Somehow we ended up with two separate arrays of strings to describe the "enum mem_type" values. In edac_mc.c we have an exported list edac_mem_types[] that is used by a couple of drivers in debug messaged. In edac_mc_sysfs.c we have a private list that is used to display values in: /sys/devices/system/edac/mc/mc*/dimm*/dimm_mem_type /sys/devices/system/edac/mc/mc*/csrow*/mem_type this list was missing a value for MEM_LRDDR3 The string values in the two lists were different :-( Combining the lists, I kept the values so that the sysfs output will be unchanged as some scripts may depend on that. Reported-by: Borislav Petkov <bp(a)suse.de&gt; Acked-by: Borislav Petkov <bp(a)suse.de&gt; Signed-off-by: Tony Luck <tony.luck(a)intel.com&gt; --- drivers/edac/edac_mc.c | 40 ++++++++++++++++++++-------------------- drivers/edac/edac_mc_sysfs.c | 26 ++------------------------ 2 files changed, 22 insertions(+), 44 deletions(-) diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 48193f5f3b56..1f61b736e075 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -195,26 +195,26 @@ static void edac_mc_dump_mci(struct mem_ctl_info *mci) #endif /* CONFIG_EDAC_DEBUG */ const char * const edac_mem_types[] = { - [MEM_EMPTY] = "Empty csrow", - [MEM_RESERVED] = "Reserved csrow type", - [MEM_UNKNOWN] = "Unknown csrow type", - [MEM_FPM] = "Fast page mode RAM", - [MEM_EDO] = "Extended data out RAM", - [MEM_BEDO] = "Burst Extended data out RAM", - [MEM_SDR] = "Single data rate SDRAM", - [MEM_RDR] = "Registered single data rate SDRAM", - [MEM_DDR] = "Double data rate SDRAM", - [MEM_RDDR] = "Registered Double data rate SDRAM", - [MEM_RMBS] = "Rambus DRAM", - [MEM_DDR2] = "Unbuffered DDR2 RAM", - [MEM_FB_DDR2] = "Fully buffered DDR2", - [MEM_RDDR2] = "Registered DDR2 RAM", - [MEM_XDR] = "Rambus XDR", - [MEM_DDR3] = "Unbuffered DDR3 RAM", - [MEM_RDDR3] = "Registered DDR3 RAM", - [MEM_LRDDR3] = "Load-Reduced DDR3 RAM", - [MEM_DDR4] = "Unbuffered DDR4 RAM", - [MEM_RDDR4] = "Registered DDR4 RAM", + [MEM_EMPTY] = "Empty", + [MEM_RESERVED] = "Reserved", + [MEM_UNKNOWN] = "Unknown", + [MEM_FPM] = "FPM", + [MEM_EDO] = "EDO", + [MEM_BEDO] = "BEDO", + [MEM_SDR] = "Unbuffered-SDR", + [MEM_RDR] = "Registered-SDR", + [MEM_DDR] = "Unbuffered-DDR", + [MEM_RDDR] = "Registered-DDR", + [MEM_RMBS] = "RMBS", + [MEM_DDR2] = "Unbuffered-DDR2", + [MEM_FB_DDR2] = "FullyBuffered-DDR2", + [MEM_RDDR2] = "Registered-DDR2", + [MEM_XDR] = "XDR", + [MEM_DDR3] = "Unbuffered-DDR3", + [MEM_RDDR3] = "Registered-DDR3", + [MEM_LRDDR3] = "Load-Reduced-DDR3-RAM", + [MEM_DDR4] = "Unbuffered-DDR4", + [MEM_RDDR4] = "Registered-DDR4" }; EXPORT_SYMBOL_GPL(edac_mem_types); diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index c70ea82c815c..7481955160a4 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -91,28 +91,6 @@ static struct device *mci_pdev; /* * various constants for Memory Controllers */ -static const char * const mem_types[] = { - [MEM_EMPTY] = "Empty", - [MEM_RESERVED] = "Reserved", - [MEM_UNKNOWN] = "Unknown", - [MEM_FPM] = "FPM", - [MEM_EDO] = "EDO", - [MEM_BEDO] = "BEDO", - [MEM_SDR] = "Unbuffered-SDR", - [MEM_RDR] = "Registered-SDR", - [MEM_DDR] = "Unbuffered-DDR", - [MEM_RDDR] = "Registered-DDR", - [MEM_RMBS] = "RMBS", - [MEM_DDR2] = "Unbuffered-DDR2", - [MEM_FB_DDR2] = "FullyBuffered-DDR2", - [MEM_RDDR2] = "Registered-DDR2", - [MEM_XDR] = "XDR", - [MEM_DDR3] = "Unbuffered-DDR3", - [MEM_RDDR3] = "Registered-DDR3", - [MEM_DDR4] = "Unbuffered-DDR4", - [MEM_RDDR4] = "Registered-DDR4" -}; - static const char * const dev_types[] = { [DEV_UNKNOWN] = "Unknown", [DEV_X1] = "x1", @@ -196,7 +174,7 @@ static ssize_t csrow_mem_type_show(struct device *dev, { struct csrow_info *csrow = to_csrow(dev); - return sprintf(data, "%s\n", mem_types[csrow->channels[0]->dimm->mtype]); + return sprintf(data, "%s\n", edac_mem_types[csrow->channels[0]->dimm->mtype]); } static ssize_t csrow_dev_type_show(struct device *dev, @@ -549,7 +527,7 @@ static ssize_t dimmdev_mem_type_show(struct device *dev, { struct dimm_info *dimm = to_dimm(dev); - return sprintf(data, "%s\n", mem_types[dimm->mtype]); + return sprintf(data, "%s\n", edac_mem_types[dimm->mtype]); } static ssize_t dimmdev_dev_type_show(struct device *dev, -- 2.14.1

EDAC driver needs to look up attributes of NVDIMMs provided in SMBIOS. Provide a function that looks up an acpi_nfit_memory_map from a device handle (node/socket/mc/channel/dimm) and returns the SMBIOS handle. Also pass back the "flags" so we can see if the NVDIMM is OK. Signed-off-by: Tony Luck <tony.luck(a)intel.com&gt; --- drivers/acpi/nfit/core.c | 27 +++++++++++++++++++++++++++ include/acpi/nfit.h | 26 ++++++++++++++++++++++++++ 2 files changed, 53 insertions(+) create mode 100644 include/acpi/nfit.h diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index bbe48ad20886..4d6eeb1793e6 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -23,6 +23,7 @@ #include <linux/io.h> #include <linux/nd.h> #include <asm/cacheflush.h> +#include <acpi/nfit.h> #include "nfit.h" /* @@ -690,6 +691,32 @@ static bool add_memdev(struct acpi_nfit_desc *acpi_desc, return true; } +int nfit_get_smbios_id(u32 device_handle, u16 *flags) +{ + struct acpi_nfit_memory_map *memdev; + struct acpi_nfit_desc *acpi_desc; + struct nfit_mem *nfit_mem; + + mutex_lock(&acpi_desc_lock); + list_for_each_entry(acpi_desc, &acpi_descs, list) { + mutex_lock(&acpi_desc->init_mutex); + list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) { + memdev = __to_nfit_memdev(nfit_mem); + if (memdev->device_handle == device_handle) { + mutex_unlock(&acpi_desc->init_mutex); + mutex_unlock(&acpi_desc_lock); + *flags = memdev->flags; + return memdev->physical_id; + } + } + mutex_unlock(&acpi_desc->init_mutex); + } + mutex_unlock(&acpi_desc_lock); + + return -ENODEV; +} +EXPORT_SYMBOL_GPL(nfit_get_smbios_id); + /* * An implementation may provide a truncated control region if no block windows * are defined. diff --git a/include/acpi/nfit.h b/include/acpi/nfit.h new file mode 100644 index 000000000000..6ccc6eacd855 --- /dev/null +++ b/include/acpi/nfit.h @@ -0,0 +1,26 @@ +/* + * Copyright(c) 2017 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef __ACPI_NFIT_H +#define __ACPI_NFIT_H + +#if IS_ENABLED(CONFIG_ACPI_NFIT) +int nfit_get_smbios_id(u32 device_handle, u16 *flags); +#else +static inline int nfit_get_smbios_id(u32 device_handle, u16 *flags) +{ + return -EOPNOTSUPP; +} +#endif + +#endif /* __ACPI_NFIT_H */ -- 2.14.1

Hi Tony, On Thu, 22 Feb 2018 11:58:10 -0800, Tony Luck wrote: On the principle I'm OK with the idea. My comments on the implementation details are inline below. A comment stating in which unit the size is stored would be appreciated. Should this not be ~0ull? On 32-bit systems ~0ul would be 0xffffffff not 0xffffffffffffffff. Also it would be nice to document somewhere that 0 means memory module not installed and all fs means size is unknown. I'm curious, do you really need to know the amount of memory to the byte? The SMBIOS specification itself does not support granularity under 1 kB. I would be very surprised if any machine running Linux today has memory modules under 1 MB. If storing in MB you wouldn't need a u64... ~0ull? ~0ull? -- Jean Delvare SUSE L3 Support

This just covers the topology function of the EDAC driver. We locate which DIMM slots are populated with NVDIMMs and query the NFIT and SMBIOS tables to get the size. Signed-off-by: Tony Luck <tony.luck(a)intel.com&gt; --- drivers/edac/Kconfig | 5 +++- drivers/edac/skx_edac.c | 68 ++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 66 insertions(+), 7 deletions(-) diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 3c4017007647..c12e34564557 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -232,9 +232,12 @@ config EDAC_SBRIDGE config EDAC_SKX tristate "Intel Skylake server Integrated MC" depends on PCI && X86_64 && X86_MCE_INTEL && PCI_MMCONFIG + select DMI help Support for error detection and correction the Intel - Skylake server Integrated Memory Controllers. + Skylake server Integrated Memory Controllers. If your + system has non-volatile DIMMs you should also manually + select CONFIG_ACPI_NFIT config EDAC_PND2 tristate "Intel Pondicherry2" diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c index 912c4930c9ef..f34c60638c4b 100644 --- a/drivers/edac/skx_edac.c +++ b/drivers/edac/skx_edac.c @@ -14,6 +14,8 @@ #include <linux/module.h> #include <linux/init.h> +#include <linux/acpi.h> +#include <linux/dmi.h> #include <linux/pci.h> #include <linux/pci_ids.h> #include <linux/slab.h> @@ -24,6 +26,7 @@ #include <linux/bitmap.h> #include <linux/math64.h> #include <linux/mod_devicetable.h> +#include <acpi/nfit.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include <asm/processor.h> @@ -302,6 +305,7 @@ static int get_dimm_attr(u32 reg, int lobit, int hibit, int add, int minval, } #define IS_DIMM_PRESENT(mtr) GET_BITFIELD((mtr), 15, 15) +#define IS_NVDIMM_PRESENT(mcddrtcfg, i) GET_BITFIELD((mcddrtcfg), (i), (i)) #define numrank(reg) get_dimm_attr((reg), 12, 13, 0, 0, 2, "ranks") #define numrow(reg) get_dimm_attr((reg), 2, 4, 12, 1, 6, "rows") @@ -350,8 +354,6 @@ static int get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm, int banks = 16, ranks, rows, cols, npages; u64 size; - if (!IS_DIMM_PRESENT(mtr)) - return 0; ranks = numrank(mtr); rows = numrow(mtr); cols = numcol(mtr); @@ -383,6 +385,55 @@ static int get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm, return 1; } +static int get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc, + int chan, int dimmno) +{ + int smbios_handle; + u32 dev_handle; + u16 flags; + u64 size = 0; + + dev_handle = ACPI_NFIT_BUILD_DEVICE_HANDLE(dimmno, chan, imc->lmc, + imc->src_id, 0); + + smbios_handle = nfit_get_smbios_id(dev_handle, &flags); + if (smbios_handle == -EOPNOTSUPP) { + pr_warn_once("skx_edac: can't find size of NVDIMM. Try enabling CONFIG_ACPI_NFIT\n"); + goto unknown_size; + } + if (smbios_handle < 0) { + skx_printk(KERN_ERR, "Can't find handle for NVDIMM ADR=%x\n", dev_handle); + return 0; + } + + if (flags & ACPI_NFIT_MEM_MAP_FAILED) { + skx_printk(KERN_ERR, "NVDIMM ADR=%x is not mapped\n", dev_handle); + return 0; + } + + size = dmi_memdev_size(smbios_handle); + if (size == ~0ul) { + skx_printk(KERN_ERR, "Can't find size for NVDIMM ADR=%x/SMBIOS=%x\n", + dev_handle, smbios_handle); + return 0; + } + +unknown_size: + edac_dbg(0, "mc#%d: channel %d, dimm %d, %lld Mb (%lld pages)\n", + imc->mc, chan, dimmno, size >> 20, size >> PAGE_SHIFT); + + dimm->nr_pages = size >> PAGE_SHIFT; + dimm->grain = 32; + dimm->dtype = DEV_UNKNOWN; + dimm->mtype = MEM_NVDIMM; + dimm->edac_mode = EDAC_SECDED; /* likely better than this */ + + snprintf(dimm->label, sizeof(dimm->label), "CPU_SrcID#%u_MC#%u_Chan#%u_DIMM#%u", + imc->src_id, imc->lmc, chan, dimmno); + + return 1; +} + #define SKX_GET_MTMTR(dev, reg) \ pci_read_config_dword((dev), 0x87c, &reg) @@ -399,20 +450,24 @@ static int skx_get_dimm_config(struct mem_ctl_info *mci) { struct skx_pvt *pvt = mci->pvt_info; struct skx_imc *imc = pvt->imc; + u32 mtr, amap, mcddrtcfg; struct dimm_info *dimm; int i, j; - u32 mtr, amap; int ndimms; for (i = 0; i < NUM_CHANNELS; i++) { ndimms = 0; pci_read_config_dword(imc->chan[i].cdev, 0x8C, &amap); + pci_read_config_dword(imc->chan[i].cdev, 0x400, &mcddrtcfg); for (j = 0; j < NUM_DIMMS; j++) { dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, j, 0); pci_read_config_dword(imc->chan[i].cdev, 0x80 + 4*j, &mtr); - ndimms += get_dimm_info(mtr, amap, dimm, imc, i, j); + if (IS_DIMM_PRESENT(mtr)) + ndimms += get_dimm_info(mtr, amap, dimm, imc, i, j); + else if (IS_NVDIMM_PRESENT(mcddrtcfg, j)) + ndimms += get_nvdimm_info(dimm, imc, i, j); } if (ndimms && !skx_check_ecc(imc->chan[0].cdev)) { skx_printk(KERN_ERR, "ECC is disabled on imc %d\n", imc->mc); @@ -468,13 +523,14 @@ static int skx_register_mci(struct skx_imc *imc) pvt = mci->pvt_info; pvt->imc = imc; - mci->ctl_name = kasprintf(GFP_KERNEL, "Skylake Socket#%d IMC#%d", imc->node_id, imc->lmc); + mci->ctl_name = kasprintf(GFP_KERNEL, "Skylake Socket#%d IMC#%d", + imc->node_id, imc->lmc); if (!mci->ctl_name) { rc = -ENOMEM; goto fail0; } - mci->mtype_cap = MEM_FLAG_DDR4; + mci->mtype_cap = MEM_FLAG_DDR4 | MEM_FLAG_NVDIMM; mci->edac_ctl_cap = EDAC_FLAG_NONE; mci->edac_cap = EDAC_FLAG_NONE; mci->mod_name = EDAC_MOD_STR; -- 2.14.1

There are now non-volatile versions of DIMMs. Add a new entry to "enum mem_type" and a new string in edac_mem_types[]. Signed-off-by: Tony Luck <tony.luck(a)intel.com&gt; --- drivers/edac/edac_mc.c | 3 ++- include/linux/edac.h | 3 +++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 1f61b736e075..3bb82e511eca 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -214,7 +214,8 @@ const char * const edac_mem_types[] = { [MEM_RDDR3] = "Registered-DDR3", [MEM_LRDDR3] = "Load-Reduced-DDR3-RAM", [MEM_DDR4] = "Unbuffered-DDR4", - [MEM_RDDR4] = "Registered-DDR4" + [MEM_RDDR4] = "Registered-DDR4", + [MEM_NVDIMM] = "Non-volatile-RAM", }; EXPORT_SYMBOL_GPL(edac_mem_types); diff --git a/include/linux/edac.h b/include/linux/edac.h index cd75c173fd00..bffb97828ed6 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -186,6 +186,7 @@ static inline char *mc_event_error_type(const unsigned int err_type) * @MEM_RDDR4: Registered DDR4 RAM * This is a variant of the DDR4 memories. * @MEM_LRDDR4: Load-Reduced DDR4 memory. + * @MEM_NVDIMM: Non-volatile RAM */ enum mem_type { MEM_EMPTY = 0, @@ -209,6 +210,7 @@ enum mem_type { MEM_DDR4, MEM_RDDR4, MEM_LRDDR4, + MEM_NVDIMM, }; #define MEM_FLAG_EMPTY BIT(MEM_EMPTY) @@ -231,6 +233,7 @@ enum mem_type { #define MEM_FLAG_DDR4 BIT(MEM_DDR4) #define MEM_FLAG_RDDR4 BIT(MEM_RDDR4) #define MEM_FLAG_LRDDR4 BIT(MEM_LRDDR4) +#define MEM_FLAG_NVDIMM BIT(MEM_NVDIMM) /** * enum edac-type - Error Detection and Correction capabilities and mode -- 2.14.1

When we first scan the SMBIOS table, save the size of the DIMM. Provide a function for other code (EDAC driver) to look up the size of a DIMM from its SMBIOS handle. Signed-off-by: Tony Luck <tony.luck(a)intel.com&gt; --- drivers/firmware/dmi_scan.c | 31 +++++++++++++++++++++++++++++++ include/linux/dmi.h | 2 ++ 2 files changed, 33 insertions(+) diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index e763e1484331..35c6c74c9304 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -32,6 +32,7 @@ static char dmi_ids_string[128] __initdata; static struct dmi_memdev_info { const char *device; const char *bank; + u64 size; /* bytes */ u16 handle; } *dmi_memdev; static int dmi_memdev_nr; @@ -386,6 +387,8 @@ static void __init save_mem_devices(const struct dmi_header *dm, void *v) { const char *d = (const char *)dm; static int nr; + u64 bytes; + u16 size; if (dm->type != DMI_ENTRY_MEM_DEVICE || dm->length < 0x12) return; @@ -396,6 +399,20 @@ static void __init save_mem_devices(const struct dmi_header *dm, void *v) dmi_memdev[nr].handle = get_unaligned(&dm->handle); dmi_memdev[nr].device = dmi_string(dm, d[0x10]); dmi_memdev[nr].bank = dmi_string(dm, d[0x11]); + + size = get_unaligned((u16 *)&d[0xC]); + if (size == 0) + bytes = 0; + else if (size == 0xffff) + bytes = ~0ull; + else if (size & 0x8000) + bytes = (u64)(size & 0x7fff) << 10; + else if (size != 0x7fff) + bytes = (u64)size << 20; + else + bytes = (u64)get_unaligned((u32 *)&d[0x1C]) << 20; + + dmi_memdev[nr].size = bytes; nr++; } @@ -1065,3 +1082,17 @@ void dmi_memdev_name(u16 handle, const char **bank, const char **device) } } EXPORT_SYMBOL_GPL(dmi_memdev_name); + +u64 dmi_memdev_size(u16 handle) +{ + int n; + + if (dmi_memdev) { + for (n = 0; n < dmi_memdev_nr; n++) { + if (handle == dmi_memdev[n].handle) + return dmi_memdev[n].size; + } + } + return ~0ull; +} +EXPORT_SYMBOL_GPL(dmi_memdev_size); diff --git a/include/linux/dmi.h b/include/linux/dmi.h index 46e151172d95..7f5929123b69 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -113,6 +113,7 @@ extern int dmi_walk(void (*decode)(const struct dmi_header *, void *), void *private_data); extern bool dmi_match(enum dmi_field f, const char *str); extern void dmi_memdev_name(u16 handle, const char **bank, const char **device); +extern u64 dmi_memdev_size(u16 handle); #else @@ -142,6 +143,7 @@ static inline bool dmi_match(enum dmi_field f, const char *str) { return false; } static inline void dmi_memdev_name(u16 handle, const char **bank, const char **device) { } +static inline u64 dmi_memdev_size(u16 handle) { return ~0ul; } static inline const struct dmi_system_id * dmi_first_match(const struct dmi_system_id *list) { return NULL; } -- 2.14.1

This just covers the topology function of the EDAC driver. We locate which DIMM slots are populated with NVDIMMs and query the NFIT and SMBIOS tables to get the size. Signed-off-by: Tony Luck <tony.luck(a)intel.com&gt; --- drivers/edac/Kconfig | 5 +++- drivers/edac/skx_edac.c | 66 ++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 64 insertions(+), 7 deletions(-) diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 3c4017007647..c12e34564557 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -232,9 +232,12 @@ config EDAC_SBRIDGE config EDAC_SKX tristate "Intel Skylake server Integrated MC" depends on PCI && X86_64 && X86_MCE_INTEL && PCI_MMCONFIG + select DMI help Support for error detection and correction the Intel - Skylake server Integrated Memory Controllers. + Skylake server Integrated Memory Controllers. If your + system has non-volatile DIMMs you should also manually + select CONFIG_ACPI_NFIT config EDAC_PND2 tristate "Intel Pondicherry2" diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c index 912c4930c9ef..84c18bb1e0cd 100644 --- a/drivers/edac/skx_edac.c +++ b/drivers/edac/skx_edac.c @@ -14,6 +14,8 @@ #include <linux/module.h> #include <linux/init.h> +#include <linux/acpi.h> +#include <linux/dmi.h> #include <linux/pci.h> #include <linux/pci_ids.h> #include <linux/slab.h> @@ -24,6 +26,7 @@ #include <linux/bitmap.h> #include <linux/math64.h> #include <linux/mod_devicetable.h> +#include <acpi/nfit.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include <asm/processor.h> @@ -302,6 +305,7 @@ static int get_dimm_attr(u32 reg, int lobit, int hibit, int add, int minval, } #define IS_DIMM_PRESENT(mtr) GET_BITFIELD((mtr), 15, 15) +#define IS_NVDIMM_PRESENT(mcddrtcfg, i) GET_BITFIELD((mcddrtcfg), (i), (i)) #define numrank(reg) get_dimm_attr((reg), 12, 13, 0, 0, 2, "ranks") #define numrow(reg) get_dimm_attr((reg), 2, 4, 12, 1, 6, "rows") @@ -350,8 +354,6 @@ static int get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm, int banks = 16, ranks, rows, cols, npages; u64 size; - if (!IS_DIMM_PRESENT(mtr)) - return 0; ranks = numrank(mtr); rows = numrow(mtr); cols = numcol(mtr); @@ -383,6 +385,53 @@ static int get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm, return 1; } +static int get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc, + int chan, int dimmno) +{ + int smbios_handle; + u32 dev_handle; + u16 flags; + u64 size = 0; + + dev_handle = ACPI_NFIT_BUILD_DEVICE_HANDLE(dimmno, chan, imc->lmc, + imc->src_id, 0); + + smbios_handle = nfit_get_smbios_id(dev_handle, &flags); + if (smbios_handle == -EOPNOTSUPP) { + pr_warn_once("skx_edac: can't find size of NVDIMM. Try enabling CONFIG_ACPI_NFIT\n"); + goto unknown_size; + } + if (smbios_handle < 0) { + skx_printk(KERN_ERR, "Can't find handle for NVDIMM ADR=%x\n", dev_handle); + goto unknown_size; + } + + if (flags & ACPI_NFIT_MEM_MAP_FAILED) { + skx_printk(KERN_ERR, "NVDIMM ADR=%x is not mapped\n", dev_handle); + goto unknown_size; + } + + size = dmi_memdev_size(smbios_handle); + if (size == ~0ull) + skx_printk(KERN_ERR, "Can't find size for NVDIMM ADR=%x/SMBIOS=%x\n", + dev_handle, smbios_handle); + +unknown_size: + dimm->nr_pages = size >> PAGE_SHIFT; + dimm->grain = 32; + dimm->dtype = DEV_UNKNOWN; + dimm->mtype = MEM_NVDIMM; + dimm->edac_mode = EDAC_SECDED; /* likely better than this */ + + edac_dbg(0, "mc#%d: channel %d, dimm %d, %llu Mb (%u pages)\n", + imc->mc, chan, dimmno, size >> 20, dimm->nr_pages); + + snprintf(dimm->label, sizeof(dimm->label), "CPU_SrcID#%u_MC#%u_Chan#%u_DIMM#%u", + imc->src_id, imc->lmc, chan, dimmno); + + return 1; +} + #define SKX_GET_MTMTR(dev, reg) \ pci_read_config_dword((dev), 0x87c, &reg) @@ -399,20 +448,24 @@ static int skx_get_dimm_config(struct mem_ctl_info *mci) { struct skx_pvt *pvt = mci->pvt_info; struct skx_imc *imc = pvt->imc; + u32 mtr, amap, mcddrtcfg; struct dimm_info *dimm; int i, j; - u32 mtr, amap; int ndimms; for (i = 0; i < NUM_CHANNELS; i++) { ndimms = 0; pci_read_config_dword(imc->chan[i].cdev, 0x8C, &amap); + pci_read_config_dword(imc->chan[i].cdev, 0x400, &mcddrtcfg); for (j = 0; j < NUM_DIMMS; j++) { dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, j, 0); pci_read_config_dword(imc->chan[i].cdev, 0x80 + 4*j, &mtr); - ndimms += get_dimm_info(mtr, amap, dimm, imc, i, j); + if (IS_DIMM_PRESENT(mtr)) + ndimms += get_dimm_info(mtr, amap, dimm, imc, i, j); + else if (IS_NVDIMM_PRESENT(mcddrtcfg, j)) + ndimms += get_nvdimm_info(dimm, imc, i, j); } if (ndimms && !skx_check_ecc(imc->chan[0].cdev)) { skx_printk(KERN_ERR, "ECC is disabled on imc %d\n", imc->mc); @@ -468,13 +521,14 @@ static int skx_register_mci(struct skx_imc *imc) pvt = mci->pvt_info; pvt->imc = imc; - mci->ctl_name = kasprintf(GFP_KERNEL, "Skylake Socket#%d IMC#%d", imc->node_id, imc->lmc); + mci->ctl_name = kasprintf(GFP_KERNEL, "Skylake Socket#%d IMC#%d", + imc->node_id, imc->lmc); if (!mci->ctl_name) { rc = -ENOMEM; goto fail0; } - mci->mtype_cap = MEM_FLAG_DDR4; + mci->mtype_cap = MEM_FLAG_DDR4 | MEM_FLAG_NVDIMM; mci->edac_ctl_cap = EDAC_FLAG_NONE; mci->edac_cap = EDAC_FLAG_NONE; mci->mod_name = EDAC_MOD_STR; -- 2.14.1

On Tue, Mar 13, 2018 at 10:59:01AM +0100, Jean Delvare wrote: Heh! We've been cut & pasting that line from EDAC drivers since the i7core_edac.c I think the origin is in 2.6.35. So you are far from the only person to not notice it in a review :-) I could fix the return to be: diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c index 84c18bb1e0cd..1a66e145c0bd 100644 --- a/drivers/edac/skx_edac.c +++ b/drivers/edac/skx_edac.c @@ -429,7 +429,7 @@ static int get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc, snprintf(dimm->label, sizeof(dimm->label), "CPU_SrcID#%u_MC#%u_Chan#%u_DIMM#%u", imc->src_id, imc->lmc, chan, dimmno); - return 1; + return (size == 0 || size == ~0ull) ? 0 : 1; } #define SKX_GET_MTMTR(dev, reg) \ Thanks. Boris ... ready to go now? Or do you have some other comments? -Tony

On Tue, Mar 13, 2018 at 08:59:56AM -0700, Luck, Tony wrote: I've committed this. Running build smoke tests now. Thx. --- From: Tony Luck <tony.luck(a)intel.com&gt; Date: Mon, 12 Mar 2018 11:24:30 -0700 Subject: [PATCH] EDAC, skx_edac: Detect non-volatile DIMMs This just covers the topology function of the EDAC driver. We locate which DIMM slots are populated with NVDIMMs and query the NFIT and SMBIOS tables to get the size. Reviewed-by: Jean Delvare <jdelvare(a)suse.de&gt; Cc: Aristeu Rozanski <aris(a)redhat.com&gt; Cc: Dan Williams <dan.j.williams(a)intel.com&gt; Cc: Len Brown <lenb(a)kernel.org&gt; Cc: Mauro Carvalho Chehab <mchehab(a)kernel.org&gt; Cc: Qiuxu Zhuo <qiuxu.zhuo(a)intel.com&gt; Cc: "Rafael J. Wysocki" <rjw(a)rjwysocki.net&gt; Cc: linux-acpi(a)vger.kernel.org Cc: linux-edac <linux-edac(a)vger.kernel.org&gt; Cc: linux-nvdimm(a)lists.01.org Link: http://lkml.kernel.org/r/20180312182430.10335-6-tony.luck@intel.com Signed-off-by: Borislav Petkov <bp(a)suse.de&gt; --- drivers/edac/Kconfig | 5 +++- drivers/edac/skx_edac.c | 67 ++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 65 insertions(+), 7 deletions(-) diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index cb4ff1cc6eb4..07d569d32b90 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -232,9 +232,12 @@ config EDAC_SBRIDGE config EDAC_SKX tristate "Intel Skylake server Integrated MC" depends on PCI && X86_64 && X86_MCE_INTEL && PCI_MMCONFIG + select DMI help Support for error detection and correction the Intel - Skylake server Integrated Memory Controllers. + Skylake server Integrated Memory Controllers. If your + system has non-volatile DIMMs you should also manually + select CONFIG_ACPI_NFIT. config EDAC_PND2 tristate "Intel Pondicherry2" diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c index 912c4930c9ef..fae095162c01 100644 --- a/drivers/edac/skx_edac.c +++ b/drivers/edac/skx_edac.c @@ -14,6 +14,8 @@ #include <linux/module.h> #include <linux/init.h> +#include <linux/acpi.h> +#include <linux/dmi.h> #include <linux/pci.h> #include <linux/pci_ids.h> #include <linux/slab.h> @@ -24,6 +26,7 @@ #include <linux/bitmap.h> #include <linux/math64.h> #include <linux/mod_devicetable.h> +#include <acpi/nfit.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include <asm/processor.h> @@ -302,6 +305,7 @@ static int get_dimm_attr(u32 reg, int lobit, int hibit, int add, int minval, } #define IS_DIMM_PRESENT(mtr) GET_BITFIELD((mtr), 15, 15) +#define IS_NVDIMM_PRESENT(mcddrtcfg, i) GET_BITFIELD((mcddrtcfg), (i), (i)) #define numrank(reg) get_dimm_attr((reg), 12, 13, 0, 0, 2, "ranks") #define numrow(reg) get_dimm_attr((reg), 2, 4, 12, 1, 6, "rows") @@ -350,8 +354,6 @@ static int get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm, int banks = 16, ranks, rows, cols, npages; u64 size; - if (!IS_DIMM_PRESENT(mtr)) - return 0; ranks = numrank(mtr); rows = numrow(mtr); cols = numcol(mtr); @@ -383,6 +385,54 @@ static int get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm, return 1; } +static int get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc, + int chan, int dimmno) +{ + int smbios_handle; + u32 dev_handle; + u16 flags; + u64 size = 0; + + dev_handle = ACPI_NFIT_BUILD_DEVICE_HANDLE(dimmno, chan, imc->lmc, + imc->src_id, 0); + + smbios_handle = nfit_get_smbios_id(dev_handle, &flags); + if (smbios_handle == -EOPNOTSUPP) { + pr_warn_once(EDAC_MOD_STR ": Can't find size of NVDIMM. Try enabling CONFIG_ACPI_NFIT\n"); + goto unknown_size; + } + + if (smbios_handle < 0) { + skx_printk(KERN_ERR, "Can't find handle for NVDIMM ADR=%x\n", dev_handle); + goto unknown_size; + } + + if (flags & ACPI_NFIT_MEM_MAP_FAILED) { + skx_printk(KERN_ERR, "NVDIMM ADR=%x is not mapped\n", dev_handle); + goto unknown_size; + } + + size = dmi_memdev_size(smbios_handle); + if (size == ~0ull) + skx_printk(KERN_ERR, "Can't find size for NVDIMM ADR=%x/SMBIOS=%x\n", + dev_handle, smbios_handle); + +unknown_size: + dimm->nr_pages = size >> PAGE_SHIFT; + dimm->grain = 32; + dimm->dtype = DEV_UNKNOWN; + dimm->mtype = MEM_NVDIMM; + dimm->edac_mode = EDAC_SECDED; /* likely better than this */ + + edac_dbg(0, "mc#%d: channel %d, dimm %d, %llu Mb (%u pages)\n", + imc->mc, chan, dimmno, size >> 20, dimm->nr_pages); + + snprintf(dimm->label, sizeof(dimm->label), "CPU_SrcID#%u_MC#%u_Chan#%u_DIMM#%u", + imc->src_id, imc->lmc, chan, dimmno); + + return (size == 0 || size == ~0ull) ? 0 : 1; +} + #define SKX_GET_MTMTR(dev, reg) \ pci_read_config_dword((dev), 0x87c, &reg) @@ -399,20 +449,24 @@ static int skx_get_dimm_config(struct mem_ctl_info *mci) { struct skx_pvt *pvt = mci->pvt_info; struct skx_imc *imc = pvt->imc; + u32 mtr, amap, mcddrtcfg; struct dimm_info *dimm; int i, j; - u32 mtr, amap; int ndimms; for (i = 0; i < NUM_CHANNELS; i++) { ndimms = 0; pci_read_config_dword(imc->chan[i].cdev, 0x8C, &amap); + pci_read_config_dword(imc->chan[i].cdev, 0x400, &mcddrtcfg); for (j = 0; j < NUM_DIMMS; j++) { dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, j, 0); pci_read_config_dword(imc->chan[i].cdev, 0x80 + 4*j, &mtr); - ndimms += get_dimm_info(mtr, amap, dimm, imc, i, j); + if (IS_DIMM_PRESENT(mtr)) + ndimms += get_dimm_info(mtr, amap, dimm, imc, i, j); + else if (IS_NVDIMM_PRESENT(mcddrtcfg, j)) + ndimms += get_nvdimm_info(dimm, imc, i, j); } if (ndimms && !skx_check_ecc(imc->chan[0].cdev)) { skx_printk(KERN_ERR, "ECC is disabled on imc %d\n", imc->mc); @@ -468,13 +522,14 @@ static int skx_register_mci(struct skx_imc *imc) pvt = mci->pvt_info; pvt->imc = imc; - mci->ctl_name = kasprintf(GFP_KERNEL, "Skylake Socket#%d IMC#%d", imc->node_id, imc->lmc); + mci->ctl_name = kasprintf(GFP_KERNEL, "Skylake Socket#%d IMC#%d", + imc->node_id, imc->lmc); if (!mci->ctl_name) { rc = -ENOMEM; goto fail0; } - mci->mtype_cap = MEM_FLAG_DDR4; + mci->mtype_cap = MEM_FLAG_DDR4 | MEM_FLAG_NVDIMM; mci->edac_ctl_cap = EDAC_FLAG_NONE; mci->edac_cap = EDAC_FLAG_NONE; mci->mod_name = EDAC_MOD_STR; -- 2.13.0 SUSE Linux GmbH, GF: Felix Imendörffer, Jane Smithard, Graham Norton, HRB 21284 (AG Nürnberg) --