From a9a0fef779074838230e04a322fd2bdc921f4f4f Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 18 Mar 2013 13:22:19 +1030 Subject: virtio_ring: expose virtio barriers for use in vringh. The host side of ring needs this logic too. Signed-off-by: Rusty Russell --- drivers/virtio/virtio_ring.c | 33 ++++++--------------------------- 1 file changed, 6 insertions(+), 27 deletions(-) (limited to 'drivers/virtio') diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index ffd7e7da5d3b..245177c286ae 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -24,27 +24,6 @@ #include #include -/* virtio guest is communicating with a virtual "device" that actually runs on - * a host processor. Memory barriers are used to control SMP effects. */ -#ifdef CONFIG_SMP -/* Where possible, use SMP barriers which are more lightweight than mandatory - * barriers, because mandatory barriers control MMIO effects on accesses - * through relaxed memory I/O windows (which virtio-pci does not use). */ -#define virtio_mb(vq) \ - do { if ((vq)->weak_barriers) smp_mb(); else mb(); } while(0) -#define virtio_rmb(vq) \ - do { if ((vq)->weak_barriers) smp_rmb(); else rmb(); } while(0) -#define virtio_wmb(vq) \ - do { if ((vq)->weak_barriers) smp_wmb(); else wmb(); } while(0) -#else -/* We must force memory ordering even if guest is UP since host could be - * running on another CPU, but SMP barriers are defined to barrier() in that - * configuration. So fall back to mandatory barriers instead. */ -#define virtio_mb(vq) mb() -#define virtio_rmb(vq) rmb() -#define virtio_wmb(vq) wmb() -#endif - #ifdef DEBUG /* For development, we want to crash whenever the ring is screwed. */ #define BAD_RING(_vq, fmt, args...) \ @@ -276,7 +255,7 @@ add_head: /* Descriptors and available array need to be set before we expose the * new available array entries. */ - virtio_wmb(vq); + virtio_wmb(vq->weak_barriers); vq->vring.avail->idx++; vq->num_added++; @@ -312,7 +291,7 @@ bool virtqueue_kick_prepare(struct virtqueue *_vq) START_USE(vq); /* We need to expose available array entries before checking avail * event. */ - virtio_mb(vq); + virtio_mb(vq->weak_barriers); old = vq->vring.avail->idx - vq->num_added; new = vq->vring.avail->idx; @@ -436,7 +415,7 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) } /* Only get used array entries after they have been exposed by host. */ - virtio_rmb(vq); + virtio_rmb(vq->weak_barriers); last_used = (vq->last_used_idx & (vq->vring.num - 1)); i = vq->vring.used->ring[last_used].id; @@ -460,7 +439,7 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) * 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); + virtio_mb(vq->weak_barriers); } #ifdef DEBUG @@ -513,7 +492,7 @@ bool virtqueue_enable_cb(struct virtqueue *_vq) * entry. Always do both to keep code simple. */ vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT; vring_used_event(&vq->vring) = vq->last_used_idx; - virtio_mb(vq); + virtio_mb(vq->weak_barriers); if (unlikely(more_used(vq))) { END_USE(vq); return false; @@ -553,7 +532,7 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_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); + virtio_mb(vq->weak_barriers); if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) { END_USE(vq); return false; -- cgit v1.2.3 From 13816c768d46586e925b22736992258d6105ad2c Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 20 Mar 2013 15:37:09 +1030 Subject: virtio_ring: virtqueue_add_sgs, to add multiple sgs. virtio_scsi can really use this, to avoid the current hack of copying the whole sg array. Some other things get slightly neater, too. This causes a slowdown in virtqueue_add_buf(), which is implemented as a wrapper. This is addressed in the next patches. for i in `seq 50`; do /usr/bin/time -f 'Wall time:%e' ./vringh_test --indirect --eventidx --parallel --fast-vringh; done 2>&1 | stats --trim-outliers: Before: Using CPUS 0 and 3 Guest: notified 0, pinged 39009-39063(39062) Host: notified 39009-39063(39062), pinged 0 Wall time:1.700000-1.950000(1.723542) After: Using CPUS 0 and 3 Guest: notified 0, pinged 39062-39063(39063) Host: notified 39062-39063(39063), pinged 0 Wall time:1.760000-2.220000(1.789167) Signed-off-by: Rusty Russell Reviewed-by: Wanlong Gao Reviewed-by: Asias He --- drivers/virtio/virtio_ring.c | 220 ++++++++++++++++++++++++++++----------- include/linux/virtio.h | 7 ++ tools/virtio/linux/scatterlist.h | 16 +++ tools/virtio/linux/virtio.h | 7 ++ 4 files changed, 187 insertions(+), 63 deletions(-) (limited to 'drivers/virtio') diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 245177c286ae..a78ad459cc85 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -98,16 +98,36 @@ struct vring_virtqueue #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq) +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 int vring_add_indirect(struct vring_virtqueue *vq, - struct scatterlist sg[], - unsigned int out, - unsigned int in, - gfp_t gfp) +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; - int i; + struct scatterlist *sg; + int i, n; /* * We require lowmem mappings for the descriptors because @@ -116,25 +136,31 @@ static int vring_add_indirect(struct vring_virtqueue *vq, */ gfp &= ~(__GFP_HIGHMEM | __GFP_HIGH); - desc = kmalloc((out + in) * sizeof(struct vring_desc), gfp); + desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp); if (!desc) return -ENOMEM; - /* Transfer entries from the sg list into the indirect page */ - for (i = 0; i < out; i++) { - desc[i].flags = VRING_DESC_F_NEXT; - desc[i].addr = sg_phys(sg); - desc[i].len = sg->length; - desc[i].next = i+1; - sg++; + /* 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 (; i < (out + in); i++) { - 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; - sg++; + 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; @@ -155,29 +181,20 @@ static int vring_add_indirect(struct vring_virtqueue *vq, return head; } -/** - * virtqueue_add_buf - expose buffer to other end - * @vq: the struct virtqueue we're talking about. - * @sg: the description of the buffer(s). - * @out_num: the number of sg readable by other side - * @in_num: the number of sg 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). - */ -int virtqueue_add_buf(struct virtqueue *_vq, - struct scatterlist sg[], - unsigned int out, - unsigned int in, - void *data, - gfp_t gfp) +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, uninitialized_var(prev); + struct scatterlist *sg; + unsigned int i, n, avail, uninitialized_var(prev), total_sg; int head; START_USE(vq); @@ -197,46 +214,54 @@ int virtqueue_add_buf(struct virtqueue *_vq, } #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 && (out + in) > 1 && vq->vq.num_free) { - head = vring_add_indirect(vq, sg, out, in, gfp); + 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(out + in > vq->vring.num); - BUG_ON(out + in == 0); + BUG_ON(total_sg > vq->vring.num); + BUG_ON(total_sg == 0); - if (vq->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->vq.num_free); + 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) + if (out_sgs) vq->notify(&vq->vq); END_USE(vq); return -ENOSPC; } /* We're about to use some buffers from the free list. */ - vq->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; @@ -269,8 +294,77 @@ add_head: return 0; } + +/** + * virtqueue_add_buf - expose buffer to other end + * @vq: the struct virtqueue we're talking about. + * @sg: the description of the buffer(s). + * @out_num: the number of sg readable by other side + * @in_num: the number of sg 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). + */ +int virtqueue_add_buf(struct virtqueue *_vq, + struct scatterlist sg[], + unsigned int out, + unsigned int in, + void *data, + gfp_t gfp) +{ + struct scatterlist *sgs[2]; + + sgs[0] = sg; + sgs[1] = sg + out; + + return virtqueue_add(_vq, sgs, sg_next_arr, + out, in, out ? 1 : 0, in ? 1 : 0, data, gfp); +} EXPORT_SYMBOL_GPL(virtqueue_add_buf); +/** + * 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). + */ +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_kick_prepare - first half of split virtqueue_kick call. * @vq: the struct virtqueue diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 5d5b3abc283d..ac80288b2920 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -41,6 +41,13 @@ int virtqueue_add_buf(struct virtqueue *vq, void *data, gfp_t gfp); +int virtqueue_add_sgs(struct virtqueue *vq, + struct scatterlist *sgs[], + unsigned int out_sgs, + unsigned int in_sgs, + void *data, + gfp_t gfp); + void virtqueue_kick(struct virtqueue *vq); bool virtqueue_kick_prepare(struct virtqueue *vq); diff --git a/tools/virtio/linux/scatterlist.h b/tools/virtio/linux/scatterlist.h index b2cf7d0f6133..68c9e2adc996 100644 --- a/tools/virtio/linux/scatterlist.h +++ b/tools/virtio/linux/scatterlist.h @@ -125,6 +125,22 @@ static inline void sg_mark_end(struct scatterlist *sg) sg->page_link &= ~0x01; } +/** + * sg_unmark_end - Undo setting the end of the scatterlist + * @sg: SG entryScatterlist + * + * Description: + * Removes the termination marker from the given entry of the scatterlist. + * + **/ +static inline void sg_unmark_end(struct scatterlist *sg) +{ +#ifdef CONFIG_DEBUG_SG + BUG_ON(sg->sg_magic != SG_MAGIC); +#endif + sg->page_link &= ~0x02; +} + static inline struct scatterlist *sg_next(struct scatterlist *sg) { #ifdef CONFIG_DEBUG_SG diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h index e4af6591f5ff..5fa612ad932c 100644 --- a/tools/virtio/linux/virtio.h +++ b/tools/virtio/linux/virtio.h @@ -56,6 +56,13 @@ int virtqueue_add_buf(struct virtqueue *vq, void *data, gfp_t gfp); +int virtqueue_add_sgs(struct virtqueue *vq, + struct scatterlist *sgs[], + unsigned int out_sgs, + unsigned int in_sgs, + void *data, + gfp_t gfp); + void virtqueue_kick(struct virtqueue *vq); void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len); -- cgit v1.2.3 From 282edb36499042a92b71f052f51754ae7ed936e4 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 20 Mar 2013 15:44:26 +1030 Subject: virtio_ring: virtqueue_add_outbuf / virtqueue_add_inbuf. These are specialized versions of virtqueue_add_buf(), which cover over 80% of cases and are far clearer. In particular, the scatterlists passed to these functions don't have to be clean (ie. we ignore end markers). Signed-off-by: Rusty Russell --- drivers/virtio/virtio_ring.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/virtio.h | 10 ++++++++++ 2 files changed, 54 insertions(+) (limited to 'drivers/virtio') diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index a78ad459cc85..5217baf5528c 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -365,6 +365,50 @@ int virtqueue_add_sgs(struct virtqueue *_vq, } 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). + */ +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). + */ +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 diff --git a/include/linux/virtio.h b/include/linux/virtio.h index ac80288b2920..833f17b6a743 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -41,6 +41,16 @@ int virtqueue_add_buf(struct virtqueue *vq, void *data, gfp_t gfp); +int virtqueue_add_outbuf(struct virtqueue *vq, + struct scatterlist sg[], unsigned int num, + void *data, + gfp_t gfp); + +int virtqueue_add_inbuf(struct virtqueue *vq, + struct scatterlist sg[], unsigned int num, + void *data, + gfp_t gfp); + int virtqueue_add_sgs(struct virtqueue *vq, struct scatterlist *sgs[], unsigned int out_sgs, -- cgit v1.2.3 From 92549abc6a6573294fc1bb9330db8b52dedfea5f Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 20 Mar 2013 15:44:30 +1030 Subject: virtio_balloon: use simplified virtqueue accessors. We never add buffers with input and output parts, so use the new accessors. Signed-off-by: Rusty Russell --- drivers/virtio/virtio_balloon.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/virtio') diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 8dab163c5ef0..bd3ae324a1a2 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -108,7 +108,7 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq) sg_init_one(&sg, vb->pfns, sizeof(vb->pfns[0]) * vb->num_pfns); /* We should always be able to add one buffer to an empty queue. */ - if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0) + if (virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL) < 0) BUG(); virtqueue_kick(vq); @@ -256,7 +256,7 @@ static void stats_handle_request(struct virtio_balloon *vb) if (!virtqueue_get_buf(vq, &len)) return; sg_init_one(&sg, vb->stats, sizeof(vb->stats)); - if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0) + if (virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL) < 0) BUG(); virtqueue_kick(vq); } @@ -341,7 +341,7 @@ static int init_vqs(struct virtio_balloon *vb) * use it to signal us later. */ sg_init_one(&sg, vb->stats, sizeof vb->stats); - if (virtqueue_add_buf(vb->stats_vq, &sg, 1, 0, vb, GFP_KERNEL) + if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL) < 0) BUG(); virtqueue_kick(vb->stats_vq); -- cgit v1.2.3