summaryrefslogtreecommitdiff
path: root/drivers/edac/amd64_edac.c
diff options
context:
space:
mode:
authorMuralidhara M K <muralidhara.mk@amd.com>2023-01-27 17:04:07 +0000
committerBorislav Petkov (AMD) <bp@alien8.de>2023-03-24 13:03:19 +0100
commited623d55eef46d0ca7557b9665b4693931bfb507 (patch)
treeccf6b64b76d41e1b57fc06b7f766e3522490dd52 /drivers/edac/amd64_edac.c
parent5a1adb375d7a86ee3b703f895b61de20773b6670 (diff)
EDAC/amd64: Merge struct amd64_family_type into struct amd64_pvt
Future AMD systems will support heterogeneous "AMD Node" types, e.g. CPU and GPU types. Therefore, a global family type shared across all AMD nodes is no longer appropriate. Move struct low_ops routines and members of struct amd64_family_type to struct amd64_pvt. Currently, there are many code branches that split between "modern" and "legacy" systems. Another code branch will be needed in order to cover GPU cases. However, rather than introduce another branching case in multiple functions, the current branching code should be switched to a set of function pointers. This change makes the code more readable and simplifies adding support for new families/models. In order to reuse code, define two sets of function pointers. Use one for modern systems (Family 17h and later). This will not change between current CPU families. Use another set of function pointers for legacy systems (before Family 17h). Use the Family 16h versions as default for the legacy ops since these are the latest, and adjust the function pointers as needed for older families. [ Yazen: rebased/reworked patch and reworded commit message. ] [ bp: Fix rev8 or later check. ] Signed-off-by: Muralidhara M K <muralidhara.mk@amd.com> Co-developed-by: Naveen Krishna Chatradhi <naveenkrishna.chatradhi@amd.com> Signed-off-by: Naveen Krishna Chatradhi <naveenkrishna.chatradhi@amd.com> Co-developed-by: Yazen Ghannam <yazen.ghannam@amd.com> Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com> Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de> Link: https://lore.kernel.org/r/20230127170419.1824692-11-yazen.ghannam@amd.com
Diffstat (limited to 'drivers/edac/amd64_edac.c')
-rw-r--r--drivers/edac/amd64_edac.c308
1 files changed, 113 insertions, 195 deletions
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index bd0af17a318d..ac64d27387c8 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -13,11 +13,9 @@ 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) {
@@ -437,7 +435,7 @@ 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
@@ -1464,7 +1462,7 @@ static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
*/
dimm = csrow_nr >> 1;
- if (!fam_type->flags.zn_regs_v2)
+ if (!pvt->flags.zn_regs_v2)
cs_mask_nr >>= 1;
/* Asymmetric dual-rank DIMM support. */
@@ -1556,7 +1554,7 @@ static void __dump_misc_regs_df(struct amd64_pvt *pvt)
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),
+ 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));
@@ -1629,7 +1627,7 @@ static void prep_chip_selects(struct amd64_pvt *pvt)
for_each_umc(umc) {
pvt->csels[umc].b_cnt = 4;
- pvt->csels[umc].m_cnt = fam_type->flags.zn_regs_v2 ? 4 : 2;
+ pvt->csels[umc].m_cnt = pvt->flags.zn_regs_v2 ? 4 : 2;
}
} else {
@@ -1669,7 +1667,7 @@ static void read_umc_base_mask(struct amd64_pvt *pvt)
}
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];
@@ -1757,7 +1755,7 @@ 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))
@@ -2739,112 +2737,6 @@ static void f1x_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr,
err->channel = get_channel_from_ecc_syndrome(mci, err->syndrome);
}
-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 = {
- .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 = {
- .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 = {
- .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 = {
- .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 = {
- .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 = {
- .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 = {
- .map_sysaddr_to_csrow = f1x_map_sysaddr_to_csrow,
- .dbam_to_cs = f16_dbam_to_chip_select,
- }
- },
- [F17_CPUS] = {
- .ctl_name = "F17h",
- .max_mcs = 2,
- },
- [F17_M10H_CPUS] = {
- .ctl_name = "F17h_M10h",
- .max_mcs = 2,
- },
- [F17_M30H_CPUS] = {
- .ctl_name = "F17h_M30h",
- .max_mcs = 8,
- },
- [F17_M60H_CPUS] = {
- .ctl_name = "F17h_M60h",
- .max_mcs = 2,
- },
- [F17_M70H_CPUS] = {
- .ctl_name = "F17h_M70h",
- .max_mcs = 2,
- },
- [F19_CPUS] = {
- .ctl_name = "F19h",
- .max_mcs = 8,
- },
- [F19_M10H_CPUS] = {
- .ctl_name = "F19h_M10h",
- .max_mcs = 12,
- .flags.zn_regs_v2 = 1,
- },
- [F19_M50H_CPUS] = {
- .ctl_name = "F19h_M50h",
- .max_mcs = 2,
- },
-};
-
/*
* These are tables of eigenvectors (one per line) which can be used for the
* construction of the syndrome tables. The modified syndrome search algorithm
@@ -3226,7 +3118,7 @@ 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 + 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);
@@ -3495,7 +3387,7 @@ static int init_csrows(struct mem_ctl_info *mci)
: EDAC_SECDED;
}
- for (j = 0; j < fam_type->max_mcs; j++) {
+ for (j = 0; j < pvt->max_mcs; j++) {
dimm = csrow->channels[j]->dimm;
dimm->mtype = pvt->dram_type;
dimm->edac_mode = edac_mode;
@@ -3767,7 +3659,7 @@ static void setup_mci_misc_attrs(struct mem_ctl_info *mci)
mci->edac_cap = 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;
@@ -3779,114 +3671,145 @@ static void setup_mci_misc_attrs(struct mem_ctl_info *mci)
mci->get_sdram_scrub_rate = get_scrub_rate;
}
-/*
- * returns a pointer to the family descriptor on success, NULL otherwise.
- */
-static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
+static struct low_ops umc_ops = {
+};
+
+/* 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,
+};
+
+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;
+ 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;
+ pvt->ctl_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->ctl_name = "F10h";
+ 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->ctl_name = "F15h_M30h";
+ 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->ctl_name = "F15h_M60h";
+ 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->ctl_name = "F15h";
+ 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->ctl_name = "F16h_M30h";
+ 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->ctl_name = "F16h";
+ 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 0x10 ... 0x2f:
+ pvt->ctl_name = "F17h_M10h";
break;
- } else if (pvt->model >= 0x30 && pvt->model <= 0x3f) {
- fam_type = &family_types[F17_M30H_CPUS];
- pvt->ops = &family_types[F17_M30H_CPUS].ops;
+ case 0x30 ... 0x3f:
+ pvt->ctl_name = "F17h_M30h";
+ pvt->max_mcs = 8;
break;
- } else if (pvt->model >= 0x60 && pvt->model <= 0x6f) {
- fam_type = &family_types[F17_M60H_CPUS];
- pvt->ops = &family_types[F17_M60H_CPUS].ops;
+ case 0x60 ... 0x6f:
+ pvt->ctl_name = "F17h_M60h";
break;
- } else if (pvt->model >= 0x70 && pvt->model <= 0x7f) {
- fam_type = &family_types[F17_M70H_CPUS];
- pvt->ops = &family_types[F17_M70H_CPUS].ops;
+ case 0x70 ... 0x7f:
+ pvt->ctl_name = "F17h_M70h";
+ break;
+ default:
+ pvt->ctl_name = "F17h";
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:
+ pvt->ctl_name = "F18h";
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->ctl_name = "F19h";
+ pvt->max_mcs = 8;
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 0x10 ... 0x1f:
+ pvt->ctl_name = "F19h_M10h";
+ pvt->max_mcs = 12;
+ 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 0x20 ... 0x2f:
+ pvt->ctl_name = "F19h_M20h";
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 0x50 ... 0x5f:
+ pvt->ctl_name = "F19h_M50h";
+ break;
+ case 0xa0 ... 0xaf:
+ pvt->ctl_name = "F19h_MA0h";
+ pvt->max_mcs = 12;
+ 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;
+ return 0;
}
static const struct attribute_group *amd64_edac_attr_groups[] = {
@@ -3903,12 +3826,12 @@ static int hw_info_get(struct amd64_pvt *pvt)
int ret;
if (pvt->fam >= 0x17) {
- pvt->umc = kcalloc(fam_type->max_mcs, sizeof(struct amd64_umc), GFP_KERNEL);
+ pvt->umc = kcalloc(pvt->max_mcs, sizeof(struct amd64_umc), GFP_KERNEL);
if (!pvt->umc)
return -ENOMEM;
} else {
- pci_id1 = fam_type->f1_id;
- pci_id2 = fam_type->f2_id;
+ pci_id1 = pvt->f1_id;
+ pci_id2 = pvt->f2_id;
}
ret = reserve_mc_sibling_devs(pvt, pci_id1, pci_id2);
@@ -3938,7 +3861,7 @@ static int init_one_instance(struct amd64_pvt *pvt)
layers[0].size = pvt->csels[0].b_cnt;
layers[0].is_virt_csrow = true;
layers[1].type = EDAC_MC_LAYER_CHANNEL;
- layers[1].size = fam_type->max_mcs;
+ layers[1].size = pvt->max_mcs;
layers[1].is_virt_csrow = false;
mci = edac_mc_alloc(pvt->mc_node_id, ARRAY_SIZE(layers), layers, 0);
@@ -3968,7 +3891,7 @@ 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);
}
@@ -3997,9 +3920,8 @@ 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);
@@ -4038,11 +3960,7 @@ 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);