Merge tag 'blk-dim-v2' into rdma.git for-next

Generic DIM

From: Tal Gilboa and Yamin Fridman

Implement net DIM over a generic DIM library, add RDMA DIM

dim.h lib exposes an implementation of the DIM algorithm for
dynamically-tuned interrupt moderation for networking interfaces.

We want a similar functionality for other protocols, which might need to
optimize interrupts differently. Main motivation here is DIM for NVMf
storage protocol.

Current DIM implementation prioritizes reducing interrupt overhead over
latency. Also, in order to reduce DIM's own overhead, the algorithm might
take some time to identify it needs to change profiles. While this is
acceptable for networking, it might not work well on other scenarios.

Here we propose a new structure to DIM. The idea is to allow a slightly
modified functionality without the risk of breaking Net DIM behavior for
netdev. We verified there are no degradations in current DIM behavior with
the modified solution.

Suggested solution:
- Common logic is implemented in lib/dim/dim.c
- Net DIM (existing) logic is implemented in lib/dim/net_dim.c, which uses
  the common logic in dim.c
- Any new DIM logic will be implemented in "lib/dim/new_dim.c".
  This new implementation will expose modified versions of profiles,
  dim_step() and dim_decision().
- DIM API is declared in include/linux/dim.h for all implementations.

Pros for this solution are:
- Zero impact on existing net_dim implementation and usage
- Relatively more code reuse (compared to two separate solutions)
- Increased extensibility

Required for dependencies in the next series.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 83 insertions, 0 deletions

diff --git a/lib/dim/dim.c b/lib/dim/dim.c
new file mode 100644
index 000000000000..439d641ec796
--- /dev/null
+++ b/lib/dim/dim.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2019, Mellanox Technologies inc.  All rights reserved.
+ */
+
+#include <linux/dim.h>
+
+bool dim_on_top(struct dim *dim)
+{
+	switch (dim->tune_state) {
+	case DIM_PARKING_ON_TOP:
+	case DIM_PARKING_TIRED:
+		return true;
+	case DIM_GOING_RIGHT:
+		return (dim->steps_left > 1) && (dim->steps_right == 1);
+	default: /* DIM_GOING_LEFT */
+		return (dim->steps_right > 1) && (dim->steps_left == 1);
+	}
+}
+EXPORT_SYMBOL(dim_on_top);
+
+void dim_turn(struct dim *dim)
+{
+	switch (dim->tune_state) {
+	case DIM_PARKING_ON_TOP:
+	case DIM_PARKING_TIRED:
+		break;
+	case DIM_GOING_RIGHT:
+		dim->tune_state = DIM_GOING_LEFT;
+		dim->steps_left = 0;
+		break;
+	case DIM_GOING_LEFT:
+		dim->tune_state = DIM_GOING_RIGHT;
+		dim->steps_right = 0;
+		break;
+	}
+}
+EXPORT_SYMBOL(dim_turn);
+
+void dim_park_on_top(struct dim *dim)
+{
+	dim->steps_right  = 0;
+	dim->steps_left   = 0;
+	dim->tired        = 0;
+	dim->tune_state   = DIM_PARKING_ON_TOP;
+}
+EXPORT_SYMBOL(dim_park_on_top);
+
+void dim_park_tired(struct dim *dim)
+{
+	dim->steps_right  = 0;
+	dim->steps_left   = 0;
+	dim->tune_state   = DIM_PARKING_TIRED;
+}
+EXPORT_SYMBOL(dim_park_tired);
+
+void dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
+		    struct dim_stats *curr_stats)
+{
+	/* u32 holds up to 71 minutes, should be enough */
+	u32 delta_us = ktime_us_delta(end->time, start->time);
+	u32 npkts = BIT_GAP(BITS_PER_TYPE(u32), end->pkt_ctr, start->pkt_ctr);
+	u32 nbytes = BIT_GAP(BITS_PER_TYPE(u32), end->byte_ctr,
+			     start->byte_ctr);
+	u32 ncomps = BIT_GAP(BITS_PER_TYPE(u32), end->comp_ctr,
+			     start->comp_ctr);
+
+	if (!delta_us)
+		return;
+
+	curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us);
+	curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us);
+	curr_stats->epms = DIV_ROUND_UP(DIM_NEVENTS * USEC_PER_MSEC,
+					delta_us);
+	curr_stats->cpms = DIV_ROUND_UP(ncomps * USEC_PER_MSEC, delta_us);
+	if (curr_stats->epms != 0)
+		curr_stats->cpe_ratio =
+				(curr_stats->cpms * 100) / curr_stats->epms;
+	else
+		curr_stats->cpe_ratio = 0;
+
+}
+EXPORT_SYMBOL(dim_calc_stats);