Skip to contentSkip to conversation

iommu/arm-smmu-v3: Fix hitless STE update in nesting cases

PATCH Superseded Nicolin Chen 3 participants 11 messages Jan 12 – Jan 14

Subsystems (2)

v6 of 7 Superseded Latest is v7 →

lore
Share & tools
lore
#0 lore raw

v6 cover iommu/arm-smmu-v3: Fix hitless STE update in nesting cases

Occasional C_BAD_STE errors were observed in nesting setups where a device attached to a nested bypass/identity domain enables PASID.

This occurred when the physical STE was updated from S2-only mode to S1+S2 nesting mode, but the update failed to use the hitless routine that it was supposed to use. Instead, it cleared STE.V bit to load the CD table, while the default substream was still actively performing DMA.

It was later found that the diff algorithm in arm_smmu_entry_qword_diff() enforced an additional critical word due to misaligned MEV and EATS fields between S2-only and S1+S2 modes.

Both fields are either well-managed or non-critical, so move them to the "ignored" list to relax the qword diff algorithm.

Additionally, add KUnit test coverage for these nesting STE cases.

This is on Github:
https://github.com/nicolinc/iommufd/commits/smmuv3_ste_fixes/

A host kernel must apply this to fix the bug.

Changelog
v6:
* Add Reviewed-by from Mostafa
* Update inline comments for EATS
* Ensure S2S is not set when returning EATS to the safe bits
v5:
* Pass in feat to arm_smmu_test_make_s2_ste()
v4:
https://lore.kernel.org/all/[email protected]/
* s/ignored/update_safe
* Change entry_set to void
v3:
https://lore.kernel.org/all/[email protected]/
* Add Reviewed-by from Shuai
* Add an inline comments in nested test cases
* Reuse arm_smmu_test_make_cdtable_ste() for nested test cases
v2:
https://lore.kernel.org/all/[email protected]/
* Fix kunit tests
* Update commit message and inline comments
* Keep MEV/EATS in used list by masking them away using ignored_bits
v1:
https://lore.kernel.org/all/[email protected]/

Jason Gunthorpe (3):
iommu/arm-smmu-v3: Add update_safe bits to fix STE update sequence iommu/arm-smmu-v3: Mark STE MEV safe when computing the update
sequence
iommu/arm-smmu-v3: Mark STE EATS safe when computing the update
sequence

Nicolin Chen (1):
iommu/arm-smmu-v3-test: Add nested s1bypass/s1dssbypass coverage

 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  4 +
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c  | 78 ++++++++++++++++++-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   | 56 +++++++++++--
 3 files changed, 128 insertions(+), 10 deletions(-)
Signature · 1 line
2.43.0
#1 lore raw

PATCH v6 1/4 iommu/arm-smmu-v3: Add update_safe bits to fix STE update sequence

From: Jason Gunthorpe <[email protected]>

C_BAD_STE was observed when updating nested STE from an S1-bypass mode to an S1DSS-bypass mode. As both modes enabled S2, the used bit is slightly different than the normal S1-bypass and S1DSS-bypass modes. As a result, fields like MEV and EATS in S2's used list marked the word1 as a critical word that requested a STE.V=0. This breaks a hitless update.

However, both MEV and EATS aren't critical in terms of STE update. One controls the merge of the events and the other controls the ATS that is managed by the driver at the same time via pci_enable_ats().

Add an arm_smmu_get_ste_update_safe() to allow STE update algorithm to relax those fields, avoiding the STE update breakages.

After this change, entry_set has no caller checking its return value, so change it to void.

Note that this change is required by both MEV and EATS fields, which were introduced in different kernel versions. So add get_update_safe() first. MEV and EATS will be added to arm_smmu_get_ste_update_safe() separately.

Fixes 1e8be08d1c91 ("iommu/arm-smmu-v3: Support IOMMU_DOMAIN_NESTED")
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  4 +++
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c  | 31 +++++++++++++++++--
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   | 28 ++++++++++++-----
 3 files changed, 53 insertions(+), 10 deletions(-)
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +4 -0
index ae23aacc3840..287e223c054d 100644
@@ -900,6 +900,8 @@ struct arm_smmu_entry_writer {
 
 struct arm_smmu_entry_writer_ops {
 	void (*get_used)(const __le64 *entry, __le64 *used);
+	void (*get_update_safe)(const __le64 *cur, const __le64 *target,
+				__le64 *safe_bits);
 	void (*sync)(struct arm_smmu_entry_writer *writer);
 };
 
@@ -911,6 +913,8 @@ void arm_smmu_make_s2_domain_ste(struct arm_smmu_ste *target,
 
 #if IS_ENABLED(CONFIG_KUNIT)
 void arm_smmu_get_ste_used(const __le64 *ent, __le64 *used_bits);
+void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target,
+				  __le64 *safe_bits);
 void arm_smmu_write_entry(struct arm_smmu_entry_writer *writer, __le64 *cur,
 			  const __le64 *target);
 void arm_smmu_get_cd_used(const __le64 *ent, __le64 *used_bits);
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c +28 -3
index d2671bfd3798..b254a94b2003 100644
@@ -38,13 +38,16 @@ enum arm_smmu_test_master_feat {
 static bool arm_smmu_entry_differs_in_used_bits(const __le64 *entry,
 						const __le64 *used_bits,
 						const __le64 *target,
+						const __le64 *safe,
 						unsigned int length)
 {
 	bool differs = false;
 	unsigned int i;
 
 	for (i = 0; i < length; i++) {
-		if ((entry[i] & used_bits[i]) != target[i])
+		__le64 used = used_bits[i] & ~safe[i];
+
+		if ((entry[i] & used) != (target[i] & used))
 			differs = true;
 	}
 	return differs;
@@ -56,12 +59,24 @@ arm_smmu_test_writer_record_syncs(struct arm_smmu_entry_writer *writer)
 	struct arm_smmu_test_writer *test_writer =
 		container_of(writer, struct arm_smmu_test_writer, writer);
 	__le64 *entry_used_bits;
+	__le64 *safe_target;
+	__le64 *safe_init;
 
 	entry_used_bits = kunit_kzalloc(
 		test_writer->test, sizeof(*entry_used_bits) * NUM_ENTRY_QWORDS,
 		GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test_writer->test, entry_used_bits);
 
+	safe_target = kunit_kzalloc(test_writer->test,
+				    sizeof(*safe_target) * NUM_ENTRY_QWORDS,
+				    GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test_writer->test, safe_target);
+
+	safe_init = kunit_kzalloc(test_writer->test,
+				  sizeof(*safe_init) * NUM_ENTRY_QWORDS,
+				  GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test_writer->test, safe_init);
+
 	pr_debug("STE value is now set to: ");
 	print_hex_dump_debug("    ", DUMP_PREFIX_NONE, 16, 8,
 			     test_writer->entry,
@@ -79,14 +94,23 @@ arm_smmu_test_writer_record_syncs(struct arm_smmu_entry_writer *writer)
 		 * configuration.
 		 */
 		writer->ops->get_used(test_writer->entry, entry_used_bits);
+		if (writer->ops->get_update_safe)
+			writer->ops->get_update_safe(test_writer->entry,
+						     test_writer->init_entry,
+						     safe_init);
+		if (writer->ops->get_update_safe)
+			writer->ops->get_update_safe(test_writer->entry,
+						     test_writer->target_entry,
+						     safe_target);
 		KUNIT_EXPECT_FALSE(
 			test_writer->test,
 			arm_smmu_entry_differs_in_used_bits(
 				test_writer->entry, entry_used_bits,
-				test_writer->init_entry, NUM_ENTRY_QWORDS) &&
+				test_writer->init_entry, safe_init,
+				NUM_ENTRY_QWORDS) &&
 				arm_smmu_entry_differs_in_used_bits(
 					test_writer->entry, entry_used_bits,
-					test_writer->target_entry,
+					test_writer->target_entry, safe_target,
 					NUM_ENTRY_QWORDS));
 	}
 }
@@ -106,6 +130,7 @@ arm_smmu_v3_test_debug_print_used_bits(struct arm_smmu_entry_writer *writer,
 static const struct arm_smmu_entry_writer_ops test_ste_ops = {
 	.sync = arm_smmu_test_writer_record_syncs,
 	.get_used = arm_smmu_get_ste_used,
+	.get_update_safe = arm_smmu_get_ste_update_safe,
 };
 
 static const struct arm_smmu_entry_writer_ops test_cd_ops = {
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +21 -7
index d16d35c78c06..390446d259ab 100644
@@ -1082,6 +1082,13 @@ void arm_smmu_get_ste_used(const __le64 *ent, __le64 *used_bits)
 }
 EXPORT_SYMBOL_IF_KUNIT(arm_smmu_get_ste_used);
 
+VISIBLE_IF_KUNIT
+void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target,
+				  __le64 *safe_bits)
+{
+}
+EXPORT_SYMBOL_IF_KUNIT(arm_smmu_get_ste_update_safe);
+
 /*
  * Figure out if we can do a hitless update of entry to become target. Returns a
  * bit mask where 1 indicates that qword needs to be set disruptively.
@@ -1094,13 +1101,22 @@ static u8 arm_smmu_entry_qword_diff(struct arm_smmu_entry_writer *writer,
 {
 	__le64 target_used[NUM_ENTRY_QWORDS] = {};
 	__le64 cur_used[NUM_ENTRY_QWORDS] = {};
+	__le64 safe[NUM_ENTRY_QWORDS] = {};
 	u8 used_qword_diff = 0;
 	unsigned int i;
 
 	writer->ops->get_used(entry, cur_used);
 	writer->ops->get_used(target, target_used);
+	if (writer->ops->get_update_safe)
+		writer->ops->get_update_safe(entry, target, safe);
 
 	for (i = 0; i != NUM_ENTRY_QWORDS; i++) {
+		/*
+		 * Safe is only used for bits that are used by both entries,
+		 * otherwise it is sequenced according to the unused entry.
+		 */
+		safe[i] &= target_used[i] & cur_used[i];
+
 		/*
 		 * Check that masks are up to date, the make functions are not
 		 * allowed to set a bit to 1 if the used function doesn't say it
@@ -1109,6 +1125,7 @@ static u8 arm_smmu_entry_qword_diff(struct arm_smmu_entry_writer *writer,
 		WARN_ON_ONCE(target[i] & ~target_used[i]);
 
 		/* Bits can change because they are not currently being used */
+		cur_used[i] &= ~safe[i];
 		unused_update[i] = (entry[i] & cur_used[i]) |
 				   (target[i] & ~cur_used[i]);
 		/*
@@ -1121,7 +1138,7 @@ static u8 arm_smmu_entry_qword_diff(struct arm_smmu_entry_writer *writer,
 	return used_qword_diff;
 }
 
-static bool entry_set(struct arm_smmu_entry_writer *writer, __le64 *entry,
+static void entry_set(struct arm_smmu_entry_writer *writer, __le64 *entry,
 		      const __le64 *target, unsigned int start,
 		      unsigned int len)
 {
@@ -1137,7 +1154,6 @@ static bool entry_set(struct arm_smmu_entry_writer *writer, __le64 *entry,
 
 	if (changed)
 		writer->ops->sync(writer);
-	return changed;
 }
 
 /*
@@ -1207,12 +1223,9 @@ void arm_smmu_write_entry(struct arm_smmu_entry_writer *writer, __le64 *entry,
 		entry_set(writer, entry, target, 0, 1);
 	} else {
 		/*
-		 * No inuse bit changed. Sanity check that all unused bits are 0
-		 * in the entry. The target was already sanity checked by
-		 * compute_qword_diff().
+		 * No inuse bit changed, though safe bits may have changed.
 		 */
-		WARN_ON_ONCE(
-			entry_set(writer, entry, target, 0, NUM_ENTRY_QWORDS));
+		entry_set(writer, entry, target, 0, NUM_ENTRY_QWORDS);
 	}
 }
 EXPORT_SYMBOL_IF_KUNIT(arm_smmu_write_entry);
@@ -1543,6 +1556,7 @@ static void arm_smmu_ste_writer_sync_entry(struct arm_smmu_entry_writer *writer)
 static const struct arm_smmu_entry_writer_ops arm_smmu_ste_writer_ops = {
 	.sync = arm_smmu_ste_writer_sync_entry,
 	.get_used = arm_smmu_get_ste_used,
+	.get_update_safe = arm_smmu_get_ste_update_safe,
 };
 
 static void arm_smmu_write_ste(struct arm_smmu_master *master, u32 sid,
Signature · 1 line
2.43.0
Reviewed-by on v6 1/4
#2 lore raw

Re: [PATCH rc v6 1/4] iommu/arm-smmu-v3: Add update_safe bits to fix STE update sequence

Quoted 22 lines · Nicolin Chen

From: Jason Gunthorpe <[email protected]>

C_BAD_STE was observed when updating nested STE from an S1-bypass mode to an S1DSS-bypass mode. As both modes enabled S2, the used bit is slightly different than the normal S1-bypass and S1DSS-bypass modes. As a result, fields like MEV and EATS in S2's used list marked the word1 as a critical word that requested a STE.V=0. This breaks a hitless update.

However, both MEV and EATS aren't critical in terms of STE update. One controls the merge of the events and the other controls the ATS that is managed by the driver at the same time via pci_enable_ats().

Add an arm_smmu_get_ste_update_safe() to allow STE update algorithm to relax those fields, avoiding the STE update breakages.

After this change, entry_set has no caller checking its return value, so change it to void.

Note that this change is required by both MEV and EATS fields, which were introduced in different kernel versions. So add get_update_safe() first. MEV and EATS will be added to arm_smmu_get_ste_update_safe() separately.

Quoted 6 lines
Fixes 1e8be08d1c91 ("iommu/arm-smmu-v3: Support IOMMU_DOMAIN_NESTED")

Thanks!

#3 lore raw

PATCH v6 2/4 iommu/arm-smmu-v3: Mark STE MEV safe when computing the update sequence

In reply to Nicolin Chen

From: Jason Gunthorpe <[email protected]>

Nested CD tables set the MEV bit to try to reduce multi-fault spamming on the hypervisor. Since MEV is in STE word 1 this causes a breaking update sequence that is not required and impacts real workloads.

For the purposes of STE updates the value of MEV doesn't matter, if it is set/cleared early or late it just results in a change to the fault reports that must be supported by the kernel anyhow. The spec says:

Note: Software must expect, and be able to deal with, coalesced fault records even when MEV == 0.

So mark STE MEV safe when computing the update sequence, to avoid creating a breaking update.

Fixes da0c56520e88 ("iommu/arm-smmu-v3: Set MEV bit in nested STE for DoS mitigations")
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 10 ++++++++++
 1 file changed, 10 insertions(+)
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +10 -0
index 390446d259ab..ccd6357fa5a8 100644
@@ -1086,6 +1086,16 @@ VISIBLE_IF_KUNIT
 void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target,
 				  __le64 *safe_bits)
 {
+	/*
+	 * MEV does not meaningfully impact the operation of the HW, it only
+	 * changes how many fault events are generated, thus we can relax it
+	 * when computing the ordering. The spec notes the device can act like
+	 * MEV=1 anyhow:
+	 *
+	 *  Note: Software must expect, and be able to deal with, coalesced
+	 *  fault records even when MEV == 0.
+	 */
+	safe_bits[1] |= cpu_to_le64(STRTAB_STE_1_MEV);
 }
 EXPORT_SYMBOL_IF_KUNIT(arm_smmu_get_ste_update_safe);
 
Signature · 1 line
2.43.0
Reviewed-by on v6 2/4
#4 lore raw

Re: [PATCH rc v6 2/4] iommu/arm-smmu-v3: Mark STE MEV safe when computing the update sequence

Quoted 16 lines · Nicolin Chen

From: Jason Gunthorpe <[email protected]>

Nested CD tables set the MEV bit to try to reduce multi-fault spamming on the hypervisor. Since MEV is in STE word 1 this causes a breaking update sequence that is not required and impacts real workloads.

For the purposes of STE updates the value of MEV doesn't matter, if it is set/cleared early or late it just results in a change to the fault reports that must be supported by the kernel anyhow. The spec says:

Note: Software must expect, and be able to deal with, coalesced fault records even when MEV == 0.

So mark STE MEV safe when computing the update sequence, to avoid creating a breaking update.

Quoted 6 lines
Fixes da0c56520e88 ("iommu/arm-smmu-v3: Set MEV bit in nested STE for DoS mitigations")
Quoted 28 lines
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 10 ++++++++++
 1 file changed, 10 insertions(+)
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +10 -0
index 390446d259ab..ccd6357fa5a8 100644
@@ -1086,6 +1086,16 @@ VISIBLE_IF_KUNIT
 void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target,
 				  __le64 *safe_bits)
 {
+	/*
+	 * MEV does not meaningfully impact the operation of the HW, it only
+	 * changes how many fault events are generated, thus we can relax it
+	 * when computing the ordering. The spec notes the device can act like
+	 * MEV=1 anyhow:
+	 *
+	 *  Note: Software must expect, and be able to deal with, coalesced
+	 *  fault records even when MEV == 0.
+	 */
+	safe_bits[1] |= cpu_to_le64(STRTAB_STE_1_MEV);
 }
 EXPORT_SYMBOL_IF_KUNIT(arm_smmu_get_ste_update_safe);
 
Signature · 1 line
2.43.0
#5 lore raw

PATCH v6 3/4 iommu/arm-smmu-v3: Mark STE EATS safe when computing the update sequence

In reply to Nicolin Chen

From: Jason Gunthorpe <[email protected]>

If a VM wants to toggle EATS off at the same time as changing the CFG, the hypervisor will see EATS change to 0 and insert a V=0 breaking update into the STE even though the VM did not ask for that.

In bare metal, EATS is ignored by CFG=ABORT/BYPASS, which is why this does not cause a problem until we have nested where CFG is always a variation of S2 trans that does use EATS.

Relax the rules for EATS sequencing, we don't need it to be exact because the enclosing code will always disable ATS at the PCI device if we are changing EATS. This ensures there are no ATS transactions that can race with an EATS change so we don't need to carefully sequence these bits.

Fixes 1e8be08d1c91 ("iommu/arm-smmu-v3: Support IOMMU_DOMAIN_NESTED")
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +18 -0
index ccd6357fa5a8..58008fe94ab3 100644
@@ -1096,6 +1096,24 @@ void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target,
 	 *  fault records even when MEV == 0.
 	 */
 	safe_bits[1] |= cpu_to_le64(STRTAB_STE_1_MEV);
+
+	/*
+	 * When a STE comes to change EATS the sequencing code in the attach
+	 * logic already will have the PCI cap for ATS disabled. Thus at this
+	 * moment we can expect that the device will not generate ATS queries
+	 * and so we don't care about the sequencing of EATS. The purpose of
+	 * EATS is to protect the system from hostile untrusted devices that
+	 * issue ATS when the PCI config space is disabled. However, if EATS
+	 * is being changed then we already must be trusting the device since
+	 * the EATS security block is being disabled.
+	 *
+	 *  Note: Since we moved the EATS update to the first phase, changing
+	 *  S2S and EATS might transiently set S2S=1 and EATS=1, resulting in
+	 *  a bad STE. See "5.2 Stream Table Entry". In such a case, we can't
+	 *  do a hitless update.
+	 */
+	if (!((cur[2] | target[2]) & cpu_to_le64(STRTAB_STE_2_S2S)))
+		safe_bits[1] |= cpu_to_le64(STRTAB_STE_1_EATS);
 }
 EXPORT_SYMBOL_IF_KUNIT(arm_smmu_get_ste_update_safe);
 
Signature · 1 line
2.43.0
#6 lore raw

Re: [PATCH rc v6 3/4] iommu/arm-smmu-v3: Mark STE EATS safe when computing the update sequence

Quoted 40 lines · Nicolin Chen

From: Jason Gunthorpe <[email protected]>

If a VM wants to toggle EATS off at the same time as changing the CFG, the hypervisor will see EATS change to 0 and insert a V=0 breaking update into the STE even though the VM did not ask for that.

In bare metal, EATS is ignored by CFG=ABORT/BYPASS, which is why this does not cause a problem until we have nested where CFG is always a variation of S2 trans that does use EATS.

Relax the rules for EATS sequencing, we don't need it to be exact because the enclosing code will always disable ATS at the PCI device if we are changing EATS. This ensures there are no ATS transactions that can race with an EATS change so we don't need to carefully sequence these bits.

Fixes 1e8be08d1c91 ("iommu/arm-smmu-v3: Support IOMMU_DOMAIN_NESTED")
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +8 -0
index ccd6357fa5a8..58008fe94ab3 100644
@@ -1096,6 +1096,24 @@ void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target,
 	 *  fault records even when MEV == 0.
 	 */
 	safe_bits[1] |= cpu_to_le64(STRTAB_STE_1_MEV);
+
+	/*
+	 * When a STE comes to change EATS the sequencing code in the attach
+	 * logic already will have the PCI cap for ATS disabled. Thus at this
+	 * moment we can expect that the device will not generate ATS queries
+	 * and so we don't care about the sequencing of EATS. The purpose of
+	 * EATS is to protect the system from hostile untrusted devices that
+	 * issue ATS when the PCI config space is disabled. However, if EATS

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target, · line 1116

Quoted 10 lines
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +10 -0
+	 * is being changed then we already must be trusting the device since
+	 * the EATS security block is being disabled.
+	 *
+	 *  Note: Since we moved the EATS update to the first phase, changing
+	 *  S2S and EATS might transiently set S2S=1 and EATS=1, resulting in
+	 *  a bad STE. See "5.2 Stream Table Entry". In such a case, we can't
+	 *  do a hitless update.
+	 */
+	if (!((cur[2] | target[2]) & cpu_to_le64(STRTAB_STE_2_S2S)))
+		safe_bits[1] |= cpu_to_le64(STRTAB_STE_1_EATS);

I understand what we're trying to do here but isn't this implicitly saying it is safe to transition hitlessly to any non-zero EATS value, including S1CHK or RSVD. S1CHK might have other config dependencies?

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target, · line 1119

Quoted 3 lines
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +0 -0
 }
 EXPORT_SYMBOL_IF_KUNIT(arm_smmu_get_ste_update_safe);
 

Thanks,
Praan

#7 lore raw

Re: [PATCH rc v6 3/4] iommu/arm-smmu-v3: Mark STE EATS safe when computing the update sequence

Quoted 14 lines · Pranjal Shrivastava
Quoted 14 lines
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +14 -0
+
+	/*
+	 * When a STE comes to change EATS the sequencing code in the attach
+	 * logic already will have the PCI cap for ATS disabled. Thus at this
+	 * moment we can expect that the device will not generate ATS queries
+	 * and so we don't care about the sequencing of EATS. The purpose of
+	 * EATS is to protect the system from hostile untrusted devices that
+	 * issue ATS when the PCI config space is disabled. However, if EATS
+	 * is being changed then we already must be trusting the device since
+	 * the EATS security block is being disabled.
+	 *
+	 *  Note: Since we moved the EATS update to the first phase, changing
+	 *  S2S and EATS might transiently set S2S=1 and EATS=1, resulting in
+	 *  a bad STE. See "5.2 Stream Table Entry". In such a case, we can't
Quoted 8 lines

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target, · line 1116

Quoted 4 lines
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +4 -0
+	 *  do a hitless update.
+	 */
+	if (!((cur[2] | target[2]) & cpu_to_le64(STRTAB_STE_2_S2S)))
+		safe_bits[1] |= cpu_to_le64(STRTAB_STE_1_EATS);

I understand what we're trying to do here but isn't this implicitly saying it is safe to transition hitlessly to any non-zero EATS value, including S1CHK or RSVD. S1CHK might have other config dependencies?

Will pointed this issue with S1CHK, Nicolin has a suggestion to fix it here:

https://lore.kernel.org/linux-iommu/aWarF90zBqxD0Gef@Asurada-Nvidia/

It would block RSVD too.

Thanks,
Jason

#8 lore raw

Re: [PATCH rc v6 3/4] iommu/arm-smmu-v3: Mark STE EATS safe when computing the update sequence

Quoted 24 lines · Jason Gunthorpe
Quoted 14 lines · Pranjal Shrivastava
Quoted 14 lines
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +14 -0
+
+	/*
+	 * When a STE comes to change EATS the sequencing code in the attach
+	 * logic already will have the PCI cap for ATS disabled. Thus at this
+	 * moment we can expect that the device will not generate ATS queries
+	 * and so we don't care about the sequencing of EATS. The purpose of
+	 * EATS is to protect the system from hostile untrusted devices that
+	 * issue ATS when the PCI config space is disabled. However, if EATS
+	 * is being changed then we already must be trusting the device since
+	 * the EATS security block is being disabled.
+	 *
+	 *  Note: Since we moved the EATS update to the first phase, changing
+	 *  S2S and EATS might transiently set S2S=1 and EATS=1, resulting in
+	 *  a bad STE. See "5.2 Stream Table Entry". In such a case, we can't
Quoted 8 lines

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target, · line 1116

Quoted 4 lines
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +4 -0
+	 *  do a hitless update.
+	 */
+	if (!((cur[2] | target[2]) & cpu_to_le64(STRTAB_STE_2_S2S)))
+		safe_bits[1] |= cpu_to_le64(STRTAB_STE_1_EATS);

I understand what we're trying to do here but isn't this implicitly saying it is safe to transition hitlessly to any non-zero EATS value, including S1CHK or RSVD. S1CHK might have other config dependencies?

Quoted 6 lines

Will pointed this issue with S1CHK, Nicolin has a suggestion to fix it here:

https://lore.kernel.org/linux-iommu/aWarF90zBqxD0Gef@Asurada-Nvidia/

It would block RSVD too.

Ohh okay, sounds good then, my client dropped it somehow. I'll defer this to Will.

Quoted 2 lines

Thanks,
Jason

Thanks,
Praan

#9 lore raw

PATCH v6 4/4 iommu/arm-smmu-v3-test: Add nested s1bypass/s1dssbypass coverage

In reply to Nicolin Chen

STE in a nested case requires both S1 and S2 fields. And this makes the use case different from the existing one.

Add coverage for previously failed cases shifting between S2-only and S1+S2 STEs.

---
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c  | 47 +++++++++++++++++++
 1 file changed, 47 insertions(+)
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c +47 -0
index b254a94b2003..69c9ef441fc1 100644
@@ -33,8 +33,12 @@ static struct mm_struct sva_mm = {
 enum arm_smmu_test_master_feat {
 	ARM_SMMU_MASTER_TEST_ATS = BIT(0),
 	ARM_SMMU_MASTER_TEST_STALL = BIT(1),
+	ARM_SMMU_MASTER_TEST_NESTED = BIT(2),
 };
 
+static void arm_smmu_test_make_s2_ste(struct arm_smmu_ste *ste,
+				      enum arm_smmu_test_master_feat feat);
+
 static bool arm_smmu_entry_differs_in_used_bits(const __le64 *entry,
 						const __le64 *used_bits,
 						const __le64 *target,
@@ -210,6 +214,18 @@ static void arm_smmu_test_make_cdtable_ste(struct arm_smmu_ste *ste,
 	};
 
 	arm_smmu_make_cdtable_ste(ste, &master, ats_enabled, s1dss);
+	if (feat & ARM_SMMU_MASTER_TEST_NESTED) {
+		struct arm_smmu_ste s2ste;
+		int i;
+
+		arm_smmu_test_make_s2_ste(&s2ste,
+					  feat & ~ARM_SMMU_MASTER_TEST_NESTED);
+		ste->data[0] |= cpu_to_le64(
+			FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_NESTED));
+		ste->data[1] |= cpu_to_le64(STRTAB_STE_1_MEV);
+		for (i = 2; i < NUM_ENTRY_QWORDS; i++)
+			ste->data[i] = s2ste.data[i];
+	}
 }
 
 static void arm_smmu_v3_write_ste_test_bypass_to_abort(struct kunit *test)
@@ -567,6 +583,35 @@ static void arm_smmu_v3_write_ste_test_s2_to_s1_stall(struct kunit *test)
 						       NUM_EXPECTED_SYNCS(3));
 }
 
+static void
+arm_smmu_v3_write_ste_test_nested_s1dssbypass_to_s1bypass(struct kunit *test)
+{
+	struct arm_smmu_ste s1_ste;
+	struct arm_smmu_ste s2_ste;
+
+	arm_smmu_test_make_cdtable_ste(
+		&s1_ste, STRTAB_STE_1_S1DSS_BYPASS, fake_cdtab_dma_addr,
+		ARM_SMMU_MASTER_TEST_ATS | ARM_SMMU_MASTER_TEST_NESTED);
+	arm_smmu_test_make_s2_ste(&s2_ste, 0);
+	/* Expect an additional sync to unset ignored bits: EATS and MEV */
+	arm_smmu_v3_test_ste_expect_hitless_transition(test, &s1_ste, &s2_ste,
+						       NUM_EXPECTED_SYNCS(3));
+}
+
+static void
+arm_smmu_v3_write_ste_test_nested_s1bypass_to_s1dssbypass(struct kunit *test)
+{
+	struct arm_smmu_ste s1_ste;
+	struct arm_smmu_ste s2_ste;
+
+	arm_smmu_test_make_cdtable_ste(
+		&s1_ste, STRTAB_STE_1_S1DSS_BYPASS, fake_cdtab_dma_addr,
+		ARM_SMMU_MASTER_TEST_ATS | ARM_SMMU_MASTER_TEST_NESTED);
+	arm_smmu_test_make_s2_ste(&s2_ste, 0);
+	arm_smmu_v3_test_ste_expect_hitless_transition(test, &s2_ste, &s1_ste,
+						       NUM_EXPECTED_SYNCS(2));
+}
+
 static void arm_smmu_v3_write_cd_test_sva_clear(struct kunit *test)
 {
 	struct arm_smmu_cd cd = {};
@@ -613,6 +658,8 @@ static struct kunit_case arm_smmu_v3_test_cases[] = {
 	KUNIT_CASE(arm_smmu_v3_write_cd_test_s1_change_asid),
 	KUNIT_CASE(arm_smmu_v3_write_ste_test_s1_to_s2_stall),
 	KUNIT_CASE(arm_smmu_v3_write_ste_test_s2_to_s1_stall),
+	KUNIT_CASE(arm_smmu_v3_write_ste_test_nested_s1dssbypass_to_s1bypass),
+	KUNIT_CASE(arm_smmu_v3_write_ste_test_nested_s1bypass_to_s1dssbypass),
 	KUNIT_CASE(arm_smmu_v3_write_cd_test_sva_clear),
 	KUNIT_CASE(arm_smmu_v3_write_cd_test_sva_release),
 	{},
Signature · 1 line
2.43.0
Reviewed-by on v6 4/4
#10 lore raw

Re: [PATCH rc v6 4/4] iommu/arm-smmu-v3-test: Add nested s1bypass/s1dssbypass coverage

Quoted 9 lines · Nicolin Chen

STE in a nested case requires both S1 and S2 fields. And this makes the use case different from the existing one.

Add coverage for previously failed cases shifting between S2-only and S1+S2 STEs.

Quoted 4 lines
---
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c  | 47 +++++++++++++++++++
 1 file changed, 47 insertions(+)