All of lore.kernel.org
 help / color / mirror / Atom feed
From: Joerg Roedel <joro@8bytes.org>
To: iommu@lists.linux-foundation.org
Cc: Joerg Roedel <joro@8bytes.org>,
	jroedel@suse.de, Tom Lendacky <thomas.lendacky@amd.com>,
	Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>,
	Alexander.Deucher@amd.com, linux-kernel@vger.kernel.org
Subject: [PATCH 1/2] iommu/amd: Do not force direct mapping when SME is active
Date: Mon, 24 Aug 2020 12:54:14 +0200	[thread overview]
Message-ID: <20200824105415.21000-2-joro@8bytes.org> (raw)
In-Reply-To: <20200824105415.21000-1-joro@8bytes.org>

From: Joerg Roedel <jroedel@suse.de>

Do not force devices supporting IOMMUv2 to be direct mapped when memory
encryption is active. This might cause them to be unusable because their
DMA mask does not include the encryption bit.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index ba9f3dbc5b94..77e4268e41cf 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2659,7 +2659,12 @@ static int amd_iommu_def_domain_type(struct device *dev)
 	if (!dev_data)
 		return 0;
 
-	if (dev_data->iommu_v2)
+	/*
+	 * Do not identity map IOMMUv2 capable devices when memory encryption is
+	 * active, because some of those devices (AMD GPUs) don't have the
+	 * encryption bit in their DMA-mask and require remapping.
+	 */
+	if (!mem_encrypt_active() && dev_data->iommu_v2)
 		return IOMMU_DOMAIN_IDENTITY;
 
 	return 0;
-- 
2.28.0


WARNING: multiple messages have this Message-ID (diff)
From: Joerg Roedel <joro@8bytes.org>
To: iommu@lists.linux-foundation.org
Cc: Tom Lendacky <thomas.lendacky@amd.com>,
	jroedel@suse.de, linux-kernel@vger.kernel.org,
	Alexander.Deucher@amd.com
Subject: [PATCH 1/2] iommu/amd: Do not force direct mapping when SME is active
Date: Mon, 24 Aug 2020 12:54:14 +0200	[thread overview]
Message-ID: <20200824105415.21000-2-joro@8bytes.org> (raw)
In-Reply-To: <20200824105415.21000-1-joro@8bytes.org>

From: Joerg Roedel <jroedel@suse.de>

Do not force devices supporting IOMMUv2 to be direct mapped when memory
encryption is active. This might cause them to be unusable because their
DMA mask does not include the encryption bit.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index ba9f3dbc5b94..77e4268e41cf 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2659,7 +2659,12 @@ static int amd_iommu_def_domain_type(struct device *dev)
 	if (!dev_data)
 		return 0;
 
-	if (dev_data->iommu_v2)
+	/*
+	 * Do not identity map IOMMUv2 capable devices when memory encryption is
+	 * active, because some of those devices (AMD GPUs) don't have the
+	 * encryption bit in their DMA-mask and require remapping.
+	 */
+	if (!mem_encrypt_active() && dev_data->iommu_v2)
 		return IOMMU_DOMAIN_IDENTITY;
 
 	return 0;
-- 
2.28.0

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

  reply	other threads:[~2020-08-24 10:55 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-24 10:54 [PATCH 0/2] iommu/amd: Fix IOMMUv2 devices when SME is active Joerg Roedel
2020-08-24 10:54 ` Joerg Roedel
2020-08-24 10:54 ` Joerg Roedel [this message]
2020-08-24 10:54   ` [PATCH 1/2] iommu/amd: Do not force direct mapping " Joerg Roedel
2020-08-26 14:23   ` Deucher, Alexander
2020-08-26 14:23     ` Deucher, Alexander
2020-08-24 10:54 ` [PATCH 2/2] iommu/amd: Do not use IOMMUv2 functionality " Joerg Roedel
2020-08-24 10:54   ` Joerg Roedel
2020-08-26 14:20   ` Deucher, Alexander
2020-08-26 14:20     ` Deucher, Alexander
2020-08-26 14:14 ` [PATCH 0/2] iommu/amd: Fix IOMMUv2 devices " Deucher, Alexander
2020-08-26 15:22   ` Felix Kuehling
2020-08-26 15:22     ` Felix Kuehling
2020-08-26 15:25     ` Deucher, Alexander
2020-08-26 15:25       ` Deucher, Alexander
2020-08-28 13:46       ` jroedel
2020-08-28 13:46         ` jroedel
2020-08-28 13:54         ` Felix Kuehling
2020-08-28 13:54           ` Felix Kuehling
2020-08-28 15:11           ` Deucher, Alexander
2020-08-28 15:11             ` Deucher, Alexander
2020-08-28 15:29             ` jroedel
2020-08-28 15:29               ` jroedel
2020-08-28 15:47               ` Deucher, Alexander
2020-08-28 15:47                 ` Deucher, Alexander
2020-09-04 10:05                 ` Joerg Roedel
2020-09-04 10:05                   ` Joerg Roedel
2020-09-06 16:08                   ` Deucher, Alexander
2020-09-06 16:08                     ` Deucher, Alexander
2020-09-07 10:44                     ` Joerg Roedel
2020-09-07 10:44                       ` Joerg Roedel
2020-09-07 11:10                       ` Christian König
2020-09-07 11:10                         ` Christian König
2020-09-08  3:38                     ` Felix Kuehling
2020-09-08  3:38                       ` Felix Kuehling
2020-08-28 15:27           ` jroedel
2020-08-28 15:27             ` jroedel

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200824105415.21000-2-joro@8bytes.org \
    --to=joro@8bytes.org \
    --cc=Alexander.Deucher@amd.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jroedel@suse.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=suravee.suthikulpanit@amd.com \
    --cc=thomas.lendacky@amd.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.