[PATCH v6 4/5] vhost_user: Function defs for add/rem mem regions
Bathija, Pravin
Pravin.Bathija at dell.com
Tue Mar 24 07:16:05 CET 2026
Hi Maxime,
I wanted to follow up if you got a chance to go through the clarifications I provided regarding post-copy migration tests and review the v7 version of the patch set.
Thanks,
Pravin
Internal Use - Confidential
> -----Original Message-----
> From: Bathija, Pravin
> Sent: Monday, March 16, 2026 3:15 AM
> To: 'Maxime Coquelin' <maxime.coquelin at redhat.com>
> Cc: 'dev at dpdk.org' <dev at dpdk.org>; 'fengchengwen at huawei.com'
> <fengchengwen at huawei.com>
> Subject: RE: [PATCH v6 4/5] vhost_user: Function defs for add/rem mem
> regions
>
> Hi Maxime,
>
> I wanted to follow up if you got a chance to review my updated patch-set v7
> and the clarifications to your earlier message. I successfully reran the post-copy
> live migration tests with qemu and dpdk-testpmd.
>
> Happy to answer any other queries you might have.
>
> Regards,
> Pravin
>
> > -----Original Message-----
> > From: Bathija, Pravin
> > Sent: Monday, March 2, 2026 11:11 PM
> > To: Maxime Coquelin <maxime.coquelin at redhat.com>
> > Cc: dev at dpdk.org; fengchengwen at huawei.com
> > Subject: RE: [PATCH v6 4/5] vhost_user: Function defs for add/rem mem
> > regions
> >
> > Dear Maxime,
> >
> > Any feedback on the latest patch v7 I submitted earlier ?
> >
> > Thanks,
> > Pravin
> >
> > > -----Original Message-----
> > > From: Bathija, Pravin
> > > Sent: Wednesday, February 11, 2026 2:20 AM
> > > To: Maxime Coquelin <maxime.coquelin at redhat.com>
> > > Cc: dev at dpdk.org; fengchengwen at huawei.com
> > > Subject: RE: [PATCH v6 4/5] vhost_user: Function defs for add/rem
> > > mem regions
> > >
> > > Dear Maxime,
> > >
> > > Answers inline.
> > >
> > > > -----Original Message-----
> > > > From: Maxime Coquelin <maxime.coquelin at redhat.com>
> > > > Sent: Monday, January 26, 2026 11:58 AM
> > > > To: Bathija, Pravin <Pravin.Bathija at dell.com>
> > > > Cc: dev at dpdk.org; fengchengwen at huawei.com
> > > > Subject: Re: [PATCH v6 4/5] vhost_user: Function defs for add/rem
> > > > mem regions
> > > >
> > > >
> > > > [EXTERNAL EMAIL]
> > > >
> > > > On Thu, Jan 22, 2026 at 8:49 AM <pravin.bathija at dell.com> wrote:
> > > > >
> > > > > From: Pravin M Bathija <pravin.bathija at dell.com>
> > > > >
> > > > > These changes cover the function definition for add/remove
> > > > > memory region calls which are invoked on receiving vhost user
> > > > > message from vhost user front-end (e.g. Qemu). In our case, in
> > > > > addition to testing with qemu front-end, the testing has also
> > > > > been performed with libblkio front-end and spdk/dpdk back-end.
> > > > > We did I/O using libblkio based device driver, to spdk based
> > > > > drives. There are also changes for set_mem_table and new definition
> for get memory slots.
> > > > > Our changes optimize the set memory table call to use common
> > > > > support
> > > functions.
> > > > > Message get memory slots is how the vhost-user front-end queries
> > > > > the vhost-user back-end about the number of memory slots
> > > > > available to be registered by the back-end. In addition support
> > > > > function to invalidate vring is also defined which is used in
> > > > > add/remove memory region
> > > functions.
> > > > >
> > > > > Signed-off-by: Pravin M Bathija <pravin.bathija at dell.com>
> > > > > ---
> > > > > lib/vhost/vhost_user.c | 234
> > > > > +++++++++++++++++++++++++++++++++++------
> > > > > 1 file changed, 202 insertions(+), 32 deletions(-)
> > > > >
> > > > > diff --git a/lib/vhost/vhost_user.c b/lib/vhost/vhost_user.c
> > > > > index e2831b7625..1a2dcfbbca 100644
> > > > > --- a/lib/vhost/vhost_user.c
> > > > > +++ b/lib/vhost/vhost_user.c
> > > > > @@ -71,6 +71,9 @@
> > > > VHOST_MESSAGE_HANDLER(VHOST_USER_SET_FEATURES,
> > > > > vhost_user_set_features, false, t
> > > > > VHOST_MESSAGE_HANDLER(VHOST_USER_SET_OWNER,
> > > > vhost_user_set_owner,
> > > > > false, true) \
> VHOST_MESSAGE_HANDLER(VHOST_USER_RESET_OWNER,
> > > > > vhost_user_reset_owner, false, false) \
> > > > > VHOST_MESSAGE_HANDLER(VHOST_USER_SET_MEM_TABLE,
> > > > > vhost_user_set_mem_table, true, true) \
> > > > > +VHOST_MESSAGE_HANDLER(VHOST_USER_GET_MAX_MEM_SLOTS,
> > > > > +vhost_user_get_max_mem_slots, false, false) \
> > > > > +VHOST_MESSAGE_HANDLER(VHOST_USER_ADD_MEM_REG,
> > > > vhost_user_add_mem_reg,
> > > > > +true, true) \
> > VHOST_MESSAGE_HANDLER(VHOST_USER_REM_MEM_REG,
> > > > > +vhost_user_rem_mem_reg, false, true) \
> > > > > VHOST_MESSAGE_HANDLER(VHOST_USER_SET_LOG_BASE,
> > > > > vhost_user_set_log_base, true, true) \
> > > > > VHOST_MESSAGE_HANDLER(VHOST_USER_SET_LOG_FD,
> > > > vhost_user_set_log_fd,
> > > > > true, true) \
> > > VHOST_MESSAGE_HANDLER(VHOST_USER_SET_VRING_NUM,
> > > > vhost_user_set_vring_num, false, true) \ @@ -1520,7 +1523,6 @@
> > > > vhost_user_set_mem_table(struct virtio_net **pdev,
> > > > > struct virtio_net *dev = *pdev;
> > > > > struct VhostUserMemory *memory = &ctx->msg.payload.memory;
> > > > > struct rte_vhost_mem_region *reg;
> > > > > - int numa_node = SOCKET_ID_ANY;
> > > > > uint64_t mmap_offset;
> > > > > uint32_t i;
> > > > > bool async_notify = false; @@ -1565,39 +1567,13 @@
> > > > > vhost_user_set_mem_table(struct virtio_net
> > > > **pdev,
> > > > > if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
> > > > > vhost_user_iotlb_flush_all(dev);
> > > > >
> > > > > - free_mem_region(dev);
> > > > > + free_all_mem_regions(dev);
> > > > > rte_free(dev->mem);
> > > > > dev->mem = NULL;
> > > > > }
> > > > >
> > > > > - /*
> > > > > - * If VQ 0 has already been allocated, try to allocate on the same
> > > > > - * NUMA node. It can be reallocated later in numa_realloc().
> > > > > - */
> > > > > - if (dev->nr_vring > 0)
> > > > > - numa_node = dev->virtqueue[0]->numa_node;
> > > > > -
> > > > > - dev->nr_guest_pages = 0;
> > > > > - if (dev->guest_pages == NULL) {
> > > > > - dev->max_guest_pages = 8;
> > > > > - dev->guest_pages = rte_zmalloc_socket(NULL,
> > > > > - dev->max_guest_pages *
> > > > > - sizeof(struct guest_page),
> > > > > - RTE_CACHE_LINE_SIZE,
> > > > > - numa_node);
> > > > > - if (dev->guest_pages == NULL) {
> > > > > - VHOST_CONFIG_LOG(dev->ifname, ERR,
> > > > > - "failed to allocate memory for dev->guest_pages");
> > > > > - goto close_msg_fds;
> > > > > - }
> > > > > - }
> > > > > -
> > > > > - dev->mem = rte_zmalloc_socket("vhost-mem-table", sizeof(struct
> > > > rte_vhost_memory) +
> > > > > - sizeof(struct rte_vhost_mem_region) * memory->nregions, 0,
> > > > numa_node);
> > > > > - if (dev->mem == NULL) {
> > > > > - VHOST_CONFIG_LOG(dev->ifname, ERR, "failed to allocate
> > > memory
> > > > for dev->mem");
> > > > > - goto free_guest_pages;
> > > > > - }
> > > > > + if (vhost_user_initialize_memory(pdev) < 0)
> > > > > + goto close_msg_fds;
> > > > >
> > > > > for (i = 0; i < memory->nregions; i++) {
> > > > > reg = &dev->mem->regions[i]; @@ -1661,11
> > > > > +1637,167 @@ vhost_user_set_mem_table(struct virtio_net **pdev,
> > > > > return RTE_VHOST_MSG_RESULT_OK;
> > > > >
> > > > > free_mem_table:
> > > > > - free_mem_region(dev);
> > > > > + free_all_mem_regions(dev);
> > > > > rte_free(dev->mem);
> > > > > dev->mem = NULL;
> > > > > + rte_free(dev->guest_pages);
> > > > > + dev->guest_pages = NULL;
> > > > > +close_msg_fds:
> > > > > + close_msg_fds(ctx);
> > > > > + return RTE_VHOST_MSG_RESULT_ERR; }
> > > > > +
> > > > > +
> > > > > +static int
> > > > > +vhost_user_get_max_mem_slots(struct virtio_net **pdev
> > __rte_unused,
> > > > > + struct vhu_msg_context *ctx,
> > > > > + int main_fd __rte_unused) {
> > > > > + uint32_t max_mem_slots = VHOST_MEMORY_MAX_NREGIONS;
> > > > > +
> > > > > + ctx->msg.payload.u64 = (uint64_t)max_mem_slots;
> > > > > + ctx->msg.size = sizeof(ctx->msg.payload.u64);
> > > > > + ctx->fd_num = 0;
> > > > > +
> > > > > + return RTE_VHOST_MSG_RESULT_REPLY; }
> > > > > +
> > > > > +static void
> > > > > +dev_invalidate_vrings(struct virtio_net *dev) {
> > > > > + uint32_t i;
> > > > > +
> > > > > + for (i = 0; i < dev->nr_vring; i++) {
> > > > > + struct vhost_virtqueue *vq = dev->virtqueue[i];
> > > > > +
> > > > > + if (!vq)
> > > > > + continue;
> > > > >
> > > > > -free_guest_pages:
> > > > > + if (vq->desc || vq->avail || vq->used) {
> > > > > + /* vhost_user_lock_all_queue_pairs locked all qps */
> > > > > + VHOST_USER_ASSERT_LOCK(dev, vq,
> > > > > + VHOST_USER_ADD_MEM_REG);
> > > > > +
> > > > > + /*
> > > > > + * If the memory table got updated, the ring addresses
> > > > > + * need to be translated again as virtual addresses have
> > > > > + * changed.
> > > > > + */
> > > > > + vring_invalidate(dev, vq);
> > > > > +
> > > > > + translate_ring_addresses(&dev, &vq);
> > > > > + }
> > > > > + }
> > > > > +}
> > > > > +
> > > > > +static int
> > > > > +vhost_user_add_mem_reg(struct virtio_net **pdev,
> > > > > + struct vhu_msg_context *ctx,
> > > > > + int main_fd __rte_unused)
> > > >
> > > > The parameter is marked as unused but is actually used.
> > >
> > > I have made the corrections in the amended patch-set I will submit
> > > following this e-mail.
> > >
> > > >
> > > > > +{
> > > > > + uint32_t i;
> > > > > + struct virtio_net *dev = *pdev;
> > > > > + struct VhostUserMemoryRegion *region =
> > > > > +&ctx->msg.payload.memory_single.region;
> > > > > +
> > > > > + /* convert first region add to normal memory table set */
> > > > > + if (dev->mem == NULL) {
> > > > > + if (vhost_user_initialize_memory(pdev) < 0)
> > > > > + goto close_msg_fds;
> > > > > + }
> > > > > +
> > > > > + /* make sure new region will fit */
> > > > > + if (dev->mem->nregions >= VHOST_MEMORY_MAX_NREGIONS) {
> > > > > + VHOST_CONFIG_LOG(dev->ifname, ERR, "too many
> > > > > + memory
> > > > regions already (%u)",
> > > > > + dev->mem->nregions);
> > > > > + goto close_msg_fds;
> > > > > + }
> > > > > +
> > > > > + /* make sure supplied memory fd present */
> > > > > + if (ctx->fd_num != 1) {
> > > > > + VHOST_CONFIG_LOG(dev->ifname, ERR, "fd count
> > > > > + makes no sense
> > > > (%u)", ctx->fd_num);
> > > > > + goto close_msg_fds;
> > > > > + }
> > > > > +
> > > > > + /* Make sure no overlap in guest virtual address space */
> > > > > + if (dev->mem != NULL && dev->mem->nregions > 0) {
> > > > > + for (i = 0; i < VHOST_MEMORY_MAX_NREGIONS; i++) {
> > > > > + struct rte_vhost_mem_region
> > > > > + *current_region = &dev->mem->regions[i];
> > > > > +
> > > > > + if (current_region->mmap_size == 0)
> > > > > + continue;
> > > > > +
> > > > > + uint64_t current_region_guest_start =
> > > > > + current_region-
> > > > >guest_user_addr;
> > > > > + uint64_t current_region_guest_end =
> > > > current_region_guest_start
> > > > > + + current_region->mmap_size - 1;
> > > > > + uint64_t proposed_region_guest_start =
> > > > > + region-
> > > > >userspace_addr;
> > > > > + uint64_t proposed_region_guest_end =
> > > > proposed_region_guest_start
> > > > > + + region->memory_size - 1;
> > > > > + bool overlap = false;
> > > > > +
> > > > > + overlap = !((proposed_region_guest_end <
> > > > current_region_guest_start) ||
> > > > > + (proposed_region_guest_start >
> > > > > + current_region_guest_end));
> > > > > +
> > > > > + if (overlap) {
> > > > > + VHOST_CONFIG_LOG(dev->ifname, ERR,
> > > > > + "requested memory region
> > > > > + overlaps with another
> > > > region");
> > > > > + VHOST_CONFIG_LOG(dev->ifname, ERR,
> > > > > + "\tRequested region address:0x%" PRIx64,
> > > > > + region->userspace_addr);
> > > > > + VHOST_CONFIG_LOG(dev->ifname, ERR,
> > > > > + "\tRequested region size:0x%" PRIx64,
> > > > > + region->memory_size);
> > > > > + VHOST_CONFIG_LOG(dev->ifname, ERR,
> > > > > + "\tOverlapping region address:0x%" PRIx64,
> > > > > + current_region->guest_user_addr);
> > > > > + VHOST_CONFIG_LOG(dev->ifname, ERR,
> > > > > + "\tOverlapping region size:0x%" PRIx64,
> > > > > + current_region->mmap_size);
> > > > > + goto close_msg_fds;
> > > > > + }
> > > > > +
> > > > > + }
> > > > > + }
> > > > > +
> > > > > + /* find a new region and set it like memory table set does */
> > > > > + struct rte_vhost_mem_region *reg = NULL;
> > > > > +
> > > > > + for (i = 0; i < VHOST_MEMORY_MAX_NREGIONS; i++) {
> > > > > + if (dev->mem->regions[i].guest_user_addr == 0) {
> > > > > + reg = &dev->mem->regions[i];
> > > > > + break;
> > > > > + }
> > > > > + }
> > > > > + if (reg == NULL) {
> > > > > + VHOST_CONFIG_LOG(dev->ifname, ERR, "no free
> > > > > + memory
> > > region");
> > > > > + goto close_msg_fds;
> > > > > + }
> > > > > +
> > > > > + reg->guest_phys_addr = region->guest_phys_addr;
> > > > > + reg->guest_user_addr = region->userspace_addr;
> > > > > + reg->size = region->memory_size;
> > > > > + reg->fd = ctx->fds[0];
> > > > > +
> > > > > + if (vhost_user_mmap_region(dev, reg, region->mmap_offset) < 0) {
> > > > > + VHOST_CONFIG_LOG(dev->ifname, ERR, "failed to
> > > > > + mmap
> > > region");
> > > > > + goto close_msg_fds;
> > > > > + }
> > > > > +
> > > > > + dev->mem->nregions++;
> > > > > +
> > > > > + if (dev->async_copy && rte_vfio_is_enabled("vfio"))
> > > > > + async_dma_map_region(dev, reg, true);
> > > > > +
> > > > > + if (vhost_user_postcopy_register(dev, main_fd, ctx) < 0)
> > > >
> > > > Post-copy live-migration is broken.
> > > > The assumes the vhost-user message is of type SET_MEM_TABLE, and
> > > > so assumes ctx contains a VhostUserMemory payload.
> > > > But here ctx contains a VhostUserMemoryRegion payload.
> > > >
> > > > Given the complexity of the patch, it is worrying that such issues
> > > > are overlooked.
> > > > What other features could be broken?
> > >
> > > Although I tested this before I have again tested Post-copy live
> > > migration successfully with qemu using the following steps.
> > > - Ran dpdk-testpmd while enabling poctcopy migration as option.
> > > - Ran two instances of qemu, source and destination. Source was
> > > running alpine linux while destination was started with option
> > > "-incoming
> > defer"
> > > - I did an add memory region at the source VM which invoked
> > > vhost_postcopy_register function. After this I did the same add
> > > memory region for destination VM.
> > > - The "post_copy_register" debug messages which I added in this
> > > upcoming patch-set were correctly seen on the testpmd console.
> > > - Following this I turned on migrate capabilities on source and
> > > destination VMs at qemu prompt. For destination VM I also set the
> > > incoming migration to TCP port 4444.
> > > - Set the "migrate" destination to host 127.0.0.1 TCP port 4444 and
> > > invoked command "migrate_start_postcopy"
> > >
> > > After the above steps, the Alpine Linux VM memory pages were
> > > correctly migrated to destination VM. I would be happy to share
> > > console logs of the above test and step by step commands.
> > >
> > > Source code clarification: In the function vhost_user_add_mem_reg we
> > > provide the argument of a single region of type
> > > "VhostUserMemoryRegion" in the message payload. This single memory
> > > region is then converted to type rte_vhost_mem_region (variable reg
> > > line#1761) and then added to the list of memory regions using the
> > > call vhost_user_mmap_region(line#1779). By the time,
> > > vhost_user_postcopy_register(line#1794) is called, the newl added
> > > region is
> > part of the "dev" structure.
> > >
> > > >
> > > > > + goto free_mem_table;
> > > > > +
> > > > > + dev_invalidate_vrings(dev);
> > > > > + dump_guest_pages(dev);
> > > > > +
> > > > > + return RTE_VHOST_MSG_RESULT_OK;
> > > > > +
> > > > > +free_mem_table:
> > > > > + free_all_mem_regions(dev);
> > > > > + rte_free(dev->mem);
> > > > > + dev->mem = NULL;
> > > > > rte_free(dev->guest_pages);
> > > > > dev->guest_pages = NULL;
> > > > > close_msg_fds:
> > > > > @@ -1673,6 +1805,44 @@ vhost_user_set_mem_table(struct
> > > > > virtio_net
> > > > **pdev,
> > > > > return RTE_VHOST_MSG_RESULT_ERR; }
> > > > >
> > > > > +static int
> > > > > +vhost_user_rem_mem_reg(struct virtio_net **pdev __rte_unused,
> > > > > + struct vhu_msg_context *ctx
> > > > > +__rte_unused,
> > > >
> > > > pdev and ctx are actually used.
> > >
> > > I have made the corrections in the amended patch-set I will submit
> > > following this e-mail.
> > >
> > > >
> > > >
> > > > > + int main_fd __rte_unused) {
> > > > > + uint32_t i;
> > > > > + struct virtio_net *dev = *pdev;
> > > > > + struct VhostUserMemoryRegion *region =
> > > > > +&ctx->msg.payload.memory_single.region;
> > > > > +
> > > > > + if (dev->mem != NULL && dev->mem->nregions > 0) {
> > > > > + for (i = 0; i < VHOST_MEMORY_MAX_NREGIONS; i++) {
> > > > > + struct rte_vhost_mem_region
> > > > > + *current_region = &dev->mem->regions[i];
> > > > > +
> > > > > + if (current_region->guest_user_addr == 0)
> > > > > + continue;
> > > > > +
> > > > > + /*
> > > > > + * According to the vhost-user specification:
> > > > > + * The memory region to be removed is
> > > > > + identified by its guest
> > > > address,
> > > > > + * user address and size. The mmap offset is ignored.
> > > > > + */
> > > > > + if (region->userspace_addr ==
> > > > > + current_region-
> > > >guest_user_addr
> > > > > + && region->guest_phys_addr ==
> > > > > + current_region-
> > > > >guest_phys_addr
> > > > > + && region->memory_size == current_region->size) {
> > > > > + if (dev->async_copy && rte_vfio_is_enabled("vfio"))
> > > > > +
> > > > > + async_dma_map_region(dev, current_region,
> > false);
> > > > > + dev_invalidate_vrings(dev);
> > > > > + free_mem_region(current_region);
> > > > > + dev->mem->nregions--;
> > > > > + return RTE_VHOST_MSG_RESULT_OK;
> > > > > + }
> > > > > + }
> > > > > + }
> > > > > +
> > > > > + VHOST_CONFIG_LOG(dev->ifname, ERR, "failed to find region");
> > > > > + return RTE_VHOST_MSG_RESULT_ERR; }
> > > > > +
> > > > > static bool
> > > > > vq_is_ready(struct virtio_net *dev, struct vhost_virtqueue *vq)
> > > > > {
> > > > > --
> > > > > 2.43.0
> > > > >
More information about the dev
mailing list