Merge tag 'edac_updates_for_6.2' of git://git.kernel.org/pub/scm/linu…

…x/kernel/git/ras/ras

Pull EDAC updates from Borislav Petkov:

 - Make ghes_edac a simple module like the rest of the EDAC drivers and
   drop the forced built-in only configuration by disentangling it from
   GHES (Jia He)

 - The usual small cleanups and improvements all over EDAC land

* tag 'edac_updates_for_6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras:
  EDAC/i10nm: fix refcount leak in pci_get_dev_wrapper()
  EDAC/i5400: Fix typo in comment: vaious -> various
  EDAC/mc_sysfs: Increase legacy channel support to 12
  MAINTAINERS: Make Mauro EDAC reviewer
  MAINTAINERS: Make Manivannan Sadhasivam the maintainer of qcom_edac
  EDAC/igen6: Return the correct error type when not the MC owner
  apei/ghes: Use xchg_release() for updating new cache slot instead of cmpxchg()
  EDAC: Check for GHES preference in the chipset-specific EDAC drivers
  EDAC/ghes: Make ghes_edac a proper module
  EDAC/ghes: Prepare to make ghes_edac a proper module
  EDAC/ghes: Add a notifier for reporting memory errors
  efi/cper: Export several helpers for ghes_edac to use
  EDAC/i5000: Mark as BROKEN

MAINTAINERS

@@ -7386,9 +7386,9 @@ F:	drivers/edac/thunderx_edac*
 
 EDAC-CORE
 M:	Borislav Petkov <bp@alien8.de>
-M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 M:	Tony Luck <tony.luck@intel.com>
 R:	James Morse <james.morse@arm.com>
+R:	Mauro Carvalho Chehab <mchehab@kernel.org>
 R:	Robert Richter <rric@kernel.org>
 L:	linux-edac@vger.kernel.org
 S:	Supported
@@ -7505,8 +7505,7 @@ S:	Maintained
 F:	drivers/edac/pnd2_edac.[ch]
 
 EDAC-QCOM
-M:	Channagoud Kadabi <ckadabi@codeaurora.org>
-M:	Venkata Narendra Kumar Gutta <vnkgutta@codeaurora.org>
+M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
 L:	linux-arm-msm@vger.kernel.org
 L:	linux-edac@vger.kernel.org
 S:	Maintained

drivers/acpi/apei/ghes.c

@@ -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;
@@ -107,6 +109,13 @@ static inline bool is_hest_type_generic_v2(struct ghes *ghes)
 bool ghes_disable;
 module_param_named(disable, ghes_disable, bool, 0);
 
+/*
+ * "ghes.edac_force_enable" forcibly enables ghes_edac and skips the platform
+ * check.
+ */
+static bool ghes_edac_force_enable;
+module_param_named(edac_force_enable, ghes_edac_force_enable, bool, 0);
+
 /*
  * All error sources notified with HED (Hardware Error Device) share a
  * single notifier callback, so they need to be linked and checked one
@@ -118,6 +127,13 @@ module_param_named(disable, ghes_disable, bool, 0);
 static LIST_HEAD(ghes_hed);
 static DEFINE_MUTEX(ghes_list_mutex);
 
+/*
+ * A list of GHES devices which are given to the corresponding EDAC driver
+ * ghes_edac for further use.
+ */
+static LIST_HEAD(ghes_devs);
+static DEFINE_MUTEX(ghes_devs_mutex);
+
 /*
  * Because the memory area used to transfer hardware error information
  * from BIOS to Linux can be determined only in NMI, IRQ or timer
@@ -645,7 +661,7 @@ 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);
@@ -1382,7 +1398,11 @@ static int ghes_probe(struct platform_device *ghes_dev)
 
 	platform_set_drvdata(ghes_dev, ghes);
 
-	ghes_edac_register(ghes, &ghes_dev->dev);
+	ghes->dev = &ghes_dev->dev;
+
+	mutex_lock(&ghes_devs_mutex);
+	list_add_tail(&ghes->elist, &ghes_devs);
+	mutex_unlock(&ghes_devs_mutex);
 
 	/* Handle any pending errors right away */
 	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
@@ -1446,7 +1466,9 @@ static int ghes_remove(struct platform_device *ghes_dev)
 
 	ghes_fini(ghes);
 
-	ghes_edac_unregister(ghes);
+	mutex_lock(&ghes_devs_mutex);
+	list_del(&ghes->elist);
+	mutex_unlock(&ghes_devs_mutex);
 
 	kfree(ghes);
 
@@ -1501,3 +1523,41 @@ void __init acpi_ghes_init(void)
 	else
 		pr_info(GHES_PFX "Failed to enable APEI firmware first mode.\n");
 }
+
+/*
+ * Known x86 systems that prefer GHES error reporting:
+ */
+static struct acpi_platform_list plat_list[] = {
+	{"HPE   ", "Server  ", 0, ACPI_SIG_FADT, all_versions},
+	{ } /* End */
+};
+
+struct list_head *ghes_get_devices(void)
+{
+	int idx = -1;
+
+	if (IS_ENABLED(CONFIG_X86)) {
+		idx = acpi_match_platform_list(plat_list);
+		if (idx < 0) {
+			if (!ghes_edac_force_enable)
+				return NULL;
+
+			pr_warn_once("Force-loading ghes_edac on an unsupported platform. You're on your own!\n");
+		}
+	}
+
+	return &ghes_devs;
+}
+EXPORT_SYMBOL_GPL(ghes_get_devices);
+
+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/Kconfig

@@ -53,8 +53,8 @@ config EDAC_DECODE_MCE
 	  has been initialized.
 
 config EDAC_GHES
-	bool "Output ACPI APEI/GHES BIOS detected errors via EDAC"
-	depends on ACPI_APEI_GHES && (EDAC=y)
+	tristate "Output ACPI APEI/GHES BIOS detected errors via EDAC"
+	depends on ACPI_APEI_GHES
 	select UEFI_CPER
 	help
 	  Not all machines support hardware-driven error report. Some of those
@@ -211,6 +211,7 @@ config EDAC_R82600
 config EDAC_I5000
 	tristate "Intel Greencreek/Blackford chipset"
 	depends on X86 && PCI
+	depends on BROKEN
 	help
 	  Support for error detection and correction the Intel
 	  Greekcreek/Blackford chipsets.

drivers/edac/amd64_edac.c

@@ -4329,6 +4329,9 @@ static int __init amd64_edac_init(void)
 	int err = -ENODEV;
 	int i;
 
+	if (ghes_get_devices())
+		return -EBUSY;
+
 	owner = edac_get_owner();
 	if (owner && strncmp(owner, EDAC_MOD_STR, sizeof(EDAC_MOD_STR)))
 		return -EBUSY;

drivers/edac/armada_xp_edac.c

@@ -599,6 +599,9 @@ static int __init armada_xp_edac_init(void)
 {
 	int res;
 
+	if (ghes_get_devices())
+		return -EBUSY;
+
 	/* only polling is supported */
 	edac_op_state = EDAC_OPSTATE_POLL;
 

drivers/edac/edac_mc_sysfs.c

@@ -298,6 +298,14 @@ DEVICE_CHANNEL(ch6_dimm_label, S_IRUGO | S_IWUSR,
 	channel_dimm_label_show, channel_dimm_label_store, 6);
 DEVICE_CHANNEL(ch7_dimm_label, S_IRUGO | S_IWUSR,
 	channel_dimm_label_show, channel_dimm_label_store, 7);
+DEVICE_CHANNEL(ch8_dimm_label, S_IRUGO | S_IWUSR,
+	channel_dimm_label_show, channel_dimm_label_store, 8);
+DEVICE_CHANNEL(ch9_dimm_label, S_IRUGO | S_IWUSR,
+	channel_dimm_label_show, channel_dimm_label_store, 9);
+DEVICE_CHANNEL(ch10_dimm_label, S_IRUGO | S_IWUSR,
+	channel_dimm_label_show, channel_dimm_label_store, 10);
+DEVICE_CHANNEL(ch11_dimm_label, S_IRUGO | S_IWUSR,
+	channel_dimm_label_show, channel_dimm_label_store, 11);
 
 /* Total possible dynamic DIMM Label attribute file table */
 static struct attribute *dynamic_csrow_dimm_attr[] = {
@@ -309,6 +317,10 @@ static struct attribute *dynamic_csrow_dimm_attr[] = {
 	&dev_attr_legacy_ch5_dimm_label.attr.attr,
 	&dev_attr_legacy_ch6_dimm_label.attr.attr,
 	&dev_attr_legacy_ch7_dimm_label.attr.attr,
+	&dev_attr_legacy_ch8_dimm_label.attr.attr,
+	&dev_attr_legacy_ch9_dimm_label.attr.attr,
+	&dev_attr_legacy_ch10_dimm_label.attr.attr,
+	&dev_attr_legacy_ch11_dimm_label.attr.attr,
 	NULL
 };
 
@@ -329,6 +341,14 @@ DEVICE_CHANNEL(ch6_ce_count, S_IRUGO,
 		   channel_ce_count_show, NULL, 6);
 DEVICE_CHANNEL(ch7_ce_count, S_IRUGO,
 		   channel_ce_count_show, NULL, 7);
+DEVICE_CHANNEL(ch8_ce_count, S_IRUGO,
+		   channel_ce_count_show, NULL, 8);
+DEVICE_CHANNEL(ch9_ce_count, S_IRUGO,
+		   channel_ce_count_show, NULL, 9);
+DEVICE_CHANNEL(ch10_ce_count, S_IRUGO,
+		   channel_ce_count_show, NULL, 10);
+DEVICE_CHANNEL(ch11_ce_count, S_IRUGO,
+		   channel_ce_count_show, NULL, 11);
 
 /* Total possible dynamic ce_count attribute file table */
 static struct attribute *dynamic_csrow_ce_count_attr[] = {
@@ -340,6 +360,10 @@ static struct attribute *dynamic_csrow_ce_count_attr[] = {
 	&dev_attr_legacy_ch5_ce_count.attr.attr,
 	&dev_attr_legacy_ch6_ce_count.attr.attr,
 	&dev_attr_legacy_ch7_ce_count.attr.attr,
+	&dev_attr_legacy_ch8_ce_count.attr.attr,
+	&dev_attr_legacy_ch9_ce_count.attr.attr,
+	&dev_attr_legacy_ch10_ce_count.attr.attr,
+	&dev_attr_legacy_ch11_ce_count.attr.attr,
 	NULL
 };
 

drivers/edac/edac_module.h

@@ -11,6 +11,7 @@
 #ifndef	__EDAC_MODULE_H__
 #define	__EDAC_MODULE_H__
 
+#include <acpi/ghes.h>
 #include "edac_mc.h"
 #include "edac_pci.h"
 #include "edac_device.h"