RE: [PATCH v2 4/4] EDAC: synopsys: Add useful debug and output information for 64bit systems

[Sherry Sun]

Hi Robert,

> -----Original Message-----
> From: Robert Richter <rrichter@xxxxxxxxxxx>
> Sent: 2020年4月1日 18:57
> To: Sherry Sun <sherry.sun@xxxxxxx>
> Cc: bp@xxxxxxxxx; mchehab@xxxxxxxxxx; tony.luck@xxxxxxxxx;
> james.morse@xxxxxxx; michal.simek@xxxxxxxxxx;
> manish.narani@xxxxxxxxxx; linux-edac@xxxxxxxxxxxxxxx; linux-
> kernel@xxxxxxxxxxxxxxx; Frank Li <frank.li@xxxxxxx>
> Subject: Re: [PATCH v2 4/4] EDAC: synopsys: Add useful debug and output
> information for 64bit systems
> 
> On 01.04.20 15:39:09, Sherry Sun wrote:
> > Now the synopsys_edac driver only support to output the 32-bit error
> > data, but for 64 bit systems, such as i.MX8MP, 64 bit error data is
> > needed. At the same time, when CE/UE happens, syndrome data is also
> > useful to showed to user. So here add data_high and syndrome data for
> > 64-bit systems.
> >
> > And in order to distinguish 64-bit systems and other systems, here
> > adjust the position of the zynqmp_get_dtype(), so we can called this
> > function to distinguish it. To ensure that functions of the same
> > function are in the same position, here adjust the position of the
> > zynq_get_dtype() too.
> >
> > Signed-off-by: Sherry Sun <sherry.sun@xxxxxxx>
> > ---
> >  drivers/edac/synopsys_edac.c | 182
> > ++++++++++++++++++++---------------
> >  1 file changed, 102 insertions(+), 80 deletions(-)
> >
> > diff --git a/drivers/edac/synopsys_edac.c
> > b/drivers/edac/synopsys_edac.c index bf4202a24683..e8c3631ddff4
> 100644
> > --- a/drivers/edac/synopsys_edac.c
> > +++ b/drivers/edac/synopsys_edac.c
> > @@ -278,18 +278,22 @@
> >   * @col:	Column number.
> >   * @bank:	Bank number.
> >   * @bitpos:	Bit position.
> > - * @data:	Data causing the error.
> > + * @data_low:	Low bit data causing the error.
> > + * @data_high:	High bit data causing the error(used for 64 bit
> systems).
> >   * @bankgrpnr:	Bank group number.
> >   * @blknr:	Block number.
> > + * @syndrome:	Syndrome of the error.
> >   */
> >  struct ecc_error_info {
> >  	u32 row;
> >  	u32 col;
> >  	u32 bank;
> >  	u32 bitpos;
> > -	u32 data;
> > +	u32 data_low;
> > +	u32 data_high;
> 
> Where are 16, 32 and 64 bit widths. You could handle them all the same in a
> u64.
> 
> If I am not wrong, the width is fix for the whole mci. So you could create
> various .get_error_info() functions depending on the data width without run
> time width checks.
> 

Yes, here we can use u64. Will correct it in v3.
For the zynq, it's 16-bit bus width, for imx8mp, it's 64-bit bus width.
But for zynqmp, it's optional between 32-bit and 64-bit bus width,
So we had better run time check the bus width, what do you think?

> >  	u32 bankgrpnr;
> >  	u32 blknr;
> > +	u32 syndrome;
> >  };
> >
> >  /**
> 
> > @@ -399,7 +467,7 @@ static int zynq_get_error_info(struct
> synps_edac_priv *priv)
> >  	p->ueinfo.row = (regval & ADDR_ROW_MASK) >> ADDR_ROW_SHIFT;
> >  	p->ueinfo.col = regval & ADDR_COL_MASK;
> >  	p->ueinfo.bank = (regval & ADDR_BANK_MASK) >>
> ADDR_BANK_SHIFT;
> > -	p->ueinfo.data = readl(base + UE_DATA_31_0_OFST);
> > +	p->ueinfo.data_low = readl(base + UE_DATA_31_0_OFST);
> >  	clearval |= ECC_CTRL_CLR_UE_ERR;
> >
> >  out:
> > @@ -443,10 +511,14 @@ static int zynqmp_get_error_info(struct
> synps_edac_priv *priv)
> >  	p->ceinfo.bankgrpnr = (regval &
> 	ECC_CEADDR1_BNKGRP_MASK) >>
> >  					ECC_CEADDR1_BNKGRP_SHIFT;
> >  	p->ceinfo.blknr = (regval & ECC_CEADDR1_BLKNR_MASK);
> > -	p->ceinfo.data = readl(base + ECC_CSYND0_OFST);
> > -	edac_dbg(2, "ECCCSYN0: 0x%08X ECCCSYN1: 0x%08X ECCCSYN2:
> 0x%08X\n",
> > -		 readl(base + ECC_CSYND0_OFST), readl(base +
> ECC_CSYND1_OFST),
> > -		 readl(base + ECC_CSYND2_OFST));
> > +	p->ceinfo.data_low = readl(base + ECC_CSYND0_OFST);
> > +	if (zynqmp_get_dtype(base) == DEV_X8) {
> > +		p->ceinfo.data_high = readl(base + ECC_CSYND1_OFST);
> > +		p->ceinfo.syndrome = readl(base + ECC_CSYND2_OFST);
> > +		edac_dbg(2, "CE data_low: 0x%08X data_high: 0x%08X
> syndrome: 0x%08X\n",
> > +			 p->ceinfo.data_low, p->ceinfo.data_high,
> > +			 p->ceinfo.syndrome);
> 
> You are loosing edac_dbg() here for the != DEV_X8 cases.
> 
> > +	}
> >  ue_err:
> >  	if (!p->ue_cnt)
> >  		goto out;
> > @@ -459,7 +531,14 @@ static int zynqmp_get_error_info(struct
> synps_edac_priv *priv)
> >  	p->ueinfo.bank = (regval & ECC_CEADDR1_BNKNR_MASK) >>
> >  					ECC_CEADDR1_BNKNR_SHIFT;
> >  	p->ueinfo.blknr = (regval & ECC_CEADDR1_BLKNR_MASK);
> > -	p->ueinfo.data = readl(base + ECC_UESYND0_OFST);
> > +	p->ueinfo.data_low = readl(base + ECC_UESYND0_OFST);
> > +	if (zynqmp_get_dtype(base) == DEV_X8) {
> > +		p->ueinfo.data_high = readl(base + ECC_UESYND1_OFST);
> > +		p->ueinfo.syndrome = readl(base + ECC_UESYND2_OFST);
> > +		edac_dbg(2, "UE data_low: 0x%08X data_high: 0x%08X
> syndrome: 0x%08X\n",
> > +			 p->ueinfo.data_low, p->ueinfo.data_high,
> > +			 p->ueinfo.syndrome);
> 
> Similar here, no edac_dbg() for != DEV_X8.

Thanks, will correct it in v3.

> 
> > +	}
> >  out:
> >  	clearval = ECC_CTRL_CLR_CE_ERR | ECC_CTRL_CLR_CE_ERRCNT;
> >  	clearval |= ECC_CTRL_CLR_UE_ERR | ECC_CTRL_CLR_UE_ERRCNT;
> @@ -480,20
> > +559,27 @@ static void handle_error(struct mem_ctl_info *mci, struct
> > synps_ecc_status *p)  {
> >  	struct synps_edac_priv *priv = mci->pvt_info;
> >  	struct ecc_error_info *pinf;
> > +	int n;
> >
> >  	if (p->ce_cnt) {
> >  		pinf = &p->ceinfo;
> >  		if (priv->p_data->quirks & DDR_ECC_INTR_SUPPORT) {
> > -			snprintf(priv->message, SYNPS_EDAC_MSG_SIZE,
> > -				 "DDR ECC error type:%s Row %d Bank %d
> BankGroup Number %d Block Number %d Bit Position: %d Data: 0x%08x",
> > -				 "CE", pinf->row, pinf->bank,
> > -				 pinf->bankgrpnr, pinf->blknr,
> > -				 pinf->bitpos, pinf->data);
> > +			n = snprintf(priv->message, SYNPS_EDAC_MSG_SIZE,
> > +				     "DDR ECC error type:%s Row %d Bank %d
> BankGroup Number %d Block Number %d Bit Position: %d Data: 0x%08x",
> > +				     "CE", pinf->row, pinf->bank,
> > +				     pinf->bankgrpnr, pinf->blknr,
> > +				     pinf->bitpos, pinf->data_low);
> > +
> > +			if (zynqmp_get_dtype(priv->baseaddr) == DEV_X8)
> 
> This is zynqmp specific, right? but you call it in the generic function
> handle_error().

Yes, although handle_error() is a generic function, 
but this operation is checked by priv->p_data->quirks,
so here is zynqmp and imx8mp specific.

Best regards
Sherry Sun

> 
> -Robert
> 
> > +				snprintf(priv->message + n,
> > +					 SYNPS_EDAC_MSG_SIZE - n,
> > +					 " Data_high: 0x%08x Syndrome:
> 0x%08x",
> > +					 pinf->data_high, pinf->syndrome);
> >  		} else {
> >  			snprintf(priv->message, SYNPS_EDAC_MSG_SIZE,
> >  				 "DDR ECC error type:%s Row %d Bank %d
> Col %d Bit Position: %d Data: 0x%08x",
> >  				 "CE", pinf->row, pinf->bank, pinf->col,
> > -				 pinf->bitpos, pinf->data);
> > +				 pinf->bitpos, pinf->data_low);
> >  		}
> >
> >  		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,