Merge tag 'arm-smmu-updates' of...

Merge tag 'arm-smmu-updates' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into arm/smmu

Arm SMMU updates for 5.12

- Support for MT8192 IOMMU from Mediatek

- Arm v7s io-pgtable extensions for MT8192

- Removal of TLBI_ON_MAP quirk

- New Qualcomm compatible strings

- Allow SVA without hardware broadcast TLB maintenance on SMMUv3

- Virtualization Host Extension support for SMMUv3 (SVA)

- Allow SMMUv3 PMU (perf) driver to be built independently from IOMMU

- Misc cleanups

Documentation/devicetree/bindings/iommu/arm,smmu.yaml

@@ -34,9 +34,11 @@ properties:
         items:
           - enum:
               - qcom,sc7180-smmu-500
+              - qcom,sc8180x-smmu-500
               - qcom,sdm845-smmu-500
               - qcom,sm8150-smmu-500
               - qcom,sm8250-smmu-500
+              - qcom,sm8350-smmu-500
           - const: arm,mmu-500
       - description: Qcom Adreno GPUs implementing "arm,smmu-v2"
         items:

Documentation/devicetree/bindings/iommu/mediatek,iommu.txt

-* Mediatek IOMMU Architecture Implementation
-
-  Some Mediatek SOCs contain a Multimedia Memory Management Unit (M4U), and
-this M4U have two generations of HW architecture. Generation one uses flat
-pagetable, and only supports 4K size page mapping. Generation two uses the
-ARM Short-Descriptor translation table format for address translation.
-
-  About the M4U Hardware Block Diagram, please check below:
-
-              EMI (External Memory Interface)
-               |
-              m4u (Multimedia Memory Management Unit)
-               |
-          +--------+
-          |        |
-      gals0-rx   gals1-rx    (Global Async Local Sync rx)
-          |        |
-          |        |
-      gals0-tx   gals1-tx    (Global Async Local Sync tx)
-          |        |          Some SoCs may have GALS.
-          +--------+
-               |
-           SMI Common(Smart Multimedia Interface Common)
-               |
-       +----------------+-------
-       |                |
-       |             gals-rx        There may be GALS in some larbs.
-       |                |
-       |                |
-       |             gals-tx
-       |                |
-   SMI larb0        SMI larb1   ... SoCs have several SMI local arbiter(larb).
-   (display)         (vdec)
-       |                |
-       |                |
- +-----+-----+     +----+----+
- |     |     |     |    |    |
- |     |     |...  |    |    |  ... There are different ports in each larb.
- |     |     |     |    |    |
-OVL0 RDMA0 WDMA0  MC   PP   VLD
-
-  As above, The Multimedia HW will go through SMI and M4U while it
-access EMI. SMI is a bridge between m4u and the Multimedia HW. It contain
-smi local arbiter and smi common. It will control whether the Multimedia
-HW should go though the m4u for translation or bypass it and talk
-directly with EMI. And also SMI help control the power domain and clocks for
-each local arbiter.
-  Normally we specify a local arbiter(larb) for each multimedia HW
-like display, video decode, and camera. And there are different ports
-in each larb. Take a example, There are many ports like MC, PP, VLD in the
-video decode local arbiter, all these ports are according to the video HW.
-  In some SoCs, there may be a GALS(Global Async Local Sync) module between
-smi-common and m4u, and additional GALS module between smi-larb and
-smi-common. GALS can been seen as a "asynchronous fifo" which could help
-synchronize for the modules in different clock frequency.
-
-Required properties:
-- compatible : must be one of the following string:
-	"mediatek,mt2701-m4u" for mt2701 which uses generation one m4u HW.
-	"mediatek,mt2712-m4u" for mt2712 which uses generation two m4u HW.
-	"mediatek,mt6779-m4u" for mt6779 which uses generation two m4u HW.
-	"mediatek,mt7623-m4u", "mediatek,mt2701-m4u" for mt7623 which uses
-						     generation one m4u HW.
-	"mediatek,mt8167-m4u" for mt8167 which uses generation two m4u HW.
-	"mediatek,mt8173-m4u" for mt8173 which uses generation two m4u HW.
-	"mediatek,mt8183-m4u" for mt8183 which uses generation two m4u HW.
-- reg : m4u register base and size.
-- interrupts : the interrupt of m4u.
-- clocks : must contain one entry for each clock-names.
-- clock-names : Only 1 optional clock:
-  - "bclk": the block clock of m4u.
-  Here is the list which require this "bclk":
-  - mt2701, mt2712, mt7623 and mt8173.
-  Note that m4u use the EMI clock which always has been enabled before kernel
-  if there is no this "bclk".
-- mediatek,larbs : List of phandle to the local arbiters in the current Socs.
-	Refer to bindings/memory-controllers/mediatek,smi-larb.txt. It must sort
-	according to the local arbiter index, like larb0, larb1, larb2...
-- iommu-cells : must be 1. This is the mtk_m4u_id according to the HW.
-	Specifies the mtk_m4u_id as defined in
-	dt-binding/memory/mt2701-larb-port.h for mt2701, mt7623
-	dt-binding/memory/mt2712-larb-port.h for mt2712,
-	dt-binding/memory/mt6779-larb-port.h for mt6779,
-	dt-binding/memory/mt8167-larb-port.h for mt8167,
-	dt-binding/memory/mt8173-larb-port.h for mt8173, and
-	dt-binding/memory/mt8183-larb-port.h for mt8183.
-
-Example:
-	iommu: iommu@10205000 {
-		compatible = "mediatek,mt8173-m4u";
-		reg = <0 0x10205000 0 0x1000>;
-		interrupts = <GIC_SPI 139 IRQ_TYPE_LEVEL_LOW>;
-		clocks = <&infracfg CLK_INFRA_M4U>;
-		clock-names = "bclk";
-		mediatek,larbs = <&larb0 &larb1 &larb2 &larb3 &larb4 &larb5>;
-		#iommu-cells = <1>;
-	};
-
-Example for a client device:
-	display {
-		compatible = "mediatek,mt8173-disp";
-		iommus = <&iommu M4U_PORT_DISP_OVL0>,
-			 <&iommu M4U_PORT_DISP_RDMA0>;
-		...
-	};

Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml

+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iommu/mediatek,iommu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: MediaTek IOMMU Architecture Implementation
+
+maintainers:
+  - Yong Wu <yong.wu@mediatek.com>
+
+description: |+
+  Some MediaTek SOCs contain a Multimedia Memory Management Unit (M4U), and
+  this M4U have two generations of HW architecture. Generation one uses flat
+  pagetable, and only supports 4K size page mapping. Generation two uses the
+  ARM Short-Descriptor translation table format for address translation.
+
+  About the M4U Hardware Block Diagram, please check below:
+
+                EMI (External Memory Interface)
+                 |
+                m4u (Multimedia Memory Management Unit)
+                 |
+            +--------+
+            |        |
+        gals0-rx   gals1-rx    (Global Async Local Sync rx)
+            |        |
+            |        |
+        gals0-tx   gals1-tx    (Global Async Local Sync tx)
+            |        |          Some SoCs may have GALS.
+            +--------+
+                 |
+             SMI Common(Smart Multimedia Interface Common)
+                 |
+         +----------------+-------
+         |                |
+         |             gals-rx        There may be GALS in some larbs.
+         |                |
+         |                |
+         |             gals-tx
+         |                |
+     SMI larb0        SMI larb1   ... SoCs have several SMI local arbiter(larb).
+     (display)         (vdec)
+         |                |
+         |                |
+   +-----+-----+     +----+----+
+   |     |     |     |    |    |
+   |     |     |...  |    |    |  ... There are different ports in each larb.
+   |     |     |     |    |    |
+  OVL0 RDMA0 WDMA0  MC   PP   VLD
+
+  As above, The Multimedia HW will go through SMI and M4U while it
+  access EMI. SMI is a bridge between m4u and the Multimedia HW. It contain
+  smi local arbiter and smi common. It will control whether the Multimedia
+  HW should go though the m4u for translation or bypass it and talk
+  directly with EMI. And also SMI help control the power domain and clocks for
+  each local arbiter.
+
+  Normally we specify a local arbiter(larb) for each multimedia HW
+  like display, video decode, and camera. And there are different ports
+  in each larb. Take a example, There are many ports like MC, PP, VLD in the
+  video decode local arbiter, all these ports are according to the video HW.
+
+  In some SoCs, there may be a GALS(Global Async Local Sync) module between
+  smi-common and m4u, and additional GALS module between smi-larb and
+  smi-common. GALS can been seen as a "asynchronous fifo" which could help
+  synchronize for the modules in different clock frequency.
+
+properties:
+  compatible:
+    oneOf:
+      - enum:
+          - mediatek,mt2701-m4u  # generation one
+          - mediatek,mt2712-m4u  # generation two
+          - mediatek,mt6779-m4u  # generation two
+          - mediatek,mt8167-m4u  # generation two
+          - mediatek,mt8173-m4u  # generation two
+          - mediatek,mt8183-m4u  # generation two
+          - mediatek,mt8192-m4u  # generation two
+
+      - description: mt7623 generation one
+        items:
+          - const: mediatek,mt7623-m4u
+          - const: mediatek,mt2701-m4u
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: bclk is the block clock.
+
+  clock-names:
+    items:
+      - const: bclk
+
+  mediatek,larbs:
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    minItems: 1
+    maxItems: 32
+    description: |
+      List of phandle to the local arbiters in the current Socs.
+      Refer to bindings/memory-controllers/mediatek,smi-larb.yaml. It must sort
+      according to the local arbiter index, like larb0, larb1, larb2...
+
+  '#iommu-cells':
+    const: 1
+    description: |
+      This is the mtk_m4u_id according to the HW. Specifies the mtk_m4u_id as
+      defined in
+      dt-binding/memory/mt2701-larb-port.h for mt2701 and mt7623,
+      dt-binding/memory/mt2712-larb-port.h for mt2712,
+      dt-binding/memory/mt6779-larb-port.h for mt6779,
+      dt-binding/memory/mt8167-larb-port.h for mt8167,
+      dt-binding/memory/mt8173-larb-port.h for mt8173,
+      dt-binding/memory/mt8183-larb-port.h for mt8183,
+      dt-binding/memory/mt8192-larb-port.h for mt8192.
+
+  power-domains:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - mediatek,larbs
+  - '#iommu-cells'
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - mediatek,mt2701-m4u
+              - mediatek,mt2712-m4u
+              - mediatek,mt8173-m4u
+              - mediatek,mt8192-m4u
+
+    then:
+      required:
+        - clocks
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - mediatek,mt8192-m4u
+
+    then:
+      required:
+        - power-domains
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/mt8173-clk.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    iommu: iommu@10205000 {
+            compatible = "mediatek,mt8173-m4u";
+            reg = <0x10205000 0x1000>;
+            interrupts = <GIC_SPI 139 IRQ_TYPE_LEVEL_LOW>;
+            clocks = <&infracfg CLK_INFRA_M4U>;
+            clock-names = "bclk";
+            mediatek,larbs = <&larb0 &larb1 &larb2
+                              &larb3 &larb4 &larb5>;
+            #iommu-cells = <1>;
+    };
+
+  - |
+    #include <dt-bindings/memory/mt8173-larb-port.h>
+
+    /* Example for a client device */
+    display {
+           compatible = "mediatek,mt8173-disp";
+           iommus = <&iommu M4U_PORT_DISP_OVL0>,
+                    <&iommu M4U_PORT_DISP_RDMA0>;
+     };

MAINTAINERS

@@ -11178,6 +11178,15 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/i2c/i2c-mt65xx.txt
 F:	drivers/i2c/busses/i2c-mt65xx.c
 
+MEDIATEK IOMMU DRIVER
+M:	Yong Wu <yong.wu@mediatek.com>
+L:	iommu@lists.linux-foundation.org
+L:	linux-mediatek@lists.infradead.org (moderated for non-subscribers)
+S:	Supported
+F:	Documentation/devicetree/bindings/iommu/mediatek*
+F:	drivers/iommu/mtk-iommu*
+F:	include/dt-bindings/memory/mt*-port.h
+
 MEDIATEK JPEG DRIVER
 M:	Rick Chang <rick.chang@mediatek.com>
 M:	Bin Liu <bin.liu@mediatek.com>

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

@@ -182,9 +182,13 @@ static void arm_smmu_mm_invalidate_range(struct mmu_notifier *mn,
 					 unsigned long start, unsigned long end)
 {
 	struct arm_smmu_mmu_notifier *smmu_mn = mn_to_smmu(mn);
+	struct arm_smmu_domain *smmu_domain = smmu_mn->domain;
+	size_t size = end - start + 1;
 
-	arm_smmu_atc_inv_domain(smmu_mn->domain, mm->pasid, start,
-				end - start + 1);
+	if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_BTM))
+		arm_smmu_tlb_inv_range_asid(start, size, smmu_mn->cd->asid,
+					    PAGE_SIZE, false, smmu_domain);
+	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, start, size);
 }
 
 static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
@@ -391,7 +395,7 @@ bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
 	unsigned long reg, fld;
 	unsigned long oas;
 	unsigned long asid_bits;
-	u32 feat_mask = ARM_SMMU_FEAT_BTM | ARM_SMMU_FEAT_COHERENCY;
+	u32 feat_mask = ARM_SMMU_FEAT_COHERENCY;
 
 	if (vabits_actual == 52)
 		feat_mask |= ARM_SMMU_FEAT_VAX;

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

@@ -139,15 +139,15 @@
 #define ARM_SMMU_CMDQ_CONS		0x9c
 
 #define ARM_SMMU_EVTQ_BASE		0xa0
-#define ARM_SMMU_EVTQ_PROD		0x100a8
-#define ARM_SMMU_EVTQ_CONS		0x100ac
+#define ARM_SMMU_EVTQ_PROD		0xa8
+#define ARM_SMMU_EVTQ_CONS		0xac
 #define ARM_SMMU_EVTQ_IRQ_CFG0		0xb0
 #define ARM_SMMU_EVTQ_IRQ_CFG1		0xb8
 #define ARM_SMMU_EVTQ_IRQ_CFG2		0xbc
 
 #define ARM_SMMU_PRIQ_BASE		0xc0
-#define ARM_SMMU_PRIQ_PROD		0x100c8
-#define ARM_SMMU_PRIQ_CONS		0x100cc
+#define ARM_SMMU_PRIQ_PROD		0xc8
+#define ARM_SMMU_PRIQ_CONS		0xcc
 #define ARM_SMMU_PRIQ_IRQ_CFG0		0xd0
 #define ARM_SMMU_PRIQ_IRQ_CFG1		0xd8
 #define ARM_SMMU_PRIQ_IRQ_CFG2		0xdc
@@ -430,6 +430,8 @@ struct arm_smmu_cmdq_ent {
 		#define CMDQ_OP_TLBI_NH_ASID	0x11
 		#define CMDQ_OP_TLBI_NH_VA	0x12
 		#define CMDQ_OP_TLBI_EL2_ALL	0x20
+		#define CMDQ_OP_TLBI_EL2_ASID	0x21
+		#define CMDQ_OP_TLBI_EL2_VA	0x22
 		#define CMDQ_OP_TLBI_S12_VMALL	0x28
 		#define CMDQ_OP_TLBI_S2_IPA	0x2a
 		#define CMDQ_OP_TLBI_NSNH_ALL	0x30
@@ -604,6 +606,7 @@ struct arm_smmu_device {
 #define ARM_SMMU_FEAT_RANGE_INV		(1 << 15)
 #define ARM_SMMU_FEAT_BTM		(1 << 16)
 #define ARM_SMMU_FEAT_SVA		(1 << 17)
+#define ARM_SMMU_FEAT_E2H		(1 << 18)
 	u32				features;
 
 #define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)
@@ -694,6 +697,9 @@ extern struct arm_smmu_ctx_desc quiet_cd;
 int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
 			    struct arm_smmu_ctx_desc *cd);
 void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid);
+void arm_smmu_tlb_inv_range_asid(unsigned long iova, size_t size, int asid,
+				 size_t granule, bool leaf,
+				 struct arm_smmu_domain *smmu_domain);
 bool arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd);
 int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, int ssid,
 			    unsigned long iova, size_t size);

drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c

@@ -166,6 +166,7 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,mdss" },
 	{ .compatible = "qcom,sc7180-mdss" },
 	{ .compatible = "qcom,sc7180-mss-pil" },
+	{ .compatible = "qcom,sc8180x-mdss" },
 	{ .compatible = "qcom,sdm845-mdss" },
 	{ .compatible = "qcom,sdm845-mss-pil" },
 	{ }
@@ -206,6 +207,8 @@ static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
 		smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(i));
 
 		if (FIELD_GET(ARM_SMMU_SMR_VALID, smr)) {
+			/* Ignore valid bit for SMR mask extraction. */
+			smr &= ~ARM_SMMU_SMR_VALID;
 			smmu->smrs[i].id = FIELD_GET(ARM_SMMU_SMR_ID, smr);
 			smmu->smrs[i].mask = FIELD_GET(ARM_SMMU_SMR_MASK, smr);
 			smmu->smrs[i].valid = true;
@@ -327,10 +330,12 @@ static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
 static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
 	{ .compatible = "qcom,msm8998-smmu-v2" },
 	{ .compatible = "qcom,sc7180-smmu-500" },
+	{ .compatible = "qcom,sc8180x-smmu-500" },
 	{ .compatible = "qcom,sdm630-smmu-v2" },
 	{ .compatible = "qcom,sdm845-smmu-500" },
 	{ .compatible = "qcom,sm8150-smmu-500" },
 	{ .compatible = "qcom,sm8250-smmu-500" },
+	{ .compatible = "qcom,sm8350-smmu-500" },
 	{ }
 };
 

drivers/iommu/io-pgtable-arm-v7s.c

@@ -44,26 +44,25 @@
 
 /*
  * We have 32 bits total; 12 bits resolved at level 1, 8 bits at level 2,
- * and 12 bits in a page. With some carefully-chosen coefficients we can
- * hide the ugly inconsistencies behind these macros and at least let the
- * rest of the code pretend to be somewhat sane.
+ * and 12 bits in a page.
+ * MediaTek extend 2 bits to reach 34bits, 14 bits at lvl1 and 8 bits at lvl2.
  */
 #define ARM_V7S_ADDR_BITS		32
-#define _ARM_V7S_LVL_BITS(lvl)		(16 - (lvl) * 4)
-#define ARM_V7S_LVL_SHIFT(lvl)		(ARM_V7S_ADDR_BITS - (4 + 8 * (lvl)))
+#define _ARM_V7S_LVL_BITS(lvl, cfg)	((lvl) == 1 ? ((cfg)->ias - 20) : 8)
+#define ARM_V7S_LVL_SHIFT(lvl)		((lvl) == 1 ? 20 : 12)
 #define ARM_V7S_TABLE_SHIFT		10
 
-#define ARM_V7S_PTES_PER_LVL(lvl)	(1 << _ARM_V7S_LVL_BITS(lvl))
-#define ARM_V7S_TABLE_SIZE(lvl)						\
-	(ARM_V7S_PTES_PER_LVL(lvl) * sizeof(arm_v7s_iopte))
+#define ARM_V7S_PTES_PER_LVL(lvl, cfg)	(1 << _ARM_V7S_LVL_BITS(lvl, cfg))
+#define ARM_V7S_TABLE_SIZE(lvl, cfg)						\
+	(ARM_V7S_PTES_PER_LVL(lvl, cfg) * sizeof(arm_v7s_iopte))
 
 #define ARM_V7S_BLOCK_SIZE(lvl)		(1UL << ARM_V7S_LVL_SHIFT(lvl))
 #define ARM_V7S_LVL_MASK(lvl)		((u32)(~0U << ARM_V7S_LVL_SHIFT(lvl)))
 #define ARM_V7S_TABLE_MASK		((u32)(~0U << ARM_V7S_TABLE_SHIFT))
-#define _ARM_V7S_IDX_MASK(lvl)		(ARM_V7S_PTES_PER_LVL(lvl) - 1)
-#define ARM_V7S_LVL_IDX(addr, lvl)	({				\
+#define _ARM_V7S_IDX_MASK(lvl, cfg)	(ARM_V7S_PTES_PER_LVL(lvl, cfg) - 1)
+#define ARM_V7S_LVL_IDX(addr, lvl, cfg)	({				\
 	int _l = lvl;							\
-	((u32)(addr) >> ARM_V7S_LVL_SHIFT(_l)) & _ARM_V7S_IDX_MASK(_l); \
+	((addr) >> ARM_V7S_LVL_SHIFT(_l)) & _ARM_V7S_IDX_MASK(_l, cfg); \
 })
 
 /*
@@ -112,9 +111,10 @@
 #define ARM_V7S_TEX_MASK		0x7
 #define ARM_V7S_ATTR_TEX(val)		(((val) & ARM_V7S_TEX_MASK) << ARM_V7S_TEX_SHIFT)
 
-/* MediaTek extend the two bits for PA 32bit/33bit */
+/* MediaTek extend the bits below for PA 32bit/33bit/34bit */
 #define ARM_V7S_ATTR_MTK_PA_BIT32	BIT(9)
 #define ARM_V7S_ATTR_MTK_PA_BIT33	BIT(4)
+#define ARM_V7S_ATTR_MTK_PA_BIT34	BIT(5)
 
 /* *well, except for TEX on level 2 large pages, of course :( */
 #define ARM_V7S_CONT_PAGE_TEX_SHIFT	6
@@ -194,6 +194,8 @@ static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl,
 		pte |= ARM_V7S_ATTR_MTK_PA_BIT32;
 	if (paddr & BIT_ULL(33))
 		pte |= ARM_V7S_ATTR_MTK_PA_BIT33;
+	if (paddr & BIT_ULL(34))
+		pte |= ARM_V7S_ATTR_MTK_PA_BIT34;
 	return pte;
 }
 
@@ -218,6 +220,8 @@ static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl,
 		paddr |= BIT_ULL(32);
 	if (pte & ARM_V7S_ATTR_MTK_PA_BIT33)
 		paddr |= BIT_ULL(33);
+	if (pte & ARM_V7S_ATTR_MTK_PA_BIT34)
+		paddr |= BIT_ULL(34);
 	return paddr;
 }
 
@@ -234,7 +238,7 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp,
 	struct device *dev = cfg->iommu_dev;
 	phys_addr_t phys;
 	dma_addr_t dma;
-	size_t size = ARM_V7S_TABLE_SIZE(lvl);
+	size_t size = ARM_V7S_TABLE_SIZE(lvl, cfg);
 	void *table = NULL;
 
 	if (lvl == 1)
@@ -280,7 +284,7 @@ static void __arm_v7s_free_table(void *table, int lvl,
 {
 	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	struct device *dev = cfg->iommu_dev;
-	size_t size = ARM_V7S_TABLE_SIZE(lvl);
+	size_t size = ARM_V7S_TABLE_SIZE(lvl, cfg);
 
 	if (!cfg->coherent_walk)
 		dma_unmap_single(dev, __arm_v7s_dma_addr(table), size,
@@ -424,7 +428,7 @@ static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data,
 			arm_v7s_iopte *tblp;
 			size_t sz = ARM_V7S_BLOCK_SIZE(lvl);
 
-			tblp = ptep - ARM_V7S_LVL_IDX(iova, lvl);
+			tblp = ptep - ARM_V7S_LVL_IDX(iova, lvl, cfg);
 			if (WARN_ON(__arm_v7s_unmap(data, NULL, iova + i * sz,
 						    sz, lvl, tblp) != sz))
 				return -EINVAL;
@@ -477,7 +481,7 @@ static int __arm_v7s_map(struct arm_v7s_io_pgtable *data, unsigned long iova,
 	int num_entries = size >> ARM_V7S_LVL_SHIFT(lvl);
 
 	/* Find our entry at the current level */
-	ptep += ARM_V7S_LVL_IDX(iova, lvl);
+	ptep += ARM_V7S_LVL_IDX(iova, lvl, cfg);
 
 	/* If we can install a leaf entry at this level, then do so */
 	if (num_entries)
@@ -519,7 +523,6 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova,
 			phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
-	struct io_pgtable *iop = &data->iop;
 	int ret;
 
 	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias) ||
@@ -535,12 +538,7 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova,
 	 * Synchronise all PTE updates for the new mapping before there's
 	 * a chance for anything to kick off a table walk for the new iova.
 	 */
-	if (iop->cfg.quirks & IO_PGTABLE_QUIRK_TLBI_ON_MAP) {
-		io_pgtable_tlb_flush_walk(iop, iova, size,
-					  ARM_V7S_BLOCK_SIZE(2));
-	} else {
-		wmb();
-	}
+	wmb();
 
 	return ret;
 }
@@ -550,7 +548,7 @@ static void arm_v7s_free_pgtable(struct io_pgtable *iop)
 	struct arm_v7s_io_pgtable *data = io_pgtable_to_data(iop);
 	int i;
 
-	for (i = 0; i < ARM_V7S_PTES_PER_LVL(1); i++) {
+	for (i = 0; i < ARM_V7S_PTES_PER_LVL(1, &data->iop.cfg); i++) {
 		arm_v7s_iopte pte = data->pgd[i];
 
 		if (ARM_V7S_PTE_IS_TABLE(pte, 1))
@@ -602,9 +600,9 @@ static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
 	if (!tablep)
 		return 0; /* Bytes unmapped */
 
-	num_ptes = ARM_V7S_PTES_PER_LVL(2);
+	num_ptes = ARM_V7S_PTES_PER_LVL(2, cfg);
 	num_entries = size >> ARM_V7S_LVL_SHIFT(2);
-	unmap_idx = ARM_V7S_LVL_IDX(iova, 2);
+	unmap_idx = ARM_V7S_LVL_IDX(iova, 2, cfg);
 
 	pte = arm_v7s_prot_to_pte(arm_v7s_pte_to_prot(blk_pte, 1), 2, cfg);
 	if (num_entries > 1)
@@ -646,7 +644,7 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
 	if (WARN_ON(lvl > 2))
 		return 0;
 
-	idx = ARM_V7S_LVL_IDX(iova, lvl);
+	idx = ARM_V7S_LVL_IDX(iova, lvl, &iop->cfg);
 	ptep += idx;
 	do {
 		pte[i] = READ_ONCE(ptep[i]);
@@ -717,7 +715,7 @@ static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 {
 	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
 
-	if (WARN_ON(upper_32_bits(iova)))
+	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias)))
 		return 0;
 
 	return __arm_v7s_unmap(data, gather, iova, size, 1, data->pgd);
@@ -732,7 +730,7 @@ static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops,
 	u32 mask;
 
 	do {
-		ptep += ARM_V7S_LVL_IDX(iova, ++lvl);
+		ptep += ARM_V7S_LVL_IDX(iova, ++lvl, &data->iop.cfg);
 		pte = READ_ONCE(*ptep);
 		ptep = iopte_deref(pte, lvl, data);
 	} while (ARM_V7S_PTE_IS_TABLE(pte, lvl));
@@ -751,15 +749,14 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 {
 	struct arm_v7s_io_pgtable *data;
 
-	if (cfg->ias > ARM_V7S_ADDR_BITS)
+	if (cfg->ias > (arm_v7s_is_mtk_enabled(cfg) ? 34 : ARM_V7S_ADDR_BITS))
 		return NULL;
 
-	if (cfg->oas > (arm_v7s_is_mtk_enabled(cfg) ? 34 : ARM_V7S_ADDR_BITS))
+	if (cfg->oas > (arm_v7s_is_mtk_enabled(cfg) ? 35 : ARM_V7S_ADDR_BITS))
 		return NULL;
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
 			    IO_PGTABLE_QUIRK_NO_PERMS |
-			    IO_PGTABLE_QUIRK_TLBI_ON_MAP |
 			    IO_PGTABLE_QUIRK_ARM_MTK_EXT |
 			    IO_PGTABLE_QUIRK_NON_STRICT))
 		return NULL;
@@ -775,8 +772,8 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 
 	spin_lock_init(&data->split_lock);
 	data->l2_tables = kmem_cache_create("io-pgtable_armv7s_l2",
-					    ARM_V7S_TABLE_SIZE(2),
-					    ARM_V7S_TABLE_SIZE(2),
+					    ARM_V7S_TABLE_SIZE(2, cfg),
+					    ARM_V7S_TABLE_SIZE(2, cfg),
 					    ARM_V7S_TABLE_SLAB_FLAGS, NULL);
 	if (!data->l2_tables)
 		goto out_free_data;

drivers/iommu/iommu.c

@@ -2426,9 +2426,6 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
 		size -= pgsize;
 	}
 
-	if (ops->iotlb_sync_map)
-		ops->iotlb_sync_map(domain);
-
 	/* unroll mapping in case something went wrong */
 	if (ret)
 		iommu_unmap(domain, orig_iova, orig_size - size);
@@ -2438,18 +2435,31 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
 	return ret;
 }
 
+static int _iommu_map(struct iommu_domain *domain, unsigned long iova,
+		      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	const struct iommu_ops *ops = domain->ops;
+	int ret;
+
+	ret = __iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
+	if (ret == 0 && ops->iotlb_sync_map)
+		ops->iotlb_sync_map(domain, iova, size);
+
+	return ret;
+}
+
 int iommu_map(struct iommu_domain *domain, unsigned long iova,
 	      phys_addr_t paddr, size_t size, int prot)
 {
 	might_sleep();
-	return __iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
+	return _iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
 }
 EXPORT_SYMBOL_GPL(iommu_map);
 
 int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova,
 	      phys_addr_t paddr, size_t size, int prot)
 {
-	return __iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC);
+	return _iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC);
 }
 EXPORT_SYMBOL_GPL(iommu_map_atomic);
 
@@ -2533,6 +2543,7 @@ static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			     struct scatterlist *sg, unsigned int nents, int prot,
 			     gfp_t gfp)
 {
+	const struct iommu_ops *ops = domain->ops;
 	size_t len = 0, mapped = 0;
 	phys_addr_t start;
 	unsigned int i = 0;
@@ -2563,6 +2574,8 @@ static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			sg = sg_next(sg);
 	}
 
+	if (ops->iotlb_sync_map)
+		ops->iotlb_sync_map(domain, iova, mapped);
 	return mapped;
 
 out_err:

drivers/iommu/msm_iommu.c

@@ -343,7 +343,6 @@ static int msm_iommu_domain_config(struct msm_priv *priv)
 	spin_lock_init(&priv->pgtlock);
 
 	priv->cfg = (struct io_pgtable_cfg) {
-		.quirks = IO_PGTABLE_QUIRK_TLBI_ON_MAP,
 		.pgsize_bitmap = msm_iommu_ops.pgsize_bitmap,
 		.ias = 32,
 		.oas = 32,
@@ -490,6 +489,14 @@ static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova,
 	return ret;
 }
 
+static void msm_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+			       size_t size)
+{
+	struct msm_priv *priv = to_msm_priv(domain);
+
+	__flush_iotlb_range(iova, size, SZ_4K, false, priv);
+}
+
 static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 			      size_t len, struct iommu_iotlb_gather *gather)
 {
@@ -680,6 +687,7 @@ static struct iommu_ops msm_iommu_ops = {
 	 * kick starting the other master.
 	 */
 	.iotlb_sync = NULL,
+	.iotlb_sync_map = msm_iommu_sync_map,
 	.iova_to_phys = msm_iommu_iova_to_phys,
 	.probe_device = msm_iommu_probe_device,
 	.release_device = msm_iommu_release_device,

drivers/iommu/mtk_iommu.h

@@ -17,10 +17,13 @@
 #include <linux/spinlock.h>
 #include <linux/dma-mapping.h>
 #include <soc/mediatek/smi.h>
+#include <dt-bindings/memory/mtk-memory-port.h>
 
 #define MTK_LARB_COM_MAX	8
 #define MTK_LARB_SUBCOM_MAX	4
 
+#define MTK_IOMMU_GROUP_MAX	8
+
 struct mtk_iommu_suspend_reg {
 	union {
 		u32			standard_axi_mode;/* v1 */
@@ -42,12 +45,18 @@ enum mtk_iommu_plat {
 	M4U_MT8167,
 	M4U_MT8173,
 	M4U_MT8183,
+	M4U_MT8192,
 };
 
+struct mtk_iommu_iova_region;
+
 struct mtk_iommu_plat_data {
 	enum mtk_iommu_plat m4u_plat;
 	u32                 flags;
 	u32                 inv_sel_reg;
+
+	unsigned int				iova_region_nr;
+	const struct mtk_iommu_iova_region	*iova_region;
 	unsigned char       larbid_remap[MTK_LARB_COM_MAX][MTK_LARB_SUBCOM_MAX];
 };
 
@@ -61,12 +70,13 @@ struct mtk_iommu_data {
 	phys_addr_t			protect_base; /* protect memory base */
 	struct mtk_iommu_suspend_reg	reg;
 	struct mtk_iommu_domain		*m4u_dom;
-	struct iommu_group		*m4u_group;
+	struct iommu_group		*m4u_group[MTK_IOMMU_GROUP_MAX];
 	bool                            enable_4GB;
 	spinlock_t			tlb_lock; /* lock for tlb range flush */
 
 	struct iommu_device		iommu;
 	const struct mtk_iommu_plat_data *plat_data;
+	struct device			*smicomm_dev;
 
 	struct dma_iommu_mapping	*mapping; /* For mtk_iommu_v1.c */
 

drivers/iommu/tegra-gart.c

@@ -261,7 +261,8 @@ static int gart_iommu_of_xlate(struct device *dev,
 	return 0;
 }
 
-static void gart_iommu_sync_map(struct iommu_domain *domain)
+static void gart_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+				size_t size)
 {
 	FLUSH_GART_REGS(gart_handle);
 }
@@ -269,7 +270,9 @@ static void gart_iommu_sync_map(struct iommu_domain *domain)
 static void gart_iommu_sync(struct iommu_domain *domain,
 			    struct iommu_iotlb_gather *gather)
 {
-	gart_iommu_sync_map(domain);
+	size_t length = gather->end - gather->start + 1;
+
+	gart_iommu_sync_map(domain, gather->start, length);
 }
 
 static const struct iommu_ops gart_iommu_ops = {

drivers/memory/mtk-smi.c

@@ -15,6 +15,7 @@
 #include <linux/pm_runtime.h>
 #include <soc/mediatek/smi.h>
 #include <dt-bindings/memory/mt2701-larb-port.h>
+#include <dt-bindings/memory/mtk-memory-port.h>
 
 /* mt8173 */
 #define SMI_LARB_MMU_EN		0xf00
@@ -43,6 +44,10 @@
 /* mt2712 */
 #define SMI_LARB_NONSEC_CON(id)	(0x380 + ((id) * 4))
 #define F_MMU_EN		BIT(0)
+#define BANK_SEL(id)		({			\
+	u32 _id = (id) & 0x3;				\
+	(_id << 8 | _id << 10 | _id << 12 | _id << 14);	\
+})
 
 /* SMI COMMON */
 #define SMI_BUS_SEL			0x220
@@ -87,6 +92,7 @@ struct mtk_smi_larb { /* larb: local arbiter */
 	const struct mtk_smi_larb_gen	*larb_gen;
 	int				larbid;
 	u32				*mmu;
+	unsigned char			*bank;
 };
 
 static int mtk_smi_clk_enable(const struct mtk_smi *smi)
@@ -153,6 +159,7 @@ mtk_smi_larb_bind(struct device *dev, struct device *master, void *data)
 		if (dev == larb_mmu[i].dev) {
 			larb->larbid = i;
 			larb->mmu = &larb_mmu[i].mmu;
+			larb->bank = larb_mmu[i].bank;
 			return 0;
 		}
 	}
@@ -171,6 +178,7 @@ static void mtk_smi_larb_config_port_gen2_general(struct device *dev)
 	for_each_set_bit(i, (unsigned long *)larb->mmu, 32) {
 		reg = readl_relaxed(larb->base + SMI_LARB_NONSEC_CON(i));
 		reg |= F_MMU_EN;
+		reg |= BANK_SEL(larb->bank[i]);
 		writel(reg, larb->base + SMI_LARB_NONSEC_CON(i));
 	}
 }

drivers/perf/Kconfig

@@ -62,7 +62,7 @@ config ARM_PMU_ACPI
 
 config ARM_SMMU_V3_PMU
 	 tristate "ARM SMMUv3 Performance Monitors Extension"
-	 depends on ARM64 && ACPI && ARM_SMMU_V3
+	 depends on ARM64 && ACPI
 	   help
 	   Provides support for the ARM SMMUv3 Performance Monitor Counter
 	   Groups (PMCG), which provide monitoring of transactions passing

include/dt-bindings/memory/mt2701-larb-port.h

@@ -4,8 +4,8 @@
  * Author: Honghui Zhang <honghui.zhang@mediatek.com>
  */
 
-#ifndef _MT2701_LARB_PORT_H_
-#define _MT2701_LARB_PORT_H_
+#ifndef _DT_BINDINGS_MEMORY_MT2701_LARB_PORT_H_
+#define _DT_BINDINGS_MEMORY_MT2701_LARB_PORT_H_
 
 /*
  * Mediatek m4u generation 1 such as mt2701 has flat m4u port numbers,

include/dt-bindings/memory/mt2712-larb-port.h

@@ -3,10 +3,10 @@
  * Copyright (c) 2017 MediaTek Inc.
  * Author: Yong Wu <yong.wu@mediatek.com>
  */
-#ifndef __DTS_IOMMU_PORT_MT2712_H
-#define __DTS_IOMMU_PORT_MT2712_H
+#ifndef _DT_BINDINGS_MEMORY_MT2712_LARB_PORT_H_
+#define _DT_BINDINGS_MEMORY_MT2712_LARB_PORT_H_
 
-#define MTK_M4U_ID(larb, port)		(((larb) << 5) | (port))
+#include <dt-bindings/memory/mtk-memory-port.h>
 
 #define M4U_LARB0_ID			0
 #define M4U_LARB1_ID			1

include/dt-bindings/memory/mt6779-larb-port.h

@@ -4,10 +4,10 @@
  * Author: Chao Hao <chao.hao@mediatek.com>
  */
 
-#ifndef _DTS_IOMMU_PORT_MT6779_H_
-#define _DTS_IOMMU_PORT_MT6779_H_
+#ifndef _DT_BINDINGS_MEMORY_MT6779_LARB_PORT_H_
+#define _DT_BINDINGS_MEMORY_MT6779_LARB_PORT_H_
 
-#define MTK_M4U_ID(larb, port)		 (((larb) << 5) | (port))
+#include <dt-bindings/memory/mtk-memory-port.h>
 
 #define M4U_LARB0_ID			 0
 #define M4U_LARB1_ID			 1

include/dt-bindings/memory/mt8167-larb-port.h

@@ -5,10 +5,10 @@
  * Author: Honghui Zhang <honghui.zhang@mediatek.com>
  * Author: Fabien Parent <fparent@baylibre.com>
  */
-#ifndef __DTS_IOMMU_PORT_MT8167_H
-#define __DTS_IOMMU_PORT_MT8167_H
+#ifndef _DT_BINDINGS_MEMORY_MT8167_LARB_PORT_H_
+#define _DT_BINDINGS_MEMORY_MT8167_LARB_PORT_H_
 
-#define MTK_M4U_ID(larb, port)		(((larb) << 5) | (port))
+#include <dt-bindings/memory/mtk-memory-port.h>
 
 #define M4U_LARB0_ID			0
 #define M4U_LARB1_ID			1

include/dt-bindings/memory/mt8173-larb-port.h

@@ -3,10 +3,10 @@
  * Copyright (c) 2015-2016 MediaTek Inc.
  * Author: Yong Wu <yong.wu@mediatek.com>
  */
-#ifndef __DTS_IOMMU_PORT_MT8173_H
-#define __DTS_IOMMU_PORT_MT8173_H
+#ifndef _DT_BINDINGS_MEMORY_MT8173_LARB_PORT_H_
+#define _DT_BINDINGS_MEMORY_MT8173_LARB_PORT_H_
 
-#define MTK_M4U_ID(larb, port)		(((larb) << 5) | (port))
+#include <dt-bindings/memory/mtk-memory-port.h>
 
 #define M4U_LARB0_ID			0
 #define M4U_LARB1_ID			1

include/dt-bindings/memory/mt8183-larb-port.h

@@ -3,10 +3,10 @@
  * Copyright (c) 2018 MediaTek Inc.
  * Author: Yong Wu <yong.wu@mediatek.com>
  */
-#ifndef __DTS_IOMMU_PORT_MT8183_H
-#define __DTS_IOMMU_PORT_MT8183_H
+#ifndef _DT_BINDINGS_MEMORY_MT8183_LARB_PORT_H_
+#define _DT_BINDINGS_MEMORY_MT8183_LARB_PORT_H_
 
-#define MTK_M4U_ID(larb, port)		(((larb) << 5) | (port))
+#include <dt-bindings/memory/mtk-memory-port.h>
 
 #define M4U_LARB0_ID			0
 #define M4U_LARB1_ID			1

include/dt-bindings/memory/mtk-memory-port.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2020 MediaTek Inc.
+ * Author: Yong Wu <yong.wu@mediatek.com>
+ */
+#ifndef __DT_BINDINGS_MEMORY_MTK_MEMORY_PORT_H_
+#define __DT_BINDINGS_MEMORY_MTK_MEMORY_PORT_H_
+
+#define MTK_LARB_NR_MAX			32
+
+#define MTK_M4U_ID(larb, port)		(((larb) << 5) | (port))
+#define MTK_M4U_TO_LARB(id)		(((id) >> 5) & 0x1f)
+#define MTK_M4U_TO_PORT(id)		((id) & 0x1f)
+
+#endif

include/linux/io-pgtable.h

@@ -68,13 +68,9 @@ struct io_pgtable_cfg {
 	 *	hardware which does not implement the permissions of a given
 	 *	format, and/or requires some format-specific default value.
 	 *
-	 * IO_PGTABLE_QUIRK_TLBI_ON_MAP: If the format forbids caching invalid
-	 *	(unmapped) entries but the hardware might do so anyway, perform
-	 *	TLB maintenance when mapping as well as when unmapping.
-	 *
 	 * IO_PGTABLE_QUIRK_ARM_MTK_EXT: (ARM v7s format) MediaTek IOMMUs extend
-	 *	to support up to 34 bits PA where the bit32 and bit33 are
-	 *	encoded in the bit9 and bit4 of the PTE respectively.
+	 *	to support up to 35 bits PA where the bit32, bit33 and bit34 are
+	 *	encoded in the bit9, bit4 and bit5 of the PTE respectively.
 	 *
 	 * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs
 	 *	on unmap, for DMA domains using the flush queue mechanism for
@@ -88,7 +84,6 @@ struct io_pgtable_cfg {
 	 */
 	#define IO_PGTABLE_QUIRK_ARM_NS		BIT(0)
 	#define IO_PGTABLE_QUIRK_NO_PERMS	BIT(1)
-	#define IO_PGTABLE_QUIRK_TLBI_ON_MAP	BIT(2)
 	#define IO_PGTABLE_QUIRK_ARM_MTK_EXT	BIT(3)
 	#define IO_PGTABLE_QUIRK_NON_STRICT	BIT(4)
 	#define IO_PGTABLE_QUIRK_ARM_TTBR1	BIT(5)
@@ -214,14 +209,16 @@ struct io_pgtable_domain_attr {
 
 static inline void io_pgtable_tlb_flush_all(struct io_pgtable *iop)
 {
-	iop->cfg.tlb->tlb_flush_all(iop->cookie);
+	if (iop->cfg.tlb && iop->cfg.tlb->tlb_flush_all)
+		iop->cfg.tlb->tlb_flush_all(iop->cookie);
 }
 
 static inline void
 io_pgtable_tlb_flush_walk(struct io_pgtable *iop, unsigned long iova,
 			  size_t size, size_t granule)
 {
-	iop->cfg.tlb->tlb_flush_walk(iova, size, granule, iop->cookie);
+	if (iop->cfg.tlb && iop->cfg.tlb->tlb_flush_walk)
+		iop->cfg.tlb->tlb_flush_walk(iova, size, granule, iop->cookie);
 }
 
 static inline void
@@ -229,7 +226,7 @@ io_pgtable_tlb_add_page(struct io_pgtable *iop,
 			struct iommu_iotlb_gather * gather, unsigned long iova,
 			size_t granule)
 {
-	if (iop->cfg.tlb->tlb_add_page)
+	if (iop->cfg.tlb && iop->cfg.tlb->tlb_add_page)
 		iop->cfg.tlb->tlb_add_page(gather, iova, granule, iop->cookie);
 }
 

include/linux/iommu.h

@@ -170,7 +170,7 @@ enum iommu_dev_features {
  * struct iommu_iotlb_gather - Range information for a pending IOTLB flush
  *
  * @start: IOVA representing the start of the range to be flushed
- * @end: IOVA representing the end of the range to be flushed (exclusive)
+ * @end: IOVA representing the end of the range to be flushed (inclusive)
  * @pgsize: The interval at which to perform the flush
  *
  * This structure is intended to be updated by multiple calls to the
@@ -246,7 +246,8 @@ struct iommu_ops {
 	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
 		     size_t size, struct iommu_iotlb_gather *iotlb_gather);
 	void (*flush_iotlb_all)(struct iommu_domain *domain);
-	void (*iotlb_sync_map)(struct iommu_domain *domain);
+	void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova,
+			       size_t size);
 	void (*iotlb_sync)(struct iommu_domain *domain,
 			   struct iommu_iotlb_gather *iotlb_gather);
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova);
@@ -538,7 +539,7 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain,
 					       struct iommu_iotlb_gather *gather,
 					       unsigned long iova, size_t size)
 {
-	unsigned long start = iova, end = start + size;
+	unsigned long start = iova, end = start + size - 1;
 
 	/*
 	 * If the new page is disjoint from the current range or is mapped at

include/soc/mediatek/smi.h

@@ -11,13 +11,12 @@
 
 #ifdef CONFIG_MTK_SMI
 
-#define MTK_LARB_NR_MAX		16
-
 #define MTK_SMI_MMU_EN(port)	BIT(port)
 
 struct mtk_smi_larb_iommu {
 	struct device *dev;
 	unsigned int   mmu;
+	unsigned char  bank[32];
 };
 
 /*