Commit 8e40612f authored by Jia He's avatar Jia He Committed by Borislav Petkov
Browse files

EDAC/ghes: Add a notifier for reporting memory errors 



In order to make it a proper module and disentangle it from facilities,
add a notifier for reporting memory errors. Use an atomic notifier
because calls sites like ghes_proc_in_irq() run in interrupt context.

  [ bp: Massage commit message. ]

Suggested-by: default avatarBorislav Petkov <bp@alien8.de>
Signed-off-by: default avatarJia He <justin.he@arm.com>
Signed-off-by: default avatarBorislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20221010023559.69655-3-justin.he@arm.com
parent 5012524e

drivers/acpi/apei/ghes.c

+15 −1
Original line number Diff line number Diff line
@@ -94,6 +94,8 @@ 
#define FIX_APEI_GHES_SDEI_CRITICAL	__end_of_fixed_addresses

#endif



static ATOMIC_NOTIFIER_HEAD(ghes_report_chain);



static inline bool is_hest_type_generic_v2(struct ghes *ghes)

{

	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
@@ -645,7 +647,7 @@ static bool ghes_do_proc(struct ghes *ghes, 
		if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {

			struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);



			ghes_edac_report_mem_error(sev, mem_err);

			atomic_notifier_call_chain(&ghes_report_chain, sev, mem_err);



			arch_apei_report_mem_error(sev, mem_err);

			queued = ghes_handle_memory_failure(gdata, sev);
@@ -1497,3 +1499,15 @@ void __init acpi_ghes_init(void) 
	else

		pr_info(GHES_PFX "Failed to enable APEI firmware first mode.\n");

}



void ghes_register_report_chain(struct notifier_block *nb)

{

	atomic_notifier_chain_register(&ghes_report_chain, nb);

}

EXPORT_SYMBOL_GPL(ghes_register_report_chain);



void ghes_unregister_report_chain(struct notifier_block *nb)

{

	atomic_notifier_chain_unregister(&ghes_report_chain, nb);

}

EXPORT_SYMBOL_GPL(ghes_unregister_report_chain);

drivers/edac/ghes_edac.c

+17 −2
Original line number Diff line number Diff line
@@ -14,6 +14,7 @@ 
#include <linux/dmi.h>

#include "edac_module.h"

#include <ras/ras_event.h>

#include <linux/notifier.h>



#define OTHER_DETAIL_LEN	400
@@ -267,11 +268,14 @@ static int print_mem_error_other_detail(const struct cper_sec_mem_err *mem, char 
	return n;

}



void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)

static int ghes_edac_report_mem_error(struct notifier_block *nb,

				      unsigned long val, void *data)

{

	struct cper_sec_mem_err *mem_err = (struct cper_sec_mem_err *)data;

	struct cper_mem_err_compact cmem;

	struct edac_raw_error_desc *e;

	struct mem_ctl_info *mci;

	unsigned long sev = val;

	struct ghes_pvt *pvt;

	unsigned long flags;

	char *p;
@@ -282,7 +286,7 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) 
	 * know.

	 */

	if (WARN_ON_ONCE(in_nmi()))

		return;

		return NOTIFY_OK;



	spin_lock_irqsave(&ghes_lock, flags);
@@ -374,8 +378,15 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) 


unlock:

	spin_unlock_irqrestore(&ghes_lock, flags);



	return NOTIFY_OK;

}



static struct notifier_block ghes_edac_mem_err_nb = {

	.notifier_call	= ghes_edac_report_mem_error,

	.priority	= 0,

};



/*

 * Known systems that are safe to enable this module.

 */
@@ -503,6 +514,8 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) 
	ghes_pvt = pvt;

	spin_unlock_irqrestore(&ghes_lock, flags);



	ghes_register_report_chain(&ghes_edac_mem_err_nb);



	/* only set on success */

	refcount_set(&ghes_refcount, 1);
@@ -548,6 +561,8 @@ void ghes_edac_unregister(struct ghes *ghes) 
	if (mci)

		edac_mc_free(mci);



	ghes_unregister_report_chain(&ghes_edac_mem_err_nb);



unlock:

	mutex_unlock(&ghes_reg_mutex);

}

include/acpi/ghes.h

+3 −7
Original line number Diff line number Diff line
@@ -76,18 +76,11 @@ int ghes_estatus_pool_init(int num_ghes); 
/* From drivers/edac/ghes_edac.c */



#ifdef CONFIG_EDAC_GHES

void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err);



int ghes_edac_register(struct ghes *ghes, struct device *dev);



void ghes_edac_unregister(struct ghes *ghes);



#else

static inline void ghes_edac_report_mem_error(int sev,

				       struct cper_sec_mem_err *mem_err)

{

}



static inline int ghes_edac_register(struct ghes *ghes, struct device *dev)

{

	return -ENODEV;
@@ -145,4 +138,7 @@ int ghes_notify_sea(void); 
static inline int ghes_notify_sea(void) { return -ENOENT; }

#endif



struct notifier_block;

extern void ghes_register_report_chain(struct notifier_block *nb);

extern void ghes_unregister_report_chain(struct notifier_block *nb);

#endif /* GHES_H */