Re: [Qemu-devel] [PATCH v2] nvme: Implement Write Zeroes

[Kevin Wolf <kwolf@redhat.com>]

Am 05.05.2017 um 11:58 hat Christoph Hellwig geschrieben:
> Signed-off-by: Keith Busch <keith.busch@intel.com>
> [hch: ported over from qemu-nvme.git to mainline]
> Signed-off-by: Christoph Hellwig <hch@lst.de>

Keith, can you give an Acked-by for this one? (I see that the code is
originally from you, but just to make sure that you agree with the
changes made and that it is merged into qemu.git this way.)

Kevin

>  hw/block/nvme.c | 26 ++++++++++++++++++++++++++
>  hw/block/nvme.h |  1 +
>  2 files changed, 27 insertions(+)
> 
>  Changes since v1:
>   - add BDRV_REQ_MAY_UNMAP flag
> 
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index ae303d44e5..7428db9f0c 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -227,6 +227,29 @@ static uint16_t nvme_flush(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
>      return NVME_NO_COMPLETE;
>  }
>  
> +static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
> +    NvmeRequest *req)
> +{
> +    NvmeRwCmd *rw = (NvmeRwCmd *)cmd;
> +    const uint8_t lba_index = NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas);
> +    const uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds;
> +    uint64_t slba = le64_to_cpu(rw->slba);
> +    uint32_t nlb  = le16_to_cpu(rw->nlb) + 1;
> +    uint64_t aio_slba = slba << (data_shift - BDRV_SECTOR_BITS);
> +    uint32_t aio_nlb = nlb << (data_shift - BDRV_SECTOR_BITS);
> +
> +    if (slba + nlb > ns->id_ns.nsze) {
> +        return NVME_LBA_RANGE | NVME_DNR;
> +    }
> +
> +    req->has_sg = false;
> +    block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0,
> +                     BLOCK_ACCT_WRITE);
> +    req->aiocb = blk_aio_pwrite_zeroes(n->conf.blk, aio_slba, aio_nlb,
> +                                        BDRV_REQ_MAY_UNMAP, nvme_rw_cb, req);
> +    return NVME_NO_COMPLETE;
> +}
> +
>  static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
>      NvmeRequest *req)
>  {
> @@ -279,6 +302,8 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
>      switch (cmd->opcode) {
>      case NVME_CMD_FLUSH:
>          return nvme_flush(n, ns, cmd, req);
> +    case NVME_CMD_WRITE_ZEROS:
> +        return nvme_write_zeros(n, ns, cmd, req);
>      case NVME_CMD_WRITE:
>      case NVME_CMD_READ:
>          return nvme_rw(n, ns, cmd, req);
> @@ -895,6 +920,7 @@ static int nvme_init(PCIDevice *pci_dev)
>      id->sqes = (0x6 << 4) | 0x6;
>      id->cqes = (0x4 << 4) | 0x4;
>      id->nn = cpu_to_le32(n->num_namespaces);
> +    id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROS);
>      id->psd[0].mp = cpu_to_le16(0x9c4);
>      id->psd[0].enlat = cpu_to_le32(0x10);
>      id->psd[0].exlat = cpu_to_le32(0x4);
> diff --git a/hw/block/nvme.h b/hw/block/nvme.h
> index 8fb0c10756..a0d15649f9 100644
> --- a/hw/block/nvme.h
> +++ b/hw/block/nvme.h
> @@ -179,6 +179,7 @@ enum NvmeIoCommands {
>      NVME_CMD_READ               = 0x02,
>      NVME_CMD_WRITE_UNCOR        = 0x04,
>      NVME_CMD_COMPARE            = 0x05,
> +    NVME_CMD_WRITE_ZEROS        = 0x08,
>      NVME_CMD_DSM                = 0x09,
>  };
>  
> -- 
> 2.11.0
>