Re: [PATCH 2/2] mtd: cfi_cmdset_0002: fix delayed error detection on HyperFlash

[Tokunori Ikegami <ikegami.t@gmail.com>]

Hi,

On 2019/10/04 3:34, Sergei Shtylyov wrote:
> The commit 4844ef80305d ("mtd: cfi_cmdset_0002: Add support for polling
> status register") added checking for the status register error bits into
> chip_good() to only return 1 if these bits are zero. Unfortunately, this
> means that polling using chip_good() always reaches a time-out condition
> when erase or program failure bits are set. I think the status register
> error checking should be fully delegated to cfi_check_err_status() that
> should return whether any error bits were set or not...
>
> Fixes: 4844ef80305d ("mtd: cfi_cmdset_0002: Add support for polling status register")
> Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
>
> ---
>   drivers/mtd/chips/cfi_cmdset_0002.c |   55 +++++++++++++++++++-----------------
>   1 file changed, 30 insertions(+), 25 deletions(-)
>
> Index: linux/drivers/mtd/chips/cfi_cmdset_0002.c
> ===================================================================
> --- linux.orig/drivers/mtd/chips/cfi_cmdset_0002.c
> +++ linux/drivers/mtd/chips/cfi_cmdset_0002.c
> @@ -123,14 +123,14 @@ static int cfi_use_status_reg(struct cfi
>   		(extp->SoftwareFeatures & poll_mask) == CFI_POLL_STATUS_REG;
>   }
>   
> -static void cfi_check_err_status(struct map_info *map, struct flchip *chip,
> -				 unsigned long adr)
> +static int cfi_check_err_status(struct map_info *map, struct flchip *chip,
> +				unsigned long adr)
>   {
>   	struct cfi_private *cfi = map->fldrv_priv;
>   	map_word status;
>   
>   	if (!cfi_use_status_reg(cfi))
> -		return;
> +		return 0;
>   
>   	cfi_send_gen_cmd(0x70, cfi->addr_unlock1, chip->start, map, cfi,
>   			 cfi->device_type, NULL);
> @@ -138,7 +138,7 @@ static void cfi_check_err_status(struct
>   
>   	/* The error bits are invalid while the chip's busy */
>   	if (!map_word_bitsset(map, status, CMD(CFI_SR_DRB)))
> -		return;
> +		return 0;
>   
>   	if (map_word_bitsset(map, status, CMD(0x3a))) {
>   		unsigned long chipstatus = MERGESTATUS(status);
> @@ -155,7 +155,9 @@ static void cfi_check_err_status(struct
>   		if (chipstatus & CFI_SR_SLSB)
>   			pr_err("%s sector write protected, status %lx\n",
>   			       map->name, chipstatus);
> +		return 1;
Is it okay to be returned 1 for the errors CFI_SR_WBASB and CFI_SR_SLSB 
also?
Before the change only CFI_SR_ESB and CFI_SR_PSB were checked by 
chip_good().
>   	}
> +	return 0;
>   }
>   
>   /* #define DEBUG_CFI_FEATURES */
> @@ -852,20 +854,16 @@ static int __xipram chip_good(struct map
>   
>   	if (cfi_use_status_reg(cfi)) {
>   		map_word ready = CMD(CFI_SR_DRB);
> -		map_word err = CMD(CFI_SR_PSB | CFI_SR_ESB);
> +
>   		/*
>   		 * For chips that support status register, check device
> -		 * ready bit and Erase/Program status bit to know if
> -		 * operation succeeded.
> +		 * ready bit
>   		 */
>   		cfi_send_gen_cmd(0x70, cfi->addr_unlock1, chip->start, map, cfi,
>   				 cfi->device_type, NULL);
>   		curd = map_read(map, addr);
>   
> -		if (map_word_andequal(map, curd, ready, ready))
> -			return !map_word_bitsset(map, curd, err);
> -
> -		return 0;
> +		return map_word_andequal(map, curd, ready, ready);
>   	}
>   
>   	oldd = map_read(map, addr);
> @@ -1703,8 +1701,11 @@ static int __xipram do_write_oneword_onc
>   			break;
>   		}
>   
> -		if (chip_good(map, chip, adr, datum))
> +		if (chip_good(map, chip, adr, datum)) {
> +			if (cfi_check_err_status(map, chip, adr))
> +				ret = -EIO;
>   			break;
> +		}
>   
>   		/* Latency issues. Drop the lock, wait a while and retry */
>   		UDELAY(map, chip, adr, 1);
> @@ -1777,7 +1778,6 @@ static int __xipram do_write_oneword_ret
>   	ret = do_write_oneword_once(map, chip, adr, datum, mode, cfi);
>   	if (ret) {
>   		/* reset on all failures. */
> -		cfi_check_err_status(map, chip, adr);
>   		map_write(map, CMD(0xF0), chip->start);
>   		/* FIXME - should have reset delay before continuing */
>   
> @@ -1974,12 +1974,17 @@ static int __xipram do_write_buffer_wait
>   		 */
>   		if (time_after(jiffies, timeo) &&
>   		    !chip_good(map, chip, adr, datum)) {
> +			pr_warn("MTD %s(): software timeout, address:0x%.8lx.\n",
> +				__func__, adr);

Is there any reason to change the message to use pr_warn() from pr_err()?
In the past it was changed to use pr_err() from printk(KERN_WARNING) as 
mentioned by the maintainer.

Regards,
Ikegami

>   			ret = -EIO;
>   			break;
>   		}
>   
> -		if (chip_good(map, chip, adr, datum))
> +		if (chip_good(map, chip, adr, datum)) {
> +			if (cfi_check_err_status(map, chip, adr))
> +				ret = -EIO;
>   			break;
> +		}
>   
>   		/* Latency issues. Drop the lock, wait a while and retry */
>   		UDELAY(map, chip, adr, 1);
> @@ -2075,12 +2080,8 @@ static int __xipram do_write_buffer(stru
>   				chip->word_write_time);
>   
>   	ret = do_write_buffer_wait(map, chip, adr, datum);
> -	if (ret) {
> -		cfi_check_err_status(map, chip, adr);
> +	if (ret)
>   		do_write_buffer_reset(map, chip, cfi);
> -		pr_err("MTD %s(): software timeout, address:0x%.8lx.\n",
> -		       __func__, adr);
> -	}
>   
>   	xip_enable(map, chip, adr);
>   
> @@ -2275,9 +2276,9 @@ retry:
>   		udelay(1);
>   	}
>   
> -	if (!chip_good(map, chip, adr, datum)) {
> +	if (!chip_good(map, chip, adr, datum) ||
> +	    cfi_check_err_status(map, chip, adr)) {
>   		/* reset on all failures. */
> -		cfi_check_err_status(map, chip, adr);
>   		map_write(map, CMD(0xF0), chip->start);
>   		/* FIXME - should have reset delay before continuing */
>   
> @@ -2471,8 +2472,11 @@ static int __xipram do_erase_chip(struct
>   			chip->erase_suspended = 0;
>   		}
>   
> -		if (chip_good(map, chip, adr, map_word_ff(map)))
> +		if (chip_good(map, chip, adr, map_word_ff(map))) {
> +			if (cfi_check_err_status(map, chip, adr))
> +				ret = -EIO;
>   			break;
> +		}
>   
>   		if (time_after(jiffies, timeo)) {
>   			printk(KERN_WARNING "MTD %s(): software timeout\n",
> @@ -2487,7 +2491,6 @@ static int __xipram do_erase_chip(struct
>   	/* Did we succeed? */
>   	if (ret) {
>   		/* reset on all failures. */
> -		cfi_check_err_status(map, chip, adr);
>   		map_write(map, CMD(0xF0), chip->start);
>   		/* FIXME - should have reset delay before continuing */
>   
> @@ -2568,8 +2571,11 @@ static int __xipram do_erase_oneblock(st
>   			chip->erase_suspended = 0;
>   		}
>   
> -		if (chip_good(map, chip, adr, map_word_ff(map)))
> +		if (chip_good(map, chip, adr, map_word_ff(map))) {
> +			if (cfi_check_err_status(map, chip, adr))
> +				ret = -EIO;
>   			break;
> +		}
>   
>   		if (time_after(jiffies, timeo)) {
>   			printk(KERN_WARNING "MTD %s(): software timeout\n",
> @@ -2584,7 +2590,6 @@ static int __xipram do_erase_oneblock(st
>   	/* Did we succeed? */
>   	if (ret) {
>   		/* reset on all failures. */
> -		cfi_check_err_status(map, chip, adr);
>   		map_write(map, CMD(0xF0), chip->start);
>   		/* FIXME - should have reset delay before continuing */
>   
>
> ______________________________________________________
> Linux MTD discussion mailing list
> http://lists.infradead.org/mailman/listinfo/linux-mtd/
>

______________________________________________________
Linux MTD discussion mailing list
http://lists.infradead.org/mailman/listinfo/linux-mtd/