cxl/region: Add inject and clear poison by region offset

Add CXL region debugfs attributes to inject and clear poison based
on an offset into the region. These new interfaces allow users to
operate on poison at the region level without needing to resolve
Device Physical Addresses (DPA) or target individual memdevs.

The implementation uses a new helper, region_offset_to_dpa_result()
that applies decoder interleave logic, including XOR-based address
decoding when applicable. Note that XOR decodes rely on driver
internal xormaps which are not exposed to userspace. So, this support
is not only a simplification of poison operations that could be done
using existing per memdev operations, but also it enables this
functionality for XOR interleaved regions for the first time.

New debugfs attributes are added in /sys/kernel/debug/cxl/regionX/:
inject_poison and clear_poison. These are only exposed if all memdevs
participating in the region support both inject and clear commands,
ensuring consistent and reliable behavior across multi-device regions.

If tracing is enabled, these operations are logged as cxl_poison
events in /sys/kernel/tracing/trace.

The ABI documentation warns users of the significant risks that
come with using these capabilities.

A CXL Maturity Map update shows this user flow is now supported.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Link: https://patch.msgid.link/f3fd8628ab57ea79704fb2d645902cd499c066af.1754290144.git.alison.schofield@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>

3 files changed, 140 insertions, 3 deletions

diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 2669f251d677..eac8cc1bdaa0 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -135,6 +135,10 @@ enum cxl_poison_trace_type {
 	CXL_POISON_TRACE_CLEAR,
 };
 
+enum poison_cmd_enabled_bits;
+bool cxl_memdev_has_poison_cmd(struct cxl_memdev *cxlmd,
+			       enum poison_cmd_enabled_bits cmd);
+
 long cxl_pci_get_latency(struct pci_dev *pdev);
 int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c);
 int cxl_update_hmat_access_coordinates(int nid, struct cxl_region *cxlr,
diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index 90d3390d9c7c..e370d733e440 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -200,6 +200,14 @@ static ssize_t security_erase_store(struct device *dev,
 static struct device_attribute dev_attr_security_erase =
 	__ATTR(erase, 0200, NULL, security_erase_store);
 
+bool cxl_memdev_has_poison_cmd(struct cxl_memdev *cxlmd,
+			       enum poison_cmd_enabled_bits cmd)
+{
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+
+	return test_bit(cmd, mds->poison.enabled_cmds);
+}
+
 static int cxl_get_poison_by_memdev(struct cxl_memdev *cxlmd)
 {
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index f492d1291e72..1e2911af9060 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>
@@ -3003,9 +3004,8 @@ struct dpa_result {
 	u64 dpa;
 };
 
-static int __maybe_unused region_offset_to_dpa_result(struct cxl_region *cxlr,
-						      u64 offset,
-						      struct dpa_result *result)
+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);
@@ -3648,6 +3648,105 @@ 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 %#llx\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 %#llx\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;
@@ -3677,6 +3776,7 @@ 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);
@@ -3700,6 +3800,31 @@ 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);