1 files changed, 92 insertions, 366 deletions

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 537b9987a431..58b1482a0fbb 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#include <linux/ras.h>
+#include <linux/string_choices.h>
 #include "amd64_edac.h"
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
+#include <asm/amd/node.h>
 
 static struct edac_pci_ctl_info *pci_ctl;
 
@@ -19,7 +22,6 @@ static inline u32 get_umc_reg(struct amd64_pvt *pvt, u32 reg)
 		return reg;
 
 	switch (reg) {
-	case UMCCH_ADDR_CFG:		return UMCCH_ADDR_CFG_DDR5;
 	case UMCCH_ADDR_MASK_SEC:	return UMCCH_ADDR_MASK_SEC_DDR5;
 	case UMCCH_DIMM_CFG:		return UMCCH_DIMM_CFG_DDR5;
 	}
@@ -80,7 +82,7 @@ int __amd64_read_pci_cfg_dword(struct pci_dev *pdev, int offset,
 		amd64_warn("%s: error reading F%dx%03x.\n",
 			   func, PCI_FUNC(pdev->devfn), offset);
 
-	return err;
+	return pcibios_err_to_errno(err);
 }
 
 int __amd64_write_pci_cfg_dword(struct pci_dev *pdev, int offset,
@@ -93,7 +95,7 @@ int __amd64_write_pci_cfg_dword(struct pci_dev *pdev, int offset,
 		amd64_warn("%s: error writing to F%dx%03x.\n",
 			   func, PCI_FUNC(pdev->devfn), offset);
 
-	return err;
+	return pcibios_err_to_errno(err);
 }
 
 /*
@@ -1024,8 +1026,10 @@ static int gpu_get_node_map(struct amd64_pvt *pvt)
 	}
 
 	ret = pci_read_config_dword(pdev, REG_LOCAL_NODE_TYPE_MAP, &tmp);
-	if (ret)
+	if (ret) {
+		ret = pcibios_err_to_errno(ret);
 		goto out;
+	}
 
 	gpu_node_map.node_count = FIELD_GET(LNTM_NODE_COUNT, tmp);
 	gpu_node_map.base_node_id = FIELD_GET(LNTM_BASE_NODE_ID, tmp);
@@ -1051,281 +1055,6 @@ static int fixup_node_id(int node_id, struct mce *m)
 	return nid - gpu_node_map.base_node_id + 1;
 }
 
-/* Protect the PCI config register pairs used for DF indirect access. */
-static DEFINE_MUTEX(df_indirect_mutex);
-
-/*
- * Data Fabric Indirect Access uses FICAA/FICAD.
- *
- * Fabric Indirect Configuration Access Address (FICAA): Constructed based
- * on the device's Instance Id and the PCI function and register offset of
- * the desired register.
- *
- * Fabric Indirect Configuration Access Data (FICAD): There are FICAD LO
- * and FICAD HI registers but so far we only need the LO register.
- *
- * Use Instance Id 0xFF to indicate a broadcast read.
- */
-#define DF_BROADCAST	0xFF
-static int __df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo)
-{
-	struct pci_dev *F4;
-	u32 ficaa;
-	int err = -ENODEV;
-
-	if (node >= amd_nb_num())
-		goto out;
-
-	F4 = node_to_amd_nb(node)->link;
-	if (!F4)
-		goto out;
-
-	ficaa  = (instance_id == DF_BROADCAST) ? 0 : 1;
-	ficaa |= reg & 0x3FC;
-	ficaa |= (func & 0x7) << 11;
-	ficaa |= instance_id << 16;
-
-	mutex_lock(&df_indirect_mutex);
-
-	err = pci_write_config_dword(F4, 0x5C, ficaa);
-	if (err) {
-		pr_warn("Error writing DF Indirect FICAA, FICAA=0x%x\n", ficaa);
-		goto out_unlock;
-	}
-
-	err = pci_read_config_dword(F4, 0x98, lo);
-	if (err)
-		pr_warn("Error reading DF Indirect FICAD LO, FICAA=0x%x.\n", ficaa);
-
-out_unlock:
-	mutex_unlock(&df_indirect_mutex);
-
-out:
-	return err;
-}
-
-static int df_indirect_read_instance(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo)
-{
-	return __df_indirect_read(node, func, reg, instance_id, lo);
-}
-
-static int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo)
-{
-	return __df_indirect_read(node, func, reg, DF_BROADCAST, lo);
-}
-
-struct addr_ctx {
-	u64 ret_addr;
-	u32 tmp;
-	u16 nid;
-	u8 inst_id;
-};
-
-static int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr)
-{
-	u64 dram_base_addr, dram_limit_addr, dram_hole_base;
-
-	u8 die_id_shift, die_id_mask, socket_id_shift, socket_id_mask;
-	u8 intlv_num_dies, intlv_num_chan, intlv_num_sockets;
-	u8 intlv_addr_sel, intlv_addr_bit;
-	u8 num_intlv_bits, hashed_bit;
-	u8 lgcy_mmio_hole_en, base = 0;
-	u8 cs_mask, cs_id = 0;
-	bool hash_enabled = false;
-
-	struct addr_ctx ctx;
-
-	memset(&ctx, 0, sizeof(ctx));
-
-	/* Start from the normalized address */
-	ctx.ret_addr = norm_addr;
-
-	ctx.nid = nid;
-	ctx.inst_id = umc;
-
-	/* Read D18F0x1B4 (DramOffset), check if base 1 is used. */
-	if (df_indirect_read_instance(nid, 0, 0x1B4, umc, &ctx.tmp))
-		goto out_err;
-
-	/* Remove HiAddrOffset from normalized address, if enabled: */
-	if (ctx.tmp & BIT(0)) {
-		u64 hi_addr_offset = (ctx.tmp & GENMASK_ULL(31, 20)) << 8;
-
-		if (norm_addr >= hi_addr_offset) {
-			ctx.ret_addr -= hi_addr_offset;
-			base = 1;
-		}
-	}
-
-	/* Read D18F0x110 (DramBaseAddress). */
-	if (df_indirect_read_instance(nid, 0, 0x110 + (8 * base), umc, &ctx.tmp))
-		goto out_err;
-
-	/* Check if address range is valid. */
-	if (!(ctx.tmp & BIT(0))) {
-		pr_err("%s: Invalid DramBaseAddress range: 0x%x.\n",
-			__func__, ctx.tmp);
-		goto out_err;
-	}
-
-	lgcy_mmio_hole_en = ctx.tmp & BIT(1);
-	intlv_num_chan	  = (ctx.tmp >> 4) & 0xF;
-	intlv_addr_sel	  = (ctx.tmp >> 8) & 0x7;
-	dram_base_addr	  = (ctx.tmp & GENMASK_ULL(31, 12)) << 16;
-
-	/* {0, 1, 2, 3} map to address bits {8, 9, 10, 11} respectively */
-	if (intlv_addr_sel > 3) {
-		pr_err("%s: Invalid interleave address select %d.\n",
-			__func__, intlv_addr_sel);
-		goto out_err;
-	}
-
-	/* Read D18F0x114 (DramLimitAddress). */
-	if (df_indirect_read_instance(nid, 0, 0x114 + (8 * base), umc, &ctx.tmp))
-		goto out_err;
-
-	intlv_num_sockets = (ctx.tmp >> 8) & 0x1;
-	intlv_num_dies	  = (ctx.tmp >> 10) & 0x3;
-	dram_limit_addr	  = ((ctx.tmp & GENMASK_ULL(31, 12)) << 16) | GENMASK_ULL(27, 0);
-
-	intlv_addr_bit = intlv_addr_sel + 8;
-
-	/* Re-use intlv_num_chan by setting it equal to log2(#channels) */
-	switch (intlv_num_chan) {
-	case 0:	intlv_num_chan = 0; break;
-	case 1: intlv_num_chan = 1; break;
-	case 3: intlv_num_chan = 2; break;
-	case 5:	intlv_num_chan = 3; break;
-	case 7:	intlv_num_chan = 4; break;
-
-	case 8: intlv_num_chan = 1;
-		hash_enabled = true;
-		break;
-	default:
-		pr_err("%s: Invalid number of interleaved channels %d.\n",
-			__func__, intlv_num_chan);
-		goto out_err;
-	}
-
-	num_intlv_bits = intlv_num_chan;
-
-	if (intlv_num_dies > 2) {
-		pr_err("%s: Invalid number of interleaved nodes/dies %d.\n",
-			__func__, intlv_num_dies);
-		goto out_err;
-	}
-
-	num_intlv_bits += intlv_num_dies;
-
-	/* Add a bit if sockets are interleaved. */
-	num_intlv_bits += intlv_num_sockets;
-
-	/* Assert num_intlv_bits <= 4 */
-	if (num_intlv_bits > 4) {
-		pr_err("%s: Invalid interleave bits %d.\n",
-			__func__, num_intlv_bits);
-		goto out_err;
-	}
-
-	if (num_intlv_bits > 0) {
-		u64 temp_addr_x, temp_addr_i, temp_addr_y;
-		u8 die_id_bit, sock_id_bit, cs_fabric_id;
-
-		/*
-		 * Read FabricBlockInstanceInformation3_CS[BlockFabricID].
-		 * This is the fabric id for this coherent slave. Use
-		 * umc/channel# as instance id of the coherent slave
-		 * for FICAA.
-		 */
-		if (df_indirect_read_instance(nid, 0, 0x50, umc, &ctx.tmp))
-			goto out_err;
-
-		cs_fabric_id = (ctx.tmp >> 8) & 0xFF;
-		die_id_bit   = 0;
-
-		/* If interleaved over more than 1 channel: */
-		if (intlv_num_chan) {
-			die_id_bit = intlv_num_chan;
-			cs_mask	   = (1 << die_id_bit) - 1;
-			cs_id	   = cs_fabric_id & cs_mask;
-		}
-
-		sock_id_bit = die_id_bit;
-
-		/* Read D18F1x208 (SystemFabricIdMask). */
-		if (intlv_num_dies || intlv_num_sockets)
-			if (df_indirect_read_broadcast(nid, 1, 0x208, &ctx.tmp))
-				goto out_err;
-
-		/* If interleaved over more than 1 die. */
-		if (intlv_num_dies) {
-			sock_id_bit  = die_id_bit + intlv_num_dies;
-			die_id_shift = (ctx.tmp >> 24) & 0xF;
-			die_id_mask  = (ctx.tmp >> 8) & 0xFF;
-
-			cs_id |= ((cs_fabric_id & die_id_mask) >> die_id_shift) << die_id_bit;
-		}
-
-		/* If interleaved over more than 1 socket. */
-		if (intlv_num_sockets) {
-			socket_id_shift	= (ctx.tmp >> 28) & 0xF;
-			socket_id_mask	= (ctx.tmp >> 16) & 0xFF;
-
-			cs_id |= ((cs_fabric_id & socket_id_mask) >> socket_id_shift) << sock_id_bit;
-		}
-
-		/*
-		 * The pre-interleaved address consists of XXXXXXIIIYYYYY
-		 * where III is the ID for this CS, and XXXXXXYYYYY are the
-		 * address bits from the post-interleaved address.
-		 * "num_intlv_bits" has been calculated to tell us how many "I"
-		 * bits there are. "intlv_addr_bit" tells us how many "Y" bits
-		 * there are (where "I" starts).
-		 */
-		temp_addr_y = ctx.ret_addr & GENMASK_ULL(intlv_addr_bit - 1, 0);
-		temp_addr_i = (cs_id << intlv_addr_bit);
-		temp_addr_x = (ctx.ret_addr & GENMASK_ULL(63, intlv_addr_bit)) << num_intlv_bits;
-		ctx.ret_addr    = temp_addr_x | temp_addr_i | temp_addr_y;
-	}
-
-	/* Add dram base address */
-	ctx.ret_addr += dram_base_addr;
-
-	/* If legacy MMIO hole enabled */
-	if (lgcy_mmio_hole_en) {
-		if (df_indirect_read_broadcast(nid, 0, 0x104, &ctx.tmp))
-			goto out_err;
-
-		dram_hole_base = ctx.tmp & GENMASK(31, 24);
-		if (ctx.ret_addr >= dram_hole_base)
-			ctx.ret_addr += (BIT_ULL(32) - dram_hole_base);
-	}
-
-	if (hash_enabled) {
-		/* Save some parentheses and grab ls-bit at the end. */
-		hashed_bit =	(ctx.ret_addr >> 12) ^
-				(ctx.ret_addr >> 18) ^
-				(ctx.ret_addr >> 21) ^
-				(ctx.ret_addr >> 30) ^
-				cs_id;
-
-		hashed_bit &= BIT(0);
-
-		if (hashed_bit != ((ctx.ret_addr >> intlv_addr_bit) & BIT(0)))
-			ctx.ret_addr ^= BIT(intlv_addr_bit);
-	}
-
-	/* Is calculated system address is above DRAM limit address? */
-	if (ctx.ret_addr > dram_limit_addr)
-		goto out_err;
-
-	*sys_addr = ctx.ret_addr;
-	return 0;
-
-out_err:
-	return -EINVAL;
-}
-
 static int get_channel_from_ecc_syndrome(struct mem_ctl_info *, u16);
 
 /*
@@ -1443,22 +1172,21 @@ static void debug_dump_dramcfg_low(struct amd64_pvt *pvt, u32 dclr, int chan)
 		edac_dbg(1, " LRDIMM %dx rank multiply\n", (dcsm & 0x3));
 	}
 
-	edac_dbg(1, "All DIMMs support ECC:%s\n",
-		    (dclr & BIT(19)) ? "yes" : "no");
+	edac_dbg(1, "All DIMMs support ECC: %s\n", str_yes_no(dclr & BIT(19)));
 
 
 	edac_dbg(1, "  PAR/ERR parity: %s\n",
-		 (dclr & BIT(8)) ?  "enabled" : "disabled");
+		 str_enabled_disabled(dclr & BIT(8)));
 
 	if (pvt->fam == 0x10)
 		edac_dbg(1, "  DCT 128bit mode width: %s\n",
 			 (dclr & BIT(11)) ?  "128b" : "64b");
 
 	edac_dbg(1, "  x4 logical DIMMs present: L0: %s L1: %s L2: %s L3: %s\n",
-		 (dclr & BIT(12)) ?  "yes" : "no",
-		 (dclr & BIT(13)) ?  "yes" : "no",
-		 (dclr & BIT(14)) ?  "yes" : "no",
-		 (dclr & BIT(15)) ?  "yes" : "no");
+		 str_yes_no(dclr & BIT(12)),
+		 str_yes_no(dclr & BIT(13)),
+		 str_yes_no(dclr & BIT(14)),
+		 str_yes_no(dclr & BIT(15)));
 }
 
 #define CS_EVEN_PRIMARY		BIT(0)
@@ -1613,41 +1341,26 @@ static void umc_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)
 static void umc_dump_misc_regs(struct amd64_pvt *pvt)
 {
 	struct amd64_umc *umc;
-	u32 i, tmp, umc_base;
+	u32 i;
 
 	for_each_umc(i) {
-		umc_base = get_umc_base(i);
 		umc = &pvt->umc[i];
 
 		edac_dbg(1, "UMC%d DIMM cfg: 0x%x\n", i, umc->dimm_cfg);
 		edac_dbg(1, "UMC%d UMC cfg: 0x%x\n", i, umc->umc_cfg);
 		edac_dbg(1, "UMC%d SDP ctrl: 0x%x\n", i, umc->sdp_ctrl);
 		edac_dbg(1, "UMC%d ECC ctrl: 0x%x\n", i, umc->ecc_ctrl);
-
-		amd_smn_read(pvt->mc_node_id, umc_base + UMCCH_ECC_BAD_SYMBOL, &tmp);
-		edac_dbg(1, "UMC%d ECC bad symbol: 0x%x\n", i, tmp);
-
-		amd_smn_read(pvt->mc_node_id, umc_base + UMCCH_UMC_CAP, &tmp);
-		edac_dbg(1, "UMC%d UMC cap: 0x%x\n", i, tmp);
 		edac_dbg(1, "UMC%d UMC cap high: 0x%x\n", i, umc->umc_cap_hi);
 
 		edac_dbg(1, "UMC%d ECC capable: %s, ChipKill ECC capable: %s\n",
-				i, (umc->umc_cap_hi & BIT(30)) ? "yes" : "no",
-				    (umc->umc_cap_hi & BIT(31)) ? "yes" : "no");
+				i, str_yes_no(umc->umc_cap_hi & BIT(30)),
+				    str_yes_no(umc->umc_cap_hi & BIT(31)));
 		edac_dbg(1, "UMC%d All DIMMs support ECC: %s\n",
-				i, (umc->umc_cfg & BIT(12)) ? "yes" : "no");
+				i, str_yes_no(umc->umc_cfg & BIT(12)));
 		edac_dbg(1, "UMC%d x4 DIMMs present: %s\n",
-				i, (umc->dimm_cfg & BIT(6)) ? "yes" : "no");
+				i, str_yes_no(umc->dimm_cfg & BIT(6)));
 		edac_dbg(1, "UMC%d x16 DIMMs present: %s\n",
-				i, (umc->dimm_cfg & BIT(7)) ? "yes" : "no");
-
-		if (umc->dram_type == MEM_LRDDR4 || umc->dram_type == MEM_LRDDR5) {
-			amd_smn_read(pvt->mc_node_id,
-				     umc_base + get_umc_reg(pvt, UMCCH_ADDR_CFG),
-				     &tmp);
-			edac_dbg(1, "UMC%d LRDIMM %dx rank multiply\n",
-					i, 1 << ((tmp >> 4) & 0x3));
-		}
+				i, str_yes_no(umc->dimm_cfg & BIT(7)));
 
 		umc_debug_display_dimm_sizes(pvt, i);
 	}
@@ -1658,11 +1371,11 @@ static void dct_dump_misc_regs(struct amd64_pvt *pvt)
 	edac_dbg(1, "F3xE8 (NB Cap): 0x%08x\n", pvt->nbcap);
 
 	edac_dbg(1, "  NB two channel DRAM capable: %s\n",
-		 (pvt->nbcap & NBCAP_DCT_DUAL) ? "yes" : "no");
+		 str_yes_no(pvt->nbcap & NBCAP_DCT_DUAL));
 
 	edac_dbg(1, "  ECC capable: %s, ChipKill ECC capable: %s\n",
-		 (pvt->nbcap & NBCAP_SECDED) ? "yes" : "no",
-		 (pvt->nbcap & NBCAP_CHIPKILL) ? "yes" : "no");
+		 str_yes_no(pvt->nbcap & NBCAP_SECDED),
+		 str_yes_no(pvt->nbcap & NBCAP_CHIPKILL));
 
 	debug_dump_dramcfg_low(pvt, pvt->dclr0, 0);
 
@@ -1685,7 +1398,7 @@ static void dct_dump_misc_regs(struct amd64_pvt *pvt)
 	if (!dct_ganging_enabled(pvt))
 		debug_dump_dramcfg_low(pvt, pvt->dclr1, 1);
 
-	edac_dbg(1, "  DramHoleValid: %s\n", dhar_valid(pvt) ? "yes" : "no");
+	edac_dbg(1, "  DramHoleValid: %s\n", str_yes_no(dhar_valid(pvt)));
 
 	amd64_info("using x%u syndromes.\n", pvt->ecc_sym_sz);
 }
@@ -1726,6 +1439,7 @@ static void umc_read_base_mask(struct amd64_pvt *pvt)
 	u32 *base, *base_sec;
 	u32 *mask, *mask_sec;
 	int cs, umc;
+	u32 tmp;
 
 	for_each_umc(umc) {
 		umc_base_reg = get_umc_base(umc) + UMCCH_BASE_ADDR;
@@ -1738,13 +1452,17 @@ static void umc_read_base_mask(struct amd64_pvt *pvt)
 			base_reg = umc_base_reg + (cs * 4);
 			base_reg_sec = umc_base_reg_sec + (cs * 4);
 
-			if (!amd_smn_read(pvt->mc_node_id, base_reg, base))
+			if (!amd_smn_read(pvt->mc_node_id, base_reg, &tmp)) {
+				*base = tmp;
 				edac_dbg(0, "  DCSB%d[%d]=0x%08x reg: 0x%x\n",
 					 umc, cs, *base, base_reg);
+			}
 
-			if (!amd_smn_read(pvt->mc_node_id, base_reg_sec, base_sec))
+			if (!amd_smn_read(pvt->mc_node_id, base_reg_sec, &tmp)) {
+				*base_sec = tmp;
 				edac_dbg(0, "    DCSB_SEC%d[%d]=0x%08x reg: 0x%x\n",
 					 umc, cs, *base_sec, base_reg_sec);
+			}
 		}
 
 		umc_mask_reg = get_umc_base(umc) + UMCCH_ADDR_MASK;
@@ -1757,13 +1475,17 @@ static void umc_read_base_mask(struct amd64_pvt *pvt)
 			mask_reg = umc_mask_reg + (cs * 4);
 			mask_reg_sec = umc_mask_reg_sec + (cs * 4);
 
-			if (!amd_smn_read(pvt->mc_node_id, mask_reg, mask))
+			if (!amd_smn_read(pvt->mc_node_id, mask_reg, &tmp)) {
+				*mask = tmp;
 				edac_dbg(0, "  DCSM%d[%d]=0x%08x reg: 0x%x\n",
 					 umc, cs, *mask, mask_reg);
+			}
 
-			if (!amd_smn_read(pvt->mc_node_id, mask_reg_sec, mask_sec))
+			if (!amd_smn_read(pvt->mc_node_id, mask_reg_sec, &tmp)) {
+				*mask_sec = tmp;
 				edac_dbg(0, "    DCSM_SEC%d[%d]=0x%08x reg: 0x%x\n",
 					 umc, cs, *mask_sec, mask_reg_sec);
+			}
 		}
 	}
 }
@@ -1915,7 +1637,7 @@ ddr3:
 /* On F10h and later ErrAddr is MC4_ADDR[47:1] */
 static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m)
 {
-	u16 mce_nid = topology_die_id(m->extcpu);
+	u16 mce_nid = topology_amd_node_id(m->extcpu);
 	struct mem_ctl_info *mci;
 	u8 start_bit = 1;
 	u8 end_bit   = 47;
@@ -2305,15 +2027,15 @@ static void read_dram_ctl_register(struct amd64_pvt *pvt)
 
 		if (!dct_ganging_enabled(pvt))
 			edac_dbg(0, "  Address range split per DCT: %s\n",
-				 (dct_high_range_enabled(pvt) ? "yes" : "no"));
+				 str_yes_no(dct_high_range_enabled(pvt)));
 
 		edac_dbg(0, "  data interleave for ECC: %s, DRAM cleared since last warm reset: %s\n",
-			 (dct_data_intlv_enabled(pvt) ? "enabled" : "disabled"),
-			 (dct_memory_cleared(pvt) ? "yes" : "no"));
+			 str_enabled_disabled(dct_data_intlv_enabled(pvt)),
+			 str_yes_no(dct_memory_cleared(pvt)));
 
 		edac_dbg(0, "  channel interleave: %s, "
 			 "interleave bits selector: 0x%x\n",
-			 (dct_interleave_enabled(pvt) ? "enabled" : "disabled"),
+			 str_enabled_disabled(dct_interleave_enabled(pvt)),
 			 dct_sel_interleave_addr(pvt));
 	}
 
@@ -3073,9 +2795,10 @@ static void decode_umc_error(int node_id, struct mce *m)
 {
 	u8 ecc_type = (m->status >> 45) & 0x3;
 	struct mem_ctl_info *mci;
+	unsigned long sys_addr;
 	struct amd64_pvt *pvt;
+	struct atl_err a_err;
 	struct err_info err;
-	u64 sys_addr;
 
 	node_id = fixup_node_id(node_id, m);
 
@@ -3106,7 +2829,12 @@ static void decode_umc_error(int node_id, struct mce *m)
 
 	pvt->ops->get_err_info(m, &err);
 
-	if (umc_normaddr_to_sysaddr(m->addr, pvt->mc_node_id, err.channel, &sys_addr)) {
+	a_err.addr = m->addr;
+	a_err.ipid = m->ipid;
+	a_err.cpu  = m->extcpu;
+
+	sys_addr = amd_convert_umc_mca_addr_to_sys_addr(&a_err);
+	if (IS_ERR_VALUE(sys_addr)) {
 		err.err_code = ERR_NORM_ADDR;
 		goto log_error;
 	}
@@ -3176,7 +2904,7 @@ static void umc_read_mc_regs(struct amd64_pvt *pvt)
 {
 	u8 nid = pvt->mc_node_id;
 	struct amd64_umc *umc;
-	u32 i, umc_base;
+	u32 i, tmp, umc_base;
 
 	/* Read registers from each UMC */
 	for_each_umc(i) {
@@ -3184,11 +2912,20 @@ static void umc_read_mc_regs(struct amd64_pvt *pvt)
 		umc_base = get_umc_base(i);
 		umc = &pvt->umc[i];
 
-		amd_smn_read(nid, umc_base + get_umc_reg(pvt, UMCCH_DIMM_CFG), &umc->dimm_cfg);
-		amd_smn_read(nid, umc_base + UMCCH_UMC_CFG, &umc->umc_cfg);
-		amd_smn_read(nid, umc_base + UMCCH_SDP_CTRL, &umc->sdp_ctrl);
-		amd_smn_read(nid, umc_base + UMCCH_ECC_CTRL, &umc->ecc_ctrl);
-		amd_smn_read(nid, umc_base + UMCCH_UMC_CAP_HI, &umc->umc_cap_hi);
+		if (!amd_smn_read(nid, umc_base + get_umc_reg(pvt, UMCCH_DIMM_CFG), &tmp))
+			umc->dimm_cfg = tmp;
+
+		if (!amd_smn_read(nid, umc_base + UMCCH_UMC_CFG, &tmp))
+			umc->umc_cfg = tmp;
+
+		if (!amd_smn_read(nid, umc_base + UMCCH_SDP_CTRL, &tmp))
+			umc->sdp_ctrl = tmp;
+
+		if (!amd_smn_read(nid, umc_base + UMCCH_ECC_CTRL, &tmp))
+			umc->ecc_ctrl = tmp;
+
+		if (!amd_smn_read(nid, umc_base + UMCCH_UMC_CAP_HI, &tmp))
+			umc->umc_cap_hi = tmp;
 	}
 }
 
@@ -3205,13 +2942,13 @@ static void dct_read_mc_regs(struct amd64_pvt *pvt)
 	 * Retrieve TOP_MEM and TOP_MEM2; no masking off of reserved bits since
 	 * those are Read-As-Zero.
 	 */
-	rdmsrl(MSR_K8_TOP_MEM1, pvt->top_mem);
+	rdmsrq(MSR_K8_TOP_MEM1, pvt->top_mem);
 	edac_dbg(0, "  TOP_MEM:  0x%016llx\n", pvt->top_mem);
 
 	/* Check first whether TOP_MEM2 is enabled: */
-	rdmsrl(MSR_AMD64_SYSCFG, msr_val);
+	rdmsrq(MSR_AMD64_SYSCFG, msr_val);
 	if (msr_val & BIT(21)) {
-		rdmsrl(MSR_K8_TOP_MEM2, pvt->top_mem2);
+		rdmsrq(MSR_K8_TOP_MEM2, pvt->top_mem2);
 		edac_dbg(0, "  TOP_MEM2: 0x%016llx\n", pvt->top_mem2);
 	} else {
 		edac_dbg(0, "  TOP_MEM2 disabled\n");
@@ -3446,7 +3183,7 @@ static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, u16 nid)
 	int cpu;
 
 	for_each_online_cpu(cpu)
-		if (topology_die_id(cpu) == nid)
+		if (topology_amd_node_id(cpu) == nid)
 			cpumask_set_cpu(cpu, mask);
 }
 
@@ -3471,8 +3208,7 @@ static bool nb_mce_bank_enabled_on_node(u16 nid)
 		nbe = reg->l & MSR_MCGCTL_NBE;
 
 		edac_dbg(0, "core: %u, MCG_CTL: 0x%llx, NB MSR is %s\n",
-			 cpu, reg->q,
-			 (nbe ? "enabled" : "disabled"));
+			 cpu, reg->q, str_enabled_disabled(nbe));
 
 		if (!nbe)
 			goto out;
@@ -3616,46 +3352,31 @@ static bool dct_ecc_enabled(struct amd64_pvt *pvt)
 		edac_dbg(0, "NB MCE bank disabled, set MSR 0x%08x[4] on node %d to enable.\n",
 			 MSR_IA32_MCG_CTL, nid);
 
-	edac_dbg(3, "Node %d: DRAM ECC %s.\n", nid, (ecc_en ? "enabled" : "disabled"));
+	edac_dbg(3, "Node %d: DRAM ECC %s.\n", nid, str_enabled_disabled(ecc_en));
 
-	if (!ecc_en || !nb_mce_en)
-		return false;
-	else
-		return true;
+	return ecc_en && nb_mce_en;
 }
 
 static bool umc_ecc_enabled(struct amd64_pvt *pvt)
 {
-	u8 umc_en_mask = 0, ecc_en_mask = 0;
-	u16 nid = pvt->mc_node_id;
 	struct amd64_umc *umc;
-	u8 ecc_en = 0, i;
+	bool ecc_en = false;
+	int i;
 
+	/* Check whether at least one UMC is enabled: */
 	for_each_umc(i) {
 		umc = &pvt->umc[i];
 
-		/* Only check enabled UMCs. */
-		if (!(umc->sdp_ctrl & UMC_SDP_INIT))
-			continue;
-
-		umc_en_mask |= BIT(i);
-
-		if (umc->umc_cap_hi & UMC_ECC_ENABLED)
-			ecc_en_mask |= BIT(i);
+		if (umc->sdp_ctrl & UMC_SDP_INIT &&
+		    umc->umc_cap_hi & UMC_ECC_ENABLED) {
+			ecc_en = true;
+			break;
+		}
 	}
 
-	/* Check whether at least one UMC is enabled: */
-	if (umc_en_mask)
-		ecc_en = umc_en_mask == ecc_en_mask;
-	else
-		edac_dbg(0, "Node %d: No enabled UMCs.\n", nid);
+	edac_dbg(3, "Node %d: DRAM ECC %s.\n", pvt->mc_node_id, str_enabled_disabled(ecc_en));
 
-	edac_dbg(3, "Node %d: DRAM ECC %s.\n", nid, (ecc_en ? "enabled" : "disabled"));
-
-	if (!ecc_en)
-		return false;
-	else
-		return true;
+	return ecc_en;
 }
 
 static inline void
@@ -3917,16 +3638,21 @@ static void gpu_read_mc_regs(struct amd64_pvt *pvt)
 {
 	u8 nid = pvt->mc_node_id;
 	struct amd64_umc *umc;
-	u32 i, umc_base;
+	u32 i, tmp, umc_base;
 
 	/* Read registers from each UMC */
 	for_each_umc(i) {
 		umc_base = gpu_get_umc_base(pvt, i, 0);
 		umc = &pvt->umc[i];
 
-		amd_smn_read(nid, umc_base + UMCCH_UMC_CFG, &umc->umc_cfg);
-		amd_smn_read(nid, umc_base + UMCCH_SDP_CTRL, &umc->sdp_ctrl);
-		amd_smn_read(nid, umc_base + UMCCH_ECC_CTRL, &umc->ecc_ctrl);
+		if (!amd_smn_read(nid, umc_base + UMCCH_UMC_CFG, &tmp))
+			umc->umc_cfg = tmp;
+
+		if (!amd_smn_read(nid, umc_base + UMCCH_SDP_CTRL, &tmp))
+			umc->sdp_ctrl = tmp;
+
+		if (!amd_smn_read(nid, umc_base + UMCCH_ECC_CTRL, &tmp))
+			umc->ecc_ctrl = tmp;
 	}
 }