APPLIED[U]: [L/Unstable] [PATCH 6/6] EDAC/i10nm: Skip the absent memory controllers

[Andrea Righi]

On Wed, Jul 26, 2023 at 01:59:17PM +0800, Kai-Heng Feng wrote:
> From: Qiuxu Zhuo <qiuxu.zhuo at intel.com>
> 
> BugLink: https://bugs.launchpad.net/bugs/2028746
> 
> Some Sapphire Rapids workstations' absent memory controllers
> still appear as PCIe devices that fool the i10nm_edac driver
> and result in "shift exponent -66 is negative" call traces
> from skx_get_dimm_info().
> 
> Skip the absent memory controllers to avoid the call traces.
> 
> Reported-by: Kai-Heng Feng <kai.heng.feng at canonical.com>
> Closes: https://lore.kernel.org/linux-edac/CAAd53p41Ku1m1rapeqb1xtD+kKuk+BaUW=dumuoF0ZO3GhFjFA@mail.gmail.com/T/#m5de16dce60a8c836ec235868c7c16e3fefad0cc2
> Tested-by: Kai-Heng Feng <kai.heng.feng at canonical.com>
> Reported-by: Koba Ko <koba.ko at canonical.com>
> Closes: https://lore.kernel.org/linux-edac/SA1PR11MB71305B71CCCC3D9305835202892AA@SA1PR11MB7130.namprd11.prod.outlook.com/T/#t
> Tested-by: Koba Ko <koba.ko at canonical.com>
> Fixes: d4dc89d069aa ("EDAC, i10nm: Add a driver for Intel 10nm server processors")
> Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo at intel.com>
> Signed-off-by: Tony Luck <tony.luck at intel.com>
> Link: https://lore.kernel.org/r/20230710013232.59712-1-qiuxu.zhuo@intel.com
> (cherry picked from commit c545f5e412250555bd4e717d062b117f20bab418 linux-next)
> Signed-off-by: Kai-Heng Feng <kai.heng.feng at canonical.com>

Applied to mantic/linux-unstable.

Thanks,
-Andrea

> ---
>  drivers/edac/i10nm_base.c | 54 +++++++++++++++++++++++++++++++++++----
>  1 file changed, 49 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c
> index 46034310b78e..7ed98b85aa90 100644
> --- a/drivers/edac/i10nm_base.c
> +++ b/drivers/edac/i10nm_base.c
> @@ -622,13 +622,49 @@ static struct pci_dev *get_ddr_munit(struct skx_dev *d, int i, u32 *offset, unsi
>  	return mdev;
>  }
>  
> +/**
> + * i10nm_imc_absent() - Check whether the memory controller @imc is absent
> + *
> + * @imc    : The pointer to the structure of memory controller EDAC device.
> + *
> + * RETURNS : true if the memory controller EDAC device is absent, false otherwise.
> + */
> +static bool i10nm_imc_absent(struct skx_imc *imc)
> +{
> +	u32 mcmtr;
> +	int i;
> +
> +	switch (res_cfg->type) {
> +	case SPR:
> +		for (i = 0; i < res_cfg->ddr_chan_num; i++) {
> +			mcmtr = I10NM_GET_MCMTR(imc, i);
> +			edac_dbg(1, "ch%d mcmtr reg %x\n", i, mcmtr);
> +			if (mcmtr != ~0)
> +				return false;
> +		}
> +
> +		/*
> +		 * Some workstations' absent memory controllers still
> +		 * appear as PCIe devices, misleading the EDAC driver.
> +		 * By observing that the MMIO registers of these absent
> +		 * memory controllers consistently hold the value of ~0.
> +		 *
> +		 * We identify a memory controller as absent by checking
> +		 * if its MMIO register "mcmtr" == ~0 in all its channels.
> +		 */
> +		return true;
> +	default:
> +		return false;
> +	}
> +}
> +
>  static int i10nm_get_ddr_munits(void)
>  {
>  	struct pci_dev *mdev;
>  	void __iomem *mbase;
>  	unsigned long size;
>  	struct skx_dev *d;
> -	int i, j = 0;
> +	int i, lmc, j = 0;
>  	u32 reg, off;
>  	u64 base;
>  
> @@ -654,7 +690,7 @@ static int i10nm_get_ddr_munits(void)
>  		edac_dbg(2, "socket%d mmio base 0x%llx (reg 0x%x)\n",
>  			 j++, base, reg);
>  
> -		for (i = 0; i < res_cfg->ddr_imc_num; i++) {
> +		for (lmc = 0, i = 0; i < res_cfg->ddr_imc_num; i++) {
>  			mdev = get_ddr_munit(d, i, &off, &size);
>  
>  			if (i == 0 && !mdev) {
> @@ -664,8 +700,6 @@ static int i10nm_get_ddr_munits(void)
>  			if (!mdev)
>  				continue;
>  
> -			d->imc[i].mdev = mdev;
> -
>  			edac_dbg(2, "mc%d mmio base 0x%llx size 0x%lx (reg 0x%x)\n",
>  				 i, base + off, size, reg);
>  
> @@ -676,7 +710,17 @@ static int i10nm_get_ddr_munits(void)
>  				return -ENODEV;
>  			}
>  
> -			d->imc[i].mbase = mbase;
> +			d->imc[lmc].mbase = mbase;
> +			if (i10nm_imc_absent(&d->imc[lmc])) {
> +				pci_dev_put(mdev);
> +				iounmap(mbase);
> +				d->imc[lmc].mbase = NULL;
> +				edac_dbg(2, "Skip absent mc%d\n", i);
> +				continue;
> +			} else {
> +				d->imc[lmc].mdev = mdev;
> +				lmc++;
> +			}
>  		}
>  	}
>  
> -- 
> 2.34.1
> 
> 
> -- 
> kernel-team mailing list
> kernel-team at lists.ubuntu.com
> https://lists.ubuntu.com/mailman/listinfo/kernel-team