1 files changed, 251 insertions, 15 deletions

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 71cc42d05248..e14c1d305b22 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2022 Intel Corporation. All rights reserved. */
 #include <linux/memregion.h>
 #include <linux/genalloc.h>
+#include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/memory.h>
@@ -10,6 +11,7 @@
 #include <linux/sort.h>
 #include <linux/idr.h>
 #include <linux/memory-tiers.h>
+#include <linux/string_choices.h>
 #include <cxlmem.h>
 #include <cxl.h>
 #include "core.h"
@@ -30,6 +32,12 @@
  * 3. Decoder targets
  */
 
+/*
+ * nodemask that sets per node when the access_coordinates for the node has
+ * been updated by the CXL memory hotplug notifier.
+ */
+static nodemask_t nodemask_region_seen = NODE_MASK_NONE;
+
 static struct cxl_region *to_cxl_region(struct device *dev);
 
 #define __ACCESS_ATTR_RO(_level, _name) {				\
@@ -1468,9 +1476,7 @@ static int cxl_port_setup_targets(struct cxl_port *port,
 				dev_name(port->uport_dev), dev_name(&port->dev),
 				__func__, cxld->interleave_ways,
 				cxld->interleave_granularity,
-				(cxld->flags & CXL_DECODER_F_ENABLE) ?
-					"enabled" :
-					"disabled",
+				str_enabled_disabled(cxld->flags & CXL_DECODER_F_ENABLE),
 				cxld->hpa_range.start, cxld->hpa_range.end);
 			return -ENXIO;
 		}
@@ -1510,8 +1516,10 @@ add_target:
 				cxl_rr->nr_targets_set);
 			return -ENXIO;
 		}
-	} else
+	} else {
 		cxlsd->target[cxl_rr->nr_targets_set] = ep->dport;
+		cxlsd->cxld.target_map[cxl_rr->nr_targets_set] = ep->dport->port_id;
+	}
 	inc = 1;
 out_target_set:
 	cxl_rr->nr_targets_set += inc;
@@ -2442,14 +2450,8 @@ static bool cxl_region_update_coordinates(struct cxl_region *cxlr, int nid)
 
 	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
 		if (cxlr->coord[i].read_bandwidth) {
-			rc = 0;
-			if (cxl_need_node_perf_attrs_update(nid))
-				node_set_perf_attrs(nid, &cxlr->coord[i], i);
-			else
-				rc = cxl_update_hmat_access_coordinates(nid, cxlr, i);
-
-			if (rc == 0)
-				cset++;
+			node_update_perf_attrs(nid, &cxlr->coord[i], i);
+			cset++;
 		}
 	}
 
@@ -2487,6 +2489,10 @@ static int cxl_region_perf_attrs_callback(struct notifier_block *nb,
 	if (nid != region_nid)
 		return NOTIFY_DONE;
 
+	/* No action needed if node bit already set */
+	if (node_test_and_set(nid, nodemask_region_seen))
+		return NOTIFY_DONE;
+
 	if (!cxl_region_update_coordinates(cxlr, nid))
 		return NOTIFY_DONE;
 
@@ -2918,6 +2924,16 @@ static bool cxl_is_hpa_in_chunk(u64 hpa, struct cxl_region *cxlr, int pos)
 	return false;
 }
 
+static bool has_hpa_to_spa(struct cxl_root_decoder *cxlrd)
+{
+	return cxlrd->ops && cxlrd->ops->hpa_to_spa;
+}
+
+static bool has_spa_to_hpa(struct cxl_root_decoder *cxlrd)
+{
+	return cxlrd->ops && cxlrd->ops->spa_to_hpa;
+}
+
 u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd,
 		   u64 dpa)
 {
@@ -2972,8 +2988,8 @@ u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd,
 	hpa = hpa_offset + p->res->start + p->cache_size;
 
 	/* Root decoder translation overrides typical modulo decode */
-	if (cxlrd->hpa_to_spa)
-		hpa = cxlrd->hpa_to_spa(cxlrd, hpa);
+	if (has_hpa_to_spa(cxlrd))
+		hpa = cxlrd->ops->hpa_to_spa(cxlrd, hpa);
 
 	if (!cxl_resource_contains_addr(p->res, hpa)) {
 		dev_dbg(&cxlr->dev,
@@ -2982,12 +2998,107 @@ u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd,
 	}
 
 	/* Simple chunk check, by pos & gran, only applies to modulo decodes */
-	if (!cxlrd->hpa_to_spa && (!cxl_is_hpa_in_chunk(hpa, cxlr, pos)))
+	if (!has_hpa_to_spa(cxlrd) && (!cxl_is_hpa_in_chunk(hpa, cxlr, pos)))
 		return ULLONG_MAX;
 
 	return hpa;
 }
 
+struct dpa_result {
+	struct cxl_memdev *cxlmd;
+	u64 dpa;
+};
+
+static int region_offset_to_dpa_result(struct cxl_region *cxlr, u64 offset,
+				       struct dpa_result *result)
+{
+	struct cxl_region_params *p = &cxlr->params;
+	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent);
+	struct cxl_endpoint_decoder *cxled;
+	u64 hpa, hpa_offset, dpa_offset;
+	u64 bits_upper, bits_lower;
+	u64 shifted, rem, temp;
+	u16 eig = 0;
+	u8 eiw = 0;
+	int pos;
+
+	lockdep_assert_held(&cxl_rwsem.region);
+	lockdep_assert_held(&cxl_rwsem.dpa);
+
+	/* Input validation ensures valid ways and gran */
+	granularity_to_eig(p->interleave_granularity, &eig);
+	ways_to_eiw(p->interleave_ways, &eiw);
+
+	/*
+	 * If the root decoder has SPA to CXL HPA callback, use it. Otherwise
+	 * CXL HPA is assumed to equal SPA.
+	 */
+	if (has_spa_to_hpa(cxlrd)) {
+		hpa = cxlrd->ops->spa_to_hpa(cxlrd, p->res->start + offset);
+		hpa_offset = hpa - p->res->start;
+	} else {
+		hpa_offset = offset;
+	}
+	/*
+	 * Interleave position: CXL Spec 3.2 Section 8.2.4.20.13
+	 * eiw < 8
+	 *	Position is in the IW bits at HPA_OFFSET[IG+8+IW-1:IG+8].
+	 *	Per spec "remove IW bits starting with bit position IG+8"
+	 * eiw >= 8
+	 *	Position is not explicitly stored in HPA_OFFSET bits. It is
+	 *	derived from the modulo operation of the upper bits using
+	 *	the total number of interleave ways.
+	 */
+	if (eiw < 8) {
+		pos = (hpa_offset >> (eig + 8)) & GENMASK(eiw - 1, 0);
+	} else {
+		shifted = hpa_offset >> (eig + 8);
+		div64_u64_rem(shifted, p->interleave_ways, &rem);
+		pos = rem;
+	}
+	if (pos < 0 || pos >= p->nr_targets) {
+		dev_dbg(&cxlr->dev, "Invalid position %d for %d targets\n",
+			pos, p->nr_targets);
+		return -ENXIO;
+	}
+
+	/*
+	 * DPA offset: CXL Spec 3.2 Section 8.2.4.20.13
+	 * Lower bits [IG+7:0] pass through unchanged
+	 * (eiw < 8)
+	 *	Per spec: DPAOffset[51:IG+8] = (HPAOffset[51:IG+IW+8] >> IW)
+	 *	Clear the position bits to isolate upper section, then
+	 *	reverse the left shift by eiw that occurred during DPA->HPA
+	 * (eiw >= 8)
+	 *	Per spec: DPAOffset[51:IG+8] = HPAOffset[51:IG+IW] / 3
+	 *	Extract upper bits from the correct bit range and divide by 3
+	 *	to recover the original DPA upper bits
+	 */
+	bits_lower = hpa_offset & GENMASK_ULL(eig + 7, 0);
+	if (eiw < 8) {
+		temp = hpa_offset &= ~((u64)GENMASK(eig + eiw + 8 - 1, 0));
+		dpa_offset = temp >> eiw;
+	} else {
+		bits_upper = div64_u64(hpa_offset >> (eig + eiw), 3);
+		dpa_offset = bits_upper << (eig + 8);
+	}
+	dpa_offset |= bits_lower;
+
+	/* Look-up and return the result: a memdev and a DPA */
+	for (int i = 0; i < p->nr_targets; i++) {
+		cxled = p->targets[i];
+		if (cxled->pos != pos)
+			continue;
+		result->cxlmd = cxled_to_memdev(cxled);
+		result->dpa = cxl_dpa_resource_start(cxled) + dpa_offset;
+
+		return 0;
+	}
+	dev_err(&cxlr->dev, "No device found for position %d\n", pos);
+
+	return -ENXIO;
+}
+
 static struct lock_class_key cxl_pmem_region_key;
 
 static int cxl_pmem_region_alloc(struct cxl_region *cxlr)
@@ -3542,6 +3653,105 @@ static void shutdown_notifiers(void *_cxlr)
 	unregister_mt_adistance_algorithm(&cxlr->adist_notifier);
 }
 
+static void remove_debugfs(void *dentry)
+{
+	debugfs_remove_recursive(dentry);
+}
+
+static int validate_region_offset(struct cxl_region *cxlr, u64 offset)
+{
+	struct cxl_region_params *p = &cxlr->params;
+	resource_size_t region_size;
+	u64 hpa;
+
+	if (offset < p->cache_size) {
+		dev_err(&cxlr->dev,
+			"Offset %#llx is within extended linear cache %pr\n",
+			offset, &p->cache_size);
+		return -EINVAL;
+	}
+
+	region_size = resource_size(p->res);
+	if (offset >= region_size) {
+		dev_err(&cxlr->dev, "Offset %#llx exceeds region size %pr\n",
+			offset, &region_size);
+		return -EINVAL;
+	}
+
+	hpa = p->res->start + offset;
+	if (hpa < p->res->start || hpa > p->res->end) {
+		dev_err(&cxlr->dev, "HPA %#llx not in region %pr\n", hpa,
+			p->res);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int cxl_region_debugfs_poison_inject(void *data, u64 offset)
+{
+	struct dpa_result result = { .dpa = ULLONG_MAX, .cxlmd = NULL };
+	struct cxl_region *cxlr = data;
+	int rc;
+
+	ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &region_rwsem)))
+		return rc;
+
+	ACQUIRE(rwsem_read_intr, dpa_rwsem)(&cxl_rwsem.dpa);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &dpa_rwsem)))
+		return rc;
+
+	if (validate_region_offset(cxlr, offset))
+		return -EINVAL;
+
+	rc = region_offset_to_dpa_result(cxlr, offset, &result);
+	if (rc || !result.cxlmd || result.dpa == ULLONG_MAX) {
+		dev_dbg(&cxlr->dev,
+			"Failed to resolve DPA for region offset %#llx rc %d\n",
+			offset, rc);
+
+		return rc ? rc : -EINVAL;
+	}
+
+	return cxl_inject_poison_locked(result.cxlmd, result.dpa);
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(cxl_poison_inject_fops, NULL,
+			 cxl_region_debugfs_poison_inject, "%llx\n");
+
+static int cxl_region_debugfs_poison_clear(void *data, u64 offset)
+{
+	struct dpa_result result = { .dpa = ULLONG_MAX, .cxlmd = NULL };
+	struct cxl_region *cxlr = data;
+	int rc;
+
+	ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &region_rwsem)))
+		return rc;
+
+	ACQUIRE(rwsem_read_intr, dpa_rwsem)(&cxl_rwsem.dpa);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &dpa_rwsem)))
+		return rc;
+
+	if (validate_region_offset(cxlr, offset))
+		return -EINVAL;
+
+	rc = region_offset_to_dpa_result(cxlr, offset, &result);
+	if (rc || !result.cxlmd || result.dpa == ULLONG_MAX) {
+		dev_dbg(&cxlr->dev,
+			"Failed to resolve DPA for region offset %#llx rc %d\n",
+			offset, rc);
+
+		return rc ? rc : -EINVAL;
+	}
+
+	return cxl_clear_poison_locked(result.cxlmd, result.dpa);
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(cxl_poison_clear_fops, NULL,
+			 cxl_region_debugfs_poison_clear, "%llx\n");
+
 static int cxl_region_can_probe(struct cxl_region *cxlr)
 {
 	struct cxl_region_params *p = &cxlr->params;
@@ -3571,6 +3781,7 @@ static int cxl_region_probe(struct device *dev)
 {
 	struct cxl_region *cxlr = to_cxl_region(dev);
 	struct cxl_region_params *p = &cxlr->params;
+	bool poison_supported = true;
 	int rc;
 
 	rc = cxl_region_can_probe(cxlr);
@@ -3594,6 +3805,31 @@ static int cxl_region_probe(struct device *dev)
 	if (rc)
 		return rc;
 
+	/* Create poison attributes if all memdevs support the capabilities */
+	for (int i = 0; i < p->nr_targets; i++) {
+		struct cxl_endpoint_decoder *cxled = p->targets[i];
+		struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+
+		if (!cxl_memdev_has_poison_cmd(cxlmd, CXL_POISON_ENABLED_INJECT) ||
+		    !cxl_memdev_has_poison_cmd(cxlmd, CXL_POISON_ENABLED_CLEAR)) {
+			poison_supported = false;
+			break;
+		}
+	}
+
+	if (poison_supported) {
+		struct dentry *dentry;
+
+		dentry = cxl_debugfs_create_dir(dev_name(dev));
+		debugfs_create_file("inject_poison", 0200, dentry, cxlr,
+				    &cxl_poison_inject_fops);
+		debugfs_create_file("clear_poison", 0200, dentry, cxlr,
+				    &cxl_poison_clear_fops);
+		rc = devm_add_action_or_reset(dev, remove_debugfs, dentry);
+		if (rc)
+			return rc;
+	}
+
 	switch (cxlr->mode) {
 	case CXL_PARTMODE_PMEM:
 		rc = devm_cxl_region_edac_register(cxlr);