Commit b734ed9d authored by Peter Maydell's avatar Peter Maydell
Browse files

Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging 



virtio,vhost,pci,pc: features, fixes and cleanups

- new stats in virtio balloon
- virtio eventfd rework for boot speedup
- vhost memory rework for boot speedup
- fixes and cleanups all over the place

Signed-off-by: default avatarMichael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Tue 13 Feb 2018 16:29:55 GMT
# gpg:                using RSA key 281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream: (22 commits)
  virtio-balloon: include statistics of disk/file caches
  acpi-test: update FADT
  lpc: drop pcie host dependency
  tests: acpi: fix FADT not being compared to reference table
  hw/pci-bridge: fix pcie root port's IO hints capability
  libvhost-user: Support across-memory-boundary access
  libvhost-user: Fix resource leak
  virtio-balloon: unref the memory region before continuing
  pci: removed the is_express field since a uniform interface was inserted
  virtio-blk: enable multiple vectors when using multiple I/O queues
  pci/bus: let it has higher migration priority
  pci-bridge/i82801b11: clear bridge registers on platform reset
  vhost: Move log_dirty check
  vhost: Merge and delete unused callbacks
  vhost: Clean out old vhost_set_memory and friends
  vhost: Regenerate region list from changed sections list
  vhost: Merge sections added to temporary list
  vhost: Simplify ring verification checks
  vhost: Build temporary section list and deref after commit
  virtio: improve virtio devices initialization time
  ...

Signed-off-by: default avatarPeter Maydell <peter.maydell@linaro.org>
parents fb68096d bf1e7140

contrib/libvhost-user/libvhost-user.c

+134 −13
Original line number Diff line number Diff line
@@ -118,15 +118,22 @@ vu_panic(VuDev *dev, const char *msg, ...) 


/* Translate guest physical address to our virtual address.  */

void *

vu_gpa_to_va(VuDev *dev, uint64_t guest_addr)

vu_gpa_to_va(VuDev *dev, uint64_t *plen, uint64_t guest_addr)

{

    int i;



    if (*plen == 0) {

        return NULL;

    }



    /* Find matching memory region.  */

    for (i = 0; i < dev->nregions; i++) {

        VuDevRegion *r = &dev->regions[i];



        if ((guest_addr >= r->gpa) && (guest_addr < (r->gpa + r->size))) {

            if ((guest_addr + *plen) > (r->gpa + r->size)) {

                *plen = r->gpa + r->size - guest_addr;

            }

            return (void *)(uintptr_t)

                guest_addr - r->gpa + r->mmap_addr + r->mmap_offset;

        }
@@ -407,6 +414,15 @@ vu_set_mem_table_exec(VuDev *dev, VhostUserMsg *vmsg) 
{

    int i;

    VhostUserMemory *memory = &vmsg->payload.memory;



    for (i = 0; i < dev->nregions; i++) {

        VuDevRegion *r = &dev->regions[i];

        void *m = (void *) (uintptr_t) r->mmap_addr;



        if (m) {

            munmap(m, r->size + r->mmap_offset);

        }

    }

    dev->nregions = memory->nregions;



    DPRINT("Nregions: %d\n", memory->nregions);
@@ -472,9 +488,14 @@ vu_set_log_base_exec(VuDev *dev, VhostUserMsg *vmsg) 


    rc = mmap(0, log_mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd,

              log_mmap_offset);

    close(fd);

    if (rc == MAP_FAILED) {

        perror("log mmap error");

    }



    if (dev->log_table) {

        munmap(dev->log_table, dev->log_size);

    }

    dev->log_table = rc;

    dev->log_size = log_mmap_size;
@@ -1102,6 +1123,37 @@ virtqueue_get_head(VuDev *dev, VuVirtq *vq, 
    return true;

}



static int

virtqueue_read_indirect_desc(VuDev *dev, struct vring_desc *desc,

                             uint64_t addr, size_t len)

{

    struct vring_desc *ori_desc;

    uint64_t read_len;



    if (len > (VIRTQUEUE_MAX_SIZE * sizeof(struct vring_desc))) {

        return -1;

    }



    if (len == 0) {

        return -1;

    }



    while (len) {

        read_len = len;

        ori_desc = vu_gpa_to_va(dev, &read_len, addr);

        if (!ori_desc) {

            return -1;

        }



        memcpy(desc, ori_desc, read_len);

        len -= read_len;

        addr += read_len;

        desc += read_len;

    }



    return 0;

}



enum {

    VIRTQUEUE_READ_DESC_ERROR = -1,

    VIRTQUEUE_READ_DESC_DONE = 0,   /* end of chain */
@@ -1148,8 +1200,10 @@ vu_queue_get_avail_bytes(VuDev *dev, VuVirtq *vq, unsigned int *in_bytes, 
    }



    while ((rc = virtqueue_num_heads(dev, vq, idx)) > 0) {

        unsigned int max, num_bufs, indirect = 0;

        unsigned int max, desc_len, num_bufs, indirect = 0;

        uint64_t desc_addr, read_len;

        struct vring_desc *desc;

        struct vring_desc desc_buf[VIRTQUEUE_MAX_SIZE];

        unsigned int i;



        max = vq->vring.num;
@@ -1173,8 +1227,24 @@ vu_queue_get_avail_bytes(VuDev *dev, VuVirtq *vq, unsigned int *in_bytes, 


            /* loop over the indirect descriptor table */

            indirect = 1;

            max = desc[i].len / sizeof(struct vring_desc);

            desc = vu_gpa_to_va(dev, desc[i].addr);

            desc_addr = desc[i].addr;

            desc_len = desc[i].len;

            max = desc_len / sizeof(struct vring_desc);

            read_len = desc_len;

            desc = vu_gpa_to_va(dev, &read_len, desc_addr);

            if (unlikely(desc && read_len != desc_len)) {

                /* Failed to use zero copy */

                desc = NULL;

                if (!virtqueue_read_indirect_desc(dev, desc_buf,

                                                  desc_addr,

                                                  desc_len)) {

                    desc = desc_buf;

                }

            }

            if (!desc) {

                vu_panic(dev, "Invalid indirect buffer table");

                goto err;

            }

            num_bufs = i = 0;

        }
@@ -1372,9 +1442,24 @@ virtqueue_map_desc(VuDev *dev, 
        return;

    }



    iov[num_sg].iov_base = vu_gpa_to_va(dev, pa);

    iov[num_sg].iov_len = sz;

    while (sz) {

        uint64_t len = sz;



        if (num_sg == max_num_sg) {

            vu_panic(dev, "virtio: too many descriptors in indirect table");

            return;

        }



        iov[num_sg].iov_base = vu_gpa_to_va(dev, &len, pa);

        if (iov[num_sg].iov_base == NULL) {

            vu_panic(dev, "virtio: invalid address for buffers");

            return;

        }

        iov[num_sg].iov_len = len;

        num_sg++;

        sz -= len;

        pa += len;

    }



    *p_num_sg = num_sg;

}
@@ -1406,10 +1491,12 @@ virtqueue_alloc_element(size_t sz, 
void *

vu_queue_pop(VuDev *dev, VuVirtq *vq, size_t sz)

{

    unsigned int i, head, max;

    unsigned int i, head, max, desc_len;

    uint64_t desc_addr, read_len;

    VuVirtqElement *elem;

    unsigned out_num, in_num;

    struct iovec iov[VIRTQUEUE_MAX_SIZE];

    struct vring_desc desc_buf[VIRTQUEUE_MAX_SIZE];

    struct vring_desc *desc;

    int rc;
@@ -1450,8 +1537,24 @@ vu_queue_pop(VuDev *dev, VuVirtq *vq, size_t sz) 
        }



        /* loop over the indirect descriptor table */

        max = desc[i].len / sizeof(struct vring_desc);

        desc = vu_gpa_to_va(dev, desc[i].addr);

        desc_addr = desc[i].addr;

        desc_len = desc[i].len;

        max = desc_len / sizeof(struct vring_desc);

        read_len = desc_len;

        desc = vu_gpa_to_va(dev, &read_len, desc_addr);

        if (unlikely(desc && read_len != desc_len)) {

            /* Failed to use zero copy */

            desc = NULL;

            if (!virtqueue_read_indirect_desc(dev, desc_buf,

                                              desc_addr,

                                              desc_len)) {

                desc = desc_buf;

            }

        }

        if (!desc) {

            vu_panic(dev, "Invalid indirect buffer table");

            return NULL;

        }

        i = 0;

    }
@@ -1527,7 +1630,9 @@ vu_log_queue_fill(VuDev *dev, VuVirtq *vq, 
                  unsigned int len)

{

    struct vring_desc *desc = vq->vring.desc;

    unsigned int i, max, min;

    unsigned int i, max, min, desc_len;

    uint64_t desc_addr, read_len;

    struct vring_desc desc_buf[VIRTQUEUE_MAX_SIZE];

    unsigned num_bufs = 0;



    max = vq->vring.num;
@@ -1539,8 +1644,24 @@ vu_log_queue_fill(VuDev *dev, VuVirtq *vq, 
        }



        /* loop over the indirect descriptor table */

        max = desc[i].len / sizeof(struct vring_desc);

        desc = vu_gpa_to_va(dev, desc[i].addr);

        desc_addr = desc[i].addr;

        desc_len = desc[i].len;

        max = desc_len / sizeof(struct vring_desc);

        read_len = desc_len;

        desc = vu_gpa_to_va(dev, &read_len, desc_addr);

        if (unlikely(desc && read_len != desc_len)) {

            /* Failed to use zero copy */

            desc = NULL;

            if (!virtqueue_read_indirect_desc(dev, desc_buf,

                                              desc_addr,

                                              desc_len)) {

                desc = desc_buf;

            }

        }

        if (!desc) {

            vu_panic(dev, "Invalid indirect buffer table");

            return;

        }

        i = 0;

    }

contrib/libvhost-user/libvhost-user.h

+2 −1
Original line number Diff line number Diff line
@@ -327,11 +327,12 @@ bool vu_dispatch(VuDev *dev); 
/**

 * vu_gpa_to_va:

 * @dev: a VuDev context

 * @plen: guest memory size

 * @guest_addr: guest address

 *

 * Translate a guest address to a pointer. Returns NULL on failure.

 */

void *vu_gpa_to_va(VuDev *dev, uint64_t guest_addr);

void *vu_gpa_to_va(VuDev *dev, uint64_t *plen, uint64_t guest_addr);



/**

 * vu_get_queue:

docs/pcie_pci_bridge.txt

+1 −1
Original line number Diff line number Diff line
@@ -110,5 +110,5 @@ To enable device hot-plug into the bridge on Linux there're 3 ways: 
Implementation

==============

The PCIE-PCI bridge is based on PCI-PCI bridge, but also accumulates PCI Express

features as a PCI Express device (is_express=1).

features as a PCI Express device.

hw/block/dataplane/virtio-blk.c

+2 −0
Original line number Diff line number Diff line
@@ -192,6 +192,7 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev) 
            fprintf(stderr, "virtio-blk failed to set host notifier (%d)\n", r);

            while (i--) {

                virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);

                virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), i);

            }

            goto fail_guest_notifiers;

        }
@@ -267,6 +268,7 @@ void virtio_blk_data_plane_stop(VirtIODevice *vdev) 


    for (i = 0; i < nvqs; i++) {

        virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);

        virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), i);

    }



    /* Clean up guest notifier (irq) */

hw/block/nvme.c

+0 −1
Original line number Diff line number Diff line
@@ -1360,7 +1360,6 @@ static void nvme_class_init(ObjectClass *oc, void *data) 
    pc->vendor_id = PCI_VENDOR_ID_INTEL;

    pc->device_id = 0x5845;

    pc->revision = 2;

    pc->is_express = 1;



    set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);

    dc->desc = "Non-Volatile Memory Express";