iommu.lists.linux-foundation.org archive mirror
 help / color / mirror / Atom feed
From: Robin Murphy <robin.murphy@arm.com>
To: joro@8bytes.org, will@kernel.org
Cc: linux-kernel@vger.kernel.org, dianders@chromium.org,
	iommu@lists.linux-foundation.org,
	linux-arm-kernel@lists.infradead.org
Subject: [PATCH 20/23] iommu: Allow choosing DMA strictness at build time
Date: Wed, 21 Jul 2021 19:20:31 +0100	[thread overview]
Message-ID: <002cd8280cc4935e294d79bef838fbfb633bb3ed.1626888445.git.robin.murphy@arm.com> (raw)
In-Reply-To: <cover.1626888444.git.robin.murphy@arm.com>

To parallel the sysfs behaviour, extend the build-time configuration
for default domains to include the new type as well.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>

---

This effectively replaces patch #3 of John's "iommu: Enhance IOMMU
default DMA mode build options" series.
---
 drivers/iommu/Kconfig | 48 +++++++++++++++++++++++++++++++++++--------
 drivers/iommu/iommu.c |  2 +-
 2 files changed, 41 insertions(+), 9 deletions(-)

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 07b7c25cbed8..e3f7990046ae 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -79,16 +79,48 @@ config IOMMU_DEBUGFS
 	  debug/iommu directory, and then populate a subdirectory with
 	  entries as required.
 
-config IOMMU_DEFAULT_PASSTHROUGH
-	bool "IOMMU passthrough by default"
+choice
+	prompt "Default IOMMU domain type"
 	depends on IOMMU_API
-	help
-	  Enable passthrough by default, removing the need to pass in
-	  iommu.passthrough=on or iommu=pt through command line. If this
-	  is enabled, you can still disable with iommu.passthrough=off
-	  or iommu=nopt depending on the architecture.
+	default IOMMU_DEFAULT_DMA_LAZY if INTEL_IOMMU || AMD_IOMMU
+	default IOMMU_DEFAULT_DMA_STRICT
 
-	  If unsure, say N here.
+config IOMMU_DEFAULT_DMA_STRICT
+	bool "Translated - Strict"
+	help
+	  Trusted devices use translation to restrict their access to only
+	  DMA-mapped pages, with strict TLB invalidation on unmap. Equivalent
+	  to passing "iommu.passthrough=0 iommu.strict=1" on the command line.
+
+	  Untrusted devices always use this mode, with an additional layer of
+	  bounce-buffering such that they cannot gain access to any unrelated
+	  data within a mapped page.
+
+config IOMMU_DEFAULT_DMA_LAZY
+	bool "Translated - Lazy"
+	help
+	  Trusted devices use translation to restrict their access to only
+	  DMA-mapped pages, but with "lazy" batched TLB invalidation. This
+	  mode allows higher performance with some IOMMUs due to reduced TLB
+	  flushing, but at the cost of reduced isolation since devices may be
+	  able to access memory for some time after it has been unmapped.
+	  Equivalent to passing "iommu.passthrough=0 iommu.strict=0" on the
+	  command line.
+
+	  If this mode is not supported by the IOMMU driver, the effective
+	  runtime default will fall back to IOMMU_DEFAULT_DMA_STRICT.
+
+config IOMMU_DEFAULT_PASSTHROUGH
+	bool "Passthrough"
+	help
+	  Trusted devices are identity-mapped, giving them unrestricted access
+	  to memory with minimal performance overhead. Equivalent to passing
+	  "iommu.passthrough=1" (historically "iommu=pt") on the command line.
+
+	  If this mode is not supported by the IOMMU driver, the effective
+	  runtime default will fall back to IOMMU_DEFAULT_DMA_STRICT.
+
+endchoice
 
 config OF_IOMMU
 	def_bool y
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index d3b562a33ac4..4fad6d427d9d 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -30,7 +30,7 @@ static struct kset *iommu_group_kset;
 static DEFINE_IDA(iommu_group_ida);
 
 static unsigned int iommu_def_domain_type __read_mostly;
-static bool iommu_dma_strict __read_mostly = true;
+static bool iommu_dma_strict __read_mostly = IS_ENABLED(CONFIG_IOMMU_DEFAULT_DMA_STRICT);
 static u32 iommu_cmd_line __read_mostly;
 
 struct iommu_group {
-- 
2.25.1

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

  parent reply	other threads:[~2021-07-21 18:21 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-21 18:20 [PATCH 00/23] iommu: Refactor DMA domain strictness Robin Murphy
2021-07-21 18:20 ` [PATCH 01/23] iommu: Pull IOVA cookie management into the core Robin Murphy
2021-07-21 18:20 ` [PATCH 02/23] iommu/amd: Drop IOVA cookie management Robin Murphy
2021-07-21 18:20 ` [PATCH 03/23] iommu/arm-smmu: " Robin Murphy
2021-07-21 18:20 ` [PATCH 04/23] iommu/vt-d: " Robin Murphy
2021-07-21 18:20 ` [PATCH 05/23] iommu/exynos: " Robin Murphy
2021-07-21 18:20 ` [PATCH 06/23] iommu/ipmmu-vmsa: " Robin Murphy
2021-07-21 18:20 ` [PATCH 07/23] iommu/mtk: " Robin Murphy
2021-07-21 18:20 ` [PATCH 08/23] iommu/rockchip: " Robin Murphy
2021-07-21 18:20 ` [PATCH 09/23] iommu/sprd: " Robin Murphy
2021-07-21 18:20 ` [PATCH 10/23] iommu/sun50i: " Robin Murphy
2021-07-21 18:20 ` [PATCH 11/23] iommu/virtio: " Robin Murphy
2021-07-21 18:20 ` [PATCH 12/23] iommu/dma: Unexport " Robin Murphy
2021-07-21 18:20 ` [PATCH 13/23] iommu/dma: Remove redundant "!dev" checks Robin Murphy
2021-07-26  8:28   ` John Garry
2021-07-21 18:20 ` [PATCH 14/23] iommu: Introduce explicit type for non-strict DMA domains Robin Murphy
2021-07-21 18:20 ` [PATCH 15/23] iommu/amd: Prepare for multiple DMA domain types Robin Murphy
2021-07-21 18:20 ` [PATCH 16/23] iommu/arm-smmu: " Robin Murphy
2021-07-26 12:46   ` Joerg Roedel
2021-07-26 13:09     ` Robin Murphy
2021-07-26 18:43       ` Joerg Roedel
2021-07-21 18:20 ` [PATCH 17/23] iommu/vt-d: " Robin Murphy
2021-07-22 16:44   ` kernel test robot
2021-07-22 17:30     ` Robin Murphy
2021-07-22 18:44   ` kernel test robot
2021-07-24  5:23   ` Lu Baolu
2021-07-26  8:30     ` Robin Murphy
2021-07-21 18:20 ` [PATCH 18/23] iommu: Express DMA strictness via the domain type Robin Murphy
2021-07-24  5:29   ` Lu Baolu
2021-07-26  8:27     ` Robin Murphy
2021-07-26 11:31       ` Lu Baolu
2021-07-26 12:29       ` Lu Baolu
2021-07-26 12:43         ` Robin Murphy
2021-07-21 18:20 ` [PATCH 19/23] iommu: Expose DMA domain strictness via sysfs Robin Murphy
2021-07-21 18:20 ` Robin Murphy [this message]
2021-07-21 18:20 ` [PATCH 21/23] iommu/dma: Factor out flush queue init Robin Murphy
2021-07-21 18:20 ` [PATCH 22/23] iommu: Allow enabling non-strict mode dynamically Robin Murphy
2021-07-21 18:20 ` [PATCH 23/23] iommu/arm-smmu: Allow non-strict in pgtable_quirks interface Robin Murphy
2021-07-26  8:13 ` [PATCH 00/23] iommu: Refactor DMA domain strictness John Garry
2021-07-26 12:06   ` Robin Murphy
2021-07-26 13:02 ` Joerg Roedel

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=002cd8280cc4935e294d79bef838fbfb633bb3ed.1626888445.git.robin.murphy@arm.com \
    --to=robin.murphy@arm.com \
    --cc=dianders@chromium.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=joro@8bytes.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=will@kernel.org \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).