cxl/region: Calculate performance data for a region

Calculate and store the performance data for a CXL region. Find the worst
read and write latency for all the included ranges from each of the devices
that attributes to the region and designate that as the latency data. Sum
all the read and write bandwidth data for each of the device region and
that is the total bandwidth for the region.

The perf list is expected to be constructed before the endpoint decoders
are registered and thus there should be no early reading of the entries
from the region assemble action. The calling of the region qos calculate
function is under the protection of cxl_dpa_rwsem and will ensure that
all DPA associated work has completed.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/20240308220055.2172956-10-dave.jiang@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

2 files changed, 67 insertions, 0 deletions

diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index 02e97a90a43c..40052666ebf1 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -9,6 +9,7 @@
 #include "cxlmem.h"
 #include "core.h"
 #include "cxl.h"
+#include "core.h"
 
 struct dsmas_entry {
 	struct range dpa_range;
@@ -515,3 +516,67 @@ void cxl_coordinates_combine(struct access_coordinate *out,
 }
 
 MODULE_IMPORT_NS(CXL);
+
+void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
+				    struct cxl_endpoint_decoder *cxled)
+{
+	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+	struct cxl_port *port = cxlmd->endpoint;
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct access_coordinate hb_coord[ACCESS_COORDINATE_MAX];
+	struct access_coordinate coord;
+	struct range dpa = {
+			.start = cxled->dpa_res->start,
+			.end = cxled->dpa_res->end,
+	};
+	struct cxl_dpa_perf *perf;
+	int rc;
+
+	switch (cxlr->mode) {
+	case CXL_DECODER_RAM:
+		perf = &mds->ram_perf;
+		break;
+	case CXL_DECODER_PMEM:
+		perf = &mds->pmem_perf;
+		break;
+	default:
+		return;
+	}
+
+	lockdep_assert_held(&cxl_dpa_rwsem);
+
+	if (!range_contains(&perf->dpa_range, &dpa))
+		return;
+
+	rc = cxl_hb_get_perf_coordinates(port, hb_coord);
+	if (rc)  {
+		dev_dbg(&port->dev, "Failed to retrieve hb perf coordinates.\n");
+		return;
+	}
+
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+		/* Pickup the host bridge coords */
+		cxl_coordinates_combine(&coord, &hb_coord[i], &perf->coord);
+
+		/* Get total bandwidth and the worst latency for the cxl region */
+		cxlr->coord[i].read_latency = max_t(unsigned int,
+						    cxlr->coord[i].read_latency,
+						    coord.read_latency);
+		cxlr->coord[i].write_latency = max_t(unsigned int,
+						     cxlr->coord[i].write_latency,
+						     coord.write_latency);
+		cxlr->coord[i].read_bandwidth += coord.read_bandwidth;
+		cxlr->coord[i].write_bandwidth += coord.write_bandwidth;
+
+		/*
+		 * Convert latency to nanosec from picosec to be consistent
+		 * with the resulting latency coordinates computed by the
+		 * HMAT_REPORTING code.
+		 */
+		cxlr->coord[i].read_latency =
+			DIV_ROUND_UP(cxlr->coord[i].read_latency, 1000);
+		cxlr->coord[i].write_latency =
+			DIV_ROUND_UP(cxlr->coord[i].write_latency, 1000);
+	}
+}
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 4c7fd2d5cccb..9a0d2d7621de 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -1752,6 +1752,8 @@ static int cxl_region_attach(struct cxl_region *cxlr,
 		return -EINVAL;
 	}
 
+	cxl_region_perf_data_calculate(cxlr, cxled);
+
 	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
 		int i;