From ea54b10c7773007e173da31fe7adcc049da33331 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Mon, 28 Jan 2008 10:40:59 +0200 Subject: IB/mlx4: Use multiple WQ blocks to post smaller send WQEs ConnectX HCA supports shrinking WQEs, so that a single work request can be made of multiple units of wqe_shift. This way, WRs can differ in size, and do not have to be a power of 2 in size, saving memory and speeding up send WR posting. Unfortunately, if we do this then the wqe_index field in CQEs can't be used to look up the WR ID anymore, so our implementation does this only if selective signaling is off. Further, on 32-bit platforms, we can't use vmap() to make the QP buffer virtually contigious. Thus we have to use constant-sized WRs to make sure a WR is always fully within a single page-sized chunk. Finally, we use WRs with the NOP opcode to avoid wrapping around the queue buffer in the middle of posting a WR, and we set the NoErrorCompletion bit to avoid getting completions with error for NOP WRs. However, NEC is only supported starting with firmware 2.2.232, so we use constant-sized WRs for older firmware. And, since MLX QPs only support SEND, we use constant-sized WRs in this case. When stamping during NOP posting, do stamping following setting of the NOP WQE valid bit. Signed-off-by: Michael S. Tsirkin Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 5 +++++ include/linux/mlx4/qp.h | 4 ++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 4210ac4a8bc..6cdf813cd47 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -133,6 +133,11 @@ enum { MLX4_STAT_RATE_OFFSET = 5 }; +static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor) +{ + return (major << 32) | (minor << 16) | subminor; +} + struct mlx4_caps { u64 fw_ver; int num_ports; diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 3968b943259..09a2230923f 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -154,7 +154,11 @@ struct mlx4_qp_context { u32 reserved5[10]; }; +/* Which firmware version adds support for NEC (NoErrorCompletion) bit */ +#define MLX4_FW_VER_WQE_CTRL_NEC mlx4_fw_ver(2, 2, 232) + enum { + MLX4_WQE_CTRL_NEC = 1 << 29, MLX4_WQE_CTRL_FENCE = 1 << 6, MLX4_WQE_CTRL_CQ_UPDATE = 3 << 2, MLX4_WQE_CTRL_SOLICITED = 1 << 1, -- cgit v1.2.3