; + + return false; +} + +/* + * The DMA ops on various arches are rather gnarly right now, and + * making all of the arch DMA ops work on the vring device itself + * is a mess. For now, we use the parent device for DMA ops. + */ +struct device *vring_dma_dev(const struct vring_virtqueue *vq) +{ + return vq->vq.vdev->dev.parent; +} + +/* Map one sg entry. */ +static dma_addr_t vring_map_one_sg(const struct vring_virtqueue *vq, + struct scatterlist *sg, + enum dma_data_direction direction) +{ + if (!vring_use_dma_api(vq->vq.vdev)) + return (dma_addr_t)sg_phys(sg); + + /* + * We can't use dma_map_sg, because we don't use scatterlists in + * the way it expects (we don't guarantee that the scatterlist + * will exist for the lifetime of the mapping). + */ + return dma_map_page(vring_dma_dev(vq), + sg_page(sg), sg->offset, sg->length, + direction); +} + +static dma_addr_t vring_map_single(const struct vring_virtqueue *vq, + void *cpu_addr, size_t size, + enum dma_data_direction direction) +{ + if (!vring_use_dma_api(vq->vq.vdev)) + return (dma_addr_t)virt_to_phys(cpu_addr); + + return dma_map_single(vring_dma_dev(vq), + cpu_addr, size, direction); +} + +static void vring_unmap_one(const struct vring_virtqueue *vq, + struct vring_desc *desc) +{ + u16 flags; + + if (!vring_use_dma_api(vq->vq.vdev)) + return; + + flags = virtio16_to_cpu(vq->vq.vdev, desc->flags); + + if (flags & VRING_DESC_F_INDIRECT) { + dma_unmap_single(vring_dma_dev(vq), + virtio64_to_cpu(vq->vq.vdev, desc->addr), + virtio32_to_cpu(vq->vq.vdev, desc->len), + (flags & VRING_DESC_F_WRITE) ? + DMA_FROM_DEVICE : DMA_TO_DEVICE); + } else { + dma_unmap_page(vring_dma_dev(vq), + virtio64_to_cpu(vq->vq.vdev, desc->addr), + virtio32_to_cpu(vq->vq.vdev, desc->len), + (flags & VRING_DESC_F_WRITE) ? + DMA_FROM_DEVICE : DMA_TO_DEVICE); + } +} + +static int vring_mapping_error(const struct vring_virtqueue *vq, + dma_addr_t addr) +{ + if (!vring_use_dma_api(vq->vq.vdev)) + return 0; + + return dma_mapping_error(vring_dma_dev(vq), addr); +} + static struct vring_desc *alloc_indirect(struct virtqueue *_vq, unsigned int total_sg, gfp_t gfp) { @@ -137,7 +257,7 @@ static inline int virtqueue_add(struct virtqueue *_vq, struct vring_virtqueue *vq = to_vvq(_vq); struct scatterlist *sg; struct vring_desc *desc; - unsigned int i, n, avail, descs_used, uninitialized_var(prev); + unsigned int i, n, avail, descs_used, uninitialized_var(prev), err_idx; int head; bool indirect; @@ -177,21 +297,15 @@ static inline int virtqueue_add(struct virtqueue *_vq, if (desc) { /* Use a single buffer which doesn't continue */ - vq->vring.desc[head].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_INDIRECT); - vq->vring.desc[head].addr = cpu_to_virtio64(_vq->vdev, virt_to_phys(desc)); - /* avoid kmemleak false positive (hidden by virt_to_phys) */ - kmemleak_ignore(desc); - vq->vring.desc[head].len = cpu_to_virtio32(_vq->vdev, total_sg * sizeof(struct vring_desc)); - + indirect = true; /* Set up rest to use this indirect table. */ i = 0; descs_used = 1; - indirect = true; } else { + indirect = false; desc = vq->vring.desc; i = head; descs_used = total_sg; - indirect = false; } if (vq->vq.num_free < descs_used) { @@ -206,13 +320,14 @@ static inline int virtqueue_add(struct virtqueue *_vq, return -ENOSPC; } - /* We're about to use some buffers from the free list. */ - vq->vq.num_free -= descs_used; - for (n = 0; n < out_sgs; n++) { for (sg = sgs[n]; sg; sg = sg_next(sg)) { + dma_addr_t addr = vring_map_one_sg(vq, sg, DMA_TO_DEVICE); + if (vring_mapping_error(vq, addr)) + goto unmap_release; + desc[i].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT); - desc[i].addr = cpu_to_virtio64(_vq->vdev, sg_phys(sg)); + desc[i].addr = cpu_to_virtio64(_vq->vdev, addr); desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length); prev = i; i = virtio16_to_cpu(_vq->vdev, desc[i].next); @@ -220,8 +335,12 @@ static inline int virtqueue_add(struct virtqueue *_vq, } for (; n < (out_sgs + in_sgs); n++) { for (sg = sgs[n]; sg; sg = sg_next(sg)) { + dma_addr_t addr = vring_map_one_sg(vq, sg, DMA_FROM_DEVICE); + if (vring_mapping_error(vq, addr)) + goto unmap_release; + desc[i].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT | VRING_DESC_F_WRITE); - desc[i].addr = cpu_to_virtio64(_vq->vdev, sg_phys(sg)); + desc[i].addr = cpu_to_virtio64(_vq->vdev, addr); desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length); prev = i; i = virtio16_to_cpu(_vq->vdev, desc[i].next); @@ -230,14 +349,33 @@ static inline int virtqueue_add(struct virtqueue *_vq, /* Last one doesn't continue. */ desc[prev].flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT); + if (indirect) { + /* Now that the indirect table is filled in, map it. */ + dma_addr_t addr = vring_map_single( + vq, desc, total_sg * sizeof(struct vring_desc), + DMA_TO_DEVICE); + if (vring_mapping_error(vq, addr)) + goto unmap_release; + + vq->vring.desc[head].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_INDIRECT); + vq->vring.desc[head].addr = cpu_to_virtio64(_vq->vdev, addr); + + vq->vring.desc[head].len = cpu_to_virtio32(_vq->vdev, total_sg * sizeof(struct vring_desc)); + } + + /* We're using some buffers from the free list. */ + vq->vq.num_free -= descs_used; + /* Update free pointer */ if (indirect) vq->free_head = virtio16_to_cpu(_vq->vdev, vq->vring.desc[head].next); else vq->free_head = i; - /* Set token. */ - vq->data[head] = data; + /* Store token and indirect buffer state. */ + vq->desc_state[head].data = data; + if (indirect) + vq->desc_state[head].indir_desc = desc; /* Put entry in available array (but don't update avail->idx until they * do sync). */ @@ -260,6 +398,24 @@ static inline int virtqueue_add(struct virtqueue *_vq, virtqueue_kick(_vq); return 0; + +unmap_release: + err_idx = i; + i = head; + + for (n = 0; n < total_sg; n++) { + if (i == err_idx) + break; + vring_unmap_one(vq, &desc[i]); + i = vq->vring.desc[i].next; + } + + vq->vq.num_free += total_sg; + + if (indirect) + kfree(desc); + + return -EIO; } /** @@ -430,27 +586,43 @@ EXPORT_SYMBOL_GPL(virtqueue_kick); static void detach_buf(struct vring_virtqueue *vq, unsigned int head) { - unsigned int i; + unsigned int i, j; + u16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT); /* Clear data ptr. */ - vq->data[head] = NULL; + vq->desc_state[head].data = NULL; - /* Put back on free list: find end */ + /* Put back on free list: unmap first-level descriptors and find end */ i = head; - /* Free the indirect table */ - if (vq->vring.desc[i].flags & cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)) - kfree(phys_to_virt(virtio64_to_cpu(vq->vq.vdev, vq->vring.desc[i].addr))); - - while (vq->vring.desc[i].flags & cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT)) { + while (vq->vring.desc[i].flags & nextflag) { + vring_unmap_one(vq, &vq->vring.desc[i]); i = virtio16_to_cpu(vq->vq.vdev, vq->vring.desc[i].next); vq->vq.num_free++; } + vring_unmap_one(vq, &vq->vring.desc[i]); vq->vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev, vq->free_head); vq->free_head = head; + /* Plus final descriptor */ vq->vq.num_free++; + + /* Free the indirect table, if any, now that it's unmapped. */ + if (vq->desc_state[head].indir_desc) { + struct vring_desc *indir_desc = vq->desc_state[head].indir_desc; + u32 len = virtio32_to_cpu(vq->vq.vdev, vq->vring.desc[head].len); + + BUG_ON(!(vq->vring.desc[head].flags & + cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT))); + BUG_ON(len == 0 || len % sizeof(struct vring_desc)); + + for (j = 0; j < len / sizeof(struct vring_desc); j++) + vring_unmap_one(vq, &indir_desc[j]); + + kfree(vq->desc_state[head].indir_desc); + vq->desc_state[head].indir_desc = NULL; + } } static inline bool more_used(const struct vring_virtqueue *vq) @@ -505,13 +677,13 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) BAD_RING(vq, "id %u out of range\n", i); return NULL; } - if (unlikely(!vq->data[i])) { + if (unlikely(!vq->desc_state[i].data)) { BAD_RING(vq, "id %u is not a head!\n", i); return NULL; } /* detach_buf clears data, so grab it now. */ - ret = vq->data[i]; + ret = vq->desc_state[i].data; detach_buf(vq, i); vq->last_used_idx++; /* If we expect an interrupt for the next entry, tell host @@ -685,10 +857,10 @@ void *virtqueue_detach_unused_buf(struct virtqueue *_vq) START_USE(vq); for (i = 0; i < vq->vring.num; i++) { - if (!vq->data[i]) + if (!vq->desc_state[i].data) continue; /* detach_buf clears data, so grab it now. */ - buf = vq->data[i]; + buf = vq->desc_state[i].data; detach_buf(vq, i); vq->avail_idx_shadow--; vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow); @@ -723,35 +895,31 @@ irqreturn_t vring_interrupt(int irq, void *_vq) } EXPORT_SYMBOL_GPL(vring_interrupt); -struct virtqueue *vring_new_virtqueue(unsigned int index, - unsigned int num, - unsigned int vring_align, - struct virtio_device *vdev, - bool weak_barriers, - void *pages, - bool (*notify)(struct virtqueue *), - void (*callback)(struct virtqueue *), - const char *name) +struct virtqueue *__vring_new_virtqueue(unsigned int index, + struct vring vring, + struct virtio_device *vdev, + bool weak_barriers, + bool (*notify)(struct virtqueue *), + void (*callback)(struct virtqueue *), + const char *name) { - struct vring_virtqueue *vq; unsigned int i; + struct vring_virtqueue *vq; - /* We assume num is a power of 2. */ - if (num & (num - 1)) { - dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num); - return NULL; - } - - vq = kmalloc(sizeof(*vq) + sizeof(void *)*num, GFP_KERNEL); + vq = kmalloc(sizeof(*vq) + vring.num * sizeof(struct vring_desc_state), + GFP_KERNEL); if (!vq) return NULL; - vring_init(&vq->vring, num, pages, vring_align); + vq->vring = vring; vq->vq.callback = callback; vq->vq.vdev = vdev; vq->vq.name = name; - vq->vq.num_free = num; + vq->vq.num_free = vring.num; vq->vq.index = index; + vq->we_own_ring = false; + vq->queue_dma_addr = 0; + vq->queue_size_in_bytes = 0; vq->notify = notify; vq->weak_barriers = weak_barriers; vq->broken = false; @@ -776,20 +944,145 @@ struct virtqueue *vring_new_virtqueue(unsigned int index, /* Put everything in free lists. */ vq->free_head = 0; - for (i = 0; i < num-1; i++) { + for (i = 0; i < vring.num-1; i++) vq->vring.desc[i].next = cpu_to_virtio16(vdev, i + 1); - vq->data[i] = NULL; - } - vq->data[i] = NULL; + memset(vq->desc_state, 0, vring.num * sizeof(struct vring_desc_state)); return &vq->vq; } +EXPORT_SYMBOL_GPL(__vring_new_virtqueue); + +static void *vring_alloc_queue(struct virtio_device *vdev, size_t size, + dma_addr_t *dma_handle, gfp_t flag) +{ + if (vring_use_dma_api(vdev)) { + return dma_alloc_coherent(vdev->dev.parent, size, + dma_handle, flag); + } else { + void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag); + if (queue) { + phys_addr_t phys_addr = virt_to_phys(queue); + *dma_handle = (dma_addr_t)phys_addr; + + /* + * Sanity check: make sure we dind't truncate + * the address. The only arches I can find that + * have 64-bit phys_addr_t but 32-bit dma_addr_t + * are certain non-highmem MIPS and x86 + * configurations, but these configurations + * should never allocate physical pages above 32 + * bits, so this is fine. Just in case, throw a + * warning and abort if we end up with an + * unrepresentable address. + */ + if (WARN_ON_ONCE(*dma_handle != phys_addr)) { + free_pages_exact(queue, PAGE_ALIGN(size)); + return NULL; + } + } + return queue; + } +} + +static void vring_free_queue(struct virtio_device *vdev, size_t size, + void *queue, dma_addr_t dma_handle) +{ + if (vring_use_dma_api(vdev)) { + dma_free_coherent(vdev->dev.parent, size, queue, dma_handle); + } else { + free_pages_exact(queue, PAGE_ALIGN(size)); + } +} + +struct virtqueue *vring_create_virtqueue( + unsigned int index, + unsigned int num, + unsigned int vring_align, + struct virtio_device *vdev, + bool weak_barriers, + bool may_reduce_num, + bool (*notify)(struct virtqueue *), + void (*callback)(struct virtqueue *), + const char *name) +{ + struct virtqueue *vq; + void *queue; + dma_addr_t dma_addr; + size_t queue_size_in_bytes; + struct vring vring; + + /* We assume num is a power of 2. */ + if (num & (num - 1)) { + dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num); + return NULL; + } + + /* TODO: allocate each queue chunk individually */ + for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) { + queue = vring_alloc_queue(vdev, vring_size(num, vring_align), + &dma_addr, + GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO); + if (queue) + break; + } + + if (!num) + return NULL; + + if (!queue) { + /* Try to get a single page. You are my only hope! */ + queue = vring_alloc_queue(vdev, vring_size(num, vring_align), + &dma_addr, GFP_KERNEL|__GFP_ZERO); + } + if (!queue) + return NULL; + + queue_size_in_bytes = vring_size(num, vring_align); + vring_init(&vring, num, queue, vring_align); + + vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers, + notify, callback, name); + if (!vq) { + vring_free_queue(vdev, queue_size_in_bytes, queue, + dma_addr); + return NULL; + } + + to_vvq(vq)->queue_dma_addr = dma_addr; + to_vvq(vq)->queue_size_in_bytes = queue_size_in_bytes; + to_vvq(vq)->we_own_ring = true; + + return vq; +} +EXPORT_SYMBOL_GPL(vring_create_virtqueue); + +struct virtqueue *vring_new_virtqueue(unsigned int index, + unsigned int num, + unsigned int vring_align, + struct virtio_device *vdev, + bool weak_barriers, + void *pages, + bool (*notify)(struct virtqueue *vq), + void (*callback)(struct virtqueue *vq), + const char *name) +{ + struct vring vring; + vring_init(&vring, num, pages, vring_align); + return __vring_new_virtqueue(index, vring, vdev, weak_barriers, + notify, callback, name); +} EXPORT_SYMBOL_GPL(vring_new_virtqueue); -void vring_del_virtqueue(struct virtqueue *vq) +void vring_del_virtqueue(struct virtqueue *_vq) { - list_del(&vq->list); - kfree(to_vvq(vq)); + struct vring_virtqueue *vq = to_vvq(_vq); + + if (vq->we_own_ring) { + vring_free_queue(vq->vq.vdev, vq->queue_size_in_bytes, + vq->vring.desc, vq->queue_dma_addr); + } + list_del(&_vq->list); + kfree(vq); } EXPORT_SYMBOL_GPL(vring_del_virtqueue); @@ -853,20 +1146,42 @@ void virtio_break_device(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(virtio_break_device); -void *virtqueue_get_avail(struct virtqueue *_vq) +dma_addr_t virtqueue_get_desc_addr(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); - return vq->vring.avail; + BUG_ON(!vq->we_own_ring); + + return vq->queue_dma_addr; } -EXPORT_SYMBOL_GPL(virtqueue_get_avail); +EXPORT_SYMBOL_GPL(virtqueue_get_desc_addr); -void *virtqueue_get_used(struct virtqueue *_vq) +dma_addr_t virtqueue_get_avail_addr(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); - return vq->vring.used; + BUG_ON(!vq->we_own_ring); + + return vq->queue_dma_addr + + ((char *)vq->vring.avail - (char *)vq->vring.desc); +} +EXPORT_SYMBOL_GPL(virtqueue_get_avail_addr); + +dma_addr_t virtqueue_get_used_addr(struct virtqueue *_vq) +{ + struct vring_virtqueue *vq = to_vvq(_vq); + + BUG_ON(!vq->we_own_ring); + + return vq->queue_dma_addr + + ((char *)vq->vring.used - (char *)vq->vring.desc); +} +EXPORT_SYMBOL_GPL(virtqueue_get_used_addr); + +const struct vring *virtqueue_get_vring(struct virtqueue *vq) +{ + return &to_vvq(vq)->vring; } -EXPORT_SYMBOL_GPL(virtqueue_get_used); +EXPORT_SYMBOL_GPL(virtqueue_get_vring); MODULE_LICENSE("GPL"); |
