Re: [Qemu-devel] [PATCH v2 1/2] vhost: add used memslot number for vhost-user and vhost-kernel separately

[Zhoujian (jay)]

> -----Original Message-----
> From: Igor Mammedov [mailto:address@hidden
> Sent: Saturday, December 23, 2017 12:25 AM
> To: Zhoujian (jay) <address@hidden>
> Cc: address@hidden; address@hidden; Huangweidong (C)
> <address@hidden>; Gonglei (Arei) <address@hidden>;
> wangxin (U) <address@hidden>; Liuzhe (Cloud Open Labs, NFV)
> <address@hidden>; address@hidden
> Subject: Re: [PATCH v2 1/2] vhost: add used memslot number for vhost-user
> and vhost-kernel separately
> 
> On Fri, 15 Dec 2017 16:45:54 +0800
> Jay Zhou <address@hidden> wrote:
> 
> > Used_memslots is equal to dev->mem->nregions now, it is true for vhost
> > kernel, but not for vhost user, which uses the memory regions that
> > have file descriptor. In fact, not all of the memory regions have file
> > descriptor.
> > It is usefully in some scenarios, e.g. used_memslots is 8, and only
> > 5 memory slots can be used by vhost user, it is failed to hot plug a
> > new memory RAM because vhost_has_free_slot just returned false, but we
> > can hot plug it safely in fact.
> 
> a bit of rant:
> it seems vhost is chasing after a tail (1-2 regions that are not actually
> RAM), while approach will allow to hotplug 1-2 extra dimms vhost-user
> still will be limited to 8 regions max.
> 
> 
> vhost-user protocol should be extended to allow qemu query limit value
> from backend (which in turn should be tunable), so that backend could be
> configured to meet user needs.

Michael mentioned it can be extended with a protocol flag, here is the 
discussion
thread:
https://lists.gnu.org/archive/html/qemu-devel/2017-11/msg04656.html

> 
> Jay,
> would you like to look into it?

Yes, will look into it.

> 
> Otherwise it looks like patch will do its job, see for a minor suggestion
> below.
> 
> > Signed-off-by: Jay Zhou <address@hidden>
> > Signed-off-by: Zhe Liu <address@hidden>
> > ---
> >  hw/virtio/vhost-backend.c         | 14 ++++++++++++++
> >  hw/virtio/vhost-user.c            | 31 +++++++++++++++++++++++++++++++
> >  hw/virtio/vhost.c                 | 16 +++++++++-------
> >  include/hw/virtio/vhost-backend.h |  4 ++++
> >  4 files changed, 58 insertions(+), 7 deletions(-)
> >
> > diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c
> > index 7f09efa..866718c 100644
> > --- a/hw/virtio/vhost-backend.c
> > +++ b/hw/virtio/vhost-backend.c
> > @@ -15,6 +15,8 @@
> >  #include "hw/virtio/vhost-backend.h"
> >  #include "qemu/error-report.h"
> >
> > +static unsigned int vhost_kernel_used_memslots;
> > +
> >  static int vhost_kernel_call(struct vhost_dev *dev, unsigned long int
> request,
> >                               void *arg)  { @@ -233,6 +235,16 @@
> > static void vhost_kernel_set_iotlb_callback(struct vhost_dev *dev,
> >          qemu_set_fd_handler((uintptr_t)dev->opaque, NULL, NULL,
> > NULL);  }
> >
> > +static void vhost_kernel_set_used_memslots(struct vhost_dev *dev) {
> > +    vhost_kernel_used_memslots = dev->mem->nregions; }
> > +
> > +static unsigned int vhost_kernel_get_used_memslots(void)
> > +{
> > +    return vhost_kernel_used_memslots; }
> > +
> >  static const VhostOps kernel_ops = {
> >          .backend_type = VHOST_BACKEND_TYPE_KERNEL,
> >          .vhost_backend_init = vhost_kernel_init, @@ -264,6 +276,8 @@
> > static const VhostOps kernel_ops = {  #endif /* CONFIG_VHOST_VSOCK */
> >          .vhost_set_iotlb_callback = vhost_kernel_set_iotlb_callback,
> >          .vhost_send_device_iotlb_msg =
> > vhost_kernel_send_device_iotlb_msg,
> > +        .vhost_set_used_memslots = vhost_kernel_set_used_memslots,
> > +        .vhost_get_used_memslots = vhost_kernel_get_used_memslots,
> >  };
> >
> >  int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType
> > backend_type) diff --git a/hw/virtio/vhost-user.c
> > b/hw/virtio/vhost-user.c index 093675e..58a4cec 100644
> > --- a/hw/virtio/vhost-user.c
> > +++ b/hw/virtio/vhost-user.c
> > @@ -122,6 +122,8 @@ static VhostUserMsg m __attribute__ ((unused));
> >  /* The version of the protocol we support */
> >  #define VHOST_USER_VERSION    (0x1)
> >
> > +static unsigned int vhost_user_used_memslots;
> > +
> >  struct vhost_user {
> >      CharBackend *chr;
> >      int slave_fd;
> > @@ -922,6 +924,33 @@ static void vhost_user_set_iotlb_callback(struct
> vhost_dev *dev, int enabled)
> >      /* No-op as the receive channel is not dedicated to IOTLB
> > messages. */  }
> >
> > +static void vhost_user_set_used_memslots(struct vhost_dev *dev) {
> > +    int counter = 0;
> > +    int i;
> > +
> > +    for (i = 0; i < dev->mem->nregions; ++i) {
> > +        struct vhost_memory_region *reg = dev->mem->regions + i;
> > +        ram_addr_t offset;
> > +        MemoryRegion *mr;
> > +        int fd;
> > +
> > +        assert((uintptr_t)reg->userspace_addr == reg->userspace_addr);
> > +        mr = memory_region_from_host((void *)(uintptr_t)reg-
> >userspace_addr,
> > +                                    &offset);
> > +        fd = memory_region_get_fd(mr);
> > +        if (fd > 0) {
> > +            counter++;
> > +        }
> > +    }
> vhost_user_set_mem_table() already does the same counting, there is no
> point in duplicating it, just drop vhost_set_used_memslots callback
> 
> > +    vhost_user_used_memslots = counter;
> and update this value from vhost_user_set_mem_table()
> 

Answered in another thread.

Regards,
Jay

> > +}
> > +
> > +static unsigned int vhost_user_get_used_memslots(void)
> > +{
> > +    return vhost_user_used_memslots;
> > +}
> > +
> >  const VhostOps user_ops = {
> >          .backend_type = VHOST_BACKEND_TYPE_USER,
> >          .vhost_backend_init = vhost_user_init, @@ -948,4 +977,6 @@
> > const VhostOps user_ops = {
> >          .vhost_net_set_mtu = vhost_user_net_set_mtu,
> >          .vhost_set_iotlb_callback = vhost_user_set_iotlb_callback,
> >          .vhost_send_device_iotlb_msg =
> > vhost_user_send_device_iotlb_msg,
> > +        .vhost_set_used_memslots = vhost_user_set_used_memslots,
> > +        .vhost_get_used_memslots = vhost_user_get_used_memslots,
> >  };
> > diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index
> > e4290ce..59a32e9 100644
> > --- a/hw/virtio/vhost.c
> > +++ b/hw/virtio/vhost.c
> > @@ -43,20 +43,21 @@
> >  static struct vhost_log *vhost_log;
> >  static struct vhost_log *vhost_log_shm;
> >
> > -static unsigned int used_memslots;
> >  static QLIST_HEAD(, vhost_dev) vhost_devices =
> >      QLIST_HEAD_INITIALIZER(vhost_devices);
> >
> >  bool vhost_has_free_slot(void)
> >  {
> > -    unsigned int slots_limit = ~0U;
> >      struct vhost_dev *hdev;
> >
> >      QLIST_FOREACH(hdev, &vhost_devices, entry) {
> > -        unsigned int r = hdev->vhost_ops-
> >vhost_backend_memslots_limit(hdev);
> > -        slots_limit = MIN(slots_limit, r);
> > +        if (hdev->vhost_ops->vhost_get_used_memslots() >=
> > +            hdev->vhost_ops->vhost_backend_memslots_limit(hdev)) {
> > +            return false;
> > +        }
> >      }
> > -    return slots_limit > used_memslots;
> > +
> > +    return true;
> >  }
> >
> >  static void vhost_dev_sync_region(struct vhost_dev *dev, @@ -606,7
> > +607,7 @@ static void vhost_set_memory(MemoryListener *listener,
> >      dev->mem_changed_start_addr = MIN(dev->mem_changed_start_addr,
> start_addr);
> >      dev->mem_changed_end_addr = MAX(dev->mem_changed_end_addr,
> start_addr + size - 1);
> >      dev->memory_changed = true;
> > -    used_memslots = dev->mem->nregions;
> > +    dev->vhost_ops->vhost_set_used_memslots(dev);
> >  }
> >
> >  static bool vhost_section(MemoryRegionSection *section) @@ -1251,7
> > +1252,8 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
> >          goto fail;
> >      }
> >
> > -    if (used_memslots > hdev->vhost_ops-
> >vhost_backend_memslots_limit(hdev)) {
> > +    if (hdev->vhost_ops->vhost_get_used_memslots() >
> > +        hdev->vhost_ops->vhost_backend_memslots_limit(hdev)) {
> >          error_report("vhost backend memory slots limit is less"
> >                  " than current number of present memory slots");
> >          r = -1;
> > diff --git a/include/hw/virtio/vhost-backend.h
> > b/include/hw/virtio/vhost-backend.h
> > index a7a5f22..19961b5 100644
> > --- a/include/hw/virtio/vhost-backend.h
> > +++ b/include/hw/virtio/vhost-backend.h
> > @@ -84,6 +84,8 @@ typedef void (*vhost_set_iotlb_callback_op)(struct
> vhost_dev *dev,
> >                                             int enabled);  typedef int
> > (*vhost_send_device_iotlb_msg_op)(struct vhost_dev *dev,
> >                                                struct vhost_iotlb_msg
> > *imsg);
> > +typedef void (*vhost_set_used_memslots_op)(struct vhost_dev *dev);
> > +typedef unsigned int (*vhost_get_used_memslots_op)(void);
> >
> >  typedef struct VhostOps {
> >      VhostBackendType backend_type;
> > @@ -118,6 +120,8 @@ typedef struct VhostOps {
> >      vhost_vsock_set_running_op vhost_vsock_set_running;
> >      vhost_set_iotlb_callback_op vhost_set_iotlb_callback;
> >      vhost_send_device_iotlb_msg_op vhost_send_device_iotlb_msg;
> > +    vhost_set_used_memslots_op vhost_set_used_memslots;
> > +    vhost_get_used_memslots_op vhost_get_used_memslots;
> >  } VhostOps;
> >
> >  extern const VhostOps user_ops;