-----Original Message-----
From: Sasha Levin <sashal@kernel.org>
Sent: Thursday, November 25, 2021 20:32
To: linux-kernel@vger.kernel.org; stable@vger.kernel.org
Cc: Limonciello, Mario <Mario.Limonciello@amd.com>; Shah, Nehal-
bakulchandra [off-list ref]; Damien Le Moal
[off-list ref]; Sasha Levin [off-list ref];
linux-ide@vger.kernel.org
Subject: [PATCH AUTOSEL 5.15 28/39] ata: libahci: Adjust behavior when
StorageD3Enable _DSD is set

From: Mario Limonciello <mario.limonciello@amd.com>

[ 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 <redacted>
BugLink:
https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fbugz
illa.kernel.org%2Fshow_bug.cgi%3Fid%3D214091&amp;data=04%7C01%7Cm
ario.limonciello%40amd.com%7C15dc139812a0497d31bc08d9b0850f45%7C3d
d8961fe4884e608e11a82d994e183d%7C0%7C0%7C637734907816859936%7CU
nknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI
6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&amp;sdata=%2BX2cfl%2BYeFYWZJ%2
FPFWX%2FzxnNtneb2er7w%2BeJpVxxBcU%3D&amp;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&amp;data=04%7C01%7Cmario.limonciello%40amd.com%7C15dc139812
a0497d31bc08d9b0850f45%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C
0%7C637734907816859936%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLj
AwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&amp;
sdata=ubGKpzMA6EaXugHAanwRUQJ2lvL957wBRFKKMjUBGlw%3D&amp;re
served=0
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Damien Le Moal <redacted>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 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