RE: [PATCH] iommu/amd: Disable IOMMU on Stoney Ridge systems

[Deucher, Alexander]

> -----Original Message-----
> From: Kai-Heng Feng <kai.heng.feng@xxxxxxxxxxxxx>
> Sent: Sunday, November 24, 2019 4:43 AM
> To: joro@xxxxxxxxxx
> Cc: iommu@xxxxxxxxxxxxxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx; Kai-
> Heng Feng <kai.heng.feng@xxxxxxxxxxxxx>; Deucher, Alexander
> <Alexander.Deucher@xxxxxxx>
> Subject: [PATCH] iommu/amd: Disable IOMMU on Stoney Ridge systems
> 
> Serious screen flickering when Stoney Ridge outputs to a 4K monitor.
> 
> According to Alex Deucher, IOMMU isn't enabled on Windows, so let's do the
> same here to avoid screen flickering on 4K monitor.
> 
> Cc: Alex Deucher <alexander.deucher@xxxxxxx>
> Bug:
> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgitla
> b.freedesktop.org%2Fdrm%2Famd%2Fissues%2F961&amp;data=02%7C01%7
> Calexander.deucher%40amd.com%7C75a108e9888645728fc208d770c2b418%
> 7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637101853875648481
> &amp;sdata=eQ%2FmiFfy%2FHRJSVurfdnvT%2FLdNMYetIPQdFgnU93l%2Fks
> %3D&amp;reserved=0
> Signed-off-by: Kai-Heng Feng <kai.heng.feng@xxxxxxxxxxxxx>
> ---
>  drivers/iommu/amd_iommu_init.c | 10 +++++++++-
>  1 file changed, 9 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/iommu/amd_iommu_init.c
> b/drivers/iommu/amd_iommu_init.c index 568c52317757..e05f1b269be6
> 100644
> --- a/drivers/iommu/amd_iommu_init.c
> +++ b/drivers/iommu/amd_iommu_init.c
> @@ -2516,6 +2516,7 @@ static int __init early_amd_iommu_init(void)
>  	struct acpi_table_header *ivrs_base;
>  	acpi_status status;
>  	int i, remap_cache_sz, ret = 0;
> +	u32 pci_id;
> 
>  	if (!amd_iommu_detected)
>  		return -ENODEV;
> @@ -2603,6 +2604,13 @@ static int __init early_amd_iommu_init(void)
>  	if (ret)
>  		goto out;
> 
> +	/* Get the host bridge VID/PID and disable IOMMU if it's Stoney
> Ridge */
> +	pci_id = read_pci_config(0, 0, 0, 0);
> +	if ((pci_id & 0xffff) == 0x1022 && (pci_id >> 16) == 0x1576) {

I'm not sure if the IOMMU device id is unique to stoney.  I think it's the same DID for the entire APU generation.   I think it would be better to walk the bus and try and find the stoney GPU and only in that case, disable the IOMMU.  E.g., if the user has disabled the GPU portion of the APU or has a dGPU installed, they may will want to use the IOMMU.  It's only the integrated GPU that has a problem when trying to display high res modes out of system memory with the IOMMU due to the added latency.
The stoney GPU is VID 0x1002, DID 0x98E4.

Alex

> +		pr_info("Disable IOMMU on Stoney Ridge\n");
> +		amd_iommu_disabled = true;
> +	}
> +
>  	/* Disable any previously enabled IOMMUs */
>  	if (!is_kdump_kernel() || amd_iommu_disabled)
>  		disable_iommus();
> @@ -2711,7 +2719,7 @@ static int __init state_next(void)
>  		ret = early_amd_iommu_init();
>  		init_state = ret ? IOMMU_INIT_ERROR :
> IOMMU_ACPI_FINISHED;
>  		if (init_state == IOMMU_ACPI_FINISHED &&
> amd_iommu_disabled) {
> -			pr_info("AMD IOMMU disabled on kernel command-
> line\n");
> +			pr_info("AMD IOMMU disabled\n");
>  			init_state = IOMMU_CMDLINE_DISABLED;
>  			ret = -EINVAL;
>  		}
> --
> 2.17.1