Re: [Virtio-fs] [PATCH v2 08/25] DAX: virtio-fs: Add vhost-user slave commands for mapping

[Greg Kurz]

On Wed, 14 Apr 2021 16:51:20 +0100
"Dr. David Alan Gilbert (git)" <dgilbert@redhat.com> wrote:

> From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
> 
> The daemon may request that fd's be mapped into the virtio-fs cache
> visible to the guest.
> These mappings are triggered by commands sent over the slave fd
> from the daemon.
> 
> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
> ---
>  docs/interop/vhost-user.rst               | 21 ++++++++
>  hw/virtio/vhost-user-fs.c                 | 66 +++++++++++++++++++++++
>  hw/virtio/vhost-user.c                    | 25 +++++++++
>  include/hw/virtio/vhost-user-fs.h         | 33 ++++++++++++
>  subprojects/libvhost-user/libvhost-user.h |  2 +
>  5 files changed, 147 insertions(+)
> 
> diff --git a/docs/interop/vhost-user.rst b/docs/interop/vhost-user.rst
> index d6085f7045..09aee3565d 100644
> --- a/docs/interop/vhost-user.rst
> +++ b/docs/interop/vhost-user.rst
> @@ -1432,6 +1432,27 @@ Slave message types
>  
>    The state.num field is currently reserved and must be set to 0.
>  
> +``VHOST_USER_SLAVE_FS_MAP``
> +  :id: 6
> +  :equivalent ioctl: N/A
> +  :slave payload: ``struct VhostUserFSSlaveMsg``
> +  :master payload: N/A
> +
> +  Requests that an fd, provided in the ancillary data, be mmapped
> +  into the virtio-fs cache; multiple chunks can be mapped in one
> +  command.
> +  A reply is generated indicating whether mapping succeeded.
> +
> +``VHOST_USER_SLAVE_FS_UNMAP``
> +  :id: 7
> +  :equivalent ioctl: N/A
> +  :slave payload: ``struct VhostUserFSSlaveMsg``
> +  :master payload: N/A
> +
> +  Requests that the range in the virtio-fs cache is unmapped;
> +  multiple chunks can be unmapped in one command.
> +  A reply is generated indicating whether unmapping succeeded.
> +
>  .. _reply_ack:
>  
>  VHOST_USER_PROTOCOL_F_REPLY_ACK
> diff --git a/hw/virtio/vhost-user-fs.c b/hw/virtio/vhost-user-fs.c
> index dd0a02aa99..169a146e72 100644
> --- a/hw/virtio/vhost-user-fs.c
> +++ b/hw/virtio/vhost-user-fs.c
> @@ -45,6 +45,72 @@ static const int user_feature_bits[] = {
>  #define DAX_WINDOW_PROT PROT_NONE
>  #endif
>  
> +/*
> + * The message apparently had 'received_size' bytes, check this
> + * matches the count in the message.
> + *
> + * Returns true if the size matches.
> + */
> +static bool check_slave_message_entries(const VhostUserFSSlaveMsg *sm,
> +                                        int received_size)
> +{
> +    int tmp;
> +
> +    /*
> +     * VhostUserFSSlaveMsg consists of a body followed by 'n' entries,
> +     * (each VhostUserFSSlaveMsgEntry).  There's a maximum of
> +     * VHOST_USER_FS_SLAVE_MAX_ENTRIES of these.
> +     */
> +    if (received_size <= sizeof(VhostUserFSSlaveMsg)) {
> +        error_report("%s: Short VhostUserFSSlaveMsg size, %d", __func__,
> +                     received_size);
> +        return false;
> +    }
> +
> +    tmp = received_size - sizeof(VhostUserFSSlaveMsg);
> +    if (tmp % sizeof(VhostUserFSSlaveMsgEntry)) {
> +        error_report("%s: Non-multiple VhostUserFSSlaveMsg size, %d", 
> __func__,
> +                     received_size);
> +        return false;
> +    }
> +
> +    tmp /= sizeof(VhostUserFSSlaveMsgEntry);
> +    if (tmp != sm->count) {
> +        error_report("%s: VhostUserFSSlaveMsg count mismatch, %d count: %d",
> +                     __func__, tmp, sm->count);
> +        return false;
> +    }
> +
> +    if (sm->count > VHOST_USER_FS_SLAVE_MAX_ENTRIES) {
> +        error_report("%s: VhostUserFSSlaveMsg too many entries: %d",
> +                     __func__, sm->count);
> +        return false;
> +    }
> +    return true;
> +}
> +
> +uint64_t vhost_user_fs_slave_map(struct vhost_dev *dev, int message_size,
> +                                 VhostUserFSSlaveMsg *sm, int fd)
> +{
> +    if (!check_slave_message_entries(sm, message_size)) {
> +        return (uint64_t)-1;
> +    }
> +
> +    /* TODO */
> +    return (uint64_t)-1;
> +}
> +
> +uint64_t vhost_user_fs_slave_unmap(struct vhost_dev *dev, int message_size,
> +                                   VhostUserFSSlaveMsg *sm)
> +{
> +    if (!check_slave_message_entries(sm, message_size)) {
> +        return (uint64_t)-1;
> +    }
> +
> +    /* TODO */
> +    return (uint64_t)-1;
> +}
> +
>  static void vuf_get_config(VirtIODevice *vdev, uint8_t *config)
>  {
>      VHostUserFS *fs = VHOST_USER_FS(vdev);
> diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
> index 3e4a25e108..ad9170f8dc 100644
> --- a/hw/virtio/vhost-user.c
> +++ b/hw/virtio/vhost-user.c
> @@ -12,6 +12,7 @@
>  #include "qapi/error.h"
>  #include "hw/virtio/vhost.h"
>  #include "hw/virtio/vhost-user.h"
> +#include "hw/virtio/vhost-user-fs.h"
>  #include "hw/virtio/vhost-backend.h"
>  #include "hw/virtio/virtio.h"
>  #include "hw/virtio/virtio-net.h"
> @@ -133,6 +134,10 @@ typedef enum VhostUserSlaveRequest {
>      VHOST_USER_SLAVE_IOTLB_MSG = 1,
>      VHOST_USER_SLAVE_CONFIG_CHANGE_MSG = 2,
>      VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG = 3,
> +    VHOST_USER_SLAVE_VRING_CALL = 4,
> +    VHOST_USER_SLAVE_VRING_ERR = 5,
> +    VHOST_USER_SLAVE_FS_MAP = 6,
> +    VHOST_USER_SLAVE_FS_UNMAP = 7,
>      VHOST_USER_SLAVE_MAX
>  }  VhostUserSlaveRequest;
>  
> @@ -205,6 +210,16 @@ typedef struct {
>      uint32_t size; /* the following payload size */
>  } QEMU_PACKED VhostUserHeader;
>  
> +/*
> + * VhostUserFSSlaveMsg is special since it has a variable entry count,
> + * but it does have a maximum, so make a type for that to fit in our union
> + * for max size.
> + */
> +typedef struct {
> +    VhostUserFSSlaveMsg fs;
> +    VhostUserFSSlaveMsgEntry entries[VHOST_USER_FS_SLAVE_MAX_ENTRIES];
> +} QEMU_PACKED VhostUserFSSlaveMsgMax;
> +
>  typedef union {
>  #define VHOST_USER_VRING_IDX_MASK   (0xff)
>  #define VHOST_USER_VRING_NOFD_MASK  (0x1<<8)
> @@ -219,6 +234,8 @@ typedef union {
>          VhostUserCryptoSession session;
>          VhostUserVringArea area;
>          VhostUserInflight inflight;
> +        VhostUserFSSlaveMsg fs;
> +        VhostUserFSSlaveMsg fs_max; /* Never actually used */
>  } VhostUserPayload;
>  
>  typedef struct VhostUserMsg {
> @@ -1538,6 +1555,14 @@ static gboolean slave_read(QIOChannel *ioc, 
> GIOCondition condition,
>          ret = vhost_user_slave_handle_vring_host_notifier(dev, &payload.area,
>                                                            fd ? fd[0] : -1);
>          break;
> +#ifdef CONFIG_VHOST_USER_FS
> +    case VHOST_USER_SLAVE_FS_MAP:
> +        ret = vhost_user_fs_slave_map(dev, hdr.size, &payload.fs, fd[0]);

Since the QIOChannel conversion, the array of fds is dynamically allocated
by qio_channel_readv_full_all() when needed. You should do "fd ? fd[0] : -1"
like for vhost_user_slave_handle_vring_host_notifier() just above.

Same goes for patch 17 "DAX/unmap: virtiofsd: Add  VHOST_USER_SLAVE_FS_IO".

> +        break;
> +    case VHOST_USER_SLAVE_FS_UNMAP:
> +        ret = vhost_user_fs_slave_unmap(dev, hdr.size, &payload.fs);
> +        break;
> +#endif
>      default:
>          error_report("Received unexpected msg type: %d.", hdr.request);
>          ret = true;
> diff --git a/include/hw/virtio/vhost-user-fs.h 
> b/include/hw/virtio/vhost-user-fs.h
> index 04596799e3..0766f17548 100644
> --- a/include/hw/virtio/vhost-user-fs.h
> +++ b/include/hw/virtio/vhost-user-fs.h
> @@ -23,6 +23,33 @@
>  #define TYPE_VHOST_USER_FS "vhost-user-fs-device"
>  OBJECT_DECLARE_SIMPLE_TYPE(VHostUserFS, VHOST_USER_FS)
>  
> +/* Structures carried over the slave channel back to QEMU */
> +#define VHOST_USER_FS_SLAVE_MAX_ENTRIES 32
> +
> +/* For the flags field of VhostUserFSSlaveMsg */
> +#define VHOST_USER_FS_FLAG_MAP_R (1u << 0)
> +#define VHOST_USER_FS_FLAG_MAP_W (1u << 1)
> +
> +typedef struct {
> +    /* Offsets within the file being mapped */
> +    uint64_t fd_offset;
> +    /* Offsets within the cache */
> +    uint64_t c_offset;
> +    /* Lengths of sections */
> +    uint64_t len;
> +    /* Flags, from VHOST_USER_FS_FLAG_* */
> +    uint64_t flags;
> +} VhostUserFSSlaveMsgEntry;
> +
> +typedef struct {
> +    /* Number of entries */
> +    uint16_t count;
> +    /* Spare */
> +    uint16_t align;
> +
> +    VhostUserFSSlaveMsgEntry entries[];
> +} VhostUserFSSlaveMsg;
> +
>  typedef struct {
>      CharBackend chardev;
>      char *tag;
> @@ -46,4 +73,10 @@ struct VHostUserFS {
>      MemoryRegion cache;
>  };
>  
> +/* Callbacks from the vhost-user code for slave commands */
> +uint64_t vhost_user_fs_slave_map(struct vhost_dev *dev, int message_size,
> +                                 VhostUserFSSlaveMsg *sm, int fd);
> +uint64_t vhost_user_fs_slave_unmap(struct vhost_dev *dev, int message_size,
> +                                   VhostUserFSSlaveMsg *sm);
> +
>  #endif /* _QEMU_VHOST_USER_FS_H */
> diff --git a/subprojects/libvhost-user/libvhost-user.h 
> b/subprojects/libvhost-user/libvhost-user.h
> index 70fc61171f..a98c5f5c11 100644
> --- a/subprojects/libvhost-user/libvhost-user.h
> +++ b/subprojects/libvhost-user/libvhost-user.h
> @@ -119,6 +119,8 @@ typedef enum VhostUserSlaveRequest {
>      VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG = 3,
>      VHOST_USER_SLAVE_VRING_CALL = 4,
>      VHOST_USER_SLAVE_VRING_ERR = 5,
> +    VHOST_USER_SLAVE_FS_MAP = 6,
> +    VHOST_USER_SLAVE_FS_UNMAP = 7,
>      VHOST_USER_SLAVE_MAX
>  }  VhostUserSlaveRequest;
>