Merge tag 'dma-mapping-5.2' of git://git.infradead.org/users/hch/dma-mapping

Pull DMA mapping updates from Christoph Hellwig:

 - remove the already broken support for NULL dev arguments to the DMA
   API calls

 - Kconfig tidyups

* tag 'dma-mapping-5.2' of git://git.infradead.org/users/hch/dma-mapping:
  dma-mapping: add a Kconfig symbol to indicate arch_dma_prep_coherent presence
  dma-mapping: remove an unnecessary NULL check
  x86/dma: Remove the x86_dma_fallback_dev hack
  dma-mapping: remove leftover NULL device support
  arm: use a dummy struct device for ISA DMA use of the DMA API
  pxa3xx-gcu: pass struct device to dma_mmap_coherent
  gbefb: switch to managed version of the DMA allocator
  da8xx-fb: pass struct device to DMA API functions
  parport_ip32: pass struct device to DMA API functions
  dma: select GENERIC_ALLOCATOR for DMA_REMAP

Documentation/DMA-API-HOWTO.txt

@@ -365,13 +365,12 @@ __get_free_pages() (but takes size instead of a page order).  If your
 driver needs regions sized smaller than a page, you may prefer using
 the dma_pool interface, described below.
 
-The consistent DMA mapping interfaces, for non-NULL dev, will by
-default return a DMA address which is 32-bit addressable.  Even if the
-device indicates (via DMA mask) that it may address the upper 32-bits,
-consistent allocation will only return > 32-bit addresses for DMA if
-the consistent DMA mask has been explicitly changed via
-dma_set_coherent_mask().  This is true of the dma_pool interface as
-well.
+The consistent DMA mapping interfaces, will by default return a DMA address
+which is 32-bit addressable.  Even if the device indicates (via the DMA mask)
+that it may address the upper 32-bits, consistent allocation will only
+return > 32-bit addresses for DMA if the consistent DMA mask has been
+explicitly changed via dma_set_coherent_mask().  This is true of the
+dma_pool interface as well.
 
 dma_alloc_coherent() returns two values: the virtual address which you
 can use to access it from the CPU and dma_handle which you pass to the

arch/arm/kernel/dma-isa.c

@@ -55,6 +55,12 @@ static int isa_get_dma_residue(unsigned int chan, dma_t *dma)
 	return chan < 4 ? count : (count << 1);
 }
 
+static struct device isa_dma_dev = {
+	.init_name		= "fallback device",
+	.coherent_dma_mask	= ~(dma_addr_t)0,
+	.dma_mask		= &isa_dma_dev.coherent_dma_mask,
+};
+
 static void isa_enable_dma(unsigned int chan, dma_t *dma)
 {
 	if (dma->invalid) {
@@ -89,7 +95,7 @@ static void isa_enable_dma(unsigned int chan, dma_t *dma)
 			dma->sg = &dma->buf;
 			dma->sgcount = 1;
 			dma->buf.length = dma->count;
-			dma->buf.dma_address = dma_map_single(NULL,
+			dma->buf.dma_address = dma_map_single(&isa_dma_dev,
 				dma->addr, dma->count,
 				direction);
 		}

arch/arm/mach-rpc/dma.c

@@ -151,6 +151,12 @@ static void iomd_free_dma(unsigned int chan, dma_t *dma)
 	free_irq(idma->irq, idma);
 }
 
+static struct device isa_dma_dev = {
+	.init_name		= "fallback device",
+	.coherent_dma_mask	= ~(dma_addr_t)0,
+	.dma_mask		= &isa_dma_dev.coherent_dma_mask,
+};
+
 static void iomd_enable_dma(unsigned int chan, dma_t *dma)
 {
 	struct iomd_dma *idma = container_of(dma, struct iomd_dma, dma);
@@ -168,7 +174,7 @@ static void iomd_enable_dma(unsigned int chan, dma_t *dma)
 			idma->dma.sg = &idma->dma.buf;
 			idma->dma.sgcount = 1;
 			idma->dma.buf.length = idma->dma.count;
-			idma->dma.buf.dma_address = dma_map_single(NULL,
+			idma->dma.buf.dma_address = dma_map_single(&isa_dma_dev,
 				idma->dma.addr, idma->dma.count,
 				idma->dma.dma_mode == DMA_MODE_READ ?
 				DMA_FROM_DEVICE : DMA_TO_DEVICE);

arch/arm64/Kconfig

@@ -13,6 +13,7 @@ config ARM64
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_DMA_COHERENT_TO_PFN
 	select ARCH_HAS_DMA_MMAP_PGPROT
+	select ARCH_HAS_DMA_PREP_COHERENT
 	select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FAST_MULTIPLIER

arch/csky/Kconfig

 config CSKY
 	def_bool y
 	select ARCH_32BIT_OFF_T
+	select ARCH_HAS_DMA_PREP_COHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_USE_BUILTIN_BSWAP

arch/x86/include/asm/dma-mapping.h

@@ -13,14 +13,7 @@
 #include <asm/swiotlb.h>
 #include <linux/dma-contiguous.h>
 
-#ifdef CONFIG_ISA
-# define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
-#else
-# define ISA_DMA_BIT_MASK DMA_BIT_MASK(32)
-#endif
-
 extern int iommu_merge;
-extern struct device x86_dma_fallback_dev;
 extern int panic_on_overflow;
 
 extern const struct dma_map_ops *dma_ops;
@@ -30,7 +23,4 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return dma_ops;
 }
 
-bool arch_dma_alloc_attrs(struct device **dev);
-#define arch_dma_alloc_attrs arch_dma_alloc_attrs
-
 #endif

arch/x86/kernel/amd_gart_64.c

@@ -233,9 +233,6 @@ static dma_addr_t gart_map_page(struct device *dev, struct page *page,
 	unsigned long bus;
 	phys_addr_t paddr = page_to_phys(page) + offset;
 
-	if (!dev)
-		dev = &x86_dma_fallback_dev;
-
 	if (!need_iommu(dev, paddr, size))
 		return paddr;
 
@@ -392,9 +389,6 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	if (nents == 0)
 		return 0;
 
-	if (!dev)
-		dev = &x86_dma_fallback_dev;
-
 	out		= 0;
 	start		= 0;
 	start_sg	= sg;

arch/x86/kernel/pci-dma.c

@@ -51,14 +51,6 @@ int iommu_pass_through __read_mostly;
 
 extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
 
-/* Dummy device used for NULL arguments (normally ISA). */
-struct device x86_dma_fallback_dev = {
-	.init_name = "fallback device",
-	.coherent_dma_mask = ISA_DMA_BIT_MASK,
-	.dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
-};
-EXPORT_SYMBOL(x86_dma_fallback_dev);
-
 void __init pci_iommu_alloc(void)
 {
 	struct iommu_table_entry *p;
@@ -77,18 +69,6 @@ void __init pci_iommu_alloc(void)
 	}
 }
 
-bool arch_dma_alloc_attrs(struct device **dev)
-{
-	if (!*dev)
-		*dev = &x86_dma_fallback_dev;
-
-	if (!is_device_dma_capable(*dev))
-		return false;
-	return true;
-
-}
-EXPORT_SYMBOL(arch_dma_alloc_attrs);
-
 /*
  * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
  * parameter documentation.

drivers/parport/parport_ip32.c

@@ -568,6 +568,7 @@ static irqreturn_t parport_ip32_merr_interrupt(int irq, void *dev_id)
 
 /**
  * parport_ip32_dma_start - begins a DMA transfer
+ * @p:		partport to work on
  * @dir:	DMA direction: DMA_TO_DEVICE or DMA_FROM_DEVICE
  * @addr:	pointer to data buffer
  * @count:	buffer size
@@ -575,8 +576,8 @@ static irqreturn_t parport_ip32_merr_interrupt(int irq, void *dev_id)
  * Calls to parport_ip32_dma_start() and parport_ip32_dma_stop() must be
  * correctly balanced.
  */
-static int parport_ip32_dma_start(enum dma_data_direction dir,
-				  void *addr, size_t count)
+static int parport_ip32_dma_start(struct parport *p,
+		enum dma_data_direction dir, void *addr, size_t count)
 {
 	unsigned int limit;
 	u64 ctrl;
@@ -601,7 +602,7 @@ static int parport_ip32_dma_start(enum dma_data_direction dir,
 
 	/* Prepare DMA pointers */
 	parport_ip32_dma.dir = dir;
-	parport_ip32_dma.buf = dma_map_single(NULL, addr, count, dir);
+	parport_ip32_dma.buf = dma_map_single(&p->bus_dev, addr, count, dir);
 	parport_ip32_dma.len = count;
 	parport_ip32_dma.next = parport_ip32_dma.buf;
 	parport_ip32_dma.left = parport_ip32_dma.len;
@@ -625,11 +626,12 @@ static int parport_ip32_dma_start(enum dma_data_direction dir,
 
 /**
  * parport_ip32_dma_stop - ends a running DMA transfer
+ * @p:		partport to work on
  *
  * Calls to parport_ip32_dma_start() and parport_ip32_dma_stop() must be
  * correctly balanced.
  */
-static void parport_ip32_dma_stop(void)
+static void parport_ip32_dma_stop(struct parport *p)
 {
 	u64 ctx_a;
 	u64 ctx_b;
@@ -685,8 +687,8 @@ static void parport_ip32_dma_stop(void)
 	enable_irq(MACEISA_PAR_CTXB_IRQ);
 	parport_ip32_dma.irq_on = 1;
 
-	dma_unmap_single(NULL, parport_ip32_dma.buf, parport_ip32_dma.len,
-			 parport_ip32_dma.dir);
+	dma_unmap_single(&p->bus_dev, parport_ip32_dma.buf,
+			 parport_ip32_dma.len, parport_ip32_dma.dir);
 }
 
 /**
@@ -1445,7 +1447,7 @@ static size_t parport_ip32_fifo_write_block_dma(struct parport *p,
 
 	priv->irq_mode = PARPORT_IP32_IRQ_HERE;
 
-	parport_ip32_dma_start(DMA_TO_DEVICE, (void *)buf, len);
+	parport_ip32_dma_start(p, DMA_TO_DEVICE, (void *)buf, len);
 	reinit_completion(&priv->irq_complete);
 	parport_ip32_frob_econtrol(p, ECR_DMAEN | ECR_SERVINTR, ECR_DMAEN);
 
@@ -1461,7 +1463,7 @@ static size_t parport_ip32_fifo_write_block_dma(struct parport *p,
 		if (ecr & ECR_SERVINTR)
 			break;	/* DMA transfer just finished */
 	}
-	parport_ip32_dma_stop();
+	parport_ip32_dma_stop(p);
 	written = len - parport_ip32_dma_get_residue();
 
 	priv->irq_mode = PARPORT_IP32_IRQ_FWD;

drivers/video/fbdev/da8xx-fb.c

@@ -1097,9 +1097,9 @@ static int fb_remove(struct platform_device *dev)
 
 		unregister_framebuffer(info);
 		fb_dealloc_cmap(&info->cmap);
-		dma_free_coherent(NULL, PALETTE_SIZE, par->v_palette_base,
+		dma_free_coherent(par->dev, PALETTE_SIZE, par->v_palette_base,
 				  par->p_palette_base);
-		dma_free_coherent(NULL, par->vram_size, par->vram_virt,
+		dma_free_coherent(par->dev, par->vram_size, par->vram_virt,
 				  par->vram_phys);
 		pm_runtime_put_sync(&dev->dev);
 		pm_runtime_disable(&dev->dev);
@@ -1425,7 +1425,7 @@ static int fb_probe(struct platform_device *device)
 	par->vram_size = roundup(par->vram_size/8, ulcm);
 	par->vram_size = par->vram_size * LCD_NUM_BUFFERS;
 
-	par->vram_virt = dma_alloc_coherent(NULL,
+	par->vram_virt = dma_alloc_coherent(par->dev,
 					    par->vram_size,
 					    &par->vram_phys,
 					    GFP_KERNEL | GFP_DMA);
@@ -1446,7 +1446,7 @@ static int fb_probe(struct platform_device *device)
 		da8xx_fb_fix.line_length - 1;
 
 	/* allocate palette buffer */
-	par->v_palette_base = dma_alloc_coherent(NULL, PALETTE_SIZE,
+	par->v_palette_base = dma_alloc_coherent(par->dev, PALETTE_SIZE,
 						 &par->p_palette_base,
 						 GFP_KERNEL | GFP_DMA);
 	if (!par->v_palette_base) {
@@ -1532,11 +1532,12 @@ static int fb_probe(struct platform_device *device)
 	fb_dealloc_cmap(&da8xx_fb_info->cmap);
 
 err_release_pl_mem:
-	dma_free_coherent(NULL, PALETTE_SIZE, par->v_palette_base,
+	dma_free_coherent(par->dev, PALETTE_SIZE, par->v_palette_base,
 			  par->p_palette_base);
 
 err_release_fb_mem:
-	dma_free_coherent(NULL, par->vram_size, par->vram_virt, par->vram_phys);
+	dma_free_coherent(par->dev, par->vram_size, par->vram_virt,
+		          par->vram_phys);
 
 err_release_fb:
 	framebuffer_release(da8xx_fb_info);

drivers/video/fbdev/gbefb.c

@@ -1162,9 +1162,9 @@ static int gbefb_probe(struct platform_device *p_dev)
 	}
 	gbe_revision = gbe->ctrlstat & 15;
 
-	gbe_tiles.cpu =
-		dma_alloc_coherent(NULL, GBE_TLB_SIZE * sizeof(uint16_t),
-				   &gbe_tiles.dma, GFP_KERNEL);
+	gbe_tiles.cpu = dmam_alloc_coherent(&p_dev->dev,
+				GBE_TLB_SIZE * sizeof(uint16_t),
+				&gbe_tiles.dma, GFP_KERNEL);
 	if (!gbe_tiles.cpu) {
 		printk(KERN_ERR "gbefb: couldn't allocate tiles table\n");
 		ret = -ENOMEM;
@@ -1178,19 +1178,20 @@ static int gbefb_probe(struct platform_device *p_dev)
 		if (!gbe_mem) {
 			printk(KERN_ERR "gbefb: couldn't map framebuffer\n");
 			ret = -ENOMEM;
-			goto out_tiles_free;
+			goto out_release_mem_region;
 		}
 
 		gbe_dma_addr = 0;
 	} else {
 		/* try to allocate memory with the classical allocator
 		 * this has high chance to fail on low memory machines */
-		gbe_mem = dma_alloc_wc(NULL, gbe_mem_size, &gbe_dma_addr,
-				       GFP_KERNEL);
+		gbe_mem = dmam_alloc_attrs(&p_dev->dev, gbe_mem_size,
+				&gbe_dma_addr, GFP_KERNEL,
+				DMA_ATTR_WRITE_COMBINE);
 		if (!gbe_mem) {
 			printk(KERN_ERR "gbefb: couldn't allocate framebuffer memory\n");
 			ret = -ENOMEM;
-			goto out_tiles_free;
+			goto out_release_mem_region;
 		}
 
 		gbe_mem_phys = (unsigned long) gbe_dma_addr;
@@ -1237,11 +1238,6 @@ static int gbefb_probe(struct platform_device *p_dev)
 
 out_gbe_unmap:
 	arch_phys_wc_del(par->wc_cookie);
-	if (gbe_dma_addr)
-		dma_free_wc(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
-out_tiles_free:
-	dma_free_coherent(NULL, GBE_TLB_SIZE * sizeof(uint16_t),
-			  (void *)gbe_tiles.cpu, gbe_tiles.dma);
 out_release_mem_region:
 	release_mem_region(GBE_BASE, sizeof(struct sgi_gbe));
 out_release_framebuffer:
@@ -1258,10 +1254,6 @@ static int gbefb_remove(struct platform_device* p_dev)
 	unregister_framebuffer(info);
 	gbe_turn_off();
 	arch_phys_wc_del(par->wc_cookie);
-	if (gbe_dma_addr)
-		dma_free_wc(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
-	dma_free_coherent(NULL, GBE_TLB_SIZE * sizeof(uint16_t),
-			  (void *)gbe_tiles.cpu, gbe_tiles.dma);
 	release_mem_region(GBE_BASE, sizeof(struct sgi_gbe));
 	gbefb_remove_sysfs(&p_dev->dev);
 	framebuffer_release(info);

drivers/video/fbdev/pxa3xx-gcu.c

@@ -96,6 +96,7 @@ struct pxa3xx_gcu_batch {
 };
 
 struct pxa3xx_gcu_priv {
+	struct device		 *dev;
 	void __iomem		 *mmio_base;
 	struct clk		 *clk;
 	struct pxa3xx_gcu_shared *shared;
@@ -493,7 +494,7 @@ pxa3xx_gcu_mmap(struct file *file, struct vm_area_struct *vma)
 		if (size != SHARED_SIZE)
 			return -EINVAL;
 
-		return dma_mmap_coherent(NULL, vma,
+		return dma_mmap_coherent(priv->dev, vma,
 			priv->shared, priv->shared_phys, size);
 
 	case SHARED_SIZE >> PAGE_SHIFT:
@@ -670,6 +671,7 @@ static int pxa3xx_gcu_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, priv);
 	priv->resource_mem = r;
+	priv->dev = dev;
 	pxa3xx_gcu_reset(priv);
 	pxa3xx_gcu_init_debug_timer(priv);
 

include/linux/dma-mapping.h

@@ -267,9 +267,9 @@ size_t dma_direct_max_mapping_size(struct device *dev);
 
 static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	if (dev && dev->dma_ops)
+	if (dev->dma_ops)
 		return dev->dma_ops;
-	return get_arch_dma_ops(dev ? dev->bus : NULL);
+	return get_arch_dma_ops(dev->bus);
 }
 
 static inline void set_dma_ops(struct device *dev,
@@ -650,7 +650,7 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 
 static inline u64 dma_get_mask(struct device *dev)
 {
-	if (dev && dev->dma_mask && *dev->dma_mask)
+	if (dev->dma_mask && *dev->dma_mask)
 		return *dev->dma_mask;
 	return DMA_BIT_MASK(32);
 }

include/linux/dma-noncoherent.h

@@ -72,6 +72,12 @@ static inline void arch_sync_dma_for_cpu_all(struct device *dev)
 }
 #endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */
 
+#ifdef CONFIG_ARCH_HAS_DMA_PREP_COHERENT
 void arch_dma_prep_coherent(struct page *page, size_t size);
+#else
+static inline void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+}
+#endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */
 
 #endif /* _LINUX_DMA_NONCOHERENT_H */

kernel/dma/Kconfig

@@ -38,6 +38,9 @@ config ARCH_HAS_SYNC_DMA_FOR_CPU
 config ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
 	bool
 
+config ARCH_HAS_DMA_PREP_COHERENT
+	bool
+
 config ARCH_HAS_DMA_COHERENT_TO_PFN
 	bool
 
@@ -57,6 +60,7 @@ config SWIOTLB
 
 config DMA_REMAP
 	depends on MMU
+	select GENERIC_ALLOCATOR
 	bool
 
 config DMA_DIRECT_REMAP

kernel/dma/direct.c

@@ -311,7 +311,7 @@ static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr,
 		size_t size)
 {
 	return swiotlb_force != SWIOTLB_FORCE &&
-		(!dev || dma_capable(dev, dma_addr, size));
+		dma_capable(dev, dma_addr, size);
 }
 
 dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,

kernel/dma/mapping.c

@@ -238,17 +238,13 @@ u64 dma_get_required_mask(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dma_get_required_mask);
 
-#ifndef arch_dma_alloc_attrs
-#define arch_dma_alloc_attrs(dev)	(true)
-#endif
-
 void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t flag, unsigned long attrs)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	void *cpu_addr;
 
-	WARN_ON_ONCE(dev && !dev->coherent_dma_mask);
+	WARN_ON_ONCE(!dev->coherent_dma_mask);
 
 	if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr))
 		return cpu_addr;
@@ -256,9 +252,6 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	/* let the implementation decide on the zone to allocate from: */
 	flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
 
-	if (!arch_dma_alloc_attrs(&dev))
-		return NULL;
-
 	if (dma_is_direct(ops))
 		cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs);
 	else if (ops->alloc)