On 2021/11/08 18:47, Geert Uytterhoeven wrote:
> Hi Damien,
>
> On Fri, Nov 5, 2021 at 8:31 AM Damien Le Moal
> <damien.lemoal@xxxxxxxxxxxxxxxxxx> wrote:
>> Some ATA drives are very slow to respond to READ_LOG_EXT and
>> READ_LOG_DMA_EXT commands issued from ata_dev_configure() when the
>> device is revalidated right after resuming a system or inserting the
>> ATA adapter driver (e.g. ahci). The default 5s timeout
>> (ATA_EH_CMD_DFL_TIMEOUT) used for these commands is too short, causing
>> errors during the device configuration. Ex:
>>
>> ...
>> ata9: SATA max UDMA/133 abar m524288@0x9d200000 port 0x9d200400 irq 209
>> ata9: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
>> ata9.00: ATA-9: XXX XXXXXXXXXXXXXXX, XXXXXXXX, max UDMA/133
>> ata9.00: qc timeout (cmd 0x2f)
>> ata9.00: Read log page 0x00 failed, Emask 0x4
>> ata9.00: Read log page 0x00 failed, Emask 0x40
>> ata9.00: NCQ Send/Recv Log not supported
>> ata9.00: Read log page 0x08 failed, Emask 0x40
>> ata9.00: 27344764928 sectors, multi 16: LBA48 NCQ (depth 32), AA
>> ata9.00: Read log page 0x00 failed, Emask 0x40
>> ata9.00: ATA Identify Device Log not supported
>> ata9.00: failed to set xfermode (err_mask=0x40)
>> ata9: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
>> ata9.00: configured for UDMA/133
>> ...
>>
>> The timeoutout error causes a soft reset of the drive link, followed in
>
> timeout
>
>> most cases by a successful revalidation as that give enough time to the
>> drive to become fully ready to quickly process the read log commands.
>> However, in some cases, this also fails resulting in the device being
>> dropped.
>>
>> Fix this by using adding the ata_eh_revalidate_timeouts entries for the
>> READ_LOG_EXT and READ_LOG_DMA_EXT commands. This defines a timeout
>> increased to 15s, retriable one time.
>>
>> Reported-by: Geert Uytterhoeven <geert@xxxxxxxxxxxxxx>
>> Cc: stable@xxxxxxxxxxxxxxx
>> Signed-off-by: Damien Le Moal <damien.lemoal@xxxxxxxxxxxxxxxxxx>
>
> Thanks for your patch! Impact on system resume on Salvator-XS:
>
> s2idle:
>
> ata1: link resume succeeded after 1 retries
> ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
> -ata1.00: qc timeout (cmd 0x2f)
> -ata1.00: Read log page 0x00 failed, Emask 0x4
> -ata1.00: ATA Identify Device Log not supported
> -ata1.00: failed to set xfermode (err_mask=0x40)
> -ata1: link resume succeeded after 1 retries
> -ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
> ata1.00: ATA Identify Device Log not supported
> ata1.00: ATA Identify Device Log not supported
> ata1.00: configured for UDMA/133
>
> s2ram:
>
> ata1: link resume succeeded after 1 retries
> ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
> -ata1.00: qc timeout (cmd 0x2f)
> -ata1.00: Read log page 0x00 failed, Emask 0x4
> -ata1.00: ATA Identify Device Log not supported
> -ata1.00: failed to set xfermode (err_mask=0x40)
> -ata1: link resume succeeded after 1 retries
> -ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
> -ata1.00: NODEV after polling detection
> -ata1.00: revalidation failed (errno=-2)
> -ata1: link resume succeeded after 1 retries
> -ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
> ata1.00: ATA Identify Device Log not supported
> ata1.00: ATA Identify Device Log not supported
> ata1.00: configured for UDMA/133
>
> Tested-by: Geert Uytterhoeven <geert+renesas@xxxxxxxxx>
Great ! Thanks for testing.
>
> Gr{oetje,eeting}s,
>
> Geert
>
> --
> Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@xxxxxxxxxxxxxx
>
> In personal conversations with technical people, I call myself a hacker. But
> when I'm talking to journalists I just say "programmer" or something like that.
> -- Linus Torvalds
>
--
Damien Le Moal
Western Digital Research
