iw_cxgb4: add fast-path for small REG_MR operations

When processing a REG_MR work request, if fw supports the
FW_RI_NSMR_TPTE_WR work request, and if the page list for this
registration is <= 2 pages, and the current state of the mr is INVALID,
then use FW_RI_NSMR_TPTE_WR to pass down a fully populated TPTE for FW
to write.  This avoids FW having to do an async read of the TPTE blocking
the SQ until the read completes.

To know if the current MR state is INVALID or not, iw_cxgb4 must track the
state of each fastreg MR.  The c4iw_mr struct state is updated as REG_MR
and LOCAL_INV WRs are posted and completed, when a reg_mr is destroyed,
and when RECV completions are processed that include a local invalidation.

This optimization increases small IO IOPS for both iSER and NVMF.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

1 files changed, 12 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
index 1e26669793c3..010c709ba3bb 100644
--- a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
+++ b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
@@ -669,6 +669,18 @@ struct fw_ri_fr_nsmr_wr {
 #define FW_RI_FR_NSMR_WR_DCACPU_G(x)	\
 	(((x) >> FW_RI_FR_NSMR_WR_DCACPU_S) & FW_RI_FR_NSMR_WR_DCACPU_M)
 
+struct fw_ri_fr_nsmr_tpte_wr {
+	__u8	opcode;
+	__u8   flags;
+	__u16  wrid;
+	__u8   r1[3];
+	__u8   len16;
+	__u32  r2;
+	__u32  stag;
+	struct fw_ri_tpte tpte;
+	__u64  pbl[2];
+};
+
 struct fw_ri_inv_lstag_wr {
 	__u8   opcode;
 	__u8   flags;