Received: by 10.192.165.148 with SMTP id m20csp272834imm; Tue, 24 Apr 2018 22:17:28 -0700 (PDT) X-Google-Smtp-Source: AB8JxZqAR9bs1VhbVnOlvEw/bgyvVtby6pZ5qDsnJIwU0HjqXciuUC20rfsTEiDfePBCtkUCHtVe X-Received: by 10.99.56.90 with SMTP id h26mr2529984pgn.147.1524633448596; Tue, 24 Apr 2018 22:17:28 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1524633448; cv=none; d=google.com; s=arc-20160816; b=nIZHHWb+yZxKk0l2OtvdRc/66uOYDuYwFNOY4g9BjRWGp9o5ne/T8WpWUwSocqEycG paGxR/aClcZ+xYF2n66X7Lm4OoARQe0kRucmwnX+/UWBaxtCEonufCtCmWmq0tu2CV/j HcfCVW2jGII1U0fHFUnD2jUUA2uV2lXqMtJ7ueOuQ4VE2j21clXsgSV/FgqYa3Gngti7 zPJatBNly0TEfryGts5yeviHvA8j0wfYC5Psful6MtiAjfMufSfQ7UBBcCqDK5ep7lgP GKlVFVTUTxOZs6Jyy/s7sfnmuf4yvQPf4i6KZica15gkQRKYqU+0yEiUS+mD8ptkiXuP LYXQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:references:in-reply-to:message-id:date :subject:cc:to:from:arc-authentication-results; bh=WLZ32RfBXvvvBDj7sWHAsuVXJGmkpVLz1SXNOxuS4Ek=; b=zOLatpSctRaNdO3RqtG99uBi1KyWfTxwCxqnaqZJpS0dQuHCwBffJ7nK+8aXV2+2X9 vUFviNknQ4zwtbQiJzA/HOVQ+dxGT8JRc17GMcNy/aU8TVYvcctyWtIbNkk1PiadQwYt xDMv/9LICdasGIrhtx8QRWvBkYImk9eGgucvI+Zm/6Hl43F5LWnNV3Aydq41aBWylsLC C+OErPyRrI3XQZ/f3f8pLzbVtwaPDvWhbqtLFTR7P8FgSKUi+4uAI16cBZdzSCY2P3LF SrDy/Di1bC/lpt18KeaQYK7v3xlID88Gb0/tRox/jUW6CWW8I7u7N8Nv6cDvZq4YPkPz zEbg== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id n3si12817497pgd.534.2018.04.24.22.17.00; Tue, 24 Apr 2018 22:17:28 -0700 (PDT) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751376AbeDYFPc (ORCPT + 99 others); Wed, 25 Apr 2018 01:15:32 -0400 Received: from mga06.intel.com ([134.134.136.31]:64024 "EHLO mga06.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751280AbeDYFP0 (ORCPT ); Wed, 25 Apr 2018 01:15:26 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga006.fm.intel.com ([10.253.24.20]) by orsmga104.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 24 Apr 2018 22:15:25 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.49,325,1520924400"; d="scan'208";a="223170581" Received: from debian.sh.intel.com ([10.67.104.164]) by fmsmga006.fm.intel.com with ESMTP; 24 Apr 2018 22:15:24 -0700 From: Tiwei Bie To: mst@redhat.com, jasowang@redhat.com, virtualization@lists.linux-foundation.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org Cc: wexu@redhat.com, jfreimann@redhat.com, tiwei.bie@intel.com Subject: [RFC v3 3/5] virtio_ring: add packed ring support Date: Wed, 25 Apr 2018 13:15:48 +0800 Message-Id: <20180425051550.24342-4-tiwei.bie@intel.com> X-Mailer: git-send-email 2.11.0 In-Reply-To: <20180425051550.24342-1-tiwei.bie@intel.com> References: <20180425051550.24342-1-tiwei.bie@intel.com> Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This commit introduces the basic support (without EVENT_IDX) for packed ring. Signed-off-by: Tiwei Bie --- drivers/virtio/virtio_ring.c | 444 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 434 insertions(+), 10 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index e164822ca66e..0181e93897be 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -58,7 +58,8 @@ struct vring_desc_state { void *data; /* Data for callback. */ - struct vring_desc *indir_desc; /* Indirect descriptor, if any. */ + void *indir_desc; /* Indirect descriptor, if any. */ + int num; /* Descriptor list length. */ }; struct vring_virtqueue { @@ -142,6 +143,16 @@ struct vring_virtqueue { #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq) +static inline bool virtqueue_use_indirect(struct virtqueue *_vq, + unsigned int total_sg) +{ + struct vring_virtqueue *vq = to_vvq(_vq); + + /* If the host supports indirect descriptor tables, and we have multiple + * buffers, then go indirect. FIXME: tune this threshold */ + return (vq->indirect && total_sg > 1 && vq->vq.num_free); +} + /* * Modern virtio devices have feature bits to specify whether they need a * quirk and bypass the IOMMU. If not there, just use the DMA API. @@ -327,9 +338,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq, head = vq->free_head; - /* 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) + if (virtqueue_use_indirect(_vq, total_sg)) desc = alloc_indirect_split(_vq, total_sg, gfp); else { desc = NULL; @@ -741,6 +750,49 @@ static inline unsigned vring_size_packed(unsigned int num, unsigned long align) & ~(align - 1)) + sizeof(struct vring_packed_desc_event) * 2; } +static void vring_unmap_one_packed(const struct vring_virtqueue *vq, + struct vring_packed_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 struct vring_packed_desc *alloc_indirect_packed(struct virtqueue *_vq, + unsigned int total_sg, + gfp_t gfp) +{ + struct vring_packed_desc *desc; + + /* + * We require lowmem mappings for the descriptors because + * otherwise virt_to_phys will give us bogus addresses in the + * virtqueue. + */ + gfp &= ~__GFP_HIGHMEM; + + desc = kmalloc(total_sg * sizeof(struct vring_packed_desc), gfp); + + return desc; +} + static inline int virtqueue_add_packed(struct virtqueue *_vq, struct scatterlist *sgs[], unsigned int total_sg, @@ -750,47 +802,419 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, void *ctx, gfp_t gfp) { + struct vring_virtqueue *vq = to_vvq(_vq); + struct vring_packed_desc *desc; + struct scatterlist *sg; + unsigned int i, n, descs_used, uninitialized_var(prev), err_idx; + __virtio16 uninitialized_var(head_flags), flags; + int head, wrap_counter; + bool indirect; + + START_USE(vq); + + BUG_ON(data == NULL); + BUG_ON(ctx && vq->indirect); + + 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 + + BUG_ON(total_sg == 0); + + head = vq->next_avail_idx; + wrap_counter = vq->wrap_counter; + + if (virtqueue_use_indirect(_vq, total_sg)) + desc = alloc_indirect_packed(_vq, total_sg, gfp); + else { + desc = NULL; + WARN_ON_ONCE(total_sg > vq->vring_packed.num && !vq->indirect); + } + + if (desc) { + /* Use a single buffer which doesn't continue */ + indirect = true; + /* Set up rest to use this indirect table. */ + i = 0; + descs_used = 1; + } else { + indirect = false; + desc = vq->vring_packed.desc; + i = head; + descs_used = total_sg; + } + + if (vq->vq.num_free < descs_used) { + pr_debug("Can't add buf len %i - avail = %i\n", + descs_used, 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); + if (indirect) + kfree(desc); + END_USE(vq); + return -ENOSPC; + } + + for (n = 0; 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, n < out_sgs ? + DMA_TO_DEVICE : DMA_FROM_DEVICE); + if (vring_mapping_error(vq, addr)) + goto unmap_release; + + flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT | + (n < out_sgs ? 0 : VRING_DESC_F_WRITE) | + VRING_DESC_F_AVAIL(vq->wrap_counter) | + VRING_DESC_F_USED(!vq->wrap_counter)); + if (!indirect && i == head) + head_flags = flags; + else + desc[i].flags = flags; + + desc[i].addr = cpu_to_virtio64(_vq->vdev, addr); + desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length); + i++; + if (!indirect && i >= vq->vring_packed.num) { + i = 0; + vq->wrap_counter ^= 1; + } + } + } + + prev = (i > 0 ? i : vq->vring_packed.num) - 1; + desc[prev].id = cpu_to_virtio32(_vq->vdev, head); + + /* Last one doesn't continue. */ + if (total_sg == 1) + head_flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT); + else + 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_packed_desc), + DMA_TO_DEVICE); + if (vring_mapping_error(vq, addr)) + goto unmap_release; + + head_flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_INDIRECT | + VRING_DESC_F_AVAIL(wrap_counter) | + VRING_DESC_F_USED(!wrap_counter)); + vq->vring_packed.desc[head].addr = cpu_to_virtio64(_vq->vdev, + addr); + vq->vring_packed.desc[head].len = cpu_to_virtio32(_vq->vdev, + total_sg * sizeof(struct vring_packed_desc)); + vq->vring_packed.desc[head].id = cpu_to_virtio32(_vq->vdev, + head); + } + + /* We're using some buffers from the free list. */ + vq->vq.num_free -= descs_used; + + /* Update free pointer */ + if (indirect) { + n = head + 1; + if (n >= vq->vring_packed.num) { + n = 0; + vq->wrap_counter ^= 1; + } + vq->next_avail_idx = n; + } else + vq->next_avail_idx = i; + + /* Store token and indirect buffer state. */ + vq->desc_state[head].num = descs_used; + vq->desc_state[head].data = data; + if (indirect) + vq->desc_state[head].indir_desc = desc; + else + vq->desc_state[head].indir_desc = ctx; + + /* A driver MUST NOT make the first descriptor in the list + * available before all subsequent descriptors comprising + * the list are made available. */ + virtio_wmb(vq->weak_barriers); + vq->vring_packed.desc[head].flags = head_flags; + vq->num_added += descs_used; + + pr_debug("Added buffer head %i to %p\n", head, vq); + END_USE(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_packed(vq, &desc[i]); + i++; + if (!indirect && i >= vq->vring_packed.num) + i = 0; + } + + vq->wrap_counter = wrap_counter; + + if (indirect) + kfree(desc); + + END_USE(vq); return -EIO; } static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq) { - return false; + struct vring_virtqueue *vq = to_vvq(_vq); + u16 flags; + bool needs_kick; + u32 snapshot; + + START_USE(vq); + /* We need to expose the new flags value before checking notification + * suppressions. */ + virtio_mb(vq->weak_barriers); + + snapshot = *(u32 *)vq->vring_packed.device; + flags = cpu_to_virtio16(_vq->vdev, snapshot >> 16) & 0x3; + +#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 + + needs_kick = (flags != VRING_EVENT_F_DISABLE); + END_USE(vq); + return needs_kick; +} + +static void detach_buf_packed(struct vring_virtqueue *vq, unsigned int head, + void **ctx) +{ + struct vring_packed_desc *desc; + unsigned int i, j; + + /* Clear data ptr. */ + vq->desc_state[head].data = NULL; + + i = head; + + for (j = 0; j < vq->desc_state[head].num; j++) { + desc = &vq->vring_packed.desc[i]; + vring_unmap_one_packed(vq, desc); + i++; + if (i >= vq->vring_packed.num) + i = 0; + } + + vq->vq.num_free += vq->desc_state[head].num; + + if (vq->indirect) { + u32 len; + + /* Free the indirect table, if any, now that it's unmapped. */ + desc = vq->desc_state[head].indir_desc; + if (!desc) + return; + + len = virtio32_to_cpu(vq->vq.vdev, + vq->vring_packed.desc[head].len); + + for (j = 0; j < len / sizeof(struct vring_packed_desc); j++) + vring_unmap_one_packed(vq, &desc[j]); + + kfree(desc); + vq->desc_state[head].indir_desc = NULL; + } else if (ctx) { + *ctx = vq->desc_state[head].indir_desc; + } } static inline bool more_used_packed(const struct vring_virtqueue *vq) { - return false; + u16 last_used, flags; + bool avail, used; + + if (vq->vq.num_free == vq->vring_packed.num) + return false; + + last_used = vq->last_used_idx; + flags = virtio16_to_cpu(vq->vq.vdev, + vq->vring_packed.desc[last_used].flags); + avail = flags & VRING_DESC_F_AVAIL(1); + used = flags & VRING_DESC_F_USED(1); + + return avail == used; } static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq, unsigned int *len, void **ctx) { - return NULL; + 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_packed(vq)) { + pr_debug("No more buffers in queue\n"); + END_USE(vq); + return NULL; + } + + /* Only get used elements after they have been exposed by host. */ + virtio_rmb(vq->weak_barriers); + + last_used = vq->last_used_idx; + i = virtio32_to_cpu(_vq->vdev, vq->vring_packed.desc[last_used].id); + *len = virtio32_to_cpu(_vq->vdev, vq->vring_packed.desc[last_used].len); + + if (unlikely(i >= vq->vring_packed.num)) { + BAD_RING(vq, "id %u out of range\n", i); + return NULL; + } + if (unlikely(!vq->desc_state[i].data)) { + BAD_RING(vq, "id %u is not a head!\n", i); + return NULL; + } + + /* detach_buf_packed clears data, so grab it now. */ + ret = vq->desc_state[i].data; + detach_buf_packed(vq, i, ctx); + + vq->last_used_idx += vq->desc_state[i].num; + if (vq->last_used_idx >= vq->vring_packed.num) + vq->last_used_idx -= vq->vring_packed.num; + +#ifdef DEBUG + vq->last_add_time_valid = false; +#endif + + END_USE(vq); + return ret; } static void virtqueue_disable_cb_packed(struct virtqueue *_vq) { + struct vring_virtqueue *vq = to_vvq(_vq); + + if (vq->event_flags_shadow != VRING_EVENT_F_DISABLE) { + vq->event_flags_shadow = VRING_EVENT_F_DISABLE; + vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev, + vq->event_flags_shadow); + } } static unsigned virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq) { - return 0; + struct vring_virtqueue *vq = to_vvq(_vq); + + START_USE(vq); + + /* We optimistically turn back on interrupts, then check if there was + * more to do. */ + + if (vq->event_flags_shadow == VRING_EVENT_F_DISABLE) { + virtio_wmb(vq->weak_barriers); + vq->event_flags_shadow = VRING_EVENT_F_ENABLE; + vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev, + vq->event_flags_shadow); + } + + END_USE(vq); + return vq->last_used_idx; } static bool virtqueue_poll_packed(struct virtqueue *_vq, unsigned last_used_idx) { - return false; + struct vring_virtqueue *vq = to_vvq(_vq); + bool avail, used; + u16 flags; + + virtio_mb(vq->weak_barriers); + flags = virtio16_to_cpu(vq->vq.vdev, + vq->vring_packed.desc[last_used_idx].flags); + avail = flags & VRING_DESC_F_AVAIL(1); + used = flags & VRING_DESC_F_USED(1); + return avail == used; } static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq) { - return false; + struct vring_virtqueue *vq = to_vvq(_vq); + + START_USE(vq); + + /* We optimistically turn back on interrupts, then check if there was + * more to do. */ + + if (vq->event_flags_shadow == VRING_EVENT_F_DISABLE) { + virtio_wmb(vq->weak_barriers); + vq->event_flags_shadow = VRING_EVENT_F_ENABLE; + vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev, + vq->event_flags_shadow); + } + + if (more_used_packed(vq)) { + END_USE(vq); + return false; + } + + END_USE(vq); + return true; } static void *virtqueue_detach_unused_buf_packed(struct virtqueue *_vq) { + struct vring_virtqueue *vq = to_vvq(_vq); + unsigned int i; + void *buf; + + START_USE(vq); + + for (i = 0; i < vq->vring_packed.num; i++) { + if (!vq->desc_state[i].data) + continue; + /* detach_buf clears data, so grab it now. */ + buf = vq->desc_state[i].data; + detach_buf_packed(vq, i, NULL); + END_USE(vq); + return buf; + } + /* That should have freed everything. */ + BUG_ON(vq->vq.num_free != vq->vring_packed.num); + + END_USE(vq); return NULL; } -- 2.11.0