x86/dma: Use DMA-direct (CONFIG_DMA_DIRECT_OPS=y)

The generic DMA-direct (CONFIG_DMA_DIRECT_OPS=y) implementation is now
functionally equivalent to the x86 nommu dma_map implementation, so
switch over to using it.

That includes switching from using x86_dma_supported in various IOMMU
drivers to use dma_direct_supported instead, which provides the same
functionality.

Tested-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Jon Mason <jdmason@kudzu.us>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Muli Ben-Yehuda <mulix@mulix.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: iommu@lists.linux-foundation.org
Link: http://lkml.kernel.org/r/20180319103826.12853-4-hch@lst.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

9 files changed, 11 insertions, 86 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 18233e4..7dc3472 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -83,6 +83,7 @@ config X86
 	select CLOCKSOURCE_VALIDATE_LAST_CYCLE
 	select CLOCKSOURCE_WATCHDOG
 	select DCACHE_WORD_ACCESS
+	select DMA_DIRECT_OPS
 	select EDAC_ATOMIC_SCRUB
 	select EDAC_SUPPORT
 	select GENERIC_CLOCKEVENTS
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 545bf37..df9816b 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -36,14 +36,6 @@ int arch_dma_supported(struct device *dev, u64 mask);
 bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp);
 #define arch_dma_alloc_attrs arch_dma_alloc_attrs
 
-extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-					dma_addr_t *dma_addr, gfp_t flag,
-					unsigned long attrs);
-
-extern void dma_generic_free_coherent(struct device *dev, size_t size,
-				      void *vaddr, dma_addr_t dma_addr,
-				      unsigned long attrs);
-
 static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
 {
 	if (dev->coherent_dma_mask <= DMA_BIT_MASK(24))
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 1e5d5d9..baedab8 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -2,13 +2,10 @@
 #ifndef _ASM_X86_IOMMU_H
 #define _ASM_X86_IOMMU_H
 
-extern const struct dma_map_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
 extern int iommu_pass_through;
 
-int x86_dma_supported(struct device *dev, u64 mask);
-
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
 
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 29786c8..2e8c8a0 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -57,7 +57,7 @@ obj-$(CONFIG_X86_ESPFIX64)	+= espfix_64.o
 obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
-obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
+obj-y			+= alternative.o i8253.o hw_breakpoint.o
 obj-y			+= tsc.o tsc_msr.o io_delay.o rtc.o
 obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index ecd486c..52e3abc 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -501,8 +501,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 		}
 		__free_pages(page, get_order(size));
 	} else
-		return dma_generic_alloc_coherent(dev, size, dma_addr, flag,
-						  attrs);
+		return dma_direct_alloc(dev, size, dma_addr, flag, attrs);
 
 	return NULL;
 }
@@ -513,7 +512,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr,
 		   dma_addr_t dma_addr, unsigned long attrs)
 {
 	gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, 0);
-	dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs);
+	dma_direct_free(dev, size, vaddr, dma_addr, attrs);
 }
 
 static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr)
@@ -705,7 +704,7 @@ static const struct dma_map_ops gart_dma_ops = {
 	.alloc				= gart_alloc_coherent,
 	.free				= gart_free_coherent,
 	.mapping_error			= gart_mapping_error,
-	.dma_supported			= x86_dma_supported,
+	.dma_supported			= dma_direct_supported,
 };
 
 static void gart_iommu_shutdown(void)
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 35c461f..5647853 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -33,6 +33,7 @@
 #include <linux/string.h>
 #include <linux/crash_dump.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <linux/bitmap.h>
 #include <linux/pci_ids.h>
 #include <linux/pci.h>
@@ -493,7 +494,7 @@ static const struct dma_map_ops calgary_dma_ops = {
 	.map_page = calgary_map_page,
 	.unmap_page = calgary_unmap_page,
 	.mapping_error = calgary_mapping_error,
-	.dma_supported = x86_dma_supported,
+	.dma_supported = dma_direct_supported,
 };
 
 static inline void __iomem * busno_to_bbar(unsigned char num)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index b598208..db0b88e 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -18,7 +18,7 @@
 
 static int forbid_dac __read_mostly;
 
-const struct dma_map_ops *dma_ops = &nommu_dma_ops;
+const struct dma_map_ops *dma_ops = &dma_direct_ops;
 EXPORT_SYMBOL(dma_ops);
 
 static int iommu_sac_force __read_mostly;
@@ -76,60 +76,6 @@ void __init pci_iommu_alloc(void)
 		}
 	}
 }
-void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-				 dma_addr_t *dma_addr, gfp_t flag,
-				 unsigned long attrs)
-{
-	struct page *page;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	dma_addr_t addr;
-
-again:
-	page = NULL;
-	/* CMA can be used only in the context which permits sleeping */
-	if (gfpflags_allow_blocking(flag)) {
-		page = dma_alloc_from_contiguous(dev, count, get_order(size),
-						 flag);
-		if (page) {
-			addr = phys_to_dma(dev, page_to_phys(page));
-			if (addr + size > dev->coherent_dma_mask) {
-				dma_release_from_contiguous(dev, page, count);
-				page = NULL;
-			}
-		}
-	}
-	/* fallback */
-	if (!page)
-		page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
-	if (!page)
-		return NULL;
-
-	addr = phys_to_dma(dev, page_to_phys(page));
-	if (addr + size > dev->coherent_dma_mask) {
-		__free_pages(page, get_order(size));
-
-		if (dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
-		    !(flag & GFP_DMA)) {
-			flag = (flag & ~GFP_DMA32) | GFP_DMA;
-			goto again;
-		}
-
-		return NULL;
-	}
-	memset(page_address(page), 0, size);
-	*dma_addr = addr;
-	return page_address(page);
-}
-
-void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
-			       dma_addr_t dma_addr, unsigned long attrs)
-{
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct page *page = virt_to_page(vaddr);
-
-	if (!dma_release_from_contiguous(dev, page, count))
-		free_pages((unsigned long)vaddr, get_order(size));
-}
 
 bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp)
 {
@@ -243,16 +189,6 @@ int arch_dma_supported(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(arch_dma_supported);
 
-int x86_dma_supported(struct device *dev, u64 mask)
-{
-	/* Copied from i386. Doesn't make much sense, because it will
-	   only work for pci_alloc_coherent.
-	   The caller just has to use GFP_DMA in this case. */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-	return 1;
-}
-
 static int __init pci_iommu_init(void)
 {
 	struct iommu_table_entry *p;
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 0ee0f8f3..bcb6a9b 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -30,8 +30,7 @@ void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	 */
 	flags |= __GFP_NOWARN;
 
-	vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags,
-					   attrs);
+	vaddr = dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
 	if (vaddr)
 		return vaddr;
 
@@ -45,7 +44,7 @@ void x86_swiotlb_free_coherent(struct device *dev, size_t size,
 	if (is_swiotlb_buffer(dma_to_phys(dev, dma_addr)))
 		swiotlb_free_coherent(dev, size, vaddr, dma_addr);
 	else
-		dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs);
+		dma_direct_free(dev, size, vaddr, dma_addr, attrs);
 }
 
 static const struct dma_map_ops x86_swiotlb_dma_ops = {
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index 75577c1..6c712fe 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -193,7 +193,7 @@ static const struct dma_map_ops sta2x11_dma_ops = {
 	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
 	.sync_sg_for_device = swiotlb_sync_sg_for_device,
 	.mapping_error = swiotlb_dma_mapping_error,
-	.dma_supported = x86_dma_supported,
+	.dma_supported = dma_direct_supported,
 };
 
 /* At setup time, we use our own ops if the device is a ConneXt one */