On Thu, 2012-05-17 at 15:48 -0400, andros@xxxxxxxxxx wrote:
> From: Andy Adamson <andros@xxxxxxxxxx>
>
> We only support one layout type per file system, so one threshold_item4 per
> mdsthreshold4.
>
> Signed-off-by: Andy Adamson <andros@xxxxxxxxxx>
> ---
> fs/nfs/nfs4xdr.c | 125 ++++++++++++++++++++++++++++++++++++++++++++++-
> include/linux/nfs4.h | 7 +++
> include/linux/nfs_xdr.h | 10 ++++
> 3 files changed, 140 insertions(+), 2 deletions(-)
>
> diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
> index db040e9..27eb873 100644
> --- a/fs/nfs/nfs4xdr.c
> +++ b/fs/nfs/nfs4xdr.c
> @@ -99,9 +99,12 @@ static int nfs4_stat_to_errno(int);
> #define nfs4_path_maxsz (1 + ((3 + NFS4_MAXPATHLEN) >> 2))
> #define nfs4_owner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ))
> #define nfs4_group_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ))
> +/* We support only one layout type per file system */
> +#define decode_mdsthreshold_maxsz (1 + 1 + nfs4_fattr_bitmap_maxsz + 1 + 8)
> /* This is based on getfattr, which uses the most attributes: */
> #define nfs4_fattr_value_maxsz (1 + (1 + 2 + 2 + 4 + 2 + 1 + 1 + 2 + 2 + \
> - 3 + 3 + 3 + nfs4_owner_maxsz + nfs4_group_maxsz))
> + 3 + 3 + 3 + nfs4_owner_maxsz + \
> + nfs4_group_maxsz + decode_mdsthreshold_maxsz))
> #define nfs4_fattr_maxsz (nfs4_fattr_bitmap_maxsz + \
> nfs4_fattr_value_maxsz)
> #define decode_getattr_maxsz (op_decode_hdr_maxsz + nfs4_fattr_maxsz)
> @@ -1170,6 +1173,16 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c
> bitmask[1] & nfs4_fattr_bitmap[1], hdr);
> }
>
> +static void encode_getfattr_open(struct xdr_stream *xdr, const u32 *bitmask,
> + struct compound_hdr *hdr)
> +{
> + encode_getattr_three(xdr,
> + bitmask[0] & nfs4_fattr_bitmap[0],
> + bitmask[1] & nfs4_fattr_bitmap[1],
> + bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD,
> + hdr);
> +}
> +
> static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
> {
> encode_getattr_three(xdr,
> @@ -2197,7 +2210,7 @@ static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req,
> encode_sequence(xdr, &args->seq_args, &hdr);
> encode_putfh(xdr, args->fh, &hdr);
> encode_open(xdr, args, &hdr);
> - encode_getfattr(xdr, args->bitmask, &hdr);
> + encode_getfattr_open(xdr, args->bitmask, &hdr);
> encode_nops(&hdr);
> }
>
> @@ -4183,6 +4196,110 @@ xdr_error:
> return status;
> }
>
> +static int decode_threshold_hint(struct xdr_stream *xdr,
> + uint32_t *bitmap,
> + uint64_t *res,
> + uint32_t hint_bit)
> +{
> + __be32 *p;
> +
> + *res = 0;
> + if (likely(bitmap[0] & hint_bit)) {
> + p = xdr_inline_decode(xdr, 8);
> + if (unlikely(!p))
> + goto out_overflow;
> + xdr_decode_hyper(p, res);
> + }
> + return 0;
> +out_overflow:
> + print_overflow_msg(__func__, xdr);
> + return -EIO;
> +}
> +
> +static int decode_first_threshold_item4(struct xdr_stream *xdr,
> + struct nfs4_threshold *res)
> +{
> + __be32 *p, *savep;
> + uint32_t bitmap[3] = {0,}, attrlen;
> + int status;
> +
> + /* layout type */
> + p = xdr_inline_decode(xdr, 4);
> + if (unlikely(!p)) {
> + print_overflow_msg(__func__, xdr);
> + return -EIO;
> + }
> + res->l_type = be32_to_cpup(p);
> +
> + /* thi_hintset bitmap */
> + status = decode_attr_bitmap(xdr, bitmap);
> + if (status < 0)
> + goto xdr_error;
> +
> + /* thi_hintlist length */
> + status = decode_attr_length(xdr, &attrlen, &savep);
> + if (status < 0)
> + goto xdr_error;
> + /* thi_hintlist */
> + status = decode_threshold_hint(xdr, bitmap, &res->rd_sz, THRESHOLD_RD);
> + if (status < 0)
> + goto xdr_error;
> + status = decode_threshold_hint(xdr, bitmap, &res->wr_sz, THRESHOLD_WR);
> + if (status < 0)
> + goto xdr_error;
> + status = decode_threshold_hint(xdr, bitmap, &res->rd_io_sz,
> + THRESHOLD_RD_IO);
> + if (status < 0)
> + goto xdr_error;
> + status = decode_threshold_hint(xdr, bitmap, &res->wr_io_sz,
> + THRESHOLD_WR_IO);
> + if (status < 0)
> + goto xdr_error;
> +
> + status = verify_attr_len(xdr, savep, attrlen);
> + res->bm = bitmap[0];
> +
> + dprintk("%s bm=0x%x rd_sz=%llu wr_sz=%llu rd_io=%llu wr_io=%llu\n",
> + __func__, res->bm, res->rd_sz, res->wr_sz, res->rd_io_sz,
> + res->wr_io_sz);
> +xdr_error:
> + dprintk("%s ret=%d!\n", __func__, status);
> + return status;
> +}
> +
> +/*
> + * Thresholds on pNFS direct I/O vrs MDS I/O
> + */
> +static int decode_attr_mdsthreshold(struct xdr_stream *xdr,
> + uint32_t *bitmap,
> + struct nfs4_threshold *res)
> +{
> + __be32 *p;
> + int status = 0;
> + uint32_t num;
> +
> + if (unlikely(bitmap[2] & (FATTR4_WORD2_MDSTHRESHOLD - 1U)))
> + return -EIO;
> + if (likely(bitmap[2] & FATTR4_WORD2_MDSTHRESHOLD)) {
> + p = xdr_inline_decode(xdr, 4);
> + if (unlikely(!p))
> + goto out_overflow;
> + num = be32_to_cpup(p);
> + if (num == 0)
> + return 0;
> + if (num > 1)
> + printk(KERN_INFO "%s: Warning: Multiple pNFS layout "
> + "drivers per filesystem not supported\n",
> + __func__);
> +
> + status = decode_first_threshold_item4(xdr, res);
> + }
> + return status;
> +out_overflow:
> + print_overflow_msg(__func__, xdr);
> + return -EIO;
> +}
> +
> static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
> struct nfs_fattr *fattr, struct nfs_fh *fh,
> struct nfs4_fs_locations *fs_loc,
> @@ -4289,6 +4406,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
> goto xdr_error;
> fattr->valid |= status;
>
> + status = decode_attr_mdsthreshold(xdr, bitmap, &fattr->mdsthreshold);
> + if (status < 0)
> + goto xdr_error;
> +
> xdr_error:
> dprintk("%s: xdr returned %d\n", __func__, -status);
> return status;
> diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
> index 0987146..72b6bad 100644
> --- a/include/linux/nfs4.h
> +++ b/include/linux/nfs4.h
> @@ -526,6 +526,13 @@ enum lock_type4 {
> #define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23)
> #define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30)
> #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1)
> +#define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4)
> +
> +/* MDS threshold bitmap bits */
> +#define THRESHOLD_RD (1UL << 0)
> +#define THRESHOLD_WR (1UL << 1)
> +#define THRESHOLD_RD_IO (1UL << 2)
> +#define THRESHOLD_WR_IO (1UL << 3)
>
> #define NFSPROC4_NULL 0
> #define NFSPROC4_COMPOUND 1
> diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
> index 2e53a3f..d23379d 100644
> --- a/include/linux/nfs_xdr.h
> +++ b/include/linux/nfs_xdr.h
> @@ -35,6 +35,15 @@ static inline int nfs_fsid_equal(const struct nfs_fsid *a, const struct nfs_fsid
> return a->major == b->major && a->minor == b->minor;
> }
>
> +struct nfs4_threshold {
> + __u32 bm;
> + __u32 l_type;
> + __u64 rd_sz;
> + __u64 wr_sz;
> + __u64 rd_io_sz;
> + __u64 wr_io_sz;
> +};
> +
> struct nfs_fattr {
> unsigned int valid; /* which fields are valid */
> umode_t mode;
> @@ -67,6 +76,7 @@ struct nfs_fattr {
> unsigned long gencount;
> struct nfs4_string *owner_name;
> struct nfs4_string *group_name;
> + struct nfs4_threshold mdsthreshold; /* pNFS threshold hints */
It should _not_ be necessary to put one of these in each and every
struct nfs_fattr: that is an increase of 32 bytes for something that is
only of interest to NFSv4.1, and only on OPEN at that.
Please make it a pointer to an mdsthreshold structure that is stored in
the struct opendata.
> };
>
> #define NFS_ATTR_FATTR_TYPE (1U << 0)
--
Trond Myklebust
Linux NFS client maintainer
NetApp
Trond.Myklebust@xxxxxxxxxx
www.netapp.com
��.n��������+%������w��{.n�����{��w��� jg��� �����ݢj����G���� ���j:+v���w�m������w�������h�����٥
