Re: [PATCH v6 4/9] iommu/amd: Introduce per-device DTE cache to store persistent bits

[Jason Gunthorpe <jgg@nvidia.com>]

On Wed, Oct 16, 2024 at 05:17:51AM +0000, Suravee Suthikulpanit wrote:
> diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
> index f537b264f118..3f53d3bc79cb 100644
> --- a/drivers/iommu/amd/amd_iommu_types.h
> +++ b/drivers/iommu/amd/amd_iommu_types.h
> @@ -830,6 +830,16 @@ struct devid_map {
>  /* Device may request super-user privileges */
>  #define AMD_IOMMU_DEVICE_FLAG_PRIV_SUP   0x10
>  
> +/*
> + * Structure defining one entry in the device table
> + */
> +struct dev_table_entry {
> +	union {
> +		u64 data[4];
> +		u128 data128[2];
> +	};
> +};

It would be appropriate to put this hunk into the prior patch so your
series does not move code it just added..

>  /*
>   * This struct contains device specific data for the IOMMU
>   */
> @@ -858,6 +868,7 @@ struct iommu_dev_data {
>  	bool defer_attach;
>  
>  	struct ratelimit_state rs;        /* Ratelimit IOPF messages */
> +	struct dev_table_entry dte_cache;
>  };

I would call this initial_dte or something, it isn't a cache, it is
the recoding of the ACPI data into a DTE format.

 /* Stores INIT/EINT,NMIm SYSMGTx,LINTx values from ACPI */
 struct dev_tabl_entry initial_dte;

> @@ -1159,19 +1171,19 @@ static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu,
>  					   u16 devid, u32 flags, u32 ext_flags)
>  {
>  	if (flags & ACPI_DEVFLAG_INITPASS)
> -		set_dev_entry_bit(iommu, devid, DEV_ENTRY_INIT_PASS);
> +		set_dte_cache_bit(iommu, devid, DEV_ENTRY_INIT_PASS);
>  	if (flags & ACPI_DEVFLAG_EXTINT)
> -		set_dev_entry_bit(iommu, devid, DEV_ENTRY_EINT_PASS);
> +		set_dte_cache_bit(iommu, devid, DEV_ENTRY_EINT_PASS);
>  	if (flags & ACPI_DEVFLAG_NMI)
> -		set_dev_entry_bit(iommu, devid, DEV_ENTRY_NMI_PASS);
> +		set_dte_cache_bit(iommu, devid, DEV_ENTRY_NMI_PASS);
>  	if (flags & ACPI_DEVFLAG_SYSMGT1)
> -		set_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT1);
> +		set_dte_cache_bit(iommu, devid, DEV_ENTRY_SYSMGT1);
>  	if (flags & ACPI_DEVFLAG_SYSMGT2)
> -		set_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT2);
> +		set_dte_cache_bit(iommu, devid, DEV_ENTRY_SYSMGT2);
>  	if (flags & ACPI_DEVFLAG_LINT0)
> -		set_dev_entry_bit(iommu, devid, DEV_ENTRY_LINT0_PASS);
> +		set_dte_cache_bit(iommu, devid, DEV_ENTRY_LINT0_PASS);
>  	if (flags & ACPI_DEVFLAG_LINT1)
> -		set_dev_entry_bit(iommu, devid, DEV_ENTRY_LINT1_PASS);
> +		set_dte_cache_bit(iommu, devid, DEV_ENTRY_LINT1_PASS);

Doesn't this break the driver at this patch? Nothing reads from the
dte_cache at this point in the series so the real DTE never got these
bits?

Maybe just add a temporary line here to copy the entire dte_cache to
the real dte? The next patch fixes it I think?

But I like the idea, I think this is the a much more understandable
direction to go.

Jason