IB/core: Fix ib_wc structure size to remain in 64 bytes boundary

The change of slid from u16 to u32 results in sizeof(struct ib_wc)
cross 64B boundary, which causes more cache misses. This patch
rearranges the fields and remain the size to 64B.

Pahole output before this change:

struct ib_wc {
        union {
                u64                wr_id;                /*           8 */
                struct ib_cqe *    wr_cqe;               /*           8 */
        };                                               /*     0     8 */
        enum ib_wc_status          status;               /*     8     4 */
        enum ib_wc_opcode          opcode;               /*    12     4 */
        u32                        vendor_err;           /*    16     4 */
        u32                        byte_len;             /*    20     4 */
        struct ib_qp *             qp;                   /*    24     8 */
        union {
                __be32             imm_data;             /*           4 */
                u32                invalidate_rkey;      /*           4 */
        } ex;                                            /*    32     4 */
        u32                        src_qp;               /*    36     4 */
        int                        wc_flags;             /*    40     4 */
        u16                        pkey_index;           /*    44     2 */

        /* XXX 2 bytes hole, try to pack */

        u32                        slid;                 /*    48     4 */
        u8                         sl;                   /*    52     1 */
        u8                         dlid_path_bits;       /*    53     1 */
        u8                         port_num;             /*    54     1 */
        u8                         smac[6];              /*    55     6 */

        /* XXX 1 byte hole, try to pack */

        u16                        vlan_id;              /*    62     2 */
        /* --- cacheline 1 boundary (64 bytes) --- */
        u8                         network_hdr_type;     /*    64     1 */

        /* size: 72, cachelines: 2, members: 17 */
        /* sum members: 62, holes: 2, sum holes: 3 */
        /* padding: 7 */
        /* last cacheline: 8 bytes */
};

Pahole output after this change:

struct ib_wc {
        union {
                u64                wr_id;                /*           8 */
                struct ib_cqe *    wr_cqe;               /*           8 */
        };                                               /*     0     8 */
        enum ib_wc_status          status;               /*     8     4 */
        enum ib_wc_opcode          opcode;               /*    12     4 */
        u32                        vendor_err;           /*    16     4 */
        u32                        byte_len;             /*    20     4 */
        struct ib_qp *             qp;                   /*    24     8 */
        union {
                __be32             imm_data;             /*           4 */
                u32                invalidate_rkey;      /*           4 */
        } ex;                                            /*    32     4 */
        u32                        src_qp;               /*    36     4 */
        u32                        slid;                 /*    40     4 */
        int                        wc_flags;             /*    44     4 */
        u16                        pkey_index;           /*    48     2 */
        u8                         sl;                   /*    50     1 */
        u8                         dlid_path_bits;       /*    51     1 */
        u8                         port_num;             /*    52     1 */
        u8                         smac[6];              /*    53     6 */

        /* XXX 1 byte hole, try to pack */

        u16                        vlan_id;              /*    60     2 */
        u8                         network_hdr_type;     /*    62     1 */

        /* size: 64, cachelines: 1, members: 17 */
        /* sum members: 62, holes: 1, sum holes: 1 */
        /* padding: 1 */
};

Cc: <stable@vger.kernel.org> # v4.13
Fixes: 7db20ecd ("IB/core: Change wc.slid from 16 to 32 bits")
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

include/rdma/ib_verbs.h

@@ -983,9 +983,9 @@ struct ib_wc {
 		u32		invalidate_rkey;
 	} ex;
 	u32			src_qp;
+	u32			slid;
 	int			wc_flags;
 	u16			pkey_index;
-	u32			slid;
 	u8			sl;
 	u8			dlid_path_bits;
 	u8			port_num;	/* valid only for DR SMPs on switches */