Merge tag 'iommu-updates-v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - Identity domain support for virtio-iommu

 - Move flush queue code into iommu-dma

 - Some fixes for AMD IOMMU suspend/resume support when x2apic is used

 - Arm SMMU Updates from Will Deacon:
      - Revert evtq and priq back to their former sizes
      - Return early on short-descriptor page-table allocation failure
      - Fix page fault reporting for Adreno GPU on SMMUv2
      - Make SMMUv3 MMU notifier ops 'const'
      - Numerous new compatible strings for Qualcomm SMMUv2 implementations

 - Various smaller fixes and cleanups

* tag 'iommu-updates-v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (38 commits)
  iommu/iova: Temporarily include dma-mapping.h from iova.h
  iommu: Move flush queue data into iommu_dma_cookie
  iommu/iova: Move flush queue code to iommu-dma
  iommu/iova: Consolidate flush queue code
  iommu/vt-d: Use put_pages_list
  iommu/amd: Use put_pages_list
  iommu/amd: Simplify pagetable freeing
  iommu/iova: Squash flush_cb abstraction
  iommu/iova: Squash entry_dtor abstraction
  iommu/iova: Fix race between FQ timeout and teardown
  iommu/amd: Fix typo in *glues … together* in comment
  iommu/vt-d: Remove unused dma_to_mm_pfn function
  iommu/vt-d: Drop duplicate check in dma_pte_free_pagetable()
  iommu/vt-d: Use bitmap_zalloc() when applicable
  iommu/amd: Remove useless irq affinity notifier
  iommu/amd: X2apic mode: mask/unmask interrupts on suspend/resume
  iommu/amd: X2apic mode: setup the INTX registers on mask/unmask
  iommu/amd: X2apic mode: re-enable after resume
  iommu/amd: Restore GA log/tail pointer on host resume
  iommu/iova: Move fast alloc size roundup into alloc_iova_fast()
  ...

20 files changed, 493 insertions, 570 deletions

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index f66a3effba73..da5381c8ee11 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -38,10 +38,12 @@ properties:
               - qcom,sc7280-smmu-500
               - qcom,sc8180x-smmu-500
               - qcom,sdm845-smmu-500
+              - qcom,sdx55-smmu-500
               - qcom,sm6350-smmu-500
               - qcom,sm8150-smmu-500
               - qcom,sm8250-smmu-500
               - qcom,sm8350-smmu-500
+              - qcom,sm8450-smmu-500
           - const: arm,mmu-500
       - description: Qcom Adreno GPUs implementing "arm,smmu-v2"
         items:
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 867535eb0ce9..ffc89c4fb120 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -645,8 +645,6 @@ struct amd_iommu {
 	/* DebugFS Info */
 	struct dentry *debugfs;
 #endif
-	/* IRQ notifier for IntCapXT interrupt */
-	struct irq_affinity_notify intcapxt_notify;
 };
 
 static inline struct amd_iommu *dev_to_amd_iommu(struct device *dev)
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 1eacd43cb436..dc338acf3338 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -806,16 +806,27 @@ static int iommu_ga_log_enable(struct amd_iommu *iommu)
 {
 #ifdef CONFIG_IRQ_REMAP
 	u32 status, i;
+	u64 entry;
 
 	if (!iommu->ga_log)
 		return -EINVAL;
 
-	status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
-
 	/* Check if already running */
-	if (status & (MMIO_STATUS_GALOG_RUN_MASK))
+	status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+	if (WARN_ON(status & (MMIO_STATUS_GALOG_RUN_MASK)))
 		return 0;
 
+	entry = iommu_virt_to_phys(iommu->ga_log) | GA_LOG_SIZE_512;
+	memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_BASE_OFFSET,
+		    &entry, sizeof(entry));
+	entry = (iommu_virt_to_phys(iommu->ga_log_tail) &
+		 (BIT_ULL(52)-1)) & ~7ULL;
+	memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_TAIL_OFFSET,
+		    &entry, sizeof(entry));
+	writel(0x00, iommu->mmio_base + MMIO_GA_HEAD_OFFSET);
+	writel(0x00, iommu->mmio_base + MMIO_GA_TAIL_OFFSET);
+
+
 	iommu_feature_enable(iommu, CONTROL_GAINT_EN);
 	iommu_feature_enable(iommu, CONTROL_GALOG_EN);
 
@@ -825,7 +836,7 @@ static int iommu_ga_log_enable(struct amd_iommu *iommu)
 			break;
 	}
 
-	if (i >= LOOP_TIMEOUT)
+	if (WARN_ON(i >= LOOP_TIMEOUT))
 		return -EINVAL;
 #endif /* CONFIG_IRQ_REMAP */
 	return 0;
@@ -834,8 +845,6 @@ static int iommu_ga_log_enable(struct amd_iommu *iommu)
 static int iommu_init_ga_log(struct amd_iommu *iommu)
 {
 #ifdef CONFIG_IRQ_REMAP
-	u64 entry;
-
 	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
 		return 0;
 
@@ -849,16 +858,6 @@ static int iommu_init_ga_log(struct amd_iommu *iommu)
 	if (!iommu->ga_log_tail)
 		goto err_out;
 
-	entry = iommu_virt_to_phys(iommu->ga_log) | GA_LOG_SIZE_512;
-	memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_BASE_OFFSET,
-		    &entry, sizeof(entry));
-	entry = (iommu_virt_to_phys(iommu->ga_log_tail) &
-		 (BIT_ULL(52)-1)) & ~7ULL;
-	memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_TAIL_OFFSET,
-		    &entry, sizeof(entry));
-	writel(0x00, iommu->mmio_base + MMIO_GA_HEAD_OFFSET);
-	writel(0x00, iommu->mmio_base + MMIO_GA_TAIL_OFFSET);
-
 	return 0;
 err_out:
 	free_ga_log(iommu);
@@ -1523,7 +1522,7 @@ static void amd_iommu_ats_write_check_workaround(struct amd_iommu *iommu)
 }
 
 /*
- * This function clues the initialization function for one IOMMU
+ * This function glues the initialization function for one IOMMU
  * together and also allocates the command buffer and programs the
  * hardware. It does NOT enable the IOMMU. This is done afterwards.
  */
@@ -2016,48 +2015,18 @@ union intcapxt {
 	};
 } __attribute__ ((packed));
 
-/*
- * There isn't really any need to mask/unmask at the irqchip level because
- * the 64-bit INTCAPXT registers can be updated atomically without tearing
- * when the affinity is being updated.
- */
-static void intcapxt_unmask_irq(struct irq_data *data)
-{
-}
-
-static void intcapxt_mask_irq(struct irq_data *data)
-{
-}
 
 static struct irq_chip intcapxt_controller;
 
 static int intcapxt_irqdomain_activate(struct irq_domain *domain,
 				       struct irq_data *irqd, bool reserve)
 {
-	struct amd_iommu *iommu = irqd->chip_data;
-	struct irq_cfg *cfg = irqd_cfg(irqd);
-	union intcapxt xt;
-
-	xt.capxt = 0ULL;
-	xt.dest_mode_logical = apic->dest_mode_logical;
-	xt.vector = cfg->vector;
-	xt.destid_0_23 = cfg->dest_apicid & GENMASK(23, 0);
-	xt.destid_24_31 = cfg->dest_apicid >> 24;
-
-	/**
-	 * Current IOMMU implemtation uses the same IRQ for all
-	 * 3 IOMMU interrupts.
-	 */
-	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET);
-	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET);
-	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET);
 	return 0;
 }
 
 static void intcapxt_irqdomain_deactivate(struct irq_domain *domain,
 					  struct irq_data *irqd)
 {
-	intcapxt_mask_irq(irqd);
 }
 
 
@@ -2091,6 +2060,38 @@ static void intcapxt_irqdomain_free(struct irq_domain *domain, unsigned int virq
 	irq_domain_free_irqs_top(domain, virq, nr_irqs);
 }
 
+
+static void intcapxt_unmask_irq(struct irq_data *irqd)
+{
+	struct amd_iommu *iommu = irqd->chip_data;
+	struct irq_cfg *cfg = irqd_cfg(irqd);
+	union intcapxt xt;
+
+	xt.capxt = 0ULL;
+	xt.dest_mode_logical = apic->dest_mode_logical;
+	xt.vector = cfg->vector;
+	xt.destid_0_23 = cfg->dest_apicid & GENMASK(23, 0);
+	xt.destid_24_31 = cfg->dest_apicid >> 24;
+
+	/**
+	 * Current IOMMU implementation uses the same IRQ for all
+	 * 3 IOMMU interrupts.
+	 */
+	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET);
+	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET);
+	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET);
+}
+
+static void intcapxt_mask_irq(struct irq_data *irqd)
+{
+	struct amd_iommu *iommu = irqd->chip_data;
+
+	writeq(0, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET);
+	writeq(0, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET);
+	writeq(0, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET);
+}
+
+
 static int intcapxt_set_affinity(struct irq_data *irqd,
 				 const struct cpumask *mask, bool force)
 {
@@ -2100,8 +2101,12 @@ static int intcapxt_set_affinity(struct irq_data *irqd,
 	ret = parent->chip->irq_set_affinity(parent, mask, force);
 	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
 		return ret;
+	return 0;
+}
 
-	return intcapxt_irqdomain_activate(irqd->domain, irqd, false);
+static int intcapxt_set_wake(struct irq_data *irqd, unsigned int on)
+{
+	return on ? -EOPNOTSUPP : 0;
 }
 
 static struct irq_chip intcapxt_controller = {
@@ -2111,7 +2116,8 @@ static struct irq_chip intcapxt_controller = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_set_affinity       = intcapxt_set_affinity,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
+	.irq_set_wake		= intcapxt_set_wake,
+	.flags			= IRQCHIP_MASK_ON_SUSPEND,
 };
 
 static const struct irq_domain_ops intcapxt_domain_ops = {
@@ -2173,7 +2179,6 @@ static int iommu_setup_intcapxt(struct amd_iommu *iommu)
 		return ret;
 	}
 
-	iommu_feature_enable(iommu, CONTROL_INTCAPXT_EN);
 	return 0;
 }
 
@@ -2196,6 +2201,10 @@ static int iommu_init_irq(struct amd_iommu *iommu)
 
 	iommu->int_enabled = true;
 enable_faults:
+
+	if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE)
+		iommu_feature_enable(iommu, CONTROL_INTCAPXT_EN);
+
 	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
 
 	if (iommu->ppr_log != NULL)
diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
index 182c93a43efd..b1bf4125b0f7 100644
--- a/drivers/iommu/amd/io_pgtable.c
+++ b/drivers/iommu/amd/io_pgtable.c
@@ -74,87 +74,61 @@ static u64 *first_pte_l7(u64 *pte, unsigned long *page_size,
  *
  ****************************************************************************/
 
-static void free_page_list(struct page *freelist)
+static void free_pt_page(u64 *pt, struct list_head *freelist)
 {
-	while (freelist != NULL) {
-		unsigned long p = (unsigned long)page_address(freelist);
+	struct page *p = virt_to_page(pt);
 
-		freelist = freelist->freelist;
-		free_page(p);
-	}
+	list_add_tail(&p->lru, freelist);
 }
 
-static struct page *free_pt_page(unsigned long pt, struct page *freelist)
+static void free_pt_lvl(u64 *pt, struct list_head *freelist, int lvl)
 {
-	struct page *p = virt_to_page((void *)pt);
+	u64 *p;
+	int i;
 
-	p->freelist = freelist;
+	for (i = 0; i < 512; ++i) {
+		/* PTE present? */
+		if (!IOMMU_PTE_PRESENT(pt[i]))
+			continue;
 
-	return p;
-}
+		/* Large PTE? */
+		if (PM_PTE_LEVEL(pt[i]) == 0 ||
+		    PM_PTE_LEVEL(pt[i]) == 7)
+			continue;
 
-#define DEFINE_FREE_PT_FN(LVL, FN)						\
-static struct page *free_pt_##LVL (unsigned long __pt, struct page *freelist)	\
-{										\
-	unsigned long p;							\
-	u64 *pt;								\
-	int i;									\
-										\
-	pt = (u64 *)__pt;							\
-										\
-	for (i = 0; i < 512; ++i) {						\
-		/* PTE present? */						\
-		if (!IOMMU_PTE_PRESENT(pt[i]))					\
-			continue;						\
-										\
-		/* Large PTE? */						\
-		if (PM_PTE_LEVEL(pt[i]) == 0 ||					\
-		    PM_PTE_LEVEL(pt[i]) == 7)					\
-			continue;						\
-										\
-		p = (unsigned long)IOMMU_PTE_PAGE(pt[i]);			\
-		freelist = FN(p, freelist);					\
-	}									\
-										\
-	return free_pt_page((unsigned long)pt, freelist);			\
-}
+		/*
+		 * Free the next level. No need to look at l1 tables here since
+		 * they can only contain leaf PTEs; just free them directly.
+		 */
+		p = IOMMU_PTE_PAGE(pt[i]);
+		if (lvl > 2)
+			free_pt_lvl(p, freelist, lvl - 1);
+		else
+			free_pt_page(p, freelist);
+	}
 
-DEFINE_FREE_PT_FN(l2, free_pt_page)
-DEFINE_FREE_PT_FN(l3, free_pt_l2)
-DEFINE_FREE_PT_FN(l4, free_pt_l3)
-DEFINE_FREE_PT_FN(l5, free_pt_l4)
-DEFINE_FREE_PT_FN(l6, free_pt_l5)
+	free_pt_page(pt, freelist);
+}
 
-static struct page *free_sub_pt(unsigned long root, int mode,
-				struct page *freelist)
+static void free_sub_pt(u64 *root, int mode, struct list_head *freelist)
 {
 	switch (mode) {
 	case PAGE_MODE_NONE:
 	case PAGE_MODE_7_LEVEL:
 		break;
 	case PAGE_MODE_1_LEVEL:
-		freelist = free_pt_page(root, freelist);
+		free_pt_page(root, freelist);
 		break;
 	case PAGE_MODE_2_LEVEL:
-		freelist = free_pt_l2(root, freelist);
-		break;
 	case PAGE_MODE_3_LEVEL:
-		freelist = free_pt_l3(root, freelist);
-		break;
 	case PAGE_MODE_4_LEVEL:
-		freelist = free_pt_l4(root, freelist);
-		break;
 	case PAGE_MODE_5_LEVEL:
-		freelist = free_pt_l5(root, freelist);
-		break;
 	case PAGE_MODE_6_LEVEL:
-		freelist = free_pt_l6(root, freelist);
+		free_pt_lvl(root, freelist, mode);
 		break;
 	default:
 		BUG();
 	}
-
-	return freelist;
 }
 
 void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
@@ -362,9 +336,9 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable,
 	return pte;
 }
 
-static struct page *free_clear_pte(u64 *pte, u64 pteval, struct page *freelist)
+static void free_clear_pte(u64 *pte, u64 pteval, struct list_head *freelist)
 {
-	unsigned long pt;
+	u64 *pt;
 	int mode;
 
 	while (cmpxchg64(pte, pteval, 0) != pteval) {
@@ -373,12 +347,12 @@ static struct page *free_clear_pte(u64 *pte, u64 pteval, struct page *freelist)
 	}
 
 	if (!IOMMU_PTE_PRESENT(pteval))
-		return freelist;
+		return;
 
-	pt   = (unsigned long)IOMMU_PTE_PAGE(pteval);
+	pt   = IOMMU_PTE_PAGE(pteval);
 	mode = IOMMU_PTE_MODE(pteval);
 
-	return free_sub_pt(pt, mode, freelist);
+	free_sub_pt(pt, mode, freelist);
 }
 
 /*
@@ -392,7 +366,7 @@ static int iommu_v1_map_page(struct io_pgtable_ops *ops, unsigned long iova,
 			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct protection_domain *dom = io_pgtable_ops_to_domain(ops);
-	struct page *freelist = NULL;
+	LIST_HEAD(freelist);
 	bool updated = false;
 	u64 __pte, *pte;
 	int ret, i, count;
@@ -412,9 +386,9 @@ static int iommu_v1_map_page(struct io_pgtable_ops *ops, unsigned long iova,
 		goto out;
 
 	for (i = 0; i < count; ++i)
-		freelist = free_clear_pte(&pte[i], pte[i], freelist);
+		free_clear_pte(&pte[i], pte[i], &freelist);
 
-	if (freelist != NULL)
+	if (!list_empty(&freelist))
 		updated = true;
 
 	if (count > 1) {
@@ -449,7 +423,7 @@ out:
 	}
 
 	/* Everything flushed out, free pages now */
-	free_page_list(freelist);
+	put_pages_list(&freelist);
 
 	return ret;
 }
@@ -511,8 +485,7 @@ static void v1_free_pgtable(struct io_pgtable *iop)
 {
 	struct amd_io_pgtable *pgtable = container_of(iop, struct amd_io_pgtable, iop);
 	struct protection_domain *dom;
-	struct page *freelist = NULL;
-	unsigned long root;
+	LIST_HEAD(freelist);
 
 	if (pgtable->mode == PAGE_MODE_NONE)
 		return;
@@ -529,10 +502,9 @@ static void v1_free_pgtable(struct io_pgtable *iop)
 	BUG_ON(pgtable->mode < PAGE_MODE_NONE ||
 	       pgtable->mode > PAGE_MODE_6_LEVEL);
 
-	root = (unsigned long)pgtable->root;
-	freelist = free_sub_pt(root, pgtable->mode, freelist);
+	free_sub_pt(pgtable->root, pgtable->mode, &freelist);
 
-	free_page_list(freelist);
+	put_pages_list(&freelist);
 }
 
 static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index ee66d1f4cb81..a737ba5f727e 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -220,7 +220,7 @@ static void arm_smmu_mmu_notifier_free(struct mmu_notifier *mn)
 	kfree(mn_to_smmu(mn));
 }
 
-static struct mmu_notifier_ops arm_smmu_mmu_notifier_ops = {
+static const struct mmu_notifier_ops arm_smmu_mmu_notifier_ops = {
 	.invalidate_range	= arm_smmu_mm_invalidate_range,
 	.release		= arm_smmu_mm_release,
 	.free_notifier		= arm_smmu_mmu_notifier_free,
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 4cb136f07914..cd48590ada30 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -184,7 +184,6 @@
 #else
 #define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_ORDER - 1)
 #endif
-#define Q_MIN_SZ_SHIFT			(PAGE_SHIFT)
 
 /*
  * Stream table.
@@ -374,7 +373,7 @@
 /* Event queue */
 #define EVTQ_ENT_SZ_SHIFT		5
 #define EVTQ_ENT_DWORDS			((1 << EVTQ_ENT_SZ_SHIFT) >> 3)
-#define EVTQ_MAX_SZ_SHIFT		(Q_MIN_SZ_SHIFT - EVTQ_ENT_SZ_SHIFT)
+#define EVTQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - EVTQ_ENT_SZ_SHIFT)
 
 #define EVTQ_0_ID			GENMASK_ULL(7, 0)
 
@@ -400,7 +399,7 @@
 /* PRI queue */
 #define PRIQ_ENT_SZ_SHIFT		4
 #define PRIQ_ENT_DWORDS			((1 << PRIQ_ENT_SZ_SHIFT) >> 3)
-#define PRIQ_MAX_SZ_SHIFT		(Q_MIN_SZ_SHIFT - PRIQ_ENT_SZ_SHIFT)
+#define PRIQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - PRIQ_ENT_SZ_SHIFT)
 
 #define PRIQ_0_SID			GENMASK_ULL(31, 0)
 #define PRIQ_0_SSID			GENMASK_ULL(51, 32)
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index ca736b065dd0..ba6298c7140e 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -51,7 +51,7 @@ static void qcom_adreno_smmu_get_fault_info(const void *cookie,
 	info->fsynr1 = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_FSYNR1);
 	info->far = arm_smmu_cb_readq(smmu, cfg->cbndx, ARM_SMMU_CB_FAR);
 	info->cbfrsynra = arm_smmu_gr1_read(smmu, ARM_SMMU_GR1_CBFRSYNRA(cfg->cbndx));
-	info->ttbr0 = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_TTBR0);
+	info->ttbr0 = arm_smmu_cb_readq(smmu, cfg->cbndx, ARM_SMMU_CB_TTBR0);
 	info->contextidr = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_CONTEXTIDR);
 }
 
@@ -415,6 +415,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
 	{ .compatible = "qcom,sm8150-smmu-500" },
 	{ .compatible = "qcom,sm8250-smmu-500" },
 	{ .compatible = "qcom,sm8350-smmu-500" },
+	{ .compatible = "qcom,sm8450-smmu-500" },
 	{ }
 };
 
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index b42e38a0dbe2..d85d54f2b549 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -9,9 +9,12 @@
  */
 
 #include <linux/acpi_iort.h>
+#include <linux/atomic.h>
+#include <linux/crash_dump.h>
 #include <linux/device.h>
-#include <linux/dma-map-ops.h>
+#include <linux/dma-direct.h>
 #include <linux/dma-iommu.h>
+#include <linux/dma-map-ops.h>
 #include <linux/gfp.h>
 #include <linux/huge_mm.h>
 #include <linux/iommu.h>
@@ -20,11 +23,10 @@
 #include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
-#include <linux/swiotlb.h>
 #include <linux/scatterlist.h>
+#include <linux/spinlock.h>
+#include <linux/swiotlb.h>
 #include <linux/vmalloc.h>
-#include <linux/crash_dump.h>
-#include <linux/dma-direct.h>
 
 struct iommu_dma_msi_page {
 	struct list_head	list;
@@ -41,7 +43,19 @@ struct iommu_dma_cookie {
 	enum iommu_dma_cookie_type	type;
 	union {
 		/* Full allocator for IOMMU_DMA_IOVA_COOKIE */
-		struct iova_domain	iovad;
+		struct {
+			struct iova_domain	iovad;
+
+			struct iova_fq __percpu *fq;	/* Flush queue */
+			/* Number of TLB flushes that have been started */
+			atomic64_t		fq_flush_start_cnt;
+			/* Number of TLB flushes that have been finished */
+			atomic64_t		fq_flush_finish_cnt;
+			/* Timer to regularily empty the flush queues */
+			struct timer_list	fq_timer;
+			/* 1 when timer is active, 0 when not */
+			atomic_t		fq_timer_on;
+		};
 		/* Trivial linear page allocator for IOMMU_DMA_MSI_COOKIE */
 		dma_addr_t		msi_iova;
 	};
@@ -64,16 +78,203 @@ static int __init iommu_dma_forcedac_setup(char *str)
 }
 early_param("iommu.forcedac", iommu_dma_forcedac_setup);
 
-static void iommu_dma_entry_dtor(unsigned long data)
+/* Number of entries per flush queue */
+#define IOVA_FQ_SIZE	256
+
+/* Timeout (in ms) after which entries are flushed from the queue */
+#define IOVA_FQ_TIMEOUT	10
+
+/* Flush queue entry for deferred flushing */
+struct iova_fq_entry {
+	unsigned long iova_pfn;
+	unsigned long pages;
+	struct list_head freelist;
+	u64 counter; /* Flush counter when this entry was added */
+};
+
+/* Per-CPU flush queue structure */
+struct iova_fq {
+	struct iova_fq_entry entries[IOVA_FQ_SIZE];
+	unsigned int head, tail;
+	spinlock_t lock;
+};
+
+#define fq_ring_for_each(i, fq) \
+	for ((i) = (fq)->head; (i) != (fq)->tail; (i) = ((i) + 1) % IOVA_FQ_SIZE)
+
+static inline bool fq_full(struct iova_fq *fq)
+{
+	assert_spin_locked(&fq->lock);
+	return (((fq->tail + 1) % IOVA_FQ_SIZE) == fq->head);
+}
+
+static inline unsigned int fq_ring_add(struct iova_fq *fq)
+{
+	unsigned int idx = fq->tail;
+
+	assert_spin_locked(&fq->lock);
+
+	fq->tail = (idx + 1) % IOVA_FQ_SIZE;
+
+	return idx;
+}
+
+static void fq_ring_free(struct iommu_dma_cookie *cookie, struct iova_fq *fq)
+{
+	u64 counter = atomic64_read(&cookie->fq_flush_finish_cnt);
+	unsigned int idx;
+
+	assert_spin_locked(&fq->lock);
+
+	fq_ring_for_each(idx, fq) {
+
+		if (fq->entries[idx].counter >= counter)
+			break;
+
+		put_pages_list(&fq->entries[idx].freelist);
+		free_iova_fast(&cookie->iovad,
+			       fq->entries[idx].iova_pfn,
+			       fq->entries[idx].pages);
+
+		fq->head = (fq->head + 1) % IOVA_FQ_SIZE;
+	}
+}
+
+static void fq_flush_iotlb(struct iommu_dma_cookie *cookie)
 {
-	struct page *freelist = (struct page *)data;
+	atomic64_inc(&cookie->fq_flush_start_cnt);
+	cookie->fq_domain->ops->flush_iotlb_all(cookie->fq_domain);
+	atomic64_inc(&cookie->fq_flush_finish_cnt);
+}
+
+static void fq_flush_timeout(struct timer_list *t)
+{
+	struct iommu_dma_cookie *cookie = from_timer(cookie, t, fq_timer);
+	int cpu;
+
+	atomic_set(&cookie->fq_timer_on, 0);
+	fq_flush_iotlb(cookie);
+
+	for_each_possible_cpu(cpu) {
+		unsigned long flags;
+		struct iova_fq *fq;
+
+		fq = per_cpu_ptr(cookie->fq, cpu);
+		spin_lock_irqsave(&fq->lock, flags);
+		fq_ring_free(cookie, fq);
+		spin_unlock_irqrestore(&fq->lock, flags);
+	}
+}
+
+static void queue_iova(struct iommu_dma_cookie *cookie,
+		unsigned long pfn, unsigned long pages,
+		struct list_head *freelist)
+{
+	struct iova_fq *fq;
+	unsigned long flags;
+	unsigned int idx;
+
+	/*
+	 * Order against the IOMMU driver's pagetable update from unmapping
+	 * @pte, to guarantee that fq_flush_iotlb() observes that if called
+	 * from a different CPU before we release the lock below. Full barrier
+	 * so it also pairs with iommu_dma_init_fq() to avoid seeing partially
+	 * written fq state here.
+	 */
+	smp_mb();
 
-	while (freelist) {
-		unsigned long p = (unsigned long)page_address(freelist);
+	fq = raw_cpu_ptr(cookie->fq);
+	spin_lock_irqsave(&fq->lock, flags);
+
+	/*
+	 * First remove all entries from the flush queue that have already been
+	 * flushed out on another CPU. This makes the fq_full() check below less
+	 * likely to be true.
+	 */
+	fq_ring_free(cookie, fq);
 
-		freelist = freelist->freelist;
-		free_page(p);
+	if (fq_full(fq)) {
+		fq_flush_iotlb(cookie);
+		fq_ring_free(cookie, fq);
 	}
+
+	idx = fq_ring_add(fq);
+
+	fq->entries[idx].iova_pfn = pfn;
+	fq->entries[idx].pages    = pages;
+	fq->entries[idx].counter  = atomic64_read(&cookie->fq_flush_start_cnt);
+	list_splice(freelist, &fq->entries[idx].freelist);
+
+	spin_unlock_irqrestore(&fq->lock, flags);
+
+	/* Avoid false sharing as much as possible. */
+	if (!atomic_read(&cookie->fq_timer_on) &&
+	    !atomic_xchg(&cookie->fq_timer_on, 1))
+		mod_timer(&cookie->fq_timer,
+			  jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT));
+}
+
+static void iommu_dma_free_fq(struct iommu_dma_cookie *cookie)
+{
+	int cpu, idx;
+
+	if (!cookie->fq)
+		return;
+
+	del_timer_sync(&cookie->fq_timer);
+	/* The IOVAs will be torn down separately, so just free our queued pages */
+	for_each_possible_cpu(cpu) {
+		struct iova_fq *fq = per_cpu_ptr(cookie->fq, cpu);
+
+		fq_ring_for_each(idx, fq)
+			put_pages_list(&fq->entries[idx].freelist);
+	}
+
+	free_percpu(cookie->fq);
+}
+
+/* sysfs updates are serialised by the mutex of the group owning @domain */
+int iommu_dma_init_fq(struct iommu_domain *domain)
+{
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_fq __percpu *queue;
+	int i, cpu;
+
+	if (cookie->fq_domain)
+		return 0;
+
+	atomic64_set(&cookie->fq_flush_start_cnt,  0);
+	atomic64_set(&cookie->fq_flush_finish_cnt, 0);
+
+	queue = alloc_percpu(struct iova_fq);
+	if (!queue) {
+		pr_warn("iova flush queue initialization failed\n");
+		return -ENOMEM;
+	}
+
+	for_each_possible_cpu(cpu) {
+		struct iova_fq *fq = per_cpu_ptr(queue, cpu);
+
+		fq->head = 0;
+		fq->tail = 0;
+
+		spin_lock_init(&fq->lock);
+
+		for (i = 0; i < IOVA_FQ_SIZE; i++)
+			INIT_LIST_HEAD(&fq->entries[i].freelist);
+	}
+
+	cookie->fq = queue;
+
+	timer_setup(&cookie->fq_timer, fq_flush_timeout, 0);
+	atomic_set(&cookie->fq_timer_on, 0);
+	/*
+	 * Prevent incomplete fq state being observable. Pairs with path from
+	 * __iommu_dma_unmap() through iommu_dma_free_iova() to queue_iova()
+	 */
+	smp_wmb();
+	WRITE_ONCE(cookie->fq_domain, domain);
+	return 0;
 }
 
 static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie)
@@ -156,8 +357,10 @@ void iommu_put_dma_cookie(struct iommu_domain *domain)
 	if (!cookie)
 		return;
 
-	if (cookie->type == IOMMU_DMA_IOVA_COOKIE && cookie->iovad.granule)
+	if (cookie->type == IOMMU_DMA_IOVA_COOKIE && cookie->iovad.granule) {
+		iommu_dma_free_fq(cookie);
 		put_iova_domain(&cookie->iovad);
+	}
 
 	list_for_each_entry_safe(msi, tmp, &cookie->msi_page_list, list) {
 		list_del(&msi->list);
@@ -294,17 +497,6 @@ static int iova_reserve_iommu_regions(struct device *dev,
 	return ret;
 }
 
-static void iommu_dma_flush_iotlb_all(struct iova_domain *iovad)
-{
-	struct iommu_dma_cookie *cookie;
-	struct iommu_domain *domain;
-
-	cookie = container_of(iovad, struct iommu_dma_cookie, iovad);
-	domain = cookie->fq_domain;
-
-	domain->ops->flush_iotlb_all(domain);
-}
-
 static bool dev_is_untrusted(struct device *dev)
 {
 	return dev_is_pci(dev) && to_pci_dev(dev)->untrusted;
@@ -315,30 +507,6 @@ static bool dev_use_swiotlb(struct device *dev)
 	return IS_ENABLED(CONFIG_SWIOTLB) && dev_is_untrusted(dev);
 }
 
-/* sysfs updates are serialised by the mutex of the group owning @domain */
-int iommu_dma_init_fq(struct iommu_domain *domain)
-{
-	struct iommu_dma_cookie *cookie = domain->iova_cookie;
-	int ret;
-
-	if (cookie->fq_domain)
-		return 0;
-
-	ret = init_iova_flush_queue(&cookie->iovad, iommu_dma_flush_iotlb_all,
-				    iommu_dma_entry_dtor);
-	if (ret) {
-		pr_warn("iova flush queue initialization failed\n");
-		return ret;
-	}
-	/*
-	 * Prevent incomplete iovad->fq being observable. Pairs with path from
-	 * __iommu_dma_unmap() through iommu_dma_free_iova() to queue_iova()
-	 */
-	smp_wmb();
-	WRITE_ONCE(cookie->fq_domain, domain);
-	return 0;
-}
-
 /**
  * iommu_dma_init_domain - Initialise a DMA mapping domain
  * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie()
@@ -442,14 +610,6 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 
 	shift = iova_shift(iovad);
 	iova_len = size >> shift;
-	/*
-	 * Freeing non-power-of-two-sized allocations back into the IOVA caches
-	 * will come back to bite us badly, so we have to waste a bit of space
-	 * rounding up anything cacheable to make sure that can't happen. The
-	 * order of the unadjusted size will still match upon freeing.
-	 */
-	if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
-		iova_len = roundup_pow_of_two(iova_len);
 
 	dma_limit = min_not_zero(dma_limit, dev->bus_dma_limit);
 
@@ -477,9 +637,9 @@ static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
 	if (cookie->type == IOMMU_DMA_MSI_COOKIE)
 		cookie->msi_iova -= size;
 	else if (gather && gather->queued)
-		queue_iova(iovad, iova_pfn(iovad, iova),
+		queue_iova(cookie, iova_pfn(iovad, iova),
 				size >> iova_shift(iovad),
-				(unsigned long)gather->freelist);
+				&gather->freelist);
 	else
 		free_iova_fast(iovad, iova_pfn(iovad, iova),
 				size >> iova_shift(iovad));
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index b6a8f3282411..92fea3fbbb11 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -133,11 +133,6 @@ static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
 
 /* VT-d pages must always be _smaller_ than MM pages. Otherwise things
    are never going to wor