diff options
Diffstat (limited to 'drivers/edac/amd64_edac.c')
| -rw-r--r-- | drivers/edac/amd64_edac.c | 1943 |
1 files changed, 870 insertions, 1073 deletions
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index e3318e5575a3..2391f3469961 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; @@ -13,15 +16,12 @@ module_param(ecc_enable_override, int, 0644); static struct msr __percpu *msrs; -static struct amd64_family_type *fam_type; - -static inline u32 get_umc_reg(u32 reg) +static inline u32 get_umc_reg(struct amd64_pvt *pvt, u32 reg) { - if (!fam_type->flags.zn_regs_v2) + if (!pvt->flags.zn_regs_v2) 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; } @@ -82,7 +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, @@ -95,7 +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); } /* @@ -182,21 +182,6 @@ static inline int amd64_read_dct_pci_cfg(struct amd64_pvt *pvt, u8 dct, * other archs, we might not have access to the caches directly. */ -static inline void __f17h_set_scrubval(struct amd64_pvt *pvt, u32 scrubval) -{ - /* - * Fam17h supports scrub values between 0x5 and 0x14. Also, the values - * are shifted down by 0x5, so scrubval 0x5 is written to the register - * as 0x0, scrubval 0x6 as 0x1, etc. - */ - if (scrubval >= 0x5 && scrubval <= 0x14) { - scrubval -= 0x5; - pci_write_bits32(pvt->F6, F17H_SCR_LIMIT_ADDR, scrubval, 0xF); - pci_write_bits32(pvt->F6, F17H_SCR_BASE_ADDR, 1, 0x1); - } else { - pci_write_bits32(pvt->F6, F17H_SCR_BASE_ADDR, 0, 0x1); - } -} /* * Scan the scrub rate mapping table for a close or matching bandwidth value to * issue. If requested is too big, then use last maximum value found. @@ -229,9 +214,7 @@ static int __set_scrub_rate(struct amd64_pvt *pvt, u32 new_bw, u32 min_rate) scrubval = scrubrates[i].scrubval; - if (pvt->umc) { - __f17h_set_scrubval(pvt, scrubval); - } else if (pvt->fam == 0x15 && pvt->model == 0x60) { + if (pvt->fam == 0x15 && pvt->model == 0x60) { f15h_select_dct(pvt, 0); pci_write_bits32(pvt->F2, F15H_M60H_SCRCTRL, scrubval, 0x001F); f15h_select_dct(pvt, 1); @@ -271,16 +254,7 @@ static int get_scrub_rate(struct mem_ctl_info *mci) int i, retval = -EINVAL; u32 scrubval = 0; - if (pvt->umc) { - amd64_read_pci_cfg(pvt->F6, F17H_SCR_BASE_ADDR, &scrubval); - if (scrubval & BIT(0)) { - amd64_read_pci_cfg(pvt->F6, F17H_SCR_LIMIT_ADDR, &scrubval); - scrubval &= 0xF; - scrubval += 0x5; - } else { - scrubval = 0; - } - } else if (pvt->fam == 0x15) { + if (pvt->fam == 0x15) { /* Erratum #505 */ if (pvt->model < 0x10) f15h_select_dct(pvt, 0); @@ -463,7 +437,7 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct, for (i = 0; i < pvt->csels[dct].m_cnt; i++) #define for_each_umc(i) \ - for (i = 0; i < fam_type->max_mcs; i++) + for (i = 0; i < pvt->max_mcs; i++) /* * @input_addr is an InputAddr associated with the node given by mci. Return the @@ -1003,321 +977,186 @@ static int sys_addr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr) return csrow; } -/* 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. + * See AMD PPR DF::LclNodeTypeMap * - * Fabric Indirect Configuration Access Data (FICAD): There are FICAD LO - * and FICAD HI registers but so far we only need the LO register. + * This register gives information for nodes of the same type within a system. * - * Use Instance Id 0xFF to indicate a broadcast read. + * Reading this register from a GPU node will tell how many GPU nodes are in the + * system and what the lowest AMD Node ID value is for the GPU nodes. Use this + * info to fixup the Linux logical "Node ID" value set in the AMD NB code and EDAC. */ -#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; - } +static struct local_node_map { + u16 node_count; + u16 base_node_id; +} gpu_node_map; - 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; -} +#define PCI_DEVICE_ID_AMD_MI200_DF_F1 0x14d1 +#define REG_LOCAL_NODE_TYPE_MAP 0x144 -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); -} +/* Local Node Type Map (LNTM) fields */ +#define LNTM_NODE_COUNT GENMASK(27, 16) +#define LNTM_BASE_NODE_ID GENMASK(11, 0) -static int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo) +static int gpu_get_node_map(struct amd64_pvt *pvt) { - return __df_indirect_read(node, func, reg, DF_BROADCAST, lo); -} - -struct addr_ctx { - u64 ret_addr; + struct pci_dev *pdev; + int ret; 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; - } + /* + * Mapping of nodes from hardware-provided AMD Node ID to a + * Linux logical one is applicable for MI200 models. Therefore, + * return early for other heterogeneous systems. + */ + if (pvt->F3->device != PCI_DEVICE_ID_AMD_MI200_DF_F3) + return 0; - num_intlv_bits = intlv_num_chan; + /* + * Node ID 0 is reserved for CPUs. Therefore, a non-zero Node ID + * means the values have been already cached. + */ + if (gpu_node_map.base_node_id) + return 0; - if (intlv_num_dies > 2) { - pr_err("%s: Invalid number of interleaved nodes/dies %d.\n", - __func__, intlv_num_dies); - goto out_err; + pdev = pci_get_device(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F1, NULL); + if (!pdev) { + ret = -ENODEV; + goto out; } - 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; + ret = pci_read_config_dword(pdev, REG_LOCAL_NODE_TYPE_MAP, &tmp); + if (ret) { + ret = pcibios_err_to_errno(ret); + goto out; } - 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; + gpu_node_map.node_count = FIELD_GET(LNTM_NODE_COUNT, tmp); + gpu_node_map.base_node_id = FIELD_GET(LNTM_BASE_NODE_ID, tmp); - /* - * 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; - } +out: + pci_dev_put(pdev); + return ret; +} - sock_id_bit = die_id_bit; +static int fixup_node_id(int node_id, struct mce *m) +{ + /* MCA_IPID[InstanceIdHi] give the AMD Node ID for the bank. */ + u8 nid = (m->ipid >> 44) & 0xF; - /* Read D18F1x208 (SystemFabricIdMask). */ - if (intlv_num_dies || intlv_num_sockets) - if (df_indirect_read_broadcast(nid, 1, 0x208, &ctx.tmp)) - goto out_err; + if (smca_get_bank_type(m->extcpu, m->bank) != SMCA_UMC_V2) + return node_id; - /* 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; + /* Nodes below the GPU base node are CPU nodes and don't need a fixup. */ + if (nid < gpu_node_map.base_node_id) + return node_id; - cs_id |= ((cs_fabric_id & die_id_mask) >> die_id_shift) << die_id_bit; - } + /* Convert the hardware-provided AMD Node ID to a Linux logical one. */ + return nid - gpu_node_map.base_node_id + 1; +} - /* 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; +static int get_channel_from_ecc_syndrome(struct mem_ctl_info *, u16); - cs_id |= ((cs_fabric_id & socket_id_mask) >> socket_id_shift) << sock_id_bit; - } +/* + * Determine if the DIMMs have ECC enabled. ECC is enabled ONLY if all the DIMMs + * are ECC capable. + */ +static unsigned long dct_determine_edac_cap(struct amd64_pvt *pvt) +{ + unsigned long edac_cap = EDAC_FLAG_NONE; + u8 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; - } + bit = (pvt->fam > 0xf || pvt->ext_model >= K8_REV_F) + ? 19 + : 17; - /* Add dram base address */ - ctx.ret_addr += dram_base_addr; + if (pvt->dclr0 & BIT(bit)) + edac_cap = EDAC_FLAG_SECDED; - /* If legacy MMIO hole enabled */ - if (lgcy_mmio_hole_en) { - if (df_indirect_read_broadcast(nid, 0, 0x104, &ctx.tmp)) - goto out_err; + return edac_cap; +} - dram_hole_base = ctx.tmp & GENMASK(31, 24); - if (ctx.ret_addr >= dram_hole_base) - ctx.ret_addr += (BIT_ULL(32) - dram_hole_base); - } +static unsigned long umc_determine_edac_cap(struct amd64_pvt *pvt) +{ + u8 i, umc_en_mask = 0, dimm_ecc_en_mask = 0; + unsigned long edac_cap = EDAC_FLAG_NONE; - 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; + for_each_umc(i) { + if (!(pvt->umc[i].sdp_ctrl & UMC_SDP_INIT)) + continue; - hashed_bit &= BIT(0); + umc_en_mask |= BIT(i); - if (hashed_bit != ((ctx.ret_addr >> intlv_addr_bit) & BIT(0))) - ctx.ret_addr ^= BIT(intlv_addr_bit); + /* UMC Configuration bit 12 (DimmEccEn) */ + if (pvt->umc[i].umc_cfg & BIT(12)) + dimm_ecc_en_mask |= BIT(i); } - /* 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; + if (umc_en_mask == dimm_ecc_en_mask) + edac_cap = EDAC_FLAG_SECDED; -out_err: - return -EINVAL; + return edac_cap; } -static int get_channel_from_ecc_syndrome(struct mem_ctl_info *, u16); - /* - * Determine if the DIMMs have ECC enabled. ECC is enabled ONLY if all the DIMMs - * are ECC capable. + * debug routine to display the memory sizes of all logical DIMMs and its + * CSROWs */ -static unsigned long determine_edac_cap(struct amd64_pvt *pvt) +static void dct_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl) { - unsigned long edac_cap = EDAC_FLAG_NONE; - u8 bit; + u32 *dcsb = ctrl ? pvt->csels[1].csbases : pvt->csels[0].csbases; + u32 dbam = ctrl ? pvt->dbam1 : pvt->dbam0; + int dimm, size0, size1; - if (pvt->umc) { - u8 i, umc_en_mask = 0, dimm_ecc_en_mask = 0; + if (pvt->fam == 0xf) { + /* K8 families < revF not supported yet */ + if (pvt->ext_model < K8_REV_F) + return; - for_each_umc(i) { - if (!(pvt->umc[i].sdp_ctrl & UMC_SDP_INIT)) - continue; + WARN_ON(ctrl != 0); + } - umc_en_mask |= BIT(i); + if (pvt->fam == 0x10) { + dbam = (ctrl && !dct_ganging_enabled(pvt)) ? pvt->dbam1 + : pvt->dbam0; + dcsb = (ctrl && !dct_ganging_enabled(pvt)) ? + pvt->csels[1].csbases : + pvt->csels[0].csbases; + } else if (ctrl) { + dbam = pvt->dbam0; + dcsb = pvt->csels[1].csbases; + } + edac_dbg(1, "F2x%d80 (DRAM Bank Address Mapping): 0x%08x\n", + ctrl, dbam); - /* UMC Configuration bit 12 (DimmEccEn) */ - if (pvt->umc[i].umc_cfg & BIT(12)) - dimm_ecc_en_mask |= BIT(i); - } + edac_printk(KERN_DEBUG, EDAC_MC, "DCT%d chip selects:\n", ctrl); - if (umc_en_mask == dimm_ecc_en_mask) - edac_cap = EDAC_FLAG_SECDED; - } else { - bit = (pvt->fam > 0xf || pvt->ext_model >= K8_REV_F) - ? 19 - : 17; + /* Dump memory sizes for DIMM and its CSROWs */ + for (dimm = 0; dimm < 4; dimm++) { + size0 = 0; + if (dcsb[dimm * 2] & DCSB_CS_ENABLE) + /* + * For F15m60h, we need multiplier for LRDIMM cs_size + * calculation. We pass dimm value to the dbam_to_cs + * mapper so we can find the multiplier from the + * corresponding DCSM. + */ + size0 = pvt->ops->dbam_to_cs(pvt, ctrl, + DBAM_DIMM(dimm, dbam), + dimm); - if (pvt->dclr0 & BIT(bit)) - edac_cap = EDAC_FLAG_SECDED; - } + size1 = 0; + if (dcsb[dimm * 2 + 1] & DCSB_CS_ENABLE) + size1 = pvt->ops->dbam_to_cs(pvt, ctrl, + DBAM_DIMM(dimm, dbam), + dimm); - return edac_cap; + amd64_info(EDAC_MC ": %d: %5dMB %d: %5dMB\n", + dimm * 2, size0, + dimm * 2 + 1, size1); + } } -static void debug_display_dimm_sizes(struct amd64_pvt *, u8); static void debug_dump_dramcfg_low(struct amd64_pvt *pvt, u32 dclr, int chan) { @@ -1333,22 +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) @@ -1360,7 +1198,7 @@ static void debug_dump_dramcfg_low(struct amd64_pvt *pvt, u32 dclr, int chan) #define CS_EVEN (CS_EVEN_PRIMARY | CS_EVEN_SECONDARY) #define CS_ODD (CS_ODD_PRIMARY | CS_ODD_SECONDARY) -static int f17_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt) +static int umc_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt) { u8 base, count = 0; int cs_mode = 0; @@ -1371,7 +1209,9 @@ static int f17_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt) if (csrow_enabled(2 * dimm + 1, ctrl, pvt)) cs_mode |= CS_ODD_PRIMARY; - /* Asymmetric dual-rank DIMM support. */ + if (csrow_sec_enabled(2 * dimm, ctrl, pvt)) + cs_mode |= CS_EVEN_SECONDARY; + if (csrow_sec_enabled(2 * dimm + 1, ctrl, pvt)) cs_mode |= CS_ODD_SECONDARY; @@ -1392,7 +1232,106 @@ static int f17_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt) return cs_mode; } -static void debug_display_dimm_sizes_df(struct amd64_pvt *pvt, u8 ctrl) +static int calculate_cs_size(u32 mask, unsigned int cs_mode) +{ + int msb, weight, num_zero_bits; + u32 deinterleaved_mask; + + if (!mask) + return 0; + + /* + * The number of zero bits in the mask is equal to the number of bits + * in a full mask minus the number of bits in the current mask. + * + * The MSB is the number of bits in the full mask because BIT[0] is + * always 0. + * + * In the special 3 Rank interleaving case, a single bit is flipped + * without swapping with the most significant bit. This can be handled + * by keeping the MSB where it is and ignoring the single zero bit. + */ + msb = fls(mask) - 1; + weight = hweight_long(mask); + num_zero_bits = msb - weight - !!(cs_mode & CS_3R_INTERLEAVE); + + /* Take the number of zero bits off from the top of the mask. */ + deinterleaved_mask = GENMASK(msb - num_zero_bits, 1); + edac_dbg(1, " Deinterleaved AddrMask: 0x%x\n", deinterleaved_mask); + + return (deinterleaved_mask >> 2) + 1; +} + +static int __addr_mask_to_cs_size(u32 addr_mask, u32 addr_mask_sec, + unsigned int cs_mode, int csrow_nr, int dimm) +{ + int size; + + edac_dbg(1, "CS%d DIMM%d AddrMasks:\n", csrow_nr, dimm); + edac_dbg(1, " Primary AddrMask: 0x%x\n", addr_mask); + + /* Register [31:1] = Address [39:9]. Size is in kBs here. */ + size = calculate_cs_size(addr_mask, cs_mode); + + edac_dbg(1, " Secondary AddrMask: 0x%x\n", addr_mask_sec); + size += calculate_cs_size(addr_mask_sec, cs_mode); + + /* Return size in MBs. */ + return size >> 10; +} + +static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc, + unsigned int cs_mode, int csrow_nr) +{ + u32 addr_mask = 0, addr_mask_sec = 0; + int cs_mask_nr = csrow_nr; + int dimm, size = 0; + + /* No Chip Selects are enabled. */ + if (!cs_mode) + return size; + + /* Requested size of an even CS but none are enabled. */ + if (!(cs_mode & CS_EVEN) && !(csrow_nr & 1)) + return size; + + /* Requested size of an odd CS but none are enabled. */ + if (!(cs_mode & CS_ODD) && (csrow_nr & 1)) + return size; + + /* + * Family 17h introduced systems with one mask per DIMM, + * and two Chip Selects per DIMM. + * + * CS0 and CS1 -> MASK0 / DIMM0 + * CS2 and CS3 -> MASK1 / DIMM1 + * + * Family 19h Model 10h introduced systems with one mask per Chip Select, + * and two Chip Selects per DIMM. + * + * CS0 -> MASK0 -> DIMM0 + * CS1 -> MASK1 -> DIMM0 + * CS2 -> MASK2 -> DIMM1 + * CS3 -> MASK3 -> DIMM1 + * + * Keep the mask number equal to the Chip Select number for newer systems, + * and shift the mask number for older systems. + */ + dimm = csrow_nr >> 1; + + if (!pvt->flags.zn_regs_v2) + cs_mask_nr >>= 1; + + if (cs_mode & (CS_EVEN_PRIMARY | CS_ODD_PRIMARY)) + addr_mask = pvt->csels[umc].csmasks[cs_mask_nr]; + + if (cs_mode & (CS_EVEN_SECONDARY | CS_ODD_SECONDARY)) + addr_mask_sec = pvt->csels[umc].csmasks_sec[cs_mask_nr]; + + return __addr_mask_to_cs_size(addr_mask, addr_mask_sec, cs_mode, csrow_nr, dimm); +} + +static void umc_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl) { int dimm, size0, size1, cs0, cs1, cs_mode; @@ -1402,10 +1341,10 @@ static void debug_display_dimm_sizes_df(struct amd64_pvt *pvt, u8 ctrl) cs0 = dimm * 2; cs1 = dimm * 2 + 1; - cs_mode = f17_get_cs_mode(dimm, ctrl, pvt); + cs_mode = umc_get_cs_mode(dimm, ctrl, pvt); - size0 = pvt->ops->dbam_to_cs(pvt, ctrl, cs_mode, cs0); - size1 = pvt->ops->dbam_to_cs(pvt, ctrl, cs_mode, cs1); + size0 = umc_addr_mask_to_cs_size(pvt, ctrl, cs_mode, cs0); + size1 = umc_addr_mask_to_cs_size(pvt, ctrl, cs_mode, cs1); amd64_info(EDAC_MC ": %d: %5dMB %d: %5dMB\n", cs0, size0, @@ -1413,63 +1352,44 @@ static void debug_display_dimm_sizes_df(struct amd64_pvt *pvt, u8 ctrl) } } -static void __dump_misc_regs_df(struct amd64_pvt *pvt) +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(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))); - debug_display_dimm_sizes_df(pvt, i); + umc_debug_display_dimm_sizes(pvt, i); } - - edac_dbg(1, "F0x104 (DRAM Hole Address): 0x%08x, base: 0x%08x\n", - pvt->dhar, dhar_base(pvt)); } -/* Display and decode various NB registers for debug purposes. */ -static void __dump_misc_regs(struct amd64_pvt *pvt) +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); @@ -1480,28 +1400,19 @@ static void __dump_misc_regs(struct amd64_pvt *pvt) (pvt->fam == 0xf) ? k8_dhar_offset(pvt) : f10_dhar_offset(pvt)); - debug_display_dimm_sizes(pvt, 0); + dct_debug_display_dimm_sizes(pvt, 0); /* everything below this point is Fam10h and above */ if (pvt->fam == 0xf) return; - debug_display_dimm_sizes(pvt, 1); + dct_debug_display_dimm_sizes(pvt, 1); /* Only if NOT ganged does dclr1 have valid info */ if (!dct_ganging_enabled(pvt)) debug_dump_dramcfg_low(pvt, pvt->dclr1, 1); -} - -/* Display and decode various NB registers for debug purposes. */ -static void dump_misc_regs(struct amd64_pvt *pvt) -{ - if (pvt->umc) - __dump_misc_regs_df(pvt); - else - __dump_misc_regs(pvt); - 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); } @@ -1509,7 +1420,7 @@ static void dump_misc_regs(struct amd64_pvt *pvt) /* * See BKDG, F2x[1,0][5C:40], F2[1,0][6C:60] */ -static void prep_chip_selects(struct amd64_pvt *pvt) +static void dct_prep_chip_selects(struct amd64_pvt *pvt) { if (pvt->fam == 0xf && pvt->ext_model < K8_REV_F) { pvt->csels[0].b_cnt = pvt->csels[1].b_cnt = 8; @@ -1517,21 +1428,23 @@ static void prep_chip_selects(struct amd64_pvt *pvt) } else if (pvt->fam == 0x15 && pvt->model == 0x30) { pvt->csels[0].b_cnt = pvt->csels[1].b_cnt = 4; pvt->csels[0].m_cnt = pvt->csels[1].m_cnt = 2; - } else if (pvt->fam >= 0x17) { - int umc; - - for_each_umc(umc) { - pvt->csels[umc].b_cnt = 4; - pvt->csels[umc].m_cnt = fam_type->flags.zn_regs_v2 ? 4 : 2; - } - } else { pvt->csels[0].b_cnt = pvt->csels[1].b_cnt = 8; pvt->csels[0].m_cnt = pvt->csels[1].m_cnt = 4; } } -static void read_umc_base_mask(struct amd64_pvt *pvt) +static void umc_prep_chip_selects(struct amd64_pvt *pvt) +{ + int umc; + + for_each_umc(umc) { + pvt->csels[umc].b_cnt = 4; + pvt->csels[umc].m_cnt = pvt->flags.zn_regs_v2 ? 4 : 2; + } +} + +static void umc_read_base_mask(struct amd64_pvt *pvt) { u32 umc_base_reg, umc_base_reg_sec; u32 umc_mask_reg, umc_mask_reg_sec; @@ -1540,6 +1453,7 @@ static void read_umc_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; @@ -1552,17 +1466,21 @@ static void read_umc_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; - umc_mask_reg_sec = get_umc_base(umc) + get_umc_reg(UMCCH_ADDR_MASK_SEC); + umc_mask_reg_sec = get_umc_base(umc) + get_umc_reg(pvt, UMCCH_ADDR_MASK_SEC); for_each_chip_select_mask(cs, umc, pvt) { mask = &pvt->csels[umc].csmasks[cs]; @@ -1571,13 +1489,17 @@ static void read_umc_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); + } } } } @@ -1585,15 +1507,10 @@ static void read_umc_base_mask(struct amd64_pvt *pvt) /* * Function 2 Offset F10_DCSB0; read in the DCS Base and DCS Mask registers */ -static void read_dct_base_mask(struct amd64_pvt *pvt) +static void dct_read_base_mask(struct amd64_pvt *pvt) { int cs; - prep_chip_selects(pvt); - - if (pvt->umc) - return read_umc_base_mask(pvt); - for_each_chip_select(cs, 0, pvt) { int reg0 = DCSB0 + (cs * 4); int reg1 = DCSB1 + (cs * 4); @@ -1633,7 +1550,7 @@ static void read_dct_base_mask(struct amd64_pvt *pvt) } } -static void determine_memory_type_df(struct amd64_pvt *pvt) +static void umc_determine_memory_type(struct amd64_pvt *pvt) { struct amd64_umc *umc; u32 i; @@ -1650,7 +1567,7 @@ static void determine_memory_type_df(struct amd64_pvt *pvt) * Check if the system supports the "DDR Type" field in UMC Config * and has DDR5 DIMMs in use. */ - if (fam_type->flags.zn_regs_v2 && ((umc->umc_cfg & GENMASK(2, 0)) == 0x1)) { + if (pvt->flags.zn_regs_v2 && ((umc->umc_cfg & GENMASK(2, 0)) == 0x1)) { if (umc->dimm_cfg & BIT(5)) umc->dram_type = MEM_LRDDR5; else if (umc->dimm_cfg & BIT(4)) @@ -1670,13 +1587,10 @@ static void determine_memory_type_df(struct amd64_pvt *pvt) } } -static void determine_memory_type(struct amd64_pvt *pvt) +static void dct_determine_memory_type(struct amd64_pvt *pvt) { u32 dram_ctrl, dcsm; - if (pvt->umc) - return determine_memory_type_df(pvt); - switch (pvt->fam) { case 0xf: if (pvt->ext_model >= K8_REV_F) @@ -1726,34 +1640,18 @@ static void determine_memory_type(struct amd64_pvt *pvt) WARN(1, KERN_ERR "%s: Family??? 0x%x\n", __func__, pvt->fam); pvt->dram_type = MEM_EMPTY; } + + edac_dbg(1, " DIMM type: %s\n", edac_mem_types[pvt->dram_type]); return; ddr3: pvt->dram_type = (pvt->dclr0 & BIT(16)) ? MEM_DDR3 : MEM_RDDR3; } -/* Get the number of DCT channels the memory controller is using. */ -static int k8_early_channel_count(struct amd64_pvt *pvt) -{ - int flag; - - if (pvt->ext_model >= K8_REV_F) - /* RevF (NPT) and later */ - flag = pvt->dclr0 & WIDTH_128; - else - /* RevE and earlier */ - flag = pvt->dclr0 & REVE_WIDTH_128; - - /* not used */ - pvt->dclr1 = 0; - - return (flag) ? 2 : 1; -} - /* 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; @@ -2001,69 +1899,6 @@ static int k8_dbam_to_chip_select(struct amd64_pvt *pvt, u8 dct, } } -/* - * Get the number of DCT channels in use. - * - * Return: - * number of Memory Channels in operation - * Pass back: - * contents of the DCL0_LOW register - */ -static int f1x_early_channel_count(struct amd64_pvt *pvt) -{ - int i, j, channels = 0; - - /* On F10h, if we are in 128 bit mode, then we are using 2 channels */ - if (pvt->fam == 0x10 && (pvt->dclr0 & WIDTH_128)) - return 2; - - /* - * Need to check if in unganged mode: In such, there are 2 channels, - * but they are not in 128 bit mode and thus the above 'dclr0' status - * bit will be OFF. - * - * Need to check DCT0[0] and DCT1[0] to see if only one of them has - * their CSEnable bit on. If so, then SINGLE DIMM case. - */ - edac_dbg(0, "Data width is not 128 bits - need more decoding\n"); - - /* - * Check DRAM Bank Address Mapping values for each DIMM to see if there - * is more than just one DIMM present in unganged mode. Need to check - * both controllers since DIMMs can be placed in either one. - */ - for (i = 0; i < 2; i++) { - u32 dbam = (i ? pvt->dbam1 : pvt->dbam0); - - for (j = 0; j < 4; j++) { - if (DBAM_DIMM(j, dbam) > 0) { - channels++; - break; - } - } - } - - if (channels > 2) - channels = 2; - - amd64_info("MCT channel count: %d\n", channels); - - return channels; -} - -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_each_umc(i) - channels += !!(pvt->umc[i].sdp_ctrl & UMC_SDP_INIT); - - amd64_info("MCT channel count: %d\n", channels); - - return channels; -} - static int ddr3_cs_size(unsigned i, bool dct_width) { unsigned shift = 0; @@ -2191,84 +2026,6 @@ static int f16_dbam_to_chip_select(struct amd64_pvt *pvt, u8 dct, return ddr3_cs_size(cs_mode, false); } -static int f17_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc, - unsigned int cs_mode, int csrow_nr) -{ - u32 addr_mask_orig, addr_mask_deinterleaved; - u32 msb, weight, num_zero_bits; - int cs_mask_nr = csrow_nr; - int dimm, size = 0; - - /* No Chip Selects are enabled. */ - if (!cs_mode) - return size; - - /* Requested size of an even CS but none are enabled. */ - if (!(cs_mode & CS_EVEN) && !(csrow_nr & 1)) - return size; - - /* Requested size of an odd CS but none are enabled. */ - if (!(cs_mode & CS_ODD) && (csrow_nr & 1)) - return size; - - /* - * Family 17h introduced systems with one mask per DIMM, - * and two Chip Selects per DIMM. - * - * CS0 and CS1 -> MASK0 / DIMM0 - * CS2 and CS3 -> MASK1 / DIMM1 - * - * Family 19h Model 10h introduced systems with one mask per Chip Select, - * and two Chip Selects per DIMM. - * - * CS0 -> MASK0 -> DIMM0 - * CS1 -> MASK1 -> DIMM0 - * CS2 -> MASK2 -> DIMM1 - * CS3 -> MASK3 -> DIMM1 - * - * Keep the mask number equal to the Chip Select number for newer systems, - * and shift the mask number for older systems. - */ - dimm = csrow_nr >> 1; - - if (!fam_type->flags.zn_regs_v2) - cs_mask_nr >>= 1; - - /* Asymmetric dual-rank DIMM support. */ - if ((csrow_nr & 1) && (cs_mode & CS_ODD_SECONDARY)) - addr_mask_orig = pvt->csels[umc].csmasks_sec[cs_mask_nr]; - else - addr_mask_orig = pvt->csels[umc].csmasks[cs_mask_nr]; - - /* - * The number of zero bits in the mask is equal to the number of bits - * in a full mask minus the number of bits in the current mask. - * - * The MSB is the number of bits in the full mask because BIT[0] is - * always 0. - * - * In the special 3 Rank interleaving case, a single bit is flipped - * without swapping with the most significant bit. This can be handled - * by keeping the MSB where it is and ignoring the single zero bit. - */ - msb = fls(addr_mask_orig) - 1; - weight = hweight_long(addr_mask_orig); - num_zero_bits = msb - weight - !!(cs_mode & CS_3R_INTERLEAVE); - - /* Take the number of zero bits off from the top of the mask. */ - addr_mask_deinterleaved = GENMASK_ULL(msb - num_zero_bits, 1); - - edac_dbg(1, "CS%d DIMM%d AddrMasks:\n", csrow_nr, dimm); - edac_dbg(1, " Original AddrMask: 0x%x\n", addr_mask_orig); - edac_dbg(1, " Deinterleaved AddrMask: 0x%x\n", addr_mask_deinterleaved); - - /* Register [31:1] = Address [39:9]. Size is in kBs here. */ - size = (addr_mask_deinterleaved >> 2) + 1; - - /* Return size in MBs. */ - return size >> 10; -} - static void read_dram_ctl_register(struct amd64_pvt *pvt) { @@ -2284,15 +2041,15 @@ 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)); } @@ -2792,227 +2549,6 @@ static void f1x_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr, } /* - * debug routine to display the memory sizes of all logical DIMMs and its - * CSROWs - */ -static void debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl) -{ - int dimm, size0, size1; - u32 *dcsb = ctrl ? pvt->csels[1].csbases : pvt->csels[0].csbases; - u32 dbam = ctrl ? pvt->dbam1 : pvt->dbam0; - - if (pvt->fam == 0xf) { - /* K8 families < revF not supported yet */ - if (pvt->ext_model < K8_REV_F) - return; - else - WARN_ON(ctrl != 0); - } - - if (pvt->fam == 0x10) { - dbam = (ctrl && !dct_ganging_enabled(pvt)) ? pvt->dbam1 - : pvt->dbam0; - dcsb = (ctrl && !dct_ganging_enabled(pvt)) ? - pvt->csels[1].csbases : - pvt->csels[0].csbases; - } else if (ctrl) { - dbam = pvt->dbam0; - dcsb = pvt->csels[1].csbases; - } - edac_dbg(1, "F2x%d80 (DRAM Bank Address Mapping): 0x%08x\n", - ctrl, dbam); - - edac_printk(KERN_DEBUG, EDAC_MC, "DCT%d chip selects:\n", ctrl); - - /* Dump memory sizes for DIMM and its CSROWs */ - for (dimm = 0; dimm < 4; dimm++) { - - size0 = 0; - if (dcsb[dimm*2] & DCSB_CS_ENABLE) - /* - * For F15m60h, we need multiplier for LRDIMM cs_size - * calculation. We pass dimm value to the dbam_to_cs - * mapper so we can find the multiplier from the - * corresponding DCSM. - */ - size0 = pvt->ops->dbam_to_cs(pvt, ctrl, - DBAM_DIMM(dimm, dbam), - dimm); - - size1 = 0; - if (dcsb[dimm*2 + 1] & DCSB_CS_ENABLE) - size1 = pvt->ops->dbam_to_cs(pvt, ctrl, - DBAM_DIMM(dimm, dbam), - dimm); - - amd64_info(EDAC_MC ": %d: %5dMB %d: %5dMB\n", - dimm * 2, size0, - dimm * 2 + 1, size1); - } -} - -static struct amd64_family_type family_types[] = { - [K8_CPUS] = { - .ctl_name = "K8", - .f1_id = PCI_DEVICE_ID_AMD_K8_NB_ADDRMAP, - .f2_id = PCI_DEVICE_ID_AMD_K8_NB_MEMCTL, - .max_mcs = 2, - .ops = { - .early_channel_count = k8_early_channel_count, - .map_sysaddr_to_csrow = k8_map_sysaddr_to_csrow, - .dbam_to_cs = k8_dbam_to_chip_select, - } - }, - [F10_CPUS] = { - .ctl_name = "F10h", - .f1_id = PCI_DEVICE_ID_AMD_10H_NB_MAP, - .f2_id = PCI_DEVICE_ID_AMD_10H_NB_DRAM, - .max_mcs = 2, - .ops = { - .early_channel_count = f1x_early_channel_count, - .map_sysaddr_to_csrow = f1x_map_sysaddr_to_csrow, - .dbam_to_cs = f10_dbam_to_chip_select, - } - }, - [F15_CPUS] = { - .ctl_name = "F15h", - .f1_id = PCI_DEVICE_ID_AMD_15H_NB_F1, - .f2_id = PCI_DEVICE_ID_AMD_15H_NB_F2, - .max_mcs = 2, - .ops = { - .early_channel_count = f1x_early_channel_count, - .map_sysaddr_to_csrow = f1x_map_sysaddr_to_csrow, - .dbam_to_cs = f15_dbam_to_chip_select, - } - }, - [F15_M30H_CPUS] = { - .ctl_name = "F15h_M30h", - .f1_id = PCI_DEVICE_ID_AMD_15H_M30H_NB_F1, - .f2_id = PCI_DEVICE_ID_AMD_15H_M30H_NB_F2, - .max_mcs = 2, - .ops = { - .early_channel_count = f1x_early_channel_count, - .map_sysaddr_to_csrow = f1x_map_sysaddr_to_csrow, - .dbam_to_cs = f16_dbam_to_chip_select, - } - }, - [F15_M60H_CPUS] = { - .ctl_name = "F15h_M60h", - .f1_id = PCI_DEVICE_ID_AMD_15H_M60H_NB_F1, - .f2_id = PCI_DEVICE_ID_AMD_15H_M60H_NB_F2, - .max_mcs = 2, - .ops = { - .early_channel_count = f1x_early_channel_count, - .map_sysaddr_to_csrow = f1x_map_sysaddr_to_csrow, - .dbam_to_cs = f15_m60h_dbam_to_chip_select, - } - }, - [F16_CPUS] = { - .ctl_name = "F16h", - .f1_id = PCI_DEVICE_ID_AMD_16H_NB_F1, - .f2_id = PCI_DEVICE_ID_AMD_16H_NB_F2, - .max_mcs = 2, - .ops = { - .early_channel_count = f1x_early_channel_count, - .map_sysaddr_to_csrow = f1x_map_sysaddr_to_csrow, - .dbam_to_cs = f16_dbam_to_chip_select, - } - }, - [F16_M30H_CPUS] = { - .ctl_name = "F16h_M30h", - .f1_id = PCI_DEVICE_ID_AMD_16H_M30H_NB_F1, - .f2_id = PCI_DEVICE_ID_AMD_16H_M30H_NB_F2, - .max_mcs = 2, - .ops = { - .early_channel_count = f1x_early_channel_count, - .map_sysaddr_to_csrow = f1x_map_sysaddr_to_csrow, - .dbam_to_cs = f16_dbam_to_chip_select, - } - }, - [F17_CPUS] = { - .ctl_name = "F17h", - .f0_id = PCI_DEVICE_ID_AMD_17H_DF_F0, - .f6_id = PCI_DEVICE_ID_AMD_17H_DF_F6, - .max_mcs = 2, - .ops = { - .early_channel_count = f17_early_channel_count, - .dbam_to_cs = f17_addr_mask_to_cs_size, - } - }, - [F17_M10H_CPUS] = { - .ctl_name = "F17h_M10h", - .f0_id = PCI_DEVICE_ID_AMD_17H_M10H_DF_F0, - .f6_id = PCI_DEVICE_ID_AMD_17H_M10H_DF_F6, - .max_mcs = 2, - .ops = { - .early_channel_count = f17_early_channel_count, - .dbam_to_cs = f17_addr_mask_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, - .max_mcs = 8, - .ops = { - .early_channel_count = f17_early_channel_count, - .dbam_to_cs = f17_addr_mask_to_cs_size, - } - }, - [F17_M60H_CPUS] = { - .ctl_name = "F17h_M60h", - .f0_id = PCI_DEVICE_ID_AMD_17H_M60H_DF_F0, - .f6_id = PCI_DEVICE_ID_AMD_17H_M60H_DF_F6, - .max_mcs = 2, - .ops = { - .early_channel_count = f17_early_channel_count, - .dbam_to_cs = f17_addr_mask_to_cs_size, - } - }, - [F17_M70H_CPUS] = { - .ctl_name = "F17h_M70h", - .f0_id = PCI_DEVICE_ID_AMD_17H_M70H_DF_F0, - .f6_id = PCI_DEVICE_ID_AMD_17H_M70H_DF_F6, - .max_mcs = 2, - .ops = { - .early_channel_count = f17_early_channel_count, - .dbam_to_cs = f17_addr_mask_to_cs_size, - } - }, - [F19_CPUS] = { - .ctl_name = "F19h", - .f0_id = PCI_DEVICE_ID_AMD_19H_DF_F0, - .f6_id = PCI_DEVICE_ID_AMD_19H_DF_F6, - .max_mcs = 8, - .ops = { - .early_channel_count = f17_early_channel_count, - .dbam_to_cs = f17_addr_mask_to_cs_size, - } - }, - [F19_M10H_CPUS] = { - .ctl_name = "F19h_M10h", - .f0_id = PCI_DEVICE_ID_AMD_19H_M10H_DF_F0, - .f6_id = PCI_DEVICE_ID_AMD_19H_M10H_DF_F6, - .max_mcs = 12, - .flags.zn_regs_v2 = 1, - .ops = { - .early_channel_count = f17_early_channel_count, - .dbam_to_cs = f17_addr_mask_to_cs_size, - } - }, - [F19_M50H_CPUS] = { - .ctl_name = "F19h_M50h", - .f0_id = PCI_DEVICE_ID_AMD_19H_M50H_DF_F0, - .f6_id = PCI_DEVICE_ID_AMD_19H_M50H_DF_F6, - .max_mcs = 2, - .ops = { - .early_channel_count = f17_early_channel_count, - .dbam_to_cs = f17_addr_mask_to_cs_size, - } - }, -}; - -/* * These are tables of eigenvectors (one per line) which can be used for the * construction of the syndrome tables. The modified syndrome search algorithm * uses those to find the symbol in error and thus the DIMM. @@ -3259,19 +2795,26 @@ static inline void decode_bus_error(int node_id, struct mce *m) * 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. + * + * For DRAM ECC errors, the Chip Select number is given in bits [2:0] of + * the MCA_SYND[ErrorInformation] field. */ -static int find_umc_channel(struct mce *m) +static void umc_get_err_info(struct mce *m, struct err_info *err) { - return (m->ipid & GENMASK(31, 0)) >> 20; + err->channel = (m->ipid & GENMASK(31, 0)) >> 20; + err->csrow = m->synd & 0x7; } 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); mci = edac_mc_find(node_id); if (!mci) @@ -3284,8 +2827,6 @@ 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(m); - if (!(m->status & MCI_STATUS_SYNDV)) { err.err_code = ERR_SYND; goto log_error; @@ -3300,9 +2841,14 @@ static void decode_umc_error(int node_id, struct mce *m) err.err_code = ERR_CHANNEL; } - err.csrow = m->synd & 0x7; + pvt->ops->get_err_info(m, &err); + + a_err.addr = m->addr; + a_err.ipid = m->ipid; + a_err.cpu = m->extcpu; - if (umc_normaddr_to_sysaddr(m->addr, pvt->mc_node_id, err.channel, &sys_addr)) { + 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; } @@ -3316,37 +2862,10 @@ log_error: /* * Use pvt->F3 which contains the F3 CPU PCI device to get the related * F1 (AddrMap) and F2 (Dct) devices. Return negative value on error. - * Reserve F0 and F6 on systems with a UMC. */ static int reserve_mc_sibling_devs(struct amd64_pvt *pvt, u16 pci_id1, u16 pci_id2) { - if (pvt->umc) { - pvt->F0 = pci_get_related_function(pvt->F3->vendor, pci_id1, pvt->F3); - if (!pvt->F0) { - edac_dbg(1, "F0 not found, device 0x%x\n", pci_id1); - return -ENODEV; - } - - pvt->F6 = pci_get_related_function(pvt->F3->vendor, pci_id2, pvt->F3); - if (!pvt->F6) { - pci_dev_put(pvt->F0); - pvt->F0 = NULL; - - edac_dbg(1, "F6 not found: device 0x%x\n", pci_id2); - return -ENODEV; - } - - if (!pci_ctl_dev) - pci_ctl_dev = &pvt->F0->dev; - - edac_dbg(1, "F0: %s\n", pci_name(pvt->F0)); - edac_dbg(1, "F3: %s\n", pci_name(pvt->F3)); - edac_dbg(1, "F6: %s\n", pci_name(pvt->F6)); - - return 0; - } - /* Reserve the ADDRESS MAP Device */ pvt->F1 = pci_get_related_function(pvt->F3->vendor, pci_id1, pvt->F3); if (!pvt->F1) { @@ -3374,37 +2893,11 @@ reserve_mc_sibling_devs(struct amd64_pvt *pvt, u16 pci_id1, u16 pci_id2) return 0; } -static void free_mc_sibling_devs(struct amd64_pvt *pvt) -{ - if (pvt->umc) { - pci_dev_put(pvt->F0); - pci_dev_put(pvt->F6); - } else { - pci_dev_put(pvt->F1); - pci_dev_put(pvt->F2); - } -} - static void determine_ecc_sym_sz(struct amd64_pvt *pvt) { pvt->ecc_sym_sz = 4; - if (pvt->umc) { - u8 i; - - for_each_umc(i) { - /* Check enabled channels only: */ - 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; - return; - } - } - } - } else if (pvt->fam >= 0x10) { + if (pvt->fam >= 0x10) { u32 tmp; amd64_read_pci_cfg(pvt->F3, EXT_NB_MCA_CFG, &tmp); @@ -3421,11 +2914,11 @@ static void determine_ecc_sym_sz(struct amd64_pvt *pvt) /* * Retrieve the hardware registers of the memory controller. */ -static void __read_mc_regs_df(struct amd64_pvt *pvt) +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) { @@ -3433,11 +2926,20 @@ static void __read_mc_regs_df(struct amd64_pvt *pvt) umc_base = get_umc_base(i); umc = &pvt->umc[i]; - amd_smn_read(nid, umc_base + get_umc_reg(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; } } @@ -3445,7 +2947,7 @@ static void __read_mc_regs_df(struct amd64_pvt *pvt) * Retrieve the hardware registers of the memory controller (this includes the * 'Address Map' and 'Misc' device regs) */ -static void read_mc_regs(struct amd64_pvt *pvt) +static void dct_read_mc_regs(struct amd64_pvt *pvt) { unsigned int range; u64 msr_val; @@ -3454,25 +2956,18 @@ static void 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"); } - if (pvt->umc) { - __read_mc_regs_df(pvt); - amd64_read_pci_cfg(pvt->F0, DF_DHAR, &pvt->dhar); - - goto skip; - } - amd64_read_pci_cfg(pvt->F3, NBCAP, &pvt->nbcap); read_dram_ctl_register(pvt); @@ -3513,14 +3008,6 @@ static void read_mc_regs(struct amd64_pvt *pvt) amd64_read_dct_pci_cfg(pvt, 1, DCHR0, &pvt->dchr1); } -skip: - read_dct_base_mask(pvt); - - determine_memory_type(pvt); - - if (!pvt->umc) - edac_dbg(1, " DIMM type: %s\n", edac_mem_types[pvt->dram_type]); - determine_ecc_sym_sz(pvt); } @@ -3558,36 +3045,47 @@ skip: * encompasses * */ -static u32 get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr_orig) +static u32 dct_get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr) { u32 dbam = dct ? pvt->dbam1 : pvt->dbam0; - int csrow_nr = csrow_nr_orig; u32 cs_mode, nr_pages; - if (!pvt->umc) { - csrow_nr >>= 1; - cs_mode = DBAM_DIMM(csrow_nr, dbam); - } else { - cs_mode = f17_get_cs_mode(csrow_nr >> 1, dct, pvt); - } + csrow_nr >>= 1; + cs_mode = DBAM_DIMM(csrow_nr, dbam); nr_pages = pvt->ops->dbam_to_cs(pvt, dct, cs_mode, csrow_nr); nr_pages <<= 20 - PAGE_SHIFT; edac_dbg(0, "csrow: %d, channel: %d, DBAM idx: %d\n", - csrow_nr_orig, dct, cs_mode); + csrow_nr, dct, cs_mode); edac_dbg(0, "nr_pages/channel: %u\n", nr_pages); return nr_pages; } -static int init_csrows_df(struct mem_ctl_info *mci) +static u32 umc_get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr_orig) +{ + int csrow_nr = csrow_nr_orig; + u32 cs_mode, nr_pages; + + cs_mode = umc_get_cs_mode(csrow_nr >> 1, dct, pvt); + + nr_pages = umc_addr_mask_to_cs_size(pvt, dct, cs_mode, csrow_nr); + nr_pages <<= 20 - PAGE_SHIFT; + + edac_dbg(0, "csrow: %d, channel: %d, cs_mode %d\n", + csrow_nr_orig, dct, cs_mode); + edac_dbg(0, "nr_pages/channel: %u\n", nr_pages); + + return nr_pages; +} + +static void umc_init_csrows(struct mem_ctl_info *mci) { struct amd64_pvt *pvt = mci->pvt_info; enum edac_type edac_mode = EDAC_NONE; enum dev_type dev_type = DEV_UNKNOWN; struct dimm_info *dimm; - int empty = 1; u8 umc, cs; if (mci->edac_ctl_cap & EDAC_FLAG_S16ECD16ED) { @@ -3608,40 +3106,34 @@ static int init_csrows_df(struct mem_ctl_info *mci) if (!csrow_enabled(cs, umc, pvt)) continue; - empty = 0; dimm = mci->csrows[cs]->channels[umc]->dimm; edac_dbg(1, "MC node: %d, csrow: %d\n", pvt->mc_node_id, cs); - dimm->nr_pages = get_csrow_nr_pages(pvt, umc, cs); + dimm->nr_pages = umc_get_csrow_nr_pages(pvt, umc, cs); dimm->mtype = pvt->umc[umc].dram_type; dimm->edac_mode = edac_mode; dimm->dtype = dev_type; dimm->grain = 64; } } - - return empty; } /* * Initialize the array of csrow attribute instances, based on the values * from pci config hardware registers. */ -static int init_csrows(struct mem_ctl_info *mci) +static void dct_init_csrows(struct mem_ctl_info *mci) { struct amd64_pvt *pvt = mci->pvt_info; enum edac_type edac_mode = EDAC_NONE; struct csrow_info *csrow; struct dimm_info *dimm; - int i, j, empty = 1; int nr_pages = 0; + int i, j; u32 val; - if (pvt->umc) - return init_csrows_df(mci); - amd64_read_pci_cfg(pvt->F3, NBCFG, &val); pvt->nbcfg = val; @@ -3664,19 +3156,18 @@ static int init_csrows(struct mem_ctl_info *mci) continue; csrow = mci->csrows[i]; - empty = 0; edac_dbg(1, "MC node: %d, csrow: %d\n", pvt->mc_node_id, i); if (row_dct0) { - nr_pages = get_csrow_nr_pages(pvt, 0, i); + nr_pages = dct_get_csrow_nr_pages(pvt, 0, i); csrow->channels[0]->dimm->nr_pages = nr_pages; } /* K8 has only one DCT */ if (pvt->fam != 0xf && row_dct1) { - int row_dct1_pages = get_csrow_nr_pages(pvt, 1, i); + int row_dct1_pages = dct_get_csrow_nr_pages(pvt, 1, i); csrow->channels[1]->dimm->nr_pages = row_dct1_pages; nr_pages += row_dct1_pages; @@ -3691,15 +3182,13 @@ static int init_csrows(struct mem_ctl_info *mci) : EDAC_SECDED; } - for (j = 0; j < pvt->channel_count; j++) { + for (j = 0; j < pvt->max_mcs; j++) { dimm = csrow->channels[j]->dimm; dimm->mtype = pvt->dram_type; dimm->edac_mode = edac_mode; dimm->grain = 64; } } - - return empty; } /* get all cores on this DCT */ @@ -3708,7 +3197,7 @@ 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); } @@ -3733,8 +3222,7 @@ 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; @@ -3862,59 +3350,51 @@ static void restore_ecc_error_reporting(struct ecc_settings *s, u16 nid, amd64_warn("Error restoring NB MCGCTL settings!\n"); } -static bool ecc_enabled(struct amd64_pvt *pvt) +static bool dct_ecc_enabled(struct amd64_pvt *pvt) { u16 nid = pvt->mc_node_id; bool nb_mce_en = false; - u8 ecc_en = 0, i; + u8 ecc_en = 0; u32 value; - if (boot_cpu_data.x86 >= 0x17) { - u8 umc_en_mask = 0, ecc_en_mask = 0; - struct amd64_umc *umc; - - for_each_umc(i) { - umc = &pvt->umc[i]; + amd64_read_pci_cfg(pvt->F3, NBCFG, &value); - /* Only check enabled UMCs. */ - if (!(umc->sdp_ctrl & UMC_SDP_INIT)) - continue; + ecc_en = !!(value & NBCFG_ECC_ENABLE); - umc_en_mask |= BIT(i); + nb_mce_en = nb_mce_bank_enabled_on_node(nid); + if (!nb_mce_en) + edac_dbg(0, "NB MCE bank disabled, set MSR 0x%08x[4] on node %d to enable.\n", + MSR_IA32_MCG_CTL, nid); - if (umc->umc_cap_hi & UMC_ECC_ENABLED) - ecc_en_mask |= BIT(i); - } + edac_dbg(3, "Node %d: DRAM ECC %s.\n", nid, str_enabled_disabled(ecc_en)); - /* 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); + return ecc_en && nb_mce_en; +} - /* Assume UMC MCA banks are enabled. */ - nb_mce_en = true; - } else { - amd64_read_pci_cfg(pvt->F3, NBCFG, &value); +static bool umc_ecc_enabled(struct amd64_pvt *pvt) +{ + struct amd64_umc *umc; + bool ecc_en = false; + int i; - ecc_en = !!(value & NBCFG_ECC_ENABLE); + /* Check whether at least one UMC is enabled: */ + for_each_umc(i) { + umc = &pvt->umc[i]; - nb_mce_en = nb_mce_bank_enabled_on_node(nid); - if (!nb_mce_en) - edac_dbg(0, "NB MCE bank disabled, set MSR 0x%08x[4] on node %d to enable.\n", - MSR_IA32_MCG_CTL, nid); + if (umc->sdp_ctrl & UMC_SDP_INIT && + umc->umc_cap_hi & UMC_ECC_ENABLED) { + ecc_en = true; + break; + } } - edac_dbg(3, "Node %d: DRAM ECC %s.\n", nid, (ecc_en ? "enabled" : "disabled")); + edac_dbg(3, "Node %d: DRAM ECC %s.\n", pvt->mc_node_id, str_enabled_disabled(ecc_en)); - if (!ecc_en || !nb_mce_en) - return false; - else - return true; + return ecc_en; } static inline void -f17h_determine_edac_ctl_cap(struct mem_ctl_info *mci, struct amd64_pvt *pvt) +umc_determine_edac_ctl_cap(struct mem_ctl_info *mci, struct amd64_pvt *pvt) { u8 i, ecc_en = 1, cpk_en = 1, dev_x4 = 1, dev_x16 = 1; @@ -3944,142 +3424,503 @@ f17h_determine_edac_ctl_cap(struct mem_ctl_info *mci, struct amd64_pvt *pvt) } } -static void setup_mci_misc_attrs(struct mem_ctl_info *mci) +static void dct_setup_mci_misc_attrs(struct mem_ctl_info *mci) { struct amd64_pvt *pvt = mci->pvt_info; mci->mtype_cap = MEM_FLAG_DDR2 | MEM_FLAG_RDDR2; mci->edac_ctl_cap = EDAC_FLAG_NONE; - if (pvt->umc) { - f17h_determine_edac_ctl_cap(mci, pvt); - } else { - if (pvt->nbcap & NBCAP_SECDED) - mci->edac_ctl_cap |= EDAC_FLAG_SECDED; + if (pvt->nbcap & NBCAP_SECDED) + mci->edac_ctl_cap |= EDAC_FLAG_SECDED; - if (pvt->nbcap & NBCAP_CHIPKILL) - mci->edac_ctl_cap |= EDAC_FLAG_S4ECD4ED; - } + if (pvt->nbcap & NBCAP_CHIPKILL) + mci->edac_ctl_cap |= EDAC_FLAG_S4ECD4ED; - mci->edac_cap = determine_edac_cap(pvt); + mci->edac_cap = dct_determine_edac_cap(pvt); mci->mod_name = EDAC_MOD_STR; - mci->ctl_name = fam_type->ctl_name; + mci->ctl_name = pvt->ctl_name; mci->dev_name = pci_name(pvt->F3); mci->ctl_page_to_phys = NULL; /* memory scrubber interface */ mci->set_sdram_scrub_rate = set_scrub_rate; mci->get_sdram_scrub_rate = get_scrub_rate; + + dct_init_csrows(mci); +} + +static void umc_setup_mci_misc_attrs(struct mem_ctl_info *mci) +{ + struct amd64_pvt *pvt = mci->pvt_info; + + mci->mtype_cap = MEM_FLAG_DDR4 | MEM_FLAG_RDDR4; + mci->edac_ctl_cap = EDAC_FLAG_NONE; + + umc_determine_edac_ctl_cap(mci, pvt); + + mci->edac_cap = umc_determine_edac_cap(pvt); + mci->mod_name = EDAC_MOD_STR; + mci->ctl_name = pvt->ctl_name; + mci->dev_name = pci_name(pvt->F3); + mci->ctl_page_to_phys = NULL; + + umc_init_csrows(mci); +} + +static int dct_hw_info_get(struct amd64_pvt *pvt) +{ + int ret = reserve_mc_sibling_devs(pvt, pvt->f1_id, pvt->f2_id); + + if (ret) + return ret; + + dct_prep_chip_selects(pvt); + dct_read_base_mask(pvt); + dct_read_mc_regs(pvt); + dct_determine_memory_type(pvt); + + return 0; +} + +static int umc_hw_info_get(struct amd64_pvt *pvt) +{ + pvt->umc = kcalloc(pvt->max_mcs, sizeof(struct amd64_umc), GFP_KERNEL); + if (!pvt->umc) + return -ENOMEM; + + umc_prep_chip_selects(pvt); + umc_read_base_mask(pvt); + umc_read_mc_regs(pvt); + umc_determine_memory_type(pvt); + + return 0; } /* - * returns a pointer to the family descriptor on success, NULL otherwise. + * The CPUs have one channel per UMC, so UMC number is equivalent to a + * channel number. The GPUs have 8 channels per UMC, so the UMC number no + * longer works as a channel number. + * + * The channel number within a GPU UMC is given in MCA_IPID[15:12]. + * However, the IDs are split such that two UMC values go to one UMC, and + * the channel numbers are split in two groups of four. + * + * Refer to comment on gpu_get_umc_base(). + * + * For example, + * UMC0 CH[3:0] = 0x0005[3:0]000 + * UMC0 CH[7:4] = 0x0015[3:0]000 + * UMC1 CH[3:0] = 0x0025[3:0]000 + * UMC1 CH[7:4] = 0x0035[3:0]000 */ -static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt) +static void gpu_get_err_info(struct mce *m, struct err_info *err) +{ + u8 ch = (m->ipid & GENMASK(31, 0)) >> 20; + u8 phy = ((m->ipid >> 12) & 0xf); + + err->channel = ch % 2 ? phy + 4 : phy; + err->csrow = phy; +} + +static int gpu_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc, + unsigned int cs_mode, int csrow_nr) +{ + u32 addr_mask = pvt->csels[umc].csmasks[csrow_nr]; + u32 addr_mask_sec = pvt->csels[umc].csmasks_sec[csrow_nr]; + + return __addr_mask_to_cs_size(addr_mask, addr_mask_sec, cs_mode, csrow_nr, csrow_nr >> 1); +} + +static void gpu_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl) +{ + int size, cs_mode, cs = 0; + + edac_printk(KERN_DEBUG, EDAC_MC, "UMC%d chip selects:\n", ctrl); + + cs_mode = CS_EVEN_PRIMARY | CS_ODD_PRIMARY; + + for_each_chip_select(cs, ctrl, pvt) { + size = gpu_addr_mask_to_cs_size(pvt, ctrl, cs_mode, cs); + amd64_info(EDAC_MC ": %d: %5dMB\n", cs, size); + } +} + +static void gpu_dump_misc_regs(struct amd64_pvt *pvt) +{ + struct amd64_umc *umc; + u32 i; + + for_each_umc(i) { + umc = &pvt->umc[i]; + + 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); + edac_dbg(1, "UMC%d All HBMs support ECC: yes\n", i); + + gpu_debug_display_dimm_sizes(pvt, i); + } +} + +static u32 gpu_get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr) +{ + u32 nr_pages; + int cs_mode = CS_EVEN_PRIMARY | CS_ODD_PRIMARY; + + nr_pages = gpu_addr_mask_to_cs_size(pvt, dct, cs_mode, csrow_nr); + nr_pages <<= 20 - PAGE_SHIFT; + + edac_dbg(0, "csrow: %d, channel: %d\n", csrow_nr, dct); + edac_dbg(0, "nr_pages/channel: %u\n", nr_pages); + + return nr_pages; +} + +static void gpu_init_csrows(struct mem_ctl_info *mci) +{ + struct amd64_pvt *pvt = mci->pvt_info; + struct dimm_info *dimm; + u8 umc, cs; + + for_each_umc(umc) { + for_each_chip_select(cs, umc, pvt) { + if (!csrow_enabled(cs, umc, pvt)) + continue; + + dimm = mci->csrows[umc]->channels[cs]->dimm; + + edac_dbg(1, "MC node: %d, csrow: %d\n", + pvt->mc_node_id, cs); + + dimm->nr_pages = gpu_get_csrow_nr_pages(pvt, umc, cs); + dimm->edac_mode = EDAC_SECDED; + dimm->mtype = pvt->dram_type; + dimm->dtype = DEV_X16; + dimm->grain = 64; + } + } +} + +static void gpu_setup_mci_misc_attrs(struct mem_ctl_info *mci) +{ + struct amd64_pvt *pvt = mci->pvt_info; + + mci->mtype_cap = MEM_FLAG_HBM2; + mci->edac_ctl_cap = EDAC_FLAG_SECDED; + + mci->edac_cap = EDAC_FLAG_EC; + mci->mod_name = EDAC_MOD_STR; + mci->ctl_name = pvt->ctl_name; + mci->dev_name = pci_name(pvt->F3); + mci->ctl_page_to_phys = NULL; + + gpu_init_csrows(mci); +} + +/* ECC is enabled by default on GPU nodes */ +static bool gpu_ecc_enabled(struct amd64_pvt *pvt) +{ + return true; +} + +static inline u32 gpu_get_umc_base(struct amd64_pvt *pvt, u8 umc, u8 channel) +{ + /* + * On CPUs, there is one channel per UMC, so UMC numbering equals + * channel numbering. On GPUs, there are eight channels per UMC, + * so the channel numbering is different from UMC numbering. + * + * On CPU nodes channels are selected in 6th nibble + * UMC chY[3:0]= [(chY*2 + 1) : (chY*2)]50000; + * + * On GPU nodes channels are selected in 3rd nibble + * HBM chX[3:0]= [Y ]5X[3:0]000; + * HBM chX[7:4]= [Y+1]5X[3:0]000 + * + * On MI300 APU nodes, same as GPU nodes but channels are selected + * in the base address of 0x90000 + */ + umc *= 2; + + if (channel >= 4) + umc++; + + return pvt->gpu_umc_base + (umc << 20) + ((channel % 4) << 12); +} + +static void gpu_read_mc_regs(struct amd64_pvt *pvt) +{ + u8 nid = pvt->mc_node_id; + struct amd64_umc *umc; + 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]; + + 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; + } +} + +static void gpu_read_base_mask(struct amd64_pvt *pvt) +{ + u32 base_reg, mask_reg; + u32 *base, *mask; + int umc, cs; + + for_each_umc(umc) { + for_each_chip_select(cs, umc, pvt) { + base_reg = gpu_get_umc_base(pvt, umc, cs) + UMCCH_BASE_ADDR; + base = &pvt->csels[umc].csbases[cs]; + + if (!amd_smn_read(pvt->mc_node_id, base_reg, base)) { + edac_dbg(0, " DCSB%d[%d]=0x%08x reg: 0x%x\n", + umc, cs, *base, base_reg); + } + + mask_reg = gpu_get_umc_base(pvt, umc, cs) + UMCCH_ADDR_MASK; + mask = &pvt->csels[umc].csmasks[cs]; + + if (!amd_smn_read(pvt->mc_node_id, mask_reg, mask)) { + edac_dbg(0, " DCSM%d[%d]=0x%08x reg: 0x%x\n", + umc, cs, *mask, mask_reg); + } + } + } +} + +static void gpu_prep_chip_selects(struct amd64_pvt *pvt) +{ + int umc; + + for_each_umc(umc) { + pvt->csels[umc].b_cnt = 8; + pvt->csels[umc].m_cnt = 8; + } +} + +static int gpu_hw_info_get(struct amd64_pvt *pvt) +{ + int ret; + + ret = gpu_get_node_map(pvt); + if (ret) + return ret; + + pvt->umc = kcalloc(pvt->max_mcs, sizeof(struct amd64_umc), GFP_KERNEL); + if (!pvt->umc) + return -ENOMEM; + + gpu_prep_chip_selects(pvt); + gpu_read_base_mask(pvt); + gpu_read_mc_regs(pvt); + + return 0; +} + +static void hw_info_put(struct amd64_pvt *pvt) +{ + pci_dev_put(pvt->F1); + pci_dev_put(pvt->F2); + kfree(pvt->umc); + kfree(pvt->csels); +} + +static struct low_ops umc_ops = { + .hw_info_get = umc_hw_info_get, + .ecc_enabled = umc_ecc_enabled, + .setup_mci_misc_attrs = umc_setup_mci_misc_attrs, + .dump_misc_regs = umc_dump_misc_regs, + .get_err_info = umc_get_err_info, +}; + +static struct low_ops gpu_ops = { + .hw_info_get = gpu_hw_info_get, + .ecc_enabled = gpu_ecc_enabled, + .setup_mci_misc_attrs = gpu_setup_mci_misc_attrs, + .dump_misc_regs = gpu_dump_misc_regs, + .get_err_info = gpu_get_err_info, +}; + +/* Use Family 16h versions for defaults and adjust as needed below. */ +static struct low_ops dct_ops = { + .map_sysaddr_to_csrow = f1x_map_sysaddr_to_csrow, + .dbam_to_cs = f16_dbam_to_chip_select, + .hw_info_get = dct_hw_info_get, + .ecc_enabled = dct_ecc_enabled, + .setup_mci_misc_attrs = dct_setup_mci_misc_attrs, + .dump_misc_regs = dct_dump_misc_regs, +}; + +static int per_family_init(struct amd64_pvt *pvt) { pvt->ext_model = boot_cpu_data.x86_model >> 4; pvt->stepping = boot_cpu_data.x86_stepping; pvt->model = boot_cpu_data.x86_model; pvt->fam = boot_cpu_data.x86; + char *tmp_name = NULL; + pvt->max_mcs = 2; + + /* + * Decide on which ops group to use here and do any family/model + * overrides below. + */ + if (pvt->fam >= 0x17) + pvt->ops = &umc_ops; + else + pvt->ops = &dct_ops; switch (pvt->fam) { case 0xf: - fam_type = &family_types[K8_CPUS]; - pvt->ops = &family_types[K8_CPUS].ops; + tmp_name = (pvt->ext_model >= K8_REV_F) ? + "K8 revF or later" : "K8 revE or earlier"; + pvt->f1_id = PCI_DEVICE_ID_AMD_K8_NB_ADDRMAP; + pvt->f2_id = PCI_DEVICE_ID_AMD_K8_NB_MEMCTL; + pvt->ops->map_sysaddr_to_csrow = k8_map_sysaddr_to_csrow; + pvt->ops->dbam_to_cs = k8_dbam_to_chip_select; break; case 0x10: - fam_type = &family_types[F10_CPUS]; - pvt->ops = &family_types[F10_CPUS].ops; + pvt->f1_id = PCI_DEVICE_ID_AMD_10H_NB_MAP; + pvt->f2_id = PCI_DEVICE_ID_AMD_10H_NB_DRAM; + pvt->ops->dbam_to_cs = f10_dbam_to_chip_select; break; case 0x15: - if (pvt->model == 0x30) { - fam_type = &family_types[F15_M30H_CPUS]; - pvt->ops = &family_types[F15_M30H_CPUS].ops; + switch (pvt->model) { + case 0x30: + pvt->f1_id = PCI_DEVICE_ID_AMD_15H_M30H_NB_F1; + pvt->f2_id = PCI_DEVICE_ID_AMD_15H_M30H_NB_F2; break; - } else if (pvt->model == 0x60) { - fam_type = &family_types[F15_M60H_CPUS]; - pvt->ops = &family_types[F15_M60H_CPUS].ops; + case 0x60: + pvt->f1_id = PCI_DEVICE_ID_AMD_15H_M60H_NB_F1; + pvt->f2_id = PCI_DEVICE_ID_AMD_15H_M60H_NB_F2; + pvt->ops->dbam_to_cs = f15_m60h_dbam_to_chip_select; + break; + case 0x13: + /* Richland is only client */ + return -ENODEV; + default: + pvt->f1_id = PCI_DEVICE_ID_AMD_15H_NB_F1; + pvt->f2_id = PCI_DEVICE_ID_AMD_15H_NB_F2; + pvt->ops->dbam_to_cs = f15_dbam_to_chip_select; break; - /* Richland is only client */ - } else if (pvt->model == 0x13) { - return NULL; - } else { - fam_type = &family_types[F15_CPUS]; - pvt->ops = &family_types[F15_CPUS].ops; } break; case 0x16: - if (pvt->model == 0x30) { - fam_type = &family_types[F16_M30H_CPUS]; - pvt->ops = &family_types[F16_M30H_CPUS].ops; + switch (pvt->model) { + case 0x30: + pvt->f1_id = PCI_DEVICE_ID_AMD_16H_M30H_NB_F1; + pvt->f2_id = PCI_DEVICE_ID_AMD_16H_M30H_NB_F2; + break; + default: + pvt->f1_id = PCI_DEVICE_ID_AMD_16H_NB_F1; + pvt->f2_id = PCI_DEVICE_ID_AMD_16H_NB_F2; break; } - fam_type = &family_types[F16_CPUS]; - pvt->ops = &family_types[F16_CPUS].ops; break; case 0x17: - if (pvt->model >= 0x10 && pvt->model <= 0x2f) { - fam_type = &family_types[F17_M10H_CPUS]; - pvt->ops = &family_types[F17_M10H_CPUS].ops; + switch (pvt->model) { + case 0x30 ... 0x3f: + pvt->max_mcs = 8; 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; - } else if (pvt->model >= 0x60 && pvt->model <= 0x6f) { - fam_type = &family_types[F17_M60H_CPUS]; - pvt->ops = &family_types[F17_M60H_CPUS].ops; - break; - } else if (pvt->model >= 0x70 && pvt->model <= 0x7f) { - fam_type = &family_types[F17_M70H_CPUS]; - pvt->ops = &family_types[F17_M70H_CPUS].ops; + default: break; } - fallthrough; - case 0x18: - fam_type = &family_types[F17_CPUS]; - pvt->ops = &family_types[F17_CPUS].ops; + break; - if (pvt->fam == 0x18) - family_types[F17_CPUS].ctl_name = "F18h"; + case 0x18: break; case 0x19: - if (pvt->model >= 0x10 && pvt->model <= 0x1f) { - fam_type = &family_types[F19_M10H_CPUS]; - pvt->ops = &family_types[F19_M10H_CPUS].ops; + switch (pvt->model) { + case 0x00 ... 0x0f: + pvt->max_mcs = 8; + break; + case 0x10 ... 0x1f: + pvt->max_mcs = 12; + pvt->flags.zn_regs_v2 = 1; + break; + case 0x30 ... 0x3f: + if (pvt->F3->device == PCI_DEVICE_ID_AMD_MI200_DF_F3) { + tmp_name = "MI200"; + pvt->max_mcs = 4; + pvt->dram_type = MEM_HBM2; + pvt->gpu_umc_base = 0x50000; + pvt->ops = &gpu_ops; + } else { + pvt->max_mcs = 8; + } + break; + case 0x60 ... 0x6f: + pvt->flags.zn_regs_v2 = 1; + break; + case 0x70 ... 0x7f: + pvt->max_mcs = 4; + pvt->flags.zn_regs_v2 = 1; + break; + case 0x90 ... 0x9f: + pvt->max_mcs = 4; + pvt->dram_type = MEM_HBM3; + pvt->gpu_umc_base = 0x90000; + pvt->ops = &gpu_ops; + break; + case 0xa0 ... 0xaf: + pvt->max_mcs = 12; + pvt->flags.zn_regs_v2 = 1; + break; + } + break; + + case 0x1A: + switch (pvt->model) { + case 0x00 ... 0x1f: + pvt->max_mcs = 12; + pvt->flags.zn_regs_v2 = 1; break; - } else if (pvt->model >= 0x20 && pvt->model <= 0x2f) { - fam_type = &family_types[F17_M70H_CPUS]; - pvt->ops = &family_types[F17_M70H_CPUS].ops; - fam_type->ctl_name = "F19h_M20h"; + case 0x40 ... 0x4f: + pvt->flags.zn_regs_v2 = 1; break; - } else if (pvt->model >= 0x50 && pvt->model <= 0x5f) { - fam_type = &family_types[F19_M50H_CPUS]; - pvt->ops = &family_types[F19_M50H_CPUS].ops; - fam_type->ctl_name = "F19h_M50h"; + case 0x50 ... 0x57: + case 0xc0 ... 0xc7: + pvt->max_mcs = 16; + pvt->flags.zn_regs_v2 = 1; break; - } else if (pvt->model >= 0xa0 && pvt->model <= 0xaf) { - fam_type = &family_types[F19_M10H_CPUS]; - pvt->ops = &family_types[F19_M10H_CPUS].ops; - fam_type->ctl_name = "F19h_MA0h"; + case 0x90 ... 0x9f: + case 0xa0 ... 0xaf: + pvt->max_mcs = 8; + pvt->flags.zn_regs_v2 = 1; break; } - fam_type = &family_types[F19_CPUS]; - pvt->ops = &family_types[F19_CPUS].ops; - family_types[F19_CPUS].ctl_name = "F19h"; break; default: amd64_err("Unsupported family!\n"); - return NULL; + return -ENODEV; } - return fam_type; + if (tmp_name) + scnprintf(pvt->ctl_name, sizeof(pvt->ctl_name), tmp_name); + else + scnprintf(pvt->ctl_name, sizeof(pvt->ctl_name), "F%02Xh_M%02Xh", + pvt->fam, pvt->model); + + pvt->csels = kcalloc(pvt->max_mcs, sizeof(*pvt->csels), GFP_KERNEL); + if (!pvt->csels) + return -ENOMEM; + + return 0; } static const struct attribute_group *amd64_edac_attr_groups[] = { @@ -4090,67 +3931,33 @@ static const struct attribute_group *amd64_edac_attr_groups[] = { NULL }; -static int hw_info_get(struct amd64_pvt *pvt) -{ - u16 pci_id1, pci_id2; - int ret; - - if (pvt->fam >= 0x17) { - pvt->umc = kcalloc(fam_type->max_mcs, sizeof(struct amd64_umc), GFP_KERNEL); - if (!pvt->umc) - return -ENOMEM; - - pci_id1 = fam_type->f0_id; - pci_id2 = fam_type->f6_id; - } else { - pci_id1 = fam_type->f1_id; - pci_id2 = fam_type->f2_id; - } - - ret = reserve_mc_sibling_devs(pvt, pci_id1, pci_id2); - if (ret) - return ret; - - read_mc_regs(pvt); - - return 0; -} - -static void hw_info_put(struct amd64_pvt *pvt) +/* + * For heterogeneous and APU models EDAC CHIP_SELECT and CHANNEL layers + * should be swapped to fit into the layers. + */ +static unsigned int get_layer_size(struct amd64_pvt *pvt, u8 layer) { - if (pvt->F0 || pvt->F1) - free_mc_sibling_devs(pvt); + bool is_gpu = (pvt->ops == &gpu_ops); - kfree(pvt->umc); + if (!layer) + return is_gpu ? pvt->max_mcs + : pvt->csels[0].b_cnt; + else + return is_gpu ? pvt->csels[0].b_cnt + : pvt->max_mcs; } static int init_one_instance(struct amd64_pvt *pvt) { struct mem_ctl_info *mci = NULL; struct edac_mc_layer layers[2]; - int ret = -EINVAL; - - /* - * We need to determine how many memory channels there are. Then use - * that information for calculating the size of the dynamic instance - * tables in the 'mci' structure. - */ - pvt->channel_count = pvt->ops->early_channel_count(pvt); - if (pvt->channel_count < 0) - return ret; + int ret = -ENOMEM; - ret = -ENOMEM; layers[0].type = EDAC_MC_LAYER_CHIP_SELECT; - layers[0].size = pvt->csels[0].b_cnt; + layers[0].size = get_layer_size(pvt, 0); layers[0].is_virt_csrow = true; layers[1].type = EDAC_MC_LAYER_CHANNEL; - - /* - * 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. - */ - layers[1].size = fam_type->max_mcs; + layers[1].size = get_layer_size(pvt, 1); layers[1].is_virt_csrow = false; mci = edac_mc_alloc(pvt->mc_node_id, ARRAY_SIZE(layers), layers, 0); @@ -4160,10 +3967,7 @@ static int init_one_instance(struct amd64_pvt *pvt) mci->pvt_info = pvt; mci->pdev = &pvt->F3->dev; - setup_mci_misc_attrs(mci); - - if (init_csrows(mci)) - mci->edac_cap = EDAC_FLAG_NONE; + pvt->ops->setup_mci_misc_attrs(mci); ret = -ENODEV; if (edac_mc_add_mc_with_groups(mci, amd64_edac_attr_groups)) { @@ -4180,7 +3984,7 @@ static bool instance_has_memory(struct amd64_pvt *pvt) bool cs_enabled = false; int cs = 0, dct = 0; - for (dct = 0; dct < fam_type->max_mcs; dct++) { + for (dct = 0; dct < pvt->max_mcs; dct++) { for_each_chip_select(cs, dct, pvt) cs_enabled |= csrow_enabled(cs, dct, pvt); } @@ -4209,12 +4013,11 @@ static int probe_one_instance(unsigned int nid) pvt->mc_node_id = nid; pvt->F3 = F3; - ret = -ENODEV; - fam_type = per_family_init(pvt); - if (!fam_type) + ret = per_family_init(pvt); + if (ret < 0) goto err_enable; - ret = hw_info_get(pvt); + ret = pvt->ops->hw_info_get(pvt); if (ret < 0) goto err_enable; @@ -4224,7 +4027,7 @@ static int probe_one_instance(unsigned int nid) goto err_enable; } - if (!ecc_enabled(pvt)) { + if (!pvt->ops->ecc_enabled(pvt)) { ret = -ENODEV; if (!ecc_enable_override) @@ -4250,13 +4053,10 @@ static int probe_one_instance(unsigned int nid) goto err_enable; } - amd64_info("%s %sdetected (node %d).\n", fam_type->ctl_name, - (pvt->fam == 0xf ? - (pvt->ext_model >= K8_REV_F ? "revF or later " - : "revE or earlier ") - : ""), pvt->mc_node_id); + amd64_info("%s detected (node %d).\n", pvt->ctl_name, pvt->mc_node_id); - dump_misc_regs(pvt); + /* Display and decode various registers for debug purposes. */ + pvt->ops->dump_misc_regs(pvt); return ret; @@ -4319,6 +4119,7 @@ static const struct x86_cpu_id amd64_cpuids[] = { X86_MATCH_VENDOR_FAM(AMD, 0x17, NULL), X86_MATCH_VENDOR_FAM(HYGON, 0x18, NULL), X86_MATCH_VENDOR_FAM(AMD, 0x19, NULL), + X86_MATCH_VENDOR_FAM(AMD, 0x1A, NULL), { } }; MODULE_DEVICE_TABLE(x86cpu, amd64_cpuids); @@ -4370,19 +4171,17 @@ static int __init amd64_edac_init(void) } /* register stuff with EDAC MCE */ - if (boot_cpu_data.x86 >= 0x17) + if (boot_cpu_data.x86 >= 0x17) { amd_register_ecc_decoder(decode_umc_error); - else + } else { amd_register_ecc_decoder(decode_bus_error); - - setup_pci_device(); + setup_pci_device(); + } #ifdef CONFIG_X86_32 amd64_err("%s on 32-bit is unsupported. USE AT YOUR OWN RISK!\n", EDAC_MOD_STR); #endif - printk(KERN_INFO "AMD64 EDAC driver v%s\n", EDAC_AMD64_VERSION); - return 0; err_pci: @@ -4427,10 +4226,8 @@ module_init(amd64_edac_init); module_exit(amd64_edac_exit); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("SoftwareBitMaker: Doug Thompson, " - "Dave Peterson, Thayne Harbaugh"); -MODULE_DESCRIPTION("MC support for AMD64 memory controllers - " - EDAC_AMD64_VERSION); +MODULE_AUTHOR("SoftwareBitMaker: Doug Thompson, Dave Peterson, Thayne Harbaugh; AMD"); +MODULE_DESCRIPTION("MC support for AMD64 memory controllers"); module_param(edac_op_state, int, 0444); MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI"); |