On Thu, Nov 30, 2017 at 12:40:42PM -0800, Tony Luck wrote:
> 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@xxxxxxxxx>
> ---
> drivers/edac/Kconfig | 2 ++
> drivers/edac/skx_edac.c | 56 ++++++++++++++++++++++++++++++++++++++++++++-----
> 2 files changed, 53 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
> index 96afb2aeed18..5c0c4a358f67 100644
> --- a/drivers/edac/Kconfig
> +++ b/drivers/edac/Kconfig
> @@ -232,6 +232,8 @@ config EDAC_SBRIDGE
> config EDAC_SKX
> tristate "Intel Skylake server Integrated MC"
> depends on PCI && X86_64 && X86_MCE_INTEL && PCI_MMCONFIG
> + select DMI
> + select ACPI_NFIT
Hmm, that ACPI_NFIT depends on a bunch of stuff and enabling EDAC_SKX
would pull in all that. Should we make this a user choice instead?
I mean, there could be boxes which don't have nvdimms so all that code
would be dead weight there...
> help
> Support for error detection and correction the Intel
> Skylake server Integrated Memory Controllers.
> diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c
> index 16dea97568a1..814a5245029c 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>
> @@ -298,6 +301,7 @@ 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, 1, 2, "ranks")
> #define numrow(reg) get_dimm_attr((reg), 2, 4, 12, 1, 6, "rows")
> @@ -346,8 +350,6 @@ 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);
> @@ -379,6 +381,46 @@ 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;
> +
> + 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 < 0) {
> + skx_printk(KERN_ERR, "Can't find handle for NVDIMM ADR=%x\n", dev_handle);
> + return 0;
> + }
<---- newline here.
> + if (flags & ACPI_NFIT_MEM_MAP_FAILED) {
> + skx_printk(KERN_ERR, "NVDIMM ADR=%x is not mapped\n", dev_handle);
> + return 0;
> + }
<---- newline here.
> + 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;
> + }
Ditto.
> + 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 */
Ditto.
/me hands aegl a bunch of newlines - seems he's all out of \n's
> + 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, ®)
--
Regards/Gruss,
Boris.
Good mailing practices for 400: avoid top-posting and trim the reply.
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
