[PATCH v4 0/4] iommu, thunderbolt: Make iommu_dma_protection more accurate

[PATCH v4 0/4] iommu, thunderbolt: Make iommu_dma_protection more accurate

[Robin Murphy]

Hi all, 

As promised, here's the really-actually-final version, cleaning up the
new interface in patch #1 to not introduce the new parameter before it's
ready, and rebased to make sure it correctly applies on -rc3.

Thanks,
Robin.


Mario Limonciello (1):
  iommu/amd: Indicate whether DMA remap support is enabled

Robin Murphy (3):
  iommu: Introduce device_iommu_capable()
  iommu: Add capability for pre-boot DMA protection
  thunderbolt: Make iommu_dma_protection more accurate

 drivers/iommu/amd/amd_iommu_types.h |  4 +++
 drivers/iommu/amd/init.c            |  3 ++
 drivers/iommu/amd/iommu.c           |  2 ++
 drivers/iommu/intel/iommu.c         |  2 ++
 drivers/iommu/iommu.c               | 23 +++++++++++++++
 drivers/thunderbolt/domain.c        | 12 ++------
 drivers/thunderbolt/nhi.c           | 44 +++++++++++++++++++++++++++++
 include/linux/iommu.h               |  8 ++++++
 include/linux/thunderbolt.h         |  2 ++
 9 files changed, 91 insertions(+), 9 deletions(-)

-- 
2.35.3.dirty

[PATCH v4 1/4] iommu: Introduce device_iommu_capable()

[Robin Murphy]

iommu_capable() only really works for systems where all IOMMU instances
are completely homogeneous, and all devices are IOMMU-mapped. Implement
the new variant which will be able to give a more accurate answer for
whichever device the caller is actually interested in, and even more so
once all the external users have been converted and we can reliably pass
the device pointer through the internal driver interface too.

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

v4: Hold off changing the internal callback interface for now

 drivers/iommu/iommu.c | 23 +++++++++++++++++++++++
 include/linux/iommu.h |  6 ++++++
 2 files changed, 29 insertions(+)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index f2c45b85b9fc..780c11734979 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1906,6 +1906,29 @@ bool iommu_present(struct bus_type *bus)
 }
 EXPORT_SYMBOL_GPL(iommu_present);
 
+/**
+ * device_iommu_capable() - check for a general IOMMU capability
+ * @dev: device to which the capability would be relevant, if available
+ * @cap: IOMMU capability
+ *
+ * Return: true if an IOMMU is present and supports the given capability
+ * for the given device, otherwise false.
+ */
+bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
+{
+	const struct iommu_ops *ops;
+
+	if (!dev->iommu || !dev->iommu->iommu_dev)
+		return false;
+
+	ops = dev_iommu_ops(dev);
+	if (!ops->capable)
+		return false;
+
+	return ops->capable(cap);
+}
+EXPORT_SYMBOL_GPL(device_iommu_capable);
+
 bool iommu_capable(struct bus_type *bus, enum iommu_cap cap)
 {
 	if (!bus->iommu_ops || !bus->iommu_ops->capable)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 9208eca4b0d1..e26cf84e5d82 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -417,6 +417,7 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev)
 extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops);
 extern int bus_iommu_probe(struct bus_type *bus);
 extern bool iommu_present(struct bus_type *bus);
+extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap);
 extern bool iommu_capable(struct bus_type *bus, enum iommu_cap cap);
 extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus);
 extern struct iommu_group *iommu_group_get_by_id(int id);
@@ -689,6 +690,11 @@ static inline bool iommu_present(struct bus_type *bus)
 	return false;
 }
 
+static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
+{
+	return false;
+}
+
 static inline bool iommu_capable(struct bus_type *bus, enum iommu_cap cap)
 {
 	return false;
-- 
2.35.3.dirty

[PATCH v4 2/4] iommu: Add capability for pre-boot DMA protection

[Robin Murphy]

VT-d's dmar_platform_optin() actually represents a combination of
properties fairly well standardised by Microsoft as "Pre-boot DMA
Protection" and "Kernel DMA Protection"[1]. As such, we can provide
interested consumers with an abstracted capability rather than
driver-specific interfaces that won't scale. We name it for the former
aspect since that's what external callers are most likely to be
interested in; the latter is for the IOMMU layer to handle itself.

[1] https://docs.microsoft.com/en-us/windows-hardware/design/device-experiences/oem-kernel-dma-protection

Suggested-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---

v4: No change

 drivers/iommu/intel/iommu.c | 2 ++
 include/linux/iommu.h       | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index df5c62ecf942..0edf6084dc14 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4551,6 +4551,8 @@ static bool intel_iommu_capable(enum iommu_cap cap)
 		return domain_update_iommu_snooping(NULL);
 	if (cap == IOMMU_CAP_INTR_REMAP)
 		return irq_remapping_enabled == 1;
+	if (cap == IOMMU_CAP_PRE_BOOT_PROTECTION)
+		return dmar_platform_optin();
 
 	return false;
 }
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index e26cf84e5d82..4123693ae319 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -107,6 +107,8 @@ enum iommu_cap {
 					   transactions */
 	IOMMU_CAP_INTR_REMAP,		/* IOMMU supports interrupt isolation */
 	IOMMU_CAP_NOEXEC,		/* IOMMU_NOEXEC flag */
+	IOMMU_CAP_PRE_BOOT_PROTECTION,	/* Firmware says it used the IOMMU for
+					   DMA protection and we should too */
 };
 
 /* These are the possible reserved region types */
-- 
2.35.3.dirty

[PATCH v4 3/4] thunderbolt: Make iommu_dma_protection more accurate

[Robin Murphy]

Between me trying to get rid of iommu_present() and Mario wanting to
support the AMD equivalent of DMAR_PLATFORM_OPT_IN, scrutiny has shown
that the iommu_dma_protection attribute is being far too optimistic.
Even if an IOMMU might be present for some PCI segment in the system,
that doesn't necessarily mean it provides translation for the device(s)
we care about. Furthermore, all that DMAR_PLATFORM_OPT_IN really does
is tell us that memory was protected before the kernel was loaded, and
prevent the user from disabling the intel-iommu driver entirely. While
that lets us assume kernel integrity, what matters for actual runtime
DMA protection is whether we trust individual devices, based on the
"external facing" property that we expect firmware to describe for
Thunderbolt ports.

It's proven challenging to determine the appropriate ports accurately
given the variety of possible topologies, so while still not getting a
perfect answer, by putting enough faith in firmware we can at least get
a good bit closer. If we can see that any device near a Thunderbolt NHI
has all the requisites for Kernel DMA Protection, chances are that it
*is* a relevant port, but moreover that implies that firmware is playing
the game overall, so we'll use that to assume that all Thunderbolt ports
should be correctly marked and thus will end up fully protected.

CC: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---

v4: No change

 drivers/thunderbolt/domain.c | 12 +++-------
 drivers/thunderbolt/nhi.c    | 44 ++++++++++++++++++++++++++++++++++++
 include/linux/thunderbolt.h  |  2 ++
 3 files changed, 49 insertions(+), 9 deletions(-)

diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c
index 7018d959f775..2889a214dadc 100644
--- a/drivers/thunderbolt/domain.c
+++ b/drivers/thunderbolt/domain.c
@@ -7,9 +7,7 @@
  */
 
 #include <linux/device.h>
-#include <linux/dmar.h>
 #include <linux/idr.h>
-#include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
@@ -257,13 +255,9 @@ static ssize_t iommu_dma_protection_show(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	/*
-	 * Kernel DMA protection is a feature where Thunderbolt security is
-	 * handled natively using IOMMU. It is enabled when IOMMU is
-	 * enabled and ACPI DMAR table has DMAR_PLATFORM_OPT_IN set.
-	 */
-	return sprintf(buf, "%d\n",
-		       iommu_present(&pci_bus_type) && dmar_platform_optin());
+	struct tb *tb = container_of(dev, struct tb, dev);
+
+	return sysfs_emit(buf, "%d\n", tb->nhi->iommu_dma_protection);
 }
 static DEVICE_ATTR_RO(iommu_dma_protection);
 
diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index 4a582183f675..4bc87b0f003a 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -15,9 +15,11 @@
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
+#include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/property.h>
+#include <linux/string_helpers.h>
 
 #include "nhi.h"
 #include "nhi_regs.h"
@@ -1103,6 +1105,47 @@ static void nhi_check_quirks(struct tb_nhi *nhi)
 		nhi->quirks |= QUIRK_AUTO_CLEAR_INT;
 }
 
+static int nhi_check_iommu_pdev(struct pci_dev *pdev, void *data)
+{
+	if (!pdev->external_facing ||
+	    !device_iommu_capable(&pdev->dev, IOMMU_CAP_PRE_BOOT_PROTECTION))
+		return 0;
+	*(bool *)data = true;
+	return 1; /* Stop walking */
+}
+
+static void nhi_check_iommu(struct tb_nhi *nhi)
+{
+	struct pci_bus *bus = nhi->pdev->bus;
+	bool port_ok = false;
+
+	/*
+	 * Ideally what we'd do here is grab every PCI device that
+	 * represents a tunnelling adapter for this NHI and check their
+	 * status directly, but unfortunately USB4 seems to make it
+	 * obnoxiously difficult to reliably make any correlation.
+	 *
+	 * So for now we'll have to bodge it... Hoping that the system
+	 * is at least sane enough that an adapter is in the same PCI
+	 * segment as its NHI, if we can find *something* on that segment
+	 * which meets the requirements for Kernel DMA Protection, we'll
+	 * take that to imply that firmware is aware and has (hopefully)
+	 * done the right thing in general. We need to know that the PCI
+	 * layer has seen the ExternalFacingPort property which will then
+	 * inform the IOMMU layer to enforce the complete "untrusted DMA"
+	 * flow, but also that the IOMMU driver itself can be trusted not
+	 * to have been subverted by a pre-boot DMA attack.
+	 */
+	while (bus->parent)
+		bus = bus->parent;
+
+	pci_walk_bus(bus, nhi_check_iommu_pdev, &port_ok);
+
+	nhi->iommu_dma_protection = port_ok;
+	dev_dbg(&nhi->pdev->dev, "IOMMU DMA protection is %s\n",
+		str_enabled_disabled(port_ok));
+}
+
 static int nhi_init_msi(struct tb_nhi *nhi)
 {
 	struct pci_dev *pdev = nhi->pdev;
@@ -1220,6 +1263,7 @@ static int nhi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return -ENOMEM;
 
 	nhi_check_quirks(nhi);
+	nhi_check_iommu(nhi);
 
 	res = nhi_init_msi(nhi);
 	if (res) {
diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h
index 124e13cb1469..7a8ad984e651 100644
--- a/include/linux/thunderbolt.h
+++ b/include/linux/thunderbolt.h
@@ -465,6 +465,7 @@ static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc)
  * @msix_ida: Used to allocate MSI-X vectors for rings
  * @going_away: The host controller device is about to disappear so when
  *		this flag is set, avoid touching the hardware anymore.
+ * @iommu_dma_protection: An IOMMU will isolate external-facing ports.
  * @interrupt_work: Work scheduled to handle ring interrupt when no
  *		    MSI-X is used.
  * @hop_count: Number of rings (end point hops) supported by NHI.
@@ -479,6 +480,7 @@ struct tb_nhi {
 	struct tb_ring **rx_rings;
 	struct ida msix_ida;
 	bool going_away;
+	bool iommu_dma_protection;
 	struct work_struct interrupt_work;
 	u32 hop_count;
 	unsigned long quirks;
-- 
2.35.3.dirty

[PATCH v4 4/4] iommu/amd: Indicate whether DMA remap support is enabled

[Robin Murphy]

From: Mario Limonciello <mario.limonciello@amd.com>

Bit 1 of the IVFS IVInfo field indicates that IOMMU has been used for
pre-boot DMA protection.

Export this capability to allow other places in the kernel to be able to
check for it on AMD systems.

Link: https://www.amd.com/system/files/TechDocs/48882_IOMMU.pdf
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---

v4: No change

 drivers/iommu/amd/amd_iommu_types.h | 4 ++++
 drivers/iommu/amd/init.c            | 3 +++
 drivers/iommu/amd/iommu.c           | 2 ++
 3 files changed, 9 insertions(+)

diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 47108ed44fbb..72d0f5e2f651 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -407,6 +407,7 @@
 /* IOMMU IVINFO */
 #define IOMMU_IVINFO_OFFSET     36
 #define IOMMU_IVINFO_EFRSUP     BIT(0)
+#define IOMMU_IVINFO_DMA_REMAP  BIT(1)
 
 /* IOMMU Feature Reporting Field (for IVHD type 10h */
 #define IOMMU_FEAT_GASUP_SHIFT	6
@@ -449,6 +450,9 @@ extern struct irq_remap_table **irq_lookup_table;
 /* Interrupt remapping feature used? */
 extern bool amd_iommu_irq_remap;
 
+/* IVRS indicates that pre-boot remapping was enabled */
+extern bool amdr_ivrs_remap_support;
+
 /* kmem_cache to get tables with 128 byte alignement */
 extern struct kmem_cache *amd_iommu_irq_cache;
 
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index b4a798c7b347..0467918bf7fd 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -182,6 +182,7 @@ u32 amd_iommu_max_pasid __read_mostly = ~0;
 
 bool amd_iommu_v2_present __read_mostly;
 static bool amd_iommu_pc_present __read_mostly;
+bool amdr_ivrs_remap_support __read_mostly;
 
 bool amd_iommu_force_isolation __read_mostly;
 
@@ -326,6 +327,8 @@ static void __init early_iommu_features_init(struct amd_iommu *iommu,
 {
 	if (amd_iommu_ivinfo & IOMMU_IVINFO_EFRSUP)
 		iommu->features = h->efr_reg;
+	if (amd_iommu_ivinfo & IOMMU_IVINFO_DMA_REMAP)
+		amdr_ivrs_remap_support = true;
 }
 
 /* Access to l1 and l2 indexed register spaces */
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index a1ada7bff44e..991f10ce350e 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2162,6 +2162,8 @@ static bool amd_iommu_capable(enum iommu_cap cap)
 		return (irq_remapping_enabled == 1);
 	case IOMMU_CAP_NOEXEC:
 		return false;
+	case IOMMU_CAP_PRE_BOOT_PROTECTION:
+		return amdr_ivrs_remap_support;
 	default:
 		break;
 	}
-- 
2.35.3.dirty