iommupt: Directly call iommupt's unmap_range()

The common algorithm in iommupt does not require the iommu_pgsize()
calculations, it can directly unmap any arbitrary range. Add a new function
pointer to directly call an iommupt unmap_range op and make
__iommu_unmap() call it directly.

Gives about a 5% gain on single page unmappings.

The function pointer is run through pt_iommu_ops instead of
iommu_domain_ops to discourage using it outside iommupt. All drivers with
their own page tables should continue to use the simplified
map/unmap_pages() style interfaces.

Reviewed-by: Samiullah Khawaja <skhawaja@google.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

4 files changed, 57 insertions, 37 deletions

diff --git a/drivers/iommu/generic_pt/iommu_pt.h b/drivers/iommu/generic_pt/iommu_pt.h
index 9c08bb594e41..a627c26fa62d 100644
--- a/drivers/iommu/generic_pt/iommu_pt.h
+++ b/drivers/iommu/generic_pt/iommu_pt.h
@@ -1031,34 +1031,12 @@ start_oa:
 	return ret;
 }
 
-/**
- * unmap_pages() - Make a range of IOVA empty/not present
- * @domain: Domain to manipulate
- * @iova: IO virtual address to start
- * @pgsize: Length of each page
- * @pgcount: Length of the range in pgsize units starting from @iova
- * @iotlb_gather: Gather struct that must be flushed on return
- *
- * unmap_pages() will remove a translation created by map_pages(). It cannot
- * subdivide a mapping created by map_pages(), so it should be called with IOVA
- * ranges that match those passed to map_pages(). The IOVA range can aggregate
- * contiguous map_pages() calls so long as no individual range is split.
- *
- * Context: The caller must hold a write range lock that includes
- * the whole range.
- *
- * Returns: Number of bytes of VA unmapped. iova + res will be the point
- * unmapping stopped.
- */
-size_t DOMAIN_NS(unmap_pages)(struct iommu_domain *domain, unsigned long iova,
-			      size_t pgsize, size_t pgcount,
+static size_t NS(unmap_range)(struct pt_iommu *iommu_table, dma_addr_t iova,
+			      dma_addr_t len,
 			      struct iommu_iotlb_gather *iotlb_gather)
 {
-	struct pt_iommu *iommu_table =
-		container_of(domain, struct pt_iommu, domain);
 	struct pt_unmap_args unmap = { .free_list = IOMMU_PAGES_LIST_INIT(
 					       unmap.free_list) };
-	pt_vaddr_t len = pgsize * pgcount;
 	struct pt_range range;
 	int ret;
 
@@ -1073,7 +1051,6 @@ size_t DOMAIN_NS(unmap_pages)(struct iommu_domain *domain, unsigned long iova,
 
 	return unmap.unmapped;
 }
-EXPORT_SYMBOL_NS_GPL(DOMAIN_NS(unmap_pages), "GENERIC_PT_IOMMU");
 
 static void NS(get_info)(struct pt_iommu *iommu_table,
 			 struct pt_iommu_info *info)
@@ -1121,6 +1098,7 @@ static void NS(deinit)(struct pt_iommu *iommu_table)
 }
 
 static const struct pt_iommu_ops NS(ops) = {
+	.unmap_range = NS(unmap_range),
 #if IS_ENABLED(CONFIG_IOMMUFD_DRIVER) && defined(pt_entry_is_write_dirty) && \
 	IS_ENABLED(CONFIG_IOMMUFD_TEST) && defined(pt_entry_make_write_dirty)
 	.set_dirty = NS(set_dirty),
@@ -1183,6 +1161,7 @@ static int pt_iommu_init_domain(struct pt_iommu *iommu_table,
 
 	domain->type = __IOMMU_DOMAIN_PAGING;
 	domain->pgsize_bitmap = info.pgsize_bitmap;
+	domain->is_iommupt = true;
 
 	if (pt_feature(common, PT_FEAT_DYNAMIC_TOP))
 		range = _pt_top_range(common,
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 35db51780954..f68269707101 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -34,6 +34,7 @@
 #include <linux/sched/mm.h>
 #include <linux/msi.h>
 #include <uapi/linux/iommufd.h>
+#include <linux/generic_pt/iommu.h>
 
 #include "dma-iommu.h"
 #include "iommu-priv.h"
@@ -2666,13 +2667,12 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 }
 EXPORT_SYMBOL_GPL(iommu_map);
 
-static size_t __iommu_unmap(struct iommu_domain *domain,
-			    unsigned long iova, size_t size,
-			    struct iommu_iotlb_gather *iotlb_gather)
+static size_t
+__iommu_unmap_domain_pgtbl(struct iommu_domain *domain, unsigned long iova,
+			   size_t size, struct iommu_iotlb_gather *iotlb_gather)
 {
 	const struct iommu_domain_ops *ops = domain->ops;
 	size_t unmapped_page, unmapped = 0;
-	unsigned long orig_iova = iova;
 	unsigned int min_pagesz;
 
 	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
@@ -2718,8 +2718,23 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 		unmapped += unmapped_page;
 	}
 
-	trace_unmap(orig_iova, size, unmapped);
-	iommu_debug_unmap_end(domain, orig_iova, size, unmapped);
+	return unmapped;
+}
+
+static size_t __iommu_unmap(struct iommu_domain *domain, unsigned long iova,
+			    size_t size,
+			    struct iommu_iotlb_gather *iotlb_gather)
+{
+	struct pt_iommu *pt = iommupt_from_domain(domain);
+	size_t unmapped;
+
+	if (pt)
+		unmapped = pt->ops->unmap_range(pt, iova, size, iotlb_gather);
+	else
+		unmapped = __iommu_unmap_domain_pgtbl(domain, iova, size,
+						      iotlb_gather);
+	trace_unmap(iova, size, unmapped);
+	iommu_debug_unmap_end(domain, iova, size, unmapped);
 	return unmapped;
 }
 
diff --git a/include/linux/generic_pt/iommu.h b/include/linux/generic_pt/iommu.h
index 49d9addb98c5..0da971134a37 100644
--- a/include/linux/generic_pt/iommu.h
+++ b/include/linux/generic_pt/iommu.h
@@ -66,6 +66,13 @@ struct pt_iommu {
 	struct device *iommu_device;
 };
 
+static inline struct pt_iommu *iommupt_from_domain(struct iommu_domain *domain)
+{
+	if (!IS_ENABLED(CONFIG_IOMMU_PT) || !domain->is_iommupt)
+		return NULL;
+	return container_of(domain, struct pt_iommu, domain);
+}
+
 /**
  * struct pt_iommu_info - Details about the IOMMU page table
  *
@@ -81,6 +88,29 @@ struct pt_iommu_info {
 
 struct pt_iommu_ops {
 	/**
+	 * @unmap_range: Make a range of IOVA empty/not present
+	 * @iommu_table: Table to manipulate
+	 * @iova: IO virtual address to start
+	 * @len: Length of the range starting from @iova
+	 * @iotlb_gather: Gather struct that must be flushed on return
+	 *
+	 * unmap_range() will remove a translation created by map_range(). It
+	 * cannot subdivide a mapping created by map_range(), so it should be
+	 * called with IOVA ranges that match those passed to map_pages. The
+	 * IOVA range can aggregate contiguous map_range() calls so long as no
+	 * individual range is split.
+	 *
+	 * Context: The caller must hold a write range lock that includes
+	 * the whole range.
+	 *
+	 * Returns: Number of bytes of VA unmapped. iova + res will be the
+	 * point unmapping stopped.
+	 */
+	size_t (*unmap_range)(struct pt_iommu *iommu_table, dma_addr_t iova,
+			      dma_addr_t len,
+			      struct iommu_iotlb_gather *iotlb_gather);
+
+	/**
 	 * @set_dirty: Make the iova write dirty
 	 * @iommu_table: Table to manipulate
 	 * @iova: IO virtual address to start
@@ -198,10 +228,6 @@ struct pt_iommu_cfg {
 				       unsigned long iova, phys_addr_t paddr,  \
 				       size_t pgsize, size_t pgcount,          \
 				       int prot, gfp_t gfp, size_t *mapped);   \
-	size_t pt_iommu_##fmt##_unmap_pages(                                   \
-		struct iommu_domain *domain, unsigned long iova,               \
-		size_t pgsize, size_t pgcount,                                 \
-		struct iommu_iotlb_gather *iotlb_gather);                      \
 	int pt_iommu_##fmt##_read_and_clear_dirty(                             \
 		struct iommu_domain *domain, unsigned long iova, size_t size,  \
 		unsigned long flags, struct iommu_dirty_bitmap *dirty);        \
@@ -223,8 +249,7 @@ struct pt_iommu_cfg {
  */
 #define IOMMU_PT_DOMAIN_OPS(fmt)                        \
 	.iova_to_phys = &pt_iommu_##fmt##_iova_to_phys, \
-	.map_pages = &pt_iommu_##fmt##_map_pages,       \
-	.unmap_pages = &pt_iommu_##fmt##_unmap_pages
+	.map_pages = &pt_iommu_##fmt##_map_pages
 #define IOMMU_PT_DIRTY_OPS(fmt) \
 	.read_and_clear_dirty = &pt_iommu_##fmt##_read_and_clear_dirty
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 54b8b48c762e..7ca648c01336 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -223,6 +223,7 @@ enum iommu_domain_cookie_type {
 struct iommu_domain {
 	unsigned type;
 	enum iommu_domain_cookie_type cookie_type;
+	bool is_iommupt;
 	const struct iommu_domain_ops *ops;
 	const struct iommu_dirty_ops *dirty_ops;
 	const struct iommu_ops *owner; /* Whose domain_alloc we came from */