Merge branch 'for-joerg/mtk' into for-joerg/arm-smmu/updates

Merge in Mediatek support from Yong Wu which introduces significant
changes to the TLB invalidation and Arm short-descriptor code in the
io-pgtable layer.

* for-joerg/mtk: (40 commits)
  MAINTAINERS: Add entry for MediaTek IOMMU
  iommu/mediatek: Add mt8192 support
  iommu/mediatek: Remove unnecessary check in attach_device
  iommu/mediatek: Support master use iova over 32bit
  iommu/mediatek: Add iova reserved function
  iommu/mediatek: Support for multi domains
  iommu/mediatek: Add get_domain_id from dev->dma_range_map
  iommu/mediatek: Add iova_region structure
  iommu/mediatek: Move geometry.aperture updating into domain_finalise
  iommu/mediatek: Move domain_finalise into attach_device
  iommu/mediatek: Adjust the structure
  iommu/mediatek: Support report iova 34bit translation fault in ISR
  iommu/mediatek: Support up to 34bit iova in tlb flush
  iommu/mediatek: Add power-domain operation
  iommu/mediatek: Add pm runtime callback
  iommu/mediatek: Add device link for smi-common and m4u
  iommu/mediatek: Add error handle for mtk_iommu_probe
  iommu/mediatek: Move hw_init into attach_device
  iommu/mediatek: Update oas for v7s
  iommu/mediatek: Add a flag for iova 34bits case
  ...

2 files changed, 11 insertions, 13 deletions

diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index ea727eb1a1a9..d69234a4a65e 100644
--- a/include/linux/io-pgtable.h
+++ b/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);
 }
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index b3f0e2018c62..ae8eddd4621b 100644
--- a/include/linux/iommu.h
+++ b/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