Merge branch 'for-6.5/cxl-region-fixes' into for-6.5/cxl

Pick up the recent fixes to how CPU caches are managed relative to
region setup / teardown, and make sure that all decoders transition
successfully before updating the region state from COMMIT => ACTIVE.

drivers/cxl/core/region.c

@@ -125,10 +125,38 @@ static struct cxl_region_ref *cxl_rr_load(struct cxl_port *port,
 	return xa_load(&port->regions, (unsigned long)cxlr);
 }
 
+static int cxl_region_invalidate_memregion(struct cxl_region *cxlr)
+{
+	if (!cpu_cache_has_invalidate_memregion()) {
+		if (IS_ENABLED(CONFIG_CXL_REGION_INVALIDATION_TEST)) {
+			dev_warn_once(
+				&cxlr->dev,
+				"Bypassing cpu_cache_invalidate_memregion() for testing!\n");
+			return 0;
+		} else {
+			dev_err(&cxlr->dev,
+				"Failed to synchronize CPU cache state\n");
+			return -ENXIO;
+		}
+	}
+
+	cpu_cache_invalidate_memregion(IORES_DESC_CXL);
+	return 0;
+}
+
 static int cxl_region_decode_reset(struct cxl_region *cxlr, int count)
 {
 	struct cxl_region_params *p = &cxlr->params;
-	int i;
+	int i, rc = 0;
+
+	/*
+	 * Before region teardown attempt to flush, and if the flush
+	 * fails cancel the region teardown for data consistency
+	 * concerns
+	 */
+	rc = cxl_region_invalidate_memregion(cxlr);
+	if (rc)
+		return rc;
 
 	for (i = count - 1; i >= 0; i--) {
 		struct cxl_endpoint_decoder *cxled = p->targets[i];
@@ -136,7 +164,6 @@ static int cxl_region_decode_reset(struct cxl_region *cxlr, int count)
 		struct cxl_port *iter = cxled_to_port(cxled);
 		struct cxl_dev_state *cxlds = cxlmd->cxlds;
 		struct cxl_ep *ep;
-		int rc = 0;
 
 		if (cxlds->rcd)
 			goto endpoint_reset;
@@ -155,14 +182,19 @@ static int cxl_region_decode_reset(struct cxl_region *cxlr, int count)
 				rc = cxld->reset(cxld);
 			if (rc)
 				return rc;
+			set_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
 		}
 
 endpoint_reset:
 		rc = cxled->cxld.reset(&cxled->cxld);
 		if (rc)
 			return rc;
+		set_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
 	}
 
+	/* all decoders associated with this region have been torn down */
+	clear_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
+
 	return 0;
 }
 
@@ -256,9 +288,19 @@ static ssize_t commit_store(struct device *dev, struct device_attribute *attr,
 		goto out;
 	}
 
-	if (commit)
+	/*
+	 * Invalidate caches before region setup to drop any speculative
+	 * consumption of this address space
+	 */
+	rc = cxl_region_invalidate_memregion(cxlr);
+	if (rc)
+		return rc;
+
+	if (commit) {
 		rc = cxl_region_decode_commit(cxlr);
-	else {
+		if (rc == 0)
+			p->state = CXL_CONFIG_COMMIT;
+	} else {
 		p->state = CXL_CONFIG_RESET_PENDING;
 		up_write(&cxl_region_rwsem);
 		device_release_driver(&cxlr->dev);
@@ -268,18 +310,20 @@ static ssize_t commit_store(struct device *dev, struct device_attribute *attr,
 		 * The lock was dropped, so need to revalidate that the reset is
 		 * still pending.
 		 */
-		if (p->state == CXL_CONFIG_RESET_PENDING)
+		if (p->state == CXL_CONFIG_RESET_PENDING) {
 			rc = cxl_region_decode_reset(cxlr, p->interleave_ways);
+			/*
+			 * Revert to committed since there may still be active
+			 * decoders associated with this region, or move forward
+			 * to active to mark the reset successful
+			 */
+			if (rc)
+				p->state = CXL_CONFIG_COMMIT;
+			else
+				p->state = CXL_CONFIG_ACTIVE;
+		}
 	}
 
-	if (rc)
-		goto out;
-
-	if (commit)
-		p->state = CXL_CONFIG_COMMIT;
-	else if (p->state == CXL_CONFIG_RESET_PENDING)
-		p->state = CXL_CONFIG_ACTIVE;
-
 out:
 	up_write(&cxl_region_rwsem);
 
@@ -1686,7 +1730,6 @@ static int cxl_region_attach(struct cxl_region *cxlr,
 		if (rc)
 			goto err_decrement;
 		p->state = CXL_CONFIG_ACTIVE;
-		set_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags);
 	}
 
 	cxled->cxld.interleave_ways = p->interleave_ways;
@@ -2815,30 +2858,6 @@ int cxl_add_to_region(struct cxl_port *root, struct cxl_endpoint_decoder *cxled)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_add_to_region, CXL);
 
-static int cxl_region_invalidate_memregion(struct cxl_region *cxlr)
-{
-	if (!test_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags))
-		return 0;
-
-	if (!cpu_cache_has_invalidate_memregion()) {
-		if (IS_ENABLED(CONFIG_CXL_REGION_INVALIDATION_TEST)) {
-			dev_warn_once(
-				&cxlr->dev,
-				"Bypassing cpu_cache_invalidate_memregion() for testing!\n");
-			clear_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags);
-			return 0;
-		} else {
-			dev_err(&cxlr->dev,
-				"Failed to synchronize CPU cache state\n");
-			return -ENXIO;
-		}
-	}
-
-	cpu_cache_invalidate_memregion(IORES_DESC_CXL);
-	clear_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags);
-	return 0;
-}
-
 static int is_system_ram(struct resource *res, void *arg)
 {
 	struct cxl_region *cxlr = arg;
@@ -2866,7 +2885,12 @@ static int cxl_region_probe(struct device *dev)
 		goto out;
 	}
 
-	rc = cxl_region_invalidate_memregion(cxlr);
+	if (test_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags)) {
+		dev_err(&cxlr->dev,
+			"failed to activate, re-commit region and retry\n");
+		rc = -ENXIO;
+		goto out;
+	}
 
 	/*
 	 * From this point on any path that changes the region's state away from

drivers/cxl/cxl.h

@@ -470,18 +470,20 @@ struct cxl_region_params {
 	int nr_targets;
 };
 
-/*
- * Flag whether this region needs to have its HPA span synchronized with
- * CPU cache state at region activation time.
- */
-#define CXL_REGION_F_INCOHERENT 0
-
 /*
  * Indicate whether this region has been assembled by autodetection or
  * userspace assembly. Prevent endpoint decoders outside of automatic
  * detection from being added to the region.
  */
-#define CXL_REGION_F_AUTO 1
+#define CXL_REGION_F_AUTO 0
+
+/*
+ * Require that a committed region successfully complete a teardown once
+ * any of its associated decoders have been torn down. This maintains
+ * the commit state for the region since there are committed decoders,
+ * but blocks cxl_region_probe().
+ */
+#define CXL_REGION_F_NEEDS_RESET 1
 
 /**
  * struct cxl_region - CXL region