Merge: [RHEL9.9] Updates to the IOMMU and DMA Mapping API subsystems

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/8007

# Merge Request Required Information

JIRA: https://issues.redhat.com/browse/RHEL-147906
Upstream-Status: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git

## Summary of Changes

Various fixes touching the subsystems that have landed upstream recently. Clean cherry-picks except for 1 commit that removed a function that has a different name in RHEL9.

Assisted-by: Claude:claude-opus-4-6
Signed-off-by: Jerry Snitselaar <jsnitsel@redhat.com>

Approved-by: Eder Zulian <ezulian@redhat.com>
Approved-by: Brian Masney <bmasney@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

drivers/iommu/amd/amd_iommu.h

@@ -15,7 +15,6 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data);
 irqreturn_t amd_iommu_int_thread_evtlog(int irq, void *data);
 irqreturn_t amd_iommu_int_thread_pprlog(int irq, void *data);
 irqreturn_t amd_iommu_int_thread_galog(int irq, void *data);
-irqreturn_t amd_iommu_int_handler(int irq, void *data);
 void amd_iommu_restart_log(struct amd_iommu *iommu, const char *evt_type,
 			   u8 cntrl_intr, u8 cntrl_log,
 			   u32 status_run_mask, u32 status_overflow_mask);

drivers/iommu/amd/init.c

@@ -1608,13 +1608,22 @@ static struct amd_iommu_pci_seg *__init alloc_pci_segment(u16 id,
 	list_add_tail(&pci_seg->list, &amd_iommu_pci_seg_list);
 
 	if (alloc_dev_table(pci_seg))
-		return NULL;
+		goto err_free_pci_seg;
 	if (alloc_alias_table(pci_seg))
-		return NULL;
+		goto err_free_dev_table;
 	if (alloc_rlookup_table(pci_seg))
-		return NULL;
+		goto err_free_alias_table;
 
 	return pci_seg;
+
+err_free_alias_table:
+	free_alias_table(pci_seg);
+err_free_dev_table:
+	free_dev_table(pci_seg);
+err_free_pci_seg:
+	list_del(&pci_seg->list);
+	kfree(pci_seg);
+	return NULL;
 }
 
 static struct amd_iommu_pci_seg *__init get_pci_segment(u16 id,
@@ -2230,12 +2239,8 @@ static int iommu_setup_msi(struct amd_iommu *iommu)
 	if (r)
 		return r;
 
-	r = request_threaded_irq(iommu->dev->irq,
-				 amd_iommu_int_handler,
-				 amd_iommu_int_thread,
-				 0, "AMD-Vi",
-				 iommu);
-
+	r = request_threaded_irq(iommu->dev->irq, NULL, amd_iommu_int_thread,
+				 IRQF_ONESHOT, "AMD-Vi", iommu);
 	if (r) {
 		pci_disable_msi(iommu->dev);
 		return r;
@@ -2409,8 +2414,8 @@ static int __iommu_setup_intcapxt(struct amd_iommu *iommu, const char *devname,
 		return irq;
 	}
 
-	ret = request_threaded_irq(irq, amd_iommu_int_handler,
-				   thread_fn, 0, devname, iommu);
+	ret = request_threaded_irq(irq, NULL, thread_fn, IRQF_ONESHOT, devname,
+				   iommu);
 	if (ret) {
 		irq_domain_free_irqs(irq, 1);
 		irq_domain_remove(domain);

drivers/iommu/amd/iommu.c

@@ -1144,11 +1144,6 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-irqreturn_t amd_iommu_int_handler(int irq, void *data)
-{
-	return IRQ_WAKE_THREAD;
-}
-
 /****************************************************************************
  *
  * IOMMU command queuing functions
@@ -2424,8 +2419,6 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev)
 		goto out_err;
 	}
 
-out_err:
-
 	iommu_completion_wait(iommu);
 
 	if (FEATURE_NUM_INT_REMAP_SUP_2K(amd_iommu_efr2))
@@ -2436,6 +2429,7 @@ out_err:
 	if (dev_is_pci(dev))
 		pci_prepare_ats(to_pci_dev(dev), PAGE_SHIFT);
 
+out_err:
 	return iommu_dev;
 }
 
@@ -2666,8 +2660,20 @@ static struct iommu_domain blocked_domain = {
 
 static struct protection_domain identity_domain;
 
+static int amd_iommu_identity_attach(struct iommu_domain *dom, struct device *dev)
+{
+	/*
+	 * Don't allow attaching a device to the identity domain if SNP is
+	 * enabled.
+	 */
+	if (amd_iommu_snp_en)
+		return -EINVAL;
+
+	return amd_iommu_attach_device(dom, dev);
+}
+
 static const struct iommu_domain_ops identity_domain_ops = {
-	.attach_dev = amd_iommu_attach_device,
+	.attach_dev = amd_iommu_identity_attach,
 };
 
 void amd_iommu_init_identity_domain(void)
@@ -3352,7 +3358,7 @@ static int __modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
 static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
 			  struct irte_ga *irte)
 {
-	bool ret;
+	int ret;
 
 	ret = __modify_irte_ga(iommu, devid, index, irte);
 	if (ret)

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c

@@ -165,7 +165,9 @@ static int arm_smmu_attach_dev_nested(struct iommu_domain *domain,
 	 * config bit here base this off the EATS value in the STE. If the EATS
 	 * is set then the VM must generate ATC flushes.
 	 */
-	state.disable_ats = !nested_domain->enable_ats;
+	if (FIELD_GET(STRTAB_STE_0_CFG, le64_to_cpu(nested_domain->ste[0])) ==
+	    STRTAB_STE_0_CFG_S1_TRANS)
+		state.disable_ats = !nested_domain->enable_ats;
 	ret = arm_smmu_attach_prepare(&state, domain);
 	if (ret) {
 		mutex_unlock(&arm_smmu_asid_lock);

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c

@@ -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

@@ -1082,6 +1082,49 @@ 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)
+{
+	const __le64 eats_s1chk =
+		FIELD_PREP(STRTAB_STE_1_EATS, STRTAB_STE_1_EATS_S1CHK);
+	const __le64 eats_trans =
+		FIELD_PREP(STRTAB_STE_1_EATS, STRTAB_STE_1_EATS_TRANS);
+
+	/*
+	 * When an STE changes EATS_TRANS, 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_TRANS is to protect the system from hostile untrusted devices
+	 * that issue ATS when the PCI config space is disabled. However, if
+	 * EATS_TRANS is being changed, then we must have already trusted the
+	 * device as the EATS_TRANS security block is being disabled.
+	 *
+	 *  Note: now the EATS_TRANS update is moved to the first entry_set().
+	 *  Changing S2S and EATS might transiently result in S2S=1 and EATS=1
+	 *  which is a bad STE (see "5.2 Stream Table Entry"). In such a case,
+	 *  we can't do a hitless update. Also, it should not be added to the
+	 *  safe bits with STRTAB_STE_1_EATS_S1CHK, because EATS=0b11 would be
+	 *  effectively an errant 0b00 configuration.
+	 */
+	if (!((cur[1] | target[1]) & cpu_to_le64(eats_s1chk)) &&
+	    !((cur[2] | target[2]) & cpu_to_le64(STRTAB_STE_2_S2S)))
+		safe_bits[1] |= cpu_to_le64(eats_trans);
+
+	/*
+	 * 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);
+
 /*
  * 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 +1137,22 @@ 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 +1161,7 @@ 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 +1174,7 @@ 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 +1190,6 @@ static bool entry_set(struct arm_smmu_entry_writer *writer, __le64 *entry,
 
 	if (changed)
 		writer->ops->sync(writer);
-	return changed;
 }
 
 /*
@@ -1207,12 +1259,9 @@ 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);
@@ -1464,7 +1513,7 @@ static int arm_smmu_alloc_cd_tables(struct arm_smmu_master *master)
 		cd_table->l2.l1tab = dma_alloc_coherent(smmu->dev, l1size,
 							&cd_table->cdtab_dma,
 							GFP_KERNEL);
-		if (!cd_table->l2.l2ptrs) {
+		if (!cd_table->l2.l1tab) {
 			ret = -ENOMEM;
 			goto err_free_l2ptrs;
 		}
@@ -1543,6 +1592,7 @@ 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,
@@ -2551,7 +2601,7 @@ static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain,
 				     ARM_SMMU_FEAT_VAX) ? 52 : 48;
 
 		pgtbl_cfg.ias = min_t(unsigned long, ias, VA_BITS);
-		pgtbl_cfg.oas = smmu->ias;
+		pgtbl_cfg.oas = smmu->oas;
 		if (enable_dirty)
 			pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_ARM_HD;
 		fmt = ARM_64_LPAE_S1;
@@ -2561,7 +2611,7 @@ static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain,
 	case ARM_SMMU_DOMAIN_S2:
 		if (enable_dirty)
 			return -EOPNOTSUPP;
-		pgtbl_cfg.ias = smmu->ias;
+		pgtbl_cfg.ias = smmu->oas;
 		pgtbl_cfg.oas = smmu->oas;
 		fmt = ARM_64_LPAE_S2;
 		finalise_stage_fn = arm_smmu_domain_finalise_s2;
@@ -4393,13 +4443,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 	}
 
 	/* We only support the AArch64 table format at present */
-	switch (FIELD_GET(IDR0_TTF, reg)) {
-	case IDR0_TTF_AARCH32_64:
-		smmu->ias = 40;
-		fallthrough;
-	case IDR0_TTF_AARCH64:
-		break;
-	default:
+	if (!(FIELD_GET(IDR0_TTF, reg) & IDR0_TTF_AARCH64)) {
 		dev_err(smmu->dev, "AArch64 table format not supported!\n");
 		return -ENXIO;
 	}
@@ -4509,8 +4553,6 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 		dev_warn(smmu->dev,
 			 "failed to set DMA mask for table walker\n");
 
-	smmu->ias = max(smmu->ias, smmu->oas);
-
 	if ((smmu->features & ARM_SMMU_FEAT_TRANS_S1) &&
 	    (smmu->features & ARM_SMMU_FEAT_TRANS_S2))
 		smmu->features |= ARM_SMMU_FEAT_NESTING;
@@ -4520,8 +4562,8 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 	if (arm_smmu_sva_supported(smmu))
 		smmu->features |= ARM_SMMU_FEAT_SVA;
 
-	dev_info(smmu->dev, "ias %lu-bit, oas %lu-bit (features 0x%08x)\n",
-		 smmu->ias, smmu->oas, smmu->features);
+	dev_info(smmu->dev, "oas %lu-bit (features 0x%08x)\n",
+		 smmu->oas, smmu->features);
 	return 0;
 }
 

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h

@@ -43,7 +43,6 @@ struct arm_vsmmu;
 #define IDR0_COHACC			(1 << 4)
 #define IDR0_TTF			GENMASK(3, 2)
 #define IDR0_TTF_AARCH64		2
-#define IDR0_TTF_AARCH32_64		3
 #define IDR0_S1P			(1 << 1)
 #define IDR0_S2P			(1 << 0)
 
@@ -782,7 +781,6 @@ struct arm_smmu_device {
 	int				gerr_irq;
 	int				combined_irq;
 
-	unsigned long			ias; /* IPA */
 	unsigned long			oas; /* PA */
 	unsigned long			pgsize_bitmap;
 
@@ -898,6 +896,8 @@ 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);
 };
 
@@ -909,6 +909,8 @@ 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/arm-smmu-qcom.c

@@ -431,17 +431,19 @@ static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
 
 	/*
 	 * Some platforms support more than the Arm SMMU architected maximum of
-	 * 128 stream matching groups. For unknown reasons, the additional
-	 * groups don't exhibit the same behavior as the architected registers,
-	 * so limit the groups to 128 until the behavior is fixed for the other
-	 * groups.
+	 * 128 stream matching groups. The additional registers appear to have
+	 * the same behavior as the architected registers in the hardware.
+	 * However, on some firmware versions, the hypervisor does not
+	 * correctly trap and emulate accesses to the additional registers,
+	 * resulting in unexpected behavior.
+	 *
+	 * If there are more than 128 groups, use the last reliable group to
+	 * detect if we need to apply the bypass quirk.
 	 */
-	if (smmu->num_mapping_groups > 128) {
-		dev_notice(smmu->dev, "\tLimiting the stream matching groups to 128\n");
-		smmu->num_mapping_groups = 128;
-	}
-
-	last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1);
+	if (smmu->num_mapping_groups > 128)
+		last_s2cr = ARM_SMMU_GR0_S2CR(127);
+	else
+		last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1);
 
 	/*
 	 * With some firmware versions writes to S2CR of type FAULT are
@@ -464,6 +466,11 @@ static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
 
 		reg = FIELD_PREP(ARM_SMMU_CBAR_TYPE, CBAR_TYPE_S1_TRANS_S2_BYPASS);
 		arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(qsmmu->bypass_cbndx), reg);
+
+		if (smmu->num_mapping_groups > 128) {
+			dev_notice(smmu->dev, "\tLimiting the stream matching groups to 128\n");
+			smmu->num_mapping_groups = 128;
+		}
 	}
 
 	for (i = 0; i < smmu->num_mapping_groups; i++) {

drivers/iommu/intel/Kconfig

@@ -66,7 +66,7 @@ config INTEL_IOMMU_DEFAULT_ON
 
 config INTEL_IOMMU_FLOPPY_WA
 	def_bool y
-	depends on X86
+	depends on X86 && BLK_DEV_FD
 	help
 	  Floppy disk drivers are known to bypass DMA API calls
 	  thereby failing to work when IOMMU is enabled. This

drivers/iommu/intel/cache.c

@@ -363,6 +363,13 @@ static void qi_batch_add_pasid_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16
 	qi_batch_increment_index(iommu, batch);
 }
 
+static bool intel_domain_use_piotlb(struct dmar_domain *domain)
+{
+	return domain->domain.type == IOMMU_DOMAIN_SVA ||
+			domain->domain.type == IOMMU_DOMAIN_NESTED ||
+			intel_domain_is_fs_paging(domain);
+}
+
 static void cache_tag_flush_iotlb(struct dmar_domain *domain, struct cache_tag *tag,
 				  unsigned long addr, unsigned long pages,
 				  unsigned long mask, int ih)
@@ -370,7 +377,7 @@ static void cache_tag_flush_iotlb(struct dmar_domain *domain, struct cache_tag *
 	struct intel_iommu *iommu = tag->iommu;
 	u64 type = DMA_TLB_PSI_FLUSH;
 
-	if (intel_domain_is_fs_paging(domain)) {
+	if (intel_domain_use_piotlb(domain)) {
 		qi_batch_add_piotlb(iommu, tag->domain_id, tag->pasid, addr,
 				    pages, ih, domain->qi_batch);
 		return;

drivers/iommu/intel/dmar.c

@@ -1314,7 +1314,6 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index)
 	if (fault & DMA_FSTS_ITE) {
 		head = readl(iommu->reg + DMAR_IQH_REG);
 		head = ((head >> shift) - 1 + QI_LENGTH) % QI_LENGTH;
-		head |= 1;
 		tail = readl(iommu->reg + DMAR_IQT_REG);
 		tail = ((tail >> shift) - 1 + QI_LENGTH) % QI_LENGTH;
 
@@ -1331,7 +1330,7 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index)
 		do {
 			if (qi->desc_status[head] == QI_IN_USE)
 				qi->desc_status[head] = QI_ABORT;
-			head = (head - 2 + QI_LENGTH) % QI_LENGTH;
+			head = (head - 1 + QI_LENGTH) % QI_LENGTH;
 		} while (head != tail);
 
 		/*

drivers/iommu/intel/iommu.c

@@ -1722,22 +1722,22 @@ static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8
 	}
 
 	did = context_domain_id(context);
-	context_clear_entry(context);
+	context_clear_present(context);
 	__iommu_flush_cache(iommu, context, sizeof(*context));
 	spin_unlock(&iommu->lock);
 	intel_context_flush_no_pasid(info, context, did);
+	context_clear_entry(context);
+	__iommu_flush_cache(iommu, context, sizeof(*context));
 }
 
 int __domain_setup_first_level(struct intel_iommu *iommu, struct device *dev,
 			       ioasid_t pasid, u16 did, phys_addr_t fsptptr,
 			       int flags, struct iommu_domain *old)
 {
-	if (!old)
-		return intel_pasid_setup_first_level(iommu, dev, fsptptr, pasid,
-						     did, flags);
-	return intel_pasid_replace_first_level(iommu, dev, fsptptr, pasid, did,
-					       iommu_domain_did(old, iommu),
-					       flags);
+	if (old)
+		intel_pasid_tear_down_entry(iommu, dev, pasid, false);
+
+	return intel_pasid_setup_first_level(iommu, dev, fsptptr, pasid, did, flags);
 }
 
 static int domain_setup_second_level(struct intel_iommu *iommu,
@@ -1745,23 +1745,20 @@ static int domain_setup_second_level(struct intel_iommu *iommu,
 				     struct device *dev, ioasid_t pasid,
 				     struct iommu_domain *old)
 {
-	if (!old)
-		return intel_pasid_setup_second_level(iommu, domain,
-						      dev, pasid);
-	return intel_pasid_replace_second_level(iommu, domain, dev,
-						iommu_domain_did(old, iommu),
-						pasid);
+	if (old)
+		intel_pasid_tear_down_entry(iommu, dev, pasid, false);
+
+	return intel_pasid_setup_second_level(iommu, domain, dev, pasid);
 }
 
 static int domain_setup_passthrough(struct intel_iommu *iommu,
 				    struct device *dev, ioasid_t pasid,
 				    struct iommu_domain *old)
 {
-	if (!old)
-		return intel_pasid_setup_pass_through(iommu, dev, pasid);
-	return intel_pasid_replace_pass_through(iommu, dev,
-						iommu_domain_did(old, iommu),
-						pasid);
+	if (old)
+		intel_pasid_tear_down_entry(iommu, dev, pasid, false);
+
+	return intel_pasid_setup_pass_through(iommu, dev, pasid);
 }
 
 static int domain_setup_first_level(struct intel_iommu *iommu,
@@ -3817,7 +3814,7 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 			}
 
 			if (info->ats_supported && ecap_prs(iommu->ecap) &&
-			    pci_pri_supported(pdev))
+			    ecap_pds(iommu->ecap) && pci_pri_supported(pdev))
 				info->pri_supported = 1;
 		}
 	}

drivers/iommu/intel/iommu.h

@@ -973,7 +973,26 @@ static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
 
 static inline void context_set_present(struct context_entry *context)
 {
-	context->lo |= 1;
+	u64 val;
+
+	dma_wmb();
+	val = READ_ONCE(context->lo) | 1;
+	WRITE_ONCE(context->lo, val);
+}
+
+/*
+ * Clear the Present (P) bit (bit 0) of a context table entry. This initiates
+ * the transition of the entry's ownership from hardware to software. The
+ * caller is responsible for fulfilling the invalidation handshake recommended
+ * by the VT-d spec, Section 6.5.3.3 (Guidance to Software for Invalidations).
+ */
+static inline void context_clear_present(struct context_entry *context)
+{
+	u64 val;
+
+	val = READ_ONCE(context->lo) & GENMASK_ULL(63, 1);
+	WRITE_ONCE(context->lo, val);
+	dma_wmb();
 }
 
 static inline void context_set_fault_enable(struct context_entry *context)
@@ -1101,7 +1120,7 @@ static inline void qi_desc_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
 				 struct qi_desc *desc)
 {
 	u8 dw = 0, dr = 0;
-	int ih = 0;
+	int ih = addr & 1;
 
 	if (cap_write_drain(iommu->cap))
 		dw = 1;

drivers/iommu/intel/nested.c

@@ -141,11 +141,10 @@ static int domain_setup_nested(struct intel_iommu *iommu,
 			       struct device *dev, ioasid_t pasid,
 			       struct iommu_domain *old)
 {
-	if (!old)
-		return intel_pasid_setup_nested(iommu, dev, pasid, domain);
-	return intel_pasid_replace_nested(iommu, dev, pasid,
-					  iommu_domain_did(old, iommu),
-					  domain);
+	if (old)
+		intel_pasid_tear_down_entry(iommu, dev, pasid, false);
+
+	return intel_pasid_setup_nested(iommu, dev, pasid, domain);
 }
 
 static int intel_nested_set_dev_pasid(struct iommu_domain *domain,

drivers/iommu/intel/pasid.c

@@ -153,6 +153,9 @@ retry:
 		if (!entries)
 			return NULL;
 
+		if (!ecap_coherent(info->iommu->ecap))
+			clflush_cache_range(entries, VTD_PAGE_SIZE);
+
 		/*
 		 * The pasid directory table entry won't be freed after
 		 * allocation. No worry about the race with free and
@@ -165,10 +168,8 @@ retry:
 			iommu_free_pages(entries);
 			goto retry;
 		}
-		if (!ecap_coherent(info->iommu->ecap)) {
-			clflush_cache_range(entries, VTD_PAGE_SIZE);
+		if (!ecap_coherent(info->iommu->ecap))
 			clflush_cache_range(&dir[dir_index].val, sizeof(*dir));
-		}
 	}
 
 	return &entries[index];
@@ -218,7 +219,7 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
 	if (!info || !info->ats_enabled)
 		return;
 
-	if (pci_dev_is_disconnected(to_pci_dev(dev)))
+	if (!pci_device_is_present(to_pci_dev(dev)))
 		return;
 
 	sid = PCI_DEVID(info->bus, info->devfn);
@@ -272,7 +273,7 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
 
 	did = pasid_get_domain_id(pte);
 	pgtt = pasid_pte_get_pgtt(pte);
-	intel_pasid_clear_entry(dev, pasid, fault_ignore);
+	pasid_clear_present(pte);
 	spin_unlock(&iommu->lock);
 
 	if (!ecap_coherent(iommu->ecap))
@@ -286,6 +287,10 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
 		iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
 
 	devtlb_invalidation_with_pasid(iommu, dev, pasid);
+	intel_pasid_clear_entry(dev, pasid, fault_ignore);
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(pte, sizeof(*pte));
+
 	if (!fault_ignore)
 		intel_iommu_drain_pasid_prq(dev, pasid);
 }
@@ -412,50 +417,6 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, struct device *dev,
 	return 0;
 }
 
-int intel_pasid_replace_first_level(struct intel_iommu *iommu,
-				    struct device *dev, phys_addr_t fsptptr,
-				    u32 pasid, u16 did, u16 old_did,
-				    int flags)
-{
-	struct pasid_entry *pte, new_pte;
-
-	if (!ecap_flts(iommu->ecap)) {
-		pr_err("No first level translation support on %s\n",
-		       iommu->name);
-		return -EINVAL;
-	}
-
-	if ((flags & PASID_FLAG_FL5LP) && !cap_fl5lp_support(iommu->cap)) {
-		pr_err("No 5-level paging support for first-level on %s\n",
-		       iommu->name);
-		return -EINVAL;
-	}
-
-	pasid_pte_config_first_level(iommu, &new_pte, fsptptr, did, flags);
-
-	spin_lock(&iommu->lock);
-	pte = intel_pasid_get_entry(dev, pasid);
-	if (!pte) {
-		spin_unlock(&iommu->lock);
-		return -ENODEV;
-	}
-
-	if (!pasid_pte_is_present(pte)) {
-		spin_unlock(&iommu->lock);
-		return -EINVAL;
-	}
-
-	WARN_ON(old_did != pasid_get_domain_id(pte));
-
-	*pte = new_pte;
-	spin_unlock(&iommu->lock);
-
-	intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
-	intel_iommu_drain_pasid_prq(dev, pasid);
-
-	return 0;
-}
-
 /*
  * Set up the scalable mode pasid entry for second only translation type.
  */
@@ -523,57 +484,6 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 	return 0;
 }
 
-int intel_pasid_replace_second_level(struct intel_iommu *iommu,
-				     struct dmar_domain *domain,
-				     struct device *dev, u16 old_did,
-				     u32 pasid)
-{
-	struct pasid_entry *pte, new_pte;
-	struct dma_pte *pgd;
-	u64 pgd_val;
-	u16 did;
-
-	/*
-	 * If hardware advertises no support for second level
-	 * translation, return directly.
-	 */
-	if (!ecap_slts(iommu->ecap)) {
-		pr_err("No second level translation support on %s\n",
-		       iommu->name);
-		return -EINVAL;
-	}
-
-	pgd = domain->pgd;
-	pgd_val = virt_to_phys(pgd);
-	did = domain_id_iommu(domain, iommu);
-
-	pasid_pte_config_second_level(iommu, &new_pte, pgd_val,
-				      domain->agaw, did,
-				      domain->dirty_tracking);
-
-	spin_lock(&iommu->lock);
-	pte = intel_pasid_get_entry(dev, pasid);
-	if (!pte) {
-		spin_unlock(&iommu->lock);
-		return -ENODEV;
-	}
-
-	if (!pasid_pte_is_present(pte)) {
-		spin_unlock(&iommu->lock);
-		return -EINVAL;
-	}
-
-	WARN_ON(old_did != pasid_get_domain_id(pte));
-
-	*pte = new_pte;
-	spin_unlock(&iommu->lock);
-
-	intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
-	intel_iommu_drain_pasid_prq(dev, pasid);
-
-	return 0;
-}
-
 /*
  * Set up dirty tracking on a second only or nested translation type.
  */
@@ -686,38 +596,6 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 	return 0;
 }
 
-int intel_pasid_replace_pass_through(struct intel_iommu *iommu,
-				     struct device *dev, u16 old_did,
-				     u32 pasid)
-{
-	struct pasid_entry *pte, new_pte;
-	u16 did = FLPT_DEFAULT_DID;
-
-	pasid_pte_config_pass_through(iommu, &new_pte, did);
-
-	spin_lock(&iommu->lock);
-	pte = intel_pasid_get_entry(dev, pasid);
-	if (!pte) {
-		spin_unlock(&iommu->lock);
-		return -ENODEV;
-	}
-
-	if (!pasid_pte_is_present(pte)) {
-		spin_unlock(&iommu->lock);
-		return -EINVAL;
-	}
-
-	WARN_ON(old_did != pasid_get_domain_id(pte));
-
-	*pte = new_pte;
-	spin_unlock(&iommu->lock);
-
-	intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
-	intel_iommu_drain_pasid_prq(dev, pasid);
-
-	return 0;
-}
-
 /*
  * Set the page snoop control for a pasid entry which has been set up.
  */
@@ -848,69 +726,6 @@ int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 	return 0;
 }
 
-int intel_pasid_replace_nested(struct intel_iommu *iommu,
-			       struct device *dev, u32 pasid,
-			       u16 old_did, struct dmar_domain *domain)
-{
-	struct iommu_hwpt_vtd_s1 *s1_cfg = &domain->s1_cfg;
-	struct dmar_domain *s2_domain = domain->s2_domain;
-	u16 did = domain_id_iommu(domain, iommu);
-	struct pasid_entry *pte, new_pte;
-
-	/* Address width should match the address width supported by hardware */
-	switch (s1_cfg->addr_width) {
-	case ADDR_WIDTH_4LEVEL:
-		break;
-	case ADDR_WIDTH_5LEVEL:
-		if (!cap_fl5lp_support(iommu->cap)) {
-			dev_err_ratelimited(dev,
-					    "5-level paging not supported\n");
-			return -EINVAL;
-		}
-		break;
-	default:
-		dev_err_ratelimited(dev, "Invalid stage-1 address width %d\n",
-				    s1_cfg->addr_width);
-		return -EINVAL;
-	}
-
-	if ((s1_cfg->flags & IOMMU_VTD_S1_SRE) && !ecap_srs(iommu->ecap)) {
-		pr_err_ratelimited("No supervisor request support on %s\n",
-				   iommu->name);
-		return -EINVAL;
-	}
-
-	if ((s1_cfg->flags & IOMMU_VTD_S1_EAFE) && !ecap_eafs(iommu->ecap)) {
-		pr_err_ratelimited("No extended access flag support on %s\n",
-				   iommu->name);
-		return -EINVAL;
-	}
-
-	pasid_pte_config_nestd(iommu, &new_pte, s1_cfg, s2_domain, did);
-
-	spin_lock(&iommu->lock);
-	pte = intel_pasid_get_entry(dev, pasid);
-	if (!pte) {
-		spin_unlock(&iommu->lock);
-		return -ENODEV;
-	}
-
-	if (!pasid_pte_is_present(pte)) {
-		spin_unlock(&iommu->lock);
-		return -EINVAL;
-	}
-
-	WARN_ON(old_did != pasid_get_domain_id(pte));
-
-	*pte = new_pte;
-	spin_unlock(&iommu->lock);
-
-	intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
-	intel_iommu_drain_pasid_prq(dev, pasid);
-
-	return 0;
-}
-
 /*
  * Interfaces to setup or teardown a pasid table to the scalable-mode
  * context table entry:
@@ -1023,7 +838,7 @@ static int device_pasid_table_setup(struct device *dev, u8 bus, u8 devfn)
 	}
 
 	if (context_copied(iommu, bus, devfn)) {
-		context_clear_entry(context);
+		context_clear_present(context);
 		__iommu_flush_cache(iommu, context, sizeof(*context));
 
 		/*
@@ -1043,6 +858,9 @@ static int device_pasid_table_setup(struct device *dev, u8 bus, u8 devfn)
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
 		devtlb_invalidation_with_pasid(iommu, dev, IOMMU_NO_PASID);
 
+		context_clear_entry(context);
+		__iommu_flush_cache(iommu, context, sizeof(*context));
+
 		/*
 		 * At this point, the device is supposed to finish reset at
 		 * its driver probe stage, so no in-flight DMA will exist,
@@ -1106,6 +924,14 @@ static void __context_flush_dev_iotlb(struct device_domain_info *info)
 	if (!info->ats_enabled)
 		return;
 
+	/*
+	 * Skip dev-IOTLB flush for inaccessible PCIe devices to prevent the
+	 * Intel IOMMU from waiting indefinitely for an ATS invalidation that
+	 * cannot complete.
+	 */
+	if (!pci_device_is_present(to_pci_dev(info->dev)))
+		return;
+
 	qi_flush_dev_iotlb(info->iommu, PCI_DEVID(info->bus, info->devfn),
 			   info->pfsid, info->ats_qdep, 0, MAX_AGAW_PFN_WIDTH);
 

drivers/iommu/intel/pasid.h

@@ -233,9 +233,23 @@ static inline void pasid_set_wpe(struct pasid_entry *pe)
  */
 static inline void pasid_set_present(struct pasid_entry *pe)
 {
+	dma_wmb();
 	pasid_set_bits(&pe->val[0], 1 << 0, 1);
 }
 
+/*
+ * Clear the Present (P) bit (bit 0) of a scalable-mode PASID table entry.
+ * This initiates the transition of the entry's ownership from hardware
+ * to software. The caller is responsible for fulfilling the invalidation
+ * handshake recommended by the VT-d spec, Section 6.5.3.3 (Guidance to
+ * Software for Invalidations).
+ */
+static inline void pasid_clear_present(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 0, 0);
+	dma_wmb();
+}
+
 /*
  * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID
  * entry.
@@ -301,20 +315,6 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 				   struct device *dev, u32 pasid);
 int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 			     u32 pasid, struct dmar_domain *domain);
-int intel_pasid_replace_first_level(struct intel_iommu *iommu,
-				    struct device *dev, phys_addr_t fsptptr,
-				    u32 pasid, u16 did, u16 old_did, int flags);
-int intel_pasid_replace_second_level(struct intel_iommu *iommu,
-				     struct dmar_domain *domain,
-				     struct device *dev, u16 old_did,
-				     u32 pasid);
-int intel_pasid_replace_pass_through(struct intel_iommu *iommu,
-				     struct device *dev, u16 old_did,
-				     u32 pasid);
-int intel_pasid_replace_nested(struct intel_iommu *iommu,
-			       struct device *dev, u32 pasid,
-			       u16 old_did, struct dmar_domain *domain);
-
 void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 				 struct device *dev, u32 pasid,
 				 bool fault_ignore);

drivers/iommu/intel/svm.c

@@ -164,9 +164,12 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 	if (IS_ERR(dev_pasid))
 		return PTR_ERR(dev_pasid);
 
-	ret = iopf_for_domain_replace(domain, old, dev);
-	if (ret)
-		goto out_remove_dev_pasid;
+	/* SVA with non-IOMMU/PRI IOPF handling is allowed. */
+	if (info->pri_supported) {
+		ret = iopf_for_domain_replace(domain, old, dev);
+		if (ret)
+			goto out_remove_dev_pasid;
+	}
 
 	/* Setup the pasid table: */
 	sflags = cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
@@ -180,7 +183,8 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 
 	return 0;
 out_unwind_iopf:
-	iopf_for_domain_replace(old, domain, dev);
+	if (info->pri_supported)
+		iopf_for_domain_replace(old, domain, dev);
 out_remove_dev_pasid:
 	domain_remove_dev_pasid(domain, dev, pasid);
 	return ret;

drivers/iommu/io-pgtable-arm.c

@@ -638,7 +638,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 	pte = READ_ONCE(*ptep);
 	if (!pte) {
 		WARN_ON(!(data->iop.cfg.quirks & IO_PGTABLE_QUIRK_NO_WARN));
-		return -ENOENT;
+		return 0;
 	}
 
 	/* If the size matches this level, we're in the right place */

drivers/iommu/iommufd/io_pagetable.c

@@ -707,7 +707,8 @@ static int iopt_unmap_iova_range(struct io_pagetable *iopt, unsigned long start,
 	struct iopt_area *area;
 	unsigned long unmapped_bytes = 0;
 	unsigned int tries = 0;
-	int rc = -ENOENT;
+	/* If there are no mapped entries then success */
+	int rc = 0;
 
 	/*
 	 * The domains_rwsem must be held in read mode any time any area->pages
@@ -777,8 +778,6 @@ again:
 
 		down_write(&iopt->iova_rwsem);
 	}
-	if (unmapped_bytes)
-		rc = 0;
 
 out_unlock_iova:
 	up_write(&iopt->iova_rwsem);
@@ -815,13 +814,8 @@ int iopt_unmap_iova(struct io_pagetable *iopt, unsigned long iova,
 
 int iopt_unmap_all(struct io_pagetable *iopt, unsigned long *unmapped)
 {
-	int rc;
-
-	rc = iopt_unmap_iova_range(iopt, 0, ULONG_MAX, unmapped);
 	/* If the IOVAs are empty then unmap all succeeds */
-	if (rc == -ENOENT)
-		return 0;
-	return rc;
+	return iopt_unmap_iova_range(iopt, 0, ULONG_MAX, unmapped);
 }
 
 /* The caller must always free all the nodes in the allowed_iova rb_root. */

drivers/iommu/iommufd/ioas.c

@@ -367,6 +367,10 @@ int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd)
 				     &unmapped);
 		if (rc)
 			goto out_put;
+		if (!unmapped) {
+			rc = -ENOENT;
+			goto out_put;
+		}
 	}
 
 	cmd->length = unmapped;

drivers/iommu/ipmmu-vmsa.c

@@ -720,6 +720,8 @@ static int ipmmu_init_platform_device(struct device *dev,
 
 	dev_iommu_priv_set(dev, platform_get_drvdata(ipmmu_pdev));
 
+	put_device(&ipmmu_pdev->dev);
+
 	return 0;
 }
 

drivers/iommu/tegra-smmu.c

@@ -830,10 +830,9 @@ static struct tegra_smmu *tegra_smmu_find(struct device_node *np)
 		return NULL;
 
 	mc = platform_get_drvdata(pdev);
-	if (!mc) {
-		put_device(&pdev->dev);
+	put_device(&pdev->dev);
+	if (!mc)
 		return NULL;
-	}
 
 	return mc->smmu;
 }

include/linux/map_benchmark.h

@@ -27,5 +27,6 @@ struct map_benchmark {
 	__u32 dma_dir; /* DMA data direction */
 	__u32 dma_trans_ns; /* time for DMA transmission in ns */
 	__u32 granule;  /* how many PAGE_SIZE will do map/unmap once a time */
+	__u8 expansion[76]; /* For future use */
 };
 #endif /* _KERNEL_DMA_BENCHMARK_H */

include/linux/of_device.h

@@ -75,8 +75,9 @@ static inline const struct of_device_id *of_match_device(
 }
 
 static inline int of_dma_configure_id(struct device *dev,
-				   struct device_node *np,
-				   bool force_dma)
+				      struct device_node *np,
+				      bool force_dma,
+				      const u32 *id)
 {
 	return 0;
 }

kernel/dma/direct.c

@@ -486,6 +486,7 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		case PCI_P2PDMA_MAP_BUS_ADDR:
 			sg->dma_address = pci_p2pdma_bus_addr_map(&p2pdma_state,
 					sg_phys(sg));
+			sg_dma_len(sg) = sg->length;
 			sg_dma_mark_bus_address(sg);
 			continue;
 		default:

kernel/dma/pool.c

@@ -93,7 +93,7 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 			page = dma_alloc_from_contiguous(NULL, 1 << order,
 							 order, false);
 		if (!page)
-			page = alloc_pages(gfp, order);
+			page = alloc_pages(gfp | __GFP_NOWARN, order);
 	} while (!page && order-- > 0);
 	if (!page)
 		goto out;
@@ -268,15 +268,20 @@ struct page *dma_alloc_from_pool(struct device *dev, size_t size,
 {
 	struct gen_pool *pool = NULL;
 	struct page *page;
+	bool pool_found = false;
 
 	while ((pool = dma_guess_pool(pool, gfp))) {
+		pool_found = true;
 		page = __dma_alloc_from_pool(dev, size, pool, cpu_addr,
 					     phys_addr_ok);
 		if (page)
 			return page;
 	}
 
-	WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev));
+	if (pool_found)
+		WARN(!(gfp & __GFP_NOWARN), "DMA pool exhausted for %s\n", dev_name(dev));
+	else
+		WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev));
 	return NULL;
 }
 

lib/sg_split.c

@@ -88,8 +88,6 @@ static void sg_split_phys(struct sg_splitter *splitters, const int nb_splits)
 			if (!j) {
 				out_sg->offset += split->skip_sg0;
 				out_sg->length -= split->skip_sg0;
-			} else {
-				out_sg->offset = 0;
 			}
 			sg_dma_address(out_sg) = 0;
 			sg_dma_len(out_sg) = 0;

tools/testing/selftests/iommu/iommufd.c

@@ -2638,6 +2638,8 @@ TEST_F(vfio_compat_mock_domain, map)
 	ASSERT_EQ(0, ioctl(self->fd, VFIO_IOMMU_MAP_DMA, &map_cmd));
 	ASSERT_EQ(0, ioctl(self->fd, VFIO_IOMMU_UNMAP_DMA, &unmap_cmd));
 	ASSERT_EQ(BUFFER_SIZE, unmap_cmd.size);
+	/* Unmap of empty is success */
+	ASSERT_EQ(0, ioctl(self->fd, VFIO_IOMMU_UNMAP_DMA, &unmap_cmd));
 
 	/* UNMAP_FLAG_ALL requires 0 iova/size */
 	ASSERT_EQ(0, ioctl(self->fd, VFIO_IOMMU_MAP_DMA, &map_cmd));