is returned to the user. The inject_poison attribute is only
visible for devices supporting the capability.
+ TEST-ONLY INTERFACE: This interface is intended for testing
+ and validation purposes only. It is not a data repair mechanism
+ and should never be used on production systems or live data.
+
+ DATA LOSS RISK: For CXL persistent memory (PMEM) devices,
+ poison injection can result in permanent data loss. Injected
+ poison may render data permanently inaccessible even after
+ clearing, as the clear operation writes zeros and does not
+ recover original data.
+
+ SYSTEM STABILITY RISK: For volatile memory, poison injection
+ can cause kernel crashes, system instability, or unpredictable
+ behavior if the poisoned addresses are accessed by running code
+ or critical kernel structures.
What: /sys/kernel/debug/cxl/memX/clear_poison
Date: April, 2023
The clear_poison attribute is only visible for devices
supporting the capability.
+ TEST-ONLY INTERFACE: This interface is intended for testing
+ and validation purposes only. It is not a data repair mechanism
+ and should never be used on production systems or live data.
+
+ CLEAR IS NOT DATA RECOVERY: This operation writes zeros to the
+ specified address range and removes the address from the poison
+ list. It does NOT recover or restore original data that may have
+ been present before poison injection. Any original data at the
+ cleared address is permanently lost and replaced with zeros.
+
+ CLEAR IS NOT A REPAIR MECHANISM: This interface is for testing
+ purposes only and should not be used as a data repair tool.
+ Clearing poison is fundamentally different from data recovery
+ or error correction.
+
+What: /sys/kernel/debug/cxl/regionX/inject_poison
+Date: August, 2025
+Contact: linux-cxl@vger.kernel.org
+Description:
+ (WO) When a Host Physical Address (HPA) is written to this
+ attribute, the region driver translates it to a Device
+ Physical Address (DPA) and identifies the corresponding
+ memdev. It then sends an inject poison command to that memdev
+ at the translated DPA. Refer to the memdev ABI entry at:
+ /sys/kernel/debug/cxl/memX/inject_poison for the detailed
+ behavior. This attribute is only visible if all memdevs
+ participating in the region support both inject and clear
+ poison commands.
+
+ TEST-ONLY INTERFACE: This interface is intended for testing
+ and validation purposes only. It is not a data repair mechanism
+ and should never be used on production systems or live data.
+
+ DATA LOSS RISK: For CXL persistent memory (PMEM) devices,
+ poison injection can result in permanent data loss. Injected
+ poison may render data permanently inaccessible even after
+ clearing, as the clear operation writes zeros and does not
+ recover original data.
+
+ SYSTEM STABILITY RISK: For volatile memory, poison injection
+ can cause kernel crashes, system instability, or unpredictable
+ behavior if the poisoned addresses are accessed by running code
+ or critical kernel structures.
+
+What: /sys/kernel/debug/cxl/regionX/clear_poison
+Date: August, 2025
+Contact: linux-cxl@vger.kernel.org
+Description:
+ (WO) When a Host Physical Address (HPA) is written to this
+ attribute, the region driver translates it to a Device
+ Physical Address (DPA) and identifies the corresponding
+ memdev. It then sends a clear poison command to that memdev
+ at the translated DPA. Refer to the memdev ABI entry at:
+ /sys/kernel/debug/cxl/memX/clear_poison for the detailed
+ behavior. This attribute is only visible if all memdevs
+ participating in the region support both inject and clear
+ poison commands.
+
+ TEST-ONLY INTERFACE: This interface is intended for testing
+ and validation purposes only. It is not a data repair mechanism
+ and should never be used on production systems or live data.
+
+ CLEAR IS NOT DATA RECOVERY: This operation writes zeros to the
+ specified address range and removes the address from the poison
+ list. It does NOT recover or restore original data that may have
+ been present before poison injection. Any original data at the
+ cleared address is permanently lost and replaced with zeros.
+
+ CLEAR IS NOT A REPAIR MECHANISM: This interface is for testing
+ purposes only and should not be used as a data repair tool.
+ Clearing poison is fundamentally different from data recovery
+ or error correction.
+
What: /sys/kernel/debug/cxl/einj_types
Date: January, 2024
KernelVersion: v6.9
/* 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>
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);
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, ®ion_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, ®ion_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;
{
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);
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);
projects / users / hch / misc.git / commitdiff