dma-mapping: bypass indirect calls for dma-direct

Avoid expensive indirect calls in the fast path DMA mapping
operations by directly calling the dma_direct_* ops if we are using
the directly mapped DMA operations.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Tony Luck <tony.luck@intel.com>

12 files changed, 13 insertions, 29 deletions

diff --git a/arch/alpha/include/asm/dma-mapping.h b/arch/alpha/include/asm/dma-mapping.h
index 8beeafd4f68e..0ee6a5c99b16 100644
--- a/arch/alpha/include/asm/dma-mapping.h
+++ b/arch/alpha/include/asm/dma-mapping.h
@@ -7,7 +7,7 @@ extern const struct dma_map_ops alpha_pci_ops;
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
 #ifdef CONFIG_ALPHA_JENSEN
-	return &dma_direct_ops;
+	return NULL;
 #else
 	return &alpha_pci_ops;
 #endif
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index f2701c13a66b..e188bb3ede53 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -1280,7 +1280,7 @@ void __init arc_cache_init_master(void)
 	/*
 	 * In case of IOC (say IOC+SLC case), pointers above could still be set
 	 * but end up not being relevant as the first function in chain is not
-	 * called at all for @dma_direct_ops
+	 * called at all for devices using coherent DMA.
 	 *     arch_sync_dma_for_cpu() -> dma_cache_*() -> __dma_cache_*()
 	 */
 }
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 965b7c846ecb..31d3b96f0f4b 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -18,7 +18,7 @@ extern const struct dma_map_ops arm_coherent_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : &dma_direct_ops;
+	return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : NULL;
 }
 
 #ifdef __arch_page_to_dma
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 712416ecd8e6..f304b10e23a4 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -22,7 +22,7 @@
 #include "dma.h"
 
 /*
- *  dma_direct_ops is used if
+ *  The generic direct mapping code is used if
  *   - MMU/MPU is off
  *   - cpu is v7m w/o cache support
  *   - device is coherent
@@ -209,16 +209,9 @@ const struct dma_map_ops arm_nommu_dma_ops = {
 };
 EXPORT_SYMBOL(arm_nommu_dma_ops);
 
-static const struct dma_map_ops *arm_nommu_get_dma_map_ops(bool coherent)
-{
-	return coherent ? &dma_direct_ops : &arm_nommu_dma_ops;
-}
-
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
 {
-	const struct dma_map_ops *dma_ops;
-
 	if (IS_ENABLED(CONFIG_CPU_V7M)) {
 		/*
 		 * Cache support for v7m is optional, so can be treated as
@@ -234,7 +227,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		dev->archdata.dma_coherent = (get_cr() & CR_M) ? coherent : true;
 	}
 
-	dma_ops = arm_nommu_get_dma_map_ops(dev->archdata.dma_coherent);
-
-	set_dma_ops(dev, dma_ops);
+	if (!dev->archdata.dma_coherent)
+		set_dma_ops(dev, &arm_nommu_dma_ops);
 }
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index ab1e417204d0..95eda81e3f2d 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -462,9 +462,6 @@ static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
 {
-	if (!dev->dma_ops)
-		dev->dma_ops = &dma_direct_ops;
-
 	dev->dma_coherent = coherent;
 	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
 
diff --git a/arch/ia64/hp/common/hwsw_iommu.c b/arch/ia64/hp/common/hwsw_iommu.c
index f40ca499b246..8840ed97712f 100644
--- a/arch/ia64/hp/common/hwsw_iommu.c
+++ b/arch/ia64/hp/common/hwsw_iommu.c
@@ -38,7 +38,7 @@ static inline int use_swiotlb(struct device *dev)
 const struct dma_map_ops *hwsw_dma_get_ops(struct device *dev)
 {
 	if (use_swiotlb(dev))
-		return &dma_direct_ops;
+		return NULL;
 	return &sba_dma_ops;
 }
 EXPORT_SYMBOL(hwsw_dma_get_ops);
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 5ee74820a0f6..5a361e51cb1e 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -2078,7 +2078,7 @@ sba_init(void)
 	 * a successful kdump kernel boot is to use the swiotlb.
 	 */
 	if (is_kdump_kernel()) {
-		dma_ops = &dma_direct_ops;
+		dma_ops = NULL;
 		if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0)
 			panic("Unable to initialize software I/O TLB:"
 				  " Try machvec=dig boot option");
@@ -2100,7 +2100,7 @@ sba_init(void)
 		 * If we didn't find something sba_iommu can claim, we
 		 * need to setup the swiotlb and switch to the dig machvec.
 		 */
-		dma_ops = &dma_direct_ops;
+		dma_ops = NULL;
 		if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0)
 			panic("Unable to find SBA IOMMU or initialize "
 			      "software I/O TLB: Try machvec=dig boot option");
diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c
index 80cd3e1ea95a..ad7d9963de34 100644
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -36,7 +36,6 @@ long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
 
 void __init swiotlb_dma_init(void)
 {
-	dma_ops = &dma_direct_ops;
 	swiotlb_init(1);
 }
 #endif
diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index 69f914667f3e..20dfaad3a55d 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -11,7 +11,7 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 #if defined(CONFIG_MACH_JAZZ)
 	return &jazz_dma_ops;
 #else
-	return &dma_direct_ops;
+	return NULL;
 #endif
 }
 
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index cd227f1cf629..54818cd78bd0 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -99,10 +99,6 @@ void __init dma_ops_init(void)
 
 	case pcxl2:
 		pa7300lc_init();
-	case pcxl: /* falls through */
-	case pcxs:
-	case pcxt:
-		hppa_dma_ops = &dma_direct_ops;
 		break;
 	default:
 		break;
diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h
index 55a44f08a9a4..ed32845bd2d2 100644
--- a/arch/sparc/include/asm/dma-mapping.h
+++ b/arch/sparc/include/asm/dma-mapping.h
@@ -12,11 +12,11 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
 #ifdef CONFIG_SPARC_LEON
 	if (sparc_cpu_model == sparc_leon)
-		return &dma_direct_ops;
+		return NULL;
 #endif
 #if defined(CONFIG_SPARC32) && defined(CONFIG_PCI)
 	if (bus == &pci_bus_type)
-		return &dma_direct_ops;
+		return NULL;
 #endif
 	return dma_ops;
 }
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index f4562fcec681..d460998ae828 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -17,7 +17,7 @@
 
 static bool disable_dac_quirk __read_mostly;
 
-const struct dma_map_ops *dma_ops = &dma_direct_ops;
+const struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 #ifdef CONFIG_IOMMU_DEBUG