diff mbox series

[v2,07/11] iommu/arm-smmu-v3: Clear dirty log according to bitmap

Message ID 20210310090614.26668-8-zhukeqian1@huawei.com (mailing list archive)
State New, archived
Headers show
Series vfio/iommu_type1: Implement dirty log tracking based on smmuv3 HTTU | expand

Commit Message

zhukeqian March 10, 2021, 9:06 a.m. UTC
From: jiangkunkun <jiangkunkun@huawei.com>

After dirty log is retrieved, user should clear dirty log to re-enable
dirty log tracking for these dirtied pages.

This adds a new interface named clear_dirty_log in iommu layer and
arm smmuv3 implements it, which clears the dirty state (As we just
enable HTTU for stage1, so set the AP[2] bit) of these TTDs that are
specified by the user provided bitmap.

Co-developed-by: Keqian Zhu <zhukeqian1@huawei.com>
Signed-off-by: Kunkun Jiang <jiangkunkun@huawei.com>
---

changelog:

v2:
 - Add new sanity check in arm_smmu_sync_dirty_log(). (smmu_domain->stage != ARM_SMMU_DOMAIN_S1)
 - Remove extra flush_iotlb in __iommu_clear_dirty_log().
 
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 25 ++++++
 drivers/iommu/io-pgtable-arm.c              | 95 +++++++++++++++++++++
 drivers/iommu/iommu.c                       | 68 +++++++++++++++
 include/linux/io-pgtable.h                  |  4 +
 include/linux/iommu.h                       | 17 ++++
 5 files changed, 209 insertions(+)
diff mbox series

Patch

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 7407896a710e..696df51a3282 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -2666,6 +2666,30 @@  static int arm_smmu_sync_dirty_log(struct iommu_domain *domain,
 				   bitmap_pgshift);
 }
 
+static int arm_smmu_clear_dirty_log(struct iommu_domain *domain,
+				    unsigned long iova, size_t size,
+				    unsigned long *bitmap,
+				    unsigned long base_iova,
+				    unsigned long bitmap_pgshift)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	if (!(smmu->features & ARM_SMMU_FEAT_HD))
+		return -ENODEV;
+	if (smmu_domain->stage != ARM_SMMU_DOMAIN_S1)
+		return -EINVAL;
+
+	if (!ops || !ops->clear_dirty_log) {
+		pr_err("io-pgtable don't realize clear dirty log\n");
+		return -ENODEV;
+	}
+
+	return ops->clear_dirty_log(ops, iova, size, bitmap, base_iova,
+				    bitmap_pgshift);
+}
+
 static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
 {
 	return iommu_fwspec_add_ids(dev, args->args, 1);
@@ -2770,6 +2794,7 @@  static struct iommu_ops arm_smmu_ops = {
 	.merge_page		= arm_smmu_merge_page,
 	.stop_dirty_log		= arm_smmu_stop_dirty_log,
 	.sync_dirty_log		= arm_smmu_sync_dirty_log,
+	.clear_dirty_log	= arm_smmu_clear_dirty_log,
 	.of_xlate		= arm_smmu_of_xlate,
 	.get_resv_regions	= arm_smmu_get_resv_regions,
 	.put_resv_regions	= generic_iommu_put_resv_regions,
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 67a208a05ab2..e3ef0f50611c 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -966,6 +966,100 @@  static int arm_lpae_sync_dirty_log(struct io_pgtable_ops *ops,
 					 bitmap, base_iova, bitmap_pgshift);
 }
 
+static int __arm_lpae_clear_dirty_log(struct arm_lpae_io_pgtable *data,
+				      unsigned long iova, size_t size,
+				      int lvl, arm_lpae_iopte *ptep,
+				      unsigned long *bitmap,
+				      unsigned long base_iova,
+				      unsigned long bitmap_pgshift)
+{
+	arm_lpae_iopte pte;
+	struct io_pgtable *iop = &data->iop;
+	unsigned long offset;
+	size_t base, next_size;
+	int nbits, ret, i;
+
+	if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS))
+		return -EINVAL;
+
+	ptep += ARM_LPAE_LVL_IDX(iova, lvl, data);
+	pte = READ_ONCE(*ptep);
+	if (WARN_ON(!pte))
+		return -EINVAL;
+
+	if (size == ARM_LPAE_BLOCK_SIZE(lvl, data)) {
+		if (iopte_leaf(pte, lvl, iop->fmt)) {
+			if (pte & ARM_LPAE_PTE_AP_RDONLY)
+				return 0;
+
+			/* Ensure all corresponding bits are set */
+			nbits = size >> bitmap_pgshift;
+			offset = (iova - base_iova) >> bitmap_pgshift;
+			for (i = offset; i < offset + nbits; i++) {
+				if (!test_bit(i, bitmap))
+					return 0;
+			}
+
+			/* Race does not exist */
+			pte |= ARM_LPAE_PTE_AP_RDONLY;
+			__arm_lpae_set_pte(ptep, pte, &iop->cfg);
+			return 0;
+		} else {
+			/* To traverse next level */
+			next_size = ARM_LPAE_BLOCK_SIZE(lvl + 1, data);
+			ptep = iopte_deref(pte, data);
+			for (base = 0; base < size; base += next_size) {
+				ret = __arm_lpae_clear_dirty_log(data,
+						iova + base, next_size, lvl + 1,
+						ptep, bitmap, base_iova,
+						bitmap_pgshift);
+				if (ret)
+					return ret;
+			}
+			return 0;
+		}
+	} else if (iopte_leaf(pte, lvl, iop->fmt)) {
+		/* Though the size is too small, it is already clean */
+		if (pte & ARM_LPAE_PTE_AP_RDONLY)
+			return 0;
+
+		return -EINVAL;
+	}
+
+	/* Keep on walkin */
+	ptep = iopte_deref(pte, data);
+	return __arm_lpae_clear_dirty_log(data, iova, size, lvl + 1, ptep,
+			bitmap, base_iova, bitmap_pgshift);
+}
+
+static int arm_lpae_clear_dirty_log(struct io_pgtable_ops *ops,
+				    unsigned long iova, size_t size,
+				    unsigned long *bitmap,
+				    unsigned long base_iova,
+				    unsigned long bitmap_pgshift)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	arm_lpae_iopte *ptep = data->pgd;
+	int lvl = data->start_level;
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	long iaext = (s64)iova >> cfg->ias;
+
+	if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
+		return -EINVAL;
+
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+		iaext = ~iaext;
+	if (WARN_ON(iaext))
+		return -EINVAL;
+
+	if (data->iop.fmt != ARM_64_LPAE_S1 &&
+	    data->iop.fmt != ARM_32_LPAE_S1)
+		return -EINVAL;
+
+	return __arm_lpae_clear_dirty_log(data, iova, size, lvl, ptep,
+			bitmap, base_iova, bitmap_pgshift);
+}
+
 static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg)
 {
 	unsigned long granule, page_sizes;
@@ -1047,6 +1141,7 @@  arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
 		.split_block	= arm_lpae_split_block,
 		.merge_page	= arm_lpae_merge_page,
 		.sync_dirty_log	= arm_lpae_sync_dirty_log,
+		.clear_dirty_log = arm_lpae_clear_dirty_log,
 	};
 
 	return data;
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 44dfb78f9050..105e4c1f015e 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2888,6 +2888,74 @@  int iommu_sync_dirty_log(struct iommu_domain *domain, unsigned long iova,
 }
 EXPORT_SYMBOL_GPL(iommu_sync_dirty_log);
 
+static int __iommu_clear_dirty_log(struct iommu_domain *domain,
+				   unsigned long iova, size_t size,
+				   unsigned long *bitmap,
+				   unsigned long base_iova,
+				   unsigned long bitmap_pgshift)
+{
+	const struct iommu_ops *ops = domain->ops;
+	size_t pgsize;
+	int ret = 0;
+
+	if (unlikely(!ops || !ops->clear_dirty_log))
+		return -ENODEV;
+
+	while (size) {
+		pgsize = iommu_pgsize(domain, iova, size);
+
+		ret = ops->clear_dirty_log(domain, iova, pgsize, bitmap,
+					   base_iova, bitmap_pgshift);
+		if (ret)
+			break;
+
+		pr_debug("dirty_log_clear handled: iova 0x%lx pagesz 0x%zx\n",
+			 iova, pgsize);
+
+		iova += pgsize;
+		size -= pgsize;
+	}
+
+	return ret;
+}
+
+int iommu_clear_dirty_log(struct iommu_domain *domain,
+			  unsigned long iova, size_t size,
+			  unsigned long *bitmap, unsigned long base_iova,
+			  unsigned long bitmap_pgshift)
+{
+	unsigned long riova, rsize;
+	unsigned int min_pagesz;
+	bool flush = false;
+	int rs, re, start, end;
+	int ret = 0;
+
+	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
+	if (!IS_ALIGNED(iova | size, min_pagesz)) {
+		pr_err("unaligned: iova 0x%lx min_pagesz 0x%x\n",
+		       iova, min_pagesz);
+		return -EINVAL;
+	}
+
+	start = (iova - base_iova) >> bitmap_pgshift;
+	end = start + (size >> bitmap_pgshift);
+	bitmap_for_each_set_region(bitmap, rs, re, start, end) {
+		flush = true;
+		riova = iova + (rs << bitmap_pgshift);
+		rsize = (re - rs) << bitmap_pgshift;
+		ret = __iommu_clear_dirty_log(domain, riova, rsize, bitmap,
+					      base_iova, bitmap_pgshift);
+		if (ret)
+			break;
+	}
+
+	if (flush)
+		iommu_flush_iotlb_all(domain);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_clear_dirty_log);
+
 void iommu_get_resv_regions(struct device *dev, struct list_head *list)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 5107a9d4ac79..48dbbd2e12b2 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -175,6 +175,10 @@  struct io_pgtable_ops {
 			      unsigned long iova, size_t size,
 			      unsigned long *bitmap, unsigned long base_iova,
 			      unsigned long bitmap_pgshift);
+	int (*clear_dirty_log)(struct io_pgtable_ops *ops,
+			       unsigned long iova, size_t size,
+			       unsigned long *bitmap, unsigned long base_iova,
+			       unsigned long bitmap_pgshift);
 };
 
 /**
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 7d5777acfdb7..4f7db5d23b23 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -278,6 +278,10 @@  struct iommu_ops {
 			      unsigned long iova, size_t size,
 			      unsigned long *bitmap, unsigned long base_iova,
 			      unsigned long bitmap_pgshift);
+	int (*clear_dirty_log)(struct iommu_domain *domain,
+			       unsigned long iova, size_t size,
+			       unsigned long *bitmap, unsigned long base_iova,
+			       unsigned long bitmap_pgshift);
 
 	/* Request/Free a list of reserved regions for a device */
 	void (*get_resv_regions)(struct device *dev, struct list_head *list);
@@ -542,6 +546,10 @@  extern int iommu_sync_dirty_log(struct iommu_domain *domain, unsigned long iova,
 				size_t size, unsigned long *bitmap,
 				unsigned long base_iova,
 				unsigned long bitmap_pgshift);
+extern int iommu_clear_dirty_log(struct iommu_domain *domain, unsigned long iova,
+				 size_t dma_size, unsigned long *bitmap,
+				 unsigned long base_iova,
+				 unsigned long bitmap_pgshift);
 
 /* Window handling function prototypes */
 extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
@@ -967,6 +975,15 @@  static inline int iommu_sync_dirty_log(struct iommu_domain *domain,
 	return -EINVAL;
 }
 
+static inline int iommu_clear_dirty_log(struct iommu_domain *domain,
+					unsigned long iova, size_t size,
+					unsigned long *bitmap,
+					unsigned long base_iova,
+					unsigned long pgshift)
+{
+	return -EINVAL;
+}
+
 static inline int  iommu_device_register(struct iommu_device *iommu)
 {
 	return -ENODEV;