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>
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
