Merge tag 'dma-mapping-5.11' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - support for a partial IOMMU bypass (Alexey Kardashevskiy)

 - add a DMA API benchmark (Barry Song)

 - misc fixes (Tiezhu Yang, tangjianqiang)

* tag 'dma-mapping-5.11' of git://git.infradead.org/users/hch/dma-mapping:
  selftests/dma: add test application for DMA_MAP_BENCHMARK
  dma-mapping: add benchmark support for streaming DMA APIs
  dma-contiguous: fix a typo error in a comment
  dma-pool: no need to check return value of debugfs_create functions
  powerpc/dma: Fallback to dma_ops when persistent memory present
  dma-mapping: Allow mixing bypass and mapped DMA operation

3 files changed, 111 insertions, 12 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index ae7391627054..107bb4319e0e 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -161,6 +161,7 @@ config PPC
 	select DCACHE_WORD_ACCESS		if PPC64 && CPU_LITTLE_ENDIAN
 	select DMA_OPS				if PPC64
 	select DMA_OPS_BYPASS			if PPC64
+	select ARCH_HAS_DMA_MAP_DIRECT 		if PPC64 && PPC_PSERIES
 	select DYNAMIC_FTRACE			if FUNCTION_TRACER
 	select EDAC_ATOMIC_SCRUB
 	select EDAC_SUPPORT
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index a1c744194018..111249fd619d 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -10,6 +10,63 @@
 #include <linux/pci.h>
 #include <asm/iommu.h>
 
+#ifdef CONFIG_ARCH_HAS_DMA_MAP_DIRECT
+#define can_map_direct(dev, addr) \
+	((dev)->bus_dma_limit >= phys_to_dma((dev), (addr)))
+
+bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr)
+{
+	if (likely(!dev->bus_dma_limit))
+		return false;
+
+	return can_map_direct(dev, addr);
+}
+
+#define is_direct_handle(dev, h) ((h) >= (dev)->archdata.dma_offset)
+
+bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle)
+{
+	if (likely(!dev->bus_dma_limit))
+		return false;
+
+	return is_direct_handle(dev, dma_handle);
+}
+
+bool arch_dma_map_sg_direct(struct device *dev, struct scatterlist *sg,
+			    int nents)
+{
+	struct scatterlist *s;
+	int i;
+
+	if (likely(!dev->bus_dma_limit))
+		return false;
+
+	for_each_sg(sg, s, nents, i) {
+		if (!can_map_direct(dev, sg_phys(s) + s->offset + s->length))
+			return false;
+	}
+
+	return true;
+}
+
+bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
+			      int nents)
+{
+	struct scatterlist *s;
+	int i;
+
+	if (likely(!dev->bus_dma_limit))
+		return false;
+
+	for_each_sg(sg, s, nents, i) {
+		if (!is_direct_handle(dev, s->dma_address + s->length))
+			return false;
+	}
+
+	return true;
+}
+#endif /* CONFIG_ARCH_HAS_DMA_MAP_DIRECT */
+
 /*
  * Generic iommu implementation
  */
@@ -90,8 +147,18 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask)
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 
 	if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
-		dev->dma_ops_bypass = true;
-		dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
+		/*
+		 * dma_iommu_bypass_supported() sets dma_max when there is
+		 * 1:1 mapping but it is somehow limited.
+		 * ibm,pmemory is one example.
+		 */
+		dev->dma_ops_bypass = dev->bus_dma_limit == 0;
+		if (!dev->dma_ops_bypass)
+			dev_warn(dev,
+				 "iommu: 64-bit OK but direct DMA is limited by %llx\n",
+				 dev->bus_dma_limit);
+		else
+			dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
 		return 1;
 	}
 
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index e4198700ed1a..9fc5217f0c8e 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -839,7 +839,7 @@ static void remove_ddw(struct device_node *np, bool remove_prop)
 			np, ret);
 }
 
-static u64 find_existing_ddw(struct device_node *pdn)
+static u64 find_existing_ddw(struct device_node *pdn, int *window_shift)
 {
 	struct direct_window *window;
 	const struct dynamic_dma_window_prop *direct64;
@@ -851,6 +851,7 @@ static u64 find_existing_ddw(struct device_node *pdn)
 		if (window->device == pdn) {
 			direct64 = window->prop;
 			dma_addr = be64_to_cpu(direct64->dma_base);
+			*window_shift = be32_to_cpu(direct64->window_shift);
 			break;
 		}
 	}
@@ -1111,11 +1112,12 @@ static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn)
  */
 static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 {
-	int len, ret;
+	int len = 0, ret;
+	int max_ram_len = order_base_2(ddw_memory_hotplug_max());
 	struct ddw_query_response query;
 	struct ddw_create_response create;
 	int page_shift;
-	u64 dma_addr, max_addr;
+	u64 dma_addr;
 	struct device_node *dn;
 	u32 ddw_avail[DDW_APPLICABLE_SIZE];
 	struct direct_window *window;
@@ -1123,10 +1125,15 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	struct dynamic_dma_window_prop *ddwprop;
 	struct failed_ddw_pdn *fpdn;
 	bool default_win_removed = false;
+	bool pmem_present;
+
+	dn = of_find_node_by_type(NULL, "ibm,pmemory");
+	pmem_present = dn != NULL;
+	of_node_put(dn);
 
 	mutex_lock(&direct_window_init_mutex);
 
-	dma_addr = find_existing_ddw(pdn);
+	dma_addr = find_existing_ddw(pdn, &len);
 	if (dma_addr != 0)
 		goto out_unlock;
 
@@ -1212,14 +1219,29 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	}
 	/* verify the window * number of ptes will map the partition */
 	/* check largest block * page size > max memory hotplug addr */
-	max_addr = ddw_memory_hotplug_max();
-	if (query.largest_available_block < (max_addr >> page_shift)) {
-		dev_dbg(&dev->dev, "can't map partition max 0x%llx with %llu "
-			  "%llu-sized pages\n", max_addr,  query.largest_available_block,
-			  1ULL << page_shift);
+	/*
+	 * The "ibm,pmemory" can appear anywhere in the address space.
+	 * Assuming it is still backed by page structs, try MAX_PHYSMEM_BITS
+	 * for the upper limit and fallback to max RAM otherwise but this
+	 * disables device::dma_ops_bypass.
+	 */
+	len = max_ram_len;
+	if (pmem_present) {
+		if (query.largest_available_block >=
+		    (1ULL << (MAX_PHYSMEM_BITS - page_shift)))
+			len = MAX_PHYSMEM_BITS - page_shift;
+		else
+			dev_info(&dev->dev, "Skipping ibm,pmemory");
+	}
+
+	if (query.largest_available_block < (1ULL << (len - page_shift))) {
+		dev_dbg(&dev->dev,
+			"can't map partition max 0x%llx with %llu %llu-sized pages\n",
+			1ULL << len,
+			query.largest_available_block,
+			1ULL << page_shift);
 		goto out_failed;
 	}
-	len = order_base_2(max_addr);
 	win64 = kzalloc(sizeof(struct property), GFP_KERNEL);
 	if (!win64) {
 		dev_info(&dev->dev,
@@ -1299,6 +1321,15 @@ out_failed:
 
 out_unlock:
 	mutex_unlock(&direct_window_init_mutex);
+
+	/*
+	 * If we have persistent memory and the window size is only as big
+	 * as RAM, then we failed to create a window to cover persistent
+	 * memory and need to set the DMA limit.
+	 */
+	if (pmem_present && dma_addr && (len == max_ram_len))
+		dev->dev.bus_dma_limit = dma_addr + (1ULL << len);
+
 	return dma_addr;
 }