Re: [PATCH 6/6] cxl/memdev: Register for and process CPER events

[Dan Williams]

Ira Weiny wrote:
> If the firmware has configured CXL event support to be firmware first
> the OS can process those events through CPER records.  The CXL layer has
> unique DPA to HPA knowledge and standard event trace parsing in place.
> Matching memory devices to the CPER records can be done via Bus, Device,
> Function which is part of the CPER record header.
> 
> Detect firmware first, register a notifier callback for each memdev, and
> trace events when they match the proper device.
> 
> Signed-off-by: Ira Weiny <ira.weiny@xxxxxxxxx>
> ---
>  drivers/cxl/core/mbox.c | 31 +++++++++++++++++++++-----
>  drivers/cxl/cxlmem.h    |  6 +++++
>  drivers/cxl/pci.c       | 58 ++++++++++++++++++++++++++++++++++++++++++++++++-
>  3 files changed, 89 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
> index 5ccc3843b736..8a0d4f67540d 100644
> --- a/drivers/cxl/core/mbox.c
> +++ b/drivers/cxl/core/mbox.c
> @@ -860,9 +860,30 @@ static const uuid_t mem_mod_event_uuid =
>  	UUID_INIT(0xfe927475, 0xdd59, 0x4339,
>  		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74);
>  
> -static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
> -				   enum cxl_event_log_type type,
> -				   struct cxl_event_record_raw *record)
> +void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
> +			    enum cxl_event_log_type type,
> +			    enum cxl_event_type event_type,
> +			    union cxl_event *event)
> +{
> +	switch (event_type) {
> +	case CXL_CPER_EVENT_GEN_MEDIA:
> +		trace_cxl_general_media(cxlmd, type, &gen_media_event_uuid,
> +					&event->gen_media);
> +		break;
> +	case CXL_CPER_EVENT_DRAM:
> +		trace_cxl_dram(cxlmd, type, &dram_event_uuid, &event->dram);
> +		break;
> +	case CXL_CPER_EVENT_MEM_MODULE:
> +		trace_cxl_memory_module(cxlmd, type, &mem_mod_event_uuid,
> +					&event->mem_module);
> +		break;
> +	}
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_event_trace_record, CXL);
> +
> +static void __cxl_event_trace_record(const struct cxl_memdev *cxlmd,
> +				     enum cxl_event_log_type type,
> +				     struct cxl_event_record_raw *record)
>  {
>  	union cxl_event *evt = &record->event;
>  	uuid_t *id = &record->id;
> @@ -985,8 +1006,8 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds,
>  			break;
>  
>  		for (i = 0; i < nr_rec; i++)
> -			cxl_event_trace_record(cxlmd, type,
> -					       &payload->records[i]);
> +			__cxl_event_trace_record(cxlmd, type,
> +						 &payload->records[i]);
>  
>  		if (payload->flags & CXL_GET_EVENT_FLAG_OVERFLOW)
>  			trace_cxl_overflow(cxlmd, type, payload);
> diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
> index f0e7ebb84f02..9cb0e3448780 100644
> --- a/drivers/cxl/cxlmem.h
> +++ b/drivers/cxl/cxlmem.h
> @@ -481,6 +481,8 @@ struct cxl_memdev_state {
>  	struct cxl_security_state security;
>  	struct cxl_fw_state fw;
>  
> +	struct notifier_block cxl_cper_nb;
> +
>  	struct rcuwait mbox_wait;
>  	int (*mbox_send)(struct cxl_memdev_state *mds,
>  			 struct cxl_mbox_cmd *cmd);
> @@ -778,6 +780,10 @@ void set_exclusive_cxl_commands(struct cxl_memdev_state *mds,
>  void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds,
>  				  unsigned long *cmds);
>  void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status);
> +void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
> +			    enum cxl_event_log_type type,
> +			    enum cxl_event_type event_type,
> +			    union cxl_event *event);
>  int cxl_set_timestamp(struct cxl_memdev_state *mds);
>  int cxl_poison_state_init(struct cxl_memdev_state *mds);
>  int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
> diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
> index 0155fb66b580..ec65c11baf17 100644
> --- a/drivers/cxl/pci.c
> +++ b/drivers/cxl/pci.c
> @@ -1,5 +1,6 @@
>  // SPDX-License-Identifier: GPL-2.0-only
>  /* Copyright(c) 2020 Intel Corporation. All rights reserved. */
> +#include <asm-generic/unaligned.h>
>  #include <linux/io-64-nonatomic-lo-hi.h>
>  #include <linux/moduleparam.h>
>  #include <linux/module.h>
> @@ -741,6 +742,59 @@ static bool cxl_event_int_is_fw(u8 setting)
>  	return mode == CXL_INT_FW;
>  }
>  
> +#define CXL_EVENT_HDR_FLAGS_REC_SEVERITY GENMASK(1, 0)
> +static int cxl_cper_event_call(struct notifier_block *nb, unsigned long action,
> +			       void *data)
> +{
> +	struct cxl_cper_notifier_data *nd = data;
> +	struct cper_cxl_event_devid *device_id = &nd->rec->hdr.device_id;
> +	enum cxl_event_log_type log_type;
> +	struct cxl_memdev_state *mds;
> +	struct cxl_dev_state *cxlds;
> +	struct pci_dev *pdev;
> +	unsigned int devfn;
> +	u32 hdr_flags;
> +
> +	mds = container_of(nb, struct cxl_memdev_state, cxl_cper_nb);
> +
> +	devfn = PCI_DEVFN(device_id->device_num, device_id->func_num);
> +	pdev = pci_get_domain_bus_and_slot(device_id->segment_num,
> +					   device_id->bus_num, devfn);
> +	cxlds = pci_get_drvdata(pdev);
> +	if (cxlds != &mds->cxlds) {

Checks of drvdata are only valid under the device lock, or with the
assumption that this callback will never be called while pci_get_drvdata
would return NULL.

With that, the check of cxlds looks like another artifact of using a
blocking notifier chain for this callback. With an explicit single
callback it simply becomes safe to assume that it is being called back
before unregister_cxl_cper() has run. I.e. it is impossible to even
write this check in that case.

> +		pci_dev_put(pdev);
> +		return NOTIFY_DONE;
> +	}
> +
> +	/* Fabricate a log type */
> +	hdr_flags = get_unaligned_le24(nd->rec->event.generic.hdr.flags);
> +	log_type = FIELD_GET(CXL_EVENT_HDR_FLAGS_REC_SEVERITY, hdr_flags);
> +
> +	cxl_event_trace_record(mds->cxlds.cxlmd, log_type, nd->event_type,
> +			       &nd->rec->event);
> +	pci_dev_put(pdev);
> +	return NOTIFY_OK;
> +}
> +
> +static void cxl_unregister_cper_events(void *_mds)
> +{
> +	struct cxl_memdev_state *mds = _mds;
> +
> +	unregister_cxl_cper_notifier(&mds->cxl_cper_nb);
> +}
> +
> +static void register_cper_events(struct cxl_memdev_state *mds)
> +{
> +	mds->cxl_cper_nb.notifier_call = cxl_cper_event_call;
> +
> +	if (register_cxl_cper_notifier(&mds->cxl_cper_nb)) {
> +		dev_err(mds->cxlds.dev, "CPER registration failed\n");
> +		return;
> +	}
> +
> +	devm_add_action_or_reset(mds->cxlds.dev, cxl_unregister_cper_events, mds);

Longer term I am not sure cxl_pci should be doing this registration
directly to the CPER code vs some indirection in the core that the
generic type-3 and the type-2 cases can register for processing. That
can definitely wait until a Type-2 CXL.mem device driver arrives and
wants to get notified of CXL CPER events.

> +}
> +
>  static int cxl_event_config(struct pci_host_bridge *host_bridge,
>  			    struct cxl_memdev_state *mds)
>  {
> @@ -751,8 +805,10 @@ static int cxl_event_config(struct pci_host_bridge *host_bridge,
>  	 * When BIOS maintains CXL error reporting control, it will process
>  	 * event records.  Only one agent can do so.
>  	 */
> -	if (!host_bridge->native_cxl_error)
> +	if (!host_bridge->native_cxl_error) {
> +		register_cper_events(mds);
>  		return 0;
> +	}
>  
>  	rc = cxl_mem_alloc_event_buf(mds);
>  	if (rc)
> 
> -- 
> 2.42.0
>