linux/include/cxl/event.h

176 lines
3.7 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright(c) 2023 Intel Corporation. */
#ifndef _LINUX_CXL_EVENT_H
#define _LINUX_CXL_EVENT_H
#include <linux/types.h>
#include <linux/uuid.h>
acpi/ghes: Process CXL Component Events BIOS can configure memory devices as firmware first. This will send CXL events to the firmware instead of the OS. The firmware can then inform the OS of these events via UEFI. UEFI v2.10 section N.2.14 defines a Common Platform Error Record (CPER) format for CXL Component Events. The format is mostly the same as the CXL Common Event Record Format. The difference lies in the use of a GUID as the CPER Section Type which matches the UUID defined in CXL 3.1 Table 8-43. Currently a configuration such as this will trace a non standard event in the log omitting useful details of the event. In addition the CXL sub-system contains additional region and HPA information useful to the user.[0] The CXL code is required to be called from process context as it needs to take a device lock. The GHES code may be in interrupt context. This complicated the use of a callback. Dan Williams suggested the use of work items as an atomic way of switching between the callback execution and a default handler.[1] The use of a kfifo simplifies queue processing by providing lock free fifo operations. cxl_cper_kfifo_get() allows easier management of the kfifo between the ghes and cxl modules. CXL 3.1 Table 8-127 requires a device to have a queue depth of 1 for each of the four event logs. A combined queue depth of 32 is chosen to provide room for 8 entries of each log type. Add GHES support to detect CXL CPER records. Add the ability for the CXL sub-system to register a work queue to process the events. This patch adds back the functionality which was removed to fix the report by Dan Carpenter[2]. Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Borislav Petkov <bp@alien8.de> Suggested-by: Dan Carpenter <dan.carpenter@linaro.org> Suggested-by: Dan Williams <dan.j.williams@intel.com> Link: http://lore.kernel.org/r/cover.1711598777.git.alison.schofield@intel.com [0] Link: http://lore.kernel.org/r/65d111eb87115_6c745294ac@dwillia2-xfh.jf.intel.com.notmuch [1] Link: http://lore.kernel.org/r/b963c490-2c13-4b79-bbe7-34c6568423c7@moroto.mountain [2] Reviewed-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: Tony Luck <tony.luck@intel.com> Tested-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com> Link: https://lore.kernel.org/r/20240426-cxl-cper3-v4-1-58076cce1624@intel.com Signed-off-by: Dave Jiang <dave.jiang@intel.com>
2024-04-26 20:34:00 -07:00
#include <linux/workqueue_types.h>
/*
* Common Event Record Format
* CXL rev 3.0 section 8.2.9.2.1; Table 8-42
*/
struct cxl_event_record_hdr {
u8 length;
u8 flags[3];
__le16 handle;
__le16 related_handle;
__le64 timestamp;
u8 maint_op_class;
u8 reserved[15];
} __packed;
struct cxl_event_media_hdr {
struct cxl_event_record_hdr hdr;
__le64 phys_addr;
u8 descriptor;
u8 type;
u8 transaction_type;
/*
* The meaning of Validity Flags from bit 2 is
* different across DRAM and General Media records
*/
u8 validity_flags[2];
u8 channel;
u8 rank;
} __packed;
#define CXL_EVENT_RECORD_DATA_LENGTH 0x50
struct cxl_event_generic {
struct cxl_event_record_hdr hdr;
u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
} __packed;
/*
* General Media Event Record
* CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
*/
#define CXL_EVENT_GEN_MED_COMP_ID_SIZE 0x10
struct cxl_event_gen_media {
struct cxl_event_media_hdr media_hdr;
u8 device[3];
u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
u8 reserved[46];
} __packed;
/*
* DRAM Event Record - DER
* CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44
*/
#define CXL_EVENT_DER_CORRECTION_MASK_SIZE 0x20
struct cxl_event_dram {
struct cxl_event_media_hdr media_hdr;
u8 nibble_mask[3];
u8 bank_group;
u8 bank;
u8 row[3];
u8 column[2];
u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE];
u8 reserved[0x17];
} __packed;
/*
* Get Health Info Record
* CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100
*/
struct cxl_get_health_info {
u8 health_status;
u8 media_status;
u8 add_status;
u8 life_used;
u8 device_temp[2];
u8 dirty_shutdown_cnt[4];
u8 cor_vol_err_cnt[4];
u8 cor_per_err_cnt[4];
} __packed;
/*
* Memory Module Event Record
* CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
*/
struct cxl_event_mem_module {
struct cxl_event_record_hdr hdr;
u8 event_type;
struct cxl_get_health_info info;
u8 reserved[0x3d];
} __packed;
union cxl_event {
struct cxl_event_generic generic;
struct cxl_event_gen_media gen_media;
struct cxl_event_dram dram;
struct cxl_event_mem_module mem_module;
/* dram & gen_media event header */
struct cxl_event_media_hdr media_hdr;
} __packed;
/*
* Common Event Record Format; in event logs
* CXL rev 3.0 section 8.2.9.2.1; Table 8-42
*/
struct cxl_event_record_raw {
uuid_t id;
union cxl_event event;
} __packed;
enum cxl_event_type {
CXL_CPER_EVENT_GENERIC,
CXL_CPER_EVENT_GEN_MEDIA,
CXL_CPER_EVENT_DRAM,
CXL_CPER_EVENT_MEM_MODULE,
};
#define CPER_CXL_DEVICE_ID_VALID BIT(0)
#define CPER_CXL_DEVICE_SN_VALID BIT(1)
#define CPER_CXL_COMP_EVENT_LOG_VALID BIT(2)
struct cxl_cper_event_rec {
struct {
u32 length;
u64 validation_bits;
struct cper_cxl_event_devid {
u16 vendor_id;
u16 device_id;
u8 func_num;
u8 device_num;
u8 bus_num;
u16 segment_num;
u16 slot_num; /* bits 2:0 reserved */
u8 reserved;
} __packed device_id;
struct cper_cxl_event_sn {
u32 lower_dw;
u32 upper_dw;
} __packed dev_serial_num;
} __packed hdr;
union cxl_event event;
} __packed;
acpi/ghes: Process CXL Component Events BIOS can configure memory devices as firmware first. This will send CXL events to the firmware instead of the OS. The firmware can then inform the OS of these events via UEFI. UEFI v2.10 section N.2.14 defines a Common Platform Error Record (CPER) format for CXL Component Events. The format is mostly the same as the CXL Common Event Record Format. The difference lies in the use of a GUID as the CPER Section Type which matches the UUID defined in CXL 3.1 Table 8-43. Currently a configuration such as this will trace a non standard event in the log omitting useful details of the event. In addition the CXL sub-system contains additional region and HPA information useful to the user.[0] The CXL code is required to be called from process context as it needs to take a device lock. The GHES code may be in interrupt context. This complicated the use of a callback. Dan Williams suggested the use of work items as an atomic way of switching between the callback execution and a default handler.[1] The use of a kfifo simplifies queue processing by providing lock free fifo operations. cxl_cper_kfifo_get() allows easier management of the kfifo between the ghes and cxl modules. CXL 3.1 Table 8-127 requires a device to have a queue depth of 1 for each of the four event logs. A combined queue depth of 32 is chosen to provide room for 8 entries of each log type. Add GHES support to detect CXL CPER records. Add the ability for the CXL sub-system to register a work queue to process the events. This patch adds back the functionality which was removed to fix the report by Dan Carpenter[2]. Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Borislav Petkov <bp@alien8.de> Suggested-by: Dan Carpenter <dan.carpenter@linaro.org> Suggested-by: Dan Williams <dan.j.williams@intel.com> Link: http://lore.kernel.org/r/cover.1711598777.git.alison.schofield@intel.com [0] Link: http://lore.kernel.org/r/65d111eb87115_6c745294ac@dwillia2-xfh.jf.intel.com.notmuch [1] Link: http://lore.kernel.org/r/b963c490-2c13-4b79-bbe7-34c6568423c7@moroto.mountain [2] Reviewed-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: Tony Luck <tony.luck@intel.com> Tested-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com> Link: https://lore.kernel.org/r/20240426-cxl-cper3-v4-1-58076cce1624@intel.com Signed-off-by: Dave Jiang <dave.jiang@intel.com>
2024-04-26 20:34:00 -07:00
struct cxl_cper_work_data {
enum cxl_event_type event_type;
struct cxl_cper_event_rec rec;
};
#ifdef CONFIG_ACPI_APEI_GHES
int cxl_cper_register_work(struct work_struct *work);
int cxl_cper_unregister_work(struct work_struct *work);
int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd);
#else
static inline int cxl_cper_register_work(struct work_struct *work)
acpi/ghes: Process CXL Component Events BIOS can configure memory devices as firmware first. This will send CXL events to the firmware instead of the OS. The firmware can then inform the OS of these events via UEFI. UEFI v2.10 section N.2.14 defines a Common Platform Error Record (CPER) format for CXL Component Events. The format is mostly the same as the CXL Common Event Record Format. The difference lies in the use of a GUID as the CPER Section Type which matches the UUID defined in CXL 3.1 Table 8-43. Currently a configuration such as this will trace a non standard event in the log omitting useful details of the event. In addition the CXL sub-system contains additional region and HPA information useful to the user.[0] The CXL code is required to be called from process context as it needs to take a device lock. The GHES code may be in interrupt context. This complicated the use of a callback. Dan Williams suggested the use of work items as an atomic way of switching between the callback execution and a default handler.[1] The use of a kfifo simplifies queue processing by providing lock free fifo operations. cxl_cper_kfifo_get() allows easier management of the kfifo between the ghes and cxl modules. CXL 3.1 Table 8-127 requires a device to have a queue depth of 1 for each of the four event logs. A combined queue depth of 32 is chosen to provide room for 8 entries of each log type. Add GHES support to detect CXL CPER records. Add the ability for the CXL sub-system to register a work queue to process the events. This patch adds back the functionality which was removed to fix the report by Dan Carpenter[2]. Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Borislav Petkov <bp@alien8.de> Suggested-by: Dan Carpenter <dan.carpenter@linaro.org> Suggested-by: Dan Williams <dan.j.williams@intel.com> Link: http://lore.kernel.org/r/cover.1711598777.git.alison.schofield@intel.com [0] Link: http://lore.kernel.org/r/65d111eb87115_6c745294ac@dwillia2-xfh.jf.intel.com.notmuch [1] Link: http://lore.kernel.org/r/b963c490-2c13-4b79-bbe7-34c6568423c7@moroto.mountain [2] Reviewed-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: Tony Luck <tony.luck@intel.com> Tested-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com> Link: https://lore.kernel.org/r/20240426-cxl-cper3-v4-1-58076cce1624@intel.com Signed-off-by: Dave Jiang <dave.jiang@intel.com>
2024-04-26 20:34:00 -07:00
{
return 0;
}
static inline int cxl_cper_unregister_work(struct work_struct *work)
acpi/ghes: Process CXL Component Events BIOS can configure memory devices as firmware first. This will send CXL events to the firmware instead of the OS. The firmware can then inform the OS of these events via UEFI. UEFI v2.10 section N.2.14 defines a Common Platform Error Record (CPER) format for CXL Component Events. The format is mostly the same as the CXL Common Event Record Format. The difference lies in the use of a GUID as the CPER Section Type which matches the UUID defined in CXL 3.1 Table 8-43. Currently a configuration such as this will trace a non standard event in the log omitting useful details of the event. In addition the CXL sub-system contains additional region and HPA information useful to the user.[0] The CXL code is required to be called from process context as it needs to take a device lock. The GHES code may be in interrupt context. This complicated the use of a callback. Dan Williams suggested the use of work items as an atomic way of switching between the callback execution and a default handler.[1] The use of a kfifo simplifies queue processing by providing lock free fifo operations. cxl_cper_kfifo_get() allows easier management of the kfifo between the ghes and cxl modules. CXL 3.1 Table 8-127 requires a device to have a queue depth of 1 for each of the four event logs. A combined queue depth of 32 is chosen to provide room for 8 entries of each log type. Add GHES support to detect CXL CPER records. Add the ability for the CXL sub-system to register a work queue to process the events. This patch adds back the functionality which was removed to fix the report by Dan Carpenter[2]. Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Borislav Petkov <bp@alien8.de> Suggested-by: Dan Carpenter <dan.carpenter@linaro.org> Suggested-by: Dan Williams <dan.j.williams@intel.com> Link: http://lore.kernel.org/r/cover.1711598777.git.alison.schofield@intel.com [0] Link: http://lore.kernel.org/r/65d111eb87115_6c745294ac@dwillia2-xfh.jf.intel.com.notmuch [1] Link: http://lore.kernel.org/r/b963c490-2c13-4b79-bbe7-34c6568423c7@moroto.mountain [2] Reviewed-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: Tony Luck <tony.luck@intel.com> Tested-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com> Link: https://lore.kernel.org/r/20240426-cxl-cper3-v4-1-58076cce1624@intel.com Signed-off-by: Dave Jiang <dave.jiang@intel.com>
2024-04-26 20:34:00 -07:00
{
return 0;
}
static inline int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd)
{
return 0;
}
#endif
#endif /* _LINUX_CXL_EVENT_H */