Merge tag 'edac_for_5.5' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras

Pull EDAC updates from Borislav Petkov:
 "A lot of changes this time around, details below.

  From the next cycle onwards, we'll switch the EDAC tree to topic
  branches (instead of a single edac-for-next branch) which should make
  the changes handling more flexible, hopefully. We'll see.

  Summary:

   - Rework error logging functions to accept a count of errors
     parameter (Hanna Hawa)

   - Part one of substantial EDAC core + ghes_edac driver cleanup
     (Robert Richter)

   - Print additional useful logging information in skx_* (Tony Luck)

   - Improve amd64_edac hw detection + cleanups (Yazen Ghannam)

   - Misc cleanups, fixes and code improvements"

* tag 'edac_for_5.5' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras: (35 commits)
  EDAC/altera: Use the Altera System Manager driver
  EDAC/altera: Cleanup the ECC Manager
  EDAC/altera: Use fast register IO for S10 IRQs
  EDAC/ghes: Do not warn when incrementing refcount on 0
  EDAC/Documentation: Describe CPER module definition and DIMM ranks
  EDAC: Unify the mc_event tracepoint call
  EDAC/ghes: Remove intermediate buffer pvt->detail_location
  EDAC/ghes: Fix grain calculation
  EDAC/ghes: Use standard kernel macros for page calculations
  EDAC: Remove misleading comment in struct edac_raw_error_desc
  EDAC/mc: Reduce indentation level in edac_mc_handle_error()
  EDAC/mc: Remove needless zero string termination
  EDAC/mc: Do not BUG_ON() in edac_mc_alloc()
  EDAC: Introduce an mci_for_each_dimm() iterator
  EDAC: Remove EDAC_DIMM_OFF() macro
  EDAC: Replace EDAC_DIMM_PTR() macro with edac_get_dimm() function
  EDAC/amd64: Get rid of the ECC disabled long message
  EDAC/ghes: Fix locking and memory barrier issues
  EDAC/amd64: Check for memory before fully initializing an instance
  EDAC/amd64: Use cached data when checking for ECC
  ...

Author: torvalds

Documentation/admin-guide/ras.rst

@@ -330,9 +330,12 @@ There can be multiple csrows and multiple channels.
 
 .. [#f4] Nowadays, the term DIMM (Dual In-line Memory Module) is widely
   used to refer to a memory module, although there are other memory
-  packaging alternatives, like SO-DIMM, SIMM, etc. Along this document,
-  and inside the EDAC system, the term "dimm" is used for all memory
-  modules, even when they use a different kind of packaging.
+  packaging alternatives, like SO-DIMM, SIMM, etc. The UEFI
+  specification (Version 2.7) defines a memory module in the Common
+  Platform Error Record (CPER) section to be an SMBIOS Memory Device
+  (Type 17). Along this document, and inside the EDAC subsystem, the term
+  "dimm" is used for all memory modules, even when they use a
+  different kind of packaging.
 
 Memory controllers allow for several csrows, with 8 csrows being a
 typical value. Yet, the actual number of csrows depends on the layout of
@@ -349,12 +352,14 @@ controllers. The following example will assume 2 channels:
 	|            |  ``ch0``  |  ``ch1``  |
 	+============+===========+===========+
 	| ``csrow0`` |  DIMM_A0  |  DIMM_B0  |
-	+------------+           |           |
-	| ``csrow1`` |           |           |
+	|            |   rank0   |   rank0   |
+	+------------+     -     |     -     |
+	| ``csrow1`` |   rank1   |   rank1   |
 	+------------+-----------+-----------+
 	| ``csrow2`` |  DIMM_A1  | DIMM_B1   |
-	+------------+           |           |
-	| ``csrow3`` |           |           |
+	|            |   rank0   |   rank0   |
+	+------------+     -     |     -     |
+	| ``csrow3`` |   rank1   |   rank1   |
 	+------------+-----------+-----------+
 
 In the above example, there are 4 physical slots on the motherboard
@@ -374,11 +379,13 @@ which the memory DIMM is placed. Thus, when 1 DIMM is placed in each
 Channel, the csrows cross both DIMMs.
 
 Memory DIMMs come single or dual "ranked". A rank is a populated csrow.
-Thus, 2 single ranked DIMMs, placed in slots DIMM_A0 and DIMM_B0 above
-will have just one csrow (csrow0). csrow1 will be empty. On the other
-hand, when 2 dual ranked DIMMs are similarly placed, then both csrow0
-and csrow1 will be populated. The pattern repeats itself for csrow2 and
-csrow3.
+In the example above 2 dual ranked DIMMs are similarly placed. Thus,
+both csrow0 and csrow1 are populated. On the other hand, when 2 single
+ranked DIMMs are placed in slots DIMM_A0 and DIMM_B0, then they will
+have just one csrow (csrow0) and csrow1 will be empty. The pattern
+repeats itself for csrow2 and csrow3. Also note that some memory
+controllers don't have any logic to identify the memory module, see
+``rankX`` directories below.
 
 The representation of the above is reflected in the directory
 tree in EDAC's sysfs interface. Starting in directory

drivers/edac/altera_edac.c

@@ -14,6 +14,7 @@
 #include <linux/interrupt.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/kernel.h>
+#include <linux/mfd/altera-sysmgr.h>
 #include <linux/mfd/syscon.h>
 #include <linux/notifier.h>
 #include <linux/of_address.h>
@@ -275,7 +276,6 @@ static int a10_unmask_irq(struct platform_device *pdev, u32 mask)
 	return ret;
 }
 
-static int socfpga_is_a10(void);
 static int altr_sdram_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *id;
@@ -399,7 +399,7 @@ static int altr_sdram_probe(struct platform_device *pdev)
 		goto err;
 
 	/* Only the Arria10 has separate IRQs */
-	if (socfpga_is_a10()) {
+	if (of_machine_is_compatible("altr,socfpga-arria10")) {
 		/* Arria10 specific initialization */
 		res = a10_init(mc_vbase);
 		if (res < 0)
@@ -502,68 +502,6 @@ module_platform_driver(altr_sdram_edac_driver);
 
 #endif	/* CONFIG_EDAC_ALTERA_SDRAM */
 
-/**************** Stratix 10 EDAC Memory Controller Functions ************/
-
-/**
- * s10_protected_reg_write
- * Write to a protected SMC register.
- * @context: Not used.
- * @reg: Address of register
- * @value: Value to write
- * Return: INTEL_SIP_SMC_STATUS_OK (0) on success
- *	   INTEL_SIP_SMC_REG_ERROR on error
- *	   INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION if not supported
- */
-static int s10_protected_reg_write(void *context, unsigned int reg,
-				   unsigned int val)
-{
-	struct arm_smccc_res result;
-	unsigned long offset = (unsigned long)context;
-
-	arm_smccc_smc(INTEL_SIP_SMC_REG_WRITE, offset + reg, val, 0, 0,
-		      0, 0, 0, &result);
-
-	return (int)result.a0;
-}
-
-/**
- * s10_protected_reg_read
- * Read the status of a protected SMC register
- * @context: Not used.
- * @reg: Address of register
- * @value: Value read.
- * Return: INTEL_SIP_SMC_STATUS_OK (0) on success
- *	   INTEL_SIP_SMC_REG_ERROR on error
- *	   INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION if not supported
- */
-static int s10_protected_reg_read(void *context, unsigned int reg,
-				  unsigned int *val)
-{
-	struct arm_smccc_res result;
-	unsigned long offset = (unsigned long)context;
-
-	arm_smccc_smc(INTEL_SIP_SMC_REG_READ, offset + reg, 0, 0, 0,
-		      0, 0, 0, &result);
-
-	*val = (unsigned int)result.a1;
-
-	return (int)result.a0;
-}
-
-static const struct regmap_config s10_sdram_regmap_cfg = {
-	.name = "s10_ddr",
-	.reg_bits = 32,
-	.reg_stride = 4,
-	.val_bits = 32,
-	.max_register = 0xffd12228,
-	.reg_read = s10_protected_reg_read,
-	.reg_write = s10_protected_reg_write,
-	.use_single_read = true,
-	.use_single_write = true,
-};
-
-/************** </Stratix10 EDAC Memory Controller Functions> ***********/
-
 /************************* EDAC Parent Probe *************************/
 
 static const struct of_device_id altr_edac_device_of_match[];
@@ -1008,16 +946,6 @@ static int __maybe_unused altr_init_memory_port(void __iomem *ioaddr, int port)
 	return ret;
 }
 
-static int socfpga_is_a10(void)
-{
-	return of_machine_is_compatible("altr,socfpga-arria10");
-}
-
-static int socfpga_is_s10(void)
-{
-	return of_machine_is_compatible("altr,socfpga-stratix10");
-}
-
 static __init int __maybe_unused
 altr_init_a10_ecc_block(struct device_node *np, u32 irq_mask,
 			u32 ecc_ctrl_en_mask, bool dual_port)
@@ -1033,34 +961,10 @@ altr_init_a10_ecc_block(struct device_node *np, u32 irq_mask,
 	/* Get the ECC Manager - parent of the device EDACs */
 	np_eccmgr = of_get_parent(np);
 
-	if (socfpga_is_a10()) {
-		ecc_mgr_map = syscon_regmap_lookup_by_phandle(np_eccmgr,
-							      "altr,sysmgr-syscon");
-	} else {
-		struct device_node *sysmgr_np;
-		struct resource res;
-		uintptr_t base;
-
-		sysmgr_np = of_parse_phandle(np_eccmgr,
-					     "altr,sysmgr-syscon", 0);
-		if (!sysmgr_np) {
-			edac_printk(KERN_ERR, EDAC_DEVICE,
-				    "Unable to find altr,sysmgr-syscon\n");
-			return -ENODEV;
-		}
-
-		if (of_address_to_resource(sysmgr_np, 0, &res)) {
-			of_node_put(sysmgr_np);
-			return -ENOMEM;
-		}
+	ecc_mgr_map =
+		altr_sysmgr_regmap_lookup_by_phandle(np_eccmgr,
+						     "altr,sysmgr-syscon");
 
-		/* Need physical address for SMCC call */
-		base = res.start;
-
-		ecc_mgr_map = regmap_init(NULL, NULL, (void *)base,
-					  &s10_sdram_regmap_cfg);
-		of_node_put(sysmgr_np);
-	}
 	of_node_put(np_eccmgr);
 	if (IS_ERR(ecc_mgr_map)) {
 		edac_printk(KERN_ERR, EDAC_DEVICE,
@@ -1125,9 +1029,6 @@ static int __init __maybe_unused altr_init_a10_ecc_device_type(char *compat)
 	int irq;
 	struct device_node *child, *np;
 
-	if (!socfpga_is_a10() && !socfpga_is_s10())
-		return -ENODEV;
-
 	np = of_find_compatible_node(NULL, NULL,
 				     "altr,socfpga-a10-ecc-manager");
 	if (!np) {
@@ -2178,33 +2079,9 @@ static int altr_edac_a10_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, edac);
 	INIT_LIST_HEAD(&edac->a10_ecc_devices);
 
-	if (socfpga_is_a10()) {
-		edac->ecc_mgr_map =
-			syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
-							"altr,sysmgr-syscon");
-	} else {
-		struct device_node *sysmgr_np;
-		struct resource res;
-		uintptr_t base;
-
-		sysmgr_np = of_parse_phandle(pdev->dev.of_node,
-					     "altr,sysmgr-syscon", 0);
-		if (!sysmgr_np) {
-			edac_printk(KERN_ERR, EDAC_DEVICE,
-				    "Unable to find altr,sysmgr-syscon\n");
-			return -ENODEV;
-		}
-
-		if (of_address_to_resource(sysmgr_np, 0, &res))
-			return -ENOMEM;
-
-		/* Need physical address for SMCC call */
-		base = res.start;
-
-		edac->ecc_mgr_map = devm_regmap_init(&pdev->dev, NULL,
-						     (void *)base,
-						     &s10_sdram_regmap_cfg);
-	}
+	edac->ecc_mgr_map =
+		altr_sysmgr_regmap_lookup_by_phandle(pdev->dev.of_node,
+						     "altr,sysmgr-syscon");
 
 	if (IS_ERR(edac->ecc_mgr_map)) {
 		edac_printk(KERN_ERR, EDAC_DEVICE,
@@ -2270,18 +2147,7 @@ static int altr_edac_a10_probe(struct platform_device *pdev)
 		if (!of_device_is_available(child))
 			continue;
 
-		if (of_device_is_compatible(child, "altr,socfpga-a10-l2-ecc") || 
-		    of_device_is_compatible(child, "altr,socfpga-a10-ocram-ecc") ||
-		    of_device_is_compatible(child, "altr,socfpga-eth-mac-ecc") ||
-		    of_device_is_compatible(child, "altr,socfpga-nand-ecc") ||
-		    of_device_is_compatible(child, "altr,socfpga-dma-ecc") ||
-		    of_device_is_compatible(child, "altr,socfpga-usb-ecc") ||
-		    of_device_is_compatible(child, "altr,socfpga-qspi-ecc") ||
-#ifdef CONFIG_EDAC_ALTERA_SDRAM
-		    of_device_is_compatible(child, "altr,sdram-edac-s10") ||
-#endif
-		    of_device_is_compatible(child, "altr,socfpga-sdmmc-ecc"))
-
+		if (of_match_node(altr_edac_a10_device_of_match, child))
 			altr_edac_a10_device_add(edac, child);
 
 #ifdef CONFIG_EDAC_ALTERA_SDRAM