Merge tag 'edac_for_5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp

Pull EDAC updates from Borislav Petkov:

 - amd64_edac: Family 0x17, models 0x30-.. enablement (Yazen Ghannam)

 - skx_*: Librarize it so that it can be shared between drivers (Qiuxu Zhuo)

 - altera: Stratix10 improvements (Thor Thayer)

 - The usual round of fixes, fixlets and cleanups

* tag 'edac_for_5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp:
  Revert "EDAC/amd64: Support more than two controllers for chip select handling"
  arm64: dts: stratix10: Use new Stratix10 EDAC bindings
  Documentation: dt: edac: Add Stratix10 Peripheral bindings
  Documentation: dt: edac: Fix Stratix10 IRQ bindings
  EDAC/altera, firmware/intel: Add Stratix10 ECC DBE SMC call
  EDAC/altera: Initialize peripheral FIFOs in probe()
  EDAC/altera: Do less intrusive error injection
  EDAC/amd64: Adjust printed chip select sizes when interleaved
  EDAC/amd64: Support more than two controllers for chip select handling
  EDAC/amd64: Recognize x16 symbol size
  EDAC/amd64: Set maximum channel layer size depending on family
  EDAC/amd64: Support more than two Unified Memory Controllers
  EDAC/amd64: Use a macro for iterating over Unified Memory Controllers
  EDAC/amd64: Add Family 17h Model 30h PCI IDs
  MAINTAINERS: Add entry for EDAC-I10NM
  MAINTAINERS: Update entry for EDAC-SKYLAKE
  EDAC, altera: Fix S10 Double Bit Error Notification
  EDAC, skx, i10nm: Make skx_common.c a pure library

Documentation/devicetree/bindings/edac/socfpga-eccmgr.txt

@@ -232,37 +232,152 @@ Example:
 		};
 	};
 
-Stratix10 SoCFPGA ECC Manager
+Stratix10 SoCFPGA ECC Manager (ARM64)
 The Stratix10 SoC ECC Manager handles the IRQs for each peripheral
-in a shared register similar to the Arria10. However, ECC requires
-access to registers that can only be read from Secure Monitor with
-SMC calls. Therefore the device tree is slightly different.
+in a shared register similar to the Arria10. However, Stratix10 ECC
+requires access to registers that can only be read from Secure Monitor
+with SMC calls. Therefore the device tree is slightly different. Note
+that only 1 interrupt is sent in Stratix10 because the double bit errors
+are treated as SErrors in ARM64 instead of IRQs in ARM32.
 
 Required Properties:
 - compatible : Should be "altr,socfpga-s10-ecc-manager"
-- interrupts : Should be single bit error interrupt, then double bit error
-	interrupt.
+- altr,sysgr-syscon : phandle to Stratix10 System Manager Block
+	              containing the ECC manager registers.
+- interrupts : Should be single bit error interrupt.
 - interrupt-controller : boolean indicator that ECC Manager is an interrupt controller
 - #interrupt-cells : must be set to 2.
+- #address-cells: must be 1
+- #size-cells: must be 1
+- ranges : standard definition, should translate from local addresses
 
 Subcomponents:
 
 SDRAM ECC
 Required Properties:
 - compatible : Should be "altr,sdram-edac-s10"
-- interrupts : Should be single bit error interrupt, then double bit error
-	interrupt, in this order.
+- interrupts : Should be single bit error interrupt.
+
+On-Chip RAM ECC
+Required Properties:
+- compatible      : Should be "altr,socfpga-s10-ocram-ecc"
+- reg             : Address and size for ECC block registers.
+- altr,ecc-parent : phandle to parent OCRAM node.
+- interrupts      : Should be single bit error interrupt.
+
+Ethernet FIFO ECC
+Required Properties:
+- compatible      : Should be "altr,socfpga-s10-eth-mac-ecc"
+- reg             : Address and size for ECC block registers.
+- altr,ecc-parent : phandle to parent Ethernet node.
+- interrupts      : Should be single bit error interrupt.
+
+NAND FIFO ECC
+Required Properties:
+- compatible      : Should be "altr,socfpga-s10-nand-ecc"
+- reg             : Address and size for ECC block registers.
+- altr,ecc-parent : phandle to parent NAND node.
+- interrupts      : Should be single bit error interrupt.
+
+DMA FIFO ECC
+Required Properties:
+- compatible      : Should be "altr,socfpga-s10-dma-ecc"
+- reg             : Address and size for ECC block registers.
+- altr,ecc-parent : phandle to parent DMA node.
+- interrupts      : Should be single bit error interrupt.
+
+USB FIFO ECC
+Required Properties:
+- compatible      : Should be "altr,socfpga-s10-usb-ecc"
+- reg             : Address and size for ECC block registers.
+- altr,ecc-parent : phandle to parent USB node.
+- interrupts      : Should be single bit error interrupt.
+
+SDMMC FIFO ECC
+Required Properties:
+- compatible      : Should be "altr,socfpga-s10-sdmmc-ecc"
+- reg             : Address and size for ECC block registers.
+- altr,ecc-parent : phandle to parent SD/MMC node.
+- interrupts      : Should be single bit error interrupt for port A
+		    and then single bit error interrupt for port B.
 
 Example:
 
 	eccmgr {
 		compatible = "altr,socfpga-s10-ecc-manager";
-		interrupts = <0 15 4>, <0 95 4>;
+		altr,sysmgr-syscon = <&sysmgr>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		interrupts = <0 15 4>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
+		ranges;
 
 		sdramedac {
 			compatible = "altr,sdram-edac-s10";
-			interrupts = <16 4>, <48 4>;
+			interrupts = <16 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		ocram-ecc@ff8cc000 {
+			compatible = "altr,socfpga-s10-ocram-ecc";
+			reg = <ff8cc000 0x100>;
+			altr,ecc-parent = <&ocram>;
+			interrupts = <1 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		emac0-rx-ecc@ff8c0000 {
+			compatible = "altr,socfpga-s10-eth-mac-ecc";
+			reg = <0xff8c0000 0x100>;
+			altr,ecc-parent = <&gmac0>;
+			interrupts = <4 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		emac0-tx-ecc@ff8c0400 {
+			compatible = "altr,socfpga-s10-eth-mac-ecc";
+			reg = <0xff8c0400 0x100>;
+			altr,ecc-parent = <&gmac0>;
+			interrupts = <5 IRQ_TYPE_LEVEL_HIGH>'
+		};
+
+		nand-buf-ecc@ff8c8000 {
+			compatible = "altr,socfpga-s10-nand-ecc";
+			reg = <0xff8c8000 0x100>;
+			altr,ecc-parent = <&nand>;
+			interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		nand-rd-ecc@ff8c8400 {
+			compatible = "altr,socfpga-s10-nand-ecc";
+			reg = <0xff8c8400 0x100>;
+			altr,ecc-parent = <&nand>;
+			interrupts = <13 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		nand-wr-ecc@ff8c8800 {
+			compatible = "altr,socfpga-s10-nand-ecc";
+			reg = <0xff8c8800 0x100>;
+			altr,ecc-parent = <&nand>;
+			interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		dma-ecc@ff8c9000 {
+			compatible = "altr,socfpga-s10-dma-ecc";
+			reg = <0xff8c9000 0x100>;
+			altr,ecc-parent = <&pdma>;
+			interrupts = <10 IRQ_TYPE_LEVEL_HIGH>;
+
+		usb0-ecc@ff8c4000 {
+			compatible = "altr,socfpga-s10-usb-ecc";
+			reg = <0xff8c4000 0x100>;
+			altr,ecc-parent = <&usb0>;
+			interrupts = <2 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		sdmmc-ecc@ff8c8c00 {
+			compatible = "altr,socfpga-s10-sdmmc-ecc";
+			reg = <0xff8c8c00 0x100>;
+			altr,ecc-parent = <&mmc>;
+			interrupts = <14 IRQ_TYPE_LEVEL_HIGH>,
+				     <15 IRQ_TYPE_LEVEL_HIGH>;
 		};
 	};

MAINTAINERS

@@ -5599,6 +5599,12 @@ L:	linux-edac@vger.kernel.org
 S:	Maintained
 F:	drivers/edac/ghes_edac.c
 
+EDAC-I10NM
+M:	Tony Luck <tony.luck@intel.com>
+L:	linux-edac@vger.kernel.org
+S:	Maintained
+F:	drivers/edac/i10nm_base.c
+
 EDAC-I3000
 L:	linux-edac@vger.kernel.org
 S:	Orphan
@@ -5680,7 +5686,7 @@ EDAC-SKYLAKE
 M:	Tony Luck <tony.luck@intel.com>
 L:	linux-edac@vger.kernel.org
 S:	Maintained
-F:	drivers/edac/skx_edac.c
+F:	drivers/edac/skx_*.c
 
 EDAC-TI
 M:	Tero Kristo <t-kristo@ti.com>

arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi

@@ -534,11 +534,12 @@ sdr: sdr@f8011100 {
 		};
 
 		eccmgr {
-			compatible = "altr,socfpga-a10-ecc-manager";
+			compatible = "altr,socfpga-s10-ecc-manager",
+				     "altr,socfpga-a10-ecc-manager";
 			altr,sysmgr-syscon = <&sysmgr>;
 			#address-cells = <1>;
 			#size-cells = <1>;
-			interrupts = <0 15 4>, <0 95 4>;
+			interrupts = <0 15 4>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
 			ranges;
@@ -546,31 +547,31 @@ eccmgr {
 			sdramedac {
 				compatible = "altr,sdram-edac-s10";
 				altr,sdr-syscon = <&sdr>;
-				interrupts = <16 4>, <48 4>;
+				interrupts = <16 4>;
 			};
 
 			usb0-ecc@ff8c4000 {
-				compatible = "altr,socfpga-usb-ecc";
+				compatible = "altr,socfpga-s10-usb-ecc",
+					     "altr,socfpga-usb-ecc";
 				reg = <0xff8c4000 0x100>;
 				altr,ecc-parent = <&usb0>;
-				interrupts = <2 4>,
-					     <34 4>;
+				interrupts = <2 4>;
 			};
 
 			emac0-rx-ecc@ff8c0000 {
-				compatible = "altr,socfpga-eth-mac-ecc";
+				compatible = "altr,socfpga-s10-eth-mac-ecc",
+					     "altr,socfpga-eth-mac-ecc";
 				reg = <0xff8c0000 0x100>;
 				altr,ecc-parent = <&gmac0>;
-				interrupts = <4 4>,
-					     <36 4>;
+				interrupts = <4 4>;
 			};
 
 			emac0-tx-ecc@ff8c0400 {
-				compatible = "altr,socfpga-eth-mac-ecc";
+				compatible = "altr,socfpga-s10-eth-mac-ecc",
+					     "altr,socfpga-eth-mac-ecc";
 				reg = <0xff8c0400 0x100>;
 				altr,ecc-parent = <&gmac0>;
-				interrupts = <5 4>,
-					     <37 4>;
+				interrupts = <5 4>;
 			};
 
 		};

drivers/edac/altera_edac.h

@@ -289,6 +289,7 @@ struct altr_sdram_mc_data {
 #define ALTR_A10_ECC_INIT_WATCHDOG_10US      10000
 
 /************* Stratix10 Defines **************/
+#define ALTR_S10_DERR_ADDRA_OFST          0x2C
 
 /* Stratix10 ECC Manager Defines */
 #define S10_SYSMGR_ECC_INTMASK_CLR_OFST   0x98
@@ -299,6 +300,7 @@ struct altr_sdram_mc_data {
 #define S10_SYSMGR_UE_ADDR_OFST           0x224
 
 #define S10_DDR0_IRQ_MASK                 BIT(16)
+#define S10_DBE_IRQ_MASK                  0x3FE
 
 /* Define ECC Block Offsets for peripherals */
 #define ECC_BLK_ADDRESS_OFST              0x40
@@ -319,7 +321,7 @@ struct altr_sdram_mc_data {
 #define ECC_BLK_STARTACC_OFST             0x7C
 
 #define ECC_XACT_KICK                     0x10000
-#define ECC_WORD_WRITE                    0xF
+#define ECC_WORD_WRITE                    0xFF
 #define ECC_WRITE_DOVR                    0x101
 #define ECC_WRITE_EDOVR                   0x103
 #define ECC_READ_EOVR                     0x2
@@ -370,69 +372,4 @@ struct altr_arria10_edac {
 	struct notifier_block	panic_notifier;
 };
 
-/*
- * Functions specified by ARM SMC Calling convention:
- *
- * FAST call executes atomic operations, returns when the requested operation
- * has completed.
- * STD call starts a operation which can be preempted by a non-secure
- * interrupt. The call can return before the requested operation has
- * completed.
- *
- * a0..a7 is used as register names in the descriptions below, on arm32
- * that translates to r0..r7 and on arm64 to w0..w7.
- */
-
-#define INTEL_SIP_SMC_STD_CALL_VAL(func_num) \
-	ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL, ARM_SMCCC_SMC_64, \
-	ARM_SMCCC_OWNER_SIP, (func_num))
-
-#define INTEL_SIP_SMC_FAST_CALL_VAL(func_num) \
-	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_64, \
-	ARM_SMCCC_OWNER_SIP, (func_num))
-
-#define INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION		0xFFFFFFFF
-#define INTEL_SIP_SMC_STATUS_OK				0x0
-#define INTEL_SIP_SMC_REG_ERROR				0x5
-
-/*
- * Request INTEL_SIP_SMC_REG_READ
- *
- * Read a protected register using SMCCC
- *
- * Call register usage:
- * a0: INTEL_SIP_SMC_REG_READ.
- * a1: register address.
- * a2-7: not used.
- *
- * Return status:
- * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_REG_ERROR, or
- *     INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION
- * a1: Value in the register
- * a2-3: not used.
- */
-#define INTEL_SIP_SMC_FUNCID_REG_READ 7
-#define INTEL_SIP_SMC_REG_READ \
-	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_READ)
-
-/*
- * Request INTEL_SIP_SMC_REG_WRITE
- *
- * Write a protected register using SMCCC
- *
- * Call register usage:
- * a0: INTEL_SIP_SMC_REG_WRITE.
- * a1: register address
- * a2: value to program into register.
- * a3-7: not used.
- *
- * Return status:
- * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_REG_ERROR, or
- *     INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION
- * a1-3: not used.
- */
-#define INTEL_SIP_SMC_FUNCID_REG_WRITE 8
-#define INTEL_SIP_SMC_REG_WRITE \
-	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_WRITE)
-
 #endif	/* #ifndef _ALTERA_EDAC_H */

drivers/edac/amd64_edac.c

@@ -18,6 +18,9 @@ static struct msr __percpu *msrs;
 /* Per-node stuff */
 static struct ecc_settings **ecc_stngs;
 
+/* Number of Unified Memory Controllers */
+static u8 num_umcs;
+
 /*
  * Valid scrub rates for the K8 hardware memory scrubber. We map the scrubbing
  * bandwidth to a valid bit pattern. The 'set' operation finds the 'matching-
@@ -449,6 +452,9 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct,
 #define for_each_chip_select_mask(i, dct, pvt) \
 	for (i = 0; i < pvt->csels[dct].m_cnt; i++)
 
+#define for_each_umc(i) \
+	for (i = 0; i < num_umcs; i++)
+
 /*
  * @input_addr is an InputAddr associated with the node given by mci. Return the
  * csrow that input_addr maps to, or -1 on failure (no csrow claims input_addr).
@@ -722,7 +728,7 @@ static unsigned long determine_edac_cap(struct amd64_pvt *pvt)
 	if (pvt->umc) {
 		u8 i, umc_en_mask = 0, dimm_ecc_en_mask = 0;
 
-		for (i = 0; i < NUM_UMCS; i++) {
+		for_each_umc(i) {
 			if (!(pvt->umc[i].sdp_ctrl & UMC_SDP_INIT))
 				continue;
 
@@ -781,6 +787,22 @@ static void debug_dump_dramcfg_low(struct amd64_pvt *pvt, u32 dclr, int chan)
 		 (dclr & BIT(15)) ?  "yes" : "no");
 }
 
+/*
+ * The Address Mask should be a contiguous set of bits in the non-interleaved
+ * case. So to check for CS interleaving, find the most- and least-significant
+ * bits of the mask, generate a contiguous bitmask, and compare the two.
+ */
+static bool f17_cs_interleaved(struct amd64_pvt *pvt, u8 ctrl, int cs)
+{
+	u32 mask = pvt->csels[ctrl].csmasks[cs >> 1];
+	u32 msb = fls(mask) - 1, lsb = ffs(mask) - 1;
+	u32 test_mask = GENMASK(msb, lsb);
+
+	edac_dbg(1, "mask=0x%08x test_mask=0x%08x\n", mask, test_mask);
+
+	return mask ^ test_mask;
+}
+
 static void debug_display_dimm_sizes_df(struct amd64_pvt *pvt, u8 ctrl)
 {
 	int dimm, size0, size1, cs0, cs1;
@@ -797,8 +819,19 @@ static void debug_display_dimm_sizes_df(struct amd64_pvt *pvt, u8 ctrl)
 		size1 = 0;
 		cs1 = dimm * 2 + 1;
 
-		if (csrow_enabled(cs1, ctrl, pvt))
+		if (csrow_enabled(cs1, ctrl, pvt)) {
+			/*
+			 * CS interleaving is only supported if both CSes have
+			 * the same amount of memory. Because they are
+			 * interleaved, it will look like both CSes have the
+			 * full amount of memory. Save the size for both as
+			 * half the amount we found on CS0, if interleaved.
+			 */
+			if (f17_cs_interleaved(pvt, ctrl, cs1))
+				size1 = size0 = (size0 >> 1);
+			else
 				size1 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, cs1);
+		}
 
 		amd64_info(EDAC_MC ": %d: %5dMB %d: %5dMB\n",
 				cs0,	size0,
@@ -811,7 +844,7 @@ static void __dump_misc_regs_df(struct amd64_pvt *pvt)
 	struct amd64_umc *umc;
 	u32 i, tmp, umc_base;
 
-	for (i = 0; i < NUM_UMCS; i++) {
+	for_each_umc(i) {
 		umc_base = get_umc_base(i);
 		umc = &pvt->umc[i];
 
@@ -894,8 +927,7 @@ static void dump_misc_regs(struct amd64_pvt *pvt)
 
 	edac_dbg(1, "  DramHoleValid: %s\n", dhar_valid(pvt) ? "yes" : "no");
 
-	amd64_info("using %s syndromes.\n",
-			((pvt->ecc_sym_sz == 8) ? "x8" : "x4"));
+	amd64_info("using x%u syndromes.\n", pvt->ecc_sym_sz);
 }
 
 /*
@@ -1388,7 +1420,7 @@ static int f17_early_channel_count(struct amd64_pvt *pvt)
 	int i, channels = 0;
 
 	/* SDP Control bit 31 (SdpInit) is clear for unused UMC channels */
-	for (i = 0; i < NUM_UMCS; i++)
+	for_each_umc(i)
 		channels += !!(pvt->umc[i].sdp_ctrl & UMC_SDP_INIT);
 
 	amd64_info("MCT channel count: %d\n", channels);
@@ -2211,6 +2243,15 @@ static struct amd64_family_type family_types[] = {
 			.dbam_to_cs		= f17_base_addr_to_cs_size,
 		}
 	},
+	[F17_M30H_CPUS] = {
+		.ctl_name = "F17h_M30h",
+		.f0_id = PCI_DEVICE_ID_AMD_17H_M30H_DF_F0,
+		.f6_id = PCI_DEVICE_ID_AMD_17H_M30H_DF_F6,
+		.ops = {
+			.early_channel_count	= f17_early_channel_count,
+			.dbam_to_cs		= f17_base_addr_to_cs_size,
+		}
+	},
 };
 
 /*
@@ -2464,18 +2505,14 @@ static inline void decode_bus_error(int node_id, struct mce *m)
  * To find the UMC channel represented by this bank we need to match on its
  * instance_id. The instance_id of a bank is held in the lower 32 bits of its
  * IPID.
+ *
+ * Currently, we can derive the channel number by looking at the 6th nibble in
+ * the instance_id. For example, instance_id=0xYXXXXX where Y is the channel
+ * number.
  */
-static int find_umc_channel(struct amd64_pvt *pvt, struct mce *m)
+static int find_umc_channel(struct mce *m)
 {
-	u32 umc_instance_id[] = {0x50f00, 0x150f00};
-	u32 instance_id = m->ipid & GENMASK(31, 0);
-	int i, channel = -1;
-
-	for (i = 0; i < ARRAY_SIZE(umc_instance_id); i++)
-		if (umc_instance_id[i] == instance_id)
-			channel = i;
-
-	return channel;
+	return (m->ipid & GENMASK(31, 0)) >> 20;
 }
 
 static void decode_umc_error(int node_id, struct mce *m)
@@ -2497,11 +2534,7 @@ static void decode_umc_error(int node_id, struct mce *m)
 	if (m->status & MCI_STATUS_DEFERRED)
 		ecc_type = 3;
 
-	err.channel = find_umc_channel(pvt, m);
-	if (err.channel < 0) {
-		err.err_code = ERR_CHANNEL;
-		goto log_error;
-	}
+	err.channel = find_umc_channel(m);
 
 	if (umc_normaddr_to_sysaddr(m->addr, pvt->mc_node_id, err.channel, &sys_addr)) {
 		err.err_code = ERR_NORM_ADDR;
@@ -2603,19 +2636,19 @@ static void determine_ecc_sym_sz(struct amd64_pvt *pvt)
 	if (pvt->umc) {
 		u8 i;
 
-		for (i = 0; i < NUM_UMCS; i++) {
+		for_each_umc(i) {
 			/* Check enabled channels only: */
-			if ((pvt->umc[i].sdp_ctrl & UMC_SDP_INIT) &&
-			    (pvt->umc[i].ecc_ctrl & BIT(7))) {
+			if (pvt->umc[i].sdp_ctrl & UMC_SDP_INIT) {
+				if (pvt->umc[i].ecc_ctrl & BIT(9)) {
+					pvt->ecc_sym_sz = 16;
+					return;
+				} else if (pvt->umc[i].ecc_ctrl & BIT(7)) {
 					pvt->ecc_sym_sz = 8;
-				break;
+					return;
 				}
 			}
-
-		return;
 		}
-
-	if (pvt->fam >= 0x10) {
+	} else if (pvt->fam >= 0x10) {
 		u32 tmp;
 
 		amd64_read_pci_cfg(pvt->F3, EXT_NB_MCA_CFG, &tmp);
@@ -2639,7 +2672,7 @@ static void __read_mc_regs_df(struct amd64_pvt *pvt)
 	u32 i, umc_base;
 
 	/* Read registers from each UMC */
-	for (i = 0; i < NUM_UMCS; i++) {
+	for_each_umc(i) {
 
 		umc_base = get_umc_base(i);
 		umc = &pvt->umc[i];
@@ -3052,7 +3085,7 @@ static bool ecc_enabled(struct pci_dev *F3, u16 nid)
 	if (boot_cpu_data.x86 >= 0x17) {
 		u8 umc_en_mask = 0, ecc_en_mask = 0;
 
-		for (i = 0; i < NUM_UMCS; i++) {
+		for_each_umc(i) {
 			u32 base = get_umc_base(i);
 
 			/* Only check enabled UMCs. */
@@ -3105,7 +3138,7 @@ f17h_determine_edac_ctl_cap(struct mem_ctl_info *mci, struct amd64_pvt *pvt)
 {
 	u8 i, ecc_en = 1, cpk_en = 1;
 
-	for (i = 0; i < NUM_UMCS; i++) {
+	for_each_umc(i) {
 		if (pvt->umc[i].sdp_ctrl & UMC_SDP_INIT) {
 			ecc_en &= !!(pvt->umc[i].umc_cap_hi & UMC_ECC_ENABLED);
 			cpk_en &= !!(pvt->umc[i].umc_cap_hi & UMC_ECC_CHIPKILL_CAP);
@@ -3203,6 +3236,10 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
 			fam_type = &family_types[F17_M10H_CPUS];
 			pvt->ops = &family_types[F17_M10H_CPUS].ops;
 			break;
+		} else if (pvt->model >= 0x30 && pvt->model <= 0x3f) {
+			fam_type = &family_types[F17_M30H_CPUS];
+			pvt->ops = &family_types[F17_M30H_CPUS].ops;
+			break;
 		}
 		/* fall through */
 	case 0x18:
@@ -3236,6 +3273,22 @@ static const struct attribute_group *amd64_edac_attr_groups[] = {
 	NULL
 };
 
+/* Set the number of Unified Memory Controllers in the system. */
+static void compute_num_umcs(void)
+{
+	u8 model = boot_cpu_data.x86_model;
+
+	if (boot_cpu_data.x86 < 0x17)
+		return;
+
+	if (model >= 0x30 && model <= 0x3f)
+		num_umcs = 8;
+	else
+		num_umcs = 2;
+
+	edac_dbg(1, "Number of UMCs: %x", num_umcs);
+}
+
 static int init_one_instance(unsigned int nid)
 {
 	struct pci_dev *F3 = node_to_amd_nb(nid)->misc;
@@ -3260,7 +3313,7 @@ static int init_one_instance(unsigned int nid)
 		goto err_free;
 
 	if (pvt->fam >= 0x17) {
-		pvt->umc = kcalloc(NUM_UMCS, sizeof(struct amd64_umc), GFP_KERNEL);
+		pvt->umc = kcalloc(num_umcs, sizeof(struct amd64_umc), GFP_KERNEL);
 		if (!pvt->umc) {
 			ret = -ENOMEM;
 			goto err_free;
@@ -3299,7 +3352,13 @@ static int init_one_instance(unsigned int nid)
 	 * Always allocate two channels since we can have setups with DIMMs on
 	 * only one channel. Also, this simplifies handling later for the price
 	 * of a couple of KBs tops.
+	 *
+	 * On Fam17h+, the number of controllers may be greater than two. So set
+	 * the size equal to the maximum number of UMCs.
 	 */
+	if (pvt->fam >= 0x17)
+		layers[1].size = num_umcs;
+	else
 		layers[1].size = 2;
 	layers[1].is_virt_csrow = false;
 
@@ -3481,6 +3540,8 @@ static int __init amd64_edac_init(void)
 	if (!msrs)
 		goto err_free;
 
+	compute_num_umcs();
+
 	for (i = 0; i < amd_nb_num(); i++) {
 		err = probe_one_instance(i);
 		if (err) {

drivers/edac/amd64_edac.h

@@ -117,6 +117,8 @@
 #define PCI_DEVICE_ID_AMD_17H_DF_F6	0x1466
 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F0 0x15e8
 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F6 0x15ee
+#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F0 0x1490
+#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F6 0x1496
 
 /*
  * Function 1 - Address Map
@@ -272,8 +274,6 @@
 
 #define UMC_SDP_INIT			BIT(31)
 
-#define NUM_UMCS			2
-
 enum amd_families {
 	K8_CPUS = 0,
 	F10_CPUS,
@@ -284,6 +284,7 @@ enum amd_families {
 	F16_M30H_CPUS,
 	F17_CPUS,
 	F17_M10H_CPUS,
+	F17_M30H_CPUS,
 	NUM_FAMILIES,
 };
 
@@ -363,7 +364,7 @@ struct amd64_pvt {
 	u32 dct_sel_hi;		/* DRAM Controller Select High */
 	u32 online_spare;	/* On-Line spare Reg */
 
-	/* x4 or x8 syndromes in use */
+	/* x4, x8, or x16 syndromes in use */
 	u8 ecc_sym_sz;
 
 	/* place to store error injection parameters prior to issue */
@@ -396,8 +397,8 @@ struct err_info {
 
 static inline u32 get_umc_base(u8 channel)
 {
-	/* ch0: 0x50000, ch1: 0x150000 */
-	return 0x50000 + (!!channel << 20);
+	/* chY: 0xY50000 */
+	return 0x50000 + (channel << 20);
 }
 
 static inline u64 get_dram_base(struct amd64_pvt *pvt, u8 i)

drivers/edac/i10nm_base.c

@@ -181,6 +181,54 @@ static struct notifier_block i10nm_mce_dec = {
 	.priority	= MCE_PRIO_EDAC,
 };
 
+#ifdef CONFIG_EDAC_DEBUG
+/*
+ * Debug feature.
+ * Exercise the address decode logic by writing an address to
+ * /sys/kernel/debug/edac/i10nm_test/addr.
+ */
+static struct dentry *i10nm_test;
+
+static int debugfs_u64_set(void *data, u64 val)
+{
+	struct mce m;
+
+	pr_warn_once("Fake error to 0x%llx injected via debugfs\n", val);
+
+	memset(&m, 0, sizeof(m));
+	/* ADDRV + MemRd + Unknown channel */
+	m.status = MCI_STATUS_ADDRV + 0x90;
+	/* One corrected error */
+	m.status |= BIT_ULL(MCI_STATUS_CEC_SHIFT);
+	m.addr = val;
+	skx_mce_check_error(NULL, 0, &m);
+
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
+
+static void setup_i10nm_debug(void)
+{
+	i10nm_test = edac_debugfs_create_dir("i10nm_test");
+	if (!i10nm_test)
+		return;
+
+	if (!edac_debugfs_create_file("addr", 0200, i10nm_test,
+				      NULL, &fops_u64_wo)) {
+		debugfs_remove(i10nm_test);
+		i10nm_test = NULL;
+	}
+}
+
+static void teardown_i10nm_debug(void)
+{
+	debugfs_remove_recursive(i10nm_test);
+}
+#else
+static inline void setup_i10nm_debug(void) {}
+static inline void teardown_i10nm_debug(void) {}
+#endif /*CONFIG_EDAC_DEBUG*/
+
 static int __init i10nm_init(void)
 {
 	u8 mc = 0, src_id = 0, node_id = 0;
@@ -249,7 +297,7 @@ static int __init i10nm_init(void)
 
 	opstate_init();
 	mce_register_decode_chain(&i10nm_mce_dec);
-	setup_skx_debug("i10nm_test");
+	setup_i10nm_debug();
 
 	i10nm_printk(KERN_INFO, "%s\n", I10NM_REVISION);
 
@@ -262,7 +310,7 @@ static int __init i10nm_init(void)
 static void __exit i10nm_exit(void)
 {
 	edac_dbg(2, "\n");
-	teardown_skx_debug();
+	teardown_i10nm_debug();
 	mce_unregister_decode_chain(&i10nm_mce_dec);
 	skx_adxl_put();
 	skx_remove();

drivers/edac/skx_base.c

@@ -540,6 +540,54 @@ static struct notifier_block skx_mce_dec = {
 	.priority	= MCE_PRIO_EDAC,
 };
 
+#ifdef CONFIG_EDAC_DEBUG
+/*
+ * Debug feature.
+ * Exercise the address decode logic by writing an address to
+ * /sys/kernel/debug/edac/skx_test/addr.
+ */
+static struct dentry *skx_test;
+
+static int debugfs_u64_set(void *data, u64 val)
+{
+	struct mce m;
+
+	pr_warn_once("Fake error to 0x%llx injected via debugfs\n", val);
+
+	memset(&m, 0, sizeof(m));
+	/* ADDRV + MemRd + Unknown channel */
+	m.status = MCI_STATUS_ADDRV + 0x90;
+	/* One corrected error */
+	m.status |= BIT_ULL(MCI_STATUS_CEC_SHIFT);
+	m.addr = val;
+	skx_mce_check_error(NULL, 0, &m);
+
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
+
+static void setup_skx_debug(void)
+{
+	skx_test = edac_debugfs_create_dir("skx_test");
+	if (!skx_test)
+		return;
+
+	if (!edac_debugfs_create_file("addr", 0200, skx_test,
+				      NULL, &fops_u64_wo)) {
+		debugfs_remove(skx_test);
+		skx_test = NULL;
+	}
+}
+
+static void teardown_skx_debug(void)
+{
+	debugfs_remove_recursive(skx_test);
+}
+#else
+static inline void setup_skx_debug(void) {}
+static inline void teardown_skx_debug(void) {}
+#endif /*CONFIG_EDAC_DEBUG*/
+
 /*
  * skx_init:
  *	make sure we are running on the correct cpu model
@@ -619,7 +667,7 @@ static int __init skx_init(void)
 	/* Ensure that the OPSTATE is set correctly for POLL or NMI */
 	opstate_init();
 
-	setup_skx_debug("skx_test");
+	setup_skx_debug();
 
 	mce_register_decode_chain(&skx_mce_dec);
 

drivers/edac/skx_common.c

 // SPDX-License-Identifier: GPL-2.0
 /*
- * Common codes for both the skx_edac driver and Intel 10nm server EDAC driver.
- * Originally split out from the skx_edac driver.
+ *
+ * Shared code by both skx_edac and i10nm_edac. Originally split out
+ * from the skx_edac driver.
+ *
+ * This file is linked into both skx_edac and i10nm_edac drivers. In
+ * order to avoid link errors, this file must be like a pure library
+ * without including symbols and defines which would otherwise conflict,
+ * when linked once into a module and into a built-in object, at the
+ * same time. For example, __this_module symbol references when that
+ * file is being linked into a built-in object.
  *
  * Copyright (c) 2018, Intel Corporation.
  */
@@ -644,48 +652,3 @@ void skx_remove(void)
 		kfree(d);
 	}
 }
-
-#ifdef CONFIG_EDAC_DEBUG
-/*
- * Debug feature.
- * Exercise the address decode logic by writing an address to
- * /sys/kernel/debug/edac/dirname/addr.
- */
-static struct dentry *skx_test;
-
-static int debugfs_u64_set(void *data, u64 val)
-{
-	struct mce m;
-
-	pr_warn_once("Fake error to 0x%llx injected via debugfs\n", val);
-
-	memset(&m, 0, sizeof(m));
-	/* ADDRV + MemRd + Unknown channel */
-	m.status = MCI_STATUS_ADDRV + 0x90;
-	/* One corrected error */
-	m.status |= BIT_ULL(MCI_STATUS_CEC_SHIFT);
-	m.addr = val;
-	skx_mce_check_error(NULL, 0, &m);
-
-	return 0;
-}
-DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
-
-void setup_skx_debug(const char *dirname)
-{
-	skx_test = edac_debugfs_create_dir(dirname);
-	if (!skx_test)
-		return;
-
-	if (!edac_debugfs_create_file("addr", 0200, skx_test,
-				      NULL, &fops_u64_wo)) {
-		debugfs_remove(skx_test);
-		skx_test = NULL;
-	}
-}
-
-void teardown_skx_debug(void)
-{
-	debugfs_remove_recursive(skx_test);
-}
-#endif /*CONFIG_EDAC_DEBUG*/

drivers/edac/skx_common.h

@@ -141,12 +141,4 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
 
 void skx_remove(void);
 
-#ifdef CONFIG_EDAC_DEBUG
-void setup_skx_debug(const char *dirname);
-void teardown_skx_debug(void);
-#else
-static inline void setup_skx_debug(const char *dirname) {}
-static inline void teardown_skx_debug(void) {}
-#endif /*CONFIG_EDAC_DEBUG*/
-
 #endif /* _SKX_COMM_EDAC_H */

include/linux/firmware/intel/stratix10-smc.h

@@ -309,4 +309,23 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE)
 #define INTEL_SIP_SMC_FUNCID_RSU_UPDATE 12
 #define INTEL_SIP_SMC_RSU_UPDATE \
 	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_UPDATE)
+
+/*
+ * Request INTEL_SIP_SMC_ECC_DBE
+ *
+ * Sync call used by service driver at EL1 to alert EL3 that a Double
+ * Bit ECC error has occurred.
+ *
+ * Call register usage:
+ * a0 INTEL_SIP_SMC_ECC_DBE
+ * a1 SysManager Double Bit Error value
+ * a2-7 not used
+ *
+ * Return status
+ * a0 INTEL_SIP_SMC_STATUS_OK
+ */
+#define INTEL_SIP_SMC_FUNCID_ECC_DBE 13
+#define INTEL_SIP_SMC_ECC_DBE \
+	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_ECC_DBE)
+
 #endif