acpi/hmat / cxl: Add exclusive caching enumeration and RAS support
Subsystems (5)
Dave Jiang
maintainerv4 cover acpi/hmat / cxl: Add exclusive caching enumeration and RAS support
v3:
- Drop region to nid function, deadcode.
- Set hpa_alias default to ~0ULL to indicate no alias. (Jonathan)
- Add endpoint check for mce handler. (Ming)
- Add mce notifier unregister. (Ming)
v2:
- Fix 0-day issues
- Fix checking of cache flag. (Ming)
- Add comment about cache range vs CFMWS. (Ming)
- Update EXPORT_SYMBOL_(). (Jonathan)
- Fix various code comments. (Jonathan)
- Emit hpa_alias0 instead of hpa_alias. (Jonathan)
- Introduce CONFIG_CXL_MCE to address kernel build dep issues.
v1:
- Drop RFC prefix
- Drop MMIO hole discovery. Will implement if there's real world implementation.
- Drop MCE_PRI_CXL. Use MCE_PRI_UC. (Boris)
- Minor refactors and grammar fixes. (Jonathan)
- Rename 'mode' to 'address_mode'. (Jonathan)
RFCv2:
- Dropped 1/6 (ACPICA definition merged)
- Change UNKNOWN to RESERVED for cache definition. (Jonathan)
- Fix spelling errors (Jonathan)
- Rename region_res_match_range() to region_res_match_cxl_range(). (Jonathan)
- Add warning when cache is not 1:1 with backing region. (Jonathan)
- Code and comments cleanup. (Jonathan)
- Make MCE code access in CXL arch independent. (Jonathan)
- Fixup 0-day reports.
Certain systems provide an exclusive caching memory configurations where a 1:1 layout of DRAM and far memory (FM) such as CXL memory is utilized. In this configuration, the memory region is provided as a single memory region to the OS. For example such as below:
128GB DRAM 128GB CXL memory
|------------------------------------|------------------------------------|
The kernel sees the region as a 256G system memory region. Data can reside in either DRAM or FM with no replication. Hot data is swapped into DRAM by the hardware behind the scenes.
This kernel series introduces code to enumerate the side cache by the kernel when configured in a exclusive-cache configuration. It also adds RAS support to deal with the aliased memory addresses.
A new ECN [1] to ACPI HMAT table was introduced and was approved to describe the "extended-linear" addressing for direct-mapped memory-side caches. A reserved field in the Memory Side Cache Information Structure of HMAT is redefined as "Address Mode" where a value of 1 is defined as Extended-linear mode. This value is valid if the cache is direct mapped. "It indicates that the associated address range (SRAT.MemoryAffinityStructure.Length) is comprised of the backing store capacity extended by the cache capacity." By augmenting the HMAT and SRAT parsing code, this new information can be stored by the HMAT handling code.
Current CXL region enumeration code is not enlightened with the side cache configuration and therefore only presents the region size as the size of the CXL region. Add support to allow CXL region enumeration code to query the HMAT handling code and retrieve the information regarding the side cache and adjust the region size accordingly. This should allow the CXL CLI to display the full region size rather than just the CXL only region size.
There are 3 sources where the kernel may be notified that error is detected for memory.
1. CXL DRAM event. This is a CXL event that is generated when an error is detected by the CXL device patrol or demand scrubber. The trace_event is augmented to display the aliased System Phyiscal Address (SPA) in addition to the alerted address. However, reporting of memory failure is TBD until the discussion [2] of failure reporting is settled upstream.
2. UCNA event from DRAM patrol or demand scrubber. This should eventually go through the MCE callback chain.
3. MCE from kernel consume poison.
It is possible that all 3 sources may report at the same time and all report at the error.
For 2 and 3, a MCE notifier callback is registered by the CXL on a per device basis. The callback will determine if the reported address is in one of the special regions and offline the aliased address if that is the case.
[1]: https://lore.kernel.org/linux-cxl/[email protected]/
[2]: https://lore.kernel.org/linux-cxl/[email protected]/
---
Dave Jiang (4):
acpi: numa: Add support to enumerate and store extended linear address mode acpi/hmat / cxl: Add extended linear cache support for CXL
cxl: Add extended linear cache address alias emission for cxl events
cxl: Add mce notifier to emit aliased address for extended linear cache
Documentation/ABI/stable/sysfs-devices-node | 6 +++ arch/x86/mm/pat/set_memory.c | 1 + drivers/acpi/numa/hmat.c | 44 ++++++++++++++++++++ drivers/base/node.c | 2 + drivers/cxl/Kconfig | 4 ++ drivers/cxl/core/Makefile | 2 + drivers/cxl/core/acpi.c | 11 +++++ drivers/cxl/core/core.h | 3 ++ drivers/cxl/core/mbox.c | 34 +++++++++++++-- drivers/cxl/core/mce.c | 65 +++++++++++++++++++++++++++++ drivers/cxl/core/mce.h | 20 +++++++++ drivers/cxl/core/region.c | 108 +++++++++++++++++++++++++++++++++++++++++++++--- drivers/cxl/core/trace.h | 22 ++++++---- drivers/cxl/cxl.h | 8 ++++ drivers/cxl/cxlmem.h | 2 + include/linux/acpi.h | 11 +++++ include/linux/node.h | 7 ++++ tools/testing/cxl/Kbuild | 2 + 18 files changed, 335 insertions(+), 17 deletions(-)
Dave Jiang
maintainerPATCH v4 1/4 acpi: numa: Add support to enumerate and store extended linear address mode
Store the address mode as part of the cache attriutes. Export the mode attribute to sysfs as all other cache attributes.
--- Documentation/ABI/stable/sysfs-devices-node | 6 ++++++ drivers/acpi/numa/hmat.c | 5 +++++ drivers/base/node.c | 2 ++ include/linux/node.h | 7 +++++++ 4 files changed, 20 insertions(+)
Documentation/ABI/stable/sysfs-devices-node +6 -0
@@ -177,6 +177,12 @@ Description: The cache write policy: 0 for write-back, 1 for write-through, other or unknown. +What: /sys/devices/system/node/nodeX/memory_side_cache/indexY/address_mode +Date: March 2025 +Contact: Dave Jiang <[email protected]> +Description: + The address mode: 0 for reserved, 1 for extended-linear. + What: /sys/devices/system/node/nodeX/x86/sgx_total_bytes Date: November 2021 Contact: Jarkko Sakkinen <[email protected]>
drivers/acpi/numa/hmat.c +5 -0
@@ -506,6 +506,11 @@ static __init int hmat_parse_cache(union acpi_subtable_headers *header,switch ((attrs &ACPI_HMAT_CACHE_ASSOCIATIVITY ) >>8 ) {case ACPI_HMAT_CA_DIRECT_MAPPED : tcache->cache_attrs.indexing =NODE_CACHE_DIRECT_MAP ; +/* Extended Linear mode is only valid if cache is direct mapped */ +if (cache->address_mode ==ACPI_HMAT_CACHE_MODE_EXTENDED_LINEAR ) { + tcache->cache_attrs.address_mode = +NODE_CACHE_ADDR_MODE_EXTENDED_LINEAR ; + }break ;case ACPI_HMAT_CA_COMPLEX_CACHE_INDEXING : tcache->cache_attrs.indexing =NODE_CACHE_INDEXED ;
drivers/base/node.c +2 -0
@@ -244,12 +244,14 @@ CACHE_ATTR(size, "%llu") CACHE_ATTR(line_size, "%u") CACHE_ATTR(indexing, "%u") CACHE_ATTR(write_policy, "%u") +CACHE_ATTR(address_mode, "%#x")static struct attribute *cache_attrs[] = { &dev_attr_indexing.attr, &dev_attr_size.attr, &dev_attr_line_size.attr, &dev_attr_write_policy.attr, + &dev_attr_address_mode.attr,NULL , };ATTRIBUTE_GROUPS (cache);
include/linux/node.h +7 -0
@@ -57,6 +57,11 @@ enum cache_write_policy { NODE_CACHE_WRITE_OTHER, }; +enum cache_mode { +NODE_CACHE_ADDR_MODE_RESERVED , +NODE_CACHE_ADDR_MODE_EXTENDED_LINEAR , +}; +/** * struct node_cache_attrs - system memory caching attributes *
@@ -65,6 +70,7 @@ enum cache_write_policy {* @size: Total size of cache in bytes * @line_size: Number of bytes fetched on a cache miss * @level: The cache hierarchy level +* @address_mode: The address mode */ struct node_cache_attrs {enum cache_indexing indexing;
@@ -72,6 +78,7 @@ struct node_cache_attrs {u64 size;u16 line_size;u8 level; +u16 address_mode; };#ifdef CONFIG_HMEM_REPORTING
Signature · 1 line
2.48.1
Re: [PATCH v4 1/4] acpi: numa: Add support to enumerate and store extended linear address mode
Quoted 6 lines · Dave Jiang
Store the address mode as part of the cache attriutes. Export the mode attribute to sysfs as all other cache attributes.
Reviewed-by Jonathan Cameron <[email protected]>Signed-off-by Dave Jiang <[email protected]>
Dave Jiang
maintainerPATCH v4 2/4 acpi/hmat / cxl: Add extended linear cache support for CXL
In reply to Dave JiangThe current cxl region size only indicates the size of the CXL memory region without accounting for the extended linear cache size. Retrieve the cache size from HMAT and append that to the cxl region size for the cxl region range that matches the SRAT range that has extended linear cache enabled.
The SRAT defines the whole memory range that includes the extended linear cache and the CXL memory region. The new HMAT ECN/ECR to the Memory Side Cache Information Structure defines the size of the extended linear cache size and matches to the SRAT Memory Affinity Structure by the memory proxmity domain. Add a helper to match the cxl range to the SRAT memory range in order to retrieve the cache size.
There are several places that checks the cxl region range against the decoder range. Use new helper to check between the two ranges and address the new cache size.
---
v4:
- Add adjustment for cxl_dpa_to_hpa() (Alison)
- Add check of adjusted region start against CFMWS. (Alison)
- Update dev_warn() to be more precise. (Alison)
--- drivers/acpi/numa/hmat.c | 39 +++++++++++++++++++ drivers/cxl/core/Makefile | 1 + drivers/cxl/core/acpi.c | 11 ++++++ drivers/cxl/core/core.h | 3 ++ drivers/cxl/core/region.c | 80 ++++++++++++++++++++++++++++++++++++--- drivers/cxl/cxl.h | 2 + include/linux/acpi.h | 11 ++++++ tools/testing/cxl/Kbuild | 1 + 8 files changed, 143 insertions(+), 5 deletions(-) create mode 100644 drivers/cxl/core/acpi.c
drivers/acpi/numa/hmat.c +39 -0
@@ -108,6 +108,45 @@ static struct memory_target *find_mem_target(unsigned int mem_pxm)return NULL ; } +/** +* hmat_get_extended_linear_cache_size - Retrieve the extended linear cache size +* @backing_res: resource from the backing media +* @nid: node id for the memory region +* @cache_size: (Output) size of extended linear cache. +* +* Return: 0 on success. Errno on failure. +* +*/ +int hmat_get_extended_linear_cache_size (struct resource *backing_res,int nid, +resource_size_t *cache_size) +{ +unsigned int pxm =node_to_pxm (nid); +struct memory_target *target; +struct target_cache *tcache; +struct resource *res; + + target =find_mem_target (pxm); +if (!target) +return -ENOENT ; + +list_for_each_entry (tcache, &target->caches, node) { +if (tcache->cache_attrs.address_mode != +NODE_CACHE_ADDR_MODE_EXTENDED_LINEAR ) +continue ; + + res = &target->memregions; +if (!resource_contains (res, backing_res)) +continue ; + + *cache_size = tcache->cache_attrs.size; +return 0 ; + } + + *cache_size =0 ; +return 0 ; +} +EXPORT_SYMBOL_NS_GPL (hmat_get_extended_linear_cache_size,"CXL" ); +static struct memory_target *acpi_find_genport_target (u32 uid) {struct memory_target *target;
drivers/cxl/core/Makefile +1 -0
@@ -14,5 +14,6 @@ cxl_core-y += pci.o cxl_core-y += hdm.o cxl_core-y += pmu.o cxl_core-y += cdat.o +cxl_core-y += acpi.o cxl_core-$(CONFIG_TRACING) += trace.o cxl_core-$(CONFIG_CXL_REGION) += region.o
drivers/cxl/core/acpi.c new file +11 -0
@@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2024 Intel Corporation. All rights reserved. */ +#include <linux/acpi.h> +#include "cxl.h" +#include "core.h" + +int cxl_acpi_get_extended_linear_cache_size (struct resource *backing_res, +int nid,resource_size_t *size) +{ +return hmat_get_extended_linear_cache_size (backing_res, nid, size); +}
drivers/cxl/core/core.h +3 -0
@@ -115,4 +115,7 @@ bool cxl_need_node_perf_attrs_update(int nid);int cxl_port_get_switch_dport_bandwidth (struct cxl_port *port,struct access_coordinate *c); +int cxl_acpi_get_extended_linear_cache_size (struct resource *backing_res, +int nid,resource_size_t *size); +#endif /* __CXL_CORE_H__ */
drivers/cxl/core/region.c +75 -5
122 lines not on this page · raw message
drivers/cxl/cxl.h +2 -0
@@ -493,6 +493,7 @@ enum cxl_config_state {* @res: allocated iomem capacity for this region * @targets: active ordered targets in current decoder configuration * @nr_targets: number of targets +* @cache_size: extended linear cache size if exists, otherwise zero. * * State transitions are protected by the cxl_region_rwsem */
@@ -504,6 +505,7 @@ struct cxl_region_params {struct resource *res;struct cxl_endpoint_decoder *targets[CXL_DECODER_MAX_INTERLEAVE ];int nr_targets; +resource_size_t cache_size; };/*
include/linux/acpi.h +11 -0
@@ -1095,6 +1095,17 @@ static inline acpi_handle acpi_get_processor_handle(int cpu)#endif /* !CONFIG_ACPI */ +#ifdef CONFIG_ACPI_HMAT +int hmat_get_extended_linear_cache_size (struct resource *backing_res,int nid, +resource_size_t *size); +#else +static inline int hmat_get_extended_linear_cache_size (struct resource *backing_res, +int nid,resource_size_t *size) +{ +return -EOPNOTSUPP ; +} +#endif +extern void arch_post_acpi_subsys_init (void );#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
tools/testing/cxl/Kbuild +1 -0
@@ -61,6 +61,7 @@ cxl_core-y += $(CXL_CORE_SRC)/pci.o cxl_core-y += $(CXL_CORE_SRC)/hdm.o cxl_core-y += $(CXL_CORE_SRC)/pmu.o cxl_core-y += $(CXL_CORE_SRC)/cdat.o +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-y += config_check.o
Signature · 1 line
2.48.1
Re: [PATCH v4 2/4] acpi/hmat / cxl: Add extended linear cache support for CXL
Quoted 13 lines · Dave Jiang
The current cxl region size only indicates the size of the CXL memory region without accounting for the extended linear cache size. Retrieve the cache size from HMAT and append that to the cxl region size for the cxl region range that matches the SRAT range that has extended linear cache enabled.
The SRAT defines the whole memory range that includes the extended linear cache and the CXL memory region. The new HMAT ECN/ECR to the Memory Side Cache Information Structure defines the size of the extended linear cache size and matches to the SRAT Memory Affinity Structure by the memory proxmity domain. Add a helper to match the cxl range to the SRAT memory range in order to retrieve the cache size.
Quoted 6 lines
There are several places that checks the cxl region range against the decoder range. Use new helper to check between the two ranges and address the new cache size.
Reviewed-by Jonathan Cameron <[email protected]>Signed-off-by Dave Jiang <[email protected]>
Alison Schofield
maintainerRe: [PATCH v4 2/4] acpi/hmat / cxl: Add extended linear cache support for CXL
In reply to Dave JiangQuoted 54 lines · Dave Jiang
The current cxl region size only indicates the size of the CXL memory region without accounting for the extended linear cache size. Retrieve the cache size from HMAT and append that to the cxl region size for the cxl region range that matches the SRAT range that has extended linear cache enabled.
The SRAT defines the whole memory range that includes the extended linear cache and the CXL memory region. The new HMAT ECN/ECR to the Memory Side Cache Information Structure defines the size of the extended linear cache size and matches to the SRAT Memory Affinity Structure by the memory proxmity domain. Add a helper to match the cxl range to the SRAT memory range in order to retrieve the cache size.
There are several places that checks the cxl region range against the decoder range. Use new helper to check between the two ranges and address the new cache size.
Reviewed-by Jonathan Cameron <[email protected]>Signed-off-by Dave Jiang <[email protected]>---
v4:
- Add adjustment forcxl_dpa_to_hpa()(Alison)
- Add check of adjusted region start against CFMWS. (Alison)
- Updatedev_warn()to be more precise. (Alison)--- drivers/acpi/numa/hmat.c | 39 +++++++++++++++++++ drivers/cxl/core/Makefile | 1 + drivers/cxl/core/acpi.c | 11 ++++++ drivers/cxl/core/core.h | 3 ++ drivers/cxl/core/region.c | 80 ++++++++++++++++++++++++++++++++++++--- drivers/cxl/cxl.h | 2 + include/linux/acpi.h | 11 ++++++ tools/testing/cxl/Kbuild | 1 + 8 files changed, 143 insertions(+), 5 deletions(-) create mode 100644 drivers/cxl/core/acpi.cdrivers/acpi/numa/hmat.c +10
-0@@ -108,6 +108,45 @@ static struct memory_target *find_mem_target(unsigned int mem_pxm)return NULL ; } +/** +* hmat_get_extended_linear_cache_size - Retrieve the extended linear cache size +* @backing_res: resource from the backing media +* @nid: node id for the memory region +* @cache_size: (Output) size of extended linear cache. +* +* Return: 0 on success. Errno on failure. +* +*/ +int hmat_get_extended_linear_cache_size(struct resource *backing_res, int nid,
drivers/acpi/numa/hmat.c static struct memory_target *find_mem_target(unsigned int mem_pxm) · line 130
Quoted 10 lines
drivers/acpi/numa/hmat.c +10
-0+ resource_size_t *cache_size) +{ +unsigned int pxm =node_to_pxm (nid); +struct memory_target *target; +struct target_cache *tcache; +struct resource *res; + + target =find_mem_target (pxm); +if (!target) +return -ENOENT ;
Remember this -ENOENT
Quoted 17 lines
drivers/acpi/numa/hmat.c +17
-0+ +list_for_each_entry (tcache, &target->caches, node) { +if (tcache->cache_attrs.address_mode != +NODE_CACHE_ADDR_MODE_EXTENDED_LINEAR ) +continue ; + + res = &target->memregions; +if (!resource_contains (res, backing_res)) +continue ; + + *cache_size = tcache->cache_attrs.size; +return 0 ; + } + + *cache_size =0 ; +return 0 ; +}
snip
Quoted 6 lines
drivers/acpi/numa/hmat.c +6
-0+static int cxl_extended_linear_cache_resize (struct cxl_region *cxlr, +struct resource *res) +{ +struct cxl_root_decoder *cxlrd =to_cxl_root_decoder (cxlr->dev.parent); +struct cxl_region_params *p = &cxlr->params; +int nid =phys_to_target_node (res->start);
drivers/acpi/numa/hmat.c
Quoted 10 lines
drivers/acpi/numa/hmat.c +10
-0+resource_size_t size, cache_size, start; +int rc; + + size =resource_size (res); +if (!size) +return -EINVAL ; + + rc =cxl_acpi_get_extended_linear_cache_size (res, nid, &cache_size); +if (rc) +return rc;
Remember this - passing thru the -ENOENT
drivers/acpi/numa/hmat.c
Quoted 6 lines
drivers/acpi/numa/hmat.c +6
-0+ +if (!cache_size) +return 0 ; + +if (size != cache_size) { +dev_warn (&cxlr->dev,"Extended Linear Cache is not 1:1, unsupported!" );
maybe emit the numbers, so in the next step we know what the mismatch was, and how much cache goes unused.
drivers/acpi/numa/hmat.c
Quoted 1 line
drivers/acpi/numa/hmat.c +1
-0+return -EOPNOTSUPP ;
EOPNOTSUPP is only other possible rc
Quoted 30 lines
drivers/acpi/numa/hmat.c +23
-0+ } + +/* +* Move the start of the range to where the cache range starts. The +* implementation assumes that the cache range is in front of the +* CXL range. This is not dictated by the HMAT spec but is how the +* current known implementation is configured. +* +* The cache range is expected to be within the CFMWS. The adjusted +* res->start should not be less than cxlrd->res->start. +*/ + start = res->start - cache_size; +if (start < cxlrd->res->start) +return -ENXIO ; + + res->start = start; + p->cache_size = cache_size; + +return 0 ; +} +/* Establish an empty region covering the given HPA range */ static struct cxl_region *construct_region (struct cxl_root_decoder *cxlrd,struct cxl_endpoint_decoder *cxled)@@ -3270,6 +3328,18 @@ static struct cxl_region *construct_region(struct cxl_root_decoder *cxlrd, *res =DEFINE_RES_MEM_NAMED (hpa->start,range_len (hpa),dev_name (&cxlr->dev)); + + rc =cxl_extended_linear_cache_resize (cxlr, res);
drivers/acpi/numa/hmat.c static struct cxl_region *construct_region(struct cxl_root_decoder *cxlrd, · line 3342
Quoted 10 lines
drivers/acpi/numa/hmat.c +10
-0+if (rc) { +/* +* Failing to support extended linear cache region resize does not +* prevent the region from functioning. Only causes cxl list showing +* incorrect region size. +*/ +dev_warn (cxlmd->dev.parent, +"Extended linear cache calculation failed.\n" ); + } +
Do you want to handle ENOENT same as EOPNOTSUPP?
Include rc in error message.
I'm still confused about this message and the state behind it.
Is this saying the region functions but only at it's lesser cxl resource size, or is it saying the region functions at its extended size?
Is there any 'thanks for the cache but we cannot use it' type response to acpi. Wondering if it can be reclaimed.
snip
Dave Jiang
maintainerRe: [PATCH v4 2/4] acpi/hmat / cxl: Add extended linear cache support for CXL
Quoted 158 lines · Alison Schofield
Quoted 54 lines · Dave Jiang
The current cxl region size only indicates the size of the CXL memory region without accounting for the extended linear cache size. Retrieve the cache size from HMAT and append that to the cxl region size for the cxl region range that matches the SRAT range that has extended linear cache enabled.
The SRAT defines the whole memory range that includes the extended linear cache and the CXL memory region. The new HMAT ECN/ECR to the Memory Side Cache Information Structure defines the size of the extended linear cache size and matches to the SRAT Memory Affinity Structure by the memory proxmity domain. Add a helper to match the cxl range to the SRAT memory range in order to retrieve the cache size.
There are several places that checks the cxl region range against the decoder range. Use new helper to check between the two ranges and address the new cache size.
Reviewed-by Jonathan Cameron <[email protected]>Signed-off-by Dave Jiang <[email protected]>---
v4:
- Add adjustment forcxl_dpa_to_hpa()(Alison)
- Add check of adjusted region start against CFMWS. (Alison)
- Updatedev_warn()to be more precise. (Alison)--- drivers/acpi/numa/hmat.c | 39 +++++++++++++++++++ drivers/cxl/core/Makefile | 1 + drivers/cxl/core/acpi.c | 11 ++++++ drivers/cxl/core/core.h | 3 ++ drivers/cxl/core/region.c | 80 ++++++++++++++++++++++++++++++++++++--- drivers/cxl/cxl.h | 2 + include/linux/acpi.h | 11 ++++++ tools/testing/cxl/Kbuild | 1 + 8 files changed, 143 insertions(+), 5 deletions(-) create mode 100644 drivers/cxl/core/acpi.cdrivers/acpi/numa/hmat.c +10
-0@@ -108,6 +108,45 @@ static struct memory_target *find_mem_target(unsigned int mem_pxm)return NULL ; } +/** +* hmat_get_extended_linear_cache_size - Retrieve the extended linear cache size +* @backing_res: resource from the backing media +* @nid: node id for the memory region +* @cache_size: (Output) size of extended linear cache. +* +* Return: 0 on success. Errno on failure. +* +*/ +int hmat_get_extended_linear_cache_size(struct resource *backing_res, int nid,drivers/acpi/numa/hmat.c static struct memory_target *find_mem_target(unsigned int mem_pxm) · line 130
Quoted 10 lines
drivers/acpi/numa/hmat.c +10
-0+ resource_size_t *cache_size) +{ +unsigned int pxm =node_to_pxm (nid); +struct memory_target *target; +struct target_cache *tcache; +struct resource *res; + + target =find_mem_target (pxm); +if (!target) +return -ENOENT ;Remember this
-ENOENTQuoted 17 lines
drivers/acpi/numa/hmat.c +17
-0+ +list_for_each_entry (tcache, &target->caches, node) { +if (tcache->cache_attrs.address_mode != +NODE_CACHE_ADDR_MODE_EXTENDED_LINEAR ) +continue ; + + res = &target->memregions; +if (!resource_contains (res, backing_res)) +continue ; + + *cache_size = tcache->cache_attrs.size; +return 0 ; + } + + *cache_size =0 ; +return 0 ; +}snip
Quoted 6 lines
drivers/acpi/numa/hmat.c +6
-0+static int cxl_extended_linear_cache_resize (struct cxl_region *cxlr, +struct resource *res) +{ +struct cxl_root_decoder *cxlrd =to_cxl_root_decoder (cxlr->dev.parent); +struct cxl_region_params *p = &cxlr->params; +int nid =phys_to_target_node (res->start);drivers/acpi/numa/hmat.c
Quoted 10 lines
drivers/acpi/numa/hmat.c +10
-0+resource_size_t size, cache_size, start; +int rc; + + size =resource_size (res); +if (!size) +return -EINVAL ; + + rc =cxl_acpi_get_extended_linear_cache_size (res, nid, &cache_size); +if (rc) +return rc;Remember this - passing thru the
-ENOENTdrivers/acpi/numa/hmat.c
Quoted 6 lines
drivers/acpi/numa/hmat.c +6
-0+ +if (!cache_size) +return 0 ; + +if (size != cache_size) { +dev_warn (&cxlr->dev,"Extended Linear Cache is not 1:1, unsupported!" );maybe emit the numbers, so in the next step we know what the mismatch was, and how much cache goes unused.
drivers/acpi/numa/hmat.c
Quoted 1 line
drivers/acpi/numa/hmat.c +1
-0+return -EOPNOTSUPP ;EOPNOTSUPP is only other possible rc
Quoted 35 lines
drivers/acpi/numa/hmat.c +28
-0+ } + +/* +* Move the start of the range to where the cache range starts. The +* implementation assumes that the cache range is in front of the +* CXL range. This is not dictated by the HMAT spec but is how the +* current known implementation is configured. +* +* The cache range is expected to be within the CFMWS. The adjusted +* res->start should not be less than cxlrd->res->start. +*/ + start = res->start - cache_size; +if (start < cxlrd->res->start) +return -ENXIO ; + + res->start = start; + p->cache_size = cache_size; + +return 0 ; +} +/* Establish an empty region covering the given HPA range */ static struct cxl_region *construct_region (struct cxl_root_decoder *cxlrd,struct cxl_endpoint_decoder *cxled)@@ -3270,6 +3328,18 @@ static struct cxl_region *construct_region(struct cxl_root_decoder *cxlrd, *res =DEFINE_RES_MEM_NAMED (hpa->start,range_len (hpa),dev_name (&cxlr->dev)); + + rc =cxl_extended_linear_cache_resize (cxlr, res); +if (rc) { +/* +* Failing to support extended linear cache region resize does not +* prevent the region from functioning. Only causes cxl list showing +* incorrect region size.
Quoted 8 lines
drivers/acpi/numa/hmat.c static struct cxl_region *construct_region(struct cxl_root_decoder *cxlrd, · line 3342
Quoted 5 lines
drivers/acpi/numa/hmat.c +5
-0+*/ +dev_warn (cxlmd->dev.parent, +"Extended linear cache calculation failed.\n" ); + } +Do you want to handle ENOENT same as EOPNOTSUPP?
Include rc in error message.
I think it's ok to consider all errnos as no support for extended cache. All memory are usable as intended. You just won't get the correct region size in 'cxl list' or get MCE notification for the aliased address. So there is no loss of resources. Mainly you just lose full RAS support.
Quoted 11 lines
I'm still confused about this message and the state behind it.
Is this saying the region functions but only at it's lesser cxl resource size, or is it saying the region functions at its extended size?
Is there any 'thanks for the cache but we cannot use it' type response to acpi. Wondering if it can be reclaimed.
snip
Alison Schofield
maintainerRe: [PATCH v4 2/4] acpi/hmat / cxl: Add extended linear cache support for CXL
In reply to Dave JiangOn Mon, Feb 24, 2025 at 11:21:00AM -0700, Dave Jiang wrote:
snip to a dev_dbg message of interest -
Quoted 4 lines
drivers/cxl/core/region.c +0
-0
snip
drivers/cxl/core/region.c static int cxl_region_attach(struct cxl_region *cxlr, · line 1971
Quoted 9 lines
drivers/cxl/core/region.c +1
-1@@ -1951,7 +1965,7 @@ static int cxl_region_attach(struct cxl_region *cxlr,return -ENXIO ; } -if (resource_size (cxled->dpa_res) * p->interleave_ways != +if (resource_size (cxled->dpa_res) * p->interleave_ways + p->cache_size !=resource_size (p->res)) { dev_dbg(&cxlr->dev, "%s:%s: decoder-size-%#llx * ways-%d != region-size-%#llx\n",
Add cache to this message since used in calculation above.
Took the liberty of trimming 'decoder-size' to '-size' since the decoder name already precedes '-size'.
dev_dbg(&cxlr->dev,
- "%s:%s: decoder-size-%#llx * ways-%d != region-size-%#llx\n",
+ "%s:%s-size-%#llx * ways-%d + cache-%#llx != region-size-%#llx\n",
dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev), (u64)resource_size(cxled->dpa_res), p->interleave_ways,
- (u64)resource_size(p->res));
+ (u64)p->cache_size, (u64)resource_size(p->res));
return -EINVAL;
}
snip
Dave Jiang
maintainerPATCH v4 3/4 cxl: Add extended linear cache address alias emission for cxl events
In reply to Dave JiangAdd the aliased address of extended linear cache when emitting event trace for DRAM and general media of CXL events.
---
v4:
- Make error using ULLONG_MAX consistently. (Alison)
- Make hpa_alias0 naming consistent. (Alison)
- Swap incorrect position of hpa and hpa_alias0. (Alison)
--- drivers/cxl/core/mbox.c | 28 ++++++++++++++++++++++++---- drivers/cxl/core/trace.h | 22 ++++++++++++++-------- 2 files changed, 38 insertions(+), 12 deletions(-)
drivers/cxl/core/mbox.c +24 -4
@@ -856,6 +856,23 @@ int cxl_enumerate_cmds(struct cxl_memdev_state *mds) }EXPORT_SYMBOL_NS_GPL (cxl_enumerate_cmds,"CXL" ); +static u64 cxlr_hpa_cache_alias (struct cxl_region *cxlr,u64 hpa) +{ +struct cxl_region_params *p; + +if (!cxlr) +return ULLONG_MAX ; + + p = &cxlr->params; +if (!p->cache_size) +return ULLONG_MAX ; + +if (hpa >= p->res->start + p->cache_size) +return hpa - p->cache_size; + +return hpa + p->cache_size; +} + void cxl_event_trace_record(const struct cxl_memdev *cxlmd, enum cxl_event_log_type type, enum cxl_event_type event_type,
@@ -871,7 +888,7 @@ void cxl_event_trace_record(const struct cxl_memdev *cxlmd, }if (trace_cxl_general_media_enabled () ||trace_cxl_dram_enabled ()) { -u64 dpa, hpa =ULLONG_MAX ; +u64 dpa, hpa =ULLONG_MAX , hpa_alias =ULLONG_MAX ;struct cxl_region *cxlr;/*
@@ -884,14 +901,17 @@ void cxl_event_trace_record(const struct cxl_memdev *cxlmd, dpa =le64_to_cpu (evt->media_hdr.phys_addr) &CXL_DPA_MASK ; cxlr =cxl_dpa_to_region (cxlmd, dpa); -if (cxlr) +if (cxlr) { hpa =cxl_dpa_to_hpa (cxlr, cxlmd, dpa); + hpa_alias =cxlr_hpa_cache_alias (cxlr, hpa); + }if (event_type ==CXL_CPER_EVENT_GEN_MEDIA )trace_cxl_general_media (cxlmd, type, cxlr, hpa, - &evt->gen_media); + hpa_alias, &evt->gen_media);else if (event_type ==CXL_CPER_EVENT_DRAM ) -trace_cxl_dram (cxlmd, type, cxlr, hpa, &evt->dram); +trace_cxl_dram (cxlmd, type, cxlr, hpa, hpa_alias, + &evt->dram); } }EXPORT_SYMBOL_NS_GPL (cxl_event_trace_record,"CXL" );
drivers/cxl/core/trace.h +14 -8
@@ -392,9 +392,10 @@ TRACE_EVENT(cxl_generic_event, TRACE_EVENT(cxl_general_media, TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log, - struct cxl_region *cxlr, u64 hpa, struct cxl_event_gen_media *rec), + struct cxl_region *cxlr, u64 hpa, u64 hpa_alias0, + struct cxl_event_gen_media *rec), - TP_ARGS(cxlmd, log, cxlr, hpa, rec), + TP_ARGS(cxlmd, log, cxlr, hpa, hpa_alias0, rec), TP_STRUCT__entry( CXL_EVT_TP_entry
@@ -408,6 +409,7 @@ TRACE_EVENT(cxl_general_media,__array (u8, comp_id,CXL_EVENT_GEN_MED_COMP_ID_SIZE ) /* Following are out of order to pack trace record */ __field(u64, hpa) + __field(u64, hpa_alias0) __field_struct(uuid_t, region_uuid) __field(u16, validity_flags)__field (u8, rank)
@@ -438,6 +440,7 @@ TRACE_EVENT(cxl_general_media, CXL_EVENT_GEN_MED_COMP_ID_SIZE); __entry->validity_flags =get_unaligned_le16 (&rec->media_hdr.validity_flags); __entry->hpa = hpa; + __entry->hpa_alias0 = hpa_alias0;if (cxlr) {__assign_str (region_name);uuid_copy (&__entry->region_uuid, &cxlr->params.uuid);
@@ -455,7 +458,7 @@ TRACE_EVENT(cxl_general_media,"device=%x validity_flags='%s' " \"comp_id=%s comp_id_pldm_valid_flags='%s' " \"pldm_entity_id=%s pldm_resource_id=%s " \ -"hpa=%llx region=%s region_uuid=%pUb " \ +"hpa=%llx hpa_alias0=%llx region=%s region_uuid=%pUb " \"cme_threshold_ev_flags='%s' cme_count=%u" , __entry->dpa,show_dpa_flags (__entry->dpa_flags), show_event_desc_flags(__entry->descriptor),
@@ -470,7 +473,7 @@ TRACE_EVENT(cxl_general_media, CXL_GMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id),show_pldm_resource_id (__entry->validity_flags,CXL_GMER_VALID_COMPONENT ,CXL_GMER_VALID_COMPONENT_ID_FORMAT , __entry->comp_id), - __entry->hpa,__get_str (region_name), &__entry->region_uuid, + __entry->hpa, __entry->hpa_alias0,__get_str (region_name), &__entry->region_uuid,show_cme_threshold_ev_flags (__entry->cme_threshold_ev_flags), __entry->cme_count ) );
@@ -529,9 +532,10 @@ TRACE_EVENT(cxl_general_media, TRACE_EVENT(cxl_dram, TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log, - struct cxl_region *cxlr, u64 hpa, struct cxl_event_dram *rec), + struct cxl_region *cxlr, u64 hpa, u64 hpa_alias0, + struct cxl_event_dram *rec), - TP_ARGS(cxlmd, log, cxlr, hpa, rec), + TP_ARGS(cxlmd, log, cxlr, hpa, hpa_alias0, rec), TP_STRUCT__entry( CXL_EVT_TP_entry
@@ -547,6 +551,7 @@ TRACE_EVENT(cxl_dram, __field(u32, row) __array(u8, cor_mask, CXL_EVENT_DER_CORRECTION_MASK_SIZE) __field(u64, hpa) + __field(u64, hpa_alias0) __field_struct(uuid_t, region_uuid) __field(u8, rank) /* Out of order to pack trace record */__field (u8, bank_group)/* Out of order to pack trace record */
@@ -584,6 +589,7 @@ TRACE_EVENT(cxl_dram,memcpy (__entry->cor_mask, &rec->correction_mask,CXL_EVENT_DER_CORRECTION_MASK_SIZE ); __entry->hpa = hpa; + __entry->hpa_alias0 = hpa_alias0;if (cxlr) {__assign_str (region_name);uuid_copy (&__entry->region_uuid, &cxlr->params.uuid);
@@ -604,7 +610,7 @@ TRACE_EVENT(cxl_dram,"validity_flags='%s' " \"comp_id=%s comp_id_pldm_valid_flags='%s' " \"pldm_entity_id=%s pldm_resource_id=%s " \ -"hpa=%llx region=%s region_uuid=%pUb " \ +"hpa=%llx hpa_alias0=%llx region=%s region_uuid=%pUb " \"sub_channel=%u cme_threshold_ev_flags='%s' cvme_count=%u" , __entry->dpa,show_dpa_flags (__entry->dpa_flags), show_event_desc_flags(__entry->descriptor),
@@ -622,7 +628,7 @@ TRACE_EVENT(cxl_dram, CXL_DER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id),show_pldm_resource_id (__entry->validity_flags,CXL_DER_VALID_COMPONENT ,CXL_DER_VALID_COMPONENT_ID_FORMAT , __entry->comp_id), - __entry->hpa,__get_str (region_name), &__entry->region_uuid, + __entry->hpa, __entry->hpa_alias0,__get_str (region_name), &__entry->region_uuid, __entry->sub_channel,show_cme_threshold_ev_flags (__entry->cme_threshold_ev_flags), __entry->cvme_count )
Signature · 1 line
2.48.1
Re: [PATCH v4 3/4] cxl: Add extended linear cache address alias emission for cxl events
Quoted 5 lines · Dave Jiang
Add the aliased address of extended linear cache when emitting event trace for DRAM and general media of CXL events.
Reviewed-by Jonathan Cameron <[email protected]>Signed-off-by Dave Jiang <[email protected]>
Alison Schofield
maintainerRe: [PATCH v4 3/4] cxl: Add extended linear cache address alias emission for cxl events
In reply to Dave JiangQuoted 2 lines · Dave Jiang
Add the aliased address of extended linear cache when emitting event trace for DRAM and general media of CXL events.
What about cxl_poison trace events?
When cxl device poison lists are read, or poison is injected or cleared, an HPA is included in the trace event. Seems the hpa_alias0 belong there too.
Quoted 18 lines
Reviewed-by Jonathan Cameron <[email protected]>Signed-off-by Dave Jiang <[email protected]>---
v4:
- Make error usingULLONG_MAXconsistently. (Alison)
- Makehpa_alias0naming consistent. (Alison)
- Swap incorrect position of hpa andhpa_alias0. (Alison)--- drivers/cxl/core/mbox.c | 28 ++++++++++++++++++++++++---- drivers/cxl/core/trace.h | 22 ++++++++++++++-------- 2 files changed, 38 insertions(+), 12 deletions(-)drivers/cxl/core/mbox.c +0
-0
drivers/cxl/core/mbox.c int cxl_enumerate_cmds(struct cxl_memdev_state *mds) · line 864
Quoted 9 lines
drivers/cxl/core/mbox.c +6
-0@@ -856,6 +856,23 @@ int cxl_enumerate_cmds(struct cxl_memdev_state *mds) }EXPORT_SYMBOL_NS_GPL (cxl_enumerate_cmds,"CXL" ); +static u64 cxlr_hpa_cache_alias (struct cxl_region *cxlr,u64 hpa) +{ +struct cxl_region_params *p; + +if (!cxlr) +return ULLONG_MAX ;
checked cxlr in caller
drivers/cxl/core/mbox.c int cxl_enumerate_cmds(struct cxl_memdev_state *mds) · line 873
Quoted 9 lines
drivers/cxl/core/mbox.c +9
-0+ + p = &cxlr->params; +if (!p->cache_size) +return ULLONG_MAX ; + +if (hpa >= p->res->start + p->cache_size) +return hpa - p->cache_size; + +return hpa + p->cache_size;
Since a DPA can only be in the cxl resource half of the p->res, not in the extended cache, is alias always hpa - cache.
Quoted 13 lines
drivers/cxl/core/mbox.c +1
-1void cxl_event_trace_record(const struct cxl_memdev *cxlmd, enum cxl_event_log_type type, enum cxl_event_type event_type,@@ -871,7 +888,7 @@ void cxl_event_trace_record(const struct cxl_memdev *cxlmd, }if (trace_cxl_general_media_enabled () ||trace_cxl_dram_enabled ()) { -u64 dpa, hpa =ULLONG_MAX ; +u64 dpa, hpa =ULLONG_MAX , hpa_alias =ULLONG_MAX ;struct cxl_region *cxlr;/*
drivers/cxl/core/mbox.c void cxl_event_trace_record(const struct cxl_memdev *cxlmd, · line 908
Quoted 9 lines
drivers/cxl/core/mbox.c +3
-1@@ -884,14 +901,17 @@ void cxl_event_trace_record(const struct cxl_memdev *cxlmd, dpa =le64_to_cpu (evt->media_hdr.phys_addr) &CXL_DPA_MASK ; cxlr =cxl_dpa_to_region (cxlmd, dpa); -if (cxlr) +if (cxlr) { hpa =cxl_dpa_to_hpa (cxlr, cxlmd, dpa); + hpa_alias =cxlr_hpa_cache_alias (cxlr, hpa); + }
How about something like this to eliminate cxlr_hpa_cache_alias():
if (trace_cxl_general_media_enabled() || trace_cxl_dram_enabled()) {
- u64 dpa, hpa = ULLONG_MAX, hpa_alias = ULLONG_MAX;
+ u64 dpa, cache_size, hpa = ULLONG_MAX, hpa_alias = ULLONG_MAX;
struct cxl_region *cxlr;
/*
@@ -904,7 +887,9 @@ void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
cxlr = cxl_dpa_to_region(cxlmd, dpa);
if (cxlr) {
hpa = cxl_dpa_to_hpa(cxlr, cxlmd, dpa);
- hpa_alias = cxlr_hpa_cache_alias(cxlr, hpa);
+ cache_size = cxlr->params.cache_size;
+ if (cache_size)
+ hpa_alias = hpa - cache_size;
}
snip
Dave Jiang
maintainerPATCH v4 4/4 cxl: Add mce notifier to emit aliased address for extended linear cache
In reply to Dave JiangBelow 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.
---
v4:
- Move devm_add_action_or_reset() to devm_cxl_add_mce_notifier() (Ming)
--- arch/x86/mm/pat/set_memory.c | 1 + drivers/cxl/Kconfig | 4 +++ drivers/cxl/core/Makefile | 1 + drivers/cxl/core/mbox.c | 6 ++++ drivers/cxl/core/mce.c | 65 ++++++++++++++++++++++++++++++++++++ drivers/cxl/core/mce.h | 20 +++++++++++ drivers/cxl/core/region.c | 28 ++++++++++++++++ drivers/cxl/cxl.h | 6 ++++ drivers/cxl/cxlmem.h | 2 ++ tools/testing/cxl/Kbuild | 1 + 10 files changed, 134 insertions(+) create mode 100644 drivers/cxl/core/mce.c create mode 100644 drivers/cxl/core/mce.h
arch/x86/mm/pat/set_memory.c +1 -0
@@ -2081,6 +2081,7 @@ int set_mce_nospec(unsigned long pfn)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)
drivers/cxl/Kconfig +4 -0
@@ -146,4 +146,8 @@ config CXL_REGION_INVALIDATION_TEST 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
drivers/cxl/core/Makefile +1 -0
@@ -17,3 +17,4 @@ cxl_core-y += cdat.o 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
drivers/cxl/core/mbox.c +6 -0
@@ -11,6 +11,7 @@#include "core.h" #include "trace.h" +#include "mce.h" static bool cxl_raw_allow_all;
@@ -1458,6 +1459,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_mailbox_init, "CXL");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) {
@@ -1473,6 +1475,10 @@ struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev) 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" );
drivers/cxl/core/mce.c new file +65 -0
65 lines not on this page · raw message
drivers/cxl/core/mce.h new file +20 -0
@@ -0,0 +1,20 @@ +/* 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
drivers/cxl/core/region.c +28 -0
@@ -3445,6 +3445,34 @@ int cxl_add_to_region(struct cxl_port *root, struct cxl_endpoint_decoder *cxled) }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;
drivers/cxl/cxl.h +6 -0
@@ -877,6 +877,7 @@ struct cxl_pmem_region *to_cxl_pmem_region(struct device *dev);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) {
@@ -895,6 +896,11 @@ static inline struct cxl_dax_region *to_cxl_dax_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);
drivers/cxl/cxlmem.h +2 -0
@@ -477,6 +477,7 @@ static inline struct cxl_dev_state *mbox_to_cxlds(struct cxl_mailbox *cxl_mbox)* @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.
@@ -503,6 +504,7 @@ struct cxl_memdev_state {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 *
tools/testing/cxl/Kbuild +1 -0
@@ -64,6 +64,7 @@ cxl_core-y += $(CXL_CORE_SRC)/cdat.o 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
Signature · 1 line
2.48.1
Re: [PATCH v4 4/4] cxl: Add mce notifier to emit aliased address for extended linear cache
Quoted 18 lines · Dave Jiang
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.
Quoted 6 lines
Added symbol export to
set_mce_nospec()in x86 code in order to callset_mce_nospec()from the CXL MCE notify callback.Reviewed-by Jonathan Cameron <[email protected]>Signed-off-by Dave Jiang <[email protected]>