| Message ID | 20190529084344.28562-14-rrichter@marvell.com |
|---|---|
| State | New |
| Headers | show |
| Series | EDAC, mc, ghes: Fixes and updates to improve memory error reporting | expand |
Hi Robert, On 29/05/2019 09:44, Robert Richter wrote: > In a later patch we want add more information about the memory > hierarchy (NUMA topology, DIMM label information). Rework memory > hierarchy detection to make the code extendable for this. > > The general approach is roughly like: > > mem_info_setup(); > for_each_node(nid) { > mci = edac_mc_alloc(nid); > mci_add_dimm_info(mci); > edac_mc_add_mc(mci); > }; > > This patch introduces mem_info_setup() and mci_add_dimm_info(). > > All data of the memory hierarchy is collected in a local struct > ghes_mem_info. > > Note: Per (NUMA) node registration will be implemented in a later > patch. > diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c > index ea4d53043199..50f4ee36b755 100644 > --- a/drivers/edac/ghes_edac.c > +++ b/drivers/edac/ghes_edac.c > @@ -67,17 +67,38 @@ struct memdev_dmi_entry { > u16 conf_mem_clk_speed; > } __attribute__((__packed__)); > > -struct ghes_edac_dimm_fill { > - struct mem_ctl_info *mci; > - unsigned count; > +struct ghes_dimm_info { > + struct dimm_info dimm_info; > + int idx; > +}; > +struct ghes_mem_info { > + int num_dimm; > + struct ghes_dimm_info *dimms; > }; > > +struct ghes_mem_info mem_info; static? > @@ -94,18 +115,17 @@ static int get_dimm_smbios_index(u16 handle) > > static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg) > { > - struct ghes_edac_dimm_fill *dimm_fill = arg; > - struct mem_ctl_info *mci = dimm_fill->mci; > - > if (dh->type == DMI_ENTRY_MEM_DEVICE) { > + int *idx = arg; > struct memdev_dmi_entry *entry = (struct memdev_dmi_entry *)dh; > - struct dimm_info *dimm = edac_get_dimm(mci, dimm_fill->count, > - 0, 0); > + struct ghes_dimm_info *mi = &mem_info.dimms[*idx]; > + struct dimm_info *dimm = &mi->dimm_info; > u16 rdr_mask = BIT(7) | BIT(13); > + mi->phys_handle = entry->phys_mem_array_handle; Where did this come from, and what is it for? ... Should this be in a later patch? (did you bisect build this?) > if (entry->size == 0xffff) { > - pr_info("Can't get DIMM%i size\n", > - dimm_fill->count); > + pr_info("Can't get DIMM%i size\n", mi->idx); > dimm->nr_pages = MiB_TO_PAGES(32);/* Unknown */ > } else if (entry->size == 0x7fff) { > dimm->nr_pages = MiB_TO_PAGES(entry->extended_size); > +static int mem_info_setup(void) > +{ > + int idx = 0; > + > + memset(&mem_info, 0, sizeof(mem_info)); Is this necessary? Isn't mem_info in the BSS, it will zero'd already. > + /* Get the number of DIMMs */ > + dmi_walk(ghes_edac_count_dimms, NULL); > + if (!mem_info.num_dimm) > + return -EINVAL; > + mem_info.dimms = kcalloc(mem_info.num_dimm, > + sizeof(*mem_info.dimms), GFP_KERNEL); > + if (!mem_info.dimms) > + return -ENOMEM; > + ghes_dimm_info_init(); Could you move the kcalloc() into ghes_dimm_info_init()? This would save you having a unnecessarily-different version in mem_info_setup_fake(). > + dmi_walk(ghes_edac_dmidecode, &idx); > + > + return 0; > +} > +static int mem_info_setup_fake(void) > +{ > + struct ghes_dimm_info *ghes_dimm; > + struct dimm_info *dimm; > + > + memset(&mem_info, 0, sizeof(mem_info)); Is this necessary? Its only been touched by mem_info_setup(), and you get in here because mem_info.num_dimm == 0... > + ghes_dimm = kzalloc(sizeof(*mem_info.dimms), GFP_KERNEL); > + if (!ghes_dimm) > + return -ENOMEM; This is common with mem_info_setup(). If ghes_dimm_info_init() read mem_info.num_dimm and did the rest, you'd avoid some duplication here. > + mem_info.num_dimm = 1; > + mem_info.dimms = ghes_dimm; > + > + ghes_dimm_info_init(); > + > + dimm = &ghes_dimm->dimm_info; > + dimm->nr_pages = 1; > + dimm->grain = 128; > + dimm->mtype = MEM_UNKNOWN; > + dimm->dtype = DEV_UNKNOWN; > + dimm->edac_mode = EDAC_SECDED; > + > + return 0; > +} > +static void mci_add_dimm_info(struct mem_ctl_info *mci) (From the name I expected this to be in edac_mc.c) > +{ > + struct dimm_info *mci_dimm, *dmi_dimm; > + struct ghes_dimm_info *dimm; > + int index = 0; > + > + for_each_dimm(dimm) { > + dmi_dimm = &dimm->dimm_info; > + mci_dimm = edac_get_dimm_by_index(mci, index); > + > + index++; > + if (index > mci->tot_dimms) > + break; > + > + mci_dimm->nr_pages = dmi_dimm->nr_pages; > + mci_dimm->mtype = dmi_dimm->mtype; > + mci_dimm->edac_mode = dmi_dimm->edac_mode; > + mci_dimm->dtype = dmi_dimm->dtype; > + mci_dimm->grain = dmi_dimm->grain; > + mci_dimm->smbios_handle = dmi_dimm->smbios_handle; > } This isn't fun. I guess 'numa' is the reason for generating a shadow copy of all this, and then having to copy it into edac. But surely that isn't a problem unique to ghes_edac.c? Can't you add the nid, and any other properties to struct dimm_info? It already has smbios_handle, which is hardly useful to other drivers! > + if (index != mci->tot_dimms) > + pr_warn("Unexpected number of DIMMs: %d (exp. %d)\n", > + index, mci->tot_dimms); > } > @@ -472,22 +566,24 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) > mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(struct ghes_edac_pvt)); > if (!mci) { > - pr_info("Can't allocate memory for EDAC data\n"); > + pr_err("Can't allocate memory for EDAC data\n"); Leftover debug? kfree(mem_info.dimms); ? > return -ENOMEM; > } > > @@ -513,26 +609,14 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) > - if (!fake) { > - dimm_fill.count = 0; > - dimm_fill.mci = mci; > - dmi_walk(ghes_edac_dmidecode, &dimm_fill); > - } else { > - struct dimm_info *dimm = edac_get_dimm(mci, 0, 0, 0); > - > - dimm->nr_pages = 1; > - dimm->grain = 128; > - dimm->mtype = MEM_UNKNOWN; > - dimm->dtype = DEV_UNKNOWN; > - dimm->edac_mode = EDAC_SECDED; > - } > + mci_add_dimm_info(mci); > > rc = edac_mc_add_mc(mci); > if (rc < 0) { > - pr_info("Can't register at EDAC core\n"); > + pr_err("Can't register at EDAC core\n"); Leftover debug? > edac_mc_free(mci); kfree(mem_info.dimms); ? > return -ENODEV; > } Thanks! James
Hi James, thanks for your review. See below. On 29.05.19 16:06:55, James Morse wrote: > Hi Robert, > > On 29/05/2019 09:44, Robert Richter wrote: > > In a later patch we want add more information about the memory > > hierarchy (NUMA topology, DIMM label information). Rework memory > > hierarchy detection to make the code extendable for this. > > > > The general approach is roughly like: > > > > mem_info_setup(); > > for_each_node(nid) { > > mci = edac_mc_alloc(nid); > > mci_add_dimm_info(mci); > > edac_mc_add_mc(mci); > > }; > > > > This patch introduces mem_info_setup() and mci_add_dimm_info(). > > > > All data of the memory hierarchy is collected in a local struct > > ghes_mem_info. > > > > Note: Per (NUMA) node registration will be implemented in a later > > patch. > > > > diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c > > index ea4d53043199..50f4ee36b755 100644 > > --- a/drivers/edac/ghes_edac.c > > +++ b/drivers/edac/ghes_edac.c > > @@ -67,17 +67,38 @@ struct memdev_dmi_entry { > > u16 conf_mem_clk_speed; > > } __attribute__((__packed__)); > > > > -struct ghes_edac_dimm_fill { > > - struct mem_ctl_info *mci; > > - unsigned count; > > > +struct ghes_dimm_info { > > + struct dimm_info dimm_info; > > + int idx; > > +}; > > > +struct ghes_mem_info { > > + int num_dimm; > > + struct ghes_dimm_info *dimms; > > }; > > > > +struct ghes_mem_info mem_info; > > static? Yes, this can be made static. Will update the code. > > > > @@ -94,18 +115,17 @@ static int get_dimm_smbios_index(u16 handle) > > > > static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg) > > { > > - struct ghes_edac_dimm_fill *dimm_fill = arg; > > - struct mem_ctl_info *mci = dimm_fill->mci; > > - > > if (dh->type == DMI_ENTRY_MEM_DEVICE) { > > + int *idx = arg; > > struct memdev_dmi_entry *entry = (struct memdev_dmi_entry *)dh; > > - struct dimm_info *dimm = edac_get_dimm(mci, dimm_fill->count, > > - 0, 0); > > + struct ghes_dimm_info *mi = &mem_info.dimms[*idx]; > > + struct dimm_info *dimm = &mi->dimm_info; > > u16 rdr_mask = BIT(7) | BIT(13); > > > > + mi->phys_handle = entry->phys_mem_array_handle; > > Where did this come from, and what is it for? > > ... > > Should this be in a later patch? (did you bisect build this?) The change should be part of the next patch: EDAC, ghes: Extract numa node information for each dimm It breaks the build here. Will update the code. > > > > if (entry->size == 0xffff) { > > - pr_info("Can't get DIMM%i size\n", > > - dimm_fill->count); > > + pr_info("Can't get DIMM%i size\n", mi->idx); > > dimm->nr_pages = MiB_TO_PAGES(32);/* Unknown */ > > } else if (entry->size == 0x7fff) { > > dimm->nr_pages = MiB_TO_PAGES(entry->extended_size); > > > > +static int mem_info_setup(void) > > +{ > > + int idx = 0; > > + > > + memset(&mem_info, 0, sizeof(mem_info)); > > Is this necessary? Isn't mem_info in the BSS, it will zero'd already. For clarity I don't want to just *assume* the data is zero, instead I want to *ensure* it is because mem_info could be initialized and used more than one time. I think this is of not much cost but improves code maintainability. This structure is used locally here for all driver instances (there is only one istance allowed but there could be a 2nd initialization attempt after a first instance has been shut down). For consistent data we rely on that struct being zero from the beginning. Without that it would be zero only after a boot. I put this in here to emphasize the assumption the struct must be zero, even if the mem is zero when initializing it the first time, and it is very unlikely, the driver will be initialized a 2nd time. > > > > + /* Get the number of DIMMs */ > > + dmi_walk(ghes_edac_count_dimms, NULL); > > + if (!mem_info.num_dimm) > > + return -EINVAL; > > > + mem_info.dimms = kcalloc(mem_info.num_dimm, > > + sizeof(*mem_info.dimms), GFP_KERNEL); > > + if (!mem_info.dimms) > > + return -ENOMEM; > > > + ghes_dimm_info_init(); > > Could you move the kcalloc() into ghes_dimm_info_init()? This would save you having a > unnecessarily-different version in mem_info_setup_fake(). Sure, see below. > > > > + dmi_walk(ghes_edac_dmidecode, &idx); > > + > > + return 0; > > +} > > > +static int mem_info_setup_fake(void) > > +{ > > + struct ghes_dimm_info *ghes_dimm; > > + struct dimm_info *dimm; > > + > > + memset(&mem_info, 0, sizeof(mem_info)); > > Is this necessary? Its only been touched by mem_info_setup(), and you get in here because > mem_info.num_dimm == 0... In this particular case everything is still zero. But the above applies here too. > > > > + ghes_dimm = kzalloc(sizeof(*mem_info.dimms), GFP_KERNEL); > > + if (!ghes_dimm) > > + return -ENOMEM; > > This is common with mem_info_setup(). If ghes_dimm_info_init() read mem_info.num_dimm and > did the rest, you'd avoid some duplication here. Looks good to me and makes the setup code more straight. Will update the code. > > > > + mem_info.num_dimm = 1; > > + mem_info.dimms = ghes_dimm; > > + > > + ghes_dimm_info_init(); > > + > > + dimm = &ghes_dimm->dimm_info; > > + dimm->nr_pages = 1; > > + dimm->grain = 128; > > + dimm->mtype = MEM_UNKNOWN; > > + dimm->dtype = DEV_UNKNOWN; > > + dimm->edac_mode = EDAC_SECDED; > > + > > + return 0; > > +} > > > > +static void mci_add_dimm_info(struct mem_ctl_info *mci) > > (From the name I expected this to be in edac_mc.c) I will rename it to mem_info_prepare_mci() which is more in the line with the other mem_info_*() functions. Will update the code. > > > > +{ > > + struct dimm_info *mci_dimm, *dmi_dimm; > > + struct ghes_dimm_info *dimm; > > + int index = 0; > > + > > + for_each_dimm(dimm) { > > + dmi_dimm = &dimm->dimm_info; > > + mci_dimm = edac_get_dimm_by_index(mci, index); > > + > > + index++; > > + if (index > mci->tot_dimms) > > + break; > > + > > + mci_dimm->nr_pages = dmi_dimm->nr_pages; > > + mci_dimm->mtype = dmi_dimm->mtype; > > + mci_dimm->edac_mode = dmi_dimm->edac_mode; > > + mci_dimm->dtype = dmi_dimm->dtype; > > + mci_dimm->grain = dmi_dimm->grain; > > + mci_dimm->smbios_handle = dmi_dimm->smbios_handle; > > } > > This isn't fun. I guess 'numa' is the reason for generating a shadow copy of all this, and > then having to copy it into edac. But surely that isn't a problem unique to ghes_edac.c? We need to collect all the memory hierarchy and dimm info before we can call edac_mc_alloc(). Thus, the data is almost duplicate but I don't see a way to avoid this. I was thinking of splitting struct dimm_info in 2 parts with another struct in it to copy over the data as struct in one shot without overwriting parts of the data setup by edac_mc_alloc(). I also see this isn't ideal but don't see an alternative at the moment. > > Can't you add the nid, and any other properties to struct dimm_info? It already has > smbios_handle, which is hardly useful to other drivers! I will move smbios_handle back to struct ghes_dimm_info. Will update the code. > > > > + if (index != mci->tot_dimms) > > + pr_warn("Unexpected number of DIMMs: %d (exp. %d)\n", > > + index, mci->tot_dimms); > > } > > > > @@ -472,22 +566,24 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) > > > mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(struct ghes_edac_pvt)); > > if (!mci) { > > - pr_info("Can't allocate memory for EDAC data\n"); > > + pr_err("Can't allocate memory for EDAC data\n"); > > Leftover debug? No, this is a real error causing the init to fail. Thus, adjusting log level here. I changed it in this patch to align the log levels with the other new introduced error message in this patch. > > kfree(mem_info.dimms); ? > > > return -ENOMEM; > > } > > > > @@ -513,26 +609,14 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) > > > - if (!fake) { > > - dimm_fill.count = 0; > > - dimm_fill.mci = mci; > > - dmi_walk(ghes_edac_dmidecode, &dimm_fill); > > - } else { > > - struct dimm_info *dimm = edac_get_dimm(mci, 0, 0, 0); > > - > > - dimm->nr_pages = 1; > > - dimm->grain = 128; > > - dimm->mtype = MEM_UNKNOWN; > > - dimm->dtype = DEV_UNKNOWN; > > - dimm->edac_mode = EDAC_SECDED; > > - } > > + mci_add_dimm_info(mci); > > > > rc = edac_mc_add_mc(mci); > > if (rc < 0) { > > - pr_info("Can't register at EDAC core\n"); > > + pr_err("Can't register at EDAC core\n"); > > Leftover debug? Same here. > > > edac_mc_free(mci); > > kfree(mem_info.dimms); ? > > > return -ENODEV; > > } > > > Thanks! Thank you for review. -Robert > > James
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index ea4d53043199..50f4ee36b755 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -67,17 +67,38 @@ struct memdev_dmi_entry { u16 conf_mem_clk_speed; } __attribute__((__packed__)); -struct ghes_edac_dimm_fill { - struct mem_ctl_info *mci; - unsigned count; +struct ghes_dimm_info { + struct dimm_info dimm_info; + int idx; +}; + +struct ghes_mem_info { + int num_dimm; + struct ghes_dimm_info *dimms; }; +struct ghes_mem_info mem_info; + +#define for_each_dimm(dimm) \ + for (dimm = mem_info.dimms; \ + dimm < mem_info.dimms + mem_info.num_dimm; \ + dimm++) + static void ghes_edac_count_dimms(const struct dmi_header *dh, void *arg) { - int *num_dimm = arg; - if (dh->type == DMI_ENTRY_MEM_DEVICE) - (*num_dimm)++; + mem_info.num_dimm++; +} + +static void ghes_dimm_info_init(void) +{ + struct ghes_dimm_info *dimm; + int idx = 0; + + for_each_dimm(dimm) { + dimm->idx = idx; + idx++; + } } static int get_dimm_smbios_index(u16 handle) @@ -94,18 +115,17 @@ static int get_dimm_smbios_index(u16 handle) static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg) { - struct ghes_edac_dimm_fill *dimm_fill = arg; - struct mem_ctl_info *mci = dimm_fill->mci; - if (dh->type == DMI_ENTRY_MEM_DEVICE) { + int *idx = arg; struct memdev_dmi_entry *entry = (struct memdev_dmi_entry *)dh; - struct dimm_info *dimm = edac_get_dimm(mci, dimm_fill->count, - 0, 0); + struct ghes_dimm_info *mi = &mem_info.dimms[*idx]; + struct dimm_info *dimm = &mi->dimm_info; u16 rdr_mask = BIT(7) | BIT(13); + mi->phys_handle = entry->phys_mem_array_handle; + if (entry->size == 0xffff) { - pr_info("Can't get DIMM%i size\n", - dimm_fill->count); + pr_info("Can't get DIMM%i size\n", mi->idx); dimm->nr_pages = MiB_TO_PAGES(32);/* Unknown */ } else if (entry->size == 0x7fff) { dimm->nr_pages = MiB_TO_PAGES(entry->extended_size); @@ -179,7 +199,7 @@ static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg) if (dimm->nr_pages) { edac_dbg(1, "DIMM%i: %s size = %d MB%s\n", - dimm_fill->count, edac_mem_types[dimm->mtype], + mi->idx, edac_mem_types[dimm->mtype], PAGES_TO_MiB(dimm->nr_pages), (dimm->edac_mode != EDAC_NONE) ? "(ECC)" : ""); edac_dbg(2, "\ttype %d, detail 0x%02x, width %d(total %d)\n", @@ -189,8 +209,83 @@ static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg) dimm->smbios_handle = entry->handle; - dimm_fill->count++; + (*idx)++; + } +} + +static int mem_info_setup(void) +{ + int idx = 0; + + memset(&mem_info, 0, sizeof(mem_info)); + + /* Get the number of DIMMs */ + dmi_walk(ghes_edac_count_dimms, NULL); + if (!mem_info.num_dimm) + return -EINVAL; + + mem_info.dimms = kcalloc(mem_info.num_dimm, + sizeof(*mem_info.dimms), GFP_KERNEL); + if (!mem_info.dimms) + return -ENOMEM; + + ghes_dimm_info_init(); + dmi_walk(ghes_edac_dmidecode, &idx); + + return 0; +} + +static int mem_info_setup_fake(void) +{ + struct ghes_dimm_info *ghes_dimm; + struct dimm_info *dimm; + + memset(&mem_info, 0, sizeof(mem_info)); + + ghes_dimm = kzalloc(sizeof(*mem_info.dimms), GFP_KERNEL); + if (!ghes_dimm) + return -ENOMEM; + + mem_info.num_dimm = 1; + mem_info.dimms = ghes_dimm; + + ghes_dimm_info_init(); + + dimm = &ghes_dimm->dimm_info; + dimm->nr_pages = 1; + dimm->grain = 128; + dimm->mtype = MEM_UNKNOWN; + dimm->dtype = DEV_UNKNOWN; + dimm->edac_mode = EDAC_SECDED; + + return 0; +} + +static void mci_add_dimm_info(struct mem_ctl_info *mci) +{ + struct dimm_info *mci_dimm, *dmi_dimm; + struct ghes_dimm_info *dimm; + int index = 0; + + for_each_dimm(dimm) { + dmi_dimm = &dimm->dimm_info; + mci_dimm = edac_get_dimm_by_index(mci, index); + + index++; + if (index > mci->tot_dimms) + break; + + mci_dimm->nr_pages = dmi_dimm->nr_pages; + mci_dimm->mtype = dmi_dimm->mtype; + mci_dimm->edac_mode = dmi_dimm->edac_mode; + mci_dimm->dtype = dmi_dimm->dtype; + mci_dimm->grain = dmi_dimm->grain; + mci_dimm->smbios_handle = dmi_dimm->smbios_handle; } + + if (index != mci->tot_dimms) + pr_warn("Unexpected number of DIMMs: %d (exp. %d)\n", + index, mci->tot_dimms); } void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) @@ -451,10 +546,9 @@ static struct acpi_platform_list plat_list[] = { int ghes_edac_register(struct ghes *ghes, struct device *dev) { bool fake = false; - int rc, num_dimm = 0; + int rc; struct mem_ctl_info *mci; struct edac_mc_layer layers[1]; - struct ghes_edac_dimm_fill dimm_fill; int idx = -1; if (IS_ENABLED(CONFIG_X86)) { @@ -472,22 +566,24 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) if (atomic_inc_return(&ghes_init) > 1) return 0; - /* Get the number of DIMMs */ - dmi_walk(ghes_edac_count_dimms, &num_dimm); - - /* Check if we've got a bogus BIOS */ - if (num_dimm == 0) { + rc = mem_info_setup(); + if (rc == -EINVAL) { + /* we've got a bogus BIOS */ fake = true; - num_dimm = 1; + rc = mem_info_setup_fake(); + } + if (rc < 0) { + pr_err("Can't allocate memory for DIMM data\n"); + return rc; } layers[0].type = EDAC_MC_LAYER_ALL_MEM; - layers[0].size = num_dimm; + layers[0].size = mem_info.num_dimm; layers[0].is_virt_csrow = true; mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(struct ghes_edac_pvt)); if (!mci) { - pr_info("Can't allocate memory for EDAC data\n"); + pr_err("Can't allocate memory for EDAC data\n"); return -ENOMEM; } @@ -513,26 +609,14 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) pr_info("So, the end result of using this driver varies from vendor to vendor.\n"); pr_info("If you find incorrect reports, please contact your hardware vendor\n"); pr_info("to correct its BIOS.\n"); - pr_info("This system has %d DIMM sockets.\n", num_dimm); + pr_info("This system has %d DIMM sockets.\n", mem_info.num_dimm); } - if (!fake) { - dimm_fill.count = 0; - dimm_fill.mci = mci; - dmi_walk(ghes_edac_dmidecode, &dimm_fill); - } else { - struct dimm_info *dimm = edac_get_dimm(mci, 0, 0, 0); - - dimm->nr_pages = 1; - dimm->grain = 128; - dimm->mtype = MEM_UNKNOWN; - dimm->dtype = DEV_UNKNOWN; - dimm->edac_mode = EDAC_SECDED; - } + mci_add_dimm_info(mci); rc = edac_mc_add_mc(mci); if (rc < 0) { - pr_info("Can't register at EDAC core\n"); + pr_err("Can't register at EDAC core\n"); edac_mc_free(mci); return -ENODEV; } @@ -549,4 +633,6 @@ void ghes_edac_unregister(struct ghes *ghes) mci = ghes_pvt->mci; edac_mc_del_mc(mci->pdev); edac_mc_free(mci); + + kfree(mem_info.dimms); }
In a later patch we want add more information about the memory hierarchy (NUMA topology, DIMM label information). Rework memory hierarchy detection to make the code extendable for this. The general approach is roughly like: mem_info_setup(); for_each_node(nid) { mci = edac_mc_alloc(nid); mci_add_dimm_info(mci); edac_mc_add_mc(mci); }; This patch introduces mem_info_setup() and mci_add_dimm_info(). All data of the memory hierarchy is collected in a local struct ghes_mem_info. Note: Per (NUMA) node registration will be implemented in a later patch. Signed-off-by: Robert Richter <rrichter@marvell.com> --- drivers/edac/ghes_edac.c | 166 +++++++++++++++++++++++++++++---------- 1 file changed, 126 insertions(+), 40 deletions(-) -- 2.20.1