1 files changed, 56 insertions, 25 deletions

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 3e817a6f94c6a..4c7fd2d5cccb2 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -397,7 +397,7 @@ static ssize_t interleave_ways_store(struct device *dev,
 		return rc;
 
 	/*
-	 * Even for x3, x9, and x12 interleaves the region interleave must be a
+	 * Even for x3, x6, and x12 interleaves the region interleave must be a
 	 * power of 2 multiple of the host bridge interleave.
 	 */
 	if (!is_power_of_2(val / cxld->interleave_ways) ||
@@ -525,7 +525,7 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size)
 	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent);
 	struct cxl_region_params *p = &cxlr->params;
 	struct resource *res;
-	u32 remainder = 0;
+	u64 remainder = 0;
 
 	lockdep_assert_held_write(&cxl_region_rwsem);
 
@@ -545,15 +545,16 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size)
 	    (cxlr->mode == CXL_DECODER_PMEM && uuid_is_null(&p->uuid)))
 		return -ENXIO;
 
-	div_u64_rem(size, SZ_256M * p->interleave_ways, &remainder);
+	div64_u64_rem(size, (u64)SZ_256M * p->interleave_ways, &remainder);
 	if (remainder)
 		return -EINVAL;
 
 	res = alloc_free_mem_region(cxlrd->res, size, SZ_256M,
 				    dev_name(&cxlr->dev));
 	if (IS_ERR(res)) {
-		dev_dbg(&cxlr->dev, "failed to allocate HPA: %ld\n",
-			PTR_ERR(res));
+		dev_dbg(&cxlr->dev,
+			"HPA allocation error (%ld) for size:%pap in %s %pr\n",
+			PTR_ERR(res), &size, cxlrd->res->name, cxlrd->res);
 		return PTR_ERR(res);
 	}
 
@@ -729,12 +730,17 @@ static int match_auto_decoder(struct device *dev, void *data)
 	return 0;
 }
 
-static struct cxl_decoder *cxl_region_find_decoder(struct cxl_port *port,
-						   struct cxl_region *cxlr)
+static struct cxl_decoder *
+cxl_region_find_decoder(struct cxl_port *port,
+			struct cxl_endpoint_decoder *cxled,
+			struct cxl_region *cxlr)
 {
 	struct device *dev;
 	int id = 0;
 
+	if (port == cxled_to_port(cxled))
+		return &cxled->cxld;
+
 	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags))
 		dev = device_find_child(&port->dev, &cxlr->params,
 					match_auto_decoder);
@@ -752,8 +758,31 @@ static struct cxl_decoder *cxl_region_find_decoder(struct cxl_port *port,
 	return to_cxl_decoder(dev);
 }
 
-static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port,
-					       struct cxl_region *cxlr)
+static bool auto_order_ok(struct cxl_port *port, struct cxl_region *cxlr_iter,
+			  struct cxl_decoder *cxld)
+{
+	struct cxl_region_ref *rr = cxl_rr_load(port, cxlr_iter);
+	struct cxl_decoder *cxld_iter = rr->decoder;
+
+	/*
+	 * Allow the out of order assembly of auto-discovered regions.
+	 * Per CXL Spec 3.1 8.2.4.20.12 software must commit decoders
+	 * in HPA order. Confirm that the decoder with the lesser HPA
+	 * starting address has the lesser id.
+	 */
+	dev_dbg(&cxld->dev, "check for HPA violation %s:%d < %s:%d\n",
+		dev_name(&cxld->dev), cxld->id,
+		dev_name(&cxld_iter->dev), cxld_iter->id);
+
+	if (cxld_iter->id > cxld->id)
+		return true;
+
+	return false;
+}
+
+static struct cxl_region_ref *
+alloc_region_ref(struct cxl_port *port, struct cxl_region *cxlr,
+		 struct cxl_endpoint_decoder *cxled)
 {
 	struct cxl_region_params *p = &cxlr->params;
 	struct cxl_region_ref *cxl_rr, *iter;
@@ -763,16 +792,21 @@ static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port,
 	xa_for_each(&port->regions, index, iter) {
 		struct cxl_region_params *ip = &iter->region->params;
 
-		if (!ip->res)
+		if (!ip->res || ip->res->start < p->res->start)
 			continue;
 
-		if (ip->res->start > p->res->start) {
-			dev_dbg(&cxlr->dev,
-				"%s: HPA order violation %s:%pr vs %pr\n",
-				dev_name(&port->dev),
-				dev_name(&iter->region->dev), ip->res, p->res);
-			return ERR_PTR(-EBUSY);
+		if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
+			struct cxl_decoder *cxld;
+
+			cxld = cxl_region_find_decoder(port, cxled, cxlr);
+			if (auto_order_ok(port, iter->region, cxld))
+				continue;
 		}
+		dev_dbg(&cxlr->dev, "%s: HPA order violation %s:%pr vs %pr\n",
+			dev_name(&port->dev),
+			dev_name(&iter->region->dev), ip->res, p->res);
+
+		return ERR_PTR(-EBUSY);
 	}
 
 	cxl_rr = kzalloc(sizeof(*cxl_rr), GFP_KERNEL);
@@ -852,10 +886,7 @@ static int cxl_rr_alloc_decoder(struct cxl_port *port, struct cxl_region *cxlr,
 {
 	struct cxl_decoder *cxld;
 
-	if (port == cxled_to_port(cxled))
-		cxld = &cxled->cxld;
-	else
-		cxld = cxl_region_find_decoder(port, cxlr);
+	cxld = cxl_region_find_decoder(port, cxled, cxlr);
 	if (!cxld) {
 		dev_dbg(&cxlr->dev, "%s: no decoder available\n",
 			dev_name(&port->dev));
@@ -952,7 +983,7 @@ static int cxl_port_attach_region(struct cxl_port *port,
 			nr_targets_inc = true;
 		}
 	} else {
-		cxl_rr = alloc_region_ref(port, cxlr);
+		cxl_rr = alloc_region_ref(port, cxlr, cxled);
 		if (IS_ERR(cxl_rr)) {
 			dev_dbg(&cxlr->dev,
 				"%s: failed to allocate region reference\n",
@@ -2083,13 +2114,13 @@ static struct cxl_region *to_cxl_region(struct device *dev)
 	return container_of(dev, struct cxl_region, dev);
 }
 
-static void unregister_region(void *dev)
+static void unregister_region(void *_cxlr)
 {
-	struct cxl_region *cxlr = to_cxl_region(dev);
+	struct cxl_region *cxlr = _cxlr;
 	struct cxl_region_params *p = &cxlr->params;
 	int i;
 
-	device_del(dev);
+	device_del(&cxlr->dev);
 
 	/*
 	 * Now that region sysfs is shutdown, the parameter block is now
@@ -2100,7 +2131,7 @@ static void unregister_region(void *dev)
 		detach_target(cxlr, i);
 
 	cxl_region_iomem_release(cxlr);
-	put_device(dev);
+	put_device(&cxlr->dev);
 }
 
 static struct lock_class_key cxl_region_key;