[5.16,24/43] net/mlx5e: Avoid field-overflowing memcpy()

From: Kees Cook <keescook@chromium.org>

commit ad5185735f7dab342fdd0dd41044da4c9ccfef67 upstream.

In preparation for FORTIFY_SOURCE performing compile-time and run-time
field bounds checking for memcpy(), memmove(), and memset(), avoid
intentionally writing across neighboring fields.

Use flexible arrays instead of zero-element arrays (which look like they
are always overflowing) and split the cross-field memcpy() into two halves
that can be appropriately bounds-checked by the compiler.

We were doing:

	#define ETH_HLEN  14
	#define VLAN_HLEN  4
	...
	#define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
	...
        struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
	...
        struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
        struct mlx5_wqe_data_seg *dseg = wqe->data;
	...
	memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE);

target is wqe->eth.inline_hdr.start (which the compiler sees as being
2 bytes in size), but copying 18, intending to write across start
(really vlan_tci, 2 bytes). The remaining 16 bytes get written into
wqe->data[0], covering byte_count (4 bytes), lkey (4 bytes), and addr
(8 bytes).

struct mlx5e_tx_wqe {
        struct mlx5_wqe_ctrl_seg   ctrl;                 /*     0    16 */
        struct mlx5_wqe_eth_seg    eth;                  /*    16    16 */
        struct mlx5_wqe_data_seg   data[];               /*    32     0 */

        /* size: 32, cachelines: 1, members: 3 */
        /* last cacheline: 32 bytes */
};

struct mlx5_wqe_eth_seg {
        u8                         swp_outer_l4_offset;  /*     0     1 */
        u8                         swp_outer_l3_offset;  /*     1     1 */
        u8                         swp_inner_l4_offset;  /*     2     1 */
        u8                         swp_inner_l3_offset;  /*     3     1 */
        u8                         cs_flags;             /*     4     1 */
        u8                         swp_flags;            /*     5     1 */
        __be16                     mss;                  /*     6     2 */
        __be32                     flow_table_metadata;  /*     8     4 */
        union {
                struct {
                        __be16     sz;                   /*    12     2 */
                        u8         start[2];             /*    14     2 */
                } inline_hdr;                            /*    12     4 */
                struct {
                        __be16     type;                 /*    12     2 */
                        __be16     vlan_tci;             /*    14     2 */
                } insert;                                /*    12     4 */
                __be32             trailer;              /*    12     4 */
        };                                               /*    12     4 */

        /* size: 16, cachelines: 1, members: 9 */
        /* last cacheline: 16 bytes */
};

struct mlx5_wqe_data_seg {
        __be32                     byte_count;           /*     0     4 */
        __be32                     lkey;                 /*     4     4 */
        __be64                     addr;                 /*     8     8 */

        /* size: 16, cachelines: 1, members: 3 */
        /* last cacheline: 16 bytes */
};

So, split the memcpy() so the compiler can reason about the buffer
sizes.

"pahole" shows no size nor member offset changes to struct mlx5e_tx_wqe
nor struct mlx5e_umr_wqe. "objdump -d" shows no meaningful object
code changes (i.e. only source line number induced differences and
optimizations).

Fixes: b5503b994ed5 ("net/mlx5e: XDP TX forwarding support")
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h     |    6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c |    4 +++-
 2 files changed, 6 insertions(+), 4 deletions(-)