@@ -479,6 +479,7 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
size_t size, int prot, u64 dma_mask)
{
struct iommu_domain *domain = iommu_get_dma_domain(dev);
+ const struct iommu_ops *ops = domain->ops;
struct iommu_dma_cookie *cookie = domain->iova_cookie;
struct iova_domain *iovad = &cookie->iovad;
size_t iova_off = iova_offset(iovad, phys);
@@ -497,6 +498,10 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
iommu_dma_free_iova(cookie, iova, size);
return DMA_MAPPING_ERROR;
}
+
+ if (ops->iotlb_sync_range)
+ ops->iotlb_sync_range(iova, size);
+
return iova + iova_off;
}
@@ -1165,6 +1170,7 @@ void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size)
static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
phys_addr_t msi_addr, struct iommu_domain *domain)
{
+ const struct iommu_ops *ops = domain->ops;
struct iommu_dma_cookie *cookie = domain->iova_cookie;
struct iommu_dma_msi_page *msi_page;
dma_addr_t iova;
@@ -1187,6 +1193,9 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
if (iommu_map(domain, iova, msi_addr, size, prot))
goto out_free_iova;
+ if (ops->iotlb_sync_range)
+ ops->iotlb_sync_range(iova, size);
+
INIT_LIST_HEAD(&msi_page->list);
msi_page->phys = msi_addr;
msi_page->iova = iova;
@@ -2304,6 +2304,9 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
unmapped += unmapped_page;
}
+ if (ops->iotlb_sync_range)
+ ops->iotlb_sync_range(iova, size);
+
trace_unmap(orig_iova, size, unmapped);
return unmapped;
}
@@ -2334,6 +2337,7 @@ static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
struct scatterlist *sg, unsigned int nents, int prot,
gfp_t gfp)
{
+ const struct iommu_ops *ops = domain->ops;
size_t len = 0, mapped = 0;
phys_addr_t start;
unsigned int i = 0;
@@ -2364,6 +2368,9 @@ static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
sg = sg_next(sg);
}
+ if (ops->iotlb_sync_range)
+ ops->iotlb_sync_range(iova, mapped);
+
return mapped;
out_err:
@@ -192,6 +192,7 @@ struct iommu_iotlb_gather {
* @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_sync_range: Sync specific iova and size mappings to the hardware
* @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
@@ -244,6 +245,7 @@ struct iommu_ops {
size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
size_t size, struct iommu_iotlb_gather *iotlb_gather);
void (*flush_iotlb_all)(struct iommu_domain *domain);
+ void (*iotlb_sync_range)(unsigned long iova, size_t size);
void (*iotlb_sync_map)(struct iommu_domain *domain);
void (*iotlb_sync)(struct iommu_domain *domain,
struct iommu_iotlb_gather *iotlb_gather);
Add iotlb_sync_range callback to support that driver can appoint iova and size to do tlb sync. Iommu will call iotlb_sync_range() after the whole mapping/unmapping is completed, and the iova and size of iotlb_sync_range() are start_iova and buffer total_size respectively. At the same time, iotlb_sync() and tlb_flush_walk/leaf() can be skipped. So iotlb_sync_range() will enhance performance by reducing the time of tlb sync. Signed-off-by: Chao Hao <chao.hao@mediatek.com> --- drivers/iommu/dma-iommu.c | 9 +++++++++ drivers/iommu/iommu.c | 7 +++++++ include/linux/iommu.h | 2 ++ 3 files changed, 18 insertions(+)