diff options
Diffstat (limited to 'drivers/virtio/virtio_ring.c')
| -rw-r--r-- | drivers/virtio/virtio_ring.c | 726 |
1 files changed, 640 insertions, 86 deletions
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index aa714028641..4d08f45a9c2 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -18,19 +18,38 @@ */ #include <linux/virtio.h> #include <linux/virtio_ring.h> +#include <linux/virtio_config.h> #include <linux/device.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/hrtimer.h> +#include <linux/kmemleak.h> #ifdef DEBUG /* For development, we want to crash whenever the ring is screwed. */ -#define BAD_RING(vq, fmt...) \ - do { dev_err(&vq->vq.vdev->dev, fmt); BUG(); } while(0) -#define START_USE(vq) \ - do { if ((vq)->in_use) panic("in_use = %i\n", (vq)->in_use); (vq)->in_use = __LINE__; mb(); } while(0) -#define END_USE(vq) \ - do { BUG_ON(!(vq)->in_use); (vq)->in_use = 0; mb(); } while(0) +#define BAD_RING(_vq, fmt, args...) \ + do { \ + dev_err(&(_vq)->vq.vdev->dev, \ + "%s:"fmt, (_vq)->vq.name, ##args); \ + BUG(); \ + } while (0) +/* Caller is supposed to guarantee no reentry. */ +#define START_USE(_vq) \ + do { \ + if ((_vq)->in_use) \ + panic("%s:in_use = %i\n", \ + (_vq)->vq.name, (_vq)->in_use); \ + (_vq)->in_use = __LINE__; \ + } while (0) +#define END_USE(_vq) \ + do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; } while(0) #else -#define BAD_RING(vq, fmt...) \ - do { dev_err(&vq->vq.vdev->dev, fmt); (vq)->broken = true; } while(0) +#define BAD_RING(_vq, fmt, args...) \ + do { \ + dev_err(&_vq->vq.vdev->dev, \ + "%s:"fmt, (_vq)->vq.name, ##args); \ + (_vq)->broken = true; \ + } while (0) #define START_USE(vq) #define END_USE(vq) #endif @@ -42,11 +61,18 @@ struct vring_virtqueue /* Actual memory layout for this queue */ struct vring vring; + /* Can we use weak barriers? */ + bool weak_barriers; + /* Other side has made a mess, don't try any more. */ bool broken; - /* Number of free buffers */ - unsigned int num_free; + /* Host supports indirect buffers */ + bool indirect; + + /* Host publishes avail event idx */ + bool event; + /* Head of free buffer list. */ unsigned int free_head; /* Number we've added since last sync. */ @@ -56,11 +82,15 @@ struct vring_virtqueue u16 last_used_idx; /* How to notify other side. FIXME: commonalize hcalls! */ - void (*notify)(struct virtqueue *vq); + bool (*notify)(struct virtqueue *vq); #ifdef DEBUG /* They're supposed to lock for us. */ unsigned int in_use; + + /* Figure out if their kicks are too delayed. */ + bool last_add_time_valid; + ktime_t last_add_time; #endif /* Tokens for callbacks. */ @@ -69,47 +99,177 @@ struct vring_virtqueue #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq) -static int vring_add_buf(struct virtqueue *_vq, - struct scatterlist sg[], - unsigned int out, - unsigned int in, - void *data) +static inline struct scatterlist *sg_next_chained(struct scatterlist *sg, + unsigned int *count) +{ + return sg_next(sg); +} + +static inline struct scatterlist *sg_next_arr(struct scatterlist *sg, + unsigned int *count) +{ + if (--(*count) == 0) + return NULL; + return sg + 1; +} + +/* Set up an indirect table of descriptors and add it to the queue. */ +static inline int vring_add_indirect(struct vring_virtqueue *vq, + struct scatterlist *sgs[], + struct scatterlist *(*next) + (struct scatterlist *, unsigned int *), + unsigned int total_sg, + unsigned int total_out, + unsigned int total_in, + unsigned int out_sgs, + unsigned int in_sgs, + gfp_t gfp) +{ + struct vring_desc *desc; + unsigned head; + struct scatterlist *sg; + int i, n; + + /* + * We require lowmem mappings for the descriptors because + * otherwise virt_to_phys will give us bogus addresses in the + * virtqueue. + */ + gfp &= ~(__GFP_HIGHMEM | __GFP_HIGH); + + desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp); + if (!desc) + return -ENOMEM; + + /* Transfer entries from the sg lists into the indirect page */ + i = 0; + for (n = 0; n < out_sgs; n++) { + for (sg = sgs[n]; sg; sg = next(sg, &total_out)) { + desc[i].flags = VRING_DESC_F_NEXT; + desc[i].addr = sg_phys(sg); + desc[i].len = sg->length; + desc[i].next = i+1; + i++; + } + } + for (; n < (out_sgs + in_sgs); n++) { + for (sg = sgs[n]; sg; sg = next(sg, &total_in)) { + desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE; + desc[i].addr = sg_phys(sg); + desc[i].len = sg->length; + desc[i].next = i+1; + i++; + } + } + BUG_ON(i != total_sg); + + /* Last one doesn't continue. */ + desc[i-1].flags &= ~VRING_DESC_F_NEXT; + desc[i-1].next = 0; + + /* We're about to use a buffer */ + vq->vq.num_free--; + + /* Use a single buffer which doesn't continue */ + head = vq->free_head; + vq->vring.desc[head].flags = VRING_DESC_F_INDIRECT; + vq->vring.desc[head].addr = virt_to_phys(desc); + /* kmemleak gives a false positive, as it's hidden by virt_to_phys */ + kmemleak_ignore(desc); + vq->vring.desc[head].len = i * sizeof(struct vring_desc); + + /* Update free pointer */ + vq->free_head = vq->vring.desc[head].next; + + return head; +} + +static inline int virtqueue_add(struct virtqueue *_vq, + struct scatterlist *sgs[], + struct scatterlist *(*next) + (struct scatterlist *, unsigned int *), + unsigned int total_out, + unsigned int total_in, + unsigned int out_sgs, + unsigned int in_sgs, + void *data, + gfp_t gfp) { struct vring_virtqueue *vq = to_vvq(_vq); - unsigned int i, avail, head, uninitialized_var(prev); + struct scatterlist *sg; + unsigned int i, n, avail, uninitialized_var(prev), total_sg; + int head; + + START_USE(vq); BUG_ON(data == NULL); - BUG_ON(out + in > vq->vring.num); - BUG_ON(out + in == 0); - START_USE(vq); + if (unlikely(vq->broken)) { + END_USE(vq); + return -EIO; + } + +#ifdef DEBUG + { + ktime_t now = ktime_get(); + + /* No kick or get, with .1 second between? Warn. */ + if (vq->last_add_time_valid) + WARN_ON(ktime_to_ms(ktime_sub(now, vq->last_add_time)) + > 100); + vq->last_add_time = now; + vq->last_add_time_valid = true; + } +#endif + + total_sg = total_in + total_out; + + /* If the host supports indirect descriptor tables, and we have multiple + * buffers, then go indirect. FIXME: tune this threshold */ + if (vq->indirect && total_sg > 1 && vq->vq.num_free) { + head = vring_add_indirect(vq, sgs, next, total_sg, total_out, + total_in, + out_sgs, in_sgs, gfp); + if (likely(head >= 0)) + goto add_head; + } + + BUG_ON(total_sg > vq->vring.num); + BUG_ON(total_sg == 0); - if (vq->num_free < out + in) { + if (vq->vq.num_free < total_sg) { pr_debug("Can't add buf len %i - avail = %i\n", - out + in, vq->num_free); - /* We notify *even if* VRING_USED_F_NO_NOTIFY is set here. */ - vq->notify(&vq->vq); + total_sg, vq->vq.num_free); + /* FIXME: for historical reasons, we force a notify here if + * there are outgoing parts to the buffer. Presumably the + * host should service the ring ASAP. */ + if (out_sgs) + vq->notify(&vq->vq); END_USE(vq); return -ENOSPC; } /* We're about to use some buffers from the free list. */ - vq->num_free -= out + in; - - head = vq->free_head; - for (i = vq->free_head; out; i = vq->vring.desc[i].next, out--) { - vq->vring.desc[i].flags = VRING_DESC_F_NEXT; - vq->vring.desc[i].addr = sg_phys(sg); - vq->vring.desc[i].len = sg->length; - prev = i; - sg++; + vq->vq.num_free -= total_sg; + + head = i = vq->free_head; + for (n = 0; n < out_sgs; n++) { + for (sg = sgs[n]; sg; sg = next(sg, &total_out)) { + vq->vring.desc[i].flags = VRING_DESC_F_NEXT; + vq->vring.desc[i].addr = sg_phys(sg); + vq->vring.desc[i].len = sg->length; + prev = i; + i = vq->vring.desc[i].next; + } } - for (; in; i = vq->vring.desc[i].next, in--) { - vq->vring.desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE; - vq->vring.desc[i].addr = sg_phys(sg); - vq->vring.desc[i].len = sg->length; - prev = i; - sg++; + for (; n < (out_sgs + in_sgs); n++) { + for (sg = sgs[n]; sg; sg = next(sg, &total_in)) { + vq->vring.desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE; + vq->vring.desc[i].addr = sg_phys(sg); + vq->vring.desc[i].len = sg->length; + prev = i; + i = vq->vring.desc[i].next; + } } /* Last one doesn't continue. */ vq->vring.desc[prev].flags &= ~VRING_DESC_F_NEXT; @@ -117,39 +277,203 @@ static int vring_add_buf(struct virtqueue *_vq, /* Update free pointer */ vq->free_head = i; +add_head: /* Set token. */ vq->data[head] = data; /* Put entry in available array (but don't update avail->idx until they - * do sync). FIXME: avoid modulus here? */ - avail = (vq->vring.avail->idx + vq->num_added++) % vq->vring.num; + * do sync). */ + avail = (vq->vring.avail->idx & (vq->vring.num-1)); vq->vring.avail->ring[avail] = head; + /* Descriptors and available array need to be set before we expose the + * new available array entries. */ + virtio_wmb(vq->weak_barriers); + vq->vring.avail->idx++; + vq->num_added++; + + /* This is very unlikely, but theoretically possible. Kick + * just in case. */ + if (unlikely(vq->num_added == (1 << 16) - 1)) + virtqueue_kick(_vq); + pr_debug("Added buffer head %i to %p\n", head, vq); END_USE(vq); + return 0; } -static void vring_kick(struct virtqueue *_vq) +/** + * virtqueue_add_sgs - expose buffers to other end + * @vq: the struct virtqueue we're talking about. + * @sgs: array of terminated scatterlists. + * @out_num: the number of scatterlists readable by other side + * @in_num: the number of scatterlists which are writable (after readable ones) + * @data: the token identifying the buffer. + * @gfp: how to do memory allocations (if necessary). + * + * Caller must ensure we don't call this with other virtqueue operations + * at the same time (except where noted). + * + * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). + */ +int virtqueue_add_sgs(struct virtqueue *_vq, + struct scatterlist *sgs[], + unsigned int out_sgs, + unsigned int in_sgs, + void *data, + gfp_t gfp) +{ + unsigned int i, total_out, total_in; + + /* Count them first. */ + for (i = total_out = total_in = 0; i < out_sgs; i++) { + struct scatterlist *sg; + for (sg = sgs[i]; sg; sg = sg_next(sg)) + total_out++; + } + for (; i < out_sgs + in_sgs; i++) { + struct scatterlist *sg; + for (sg = sgs[i]; sg; sg = sg_next(sg)) + total_in++; + } + return virtqueue_add(_vq, sgs, sg_next_chained, + total_out, total_in, out_sgs, in_sgs, data, gfp); +} +EXPORT_SYMBOL_GPL(virtqueue_add_sgs); + +/** + * virtqueue_add_outbuf - expose output buffers to other end + * @vq: the struct virtqueue we're talking about. + * @sgs: array of scatterlists (need not be terminated!) + * @num: the number of scatterlists readable by other side + * @data: the token identifying the buffer. + * @gfp: how to do memory allocations (if necessary). + * + * Caller must ensure we don't call this with other virtqueue operations + * at the same time (except where noted). + * + * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). + */ +int virtqueue_add_outbuf(struct virtqueue *vq, + struct scatterlist sg[], unsigned int num, + void *data, + gfp_t gfp) +{ + return virtqueue_add(vq, &sg, sg_next_arr, num, 0, 1, 0, data, gfp); +} +EXPORT_SYMBOL_GPL(virtqueue_add_outbuf); + +/** + * virtqueue_add_inbuf - expose input buffers to other end + * @vq: the struct virtqueue we're talking about. + * @sgs: array of scatterlists (need not be terminated!) + * @num: the number of scatterlists writable by other side + * @data: the token identifying the buffer. + * @gfp: how to do memory allocations (if necessary). + * + * Caller must ensure we don't call this with other virtqueue operations + * at the same time (except where noted). + * + * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). + */ +int virtqueue_add_inbuf(struct virtqueue *vq, + struct scatterlist sg[], unsigned int num, + void *data, + gfp_t gfp) +{ + return virtqueue_add(vq, &sg, sg_next_arr, 0, num, 0, 1, data, gfp); +} +EXPORT_SYMBOL_GPL(virtqueue_add_inbuf); + +/** + * virtqueue_kick_prepare - first half of split virtqueue_kick call. + * @vq: the struct virtqueue + * + * Instead of virtqueue_kick(), you can do: + * if (virtqueue_kick_prepare(vq)) + * virtqueue_notify(vq); + * + * This is sometimes useful because the virtqueue_kick_prepare() needs + * to be serialized, but the actual virtqueue_notify() call does not. + */ +bool virtqueue_kick_prepare(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); + u16 new, old; + bool needs_kick; + START_USE(vq); - /* Descriptors and available array need to be set before we expose the - * new available array entries. */ - wmb(); + /* We need to expose available array entries before checking avail + * event. */ + virtio_mb(vq->weak_barriers); - vq->vring.avail->idx += vq->num_added; + old = vq->vring.avail->idx - vq->num_added; + new = vq->vring.avail->idx; vq->num_added = 0; - /* Need to update avail index before checking if we should notify */ - mb(); - - if (!(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY)) - /* Prod other side to tell it about changes. */ - vq->notify(&vq->vq); +#ifdef DEBUG + if (vq->last_add_time_valid) { + WARN_ON(ktime_to_ms(ktime_sub(ktime_get(), + vq->last_add_time)) > 100); + } + vq->last_add_time_valid = false; +#endif + if (vq->event) { + needs_kick = vring_need_event(vring_avail_event(&vq->vring), + new, old); + } else { + needs_kick = !(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY); + } END_USE(vq); + return needs_kick; +} +EXPORT_SYMBOL_GPL(virtqueue_kick_prepare); + +/** + * virtqueue_notify - second half of split virtqueue_kick call. + * @vq: the struct virtqueue + * + * This does not need to be serialized. + * + * Returns false if host notify failed or queue is broken, otherwise true. + */ +bool virtqueue_notify(struct virtqueue *_vq) +{ + struct vring_virtqueue *vq = to_vvq(_vq); + + if (unlikely(vq->broken)) + return false; + + /* Prod other side to tell it about changes. */ + if (!vq->notify(_vq)) { + vq->broken = true; + return false; + } + return true; +} +EXPORT_SYMBOL_GPL(virtqueue_notify); + +/** + * virtqueue_kick - update after add_buf + * @vq: the struct virtqueue + * + * After one or more virtqueue_add_* calls, invoke this to kick + * the other side. + * + * Caller must ensure we don't call this with other virtqueue + * operations at the same time (except where noted). + * + * Returns false if kick failed, otherwise true. + */ +bool virtqueue_kick(struct virtqueue *vq) +{ + if (virtqueue_kick_prepare(vq)) + return virtqueue_notify(vq); + return true; } +EXPORT_SYMBOL_GPL(virtqueue_kick); static void detach_buf(struct vring_virtqueue *vq, unsigned int head) { @@ -160,15 +484,20 @@ static void detach_buf(struct vring_virtqueue *vq, unsigned int head) /* Put back on free list: find end */ i = head; + + /* Free the indirect table */ + if (vq->vring.desc[i].flags & VRING_DESC_F_INDIRECT) + kfree(phys_to_virt(vq->vring.desc[i].addr)); + while (vq->vring.desc[i].flags & VRING_DESC_F_NEXT) { i = vq->vring.desc[i].next; - vq->num_free++; + vq->vq.num_free++; } vq->vring.desc[i].next = vq->free_head; vq->free_head = head; /* Plus final descriptor */ - vq->num_free++; + vq->vq.num_free++; } static inline bool more_used(const struct vring_virtqueue *vq) @@ -176,22 +505,48 @@ static inline bool more_used(const struct vring_virtqueue *vq) return vq->last_used_idx != vq->vring.used->idx; } -static void *vring_get_buf(struct virtqueue *_vq, unsigned int *len) +/** + * virtqueue_get_buf - get the next used buffer + * @vq: the struct virtqueue we're talking about. + * @len: the length written into the buffer + * + * If the driver wrote data into the buffer, @len will be set to the + * amount written. This means you don't need to clear the buffer + * beforehand to ensure there's no data leakage in the case of short + * writes. + * + * Caller must ensure we don't call this with other virtqueue + * operations at the same time (except where noted). + * + * Returns NULL if there are no used buffers, or the "data" token + * handed to virtqueue_add_*(). + */ +void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) { struct vring_virtqueue *vq = to_vvq(_vq); void *ret; unsigned int i; + u16 last_used; START_USE(vq); + if (unlikely(vq->broken)) { + END_USE(vq); + return NULL; + } + if (!more_used(vq)) { pr_debug("No more buffers in queue\n"); END_USE(vq); return NULL; } - i = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].id; - *len = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].len; + /* Only get used array entries after they have been exposed by host. */ + virtio_rmb(vq->weak_barriers); + + last_used = (vq->last_used_idx & (vq->vring.num - 1)); + i = vq->vring.used->ring[last_used].id; + *len = vq->vring.used->ring[last_used].len; if (unlikely(i >= vq->vring.num)) { BAD_RING(vq, "id %u out of range\n", i); @@ -206,32 +561,138 @@ static void *vring_get_buf(struct virtqueue *_vq, unsigned int *len) ret = vq->data[i]; detach_buf(vq, i); vq->last_used_idx++; + /* If we expect an interrupt for the next entry, tell host + * by writing event index and flush out the write before + * the read in the next get_buf call. */ + if (!(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) { + vring_used_event(&vq->vring) = vq->last_used_idx; + virtio_mb(vq->weak_barriers); + } + +#ifdef DEBUG + vq->last_add_time_valid = false; +#endif + END_USE(vq); return ret; } +EXPORT_SYMBOL_GPL(virtqueue_get_buf); -static void vring_disable_cb(struct virtqueue *_vq) +/** + * virtqueue_disable_cb - disable callbacks + * @vq: the struct virtqueue we're talking about. + * + * Note that this is not necessarily synchronous, hence unreliable and only + * useful as an optimization. + * + * Unlike other operations, this need not be serialized. + */ +void virtqueue_disable_cb(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); - START_USE(vq); - BUG_ON(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT); vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT; +} +EXPORT_SYMBOL_GPL(virtqueue_disable_cb); + +/** + * virtqueue_enable_cb_prepare - restart callbacks after disable_cb + * @vq: the struct virtqueue we're talking about. + * + * This re-enables callbacks; it returns current queue state + * in an opaque unsigned value. This value should be later tested by + * virtqueue_poll, to detect a possible race between the driver checking for + * more work, and enabling callbacks. + * + * Caller must ensure we don't call this with other virtqueue + * operations at the same time (except where noted). + */ +unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq) +{ + struct vring_virtqueue *vq = to_vvq(_vq); + u16 last_used_idx; + + START_USE(vq); + + /* We optimistically turn back on interrupts, then check if there was + * more to do. */ + /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to + * either clear the flags bit or point the event index at the next + * entry. Always do both to keep code simple. */ + vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT; + vring_used_event(&vq->vring) = last_used_idx = vq->last_used_idx; END_USE(vq); + return last_used_idx; +} +EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare); + +/** + * virtqueue_poll - query pending used buffers + * @vq: the struct virtqueue we're talking about. + * @last_used_idx: virtqueue state (from call to virtqueue_enable_cb_prepare). + * + * Returns "true" if there are pending used buffers in the queue. + * + * This does not need to be serialized. + */ +bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx) +{ + struct vring_virtqueue *vq = to_vvq(_vq); + + virtio_mb(vq->weak_barriers); + return (u16)last_used_idx != vq->vring.used->idx; +} +EXPORT_SYMBOL_GPL(virtqueue_poll); + +/** + * virtqueue_enable_cb - restart callbacks after disable_cb. + * @vq: the struct virtqueue we're talking about. + * + * This re-enables callbacks; it returns "false" if there are pending + * buffers in the queue, to detect a possible race between the driver + * checking for more work, and enabling callbacks. + * + * Caller must ensure we don't call this with other virtqueue + * operations at the same time (except where noted). + */ +bool virtqueue_enable_cb(struct virtqueue *_vq) +{ + unsigned last_used_idx = virtqueue_enable_cb_prepare(_vq); + return !virtqueue_poll(_vq, last_used_idx); } +EXPORT_SYMBOL_GPL(virtqueue_enable_cb); -static bool vring_enable_cb(struct virtqueue *_vq) +/** + * virtqueue_enable_cb_delayed - restart callbacks after disable_cb. + * @vq: the struct virtqueue we're talking about. + * + * This re-enables callbacks but hints to the other side to delay + * interrupts until most of the available buffers have been processed; + * it returns "false" if there are many pending buffers in the queue, + * to detect a possible race between the driver checking for more work, + * and enabling callbacks. + * + * Caller must ensure we don't call this with other virtqueue + * operations at the same time (except where noted). + */ +bool virtqueue_enable_cb_delayed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); + u16 bufs; START_USE(vq); - BUG_ON(!(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)); /* We optimistically turn back on interrupts, then check if there was * more to do. */ + /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to + * either clear the flags bit or point the event index at the next + * entry. Always do both to keep code simple. */ vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT; - mb(); - if (unlikely(more_used(vq))) { + /* TODO: tune this threshold */ + bufs = (u16)(vq->vring.avail->idx - vq->last_used_idx) * 3 / 4; + vring_used_event(&vq->vring) = vq->last_used_idx + bufs; + virtio_mb(vq->weak_barriers); + if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) { END_USE(vq); return false; } @@ -239,6 +700,41 @@ static bool vring_enable_cb(struct virtqueue *_vq) END_USE(vq); return true; } +EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed); + +/** + * virtqueue_detach_unused_buf - detach first unused buffer + * @vq: the struct virtqueue we're talking about. + * + * Returns NULL or the "data" token handed to virtqueue_add_*(). + * This is not valid on an active queue; it is useful only for device + * shutdown. + */ +void *virtqueue_detach_unused_buf(struct virtqueue *_vq) +{ + struct vring_virtqueue *vq = to_vvq(_vq); + unsigned int i; + void *buf; + + START_USE(vq); + + for (i = 0; i < vq->vring.num; i++) { + if (!vq->data[i]) + continue; + /* detach_buf clears data, so grab it now. */ + buf = vq->data[i]; + detach_buf(vq, i); + vq->vring.avail->idx--; + END_USE(vq); + return buf; + } + /* That should have freed everything. */ + BUG_ON(vq->vq.num_free != vq->vring.num); + + END_USE(vq); + return NULL; +} +EXPORT_SYMBOL_GPL(virtqueue_detach_unused_buf); irqreturn_t vring_interrupt(int irq, void *_vq) { @@ -252,13 +748,6 @@ irqreturn_t vring_interrupt(int irq, void *_vq) if (unlikely(vq->broken)) return IRQ_HANDLED; - /* Other side may have missed us turning off the interrupt, - * but we should preserve disable semantic for virtio users. */ - if (unlikely(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) { - pr_debug("virtqueue interrupt after disable for %p\n", vq); - return IRQ_HANDLED; - } - pr_debug("virtqueue callback for %p (%p)\n", vq, vq->vq.callback); if (vq->vq.callback) vq->vq.callback(&vq->vq); @@ -267,19 +756,15 @@ irqreturn_t vring_interrupt(int irq, void *_vq) } EXPORT_SYMBOL_GPL(vring_interrupt); -static struct virtqueue_ops vring_vq_ops = { - .add_buf = vring_add_buf, - .get_buf = vring_get_buf, - .kick = vring_kick, - .disable_cb = vring_disable_cb, - .enable_cb = vring_enable_cb, -}; - -struct virtqueue *vring_new_virtqueue(unsigned int num, +struct virtqueue *vring_new_virtqueue(unsigned int index, + unsigned int num, + unsigned int vring_align, struct virtio_device *vdev, + bool weak_barriers, void *pages, - void (*notify)(struct virtqueue *), - void (*callback)(struct virtqueue *)) + bool (*notify)(struct virtqueue *), + void (*callback)(struct virtqueue *), + const char *name) { struct vring_virtqueue *vq; unsigned int i; @@ -294,27 +779,37 @@ struct virtqueue *vring_new_virtqueue(unsigned int num, if (!vq) return NULL; - vring_init(&vq->vring, num, pages, PAGE_SIZE); + vring_init(&vq->vring, num, pages, vring_align); vq->vq.callback = callback; vq->vq.vdev = vdev; - vq->vq.vq_ops = &vring_vq_ops; + vq->vq.name = name; + vq->vq.num_free = num; + vq->vq.index = index; vq->notify = notify; + vq->weak_barriers = weak_barriers; vq->broken = false; vq->last_used_idx = 0; vq->num_added = 0; + list_add_tail(&vq->vq.list, &vdev->vqs); #ifdef DEBUG vq->in_use = false; + vq->last_add_time_valid = false; #endif + vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC); + vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); + /* No callback? Tell other side not to bother us. */ if (!callback) vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT; /* Put everything in free lists. */ - vq->num_free = num; vq->free_head = 0; - for (i = 0; i < num-1; i++) + for (i = 0; i < num-1; i++) { vq->vring.desc[i].next = i+1; + vq->data[i] = NULL; + } + vq->data[i] = NULL; return &vq->vq; } @@ -322,8 +817,67 @@ EXPORT_SYMBOL_GPL(vring_new_virtqueue); void vring_del_virtqueue(struct virtqueue *vq) { + list_del(&vq->list); kfree(to_vvq(vq)); } EXPORT_SYMBOL_GPL(vring_del_virtqueue); +/* Manipulates transport-specific feature bits. */ +void vring_transport_features(struct virtio_device *vdev) +{ + unsigned int i; + + for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++) { + switch (i) { + case VIRTIO_RING_F_INDIRECT_DESC: + break; + case VIRTIO_RING_F_EVENT_IDX: + break; + default: + /* We don't understand this bit. */ + clear_bit(i, vdev->features); + } + } +} +EXPORT_SYMBOL_GPL(vring_transport_features); + +/** + * virtqueue_get_vring_size - return the size of the virtqueue's vring + * @vq: the struct virtqueue containing the vring of interest. + * + * Returns the size of the vring. This is mainly used for boasting to + * userspace. Unlike other operations, this need not be serialized. + */ +unsigned int virtqueue_get_vring_size(struct virtqueue *_vq) +{ + + struct vring_virtqueue *vq = to_vvq(_vq); + + return vq->vring.num; +} +EXPORT_SYMBOL_GPL(virtqueue_get_vring_size); + +bool virtqueue_is_broken(struct virtqueue *_vq) +{ + struct vring_virtqueue *vq = to_vvq(_vq); + + return vq->broken; +} +EXPORT_SYMBOL_GPL(virtqueue_is_broken); + +/* + * This should prevent the device from being used, allowing drivers to + * recover. You may need to grab appropriate locks to flush. + */ +void virtio_break_device(struct virtio_device *dev) +{ + struct virtqueue *_vq; + + list_for_each_entry(_vq, &dev->vqs, list) { + struct vring_virtqueue *vq = to_vvq(_vq); + vq->broken = true; + } +} +EXPORT_SYMBOL_GPL(virtio_break_device); + MODULE_LICENSE("GPL"); |