cfn/computing-offload
Code Issues Proposed changes
79c4324644
computing-offload/generic_vdpa/qemu/vdpa-Add-custom-IOTLB-translations-to-SVQ.patch
jiangdongxu 79c4324644 add generic_vdpa basecode 
Change-Id: I2d302dda68298877c65c99147f5bf22186a59aac
2024-09-19 17:19:46 +08:00

416 lines
15 KiB
Diff
Raw Blame History

From 649e277b6ec0d2cd798f6d43776ea38b00450db9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Mon, 14 Mar 2022 18:34:51 +0100
Subject: [PATCH] vdpa: Add custom IOTLB translations to SVQ
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Use translations added in VhostIOVATree in SVQ.
Only introduce usage here, not allocation and deallocation. As with
previous patches, we use the dead code paths of shadow_vqs_enabled to
avoid commiting too many changes at once. These are impossible to take
at the moment.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: fangyi <eric.fangyi@huawei.com>
---
hw/virtio/vhost-shadow-virtqueue.c | 86 +++++++++++++++++---
hw/virtio/vhost-shadow-virtqueue.h | 6 +-
hw/virtio/vhost-vdpa.c | 122 ++++++++++++++++++++++++-----
include/hw/virtio/vhost-vdpa.h | 3 +
4 files changed, 187 insertions(+), 30 deletions(-)
diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c
index 46e94f0861..c38b6b6ab5 100644
--- a/hw/virtio/vhost-shadow-virtqueue.c
+++ b/hw/virtio/vhost-shadow-virtqueue.c
@@ -69,7 +69,59 @@ static uint16_t vhost_svq_available_slots(const VhostShadowVirtqueue *svq)
return svq->vring.num - (svq->shadow_avail_idx - svq->shadow_used_idx);
}
-static void vhost_vring_write_descs(VhostShadowVirtqueue *svq,
+/**
+ * Translate addresses between the qemu's virtual address and the SVQ IOVA
+ *
+ * @svq: Shadow VirtQueue
+ * @vaddr: Translated IOVA addresses
+ * @iovec: Source qemu's VA addresses
+ * @num: Length of iovec and minimum length of vaddr
+ */
+static bool vhost_svq_translate_addr(const VhostShadowVirtqueue *svq,
+ hwaddr *addrs, const struct iovec *iovec,
+ size_t num)
+{
+ if (num == 0) {
+ return true;
+ }
+
+ for (size_t i = 0; i < num; ++i) {
+ DMAMap needle = {
+ .translated_addr = (hwaddr)(uintptr_t)iovec[i].iov_base,
+ .size = iovec[i].iov_len,
+ };
+ Int128 needle_last, map_last;
+ size_t off;
+
+ const DMAMap *map = vhost_iova_tree_find_iova(svq->iova_tree, &needle);
+ /*
+ * Map cannot be NULL since iova map contains all guest space and
+ * qemu already has a physical address mapped
+ */
+ if (unlikely(!map)) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "Invalid address 0x%"HWADDR_PRIx" given by guest",
+ needle.translated_addr);
+ return false;
+ }
+
+ off = needle.translated_addr - map->translated_addr;
+ addrs[i] = map->iova + off;
+
+ needle_last = int128_add(int128_make64(needle.translated_addr),
+ int128_make64(iovec[i].iov_len));
+ map_last = int128_make64(map->translated_addr + map->size);
+ if (unlikely(int128_gt(needle_last, map_last))) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "Guest buffer expands over iova range");
+ return false;
+ }
+ }
+
+ return true;
+}
+
+static void vhost_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg,
const struct iovec *iovec, size_t num,
bool more_descs, bool write)
{
@@ -88,7 +140,7 @@ static void vhost_vring_write_descs(VhostShadowVirtqueue *svq,
} else {
descs[i].flags = flags;
}
- descs[i].addr = cpu_to_le64((hwaddr)(intptr_t)iovec[n].iov_base);
+ descs[i].addr = cpu_to_le64(sg[n]);
descs[i].len = cpu_to_le32(iovec[n].iov_len);
last = i;
@@ -103,6 +155,8 @@ static bool vhost_svq_add_split(VhostShadowVirtqueue *svq,
{
unsigned avail_idx;
vring_avail_t *avail = svq->vring.avail;
+ bool ok;
+ g_autofree hwaddr *sgs = g_new(hwaddr, MAX(elem->out_num, elem->in_num));
*head = svq->free_head;
@@ -113,9 +167,20 @@ static bool vhost_svq_add_split(VhostShadowVirtqueue *svq,
return false;
}
- vhost_vring_write_descs(svq, elem->out_sg, elem->out_num, elem->in_num > 0,
- false);
- vhost_vring_write_descs(svq, elem->in_sg, elem->in_num, false, true);
+ ok = vhost_svq_translate_addr(svq, sgs, elem->out_sg, elem->out_num);
+ if (unlikely(!ok)) {
+ return false;
+ }
+ vhost_vring_write_descs(svq, sgs, elem->out_sg, elem->out_num,
+ elem->in_num > 0, false);
+
+
+ ok = vhost_svq_translate_addr(svq, sgs, elem->in_sg, elem->in_num);
+ if (unlikely(!ok)) {
+ return false;
+ }
+
+ vhost_vring_write_descs(svq, sgs, elem->in_sg, elem->in_num, false, true);
/*
* Put the entry in the available array (but don't update avail->idx until
@@ -394,9 +459,9 @@ void vhost_svq_set_svq_call_fd(VhostShadowVirtqueue *svq, int call_fd)
void vhost_svq_get_vring_addr(const VhostShadowVirtqueue *svq,
struct vhost_vring_addr *addr)
{
- addr->desc_user_addr = (uint64_t)(intptr_t)svq->vring.desc;
- addr->avail_user_addr = (uint64_t)(intptr_t)svq->vring.avail;
- addr->used_user_addr = (uint64_t)(intptr_t)svq->vring.used;
+ addr->desc_user_addr = (uint64_t)(uintptr_t)svq->vring.desc;
+ addr->avail_user_addr = (uint64_t)(uintptr_t)svq->vring.avail;
+ addr->used_user_addr = (uint64_t)(uintptr_t)svq->vring.used;
}
size_t vhost_svq_driver_area_size(const VhostShadowVirtqueue *svq)
@@ -517,11 +582,13 @@ void vhost_svq_stop(VhostShadowVirtqueue *svq)
* Creates vhost shadow virtqueue, and instructs the vhost device to use the
* shadow methods and file descriptors.
*
+ * @iova_tree: Tree to perform descriptors translations
+ *
* Returns the new virtqueue or NULL.
*
* In case of error, reason is reported through error_report.
*/
-VhostShadowVirtqueue *vhost_svq_new(void)
+VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree)
{
g_autofree VhostShadowVirtqueue *svq = g_new0(VhostShadowVirtqueue, 1);
int r;
@@ -542,6 +609,7 @@ VhostShadowVirtqueue *vhost_svq_new(void)
event_notifier_init_fd(&svq->svq_kick, VHOST_FILE_UNBIND);
event_notifier_set_handler(&svq->hdev_call, vhost_svq_handle_call);
+ svq->iova_tree = iova_tree;
return g_steal_pointer(&svq);
err_init_hdev_call:
diff --git a/hw/virtio/vhost-shadow-virtqueue.h b/hw/virtio/vhost-shadow-virtqueue.h
index 38b3b91ca7..e5e24c536d 100644
--- a/hw/virtio/vhost-shadow-virtqueue.h
+++ b/hw/virtio/vhost-shadow-virtqueue.h
@@ -13,6 +13,7 @@
#include "qemu/event_notifier.h"
#include "hw/virtio/virtio.h"
#include "standard-headers/linux/vhost_types.h"
+#include "hw/virtio/vhost-iova-tree.h"
/* Shadow virtqueue to relay notifications */
typedef struct VhostShadowVirtqueue {
@@ -43,6 +44,9 @@ typedef struct VhostShadowVirtqueue {
/* Virtio device */
VirtIODevice *vdev;
+ /* IOVA mapping */
+ VhostIOVATree *iova_tree;
+
/* Map for use the guest's descriptors */
VirtQueueElement **ring_id_maps;
@@ -75,7 +79,7 @@ void vhost_svq_start(VhostShadowVirtqueue *svq, VirtIODevice *vdev,
VirtQueue *vq);
void vhost_svq_stop(VhostShadowVirtqueue *svq);
-VhostShadowVirtqueue *vhost_svq_new(void);
+VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree);
void vhost_svq_free(gpointer vq);
G_DEFINE_AUTOPTR_CLEANUP_FUNC(VhostShadowVirtqueue, vhost_svq_free);
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index db34f26246..8245345bcd 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -211,6 +211,21 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener,
vaddr, section->readonly);
llsize = int128_sub(llend, int128_make64(iova));
+ if (v->shadow_vqs_enabled) {
+ DMAMap mem_region = {
+ .translated_addr = (hwaddr)(uintptr_t)vaddr,
+ .size = int128_get64(llsize) - 1,
+ .perm = IOMMU_ACCESS_FLAG(true, section->readonly),
+ };
+
+ int r = vhost_iova_tree_map_alloc(v->iova_tree, &mem_region);
+ if (unlikely(r != IOVA_OK)) {
+ error_report("Can't allocate a mapping (%d)", r);
+ goto fail;
+ }
+
+ iova = mem_region.iova;
+ }
vhost_vdpa_iotlb_batch_begin_once(v);
ret = vhost_vdpa_dma_map(v, iova, int128_get64(llsize),
@@ -263,6 +278,20 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener,
llsize = int128_sub(llend, int128_make64(iova));
+ if (v->shadow_vqs_enabled) {
+ const DMAMap *result;
+ const void *vaddr = memory_region_get_ram_ptr(section->mr) +
+ section->offset_within_region +
+ (iova - section->offset_within_address_space);
+ DMAMap mem_region = {
+ .translated_addr = (hwaddr)(uintptr_t)vaddr,
+ .size = int128_get64(llsize) - 1,
+ };
+
+ result = vhost_iova_tree_find_iova(v->iova_tree, &mem_region);
+ iova = result->iova;
+ vhost_iova_tree_remove(v->iova_tree, &mem_region);
+ }
vhost_vdpa_iotlb_batch_begin_once(v);
ret = vhost_vdpa_dma_unmap(v, iova, int128_get64(llsize));
if (ret) {
@@ -372,7 +401,7 @@ static int vhost_vdpa_init_svq(struct vhost_dev *hdev, struct vhost_vdpa *v,
shadow_vqs = g_ptr_array_new_full(hdev->nvqs, vhost_svq_free);
for (unsigned n = 0; n < hdev->nvqs; ++n) {
- g_autoptr(VhostShadowVirtqueue) svq = vhost_svq_new();
+ g_autoptr(VhostShadowVirtqueue) svq = vhost_svq_new(v->iova_tree);
if (unlikely(!svq)) {
error_setg(errp, "Cannot create svq %u", n);
@@ -809,33 +838,70 @@ static int vhost_vdpa_svq_set_fds(struct vhost_dev *dev,
/**
* Unmap a SVQ area in the device
*/
-static bool vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, hwaddr iova,
- hwaddr size)
+static bool vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v,
+ const DMAMap *needle)
{
+ const DMAMap *result = vhost_iova_tree_find_iova(v->iova_tree, needle);
+ hwaddr size;
int r;
- size = ROUND_UP(size, qemu_real_host_page_size);
- r = vhost_vdpa_dma_unmap(v, iova, size);
+ if (unlikely(!result)) {
+ error_report("Unable to find SVQ address to unmap");
+ return false;
+ }
+
+ size = ROUND_UP(result->size, qemu_real_host_page_size);
+ r = vhost_vdpa_dma_unmap(v, result->iova, size);
return r == 0;
}
static bool vhost_vdpa_svq_unmap_rings(struct vhost_dev *dev,
const VhostShadowVirtqueue *svq)
{
+ DMAMap needle = {};
struct vhost_vdpa *v = dev->opaque;
struct vhost_vring_addr svq_addr;
- size_t device_size = vhost_svq_device_area_size(svq);
- size_t driver_size = vhost_svq_driver_area_size(svq);
bool ok;
vhost_svq_get_vring_addr(svq, &svq_addr);
- ok = vhost_vdpa_svq_unmap_ring(v, svq_addr.desc_user_addr, driver_size);
+ needle.translated_addr = svq_addr.desc_user_addr;
+ ok = vhost_vdpa_svq_unmap_ring(v, &needle);
if (unlikely(!ok)) {
return false;
}
- return vhost_vdpa_svq_unmap_ring(v, svq_addr.used_user_addr, device_size);
+ needle.translated_addr = svq_addr.used_user_addr;
+ return vhost_vdpa_svq_unmap_ring(v, &needle);
+}
+
+/**
+ * Map the SVQ area in the device
+ *
+ * @v: Vhost-vdpa device
+ * @needle: The area to search iova
+ * @errorp: Error pointer
+ */
+static bool vhost_vdpa_svq_map_ring(struct vhost_vdpa *v, DMAMap *needle,
+ Error **errp)
+{
+ int r;
+
+ r = vhost_iova_tree_map_alloc(v->iova_tree, needle);
+ if (unlikely(r != IOVA_OK)) {
+ error_setg(errp, "Cannot allocate iova (%d)", r);
+ return false;
+ }
+
+ r = vhost_vdpa_dma_map(v, needle->iova, needle->size + 1,
+ (void *)(uintptr_t)needle->translated_addr,
+ needle->perm == IOMMU_RO);
+ if (unlikely(r != 0)) {
+ error_setg_errno(errp, -r, "Cannot map region to device");
+ vhost_iova_tree_remove(v->iova_tree, needle);
+ }
+
+ return r == 0;
}
/**
@@ -851,28 +917,44 @@ static bool vhost_vdpa_svq_map_rings(struct vhost_dev *dev,
struct vhost_vring_addr *addr,
Error **errp)
{
+ DMAMap device_region, driver_region;
+ struct vhost_vring_addr svq_addr;
struct vhost_vdpa *v = dev->opaque;
size_t device_size = vhost_svq_device_area_size(svq);
size_t driver_size = vhost_svq_driver_area_size(svq);
- int r;
+ size_t avail_offset;
+ bool ok;
ERRP_GUARD();
- vhost_svq_get_vring_addr(svq, addr);
+ vhost_svq_get_vring_addr(svq, &svq_addr);
- r = vhost_vdpa_dma_map(v, addr->desc_user_addr, driver_size,
- (void *)(uintptr_t)addr->desc_user_addr, true);
- if (unlikely(r != 0)) {
- error_setg_errno(errp, -r, "Cannot create vq driver region: ");
+ driver_region = (DMAMap) {
+ .translated_addr = svq_addr.desc_user_addr,
+ .size = driver_size - 1,
+ .perm = IOMMU_RO,
+ };
+ ok = vhost_vdpa_svq_map_ring(v, &driver_region, errp);
+ if (unlikely(!ok)) {
+ error_prepend(errp, "Cannot create vq driver region: ");
return false;
}
+ addr->desc_user_addr = driver_region.iova;
+ avail_offset = svq_addr.avail_user_addr - svq_addr.desc_user_addr;
+ addr->avail_user_addr = driver_region.iova + avail_offset;
- r = vhost_vdpa_dma_map(v, addr->used_user_addr, device_size,
- (void *)(intptr_t)addr->used_user_addr, false);
- if (unlikely(r != 0)) {
- error_setg_errno(errp, -r, "Cannot create vq device region: ");
+ device_region = (DMAMap) {
+ .translated_addr = svq_addr.used_user_addr,
+ .size = device_size - 1,
+ .perm = IOMMU_RW,
+ };
+ ok = vhost_vdpa_svq_map_ring(v, &device_region, errp);
+ if (unlikely(!ok)) {
+ error_prepend(errp, "Cannot create vq device region: ");
+ vhost_vdpa_svq_unmap_ring(v, &driver_region);
}
+ addr->used_user_addr = device_region.iova;
- return r == 0;
+ return ok;
}
static bool vhost_vdpa_svq_setup(struct vhost_dev *dev,
diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h
index 009a9f3b6b..ee8e939ad0 100644
--- a/include/hw/virtio/vhost-vdpa.h
+++ b/include/hw/virtio/vhost-vdpa.h
@@ -14,6 +14,7 @@
#include <gmodule.h>
+#include "hw/virtio/vhost-iova-tree.h"
#include "hw/virtio/virtio.h"
#include "standard-headers/linux/vhost_types.h"
@@ -30,6 +31,8 @@ typedef struct vhost_vdpa {
MemoryListener listener;
struct vhost_vdpa_iova_range iova_range;
bool shadow_vqs_enabled;
+ /* IOVA mapping used by the Shadow Virtqueue */
+ VhostIOVATree *iova_tree;
GPtrArray *shadow_vqs;
struct vhost_dev *dev;
VhostVDPAHostNotifier notifier[VIRTIO_QUEUE_MAX];
--
2.27.0
View Git Blame Copy Permalink