[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <MN2PR12MB4488CD47D15A9A291B8A0499F7469@MN2PR12MB4488.namprd12.prod.outlook.com>
Date: Thu, 22 Apr 2021 19:05:04 +0000
From: "Deucher, Alexander" <Alexander.Deucher@....com>
To: Joerg Roedel <joro@...tes.org>,
"iommu@...ts.linux-foundation.org" <iommu@...ts.linux-foundation.org>
CC: Will Deacon <will@...nel.org>,
"d1nuc0m@...tonmail.com" <d1nuc0m@...tonmail.com>,
"linux-doc@...r.kernel.org" <linux-doc@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
Joerg Roedel <jroedel@...e.de>
Subject: RE: [PATCH] iommu/amd: Add amd_iommu=force_enable option
[AMD Public Use]
> -----Original Message-----
> From: Joerg Roedel <joro@...tes.org>
> Sent: Thursday, April 22, 2021 9:07 AM
> To: iommu@...ts.linux-foundation.org
> Cc: Joerg Roedel <joro@...tes.org>; Will Deacon <will@...nel.org>;
> Deucher, Alexander <Alexander.Deucher@....com>;
> d1nuc0m@...tonmail.com; linux-doc@...r.kernel.org; linux-
> kernel@...r.kernel.org; Joerg Roedel <jroedel@...e.de>
> Subject: [PATCH] iommu/amd: Add amd_iommu=force_enable option
>
> From: Joerg Roedel <jroedel@...e.de>
>
> Add this option to enable the IOMMU on platforms like AMD Stoney, where
> the kernel usually disables it because it may cause problems in some
> scenarios.
>
> Signed-off-by: Joerg Roedel <jroedel@...e.de>
Acked-by: Alex Deucher <alexander.deucher@....com>
> ---
> Documentation/admin-guide/kernel-parameters.txt | 3 +++
> drivers/iommu/amd/init.c | 7 +++++++
> 2 files changed, 10 insertions(+)
>
> diff --git a/Documentation/admin-guide/kernel-parameters.txt
> b/Documentation/admin-guide/kernel-parameters.txt
> index 04545725f187..c9573f726707 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -303,6 +303,9 @@
> allowed anymore to lift isolation
> requirements as needed. This
> option
> does not override iommu=pt
> + force_enable - Force enable the IOMMU on
> platforms known
> + to be buggy with IOMMU enabled. Use
> this
> + option with care.
>
> amd_iommu_dump= [HW,X86-64]
> Enable AMD IOMMU driver option to dump the ACPI
> table diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
> index 321f5906e6ed..3e2295d3b3e2 100644
> --- a/drivers/iommu/amd/init.c
> +++ b/drivers/iommu/amd/init.c
> @@ -155,6 +155,7 @@ static int amd_iommu_xt_mode =
> IRQ_REMAP_XAPIC_MODE;
>
> static bool amd_iommu_detected;
> static bool __initdata amd_iommu_disabled;
> +static bool __initdata amd_iommu_force_enable;
> static int amd_iommu_target_ivhd_type;
>
> u16 amd_iommu_last_bdf; /* largest PCI device id we
> have
> @@ -2882,6 +2883,9 @@ static bool detect_ivrs(void)
>
> acpi_put_table(ivrs_base);
>
> + if (amd_iommu_force_enable)
> + goto out;
> +
> /* Don't use IOMMU if there is Stoney Ridge graphics */
> for (i = 0; i < 32; i++) {
> u32 pci_id;
> @@ -2893,6 +2897,7 @@ static bool detect_ivrs(void)
> }
> }
>
> +out:
> /* Make sure ACS will be enabled during PCI probe */
> pci_request_acs();
>
> @@ -3148,6 +3153,8 @@ static int __init parse_amd_iommu_options(char
> *str)
> for (; *str; ++str) {
> if (strncmp(str, "fullflush", 9) == 0)
> amd_iommu_unmap_flush = true;
> + if (strncmp(str, "force_enable", 12) == 0)
> + amd_iommu_force_enable = true;
> if (strncmp(str, "off", 3) == 0)
> amd_iommu_disabled = true;
> if (strncmp(str, "force_isolation", 15) == 0)
> --
> 2.31.1
Powered by blists - more mailing lists