Below is a setup with extended linear cache configuration with an example
layout of memory region shown below presented as a single memory region
consists of 256G memory where there's 128G of DRAM and 128G of CXL memory.
The kernel sees a region of total 256G of system memory.
128G DRAM 128G CXL memory
|-----------------------------------|-------------------------------------|
Data resides in either DRAM or far memory (FM) with no replication. Hot
data is swapped into DRAM by the hardware behind the scenes. When error is
detected in one location, it is possible that error also resides in the
aliased location. Therefore when a memory location that is flagged by MCE
is part of the special region, the aliased memory location needs to be
offlined as well.
Add an mce notify callback to identify if the MCE address location is part
of an extended linear cache region and handle accordingly.
Added symbol export to set_mce_nospec() in x86 code in order to call
set_mce_nospec() from the CXL MCE notify callback.
Link: https://lore.kernel.org/linux-cxl/668333b17e4b2_5639294fd@dwillia2-xfh.jf.intel.com.notmuch/
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Li Ming <ming.li@zohomail.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Link: https://patch.msgid.link/20250226162224.3633792-5-dave.jiang@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
return rc;
}
+EXPORT_SYMBOL_GPL(set_mce_nospec);
/* Restore full speculative operation to the pfn. */
int clear_mce_nospec(unsigned long pfn)
If unsure, or if this kernel is meant for production environments,
say N.
+config CXL_MCE
+ def_bool y
+ depends on X86_MCE && MEMORY_FAILURE
+
endif
cxl_core-y += acpi.o
cxl_core-$(CONFIG_TRACING) += trace.o
cxl_core-$(CONFIG_CXL_REGION) += region.o
+cxl_core-$(CONFIG_CXL_MCE) += mce.o
#include "core.h"
#include "trace.h"
+#include "mce.h"
static bool cxl_raw_allow_all;
struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev)
{
struct cxl_memdev_state *mds;
+ int rc;
mds = devm_kzalloc(dev, sizeof(*mds), GFP_KERNEL);
if (!mds) {
mds->ram_perf.qos_class = CXL_QOS_CLASS_INVALID;
mds->pmem_perf.qos_class = CXL_QOS_CLASS_INVALID;
+ rc = devm_cxl_register_mce_notifier(dev, &mds->mce_notifier);
+ if (rc)
+ return ERR_PTR(rc);
+
return mds;
}
EXPORT_SYMBOL_NS_GPL(cxl_memdev_state_create, "CXL");
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2024 Intel Corporation. All rights reserved. */
+#include <linux/mm.h>
+#include <linux/notifier.h>
+#include <linux/set_memory.h>
+#include <asm/mce.h>
+#include <cxlmem.h>
+#include "mce.h"
+
+static int cxl_handle_mce(struct notifier_block *nb, unsigned long val,
+ void *data)
+{
+ struct cxl_memdev_state *mds = container_of(nb, struct cxl_memdev_state,
+ mce_notifier);
+ struct cxl_memdev *cxlmd = mds->cxlds.cxlmd;
+ struct cxl_port *endpoint = cxlmd->endpoint;
+ struct mce *mce = data;
+ u64 spa, spa_alias;
+ unsigned long pfn;
+
+ if (!mce || !mce_usable_address(mce))
+ return NOTIFY_DONE;
+
+ if (!endpoint)
+ return NOTIFY_DONE;
+
+ spa = mce->addr & MCI_ADDR_PHYSADDR;
+
+ pfn = spa >> PAGE_SHIFT;
+ if (!pfn_valid(pfn))
+ return NOTIFY_DONE;
+
+ spa_alias = cxl_port_get_spa_cache_alias(endpoint, spa);
+ if (spa_alias == ~0ULL)
+ return NOTIFY_DONE;
+
+ pfn = spa_alias >> PAGE_SHIFT;
+
+ /*
+ * Take down the aliased memory page. The original memory page flagged
+ * by the MCE will be taken cared of by the standard MCE handler.
+ */
+ dev_emerg(mds->cxlds.dev, "Offlining aliased SPA address0: %#llx\n",
+ spa_alias);
+ if (!memory_failure(pfn, 0))
+ set_mce_nospec(pfn);
+
+ return NOTIFY_OK;
+}
+
+static void cxl_unregister_mce_notifier(void *mce_notifier)
+{
+ mce_unregister_decode_chain(mce_notifier);
+}
+
+int devm_cxl_register_mce_notifier(struct device *dev,
+ struct notifier_block *mce_notifier)
+{
+ mce_notifier->notifier_call = cxl_handle_mce;
+ mce_notifier->priority = MCE_PRIO_UC;
+ mce_register_decode_chain(mce_notifier);
+
+ return devm_add_action_or_reset(dev, cxl_unregister_mce_notifier,
+ mce_notifier);
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2024 Intel Corporation. All rights reserved. */
+#ifndef _CXL_CORE_MCE_H_
+#define _CXL_CORE_MCE_H_
+
+#include <linux/notifier.h>
+
+#ifdef CONFIG_CXL_MCE
+int devm_cxl_register_mce_notifier(struct device *dev,
+ struct notifier_block *mce_notifer);
+#else
+static inline int
+devm_cxl_register_mce_notifier(struct device *dev,
+ struct notifier_block *mce_notifier)
+{
+ return -EOPNOTSUPP;
+}
+#endif
+
+#endif
}
EXPORT_SYMBOL_NS_GPL(cxl_add_to_region, "CXL");
+u64 cxl_port_get_spa_cache_alias(struct cxl_port *endpoint, u64 spa)
+{
+ struct cxl_region_ref *iter;
+ unsigned long index;
+
+ if (!endpoint)
+ return ~0ULL;
+
+ guard(rwsem_write)(&cxl_region_rwsem);
+
+ xa_for_each(&endpoint->regions, index, iter) {
+ struct cxl_region_params *p = &iter->region->params;
+
+ if (p->res->start <= spa && spa <= p->res->end) {
+ if (!p->cache_size)
+ return ~0ULL;
+
+ if (spa > p->res->start + p->cache_size)
+ return spa - p->cache_size;
+
+ return spa + p->cache_size;
+ }
+ }
+
+ return ~0ULL;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_port_get_spa_cache_alias, "CXL");
+
static int is_system_ram(struct resource *res, void *arg)
{
struct cxl_region *cxlr = arg;
int cxl_add_to_region(struct cxl_port *root,
struct cxl_endpoint_decoder *cxled);
struct cxl_dax_region *to_cxl_dax_region(struct device *dev);
+u64 cxl_port_get_spa_cache_alias(struct cxl_port *endpoint, u64 spa);
#else
static inline bool is_cxl_pmem_region(struct device *dev)
{
{
return NULL;
}
+static inline u64 cxl_port_get_spa_cache_alias(struct cxl_port *endpoint,
+ u64 spa)
+{
+ return 0;
+}
#endif
void cxl_endpoint_parse_cdat(struct cxl_port *port);
* @poison: poison driver state info
* @security: security driver state info
* @fw: firmware upload / activation state
+ * @mce_notifier: MCE notifier
*
* See CXL 3.0 8.2.9.8.2 Capacity Configuration and Label Storage for
* details on capacity parameters.
struct cxl_poison_state poison;
struct cxl_security_state security;
struct cxl_fw_state fw;
+ struct notifier_block mce_notifier;
};
static inline struct cxl_memdev_state *
cxl_core-y += $(CXL_CORE_SRC)/acpi.o
cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o
cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o
+cxl_core-$(CONFIG_CXL_MCE) += $(CXL_CORE_SRC)/mce.o
cxl_core-y += config_check.o
cxl_core-y += cxl_core_test.o
cxl_core-y += cxl_core_exports.o
projects / users / willy / linux.git / commitdiff