From 6d1bcb957be2850e0776f24c289e1f87c256baeb Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 2 Jul 2019 16:43:07 +0100
Subject: iommu: Remove empty iommu_tlb_range_add() callback from iommu_ops

Commit add02cfdc9bc ("iommu: Introduce Interface for IOMMU TLB Flushing")
added three new TLB flushing operations to the IOMMU API so that the
underlying driver operations can be batched when unmapping large regions
of IO virtual address space.

However, the ->iotlb_range_add() callback has not been implemented by
any IOMMU drivers (amd_iommu.c implements it as an empty function, which
incurs the overhead of an indirect branch). Instead, drivers either flush
the entire IOTLB in the ->iotlb_sync() callback or perform the necessary
invalidation during ->unmap().

Attempting to implement ->iotlb_range_add() for arm-smmu-v3.c revealed
two major issues:

  1. The page size used to map the region in the page-table is not known,
     and so it is not generally possible to issue TLB flushes in the most
     efficient manner.

  2. The only mutable state passed to the callback is a pointer to the
     iommu_domain, which can be accessed concurrently and therefore
     requires expensive synchronisation to keep track of the outstanding
     flushes.

Remove the callback entirely in preparation for extending ->unmap() and
->iotlb_sync() to update a token on the caller's stack.

Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/iommu.h | 15 ---------------
 1 file changed, 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index fdc355ccc570..1e21431262d9 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -201,7 +201,6 @@ struct iommu_sva_ops {
  * @map: map a physically contiguous memory region to an iommu domain
  * @unmap: unmap a physically contiguous memory region from an iommu domain
  * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain
- * @iotlb_range_add: Add a given iova range to the flush queue for this domain
  * @iotlb_sync_map: Sync mappings created recently using @map to the hardware
  * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
  *            queue
@@ -244,8 +243,6 @@ struct iommu_ops {
 	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
 		     size_t size);
 	void (*flush_iotlb_all)(struct iommu_domain *domain);
-	void (*iotlb_range_add)(struct iommu_domain *domain,
-				unsigned long iova, size_t size);
 	void (*iotlb_sync_map)(struct iommu_domain *domain);
 	void (*iotlb_sync)(struct iommu_domain *domain);
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova);
@@ -476,13 +473,6 @@ static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
 		domain->ops->flush_iotlb_all(domain);
 }
 
-static inline void iommu_tlb_range_add(struct iommu_domain *domain,
-				       unsigned long iova, size_t size)
-{
-	if (domain->ops->iotlb_range_add)
-		domain->ops->iotlb_range_add(domain, iova, size);
-}
-
 static inline void iommu_tlb_sync(struct iommu_domain *domain)
 {
 	if (domain->ops->iotlb_sync)
@@ -637,11 +627,6 @@ static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
 {
 }
 
-static inline void iommu_tlb_range_add(struct iommu_domain *domain,
-				       unsigned long iova, size_t size)
-{
-}
-
 static inline void iommu_tlb_sync(struct iommu_domain *domain)
 {
 }
-- 
cgit v1.3-14-g43fede


From 298f78895b081911e0b3605f07d79ebd3d4cf7b0 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 2 Jul 2019 16:43:34 +0100
Subject: iommu/io-pgtable: Rename iommu_gather_ops to iommu_flush_ops

In preparation for TLB flush gathering in the IOMMU API, rename the
iommu_gather_ops structure in io-pgtable to iommu_flush_ops, which
better describes its purpose and avoids the potential for confusion
between different levels of the API.

$ find linux/ -type f -name '*.[ch]' | xargs sed -i 's/gather_ops/flush_ops/g'

Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/gpu/drm/panfrost/panfrost_mmu.c | 2 +-
 drivers/iommu/arm-smmu-v3.c             | 4 ++--
 drivers/iommu/arm-smmu.c                | 8 ++++----
 drivers/iommu/io-pgtable-arm-v7s.c      | 2 +-
 drivers/iommu/io-pgtable-arm.c          | 2 +-
 drivers/iommu/ipmmu-vmsa.c              | 4 ++--
 drivers/iommu/msm_iommu.c               | 4 ++--
 drivers/iommu/mtk_iommu.c               | 4 ++--
 drivers/iommu/qcom_iommu.c              | 4 ++--
 include/linux/io-pgtable.h              | 6 +++---
 10 files changed, 20 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 92ac995dd9c6..17bceb11e708 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -257,7 +257,7 @@ static void mmu_tlb_sync_context(void *cookie)
 	// TODO: Wait 1000 GPU cycles for HW_ISSUE_6367/T60X
 }
 
-static const struct iommu_gather_ops mmu_tlb_ops = {
+static const struct iommu_flush_ops mmu_tlb_ops = {
 	.tlb_flush_all	= mmu_tlb_inv_context_s1,
 	.tlb_add_flush	= mmu_tlb_inv_range_nosync,
 	.tlb_sync	= mmu_tlb_sync_context,
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index a9a9fabd3968..7e137e1e28f1 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1603,7 +1603,7 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
 	} while (size -= granule);
 }
 
-static const struct iommu_gather_ops arm_smmu_gather_ops = {
+static const struct iommu_flush_ops arm_smmu_flush_ops = {
 	.tlb_flush_all	= arm_smmu_tlb_inv_context,
 	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
 	.tlb_sync	= arm_smmu_tlb_sync,
@@ -1796,7 +1796,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 		.ias		= ias,
 		.oas		= oas,
 		.coherent_walk	= smmu->features & ARM_SMMU_FEAT_COHERENCY,
-		.tlb		= &arm_smmu_gather_ops,
+		.tlb		= &arm_smmu_flush_ops,
 		.iommu_dev	= smmu->dev,
 	};
 
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 64977c131ee6..dc08db347ef3 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -251,7 +251,7 @@ enum arm_smmu_domain_stage {
 struct arm_smmu_domain {
 	struct arm_smmu_device		*smmu;
 	struct io_pgtable_ops		*pgtbl_ops;
-	const struct iommu_gather_ops	*tlb_ops;
+	const struct iommu_flush_ops	*tlb_ops;
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
 	bool				non_strict;
@@ -547,19 +547,19 @@ static void arm_smmu_tlb_inv_vmid_nosync(unsigned long iova, size_t size,
 	writel_relaxed(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID);
 }
 
-static const struct iommu_gather_ops arm_smmu_s1_tlb_ops = {
+static const struct iommu_flush_ops arm_smmu_s1_tlb_ops = {
 	.tlb_flush_all	= arm_smmu_tlb_inv_context_s1,
 	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
 	.tlb_sync	= arm_smmu_tlb_sync_context,
 };
 
-static const struct iommu_gather_ops arm_smmu_s2_tlb_ops_v2 = {
+static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
 	.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
 	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
 	.tlb_sync	= arm_smmu_tlb_sync_context,
 };
 
-static const struct iommu_gather_ops arm_smmu_s2_tlb_ops_v1 = {
+static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
 	.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
 	.tlb_add_flush	= arm_smmu_tlb_inv_vmid_nosync,
 	.tlb_sync	= arm_smmu_tlb_sync_vmid,
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index a62733c6a632..116f97ee991e 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -817,7 +817,7 @@ static void dummy_tlb_sync(void *cookie)
 	WARN_ON(cookie != cfg_cookie);
 }
 
-static const struct iommu_gather_ops dummy_tlb_ops = {
+static const struct iommu_flush_ops dummy_tlb_ops = {
 	.tlb_flush_all	= dummy_tlb_flush_all,
 	.tlb_add_flush	= dummy_tlb_add_flush,
 	.tlb_sync	= dummy_tlb_sync,
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 0d6633921c1e..402f913b6f6d 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -1081,7 +1081,7 @@ static void dummy_tlb_sync(void *cookie)
 	WARN_ON(cookie != cfg_cookie);
 }
 
-static const struct iommu_gather_ops dummy_tlb_ops __initconst = {
+static const struct iommu_flush_ops dummy_tlb_ops __initconst = {
 	.tlb_flush_all	= dummy_tlb_flush_all,
 	.tlb_add_flush	= dummy_tlb_add_flush,
 	.tlb_sync	= dummy_tlb_sync,
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index ad0098c0c87c..2c14a2c65b22 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -367,7 +367,7 @@ static void ipmmu_tlb_add_flush(unsigned long iova, size_t size,
 	/* The hardware doesn't support selective TLB flush. */
 }
 
-static const struct iommu_gather_ops ipmmu_gather_ops = {
+static const struct iommu_flush_ops ipmmu_flush_ops = {
 	.tlb_flush_all = ipmmu_tlb_flush_all,
 	.tlb_add_flush = ipmmu_tlb_add_flush,
 	.tlb_sync = ipmmu_tlb_flush_all,
@@ -480,7 +480,7 @@ static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
 	domain->cfg.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K;
 	domain->cfg.ias = 32;
 	domain->cfg.oas = 40;
-	domain->cfg.tlb = &ipmmu_gather_ops;
+	domain->cfg.tlb = &ipmmu_flush_ops;
 	domain->io_domain.geometry.aperture_end = DMA_BIT_MASK(32);
 	domain->io_domain.geometry.force_aperture = true;
 	/*
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index b25e2eb9e038..8b602384a385 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -178,7 +178,7 @@ static void __flush_iotlb_sync(void *cookie)
 	 */
 }
 
-static const struct iommu_gather_ops msm_iommu_gather_ops = {
+static const struct iommu_flush_ops msm_iommu_flush_ops = {
 	.tlb_flush_all = __flush_iotlb,
 	.tlb_add_flush = __flush_iotlb_range,
 	.tlb_sync = __flush_iotlb_sync,
@@ -345,7 +345,7 @@ static int msm_iommu_domain_config(struct msm_priv *priv)
 		.pgsize_bitmap = msm_iommu_ops.pgsize_bitmap,
 		.ias = 32,
 		.oas = 32,
-		.tlb = &msm_iommu_gather_ops,
+		.tlb = &msm_iommu_flush_ops,
 		.iommu_dev = priv->dev,
 	};
 
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 82e4be4dfdaf..fed77658d67e 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -188,7 +188,7 @@ static void mtk_iommu_tlb_sync(void *cookie)
 	}
 }
 
-static const struct iommu_gather_ops mtk_iommu_gather_ops = {
+static const struct iommu_flush_ops mtk_iommu_flush_ops = {
 	.tlb_flush_all = mtk_iommu_tlb_flush_all,
 	.tlb_add_flush = mtk_iommu_tlb_add_flush_nosync,
 	.tlb_sync = mtk_iommu_tlb_sync,
@@ -267,7 +267,7 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom)
 		.pgsize_bitmap = mtk_iommu_ops.pgsize_bitmap,
 		.ias = 32,
 		.oas = 32,
-		.tlb = &mtk_iommu_gather_ops,
+		.tlb = &mtk_iommu_flush_ops,
 		.iommu_dev = data->dev,
 	};
 
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 34d0b9783b3e..fd9d9f4da735 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -164,7 +164,7 @@ static void qcom_iommu_tlb_inv_range_nosync(unsigned long iova, size_t size,
 	}
 }
 
-static const struct iommu_gather_ops qcom_gather_ops = {
+static const struct iommu_flush_ops qcom_flush_ops = {
 	.tlb_flush_all	= qcom_iommu_tlb_inv_context,
 	.tlb_add_flush	= qcom_iommu_tlb_inv_range_nosync,
 	.tlb_sync	= qcom_iommu_tlb_sync,
@@ -215,7 +215,7 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
 		.pgsize_bitmap	= qcom_iommu_ops.pgsize_bitmap,
 		.ias		= 32,
 		.oas		= 40,
-		.tlb		= &qcom_gather_ops,
+		.tlb		= &qcom_flush_ops,
 		.iommu_dev	= qcom_iommu->dev,
 	};
 
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index b5a450a3bb47..6292ea15d674 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -17,7 +17,7 @@ enum io_pgtable_fmt {
 };
 
 /**
- * struct iommu_gather_ops - IOMMU callbacks for TLB and page table management.
+ * struct iommu_flush_ops - IOMMU callbacks for TLB and page table management.
  *
  * @tlb_flush_all: Synchronously invalidate the entire TLB context.
  * @tlb_add_flush: Queue up a TLB invalidation for a virtual address range.
@@ -28,7 +28,7 @@ enum io_pgtable_fmt {
  * Note that these can all be called in atomic context and must therefore
  * not block.
  */
-struct iommu_gather_ops {
+struct iommu_flush_ops {
 	void (*tlb_flush_all)(void *cookie);
 	void (*tlb_add_flush)(unsigned long iova, size_t size, size_t granule,
 			      bool leaf, void *cookie);
@@ -84,7 +84,7 @@ struct io_pgtable_cfg {
 	unsigned int			ias;
 	unsigned int			oas;
 	bool				coherent_walk;
-	const struct iommu_gather_ops	*tlb;
+	const struct iommu_flush_ops	*tlb;
 	struct device			*iommu_dev;
 
 	/* Low-level data specific to the table format */
-- 
cgit v1.3-14-g43fede


From a7d20dc19d9ea7012227be5144353012ffa3ddc4 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 2 Jul 2019 16:43:48 +0100
Subject: iommu: Introduce struct iommu_iotlb_gather for batching TLB flushes

To permit batching of TLB flushes across multiple calls to the IOMMU
driver's ->unmap() implementation, introduce a new structure for
tracking the address range to be flushed and the granularity at which
the flushing is required.

This is hooked into the IOMMU API and its caller are updated to make use
of the new structure. Subsequent patches will plumb this into the IOMMU
drivers as well, but for now the gathering information is ignored.

Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/dma-iommu.c       |  9 +++++++--
 drivers/iommu/iommu.c           | 19 +++++++++++-------
 drivers/vfio/vfio_iommu_type1.c | 26 ++++++++++++++++---------
 include/linux/iommu.h           | 43 +++++++++++++++++++++++++++++++++++++----
 4 files changed, 75 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index a7f9c3edbcb2..80beb1f5994a 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -444,13 +444,18 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	size_t iova_off = iova_offset(iovad, dma_addr);
+	struct iommu_iotlb_gather iotlb_gather;
+	size_t unmapped;
 
 	dma_addr -= iova_off;
 	size = iova_align(iovad, size + iova_off);
+	iommu_iotlb_gather_init(&iotlb_gather);
+
+	unmapped = iommu_unmap_fast(domain, dma_addr, size, &iotlb_gather);
+	WARN_ON(unmapped != size);
 
-	WARN_ON(iommu_unmap_fast(domain, dma_addr, size) != size);
 	if (!cookie->fq_domain)
-		iommu_tlb_sync(domain);
+		iommu_tlb_sync(domain, &iotlb_gather);
 	iommu_dma_free_iova(cookie, dma_addr, size);
 }
 
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 6d7b25fe2474..d67222fdfe44 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1862,7 +1862,7 @@ EXPORT_SYMBOL_GPL(iommu_map);
 
 static size_t __iommu_unmap(struct iommu_domain *domain,
 			    unsigned long iova, size_t size,
-			    bool sync)
+			    struct iommu_iotlb_gather *iotlb_gather)
 {
 	const struct iommu_ops *ops = domain->ops;
 	size_t unmapped_page, unmapped = 0;
@@ -1910,9 +1910,6 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 		unmapped += unmapped_page;
 	}
 
-	if (sync && ops->iotlb_sync)
-		ops->iotlb_sync(domain);
-
 	trace_unmap(orig_iova, size, unmapped);
 	return unmapped;
 }
@@ -1920,14 +1917,22 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 size_t iommu_unmap(struct iommu_domain *domain,
 		   unsigned long iova, size_t size)
 {
-	return __iommu_unmap(domain, iova, size, true);
+	struct iommu_iotlb_gather iotlb_gather;
+	size_t ret;
+
+	iommu_iotlb_gather_init(&iotlb_gather);
+	ret = __iommu_unmap(domain, iova, size, &iotlb_gather);
+	iommu_tlb_sync(domain, &iotlb_gather);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_unmap);
 
 size_t iommu_unmap_fast(struct iommu_domain *domain,
-			unsigned long iova, size_t size)
+			unsigned long iova, size_t size,
+			struct iommu_iotlb_gather *iotlb_gather)
 {
-	return __iommu_unmap(domain, iova, size, false);
+	return __iommu_unmap(domain, iova, size, iotlb_gather);
 }
 EXPORT_SYMBOL_GPL(iommu_unmap_fast);
 
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index fad7fd8c167c..ad830abe1021 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -650,12 +650,13 @@ unpin_exit:
 }
 
 static long vfio_sync_unpin(struct vfio_dma *dma, struct vfio_domain *domain,
-				struct list_head *regions)
+			    struct list_head *regions,
+			    struct iommu_iotlb_gather *iotlb_gather)
 {
 	long unlocked = 0;
 	struct vfio_regions *entry, *next;
 
-	iommu_tlb_sync(domain->domain);
+	iommu_tlb_sync(domain->domain, iotlb_gather);
 
 	list_for_each_entry_safe(entry, next, regions, list) {
 		unlocked += vfio_unpin_pages_remote(dma,
@@ -685,13 +686,15 @@ static size_t unmap_unpin_fast(struct vfio_domain *domain,
 			       struct vfio_dma *dma, dma_addr_t *iova,
 			       size_t len, phys_addr_t phys, long *unlocked,
 			       struct list_head *unmapped_list,
-			       int *unmapped_cnt)
+			       int *unmapped_cnt,
+			       struct iommu_iotlb_gather *iotlb_gather)
 {
 	size_t unmapped = 0;
 	struct vfio_regions *entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 
 	if (entry) {
-		unmapped = iommu_unmap_fast(domain->domain, *iova, len);
+		unmapped = iommu_unmap_fast(domain->domain, *iova, len,
+					    iotlb_gather);
 
 		if (!unmapped) {
 			kfree(entry);
@@ -711,8 +714,8 @@ static size_t unmap_unpin_fast(struct vfio_domain *domain,
 	 * or in case of errors.
 	 */
 	if (*unmapped_cnt >= VFIO_IOMMU_TLB_SYNC_MAX || !unmapped) {
-		*unlocked += vfio_sync_unpin(dma, domain,
-					     unmapped_list);
+		*unlocked += vfio_sync_unpin(dma, domain, unmapped_list,
+					     iotlb_gather);
 		*unmapped_cnt = 0;
 	}
 
@@ -743,6 +746,7 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
 	dma_addr_t iova = dma->iova, end = dma->iova + dma->size;
 	struct vfio_domain *domain, *d;
 	LIST_HEAD(unmapped_region_list);
+	struct iommu_iotlb_gather iotlb_gather;
 	int unmapped_region_cnt = 0;
 	long unlocked = 0;
 
@@ -767,6 +771,7 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
 		cond_resched();
 	}
 
+	iommu_iotlb_gather_init(&iotlb_gather);
 	while (iova < end) {
 		size_t unmapped, len;
 		phys_addr_t phys, next;
@@ -795,7 +800,8 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
 		 */
 		unmapped = unmap_unpin_fast(domain, dma, &iova, len, phys,
 					    &unlocked, &unmapped_region_list,
-					    &unmapped_region_cnt);
+					    &unmapped_region_cnt,
+					    &iotlb_gather);
 		if (!unmapped) {
 			unmapped = unmap_unpin_slow(domain, dma, &iova, len,
 						    phys, &unlocked);
@@ -806,8 +812,10 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
 
 	dma->iommu_mapped = false;
 
-	if (unmapped_region_cnt)
-		unlocked += vfio_sync_unpin(dma, domain, &unmapped_region_list);
+	if (unmapped_region_cnt) {
+		unlocked += vfio_sync_unpin(dma, domain, &unmapped_region_list,
+					    &iotlb_gather);
+	}
 
 	if (do_accounting) {
 		vfio_lock_acct(dma, -unlocked, true);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 1e21431262d9..aaf073010a9a 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -191,6 +191,23 @@ struct iommu_sva_ops {
 
 #ifdef CONFIG_IOMMU_API
 
+/**
+ * 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)
+ * @pgsize: The interval at which to perform the flush
+ *
+ * This structure is intended to be updated by multiple calls to the
+ * ->unmap() function in struct iommu_ops before eventually being passed
+ * into ->iotlb_sync().
+ */
+struct iommu_iotlb_gather {
+	unsigned long		start;
+	unsigned long		end;
+	size_t			pgsize;
+};
+
 /**
  * struct iommu_ops - iommu ops and capabilities
  * @capable: check capability
@@ -375,6 +392,13 @@ static inline struct iommu_device *dev_to_iommu_device(struct device *dev)
 	return (struct iommu_device *)dev_get_drvdata(dev);
 }
 
+static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather)
+{
+	*gather = (struct iommu_iotlb_gather) {
+		.start	= ULONG_MAX,
+	};
+}
+
 #define IOMMU_GROUP_NOTIFY_ADD_DEVICE		1 /* Device added */
 #define IOMMU_GROUP_NOTIFY_DEL_DEVICE		2 /* Pre Device removed */
 #define IOMMU_GROUP_NOTIFY_BIND_DRIVER		3 /* Pre Driver bind */
@@ -399,7 +423,8 @@ extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
 extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 			  size_t size);
 extern size_t iommu_unmap_fast(struct iommu_domain *domain,
-			       unsigned long iova, size_t size);
+			       unsigned long iova, size_t size,
+			       struct iommu_iotlb_gather *iotlb_gather);
 extern size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			   struct scatterlist *sg,unsigned int nents, int prot);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova);
@@ -473,10 +498,13 @@ static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
 		domain->ops->flush_iotlb_all(domain);
 }
 
-static inline void iommu_tlb_sync(struct iommu_domain *domain)
+static inline void iommu_tlb_sync(struct iommu_domain *domain,
+				  struct iommu_iotlb_gather *iotlb_gather)
 {
 	if (domain->ops->iotlb_sync)
 		domain->ops->iotlb_sync(domain);
+
+	iommu_iotlb_gather_init(iotlb_gather);
 }
 
 /* PCI device grouping function */
@@ -557,6 +585,7 @@ struct iommu_group {};
 struct iommu_fwspec {};
 struct iommu_device {};
 struct iommu_fault_param {};
+struct iommu_iotlb_gather {};
 
 static inline bool iommu_present(struct bus_type *bus)
 {
@@ -611,7 +640,8 @@ static inline size_t iommu_unmap(struct iommu_domain *domain,
 }
 
 static inline size_t iommu_unmap_fast(struct iommu_domain *domain,
-				      unsigned long iova, int gfp_order)
+				      unsigned long iova, int gfp_order,
+				      struct iommu_iotlb_gather *iotlb_gather)
 {
 	return 0;
 }
@@ -627,7 +657,8 @@ static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
 {
 }
 
-static inline void iommu_tlb_sync(struct iommu_domain *domain)
+static inline void iommu_tlb_sync(struct iommu_domain *domain,
+				  struct iommu_iotlb_gather *iotlb_gather)
 {
 }
 
@@ -812,6 +843,10 @@ static inline struct iommu_device *dev_to_iommu_device(struct device *dev)
 	return NULL;
 }
 
+static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather)
+{
+}
+
 static inline void iommu_device_unregister(struct iommu_device *iommu)
 {
 }
-- 
cgit v1.3-14-g43fede


From 4fcf8544fc677fc8af135f1d86b3ba69c4ad429d Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 2 Jul 2019 16:43:57 +0100
Subject: iommu: Introduce iommu_iotlb_gather_add_page()

Introduce a helper function for drivers to use when updating an
iommu_iotlb_gather structure in response to an ->unmap() call, rather
than having to open-code the logic in every page-table implementation.

Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/iommu.h | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index aaf073010a9a..ad41aee55bc6 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -507,6 +507,31 @@ static inline void iommu_tlb_sync(struct iommu_domain *domain,
 	iommu_iotlb_gather_init(iotlb_gather);
 }
 
+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;
+
+	/*
+	 * If the new page is disjoint from the current range or is mapped at
+	 * a different granularity, then sync the TLB so that the gather
+	 * structure can be rewritten.
+	 */
+	if (gather->pgsize != size ||
+	    end < gather->start || start > gather->end) {
+		if (gather->pgsize)
+			iommu_tlb_sync(domain, gather);
+		gather->pgsize = size;
+	}
+
+	if (gather->end < end)
+		gather->end = end;
+
+	if (gather->start > start)
+		gather->start = start;
+}
+
 /* PCI device grouping function */
 extern struct iommu_group *pci_device_group(struct device *dev);
 /* Generic device grouping function */
@@ -847,6 +872,12 @@ static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather)
 {
 }
 
+static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain,
+					       struct iommu_iotlb_gather *gather,
+					       unsigned long iova, size_t size)
+{
+}
+
 static inline void iommu_device_unregister(struct iommu_device *iommu)
 {
 }
-- 
cgit v1.3-14-g43fede


From 56f8af5e9d38f120cba2c2adb0786fa2dbc901a4 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 2 Jul 2019 16:44:06 +0100
Subject: iommu: Pass struct iommu_iotlb_gather to ->unmap() and ->iotlb_sync()

To allow IOMMU drivers to batch up TLB flushing operations and postpone
them until ->iotlb_sync() is called, extend the prototypes for the
->unmap() and ->iotlb_sync() IOMMU ops callbacks to take a pointer to
the current iommu_iotlb_gather structure.

All affected IOMMU drivers are updated, but there should be no
functional change since the extra parameter is ignored for now.

Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/amd_iommu.c      | 11 +++++++++--
 drivers/iommu/arm-smmu-v3.c    |  7 ++++---
 drivers/iommu/arm-smmu.c       |  5 +++--
 drivers/iommu/exynos-iommu.c   |  3 ++-
 drivers/iommu/intel-iommu.c    |  3 ++-
 drivers/iommu/iommu.c          |  2 +-
 drivers/iommu/ipmmu-vmsa.c     | 12 +++++++++---
 drivers/iommu/msm_iommu.c      |  2 +-
 drivers/iommu/mtk_iommu.c      | 13 ++++++++++---
 drivers/iommu/mtk_iommu_v1.c   |  3 ++-
 drivers/iommu/omap-iommu.c     |  2 +-
 drivers/iommu/qcom_iommu.c     | 12 +++++++++---
 drivers/iommu/rockchip-iommu.c |  2 +-
 drivers/iommu/s390-iommu.c     |  3 ++-
 drivers/iommu/tegra-gart.c     | 12 +++++++++---
 drivers/iommu/tegra-smmu.c     |  2 +-
 drivers/iommu/virtio-iommu.c   |  5 +++--
 include/linux/iommu.h          |  7 ++++---
 18 files changed, 73 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index f93b148cf55e..29eeea914660 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3055,7 +3055,8 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova,
 }
 
 static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
-			   size_t page_size)
+			      size_t page_size,
+			      struct iommu_iotlb_gather *gather)
 {
 	struct protection_domain *domain = to_pdomain(dom);
 	size_t unmap_size;
@@ -3196,6 +3197,12 @@ static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
 	domain_flush_complete(dom);
 }
 
+static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
+				 struct iommu_iotlb_gather *gather)
+{
+	amd_iommu_flush_iotlb_all(domain);
+}
+
 const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
 	.domain_alloc = amd_iommu_domain_alloc,
@@ -3214,7 +3221,7 @@ const struct iommu_ops amd_iommu_ops = {
 	.is_attach_deferred = amd_iommu_is_attach_deferred,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 	.flush_iotlb_all = amd_iommu_flush_iotlb_all,
-	.iotlb_sync = amd_iommu_flush_iotlb_all,
+	.iotlb_sync = amd_iommu_iotlb_sync,
 };
 
 /*****************************************************************************
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 7e137e1e28f1..80753b8ca054 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1985,8 +1985,8 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
 	return ops->map(ops, iova, paddr, size, prot);
 }
 
-static size_t
-arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
+static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
+			     size_t size, struct iommu_iotlb_gather *gather)
 {
 	int ret;
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
@@ -2010,7 +2010,8 @@ static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
 		arm_smmu_tlb_inv_context(smmu_domain);
 }
 
-static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
+static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
+				struct iommu_iotlb_gather *gather)
 {
 	struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
 
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index dc08db347ef3..e535ae2a9e65 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1301,7 +1301,7 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
 }
 
 static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
-			     size_t size)
+			     size_t size, struct iommu_iotlb_gather *gather)
 {
 	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
 	struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
@@ -1329,7 +1329,8 @@ static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
 	}
 }
 
-static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
+static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
+				struct iommu_iotlb_gather *gather)
 {
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index b0c1e5f9daae..cf5af34cb681 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -1130,7 +1130,8 @@ static void exynos_iommu_tlb_invalidate_entry(struct exynos_iommu_domain *domain
 }
 
 static size_t exynos_iommu_unmap(struct iommu_domain *iommu_domain,
-				 unsigned long l_iova, size_t size)
+				 unsigned long l_iova, size_t size,
+				 struct iommu_iotlb_gather *gather)
 {
 	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
 	sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index ac4172c02244..b9fb8d6ddc6e 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -5147,7 +5147,8 @@ static int intel_iommu_map(struct iommu_domain *domain,
 }
 
 static size_t intel_iommu_unmap(struct iommu_domain *domain,
-				unsigned long iova, size_t size)
+				unsigned long iova, size_t size,
+				struct iommu_iotlb_gather *gather)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	struct page *freelist = NULL;
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index d67222fdfe44..70bfbcc09248 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1899,7 +1899,7 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 	while (unmapped < size) {
 		size_t pgsize = iommu_pgsize(domain, iova, size - unmapped);
 
-		unmapped_page = ops->unmap(domain, iova, pgsize);
+		unmapped_page = ops->unmap(domain, iova, pgsize, iotlb_gather);
 		if (!unmapped_page)
 			break;
 
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 2c14a2c65b22..a9332b893ce2 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -733,14 +733,14 @@ static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova,
 }
 
 static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova,
-			  size_t size)
+			  size_t size, struct iommu_iotlb_gather *gather)
 {
 	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
 
 	return domain->iop->unmap(domain->iop, iova, size);
 }
 
-static void ipmmu_iotlb_sync(struct iommu_domain *io_domain)
+static void ipmmu_flush_iotlb_all(struct iommu_domain *io_domain)
 {
 	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
 
@@ -748,6 +748,12 @@ static void ipmmu_iotlb_sync(struct iommu_domain *io_domain)
 		ipmmu_tlb_flush_all(domain);
 }
 
+static void ipmmu_iotlb_sync(struct iommu_domain *io_domain,
+			     struct iommu_iotlb_gather *gather)
+{
+	ipmmu_flush_iotlb_all(io_domain);
+}
+
 static phys_addr_t ipmmu_iova_to_phys(struct iommu_domain *io_domain,
 				      dma_addr_t iova)
 {
@@ -957,7 +963,7 @@ static const struct iommu_ops ipmmu_ops = {
 	.detach_dev = ipmmu_detach_device,
 	.map = ipmmu_map,
 	.unmap = ipmmu_unmap,
-	.flush_iotlb_all = ipmmu_iotlb_sync,
+	.flush_iotlb_all = ipmmu_flush_iotlb_all,
 	.iotlb_sync = ipmmu_iotlb_sync,
 	.iova_to_phys = ipmmu_iova_to_phys,
 	.add_device = ipmmu_add_device,
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 8b602384a385..681ab3d3376d 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -509,7 +509,7 @@ static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova,
 }
 
 static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
-			      size_t len)
+			      size_t len, struct iommu_iotlb_gather *gather)
 {
 	struct msm_priv *priv = to_msm_priv(domain);
 	unsigned long flags;
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index fed77658d67e..c870f1674903 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -371,7 +371,8 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
 }
 
 static size_t mtk_iommu_unmap(struct iommu_domain *domain,
-			      unsigned long iova, size_t size)
+			      unsigned long iova, size_t size,
+			      struct iommu_iotlb_gather *gather)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	unsigned long flags;
@@ -384,7 +385,13 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain,
 	return unmapsz;
 }
 
-static void mtk_iommu_iotlb_sync(struct iommu_domain *domain)
+static void mtk_iommu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
+}
+
+static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
+				 struct iommu_iotlb_gather *gather)
 {
 	mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
 }
@@ -490,7 +497,7 @@ static const struct iommu_ops mtk_iommu_ops = {
 	.detach_dev	= mtk_iommu_detach_device,
 	.map		= mtk_iommu_map,
 	.unmap		= mtk_iommu_unmap,
-	.flush_iotlb_all = mtk_iommu_iotlb_sync,
+	.flush_iotlb_all = mtk_iommu_flush_iotlb_all,
 	.iotlb_sync	= mtk_iommu_iotlb_sync,
 	.iova_to_phys	= mtk_iommu_iova_to_phys,
 	.add_device	= mtk_iommu_add_device,
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index abeeac488372..7b92ddd5d9fd 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -324,7 +324,8 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
 }
 
 static size_t mtk_iommu_unmap(struct iommu_domain *domain,
-			      unsigned long iova, size_t size)
+			      unsigned long iova, size_t size,
+			      struct iommu_iotlb_gather *gather)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	unsigned long flags;
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index dfb961d8c21b..8039bc5ee425 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -1149,7 +1149,7 @@ static int omap_iommu_map(struct iommu_domain *domain, unsigned long da,
 }
 
 static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da,
-			       size_t size)
+			       size_t size, struct iommu_iotlb_gather *gather)
 {
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 	struct device *dev = omap_domain->dev;
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index fd9d9f4da735..a7432991fa04 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -417,7 +417,7 @@ static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova,
 }
 
 static size_t qcom_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
-			       size_t size)
+			       size_t size, struct iommu_iotlb_gather *gather)
 {
 	size_t ret;
 	unsigned long flags;
@@ -441,7 +441,7 @@ static size_t qcom_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 	return ret;
 }
 
-static void qcom_iommu_iotlb_sync(struct iommu_domain *domain)
+static void qcom_iommu_flush_iotlb_all(struct iommu_domain *domain)
 {
 	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
 	struct io_pgtable *pgtable = container_of(qcom_domain->pgtbl_ops,
@@ -454,6 +454,12 @@ static void qcom_iommu_iotlb_sync(struct iommu_domain *domain)
 	pm_runtime_put_sync(qcom_domain->iommu->dev);
 }
 
+static void qcom_iommu_iotlb_sync(struct iommu_domain *domain,
+				  struct iommu_iotlb_gather *gather)
+{
+	qcom_iommu_flush_iotlb_all(domain);
+}
+
 static phys_addr_t qcom_iommu_iova_to_phys(struct iommu_domain *domain,
 					   dma_addr_t iova)
 {
@@ -581,7 +587,7 @@ static const struct iommu_ops qcom_iommu_ops = {
 	.detach_dev	= qcom_iommu_detach_dev,
 	.map		= qcom_iommu_map,
 	.unmap		= qcom_iommu_unmap,
-	.flush_iotlb_all = qcom_iommu_iotlb_sync,
+	.flush_iotlb_all = qcom_iommu_flush_iotlb_all,
 	.iotlb_sync	= qcom_iommu_iotlb_sync,
 	.iova_to_phys	= qcom_iommu_iova_to_phys,
 	.add_device	= qcom_iommu_add_device,
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index dc26d74d79c2..26290f310f90 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -794,7 +794,7 @@ static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova,
 }
 
 static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova,
-			     size_t size)
+			     size_t size, struct iommu_iotlb_gather *gather)
 {
 	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
 	unsigned long flags;
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index 22d4db302c1c..3b0b18e23187 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -314,7 +314,8 @@ static phys_addr_t s390_iommu_iova_to_phys(struct iommu_domain *domain,
 }
 
 static size_t s390_iommu_unmap(struct iommu_domain *domain,
-			       unsigned long iova, size_t size)
+			       unsigned long iova, size_t size,
+			       struct iommu_iotlb_gather *gather)
 {
 	struct s390_domain *s390_domain = to_s390_domain(domain);
 	int flags = ZPCI_PTE_INVALID;
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index 6d40bc1b38bf..3924f7c05544 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -207,7 +207,7 @@ static inline int __gart_iommu_unmap(struct gart_device *gart,
 }
 
 static size_t gart_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
-			       size_t bytes)
+			       size_t bytes, struct iommu_iotlb_gather *gather)
 {
 	struct gart_device *gart = gart_handle;
 	int err;
@@ -273,11 +273,17 @@ static int gart_iommu_of_xlate(struct device *dev,
 	return 0;
 }
 
-static void gart_iommu_sync(struct iommu_domain *domain)
+static void gart_iommu_sync_map(struct iommu_domain *domain)
 {
 	FLUSH_GART_REGS(gart_handle);
 }
 
+static void gart_iommu_sync(struct iommu_domain *domain,
+			    struct iommu_iotlb_gather *gather)
+{
+	gart_iommu_sync_map(domain);
+}
+
 static const struct iommu_ops gart_iommu_ops = {
 	.capable	= gart_iommu_capable,
 	.domain_alloc	= gart_iommu_domain_alloc,
@@ -292,7 +298,7 @@ static const struct iommu_ops gart_iommu_ops = {
 	.iova_to_phys	= gart_iommu_iova_to_phys,
 	.pgsize_bitmap	= GART_IOMMU_PGSIZES,
 	.of_xlate	= gart_iommu_of_xlate,
-	.iotlb_sync_map	= gart_iommu_sync,
+	.iotlb_sync_map	= gart_iommu_sync_map,
 	.iotlb_sync	= gart_iommu_sync,
 };
 
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index c4a652b227f8..7293fc3f796d 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -680,7 +680,7 @@ static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
 }
 
 static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
-			       size_t size)
+			       size_t size, struct iommu_iotlb_gather *gather)
 {
 	struct tegra_smmu_as *as = to_smmu_as(domain);
 	dma_addr_t pte_dma;
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 433f4d2ee956..5f9f91a4d7f3 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -742,7 +742,7 @@ static int viommu_map(struct iommu_domain *domain, unsigned long iova,
 }
 
 static size_t viommu_unmap(struct iommu_domain *domain, unsigned long iova,
-			   size_t size)
+			   size_t size, struct iommu_iotlb_gather *gather)
 {
 	int ret = 0;
 	size_t unmapped;
@@ -788,7 +788,8 @@ static phys_addr_t viommu_iova_to_phys(struct iommu_domain *domain,
 	return paddr;
 }
 
-static void viommu_iotlb_sync(struct iommu_domain *domain)
+static void viommu_iotlb_sync(struct iommu_domain *domain,
+			      struct iommu_iotlb_gather *gather)
 {
 	struct viommu_domain *vdomain = to_viommu_domain(domain);
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index ad41aee55bc6..64ebaff33455 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -258,10 +258,11 @@ struct iommu_ops {
 	int (*map)(struct iommu_domain *domain, unsigned long iova,
 		   phys_addr_t paddr, size_t size, int prot);
 	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
-		     size_t size);
+		     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)(struct iommu_domain *domain);
+	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);
 	int (*add_device)(struct device *dev);
 	void (*remove_device)(struct device *dev);
@@ -502,7 +503,7 @@ static inline void iommu_tlb_sync(struct iommu_domain *domain,
 				  struct iommu_iotlb_gather *iotlb_gather)
 {
 	if (domain->ops->iotlb_sync)
-		domain->ops->iotlb_sync(domain);
+		domain->ops->iotlb_sync(domain, iotlb_gather);
 
 	iommu_iotlb_gather_init(iotlb_gather);
 }
-- 
cgit v1.3-14-g43fede


From 3445545b2248300319b6965208e77140c960c3fd Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 2 Jul 2019 16:44:16 +0100
Subject: iommu/io-pgtable: Introduce tlb_flush_walk() and tlb_flush_leaf()

In preparation for deferring TLB flushes to iommu_tlb_sync(), introduce
two new synchronous invalidation helpers to the io-pgtable API, which
allow the unmap() code to force invalidation in cases where it cannot be
deferred (e.g. when replacing a table with a block or when TLBI_ON_MAP
is set).

Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/io-pgtable.h | 24 +++++++++++++++++++-----
 1 file changed, 19 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 6292ea15d674..27275575b305 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -19,17 +19,31 @@ enum io_pgtable_fmt {
 /**
  * struct iommu_flush_ops - IOMMU callbacks for TLB and page table management.
  *
- * @tlb_flush_all: Synchronously invalidate the entire TLB context.
- * @tlb_add_flush: Queue up a TLB invalidation for a virtual address range.
- * @tlb_sync:      Ensure any queued TLB invalidation has taken effect, and
- *                 any corresponding page table updates are visible to the
- *                 IOMMU.
+ * @tlb_flush_all:  Synchronously invalidate the entire TLB context.
+ * @tlb_flush_walk: Synchronously invalidate all intermediate TLB state
+ *                  (sometimes referred to as the "walk cache") for a virtual
+ *                  address range.
+ * @tlb_flush_leaf: Synchronously invalidate all leaf TLB state for a virtual
+ *                  address range.
+ * @tlb_add_flush:  Optional callback to queue up leaf TLB invalidation for a
+ *                  virtual address range.  This function exists purely as an
+ *                  optimisation for IOMMUs that cannot batch TLB invalidation
+ *                  operations efficiently and are therefore better suited to
+ *                  issuing them early rather than deferring them until
+ *                  iommu_tlb_sync().
+ * @tlb_sync:       Ensure any queued TLB invalidation has taken effect, and
+ *                  any corresponding page table updates are visible to the
+ *                  IOMMU.
  *
  * Note that these can all be called in atomic context and must therefore
  * not block.
  */
 struct iommu_flush_ops {
 	void (*tlb_flush_all)(void *cookie);
+	void (*tlb_flush_walk)(unsigned long iova, size_t size, size_t granule,
+			       void *cookie);
+	void (*tlb_flush_leaf)(unsigned long iova, size_t size, size_t granule,
+			       void *cookie);
 	void (*tlb_add_flush)(unsigned long iova, size_t size, size_t granule,
 			      bool leaf, void *cookie);
 	void (*tlb_sync)(void *cookie);
-- 
cgit v1.3-14-g43fede


From 10b7a7d912697afd681a0bcfced9e05543aded35 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 2 Jul 2019 16:44:32 +0100
Subject: iommu/io-pgtable-arm: Call ->tlb_flush_walk() and ->tlb_flush_leaf()

Now that all IOMMU drivers using the io-pgtable API implement the
->tlb_flush_walk() and ->tlb_flush_leaf() callbacks, we can use them in
the io-pgtable code instead of ->tlb_add_flush() immediately followed by
->tlb_sync().

Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/io-pgtable-arm-v7s.c | 25 +++++++++++++++----------
 drivers/iommu/io-pgtable-arm.c     | 17 ++++++++++++-----
 include/linux/io-pgtable.h         | 14 ++++++++++++++
 3 files changed, 41 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 116f97ee991e..8d4914fe73bc 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -493,9 +493,8 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova,
 	 * 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_add_flush(iop, iova, size,
-					 ARM_V7S_BLOCK_SIZE(2), false);
-		io_pgtable_tlb_sync(iop);
+		io_pgtable_tlb_flush_walk(iop, iova, size,
+					  ARM_V7S_BLOCK_SIZE(2));
 	} else {
 		wmb();
 	}
@@ -541,8 +540,7 @@ static arm_v7s_iopte arm_v7s_split_cont(struct arm_v7s_io_pgtable *data,
 	__arm_v7s_pte_sync(ptep, ARM_V7S_CONT_PAGES, &iop->cfg);
 
 	size *= ARM_V7S_CONT_PAGES;
-	io_pgtable_tlb_add_flush(iop, iova, size, size, true);
-	io_pgtable_tlb_sync(iop);
+	io_pgtable_tlb_flush_leaf(iop, iova, size, size);
 	return pte;
 }
 
@@ -637,9 +635,8 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
 		for (i = 0; i < num_entries; i++) {
 			if (ARM_V7S_PTE_IS_TABLE(pte[i], lvl)) {
 				/* Also flush any partial walks */
-				io_pgtable_tlb_add_flush(iop, iova, blk_size,
-					ARM_V7S_BLOCK_SIZE(lvl + 1), false);
-				io_pgtable_tlb_sync(iop);
+				io_pgtable_tlb_flush_walk(iop, iova, blk_size,
+						ARM_V7S_BLOCK_SIZE(lvl + 1));
 				ptep = iopte_deref(pte[i], lvl);
 				__arm_v7s_free_table(ptep, lvl + 1, data);
 			} else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) {
@@ -805,13 +802,19 @@ static void dummy_tlb_flush_all(void *cookie)
 	WARN_ON(cookie != cfg_cookie);
 }
 
-static void dummy_tlb_add_flush(unsigned long iova, size_t size,
-				size_t granule, bool leaf, void *cookie)
+static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule,
+			    void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
 	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
 }
 
+static void dummy_tlb_add_flush(unsigned long iova, size_t size,
+				size_t granule, bool leaf, void *cookie)
+{
+	dummy_tlb_flush(iova, size, granule, cookie);
+}
+
 static void dummy_tlb_sync(void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
@@ -819,6 +822,8 @@ static void dummy_tlb_sync(void *cookie)
 
 static const struct iommu_flush_ops dummy_tlb_ops = {
 	.tlb_flush_all	= dummy_tlb_flush_all,
+	.tlb_flush_walk	= dummy_tlb_flush,
+	.tlb_flush_leaf	= dummy_tlb_flush,
 	.tlb_add_flush	= dummy_tlb_add_flush,
 	.tlb_sync	= dummy_tlb_sync,
 };
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 402f913b6f6d..b58338c86323 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -611,9 +611,8 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 
 		if (!iopte_leaf(pte, lvl, iop->fmt)) {
 			/* Also flush any partial walks */
-			io_pgtable_tlb_add_flush(iop, iova, size,
-						ARM_LPAE_GRANULE(data), false);
-			io_pgtable_tlb_sync(iop);
+			io_pgtable_tlb_flush_walk(iop, iova, size,
+						  ARM_LPAE_GRANULE(data));
 			ptep = iopte_deref(pte, data);
 			__arm_lpae_free_pgtable(data, lvl + 1, ptep);
 		} else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) {
@@ -1069,13 +1068,19 @@ static void dummy_tlb_flush_all(void *cookie)
 	WARN_ON(cookie != cfg_cookie);
 }
 
-static void dummy_tlb_add_flush(unsigned long iova, size_t size,
-				size_t granule, bool leaf, void *cookie)
+static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule,
+			    void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
 	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
 }
 
+static void dummy_tlb_add_flush(unsigned long iova, size_t size,
+				size_t granule, bool leaf, void *cookie)
+{
+	dummy_tlb_flush(iova, size, granule, cookie);
+}
+
 static void dummy_tlb_sync(void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
@@ -1083,6 +1088,8 @@ static void dummy_tlb_sync(void *cookie)
 
 static const struct iommu_flush_ops dummy_tlb_ops __initconst = {
 	.tlb_flush_all	= dummy_tlb_flush_all,
+	.tlb_flush_walk	= dummy_tlb_flush,
+	.tlb_flush_leaf	= dummy_tlb_flush,
 	.tlb_add_flush	= dummy_tlb_add_flush,
 	.tlb_sync	= dummy_tlb_sync,
 };
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 27275575b305..0618aac59e74 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -198,6 +198,20 @@ static inline void io_pgtable_tlb_flush_all(struct io_pgtable *iop)
 	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);
+}
+
+static inline void
+io_pgtable_tlb_flush_leaf(struct io_pgtable *iop, unsigned long iova,
+			  size_t size, size_t granule)
+{
+	iop->cfg.tlb->tlb_flush_leaf(iova, size, granule, iop->cookie);
+}
+
 static inline void io_pgtable_tlb_add_flush(struct io_pgtable *iop,
 		unsigned long iova, size_t size, size_t granule, bool leaf)
 {
-- 
cgit v1.3-14-g43fede


From abfd6fe0cd535d31ee83b668be6eb59ce6a8469d Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 2 Jul 2019 16:44:41 +0100
Subject: iommu/io-pgtable: Replace ->tlb_add_flush() with ->tlb_add_page()

The ->tlb_add_flush() callback in the io-pgtable API now looks a bit
silly:

  - It takes a size and a granule, which are always the same
  - It takes a 'bool leaf', which is always true
  - It only ever flushes a single page

With that in mind, replace it with an optional ->tlb_add_page() callback
that drops the useless parameters.

Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/gpu/drm/panfrost/panfrost_mmu.c |  5 --
 drivers/iommu/arm-smmu-v3.c             |  8 ++-
 drivers/iommu/arm-smmu.c                | 88 +++++++++++++++++++++------------
 drivers/iommu/io-pgtable-arm-v7s.c      | 12 ++---
 drivers/iommu/io-pgtable-arm.c          | 11 ++---
 drivers/iommu/ipmmu-vmsa.c              |  7 ---
 drivers/iommu/msm_iommu.c               |  7 ++-
 drivers/iommu/mtk_iommu.c               |  8 ++-
 drivers/iommu/qcom_iommu.c              |  8 ++-
 include/linux/io-pgtable.h              | 22 ++++-----
 10 files changed, 105 insertions(+), 71 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 651858147bd6..ff9af320cacc 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -247,10 +247,6 @@ static void mmu_tlb_inv_context_s1(void *cookie)
 	mmu_hw_do_operation(pfdev, 0, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
 }
 
-static void mmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
-				     size_t granule, bool leaf, void *cookie)
-{}
-
 static void mmu_tlb_sync_context(void *cookie)
 {
 	//struct panfrost_device *pfdev = cookie;
@@ -273,7 +269,6 @@ static const struct iommu_flush_ops mmu_tlb_ops = {
 	.tlb_flush_all	= mmu_tlb_inv_context_s1,
 	.tlb_flush_walk = mmu_tlb_flush_walk,
 	.tlb_flush_leaf = mmu_tlb_flush_leaf,
-	.tlb_add_flush	= mmu_tlb_inv_range_nosync,
 	.tlb_sync	= mmu_tlb_sync_context,
 };
 
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 79819b003b07..98c90a1b4b22 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1603,6 +1603,12 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
 	} while (size -= granule);
 }
 
+static void arm_smmu_tlb_inv_page_nosync(unsigned long iova, size_t granule,
+					 void *cookie)
+{
+	arm_smmu_tlb_inv_range_nosync(iova, granule, granule, true, cookie);
+}
+
 static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size,
 				  size_t granule, void *cookie)
 {
@@ -1627,7 +1633,7 @@ static const struct iommu_flush_ops arm_smmu_flush_ops = {
 	.tlb_flush_all	= arm_smmu_tlb_inv_context,
 	.tlb_flush_walk = arm_smmu_tlb_inv_walk,
 	.tlb_flush_leaf = arm_smmu_tlb_inv_leaf,
-	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
+	.tlb_add_page	= arm_smmu_tlb_inv_page_nosync,
 	.tlb_sync	= arm_smmu_tlb_sync,
 };
 
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index e9f01b860ae3..f056164a94b0 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -248,10 +248,16 @@ enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_BYPASS,
 };
 
+struct arm_smmu_flush_ops {
+	struct iommu_flush_ops		tlb;
+	void (*tlb_inv_range)(unsigned long iova, size_t size, size_t granule,
+			      bool leaf, void *cookie)
+};
+
 struct arm_smmu_domain {
 	struct arm_smmu_device		*smmu;
 	struct io_pgtable_ops		*pgtbl_ops;
-	const struct iommu_flush_ops	*tlb_ops;
+	const struct arm_smmu_flush_ops	*flush_ops;
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
 	bool				non_strict;
@@ -551,42 +557,62 @@ static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size,
 				  size_t granule, void *cookie)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
+	const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
 
-	smmu_domain->tlb_ops->tlb_add_flush(iova, size, granule, false, cookie);
-	smmu_domain->tlb_ops->tlb_sync(cookie);
+	ops->tlb_inv_range(iova, size, granule, false, cookie);
+	ops->tlb.tlb_sync(cookie);
 }
 
 static void arm_smmu_tlb_inv_leaf(unsigned long iova, size_t size,
 				  size_t granule, void *cookie)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
+	const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
+
+	ops->tlb_inv_range(iova, size, granule, true, cookie);
+	ops->tlb.tlb_sync(cookie);
+}
+
+static void arm_smmu_tlb_add_page(unsigned long iova, size_t granule,
+				  void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
 
-	smmu_domain->tlb_ops->tlb_add_flush(iova, size, granule, true, cookie);
-	smmu_domain->tlb_ops->tlb_sync(cookie);
+	ops->tlb_inv_range(iova, granule, granule, true, cookie);
 }
 
-static const struct iommu_flush_ops arm_smmu_s1_tlb_ops = {
-	.tlb_flush_all	= arm_smmu_tlb_inv_context_s1,
-	.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
-	.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
-	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
-	.tlb_sync	= arm_smmu_tlb_sync_context,
+static const struct arm_smmu_flush_ops arm_smmu_s1_tlb_ops = {
+	.tlb = {
+		.tlb_flush_all	= arm_smmu_tlb_inv_context_s1,
+		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
+		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
+		.tlb_add_page	= arm_smmu_tlb_add_page,
+		.tlb_sync	= arm_smmu_tlb_sync_context,
+	},
+	.tlb_inv_range		= arm_smmu_tlb_inv_range_nosync,
 };
 
-static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
-	.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
-	.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
-	.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
-	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
-	.tlb_sync	= arm_smmu_tlb_sync_context,
+static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
+	.tlb = {
+		.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
+		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
+		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
+		.tlb_add_page	= arm_smmu_tlb_add_page,
+		.tlb_sync	= arm_smmu_tlb_sync_context,
+	},
+	.tlb_inv_range		= arm_smmu_tlb_inv_range_nosync,
 };
 
-static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
-	.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
-	.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
-	.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
-	.tlb_add_flush	= arm_smmu_tlb_inv_vmid_nosync,
-	.tlb_sync	= arm_smmu_tlb_sync_vmid,
+static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
+	.tlb = {
+		.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
+		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
+		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
+		.tlb_add_page	= arm_smmu_tlb_add_page,
+		.tlb_sync	= arm_smmu_tlb_sync_vmid,
+	},
+	.tlb_inv_range		= arm_smmu_tlb_inv_vmid_nosync,
 };
 
 static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
@@ -866,7 +892,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 			ias = min(ias, 32UL);
 			oas = min(oas, 32UL);
 		}
-		smmu_domain->tlb_ops = &arm_smmu_s1_tlb_ops;
+		smmu_domain->flush_ops = &arm_smmu_s1_tlb_ops;
 		break;
 	case ARM_SMMU_DOMAIN_NESTED:
 		/*
@@ -886,9 +912,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 			oas = min(oas, 40UL);
 		}
 		if (smmu->version == ARM_SMMU_V2)
-			smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v2;
+			smmu_domain->flush_ops = &arm_smmu_s2_tlb_ops_v2;
 		else
-			smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v1;
+			smmu_domain->flush_ops = &arm_smmu_s2_tlb_ops_v1;
 		break;
 	default:
 		ret = -EINVAL;
@@ -917,7 +943,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		.ias		= ias,
 		.oas		= oas,
 		.coherent_walk	= smmu->features & ARM_SMMU_FEAT_COHERENT_WALK,
-		.tlb		= smmu_domain->tlb_ops,
+		.tlb		= &smmu_domain->flush_ops->tlb,
 		.iommu_dev	= smmu->dev,
 	};
 
@@ -1346,9 +1372,9 @@ static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 
-	if (smmu_domain->tlb_ops) {
+	if (smmu_domain->flush_ops) {
 		arm_smmu_rpm_get(smmu);
-		smmu_domain->tlb_ops->tlb_flush_all(smmu_domain);
+		smmu_domain->flush_ops->tlb.tlb_flush_all(smmu_domain);
 		arm_smmu_rpm_put(smmu);
 	}
 }
@@ -1359,9 +1385,9 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 
-	if (smmu_domain->tlb_ops) {
+	if (smmu_domain->flush_ops) {
 		arm_smmu_rpm_get(smmu);
-		smmu_domain->tlb_ops->tlb_sync(smmu_domain);
+		smmu_domain->flush_ops->tlb.tlb_sync(smmu_domain);
 		arm_smmu_rpm_put(smmu);
 	}
 }
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 8d4914fe73bc..b3f975c95f76 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -584,7 +584,7 @@ static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
 		return __arm_v7s_unmap(data, iova, size, 2, tablep);
 	}
 
-	io_pgtable_tlb_add_flush(&data->iop, iova, size, size, true);
+	io_pgtable_tlb_add_page(&data->iop, iova, size);
 	return size;
 }
 
@@ -647,8 +647,7 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
 				 */
 				smp_wmb();
 			} else {
-				io_pgtable_tlb_add_flush(iop, iova, blk_size,
-							 blk_size, true);
+				io_pgtable_tlb_add_page(iop, iova, blk_size);
 			}
 			iova += blk_size;
 		}
@@ -809,10 +808,9 @@ static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule,
 	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
 }
 
-static void dummy_tlb_add_flush(unsigned long iova, size_t size,
-				size_t granule, bool leaf, void *cookie)
+static void dummy_tlb_add_page(unsigned long iova, size_t granule, void *cookie)
 {
-	dummy_tlb_flush(iova, size, granule, cookie);
+	dummy_tlb_flush(iova, granule, granule, cookie);
 }
 
 static void dummy_tlb_sync(void *cookie)
@@ -824,7 +822,7 @@ static const struct iommu_flush_ops dummy_tlb_ops = {
 	.tlb_flush_all	= dummy_tlb_flush_all,
 	.tlb_flush_walk	= dummy_tlb_flush,
 	.tlb_flush_leaf	= dummy_tlb_flush,
-	.tlb_add_flush	= dummy_tlb_add_flush,
+	.tlb_add_page	= dummy_tlb_add_page,
 	.tlb_sync	= dummy_tlb_sync,
 };
 
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index b58338c86323..a5c0db01533e 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -582,7 +582,7 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 
 		tablep = iopte_deref(pte, data);
 	} else if (unmap_idx >= 0) {
-		io_pgtable_tlb_add_flush(&data->iop, iova, size, size, true);
+		io_pgtable_tlb_add_page(&data->iop, iova, size);
 		return size;
 	}
 
@@ -623,7 +623,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 			 */
 			smp_wmb();
 		} else {
-			io_pgtable_tlb_add_flush(iop, iova, size, size, true);
+			io_pgtable_tlb_add_page(iop, iova, size);
 		}
 
 		return size;
@@ -1075,10 +1075,9 @@ static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule,
 	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
 }
 
-static void dummy_tlb_add_flush(unsigned long iova, size_t size,
-				size_t granule, bool leaf, void *cookie)
+static void dummy_tlb_add_page(unsigned long iova, size_t granule, void *cookie)
 {
-	dummy_tlb_flush(iova, size, granule, cookie);
+	dummy_tlb_flush(iova, granule, granule, cookie);
 }
 
 static void dummy_tlb_sync(void *cookie)
@@ -1090,7 +1089,7 @@ static const struct iommu_flush_ops dummy_tlb_ops __initconst = {
 	.tlb_flush_all	= dummy_tlb_flush_all,
 	.tlb_flush_walk	= dummy_tlb_flush,
 	.tlb_flush_leaf	= dummy_tlb_flush,
-	.tlb_add_flush	= dummy_tlb_add_flush,
+	.tlb_add_page	= dummy_tlb_add_page,
 	.tlb_sync	= dummy_tlb_sync,
 };
 
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 9cc7bcb7e39d..c4da271af90e 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -367,17 +367,10 @@ static void ipmmu_tlb_flush(unsigned long iova, size_t size,
 	ipmmu_tlb_flush_all(cookie);
 }
 
-static void ipmmu_tlb_add_flush(unsigned long iova, size_t size,
-				size_t granule, bool leaf, void *cookie)
-{
-	/* The hardware doesn't support selective TLB flush. */
-}
-
 static const struct iommu_flush_ops ipmmu_flush_ops = {
 	.tlb_flush_all = ipmmu_tlb_flush_all,
 	.tlb_flush_walk = ipmmu_tlb_flush,
 	.tlb_flush_leaf = ipmmu_tlb_flush,
-	.tlb_add_flush = ipmmu_tlb_add_flush,
 	.tlb_sync = ipmmu_tlb_flush_all,
 };
 
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 64132093751a..2cd83295a841 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -192,11 +192,16 @@ static void __flush_iotlb_leaf(unsigned long iova, size_t size,
 	__flush_iotlb_sync(cookie);
 }
 
+static void __flush_iotlb_page(unsigned long iova, size_t granule, void *cookie)
+{
+	__flush_iotlb_range(iova, granule, granule, true, cookie);
+}
+
 static const struct iommu_flush_ops msm_iommu_flush_ops = {
 	.tlb_flush_all = __flush_iotlb,
 	.tlb_flush_walk = __flush_iotlb_walk,
 	.tlb_flush_leaf = __flush_iotlb_leaf,
-	.tlb_add_flush = __flush_iotlb_range,
+	.tlb_add_page = __flush_iotlb_page,
 	.tlb_sync = __flush_iotlb_sync,
 };
 
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 85a7176bf9ae..a0b4b4dc4b90 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -202,11 +202,17 @@ static void mtk_iommu_tlb_flush_leaf(unsigned long iova, size_t size,
 	mtk_iommu_tlb_sync(cookie);
 }
 
+static void mtk_iommu_tlb_flush_page_nosync(unsigned long iova, size_t granule,
+					    void *cookie)
+{
+	mtk_iommu_tlb_add_flush_nosync(iova, granule, granule, true, cookie);
+}
+
 static const struct iommu_flush_ops mtk_iommu_flush_ops = {
 	.tlb_flush_all = mtk_iommu_tlb_flush_all,
 	.tlb_flush_walk = mtk_iommu_tlb_flush_walk,
 	.tlb_flush_leaf = mtk_iommu_tlb_flush_leaf,
-	.tlb_add_flush = mtk_iommu_tlb_add_flush_nosync,
+	.tlb_add_page = mtk_iommu_tlb_flush_page_nosync,
 	.tlb_sync = mtk_iommu_tlb_sync,
 };
 
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 643079e52e69..7d8411dee4cf 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -178,11 +178,17 @@ static void qcom_iommu_tlb_flush_leaf(unsigned long iova, size_t size,
 	qcom_iommu_tlb_sync(cookie);
 }
 
+static void qcom_iommu_tlb_add_page(unsigned long iova, size_t granule,
+				    void *cookie)
+{
+	qcom_iommu_tlb_inv_range_nosync(iova, granule, granule, true, cookie);
+}
+
 static const struct iommu_flush_ops qcom_flush_ops = {
 	.tlb_flush_all	= qcom_iommu_tlb_inv_context,
 	.tlb_flush_walk = qcom_iommu_tlb_flush_walk,
 	.tlb_flush_leaf = qcom_iommu_tlb_flush_leaf,
-	.tlb_add_flush	= qcom_iommu_tlb_inv_range_nosync,
+	.tlb_add_page	= qcom_iommu_tlb_add_page,
 	.tlb_sync	= qcom_iommu_tlb_sync,
 };
 
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 0618aac59e74..99e04bd2baa1 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -25,12 +25,11 @@ enum io_pgtable_fmt {
  *                  address range.
  * @tlb_flush_leaf: Synchronously invalidate all leaf TLB state for a virtual
  *                  address range.
- * @tlb_add_flush:  Optional callback to queue up leaf TLB invalidation for a
- *                  virtual address range.  This function exists purely as an
- *                  optimisation for IOMMUs that cannot batch TLB invalidation
- *                  operations efficiently and are therefore better suited to
- *                  issuing them early rather than deferring them until
- *                  iommu_tlb_sync().
+ * @tlb_add_page:   Optional callback to queue up leaf TLB invalidation for a
+ *                  single page. This function exists purely as an optimisation
+ *                  for IOMMUs that cannot batch TLB invalidation operations
+ *                  efficiently and are therefore better suited to issuing them
+ *                  early rather than deferring them until iommu_tlb_sync().
  * @tlb_sync:       Ensure any queued TLB invalidation has taken effect, and
  *                  any corresponding page table updates are visible to the
  *                  IOMMU.
@@ -44,8 +43,7 @@ struct iommu_flush_ops {
 			       void *cookie);
 	void (*tlb_flush_leaf)(unsigned long iova, size_t size, size_t granule,
 			       void *cookie);
-	void (*tlb_add_flush)(unsigned long iova, size_t size, size_t granule,
-			      bool leaf, void *cookie);
+	void (*tlb_add_page)(unsigned long iova, size_t granule, void *cookie);
 	void (*tlb_sync)(void *cookie);
 };
 
@@ -212,10 +210,12 @@ io_pgtable_tlb_flush_leaf(struct io_pgtable *iop, unsigned long iova,
 	iop->cfg.tlb->tlb_flush_leaf(iova, size, granule, iop->cookie);
 }
 
-static inline void io_pgtable_tlb_add_flush(struct io_pgtable *iop,
-		unsigned long iova, size_t size, size_t granule, bool leaf)
+static inline void
+io_pgtable_tlb_add_page(struct io_pgtable *iop, unsigned long iova,
+			size_t granule)
 {
-	iop->cfg.tlb->tlb_add_flush(iova, size, granule, leaf, iop->cookie);
+	if (iop->cfg.tlb->tlb_add_page)
+		iop->cfg.tlb->tlb_add_page(iova, granule, iop->cookie);
 }
 
 static inline void io_pgtable_tlb_sync(struct io_pgtable *iop)
-- 
cgit v1.3-14-g43fede


From e953f7f2fa78d1c7fd064171f88457c6b1e21af9 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 2 Jul 2019 16:44:50 +0100
Subject: iommu/io-pgtable: Remove unused ->tlb_sync() callback

The ->tlb_sync() callback is no longer used, so it can be removed.

Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/gpu/drm/panfrost/panfrost_mmu.c |  1 -
 drivers/iommu/arm-smmu-v3.c             |  8 --------
 drivers/iommu/arm-smmu.c                | 17 +++++++++--------
 drivers/iommu/io-pgtable-arm-v7s.c      |  6 ------
 drivers/iommu/io-pgtable-arm.c          |  6 ------
 drivers/iommu/ipmmu-vmsa.c              |  1 -
 drivers/iommu/msm_iommu.c               | 20 +++++++-------------
 drivers/iommu/mtk_iommu.c               |  1 -
 drivers/iommu/qcom_iommu.c              |  1 -
 include/linux/io-pgtable.h              |  9 ---------
 10 files changed, 16 insertions(+), 54 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index ff9af320cacc..de22a2276e00 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -269,7 +269,6 @@ static const struct iommu_flush_ops mmu_tlb_ops = {
 	.tlb_flush_all	= mmu_tlb_inv_context_s1,
 	.tlb_flush_walk = mmu_tlb_flush_walk,
 	.tlb_flush_leaf = mmu_tlb_flush_leaf,
-	.tlb_sync	= mmu_tlb_sync_context,
 };
 
 static const char *access_type_name(struct panfrost_device *pfdev,
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 98c90a1b4b22..231093413ff9 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1545,13 +1545,6 @@ static int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain,
 }
 
 /* IO_PGTABLE API */
-static void arm_smmu_tlb_sync(void *cookie)
-{
-	struct arm_smmu_domain *smmu_domain = cookie;
-
-	arm_smmu_cmdq_issue_sync(smmu_domain->smmu);
-}
-
 static void arm_smmu_tlb_inv_context(void *cookie)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
@@ -1634,7 +1627,6 @@ static const struct iommu_flush_ops arm_smmu_flush_ops = {
 	.tlb_flush_walk = arm_smmu_tlb_inv_walk,
 	.tlb_flush_leaf = arm_smmu_tlb_inv_leaf,
 	.tlb_add_page	= arm_smmu_tlb_inv_page_nosync,
-	.tlb_sync	= arm_smmu_tlb_sync,
 };
 
 /* IOMMU API */
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index f056164a94b0..07a267c437d6 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -251,7 +251,8 @@ enum arm_smmu_domain_stage {
 struct arm_smmu_flush_ops {
 	struct iommu_flush_ops		tlb;
 	void (*tlb_inv_range)(unsigned long iova, size_t size, size_t granule,
-			      bool leaf, void *cookie)
+			      bool leaf, void *cookie);
+	void (*tlb_sync)(void *cookie);
 };
 
 struct arm_smmu_domain {
@@ -539,7 +540,7 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
  * On MMU-401 at least, the cost of firing off multiple TLBIVMIDs appears
  * almost negligible, but the benefit of getting the first one in as far ahead
  * of the sync as possible is significant, hence we don't just make this a
- * no-op and set .tlb_sync to arm_smmu_inv_context_s2() as you might think.
+ * no-op and set .tlb_sync to arm_smmu_tlb_inv_context_s2() as you might think.
  */
 static void arm_smmu_tlb_inv_vmid_nosync(unsigned long iova, size_t size,
 					 size_t granule, bool leaf, void *cookie)
@@ -560,7 +561,7 @@ static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size,
 	const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
 
 	ops->tlb_inv_range(iova, size, granule, false, cookie);
-	ops->tlb.tlb_sync(cookie);
+	ops->tlb_sync(cookie);
 }
 
 static void arm_smmu_tlb_inv_leaf(unsigned long iova, size_t size,
@@ -570,7 +571,7 @@ static void arm_smmu_tlb_inv_leaf(unsigned long iova, size_t size,
 	const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
 
 	ops->tlb_inv_range(iova, size, granule, true, cookie);
-	ops->tlb.tlb_sync(cookie);
+	ops->tlb_sync(cookie);
 }
 
 static void arm_smmu_tlb_add_page(unsigned long iova, size_t granule,
@@ -588,9 +589,9 @@ static const struct arm_smmu_flush_ops arm_smmu_s1_tlb_ops = {
 		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
 		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
 		.tlb_add_page	= arm_smmu_tlb_add_page,
-		.tlb_sync	= arm_smmu_tlb_sync_context,
 	},
 	.tlb_inv_range		= arm_smmu_tlb_inv_range_nosync,
+	.tlb_sync		= arm_smmu_tlb_sync_context,
 };
 
 static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
@@ -599,9 +600,9 @@ static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
 		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
 		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
 		.tlb_add_page	= arm_smmu_tlb_add_page,
-		.tlb_sync	= arm_smmu_tlb_sync_context,
 	},
 	.tlb_inv_range		= arm_smmu_tlb_inv_range_nosync,
+	.tlb_sync		= arm_smmu_tlb_sync_context,
 };
 
 static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
@@ -610,9 +611,9 @@ static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
 		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
 		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
 		.tlb_add_page	= arm_smmu_tlb_add_page,
-		.tlb_sync	= arm_smmu_tlb_sync_vmid,
 	},
 	.tlb_inv_range		= arm_smmu_tlb_inv_vmid_nosync,
+	.tlb_sync		= arm_smmu_tlb_sync_vmid,
 };
 
 static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
@@ -1387,7 +1388,7 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
 
 	if (smmu_domain->flush_ops) {
 		arm_smmu_rpm_get(smmu);
-		smmu_domain->flush_ops->tlb.tlb_sync(smmu_domain);
+		smmu_domain->flush_ops->tlb_sync(smmu_domain);
 		arm_smmu_rpm_put(smmu);
 	}
 }
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index b3f975c95f76..203894fb6765 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -813,17 +813,11 @@ static void dummy_tlb_add_page(unsigned long iova, size_t granule, void *cookie)
 	dummy_tlb_flush(iova, granule, granule, cookie);
 }
 
-static void dummy_tlb_sync(void *cookie)
-{
-	WARN_ON(cookie != cfg_cookie);
-}
-
 static const struct iommu_flush_ops dummy_tlb_ops = {
 	.tlb_flush_all	= dummy_tlb_flush_all,
 	.tlb_flush_walk	= dummy_tlb_flush,
 	.tlb_flush_leaf	= dummy_tlb_flush,
 	.tlb_add_page	= dummy_tlb_add_page,
-	.tlb_sync	= dummy_tlb_sync,
 };
 
 #define __FAIL(ops)	({				\
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index a5c0db01533e..f35516744965 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -1080,17 +1080,11 @@ static void dummy_tlb_add_page(unsigned long iova, size_t granule, void *cookie)
 	dummy_tlb_flush(iova, granule, granule, cookie);
 }
 
-static void dummy_tlb_sync(void *cookie)
-{
-	WARN_ON(cookie != cfg_cookie);
-}
-
 static const struct iommu_flush_ops dummy_tlb_ops __initconst = {
 	.tlb_flush_all	= dummy_tlb_flush_all,
 	.tlb_flush_walk	= dummy_tlb_flush,
 	.tlb_flush_leaf	= dummy_tlb_flush,
 	.tlb_add_page	= dummy_tlb_add_page,
-	.tlb_sync	= dummy_tlb_sync,
 };
 
 static void __init arm_lpae_dump_ops(struct io_pgtable_ops *ops)
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index c4da271af90e..a2b8eff4c1f7 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -371,7 +371,6 @@ static const struct iommu_flush_ops ipmmu_flush_ops = {
 	.tlb_flush_all = ipmmu_tlb_flush_all,
 	.tlb_flush_walk = ipmmu_tlb_flush,
 	.tlb_flush_leaf = ipmmu_tlb_flush,
-	.tlb_sync = ipmmu_tlb_flush_all,
 };
 
 /* -----------------------------------------------------------------------------
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 2cd83295a841..ccfc7ed230ef 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -168,28 +168,16 @@ fail:
 	return;
 }
 
-static void __flush_iotlb_sync(void *cookie)
-{
-	/*
-	 * Nothing is needed here, the barrier to guarantee
-	 * completion of the tlb sync operation is implicitly
-	 * taken care when the iommu client does a writel before
-	 * kick starting the other master.
-	 */
-}
-
 static void __flush_iotlb_walk(unsigned long iova, size_t size,
 			       size_t granule, void *cookie)
 {
 	__flush_iotlb_range(iova, size, granule, false, cookie);
-	__flush_iotlb_sync(cookie);
 }
 
 static void __flush_iotlb_leaf(unsigned long iova, size_t size,
 			       size_t granule, void *cookie)
 {
 	__flush_iotlb_range(iova, size, granule, true, cookie);
-	__flush_iotlb_sync(cookie);
 }
 
 static void __flush_iotlb_page(unsigned long iova, size_t granule, void *cookie)
@@ -202,7 +190,6 @@ static const struct iommu_flush_ops msm_iommu_flush_ops = {
 	.tlb_flush_walk = __flush_iotlb_walk,
 	.tlb_flush_leaf = __flush_iotlb_leaf,
 	.tlb_add_page = __flush_iotlb_page,
-	.tlb_sync = __flush_iotlb_sync,
 };
 
 static int msm_iommu_alloc_ctx(unsigned long *map, int start, int end)
@@ -712,6 +699,13 @@ static struct iommu_ops msm_iommu_ops = {
 	.detach_dev = msm_iommu_detach_dev,
 	.map = msm_iommu_map,
 	.unmap = msm_iommu_unmap,
+	/*
+	 * Nothing is needed here, the barrier to guarantee
+	 * completion of the tlb sync operation is implicitly
+	 * taken care when the iommu client does a writel before
+	 * kick starting the other master.
+	 */
+	.iotlb_sync = NULL,
 	.iova_to_phys = msm_iommu_iova_to_phys,
 	.add_device = msm_iommu_add_device,
 	.remove_device = msm_iommu_remove_device,
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index a0b4b4dc4b90..3785750bdb44 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -213,7 +213,6 @@ static const struct iommu_flush_ops mtk_iommu_flush_ops = {
 	.tlb_flush_walk = mtk_iommu_tlb_flush_walk,
 	.tlb_flush_leaf = mtk_iommu_tlb_flush_leaf,
 	.tlb_add_page = mtk_iommu_tlb_flush_page_nosync,
-	.tlb_sync = mtk_iommu_tlb_sync,
 };
 
 static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 7d8411dee4cf..0b8a6d6bb475 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -189,7 +189,6 @@ static const struct iommu_flush_ops qcom_flush_ops = {
 	.tlb_flush_walk = qcom_iommu_tlb_flush_walk,
 	.tlb_flush_leaf = qcom_iommu_tlb_flush_leaf,
 	.tlb_add_page	= qcom_iommu_tlb_add_page,
-	.tlb_sync	= qcom_iommu_tlb_sync,
 };
 
 static irqreturn_t qcom_iommu_fault(int irq, void *dev)
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 99e04bd2baa1..843310484fe2 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -30,9 +30,6 @@ enum io_pgtable_fmt {
  *                  for IOMMUs that cannot batch TLB invalidation operations
  *                  efficiently and are therefore better suited to issuing them
  *                  early rather than deferring them until iommu_tlb_sync().
- * @tlb_sync:       Ensure any queued TLB invalidation has taken effect, and
- *                  any corresponding page table updates are visible to the
- *                  IOMMU.
  *
  * Note that these can all be called in atomic context and must therefore
  * not block.
@@ -44,7 +41,6 @@ struct iommu_flush_ops {
 	void (*tlb_flush_leaf)(unsigned long iova, size_t size, size_t granule,
 			       void *cookie);
 	void (*tlb_add_page)(unsigned long iova, size_t granule, void *cookie);
-	void (*tlb_sync)(void *cookie);
 };
 
 /**
@@ -218,11 +214,6 @@ io_pgtable_tlb_add_page(struct io_pgtable *iop, unsigned long iova,
 		iop->cfg.tlb->tlb_add_page(iova, granule, iop->cookie);
 }
 
-static inline void io_pgtable_tlb_sync(struct io_pgtable *iop)
-{
-	iop->cfg.tlb->tlb_sync(iop->cookie);
-}
-
 /**
  * struct io_pgtable_init_fns - Alloc/free a set of page tables for a
  *                              particular format.
-- 
cgit v1.3-14-g43fede


From a2d3a382d6c682e22b263c9e7f0d857c3fa6c9d6 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 2 Jul 2019 16:44:58 +0100
Subject: iommu/io-pgtable: Pass struct iommu_iotlb_gather to ->unmap()

Update the io-pgtable ->unmap() function to take an iommu_iotlb_gather
pointer as an argument, and update the callers as appropriate.

Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/gpu/drm/panfrost/panfrost_mmu.c | 2 +-
 drivers/iommu/arm-smmu-v3.c             | 2 +-
 drivers/iommu/arm-smmu.c                | 2 +-
 drivers/iommu/io-pgtable-arm-v7s.c      | 6 +++---
 drivers/iommu/io-pgtable-arm.c          | 7 +++----
 drivers/iommu/ipmmu-vmsa.c              | 2 +-
 drivers/iommu/msm_iommu.c               | 2 +-
 drivers/iommu/mtk_iommu.c               | 2 +-
 drivers/iommu/qcom_iommu.c              | 2 +-
 include/linux/io-pgtable.h              | 4 +++-
 10 files changed, 16 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index de22a2276e00..6e8145c36e93 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -222,7 +222,7 @@ void panfrost_mmu_unmap(struct panfrost_gem_object *bo)
 		size_t unmapped_page;
 		size_t pgsize = get_pgsize(iova, len - unmapped_len);
 
-		unmapped_page = ops->unmap(ops, iova, pgsize);
+		unmapped_page = ops->unmap(ops, iova, pgsize, NULL);
 		if (!unmapped_page)
 			break;
 
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 231093413ff9..8e2e53079f48 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -2015,7 +2015,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 	if (!ops)
 		return 0;
 
-	ret = ops->unmap(ops, iova, size);
+	ret = ops->unmap(ops, iova, size, gather);
 	if (ret && arm_smmu_atc_inv_domain(smmu_domain, 0, iova, size))
 		return 0;
 
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 07a267c437d6..f6689956ab6e 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1362,7 +1362,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 		return 0;
 
 	arm_smmu_rpm_get(smmu);
-	ret = ops->unmap(ops, iova, size);
+	ret = ops->unmap(ops, iova, size, gather);
 	arm_smmu_rpm_put(smmu);
 
 	return ret;
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 203894fb6765..a7776e982b6c 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -666,7 +666,7 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
 }
 
 static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
-			    size_t size)
+			    size_t size, struct iommu_iotlb_gather *gather)
 {
 	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
 
@@ -892,7 +892,7 @@ static int __init arm_v7s_do_selftests(void)
 	size = 1UL << __ffs(cfg.pgsize_bitmap);
 	while (i < loopnr) {
 		iova_start = i * SZ_16M;
-		if (ops->unmap(ops, iova_start + size, size) != size)
+		if (ops->unmap(ops, iova_start + size, size, NULL) != size)
 			return __FAIL(ops);
 
 		/* Remap of partial unmap */
@@ -910,7 +910,7 @@ static int __init arm_v7s_do_selftests(void)
 	for_each_set_bit(i, &cfg.pgsize_bitmap, BITS_PER_LONG) {
 		size = 1UL << i;
 
-		if (ops->unmap(ops, iova, size) != size)
+		if (ops->unmap(ops, iova, size, NULL) != size)
 			return __FAIL(ops);
 
 		if (ops->iova_to_phys(ops, iova + 42))
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index f35516744965..325430f8a0a1 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -12,7 +12,6 @@
 #include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/io-pgtable.h>
-#include <linux/iommu.h>
 #include <linux/kernel.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
@@ -642,7 +641,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 }
 
 static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
-			     size_t size)
+			     size_t size, struct iommu_iotlb_gather *gather)
 {
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	arm_lpae_iopte *ptep = data->pgd;
@@ -1167,7 +1166,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 
 		/* Partial unmap */
 		size = 1UL << __ffs(cfg->pgsize_bitmap);
-		if (ops->unmap(ops, SZ_1G + size, size) != size)
+		if (ops->unmap(ops, SZ_1G + size, size, NULL) != size)
 			return __FAIL(ops, i);
 
 		/* Remap of partial unmap */
@@ -1182,7 +1181,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 		for_each_set_bit(j, &cfg->pgsize_bitmap, BITS_PER_LONG) {
 			size = 1UL << j;
 
-			if (ops->unmap(ops, iova, size) != size)
+			if (ops->unmap(ops, iova, size, NULL) != size)
 				return __FAIL(ops, i);
 
 			if (ops->iova_to_phys(ops, iova + 42))
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index a2b8eff4c1f7..76a8ec343d53 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -737,7 +737,7 @@ static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova,
 {
 	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
 
-	return domain->iop->unmap(domain->iop, iova, size);
+	return domain->iop->unmap(domain->iop, iova, size, gather);
 }
 
 static void ipmmu_flush_iotlb_all(struct iommu_domain *io_domain)
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index ccfc7ed230ef..8a0dcaf0a9e9 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -523,7 +523,7 @@ static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 	unsigned long flags;
 
 	spin_lock_irqsave(&priv->pgtlock, flags);
-	len = priv->iop->unmap(priv->iop, iova, len);
+	len = priv->iop->unmap(priv->iop, iova, len, gather);
 	spin_unlock_irqrestore(&priv->pgtlock, flags);
 
 	return len;
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 3785750bdb44..b73cffd63262 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -400,7 +400,7 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain,
 	size_t unmapsz;
 
 	spin_lock_irqsave(&dom->pgtlock, flags);
-	unmapsz = dom->iop->unmap(dom->iop, iova, size);
+	unmapsz = dom->iop->unmap(dom->iop, iova, size, gather);
 	spin_unlock_irqrestore(&dom->pgtlock, flags);
 
 	return unmapsz;
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 0b8a6d6bb475..48b288ef74b4 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -455,7 +455,7 @@ static size_t qcom_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 	 */
 	pm_runtime_get_sync(qcom_domain->iommu->dev);
 	spin_lock_irqsave(&qcom_domain->pgtbl_lock, flags);
-	ret = ops->unmap(ops, iova, size);
+	ret = ops->unmap(ops, iova, size, gather);
 	spin_unlock_irqrestore(&qcom_domain->pgtbl_lock, flags);
 	pm_runtime_put_sync(qcom_domain->iommu->dev);
 
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 843310484fe2..fe27d93c8ad9 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -1,7 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __IO_PGTABLE_H
 #define __IO_PGTABLE_H
+
 #include <linux/bitops.h>
+#include <linux/iommu.h>
 
 /*
  * Public API for use by IOMMU drivers
@@ -136,7 +138,7 @@ struct io_pgtable_ops {
 	int (*map)(struct io_pgtable_ops *ops, unsigned long iova,
 		   phys_addr_t paddr, size_t size, int prot);
 	size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova,
-			size_t size);
+			size_t size, struct iommu_iotlb_gather *gather);
 	phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops,
 				    unsigned long iova);
 };
-- 
cgit v1.3-14-g43fede


From 3951c41af4a65ba418e6b1b973d398552bedb84f Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 2 Jul 2019 16:45:15 +0100
Subject: iommu/io-pgtable: Pass struct iommu_iotlb_gather to ->tlb_add_page()

With all the pieces in place, we can finally propagate the
iommu_iotlb_gather structure from the call to unmap() down to the IOMMU
drivers' implementation of ->tlb_add_page(). Currently everybody ignores
it, but the machinery is now there to defer invalidation.

Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu-v3.c        |  3 ++-
 drivers/iommu/arm-smmu.c           |  3 ++-
 drivers/iommu/io-pgtable-arm-v7s.c | 23 ++++++++++++++---------
 drivers/iommu/io-pgtable-arm.c     | 22 ++++++++++++++--------
 drivers/iommu/msm_iommu.c          |  3 ++-
 drivers/iommu/mtk_iommu.c          |  3 ++-
 drivers/iommu/qcom_iommu.c         |  3 ++-
 include/linux/io-pgtable.h         | 16 +++++++++-------
 8 files changed, 47 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 8e2e53079f48..d1ebc7103065 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1596,7 +1596,8 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
 	} while (size -= granule);
 }
 
-static void arm_smmu_tlb_inv_page_nosync(unsigned long iova, size_t granule,
+static void arm_smmu_tlb_inv_page_nosync(struct iommu_iotlb_gather *gather,
+					 unsigned long iova, size_t granule,
 					 void *cookie)
 {
 	arm_smmu_tlb_inv_range_nosync(iova, granule, granule, true, cookie);
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index f6689956ab6e..5598d0ff71a8 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -574,7 +574,8 @@ static void arm_smmu_tlb_inv_leaf(unsigned long iova, size_t size,
 	ops->tlb_sync(cookie);
 }
 
-static void arm_smmu_tlb_add_page(unsigned long iova, size_t granule,
+static void arm_smmu_tlb_add_page(struct iommu_iotlb_gather *gather,
+				  unsigned long iova, size_t granule,
 				  void *cookie)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index a7776e982b6c..18e7d212c7de 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -362,7 +362,8 @@ static bool arm_v7s_pte_is_cont(arm_v7s_iopte pte, int lvl)
 	return false;
 }
 
-static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *, unsigned long,
+static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *,
+			      struct iommu_iotlb_gather *, unsigned long,
 			      size_t, int, arm_v7s_iopte *);
 
 static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data,
@@ -383,7 +384,7 @@ static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data,
 			size_t sz = ARM_V7S_BLOCK_SIZE(lvl);
 
 			tblp = ptep - ARM_V7S_LVL_IDX(iova, lvl);
-			if (WARN_ON(__arm_v7s_unmap(data, iova + i * sz,
+			if (WARN_ON(__arm_v7s_unmap(data, NULL, iova + i * sz,
 						    sz, lvl, tblp) != sz))
 				return -EINVAL;
 		} else if (ptep[i]) {
@@ -545,6 +546,7 @@ static arm_v7s_iopte arm_v7s_split_cont(struct arm_v7s_io_pgtable *data,
 }
 
 static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
+				      struct iommu_iotlb_gather *gather,
 				      unsigned long iova, size_t size,
 				      arm_v7s_iopte blk_pte,
 				      arm_v7s_iopte *ptep)
@@ -581,14 +583,15 @@ static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
 			return 0;
 
 		tablep = iopte_deref(pte, 1);
-		return __arm_v7s_unmap(data, iova, size, 2, tablep);
+		return __arm_v7s_unmap(data, gather, iova, size, 2, tablep);
 	}
 
-	io_pgtable_tlb_add_page(&data->iop, iova, size);
+	io_pgtable_tlb_add_page(&data->iop, gather, iova, size);
 	return size;
 }
 
 static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
+			      struct iommu_iotlb_gather *gather,
 			      unsigned long iova, size_t size, int lvl,
 			      arm_v7s_iopte *ptep)
 {
@@ -647,7 +650,7 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
 				 */
 				smp_wmb();
 			} else {
-				io_pgtable_tlb_add_page(iop, iova, blk_size);
+				io_pgtable_tlb_add_page(iop, gather, iova, blk_size);
 			}
 			iova += blk_size;
 		}
@@ -657,12 +660,13 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
 		 * Insert a table at the next level to map the old region,
 		 * minus the part we want to unmap
 		 */
-		return arm_v7s_split_blk_unmap(data, iova, size, pte[0], ptep);
+		return arm_v7s_split_blk_unmap(data, gather, iova, size, pte[0],
+					       ptep);
 	}
 
 	/* Keep on walkin' */
 	ptep = iopte_deref(pte[0], lvl);
-	return __arm_v7s_unmap(data, iova, size, lvl + 1, ptep);
+	return __arm_v7s_unmap(data, gather, iova, size, lvl + 1, ptep);
 }
 
 static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
@@ -673,7 +677,7 @@ static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 	if (WARN_ON(upper_32_bits(iova)))
 		return 0;
 
-	return __arm_v7s_unmap(data, iova, size, 1, data->pgd);
+	return __arm_v7s_unmap(data, gather, iova, size, 1, data->pgd);
 }
 
 static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops,
@@ -808,7 +812,8 @@ static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule,
 	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
 }
 
-static void dummy_tlb_add_page(unsigned long iova, size_t granule, void *cookie)
+static void dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
+			       unsigned long iova, size_t granule, void *cookie)
 {
 	dummy_tlb_flush(iova, granule, granule, cookie);
 }
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 325430f8a0a1..4c91359057c5 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -289,6 +289,7 @@ static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte,
 }
 
 static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
+			       struct iommu_iotlb_gather *gather,
 			       unsigned long iova, size_t size, int lvl,
 			       arm_lpae_iopte *ptep);
 
@@ -334,8 +335,10 @@ static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
 		size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
 
 		tblp = ptep - ARM_LPAE_LVL_IDX(iova, lvl, data);
-		if (WARN_ON(__arm_lpae_unmap(data, iova, sz, lvl, tblp) != sz))
+		if (__arm_lpae_unmap(data, NULL, iova, sz, lvl, tblp) != sz) {
+			WARN_ON(1);
 			return -EINVAL;
+		}
 	}
 
 	__arm_lpae_init_pte(data, paddr, prot, lvl, ptep);
@@ -536,6 +539,7 @@ static void arm_lpae_free_pgtable(struct io_pgtable *iop)
 }
 
 static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
+				       struct iommu_iotlb_gather *gather,
 				       unsigned long iova, size_t size,
 				       arm_lpae_iopte blk_pte, int lvl,
 				       arm_lpae_iopte *ptep)
@@ -581,14 +585,15 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 
 		tablep = iopte_deref(pte, data);
 	} else if (unmap_idx >= 0) {
-		io_pgtable_tlb_add_page(&data->iop, iova, size);
+		io_pgtable_tlb_add_page(&data->iop, gather, iova, size);
 		return size;
 	}
 
-	return __arm_lpae_unmap(data, iova, size, lvl, tablep);
+	return __arm_lpae_unmap(data, gather, iova, size, lvl, tablep);
 }
 
 static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
+			       struct iommu_iotlb_gather *gather,
 			       unsigned long iova, size_t size, int lvl,
 			       arm_lpae_iopte *ptep)
 {
@@ -622,7 +627,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 			 */
 			smp_wmb();
 		} else {
-			io_pgtable_tlb_add_page(iop, iova, size);
+			io_pgtable_tlb_add_page(iop, gather, iova, size);
 		}
 
 		return size;
@@ -631,13 +636,13 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 		 * Insert a table at the next level to map the old region,
 		 * minus the part we want to unmap
 		 */
-		return arm_lpae_split_blk_unmap(data, iova, size, pte,
+		return arm_lpae_split_blk_unmap(data, gather, iova, size, pte,
 						lvl + 1, ptep);
 	}
 
 	/* Keep on walkin' */
 	ptep = iopte_deref(pte, data);
-	return __arm_lpae_unmap(data, iova, size, lvl + 1, ptep);
+	return __arm_lpae_unmap(data, gather, iova, size, lvl + 1, ptep);
 }
 
 static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
@@ -650,7 +655,7 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias)))
 		return 0;
 
-	return __arm_lpae_unmap(data, iova, size, lvl, ptep);
+	return __arm_lpae_unmap(data, gather, iova, size, lvl, ptep);
 }
 
 static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
@@ -1074,7 +1079,8 @@ static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule,
 	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
 }
 
-static void dummy_tlb_add_page(unsigned long iova, size_t granule, void *cookie)
+static void dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
+			       unsigned long iova, size_t granule, void *cookie)
 {
 	dummy_tlb_flush(iova, granule, granule, cookie);
 }
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 8a0dcaf0a9e9..4c0be5b75c28 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -180,7 +180,8 @@ static void __flush_iotlb_leaf(unsigned long iova, size_t size,
 	__flush_iotlb_range(iova, size, granule, true, cookie);
 }
 
-static void __flush_iotlb_page(unsigned long iova, size_t granule, void *cookie)
+static void __flush_iotlb_page(struct iommu_iotlb_gather *gather,
+			       unsigned long iova, size_t granule, void *cookie)
 {
 	__flush_iotlb_range(iova, granule, granule, true, cookie);
 }
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index b73cffd63262..0827d51936fa 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -202,7 +202,8 @@ static void mtk_iommu_tlb_flush_leaf(unsigned long iova, size_t size,
 	mtk_iommu_tlb_sync(cookie);
 }
 
-static void mtk_iommu_tlb_flush_page_nosync(unsigned long iova, size_t granule,
+static void mtk_iommu_tlb_flush_page_nosync(struct iommu_iotlb_gather *gather,
+					    unsigned long iova, size_t granule,
 					    void *cookie)
 {
 	mtk_iommu_tlb_add_flush_nosync(iova, granule, granule, true, cookie);
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 48b288ef74b4..eac760cdbb28 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -178,7 +178,8 @@ static void qcom_iommu_tlb_flush_leaf(unsigned long iova, size_t size,
 	qcom_iommu_tlb_sync(cookie);
 }
 
-static void qcom_iommu_tlb_add_page(unsigned long iova, size_t granule,
+static void qcom_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
+				    unsigned long iova, size_t granule,
 				    void *cookie)
 {
 	qcom_iommu_tlb_inv_range_nosync(iova, granule, granule, true, cookie);
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index fe27d93c8ad9..6b1b8be3ebec 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -28,10 +28,10 @@ enum io_pgtable_fmt {
  * @tlb_flush_leaf: Synchronously invalidate all leaf TLB state for a virtual
  *                  address range.
  * @tlb_add_page:   Optional callback to queue up leaf TLB invalidation for a
- *                  single page. This function exists purely as an optimisation
- *                  for IOMMUs that cannot batch TLB invalidation operations
- *                  efficiently and are therefore better suited to issuing them
- *                  early rather than deferring them until iommu_tlb_sync().
+ *                  single page.  IOMMUs that cannot batch TLB invalidation
+ *                  operations efficiently will typically issue them here, but
+ *                  others may decide to update the iommu_iotlb_gather structure
+ *                  and defer the invalidation until iommu_tlb_sync() instead.
  *
  * Note that these can all be called in atomic context and must therefore
  * not block.
@@ -42,7 +42,8 @@ struct iommu_flush_ops {
 			       void *cookie);
 	void (*tlb_flush_leaf)(unsigned long iova, size_t size, size_t granule,
 			       void *cookie);
-	void (*tlb_add_page)(unsigned long iova, size_t granule, void *cookie);
+	void (*tlb_add_page)(struct iommu_iotlb_gather *gather,
+			     unsigned long iova, size_t granule, void *cookie);
 };
 
 /**
@@ -209,11 +210,12 @@ io_pgtable_tlb_flush_leaf(struct io_pgtable *iop, unsigned long iova,
 }
 
 static inline void
-io_pgtable_tlb_add_page(struct io_pgtable *iop, unsigned long iova,
+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)
-		iop->cfg.tlb->tlb_add_page(iova, granule, iop->cookie);
+		iop->cfg.tlb->tlb_add_page(gather, iova, granule, iop->cookie);
 }
 
 /**
-- 
cgit v1.3-14-g43fede


From b9c6ff94e43a0ee053e0c1d983fba1ac4953b762 Mon Sep 17 00:00:00 2001
From: "Suthikulpanit, Suravee" <Suravee.Suthikulpanit@amd.com>
Date: Tue, 23 Jul 2019 19:00:37 +0000
Subject: iommu/amd: Re-factor guest virtual APIC (de-)activation code

Re-factore the logic for activate/deactivate guest virtual APIC mode (GAM)
into helper functions, and export them for other drivers (e.g. SVM).
to support run-time activate/deactivate of SVM AVIC.

Cc: Joerg Roedel <joro@8bytes.org>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd_iommu.c       | 85 +++++++++++++++++++++++++++++------------
 drivers/iommu/amd_iommu_types.h |  9 +++++
 include/linux/amd-iommu.h       | 12 ++++++
 3 files changed, 82 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index b607a92791d3..008da21a2592 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -4313,13 +4313,62 @@ static const struct irq_domain_ops amd_ir_domain_ops = {
 	.deactivate = irq_remapping_deactivate,
 };
 
+int amd_iommu_activate_guest_mode(void *data)
+{
+	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
+	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+
+	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
+	    !entry || entry->lo.fields_vapic.guest_mode)
+		return 0;
+
+	entry->lo.val = 0;
+	entry->hi.val = 0;
+
+	entry->lo.fields_vapic.guest_mode  = 1;
+	entry->lo.fields_vapic.ga_log_intr = 1;
+	entry->hi.fields.ga_root_ptr       = ir_data->ga_root_ptr;
+	entry->hi.fields.vector            = ir_data->ga_vector;
+	entry->lo.fields_vapic.ga_tag      = ir_data->ga_tag;
+
+	return modify_irte_ga(ir_data->irq_2_irte.devid,
+			      ir_data->irq_2_irte.index, entry, NULL);
+}
+EXPORT_SYMBOL(amd_iommu_activate_guest_mode);
+
+int amd_iommu_deactivate_guest_mode(void *data)
+{
+	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
+	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+	struct irq_cfg *cfg = ir_data->cfg;
+
+	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
+	    !entry || !entry->lo.fields_vapic.guest_mode)
+		return 0;
+
+	entry->lo.val = 0;
+	entry->hi.val = 0;
+
+	entry->lo.fields_remap.dm          = apic->irq_dest_mode;
+	entry->lo.fields_remap.int_type    = apic->irq_delivery_mode;
+	entry->hi.fields.vector            = cfg->vector;
+	entry->lo.fields_remap.destination =
+				APICID_TO_IRTE_DEST_LO(cfg->dest_apicid);
+	entry->hi.fields.destination =
+				APICID_TO_IRTE_DEST_HI(cfg->dest_apicid);
+
+	return modify_irte_ga(ir_data->irq_2_irte.devid,
+			      ir_data->irq_2_irte.index, entry, NULL);
+}
+EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode);
+
 static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 {
+	int ret;
 	struct amd_iommu *iommu;
 	struct amd_iommu_pi_data *pi_data = vcpu_info;
 	struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data;
 	struct amd_ir_data *ir_data = data->chip_data;
-	struct irte_ga *irte = (struct irte_ga *) ir_data->entry;
 	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
 	struct iommu_dev_data *dev_data = search_dev_data(irte_info->devid);
 
@@ -4330,6 +4379,7 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 	if (!dev_data || !dev_data->use_vapic)
 		return 0;
 
+	ir_data->cfg = irqd_cfg(data);
 	pi_data->ir_data = ir_data;
 
 	/* Note:
@@ -4348,37 +4398,24 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 
 	pi_data->prev_ga_tag = ir_data->cached_ga_tag;
 	if (pi_data->is_guest_mode) {
-		/* Setting */
-		irte->hi.fields.ga_root_ptr = (pi_data->base >> 12);
-		irte->hi.fields.vector = vcpu_pi_info->vector;
-		irte->lo.fields_vapic.ga_log_intr = 1;
-		irte->lo.fields_vapic.guest_mode = 1;
-		irte->lo.fields_vapic.ga_tag = pi_data->ga_tag;
-
-		ir_data->cached_ga_tag = pi_data->ga_tag;
+		ir_data->ga_root_ptr = (pi_data->base >> 12);
+		ir_data->ga_vector = vcpu_pi_info->vector;
+		ir_data->ga_tag = pi_data->ga_tag;
+		ret = amd_iommu_activate_guest_mode(ir_data);
+		if (!ret)
+			ir_data->cached_ga_tag = pi_data->ga_tag;
 	} else {
-		/* Un-Setting */
-		struct irq_cfg *cfg = irqd_cfg(data);
-
-		irte->hi.val = 0;
-		irte->lo.val = 0;
-		irte->hi.fields.vector = cfg->vector;
-		irte->lo.fields_remap.guest_mode = 0;
-		irte->lo.fields_remap.destination =
-				APICID_TO_IRTE_DEST_LO(cfg->dest_apicid);
-		irte->hi.fields.destination =
-				APICID_TO_IRTE_DEST_HI(cfg->dest_apicid);
-		irte->lo.fields_remap.int_type = apic->irq_delivery_mode;
-		irte->lo.fields_remap.dm = apic->irq_dest_mode;
+		ret = amd_iommu_deactivate_guest_mode(ir_data);
 
 		/*
 		 * This communicates the ga_tag back to the caller
 		 * so that it can do all the necessary clean up.
 		 */
-		ir_data->cached_ga_tag = 0;
+		if (!ret)
+			ir_data->cached_ga_tag = 0;
 	}
 
-	return modify_irte_ga(irte_info->devid, irte_info->index, irte, ir_data);
+	return ret;
 }
 
 
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 64edd5a9694c..9ac229e92b07 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -873,6 +873,15 @@ struct amd_ir_data {
 	struct msi_msg msi_entry;
 	void *entry;    /* Pointer to union irte or struct irte_ga */
 	void *ref;      /* Pointer to the actual irte */
+
+	/**
+	 * Store information for activate/de-activate
+	 * Guest virtual APIC mode during runtime.
+	 */
+	struct irq_cfg *cfg;
+	int ga_vector;
+	int ga_root_ptr;
+	int ga_tag;
 };
 
 struct amd_irte_ops {
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index 4a4d00646040..21e950e4ab62 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -184,6 +184,9 @@ extern int amd_iommu_register_ga_log_notifier(int (*notifier)(u32));
 extern int
 amd_iommu_update_ga(int cpu, bool is_run, void *data);
 
+extern int amd_iommu_activate_guest_mode(void *data);
+extern int amd_iommu_deactivate_guest_mode(void *data);
+
 #else /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */
 
 static inline int
@@ -198,6 +201,15 @@ amd_iommu_update_ga(int cpu, bool is_run, void *data)
 	return 0;
 }
 
+static inline int amd_iommu_activate_guest_mode(void *data)
+{
+	return 0;
+}
+
+static inline int amd_iommu_deactivate_guest_mode(void *data)
+{
+	return 0;
+}
 #endif /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */
 
 #endif /* _ASM_X86_AMD_IOMMU_H */
-- 
cgit v1.3-14-g43fede


From 3846a3b9511c5166082a93536d919a9c42abcd91 Mon Sep 17 00:00:00 2001
From: Suman Anna <s-anna@ti.com>
Date: Wed, 7 Aug 2019 11:26:45 +0300
Subject: iommu/omap: fix boot issue on remoteprocs with AMMU/Unicache

Support has been added to the OMAP IOMMU driver to fix a boot hang
issue on OMAP remoteprocs with AMMU/Unicache, caused by an improper
AMMU/Unicache state upon initial deassertion of the processor reset.
The issue is described in detail in the next three paragraphs.

All the Cortex M3/M4 IPU processor subsystems in OMAP SoCs have a
AMMU/Unicache IP that dictates the memory attributes for addresses
seen by the processor cores. The AMMU/Unicache is configured/enabled
by the SCACHE_CONFIG.BYPASS bit - a value of 1 enables the cache and
mandates all addresses accessed by M3/M4 be defined in the AMMU. This
bit is not programmable from the host processor. The M3/M4 boot
sequence starts out with the AMMU/Unicache in disabled state, and
SYS/BIOS programs the AMMU regions and enables the Unicache during
one of its initial boot steps. This SCACHE_CONFIG.BYPASS bit is
however enabled by default whenever a RET reset is applied to the IP,
irrespective of whether it was previously enabled or not. The AMMU
registers lose their context whenever this reset is applied. The reset
is effective as long as the MMU portion of the subsystem is enabled
and clocked. This behavior is common to all the IPU and DSP subsystems
that have an AMMU/Unicache.

The IPU boot sequence involves enabling and programming the MMU, and
loading the processor and releasing the reset(s) for the processor.
The PM setup code currently sets the target state for most of the
power domains to RET. The L2 MMU can be enabled, programmed and
accessed properly just fine with the domain in hardware supervised
mode, while the power domain goes through a RET->ON->RET transition
during the programming sequence. However, the ON->RET transition
asserts a RET reset, and the SCACHE_CONFIG.BYPASS bit gets auto-set.
An AMMU fault is thrown immediately when the M3/M4 core's reset is
released since the first instruction address itself will not be
defined in any valid AMMU regions. The ON->RET transition happens
automatically on the power domain after enabling the iommu due to
the hardware supervised mode.

This patch adds and invokes the .set_pwrdm_constraint pdata ops, if
present, during the OMAP IOMMU enable and disable functions to resolve
the above boot hang issue. The ops will allow to invoke a mach-omap2
layer API pwrdm_set_next_pwrst() in a multi-arch kernel environment.
The ops also returns the current power domain state while enforcing
the constraint so that the driver can store it and use it to set back
the power domain state while releasing the constraint. The pdata ops
implementation restricts the target power domain to ON during enable,
and back to the original power domain state during disable, and thereby
eliminating the conditions for the boot issue. The implementation is
effective only when the original power domain state is either RET or
OFF, and is a no-op when it is ON or INACTIVE.

The .set_pwrdm_constraint ops need to be plugged in pdata-quirks
for the affected remote processors to be able to boot properly.

Note that the current issue is seen only on kernels with the affected
power domains programmed to enter RET. For eg., IPU1 on DRA7xx is in a
separate domain and is susceptible to this bug, while the IPU2 subsystem
is within CORE power domain, and CORE RET is not supported on this SoC.
IPUs on OMAP4 and OMAP5 are also susceptible since they are in CORE power
domain, and CORE RET is a valid power target on these SoCs.

Signed-off-by: Suman Anna <s-anna@ti.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 arch/arm/mach-omap2/Makefile             |  2 ++
 arch/arm/mach-omap2/omap-iommu.c         | 43 ++++++++++++++++++++++++++++++++
 drivers/iommu/omap-iommu.c               | 17 +++++++++++++
 drivers/iommu/omap-iommu.h               |  2 ++
 include/linux/platform_data/iommu-omap.h |  2 ++
 5 files changed, 66 insertions(+)
 create mode 100644 arch/arm/mach-omap2/omap-iommu.c

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 600650551621..d4f11c5070ae 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -229,3 +229,5 @@ include/generated/ti-pm-asm-offsets.h: arch/arm/mach-omap2/pm-asm-offsets.s FORC
 $(obj)/sleep33xx.o $(obj)/sleep43xx.o: include/generated/ti-pm-asm-offsets.h
 
 targets += pm-asm-offsets.s
+
+obj-$(CONFIG_OMAP_IOMMU)		+= omap-iommu.o
diff --git a/arch/arm/mach-omap2/omap-iommu.c b/arch/arm/mach-omap2/omap-iommu.c
new file mode 100644
index 000000000000..f1a6ece8108e
--- /dev/null
+++ b/arch/arm/mach-omap2/omap-iommu.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * OMAP IOMMU quirks for various TI SoCs
+ *
+ * Copyright (C) 2015-2019 Texas Instruments Incorporated - http://www.ti.com/
+ *      Suman Anna <s-anna@ti.com>
+ */
+
+#include <linux/platform_device.h>
+#include <linux/err.h>
+
+#include "omap_hwmod.h"
+#include "omap_device.h"
+#include "powerdomain.h"
+
+int omap_iommu_set_pwrdm_constraint(struct platform_device *pdev, bool request,
+				    u8 *pwrst)
+{
+	struct powerdomain *pwrdm;
+	struct omap_device *od;
+	u8 next_pwrst;
+
+	od = to_omap_device(pdev);
+	if (!od)
+		return -ENODEV;
+
+	if (od->hwmods_cnt != 1)
+		return -EINVAL;
+
+	pwrdm = omap_hwmod_get_pwrdm(od->hwmods[0]);
+	if (!pwrdm)
+		return -EINVAL;
+
+	if (request)
+		*pwrst = pwrdm_read_next_pwrst(pwrdm);
+
+	if (*pwrst > PWRDM_POWER_RET)
+		return 0;
+
+	next_pwrst = request ? PWRDM_POWER_ON : *pwrst;
+
+	return pwrdm_set_next_pwrst(pwrdm, next_pwrst);
+}
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index dfb961d8c21b..84b99d5841ae 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -190,6 +190,14 @@ static int iommu_enable(struct omap_iommu *obj)
 	struct platform_device *pdev = to_platform_device(obj->dev);
 	struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev);
 
+	if (pdata && pdata->set_pwrdm_constraint) {
+		err = pdata->set_pwrdm_constraint(pdev, true, &obj->pwrst);
+		if (err) {
+			dev_warn(obj->dev, "pwrdm_constraint failed to be set, status = %d\n",
+				 err);
+		}
+	}
+
 	if (pdata && pdata->deassert_reset) {
 		err = pdata->deassert_reset(pdev, pdata->reset_name);
 		if (err) {
@@ -209,6 +217,7 @@ static void iommu_disable(struct omap_iommu *obj)
 {
 	struct platform_device *pdev = to_platform_device(obj->dev);
 	struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	int ret;
 
 	omap2_iommu_disable(obj);
 
@@ -216,6 +225,14 @@ static void iommu_disable(struct omap_iommu *obj)
 
 	if (pdata && pdata->assert_reset)
 		pdata->assert_reset(pdev, pdata->reset_name);
+
+	if (pdata && pdata->set_pwrdm_constraint) {
+		ret = pdata->set_pwrdm_constraint(pdev, false, &obj->pwrst);
+		if (ret) {
+			dev_warn(obj->dev, "pwrdm_constraint failed to be reset, status = %d\n",
+				 ret);
+		}
+	}
 }
 
 /*
diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h
index 09968a02d291..aac1ca65ef9d 100644
--- a/drivers/iommu/omap-iommu.h
+++ b/drivers/iommu/omap-iommu.h
@@ -78,6 +78,8 @@ struct omap_iommu {
 
 	struct iommu_device iommu;
 	struct iommu_group *group;
+
+	u8 pwrst;
 };
 
 /**
diff --git a/include/linux/platform_data/iommu-omap.h b/include/linux/platform_data/iommu-omap.h
index 44d913a7580c..1ed60265a20e 100644
--- a/include/linux/platform_data/iommu-omap.h
+++ b/include/linux/platform_data/iommu-omap.h
@@ -13,4 +13,6 @@ struct iommu_platform_data {
 	const char *reset_name;
 	int (*assert_reset)(struct platform_device *pdev, const char *name);
 	int (*deassert_reset)(struct platform_device *pdev, const char *name);
+	int (*set_pwrdm_constraint)(struct platform_device *pdev, bool request,
+				    u8 *pwrst);
 };
-- 
cgit v1.3-14-g43fede


From 74c116df66d25a9fb48d44ce545a505edc5fbbba Mon Sep 17 00:00:00 2001
From: Suman Anna <s-anna@ti.com>
Date: Wed, 7 Aug 2019 11:26:46 +0300
Subject: iommu/omap: add pdata ops for omap_device_enable/idle

Add two new platform data ops to allow the OMAP iommu driver to
be able to invoke the omap_device_enable and omap_device_idle
from within the driver. These are being added to streamline the
sequence between managing the hard reset lines and the clocks
during the suspend path, as the default device pm_domain callback
sequences in omap_device layer are not conducive for the OMAP
IOMMU driver.

This could have been done by expanding the existing pdata ops
for reset management (like in the OMAP remoteproc driver), but
this was chosen to avoid adding additional code in the separate
file in the mach-omap2 layer.

Signed-off-by: Suman Anna <s-anna@ti.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/linux/platform_data/iommu-omap.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/iommu-omap.h b/include/linux/platform_data/iommu-omap.h
index 1ed60265a20e..8474a0208b34 100644
--- a/include/linux/platform_data/iommu-omap.h
+++ b/include/linux/platform_data/iommu-omap.h
@@ -13,6 +13,8 @@ struct iommu_platform_data {
 	const char *reset_name;
 	int (*assert_reset)(struct platform_device *pdev, const char *name);
 	int (*deassert_reset)(struct platform_device *pdev, const char *name);
+	int (*device_enable)(struct platform_device *pdev);
+	int (*device_idle)(struct platform_device *pdev);
 	int (*set_pwrdm_constraint)(struct platform_device *pdev, bool request,
 				    u8 *pwrst);
 };
-- 
cgit v1.3-14-g43fede


From d9c4d8a6cc0f852adf3829fbe40e2e3f6213b0c6 Mon Sep 17 00:00:00 2001
From: Suman Anna <s-anna@ti.com>
Date: Wed, 7 Aug 2019 11:26:50 +0300
Subject: iommu/omap: introduce new API for runtime suspend/resume control

This patch adds the support for the OMAP IOMMUs to be suspended
during the auto suspend/resume of the OMAP remoteproc devices. The
remote processors are auto suspended after a certain time of idle
or inactivity period. This is done by introducing two new API,
omap_iommu_domain_deactivate() and omap_iommu_domain_activate()
to allow the client users/master devices of the IOMMU devices to
deactivate & activate the IOMMU devices from their runtime
suspend/resume operations. There is no API exposed by the IOMMU
layer at present, and so these new API are added directly in the
OMAP IOMMU driver to minimize framework changes.

The API simply decrements and increments the runtime usage count
of the IOMMU devices and let the context be saved/restored using
the existing runtime pm callbacks.

Signed-off-by: Suman Anna <s-anna@ti.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/omap-iommu.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/omap-iommu.h |  8 +++++++
 2 files changed, 66 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index ef62ac9057bb..ecf14001beed 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -938,6 +938,64 @@ static void omap_iommu_restore_tlb_entries(struct omap_iommu *obj)
 	iotlb_lock_set(obj, &l);
 }
 
+/**
+ * omap_iommu_domain_deactivate - deactivate attached iommu devices
+ * @domain: iommu domain attached to the target iommu device
+ *
+ * This API allows the client devices of IOMMU devices to suspend
+ * the IOMMUs they control at runtime, after they are idled and
+ * suspended all activity. System Suspend will leverage the PM
+ * driver late callbacks.
+ **/
+int omap_iommu_domain_deactivate(struct iommu_domain *domain)
+{
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+	struct omap_iommu_device *iommu;
+	struct omap_iommu *oiommu;
+	int i;
+
+	if (!omap_domain->dev)
+		return 0;
+
+	iommu = omap_domain->iommus;
+	iommu += (omap_domain->num_iommus - 1);
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu--) {
+		oiommu = iommu->iommu_dev;
+		pm_runtime_put_sync(oiommu->dev);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(omap_iommu_domain_deactivate);
+
+/**
+ * omap_iommu_domain_activate - activate attached iommu devices
+ * @domain: iommu domain attached to the target iommu device
+ *
+ * This API allows the client devices of IOMMU devices to resume the
+ * IOMMUs they control at runtime, before they can resume operations.
+ * System Resume will leverage the PM driver late callbacks.
+ **/
+int omap_iommu_domain_activate(struct iommu_domain *domain)
+{
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+	struct omap_iommu_device *iommu;
+	struct omap_iommu *oiommu;
+	int i;
+
+	if (!omap_domain->dev)
+		return 0;
+
+	iommu = omap_domain->iommus;
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu++) {
+		oiommu = iommu->iommu_dev;
+		pm_runtime_get_sync(oiommu->dev);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(omap_iommu_domain_activate);
+
 /**
  * omap_iommu_runtime_suspend - disable an iommu device
  * @dev:	iommu device
diff --git a/include/linux/omap-iommu.h b/include/linux/omap-iommu.h
index 153bf25b4df3..36b645726813 100644
--- a/include/linux/omap-iommu.h
+++ b/include/linux/omap-iommu.h
@@ -10,12 +10,20 @@
 #ifndef _OMAP_IOMMU_H_
 #define _OMAP_IOMMU_H_
 
+struct iommu_domain;
+
 #ifdef CONFIG_OMAP_IOMMU
 extern void omap_iommu_save_ctx(struct device *dev);
 extern void omap_iommu_restore_ctx(struct device *dev);
+
+int omap_iommu_domain_deactivate(struct iommu_domain *domain);
+int omap_iommu_domain_activate(struct iommu_domain *domain);
 #else
 static inline void omap_iommu_save_ctx(struct device *dev) {}
 static inline void omap_iommu_restore_ctx(struct device *dev) {}
+
+static inline int omap_iommu_domain_deactivate(struct iommu_domain *domain) {}
+static inline int omap_iommu_domain_activate(struct iommu_domain *domain) {}
 #endif
 
 #endif
-- 
cgit v1.3-14-g43fede


From 73499ad21d595638213f2a5f8b9b58259fa0cae2 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Fri, 9 Aug 2019 18:09:13 +0200
Subject: iommu/omap: Fix compilation warnings

A recent patch introduced a new compiler warning because
two functions with non-void return type have no return
statement in omap-iommu.h for CONFIG_OMAP_IOMMU=n.

Fix this by adding return statements to these functions.

Fixes: d9c4d8a6cc0f8 ('iommu/omap: introduce new API for runtime suspend/resume control')
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/linux/omap-iommu.h | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/omap-iommu.h b/include/linux/omap-iommu.h
index 36b645726813..2c32ca09df02 100644
--- a/include/linux/omap-iommu.h
+++ b/include/linux/omap-iommu.h
@@ -22,8 +22,15 @@ int omap_iommu_domain_activate(struct iommu_domain *domain);
 static inline void omap_iommu_save_ctx(struct device *dev) {}
 static inline void omap_iommu_restore_ctx(struct device *dev) {}
 
-static inline int omap_iommu_domain_deactivate(struct iommu_domain *domain) {}
-static inline int omap_iommu_domain_activate(struct iommu_domain *domain) {}
+static inline int omap_iommu_domain_deactivate(struct iommu_domain *domain)
+{
+	return -ENODEV;
+}
+
+static inline int omap_iommu_domain_activate(struct iommu_domain *domain)
+{
+	return -ENODEV;
+}
 #endif
 
 #endif
-- 
cgit v1.3-14-g43fede


From 8a69961c7f7583742ab9064feab5ea533a6b1b97 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Mon, 19 Aug 2019 15:22:47 +0200
Subject: iommu: Add helpers to set/get default domain type

Add a couple of functions to allow changing the default
domain type from architecture code and a function for iommu
drivers to request whether the default domain is
passthrough.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 22 ++++++++++++++++++++++
 include/linux/iommu.h | 16 ++++++++++++++++
 2 files changed, 38 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 0ae34cca0d4a..c5e0fc5ffe8b 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2213,6 +2213,28 @@ int iommu_request_dma_domain_for_dev(struct device *dev)
 	return request_default_domain_for_dev(dev, IOMMU_DOMAIN_DMA);
 }
 
+void iommu_set_default_passthrough(bool cmd_line)
+{
+	if (cmd_line)
+		iommu_set_cmd_line_dma_api();
+
+	iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY;
+}
+
+void iommu_set_default_translated(bool cmd_line)
+{
+	if (cmd_line)
+		iommu_set_cmd_line_dma_api();
+
+	iommu_def_domain_type = IOMMU_DOMAIN_DMA;
+}
+
+bool iommu_default_passthrough(void)
+{
+	return iommu_def_domain_type == IOMMU_DOMAIN_IDENTITY;
+}
+EXPORT_SYMBOL_GPL(iommu_default_passthrough);
+
 const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode)
 {
 	const struct iommu_ops *ops = NULL;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 64ebaff33455..29bac5345563 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -436,6 +436,9 @@ extern void iommu_get_resv_regions(struct device *dev, struct list_head *list);
 extern void iommu_put_resv_regions(struct device *dev, struct list_head *list);
 extern int iommu_request_dm_for_dev(struct device *dev);
 extern int iommu_request_dma_domain_for_dev(struct device *dev);
+extern void iommu_set_default_passthrough(bool cmd_line);
+extern void iommu_set_default_translated(bool cmd_line);
+extern bool iommu_default_passthrough(void);
 extern struct iommu_resv_region *
 iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot,
 			enum iommu_resv_type type);
@@ -736,6 +739,19 @@ static inline int iommu_request_dma_domain_for_dev(struct device *dev)
 	return -ENODEV;
 }
 
+static inline void iommu_set_default_passthrough(bool cmd_line)
+{
+}
+
+static inline void iommu_set_default_translated(bool cmd_line)
+{
+}
+
+static inline bool iommu_default_passthrough(void)
+{
+	return true;
+}
+
 static inline int iommu_attach_group(struct iommu_domain *domain,
 				     struct iommu_group *group)
 {
-- 
cgit v1.3-14-g43fede


From 73d50811bc91d2a173213a78b6b43ac762f6cc54 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Sat, 24 Aug 2019 11:01:53 +0800
Subject: iommu/io-pgtable-arm-v7s: Rename the quirk from MTK_4GB to MTK_EXT

In previous mt2712/mt8173, MediaTek extend the v7s to support 4GB dram.
But in the latest mt8183, We extend it to support the PA up to 34bit.
Then the "MTK_4GB" name is not so fit, This patch only change the quirk
name to "MTK_EXT".

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Acked-by: Will Deacon <will@kernel.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/io-pgtable-arm-v7s.c | 6 +++---
 drivers/iommu/mtk_iommu.c          | 2 +-
 include/linux/io-pgtable.h         | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index fa1b38f4c271..77cc1eb1243b 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -315,7 +315,7 @@ static arm_v7s_iopte arm_v7s_prot_to_pte(int prot, int lvl,
 	if (lvl == 1 && (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS))
 		pte |= ARM_V7S_ATTR_NS_SECTION;
 
-	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_4GB)
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_EXT)
 		pte |= ARM_V7S_ATTR_MTK_4GB;
 
 	return pte;
@@ -737,12 +737,12 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
 			    IO_PGTABLE_QUIRK_NO_PERMS |
 			    IO_PGTABLE_QUIRK_TLBI_ON_MAP |
-			    IO_PGTABLE_QUIRK_ARM_MTK_4GB |
+			    IO_PGTABLE_QUIRK_ARM_MTK_EXT |
 			    IO_PGTABLE_QUIRK_NON_STRICT))
 		return NULL;
 
 	/* If ARM_MTK_4GB is enabled, the NO_PERMS is also expected. */
-	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_4GB &&
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_EXT &&
 	    !(cfg->quirks & IO_PGTABLE_QUIRK_NO_PERMS))
 			return NULL;
 
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 9ba270620767..62edce75c366 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -296,7 +296,7 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom)
 	};
 
 	if (data->enable_4GB)
-		dom->cfg.quirks |= IO_PGTABLE_QUIRK_ARM_MTK_4GB;
+		dom->cfg.quirks |= IO_PGTABLE_QUIRK_ARM_MTK_EXT;
 
 	dom->iop = alloc_io_pgtable_ops(ARM_V7S, &dom->cfg, data);
 	if (!dom->iop) {
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index b5a450a3bb47..915fb7303aa3 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -65,7 +65,7 @@ struct io_pgtable_cfg {
 	 *	(unmapped) entries but the hardware might do so anyway, perform
 	 *	TLB maintenance when mapping as well as when unmapping.
 	 *
-	 * IO_PGTABLE_QUIRK_ARM_MTK_4GB: (ARM v7s format) Set bit 9 in all
+	 * IO_PGTABLE_QUIRK_ARM_MTK_EXT: (ARM v7s format) Set bit 9 in all
 	 *	PTEs, for Mediatek IOMMUs which treat it as a 33rd address bit
 	 *	when the SoC is in "4GB mode" and they can only access the high
 	 *	remap of DRAM (0x1_00000000 to 0x1_ffffffff).
@@ -77,7 +77,7 @@ 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_4GB	BIT(3)
+	#define IO_PGTABLE_QUIRK_ARM_MTK_EXT	BIT(3)
 	#define IO_PGTABLE_QUIRK_NON_STRICT	BIT(4)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
-- 
cgit v1.3-14-g43fede


From 4c019de653237674d38cf2b3119153b144ffe173 Mon Sep 17 00:00:00 2001
From: Yong Wu <yong.wu@mediatek.com>
Date: Sat, 24 Aug 2019 11:01:54 +0800
Subject: iommu/io-pgtable-arm-v7s: Extend to support PA[33:32] for MediaTek

MediaTek extend the arm v7s descriptor to support up to 34 bits PA where
the bit32 and bit33 are encoded in the bit9 and bit4 of the PTE
respectively. Meanwhile the iova still is 32bits.

Regarding whether the pagetable address could be over 4GB, the mt8183
support it while the previous mt8173 don't, thus keep it as is.

Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Acked-by: Will Deacon <will@kernel.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/io-pgtable-arm-v7s.c | 40 +++++++++++++++++++++++++++++++-------
 include/linux/io-pgtable.h         |  7 +++----
 2 files changed, 36 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 77cc1eb1243b..545287148147 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -112,7 +112,9 @@
 #define ARM_V7S_TEX_MASK		0x7
 #define ARM_V7S_ATTR_TEX(val)		(((val) & ARM_V7S_TEX_MASK) << ARM_V7S_TEX_SHIFT)
 
-#define ARM_V7S_ATTR_MTK_4GB		BIT(9) /* MTK extend it for 4GB mode */
+/* MediaTek extend the two bits for PA 32bit/33bit */
+#define ARM_V7S_ATTR_MTK_PA_BIT32	BIT(9)
+#define ARM_V7S_ATTR_MTK_PA_BIT33	BIT(4)
 
 /* *well, except for TEX on level 2 large pages, of course :( */
 #define ARM_V7S_CONT_PAGE_TEX_SHIFT	6
@@ -176,16 +178,32 @@ static dma_addr_t __arm_v7s_dma_addr(void *pages)
 	return (dma_addr_t)virt_to_phys(pages);
 }
 
+static bool arm_v7s_is_mtk_enabled(struct io_pgtable_cfg *cfg)
+{
+	return IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT) &&
+		(cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_EXT);
+}
+
 static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl,
 				    struct io_pgtable_cfg *cfg)
 {
-	return paddr & ARM_V7S_LVL_MASK(lvl);
+	arm_v7s_iopte pte = paddr & ARM_V7S_LVL_MASK(lvl);
+
+	if (!arm_v7s_is_mtk_enabled(cfg))
+		return pte;
+
+	if (paddr & BIT_ULL(32))
+		pte |= ARM_V7S_ATTR_MTK_PA_BIT32;
+	if (paddr & BIT_ULL(33))
+		pte |= ARM_V7S_ATTR_MTK_PA_BIT33;
+	return pte;
 }
 
 static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl,
 				  struct io_pgtable_cfg *cfg)
 {
 	arm_v7s_iopte mask;
+	phys_addr_t paddr;
 
 	if (ARM_V7S_PTE_IS_TABLE(pte, lvl))
 		mask = ARM_V7S_TABLE_MASK;
@@ -194,7 +212,15 @@ static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl,
 	else
 		mask = ARM_V7S_LVL_MASK(lvl);
 
-	return pte & mask;
+	paddr = pte & mask;
+	if (!arm_v7s_is_mtk_enabled(cfg))
+		return paddr;
+
+	if (pte & ARM_V7S_ATTR_MTK_PA_BIT32)
+		paddr |= BIT_ULL(32);
+	if (pte & ARM_V7S_ATTR_MTK_PA_BIT33)
+		paddr |= BIT_ULL(33);
+	return paddr;
 }
 
 static arm_v7s_iopte *iopte_deref(arm_v7s_iopte pte, int lvl,
@@ -315,9 +341,6 @@ static arm_v7s_iopte arm_v7s_prot_to_pte(int prot, int lvl,
 	if (lvl == 1 && (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS))
 		pte |= ARM_V7S_ATTR_NS_SECTION;
 
-	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_EXT)
-		pte |= ARM_V7S_ATTR_MTK_4GB;
-
 	return pte;
 }
 
@@ -731,7 +754,10 @@ 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 || cfg->oas > ARM_V7S_ADDR_BITS)
+	if (cfg->ias > ARM_V7S_ADDR_BITS)
+		return NULL;
+
+	if (cfg->oas > (arm_v7s_is_mtk_enabled(cfg) ? 34 : ARM_V7S_ADDR_BITS))
 		return NULL;
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 915fb7303aa3..a2a52c349fe4 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -65,10 +65,9 @@ struct io_pgtable_cfg {
 	 *	(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) Set bit 9 in all
-	 *	PTEs, for Mediatek IOMMUs which treat it as a 33rd address bit
-	 *	when the SoC is in "4GB mode" and they can only access the high
-	 *	remap of DRAM (0x1_00000000 to 0x1_ffffffff).
+	 * 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.
 	 *
 	 * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs
 	 *	on unmap, for DMA domains using the flush queue mechanism for
-- 
cgit v1.3-14-g43fede


From 3fc1ca00653db6371585e3c21c4b873b2f20e60a Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Fri, 6 Sep 2019 14:14:48 +0800
Subject: swiotlb: Split size parameter to map/unmap APIs

This splits the size parameter to swiotlb_tbl_map_single() and
swiotlb_tbl_unmap_single() into an alloc_size and a mapping_size
parameter, where the latter one is rounded up to the iommu page
size.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/xen/swiotlb-xen.c |  8 ++++----
 include/linux/swiotlb.h   |  8 ++++++--
 kernel/dma/direct.c       |  2 +-
 kernel/dma/swiotlb.c      | 34 +++++++++++++++++++++-------------
 4 files changed, 32 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index ae1df496bf38..adcabd9473eb 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -386,8 +386,8 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 */
 	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
 
-	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir,
-				     attrs);
+	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys,
+				     size, size, dir, attrs);
 	if (map == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;
 
@@ -397,7 +397,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * Ensure that the address returned is DMA'ble
 	 */
 	if (unlikely(!dma_capable(dev, dev_addr, size))) {
-		swiotlb_tbl_unmap_single(dev, map, size, dir,
+		swiotlb_tbl_unmap_single(dev, map, size, size, dir,
 				attrs | DMA_ATTR_SKIP_CPU_SYNC);
 		return DMA_MAPPING_ERROR;
 	}
@@ -433,7 +433,7 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr))
-		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
+		swiotlb_tbl_unmap_single(hwdev, paddr, size, size, dir, attrs);
 }
 
 static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 361f62bb4a8e..cde3dc18e21a 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -46,13 +46,17 @@ enum dma_sync_target {
 
 extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 					  dma_addr_t tbl_dma_addr,
-					  phys_addr_t phys, size_t size,
+					  phys_addr_t phys,
+					  size_t mapping_size,
+					  size_t alloc_size,
 					  enum dma_data_direction dir,
 					  unsigned long attrs);
 
 extern void swiotlb_tbl_unmap_single(struct device *hwdev,
 				     phys_addr_t tlb_addr,
-				     size_t size, enum dma_data_direction dir,
+				     size_t mapping_size,
+				     size_t alloc_size,
+				     enum dma_data_direction dir,
 				     unsigned long attrs);
 
 extern void swiotlb_tbl_sync_single(struct device *hwdev,
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 795c9b095d75..a7f2a0163426 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -297,7 +297,7 @@ void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
 		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
 
 	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
+		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
 }
 EXPORT_SYMBOL(dma_direct_unmap_page);
 
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 9de232229063..796a44f8ef5a 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -444,7 +444,9 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
 
 phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 				   dma_addr_t tbl_dma_addr,
-				   phys_addr_t orig_addr, size_t size,
+				   phys_addr_t orig_addr,
+				   size_t mapping_size,
+				   size_t alloc_size,
 				   enum dma_data_direction dir,
 				   unsigned long attrs)
 {
@@ -464,6 +466,12 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 		pr_warn_once("%s is active and system is using DMA bounce buffers\n",
 			     sme_active() ? "SME" : "SEV");
 
+	if (mapping_size > alloc_size) {
+		dev_warn_once(hwdev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
+			      mapping_size, alloc_size);
+		return (phys_addr_t)DMA_MAPPING_ERROR;
+	}
+
 	mask = dma_get_seg_boundary(hwdev);
 
 	tbl_dma_addr &= mask;
@@ -471,8 +479,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 	offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
 
 	/*
- 	 * Carefully handle integer overflow which can occur when mask == ~0UL.
- 	 */
+	 * Carefully handle integer overflow which can occur when mask == ~0UL.
+	 */
 	max_slots = mask + 1
 		    ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
 		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
@@ -481,8 +489,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 	 * For mappings greater than or equal to a page, we limit the stride
 	 * (and hence alignment) to a page size.
 	 */
-	nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-	if (size >= PAGE_SIZE)
+	nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+	if (alloc_size >= PAGE_SIZE)
 		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
 	else
 		stride = 1;
@@ -547,7 +555,7 @@ not_found:
 	spin_unlock_irqrestore(&io_tlb_lock, flags);
 	if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit())
 		dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
-			 size, io_tlb_nslabs, tmp_io_tlb_used);
+			 alloc_size, io_tlb_nslabs, tmp_io_tlb_used);
 	return (phys_addr_t)DMA_MAPPING_ERROR;
 found:
 	io_tlb_used += nslots;
@@ -562,7 +570,7 @@ found:
 		io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
-		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
+		swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE);
 
 	return tlb_addr;
 }
@@ -571,11 +579,11 @@ found:
  * tlb_addr is the physical address of the bounce buffer to unmap.
  */
 void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
-			      size_t size, enum dma_data_direction dir,
-			      unsigned long attrs)
+			      size_t mapping_size, size_t alloc_size,
+			      enum dma_data_direction dir, unsigned long attrs)
 {
 	unsigned long flags;
-	int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+	int i, count, nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
 	int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
 	phys_addr_t orig_addr = io_tlb_orig_addr[index];
 
@@ -585,7 +593,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	if (orig_addr != INVALID_PHYS_ADDR &&
 	    !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
-		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
+		swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_FROM_DEVICE);
 
 	/*
 	 * Return the buffer to the free list by setting the corresponding
@@ -665,14 +673,14 @@ bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
 
 	/* Oh well, have to allocate and map a bounce buffer. */
 	*phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start),
-			*phys, size, dir, attrs);
+			*phys, size, size, dir, attrs);
 	if (*phys == (phys_addr_t)DMA_MAPPING_ERROR)
 		return false;
 
 	/* Ensure that the address returned is DMA'ble */
 	*dma_addr = __phys_to_dma(dev, *phys);
 	if (unlikely(!dma_capable(dev, *dma_addr, size))) {
-		swiotlb_tbl_unmap_single(dev, *phys, size, dir,
+		swiotlb_tbl_unmap_single(dev, *phys, size, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
 		return false;
 	}
-- 
cgit v1.3-14-g43fede


From fd730007a06e9b11664e3816fcebd3faa91761ea Mon Sep 17 00:00:00 2001
From: Kyung Min Park <kyung.min.park@intel.com>
Date: Fri, 6 Sep 2019 11:14:02 -0700
Subject: iommu/vt-d: Add Scalable Mode fault information

Intel VT-d specification revision 3 added support for Scalable Mode
Translation for DMA remapping. Add the Scalable Mode fault reasons to
show detailed fault reasons when the translation fault happens.

Link: https://software.intel.com/sites/default/files/managed/c5/15/vt-directed-io-spec.pdf

Reviewed-by: Sohil Mehta <sohil.mehta@intel.com>
Signed-off-by: Kyung Min Park <kyung.min.park@intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/dmar.c        | 77 ++++++++++++++++++++++++++++++++++++++++++---
 include/linux/intel-iommu.h |  2 ++
 2 files changed, 75 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 5d0754ed5fa0..eecd6a421667 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1519,6 +1519,64 @@ static const char *dma_remap_fault_reasons[] =
 	"PCE for translation request specifies blocking",
 };
 
+static const char * const dma_remap_sm_fault_reasons[] = {
+	"SM: Invalid Root Table Address",
+	"SM: TTM 0 for request with PASID",
+	"SM: TTM 0 for page group request",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x33-0x37 */
+	"SM: Error attempting to access Root Entry",
+	"SM: Present bit in Root Entry is clear",
+	"SM: Non-zero reserved field set in Root Entry",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x3B-0x3F */
+	"SM: Error attempting to access Context Entry",
+	"SM: Present bit in Context Entry is clear",
+	"SM: Non-zero reserved field set in the Context Entry",
+	"SM: Invalid Context Entry",
+	"SM: DTE field in Context Entry is clear",
+	"SM: PASID Enable field in Context Entry is clear",
+	"SM: PASID is larger than the max in Context Entry",
+	"SM: PRE field in Context-Entry is clear",
+	"SM: RID_PASID field error in Context-Entry",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x49-0x4F */
+	"SM: Error attempting to access the PASID Directory Entry",
+	"SM: Present bit in Directory Entry is clear",
+	"SM: Non-zero reserved field set in PASID Directory Entry",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x53-0x57 */
+	"SM: Error attempting to access PASID Table Entry",
+	"SM: Present bit in PASID Table Entry is clear",
+	"SM: Non-zero reserved field set in PASID Table Entry",
+	"SM: Invalid Scalable-Mode PASID Table Entry",
+	"SM: ERE field is clear in PASID Table Entry",
+	"SM: SRE field is clear in PASID Table Entry",
+	"Unknown", "Unknown",/* 0x5E-0x5F */
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x60-0x67 */
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x68-0x6F */
+	"SM: Error attempting to access first-level paging entry",
+	"SM: Present bit in first-level paging entry is clear",
+	"SM: Non-zero reserved field set in first-level paging entry",
+	"SM: Error attempting to access FL-PML4 entry",
+	"SM: First-level entry address beyond MGAW in Nested translation",
+	"SM: Read permission error in FL-PML4 entry in Nested translation",
+	"SM: Read permission error in first-level paging entry in Nested translation",
+	"SM: Write permission error in first-level paging entry in Nested translation",
+	"SM: Error attempting to access second-level paging entry",
+	"SM: Read/Write permission error in second-level paging entry",
+	"SM: Non-zero reserved field set in second-level paging entry",
+	"SM: Invalid second-level page table pointer",
+	"SM: A/D bit update needed in second-level entry when set up in no snoop",
+	"Unknown", "Unknown", "Unknown", /* 0x7D-0x7F */
+	"SM: Address in first-level translation is not canonical",
+	"SM: U/S set 0 for first-level translation with user privilege",
+	"SM: No execute permission for request with PASID and ER=1",
+	"SM: Address beyond the DMA hardware max",
+	"SM: Second-level entry address beyond the max",
+	"SM: No write permission for Write/AtomicOp request",
+	"SM: No read permission for Read/AtomicOp request",
+	"SM: Invalid address-interrupt address",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x88-0x8F */
+	"SM: A/D bit update needed in first-level entry when set up in no snoop",
+};
+
 static const char *irq_remap_fault_reasons[] =
 {
 	"Detected reserved fields in the decoded interrupt-remapped request",
@@ -1536,6 +1594,10 @@ static const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
 					ARRAY_SIZE(irq_remap_fault_reasons))) {
 		*fault_type = INTR_REMAP;
 		return irq_remap_fault_reasons[fault_reason - 0x20];
+	} else if (fault_reason >= 0x30 && (fault_reason - 0x30 <
+			ARRAY_SIZE(dma_remap_sm_fault_reasons))) {
+		*fault_type = DMA_REMAP;
+		return dma_remap_sm_fault_reasons[fault_reason - 0x30];
 	} else if (fault_reason < ARRAY_SIZE(dma_remap_fault_reasons)) {
 		*fault_type = DMA_REMAP;
 		return dma_remap_fault_reasons[fault_reason];
@@ -1611,7 +1673,8 @@ void dmar_msi_read(int irq, struct msi_msg *msg)
 }
 
 static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
-		u8 fault_reason, u16 source_id, unsigned long long addr)
+		u8 fault_reason, int pasid, u16 source_id,
+		unsigned long long addr)
 {
 	const char *reason;
 	int fault_type;
@@ -1624,10 +1687,11 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
 			PCI_FUNC(source_id & 0xFF), addr >> 48,
 			fault_reason, reason);
 	else
-		pr_err("[%s] Request device [%02x:%02x.%d] fault addr %llx [fault reason %02d] %s\n",
+		pr_err("[%s] Request device [%02x:%02x.%d] PASID %x fault addr %llx [fault reason %02d] %s\n",
 		       type ? "DMA Read" : "DMA Write",
 		       source_id >> 8, PCI_SLOT(source_id & 0xFF),
-		       PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
+		       PCI_FUNC(source_id & 0xFF), pasid, addr,
+		       fault_reason, reason);
 	return 0;
 }
 
@@ -1659,8 +1723,9 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 		u8 fault_reason;
 		u16 source_id;
 		u64 guest_addr;
-		int type;
+		int type, pasid;
 		u32 data;
+		bool pasid_present;
 
 		/* highest 32 bits */
 		data = readl(iommu->reg + reg +
@@ -1672,10 +1737,12 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 			fault_reason = dma_frcd_fault_reason(data);
 			type = dma_frcd_type(data);
 
+			pasid = dma_frcd_pasid_value(data);
 			data = readl(iommu->reg + reg +
 				     fault_index * PRIMARY_FAULT_REG_LEN + 8);
 			source_id = dma_frcd_source_id(data);
 
+			pasid_present = dma_frcd_pasid_present(data);
 			guest_addr = dmar_readq(iommu->reg + reg +
 					fault_index * PRIMARY_FAULT_REG_LEN);
 			guest_addr = dma_frcd_page_addr(guest_addr);
@@ -1688,7 +1755,9 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
 
 		if (!ratelimited)
+			/* Using pasid -1 if pasid is not present */
 			dmar_fault_do_one(iommu, type, fault_reason,
+					  pasid_present ? pasid : -1,
 					  source_id, guest_addr);
 
 		fault_index++;
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index f2ae8a006ff8..10e79a49af9d 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -272,6 +272,8 @@
 #define dma_frcd_type(d) ((d >> 30) & 1)
 #define dma_frcd_fault_reason(c) (c & 0xff)
 #define dma_frcd_source_id(c) (c & 0xffff)
+#define dma_frcd_pasid_value(c) (((c) >> 8) & 0xfffff)
+#define dma_frcd_pasid_present(c) (((c) >> 31) & 1)
 /* low 64 bit */
 #define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT))
 
-- 
cgit v1.3-14-g43fede