> -----Original Message----- > From: Sasha Levin <sashal@xxxxxxxxxx> > Sent: Thursday, November 25, 2021 20:32 > To: linux-kernel@xxxxxxxxxxxxxxx; stable@xxxxxxxxxxxxxxx > Cc: Limonciello, Mario <Mario.Limonciello@xxxxxxx>; Shah, Nehal- > bakulchandra <Nehal-bakulchandra.Shah@xxxxxxx>; Damien Le Moal > <damien.lemoal@xxxxxxxxxxxxxxxxxx>; Sasha Levin <sashal@xxxxxxxxxx>; > linux-ide@xxxxxxxxxxxxxxx > Subject: [PATCH AUTOSEL 5.15 28/39] ata: libahci: Adjust behavior when > StorageD3Enable _DSD is set > > From: Mario Limonciello <mario.limonciello@xxxxxxx> > > [ Upstream commit 7c5f641a5914ce0303b06bcfcd7674ee64aeebe9 ] > > The StorageD3Enable _DSD is used for the vendor to indicate that the disk > should be opted into or out of a different behavior based upon the platform > design. > > For AMD's Renoir and Green Sardine platforms it's important that any > attached SATA storage has transitioned into DevSlp when s2idle is used. > > If the disk is left in active/partial/slumber, then the system is not able > to resume properly. > > When the StorageD3Enable _DSD is detected, check the system is using > s2idle > and DevSlp is enabled and if so explicitly wait long enough for the disk to > enter DevSlp. > > Cc: Nehal-bakulchandra Shah <Nehal-bakulchandra.Shah@xxxxxxx> > BugLink: > https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fbugz > illa.kernel.org%2Fshow_bug.cgi%3Fid%3D214091&data=04%7C01%7Cm > ario.limonciello%40amd.com%7C15dc139812a0497d31bc08d9b0850f45%7C3d > d8961fe4884e608e11a82d994e183d%7C0%7C0%7C637734907816859936%7CU > nknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI > 6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=%2BX2cfl%2BYeFYWZJ%2 > FPFWX%2FzxnNtneb2er7w%2BeJpVxxBcU%3D&reserved=0 > Link: > https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fdocs > .microsoft.com%2Fen-us%2Fwindows-hardware%2Fdesign%2Fcomponent- > guidelines%2Fpower-management-for-storage-hardware-devices- > intro&data=04%7C01%7Cmario.limonciello%40amd.com%7C15dc139812 > a0497d31bc08d9b0850f45%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C > 0%7C637734907816859936%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLj > AwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000& > sdata=ubGKpzMA6EaXugHAanwRUQJ2lvL957wBRFKKMjUBGlw%3D&re > served=0 > Signed-off-by: Mario Limonciello <mario.limonciello@xxxxxxx> > Signed-off-by: Damien Le Moal <damien.lemoal@xxxxxxxxxxxxxxxxxx> > Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> > --- > drivers/ata/libahci.c | 15 +++++++++++++++ > 1 file changed, 15 insertions(+) > > diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c > index 5b3fa2cbe7223..395772fa39432 100644 > --- a/drivers/ata/libahci.c > +++ b/drivers/ata/libahci.c > @@ -2305,6 +2305,18 @@ int ahci_port_resume(struct ata_port *ap) > EXPORT_SYMBOL_GPL(ahci_port_resume); > > #ifdef CONFIG_PM > +static void ahci_handle_s2idle(struct ata_port *ap) > +{ > + void __iomem *port_mmio = ahci_port_base(ap); > + u32 devslp; > + > + if (pm_suspend_via_firmware()) > + return; > + devslp = readl(port_mmio + PORT_DEVSLP); > + if ((devslp & PORT_DEVSLP_ADSE)) > + ata_msleep(ap, devslp_idle_timeout); > +} > + > static int ahci_port_suspend(struct ata_port *ap, pm_message_t mesg) > { > const char *emsg = NULL; > @@ -2318,6 +2330,9 @@ static int ahci_port_suspend(struct ata_port *ap, > pm_message_t mesg) > ata_port_freeze(ap); > } > > + if (acpi_storage_d3(ap->host->dev)) > + ahci_handle_s2idle(ap); > + > ahci_rpm_put_port(ap); > return rc; > } > -- > 2.33.0 Sasha, No concerns for me to 5.15 or any of the earlier kernels the autosel picked, but would you mind also sending this to 5.14.y too? Thanks,
