iommu: Introduce dirty log tracking framework

virt inclusion
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZUKK
CVE: NA

------------------------------

Some types of IOMMU are capable of tracking DMA dirty log, such as
ARM SMMU with HTTU or Intel IOMMU with SLADE. This introduces the
dirty log tracking framework in the IOMMU base layer.

Four new essential interfaces are added, and we maintaince the status
of dirty log tracking in iommu_domain.
1. iommu_support_dirty_log: Check whether domain supports dirty log tracking
2. iommu_switch_dirty_log: Perform actions to start|stop dirty log tracking
3. iommu_sync_dirty_log: Sync dirty log from IOMMU into a dirty bitmap
4. iommu_clear_dirty_log: Clear dirty log of IOMMU by a mask bitmap

Note: Don't concurrently call these interfaces with other ops that
access underlying page table.
Signed-off-by: NKeqian Zhu <zhukeqian1@huawei.com>
Signed-off-by: NKunkun Jiang <jiangkunkun@huawei.com>
Reviewed-by: NKeqian Zhu <zhukeqian1@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

drivers/iommu/iommu.c

@@ -2073,6 +2073,7 @@ static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
 	domain->type = type;
 	/* Assume all sizes by default; the driver may override this later */
 	domain->pgsize_bitmap  = bus->iommu_ops->pgsize_bitmap;
+	mutex_init(&domain->switch_log_lock);
 
 	return domain;
 }
@@ -2890,6 +2891,206 @@ int iommu_domain_set_attr(struct iommu_domain *domain,
 }
 EXPORT_SYMBOL_GPL(iommu_domain_set_attr);
 
+bool iommu_support_dirty_log(struct iommu_domain *domain)
+{
+	const struct iommu_ops *ops = domain->ops;
+
+	return ops->support_dirty_log && ops->support_dirty_log(domain);
+}
+EXPORT_SYMBOL_GPL(iommu_support_dirty_log);
+
+int iommu_switch_dirty_log(struct iommu_domain *domain, bool enable,
+			   unsigned long iova, size_t size, int prot)
+{
+	const struct iommu_ops *ops = domain->ops;
+	unsigned long orig_iova = iova;
+	unsigned int min_pagesz;
+	size_t orig_size = size;
+	bool flush = false;
+	int ret = 0;
+
+	if (unlikely(!ops->switch_dirty_log))
+		return -ENODEV;
+
+	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
+	if (!IS_ALIGNED(iova | size, min_pagesz)) {
+		pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n",
+		       iova, size, min_pagesz);
+		return -EINVAL;
+	}
+
+	mutex_lock(&domain->switch_log_lock);
+	if (enable && domain->dirty_log_tracking) {
+		ret = -EBUSY;
+		goto out;
+	} else if (!enable && !domain->dirty_log_tracking) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	pr_debug("switch_dirty_log %s for: iova 0x%lx size 0x%zx\n",
+		 enable ? "enable" : "disable", iova, size);
+
+	while (size) {
+		size_t pgsize = iommu_pgsize(domain, iova, size);
+
+		flush = true;
+		ret = ops->switch_dirty_log(domain, enable, iova, pgsize, prot);
+		if (ret)
+			break;
+
+		pr_debug("switch_dirty_log handled: iova 0x%lx size 0x%zx\n",
+			 iova, pgsize);
+
+		iova += pgsize;
+		size -= pgsize;
+	}
+
+	if (flush)
+		iommu_flush_iotlb_all(domain);
+
+	if (!ret) {
+		domain->dirty_log_tracking = enable;
+		trace_switch_dirty_log(orig_iova, orig_size, enable);
+	}
+out:
+	mutex_unlock(&domain->switch_log_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_switch_dirty_log);
+
+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)
+{
+	const struct iommu_ops *ops = domain->ops;
+	unsigned long orig_iova = iova;
+	unsigned int min_pagesz;
+	size_t orig_size = size;
+	int ret = 0;
+
+	if (unlikely(!ops->sync_dirty_log))
+		return -ENODEV;
+
+	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
+	if (!IS_ALIGNED(iova | size, min_pagesz)) {
+		pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n",
+		       iova, size, min_pagesz);
+		return -EINVAL;
+	}
+
+	mutex_lock(&domain->switch_log_lock);
+	if (!domain->dirty_log_tracking) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	pr_debug("sync_dirty_log for: iova 0x%lx size 0x%zx\n", iova, size);
+
+	while (size) {
+		size_t pgsize = iommu_pgsize(domain, iova, size);
+
+		ret = ops->sync_dirty_log(domain, iova, pgsize,
+					  bitmap, base_iova, bitmap_pgshift);
+		if (ret)
+			break;
+
+		pr_debug("sync_dirty_log handled: iova 0x%lx size 0x%zx\n",
+			 iova, pgsize);
+
+		iova += pgsize;
+		size -= pgsize;
+	}
+
+	if (!ret)
+		trace_sync_dirty_log(orig_iova, orig_size);
+out:
+	mutex_unlock(&domain->switch_log_lock);
+	return ret;
+}
+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;
+	unsigned long orig_iova = iova;
+	size_t orig_size = size;
+	int ret = 0;
+
+	if (unlikely(!ops->clear_dirty_log))
+		return -ENODEV;
+
+	pr_debug("clear_dirty_log for: iova 0x%lx size 0x%zx\n", iova, size);
+
+	while (size) {
+		size_t pgsize = iommu_pgsize(domain, iova, size);
+
+		ret = ops->clear_dirty_log(domain, iova, pgsize, bitmap,
+					   base_iova, bitmap_pgshift);
+		if (ret)
+			break;
+
+		pr_debug("clear_dirty_log handled: iova 0x%lx size 0x%zx\n",
+			 iova, pgsize);
+
+		iova += pgsize;
+		size -= pgsize;
+	}
+
+	if (!ret)
+		trace_clear_dirty_log(orig_iova, orig_size);
+
+	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;
+	}
+
+	mutex_lock(&domain->switch_log_lock);
+	if (!domain->dirty_log_tracking) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	start = (iova - base_iova) >> bitmap_pgshift;
+	end = start + (size >> bitmap_pgshift);
+	bitmap_for_each_set_region(bitmap, rs, re, start, end) {
+		flush = true;
+		riova = base_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);
+out:
+	mutex_unlock(&domain->switch_log_lock);
+	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;

include/linux/iommu.h

@@ -87,6 +87,8 @@ struct iommu_domain {
 	void *handler_token;
 	struct iommu_domain_geometry geometry;
 	void *iova_cookie;
+	bool dirty_log_tracking;
+	struct mutex switch_log_lock;
 };
 
 enum iommu_cap {
@@ -217,6 +219,10 @@ struct iommu_iotlb_gather {
  * @device_group: find iommu group for a particular device
  * @domain_get_attr: Query domain attributes
  * @domain_set_attr: Change domain attributes
+ * @support_dirty_log: Check whether domain supports dirty log tracking
+ * @switch_dirty_log: Perform actions to start|stop dirty log tracking
+ * @sync_dirty_log: Sync dirty log from IOMMU into a dirty bitmap
+ * @clear_dirty_log: Clear dirty log of IOMMU by a mask bitmap
  * @get_resv_regions: Request list of reserved regions for a device
  * @put_resv_regions: Free list of reserved regions for a device
  * @apply_resv_region: Temporary helper call-back for iova reserved ranges
@@ -274,6 +280,22 @@ struct iommu_ops {
 	int (*domain_set_attr)(struct iommu_domain *domain,
 			       enum iommu_attr attr, void *data);
 
+	/*
+	 * Track dirty log. Note: Don't concurrently call these interfaces with
+	 * other ops that access underlying page table.
+	 */
+	bool (*support_dirty_log)(struct iommu_domain *domain);
+	int (*switch_dirty_log)(struct iommu_domain *domain, bool enable,
+				unsigned long iova, size_t size, int prot);
+	int (*sync_dirty_log)(struct iommu_domain *domain,
+			      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);
 	void (*put_resv_regions)(struct device *dev, struct list_head *list);
@@ -536,6 +558,17 @@ extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr,
 				 void *data);
 extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr,
 				 void *data);
+extern bool iommu_support_dirty_log(struct iommu_domain *domain);
+extern int iommu_switch_dirty_log(struct iommu_domain *domain, bool enable,
+				  unsigned long iova, size_t size, int prot);
+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,
@@ -934,7 +967,39 @@ static inline int iommu_domain_set_attr(struct iommu_domain *domain,
 	return -EINVAL;
 }
 
-static inline int  iommu_device_register(struct iommu_device *iommu)
+static inline bool iommu_support_dirty_log(struct iommu_domain *domain)
+{
+	return false;
+}
+
+static inline int iommu_switch_dirty_log(struct iommu_domain *domain,
+					 bool enable, unsigned long iova,
+					 size_t size, int prot)
+{
+	return -EINVAL;
+}
+
+static inline int iommu_sync_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_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,
+					const struct iommu_ops *ops,
+					struct device *hwdev)
 {
 	return -ENODEV;
 }

include/trace/events/iommu.h

@@ -131,6 +131,69 @@ TRACE_EVENT(unmap,
 	)
 );
 
+TRACE_EVENT(switch_dirty_log,
+
+	TP_PROTO(unsigned long iova, size_t size, bool enable),
+
+	TP_ARGS(iova, size, enable),
+
+	TP_STRUCT__entry(
+		__field(u64, iova)
+		__field(size_t, size)
+		__field(bool, enable)
+	),
+
+	TP_fast_assign(
+		__entry->iova = iova;
+		__entry->size = size;
+		__entry->enable = enable;
+	),
+
+	TP_printk("IOMMU: iova=0x%016llx size=%zu enable=%u",
+			__entry->iova, __entry->size, __entry->enable
+	)
+);
+
+TRACE_EVENT(sync_dirty_log,
+
+	TP_PROTO(unsigned long iova, size_t size),
+
+	TP_ARGS(iova, size),
+
+	TP_STRUCT__entry(
+		__field(u64, iova)
+		__field(size_t, size)
+	),
+
+	TP_fast_assign(
+		__entry->iova = iova;
+		__entry->size = size;
+	),
+
+	TP_printk("IOMMU: iova=0x%016llx size=%zu", __entry->iova,
+			__entry->size)
+);
+
+TRACE_EVENT(clear_dirty_log,
+
+	TP_PROTO(unsigned long iova, size_t size),
+
+	TP_ARGS(iova, size),
+
+	TP_STRUCT__entry(
+		__field(u64, iova)
+		__field(size_t, size)
+	),
+
+	TP_fast_assign(
+		__entry->iova = iova;
+		__entry->size = size;
+	),
+
+	TP_printk("IOMMU: iova=0x%016llx size=%zu", __entry->iova,
+			__entry->size)
+);
+
 DECLARE_EVENT_CLASS(iommu_error,
 
 	TP_PROTO(struct device *dev, unsigned long iova, int flags),