Merge tag 'dma-mapping-5.3' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - move the USB special case that bounced DMA through a device bar into
   the USB code instead of handling it in the common DMA code (Laurentiu
   Tudor and Fredrik Noring)

 - don't dip into the global CMA pool for single page allocations
   (Nicolin Chen)

 - fix a crash when allocating memory for the atomic pool failed during
   boot (Florian Fainelli)

 - move support for MIPS-style uncached segments to the common code and
   use that for MIPS and nios2 (me)

 - make support for DMA_ATTR_NON_CONSISTENT and
   DMA_ATTR_NO_KERNEL_MAPPING generic (me)

 - convert nds32 to the generic remapping allocator (me)

* tag 'dma-mapping-5.3' of git://git.infradead.org/users/hch/dma-mapping: (29 commits)
  dma-mapping: mark dma_alloc_need_uncached as __always_inline
  MIPS: only select ARCH_HAS_UNCACHED_SEGMENT for non-coherent platforms
  usb: host: Fix excessive alignment restriction for local memory allocations
  lib/genalloc.c: Add algorithm, align and zeroed family of DMA allocators
  nios2: use the generic uncached segment support in dma-direct
  nds32: use the generic remapping allocator for coherent DMA allocations
  arc: use the generic remapping allocator for coherent DMA allocations
  dma-direct: handle DMA_ATTR_NO_KERNEL_MAPPING in common code
  dma-direct: handle DMA_ATTR_NON_CONSISTENT in common code
  dma-mapping: add a dma_alloc_need_uncached helper
  openrisc: remove the partial DMA_ATTR_NON_CONSISTENT support
  arc: remove the partial DMA_ATTR_NON_CONSISTENT support
  arm-nommu: remove the partial DMA_ATTR_NON_CONSISTENT support
  ARM: dma-mapping: allow larger DMA mask than supported
  dma-mapping: truncate dma masks to what dma_addr_t can hold
  iommu/dma: Apply dma_{alloc,free}_contiguous functions
  dma-remap: Avoid de-referencing NULL atomic_pool
  MIPS: use the generic uncached segment support in dma-direct
  dma-direct: provide generic support for uncached kernel segments
  au1100fb: fix DMA API abuse
  ...

14 files changed, 149 insertions, 94 deletions

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index f802255219d3..a7f9c3edbcb2 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -951,8 +951,8 @@ static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
 
 	if (pages)
 		__iommu_dma_free_pages(pages, count);
-	if (page && !dma_release_from_contiguous(dev, page, count))
-		__free_pages(page, get_order(alloc_size));
+	if (page)
+		dma_free_contiguous(dev, page, alloc_size);
 }
 
 static void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
@@ -970,12 +970,7 @@ static void *iommu_dma_alloc_pages(struct device *dev, size_t size,
 	struct page *page = NULL;
 	void *cpu_addr;
 
-	if (gfpflags_allow_blocking(gfp))
-		page = dma_alloc_from_contiguous(dev, alloc_size >> PAGE_SHIFT,
-						 get_order(alloc_size),
-						 gfp & __GFP_NOWARN);
-	if (!page)
-		page = alloc_pages(gfp, get_order(alloc_size));
+	page = dma_alloc_contiguous(dev, alloc_size, gfp);
 	if (!page)
 		return NULL;
 
@@ -997,8 +992,7 @@ static void *iommu_dma_alloc_pages(struct device *dev, size_t size,
 	memset(cpu_addr, 0, alloc_size);
 	return cpu_addr;
 out_free_pages:
-	if (!dma_release_from_contiguous(dev, page, alloc_size >> PAGE_SHIFT))
-		__free_pages(page, get_order(alloc_size));
+	dma_free_contiguous(dev, page, alloc_size);
 	return NULL;
 }
 
diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig
index 94573fb68304..6e59d370ef81 100644
--- a/drivers/usb/Kconfig
+++ b/drivers/usb/Kconfig
@@ -45,6 +45,7 @@ config USB_ARCH_HAS_HCD
 config USB
 	tristate "Support for Host-side USB"
 	depends on USB_ARCH_HAS_HCD
+	select GENERIC_ALLOCATOR
 	select USB_COMMON
 	select NLS  # for UTF-8 strings
 	---help---
diff --git a/drivers/usb/core/buffer.c b/drivers/usb/core/buffer.c
index f641342cdec0..1359b78a624e 100644
--- a/drivers/usb/core/buffer.c
+++ b/drivers/usb/core/buffer.c
@@ -16,6 +16,7 @@
 #include <linux/io.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmapool.h>
+#include <linux/genalloc.h>
 #include <linux/usb.h>
 #include <linux/usb/hcd.h>
 
@@ -67,7 +68,7 @@ int hcd_buffer_create(struct usb_hcd *hcd)
 
 	if (!IS_ENABLED(CONFIG_HAS_DMA) ||
 	    (!is_device_dma_capable(hcd->self.sysdev) &&
-	     !(hcd->driver->flags & HCD_LOCAL_MEM)))
+	     !hcd->localmem_pool))
 		return 0;
 
 	for (i = 0; i < HCD_BUFFER_POOLS; i++) {
@@ -124,10 +125,12 @@ void *hcd_buffer_alloc(
 	if (size == 0)
 		return NULL;
 
+	if (hcd->localmem_pool)
+		return gen_pool_dma_alloc(hcd->localmem_pool, size, dma);
+
 	/* some USB hosts just use PIO */
 	if (!IS_ENABLED(CONFIG_HAS_DMA) ||
-	    (!is_device_dma_capable(bus->sysdev) &&
-	     !(hcd->driver->flags & HCD_LOCAL_MEM))) {
+	    !is_device_dma_capable(bus->sysdev)) {
 		*dma = ~(dma_addr_t) 0;
 		return kmalloc(size, mem_flags);
 	}
@@ -152,9 +155,13 @@ void hcd_buffer_free(
 	if (!addr)
 		return;
 
+	if (hcd->localmem_pool) {
+		gen_pool_free(hcd->localmem_pool, (unsigned long)addr, size);
+		return;
+	}
+
 	if (!IS_ENABLED(CONFIG_HAS_DMA) ||
-	    (!is_device_dma_capable(bus->sysdev) &&
-	     !(hcd->driver->flags & HCD_LOCAL_MEM))) {
+	    !is_device_dma_capable(bus->sysdev)) {
 		kfree(addr);
 		return;
 	}
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 94d22551fc1b..88533938ce19 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -29,6 +29,8 @@
 #include <linux/workqueue.h>
 #include <linux/pm_runtime.h>
 #include <linux/types.h>
+#include <linux/genalloc.h>
+#include <linux/io.h>
 
 #include <linux/phy/phy.h>
 #include <linux/usb.h>
@@ -1345,14 +1347,14 @@ EXPORT_SYMBOL_GPL(usb_hcd_unlink_urb_from_ep);
  * using regular system memory - like pci devices doing bus mastering.
  *
  * To support host controllers with limited dma capabilities we provide dma
- * bounce buffers. This feature can be enabled using the HCD_LOCAL_MEM flag.
+ * bounce buffers. This feature can be enabled by initializing
+ * hcd->localmem_pool using usb_hcd_setup_local_mem().
  * For this to work properly the host controller code must first use the
  * function dma_declare_coherent_memory() to point out which memory area
  * that should be used for dma allocations.
  *
- * The HCD_LOCAL_MEM flag then tells the usb code to allocate all data for
- * dma using dma_alloc_coherent() which in turn allocates from the memory
- * area pointed out with dma_declare_coherent_memory().
+ * The initialized hcd->localmem_pool then tells the usb code to allocate all
+ * data for dma using the genalloc API.
  *
  * So, to summarize...
  *
@@ -1362,9 +1364,6 @@ EXPORT_SYMBOL_GPL(usb_hcd_unlink_urb_from_ep);
  *   (a) "normal" kernel memory is no good, and
  *   (b) there's not enough to share
  *
- * - The only *portable* hook for such stuff in the
- *   DMA framework is dma_declare_coherent_memory()
- *
  * - So we use that, even though the primary requirement
  *   is that the memory be "local" (hence addressable
  *   by that device), not "coherent".
@@ -1531,7 +1530,7 @@ int usb_hcd_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb,
 						urb->setup_dma))
 				return -EAGAIN;
 			urb->transfer_flags |= URB_SETUP_MAP_SINGLE;
-		} else if (hcd->driver->flags & HCD_LOCAL_MEM) {
+		} else if (hcd->localmem_pool) {
 			ret = hcd_alloc_coherent(
 					urb->dev->bus, mem_flags,
 					&urb->setup_dma,
@@ -1601,7 +1600,7 @@ int usb_hcd_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb,
 				else
 					urb->transfer_flags |= URB_DMA_MAP_SINGLE;
 			}
-		} else if (hcd->driver->flags & HCD_LOCAL_MEM) {
+		} else if (hcd->localmem_pool) {
 			ret = hcd_alloc_coherent(
 					urb->dev->bus, mem_flags,
 					&urb->transfer_dma,
@@ -3039,6 +3038,40 @@ usb_hcd_platform_shutdown(struct platform_device *dev)
 }
 EXPORT_SYMBOL_GPL(usb_hcd_platform_shutdown);
 
+int usb_hcd_setup_local_mem(struct usb_hcd *hcd, phys_addr_t phys_addr,
+			    dma_addr_t dma, size_t size)
+{
+	int err;
+	void *local_mem;
+
+	hcd->localmem_pool = devm_gen_pool_create(hcd->self.sysdev, 4,
+						  dev_to_node(hcd->self.sysdev),
+						  dev_name(hcd->self.sysdev));
+	if (IS_ERR(hcd->localmem_pool))
+		return PTR_ERR(hcd->localmem_pool);
+
+	local_mem = devm_memremap(hcd->self.sysdev, phys_addr,
+				  size, MEMREMAP_WC);
+	if (!local_mem)
+		return -ENOMEM;
+
+	/*
+	 * Here we pass a dma_addr_t but the arg type is a phys_addr_t.
+	 * It's not backed by system memory and thus there's no kernel mapping
+	 * for it.
+	 */
+	err = gen_pool_add_virt(hcd->localmem_pool, (unsigned long)local_mem,
+				dma, size, dev_to_node(hcd->self.sysdev));
+	if (err < 0) {
+		dev_err(hcd->self.sysdev, "gen_pool_add_virt failed with %d\n",
+			err);
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(usb_hcd_setup_local_mem);
+
 /*-------------------------------------------------------------------------*/
 
 #if IS_ENABLED(CONFIG_USB_MON)
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index cdafa97f632d..9da7e22848c9 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -559,7 +559,7 @@ static int ehci_init(struct usb_hcd *hcd)
 	ehci->command = temp;
 
 	/* Accept arbitrarily long scatter-gather lists */
-	if (!(hcd->driver->flags & HCD_LOCAL_MEM))
+	if (!hcd->localmem_pool)
 		hcd->self.sg_tablesize = ~0;
 
 	/* Prepare for unlinking active QHs */
diff --git a/drivers/usb/host/fotg210-hcd.c b/drivers/usb/host/fotg210-hcd.c
index e835a22b12af..77cc36efae95 100644
--- a/drivers/usb/host/fotg210-hcd.c
+++ b/drivers/usb/host/fotg210-hcd.c
@@ -4996,7 +4996,7 @@ static int hcd_fotg210_init(struct usb_hcd *hcd)
 	fotg210->command = temp;
 
 	/* Accept arbitrarily long scatter-gather lists */
-	if (!(hcd->driver->flags & HCD_LOCAL_MEM))
+	if (!hcd->localmem_pool)
 		hcd->self.sg_tablesize = ~0;
 	return 0;
 }
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index 210181fd98d2..b457fdaff297 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -40,6 +40,7 @@
 #include <linux/dmapool.h>
 #include <linux/workqueue.h>
 #include <linux/debugfs.h>
+#include <linux/genalloc.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
@@ -447,7 +448,7 @@ static int ohci_init (struct ohci_hcd *ohci)
 	struct usb_hcd *hcd = ohci_to_hcd(ohci);
 
 	/* Accept arbitrarily long scatter-gather lists */
-	if (!(hcd->driver->flags & HCD_LOCAL_MEM))
+	if (!hcd->localmem_pool)
 		hcd->self.sg_tablesize = ~0;
 
 	if (distrust_firmware)
@@ -505,8 +506,15 @@ static int ohci_init (struct ohci_hcd *ohci)
 	timer_setup(&ohci->io_watchdog, io_watchdog_func, 0);
 	ohci->prev_frame_no = IO_WATCHDOG_OFF;
 
-	ohci->hcca = dma_alloc_coherent (hcd->self.controller,
-			sizeof(*ohci->hcca), &ohci->hcca_dma, GFP_KERNEL);
+	if (hcd->localmem_pool)
+		ohci->hcca = gen_pool_dma_alloc_align(hcd->localmem_pool,
+						sizeof(*ohci->hcca),
+						&ohci->hcca_dma, 256);
+	else
+		ohci->hcca = dma_alloc_coherent(hcd->self.controller,
+						sizeof(*ohci->hcca),
+						&ohci->hcca_dma,
+						GFP_KERNEL);
 	if (!ohci->hcca)
 		return -ENOMEM;
 
@@ -990,9 +998,14 @@ static void ohci_stop (struct usb_hcd *hcd)
 	remove_debug_files (ohci);
 	ohci_mem_cleanup (ohci);
 	if (ohci->hcca) {
-		dma_free_coherent (hcd->self.controller,
-				sizeof *ohci->hcca,
-				ohci->hcca, ohci->hcca_dma);
+		if (hcd->localmem_pool)
+			gen_pool_free(hcd->localmem_pool,
+				      (unsigned long)ohci->hcca,
+				      sizeof(*ohci->hcca));
+		else
+			dma_free_coherent(hcd->self.controller,
+					  sizeof(*ohci->hcca),
+					  ohci->hcca, ohci->hcca_dma);
 		ohci->hcca = NULL;
 		ohci->hcca_dma = 0;
 	}
diff --git a/drivers/usb/host/ohci-mem.c b/drivers/usb/host/ohci-mem.c
index 3965ac0341eb..1425335c6baf 100644
--- a/drivers/usb/host/ohci-mem.c
+++ b/drivers/usb/host/ohci-mem.c
@@ -36,6 +36,13 @@ static void ohci_hcd_init (struct ohci_hcd *ohci)
 
 static int ohci_mem_init (struct ohci_hcd *ohci)
 {
+	/*
+	 * HCs with local memory allocate from localmem_pool so there's
+	 * no need to create the below dma pools.
+	 */
+	if (ohci_to_hcd(ohci)->localmem_pool)
+		return 0;
+
 	ohci->td_cache = dma_pool_create ("ohci_td",
 		ohci_to_hcd(ohci)->self.controller,
 		sizeof (struct td),
@@ -84,8 +91,13 @@ td_alloc (struct ohci_hcd *hc, gfp_t mem_flags)
 {
 	dma_addr_t	dma;
 	struct td	*td;
+	struct usb_hcd	*hcd = ohci_to_hcd(hc);
 
-	td = dma_pool_zalloc (hc->td_cache, mem_flags, &dma);
+	if (hcd->localmem_pool)
+		td = gen_pool_dma_zalloc_align(hcd->localmem_pool,
+				sizeof(*td), &dma, 32);
+	else
+		td = dma_pool_zalloc(hc->td_cache, mem_flags, &dma);
 	if (td) {
 		/* in case hc fetches it, make it look dead */
 		td->hwNextTD = cpu_to_hc32 (hc, dma);
@@ -99,6 +111,7 @@ static void
 td_free (struct ohci_hcd *hc, struct td *td)
 {
 	struct td	**prev = &hc->td_hash [TD_HASH_FUNC (td->td_dma)];
+	struct usb_hcd	*hcd = ohci_to_hcd(hc);
 
 	while (*prev && *prev != td)
 		prev = &(*prev)->td_hash;
@@ -106,7 +119,12 @@ td_free (struct ohci_hcd *hc, struct td *td)
 		*prev = td->td_hash;
 	else if ((td->hwINFO & cpu_to_hc32(hc, TD_DONE)) != 0)
 		ohci_dbg (hc, "no hash for td %p\n", td);
-	dma_pool_free (hc->td_cache, td, td->td_dma);
+
+	if (hcd->localmem_pool)
+		gen_pool_free(hcd->localmem_pool, (unsigned long)td,
+			      sizeof(*td));
+	else
+		dma_pool_free(hc->td_cache, td, td->td_dma);
 }
 
 /*-------------------------------------------------------------------------*/
@@ -117,8 +135,13 @@ ed_alloc (struct ohci_hcd *hc, gfp_t mem_flags)
 {
 	dma_addr_t	dma;
 	struct ed	*ed;
+	struct usb_hcd	*hcd = ohci_to_hcd(hc);
 
-	ed = dma_pool_zalloc (hc->ed_cache, mem_flags, &dma);
+	if (hcd->localmem_pool)
+		ed = gen_pool_dma_zalloc_align(hcd->localmem_pool,
+				sizeof(*ed), &dma, 16);
+	else
+		ed = dma_pool_zalloc(hc->ed_cache, mem_flags, &dma);
 	if (ed) {
 		INIT_LIST_HEAD (&ed->td_list);
 		ed->dma = dma;
@@ -129,6 +152,12 @@ ed_alloc (struct ohci_hcd *hc, gfp_t mem_flags)
 static void
 ed_free (struct ohci_hcd *hc, struct ed *ed)
 {
-	dma_pool_free (hc->ed_cache, ed, ed->dma);
+	struct usb_hcd	*hcd = ohci_to_hcd(hc);
+
+	if (hcd->localmem_pool)
+		gen_pool_free(hcd->localmem_pool, (unsigned long)ed,
+			      sizeof(*ed));
+	else
+		dma_pool_free(hc->ed_cache, ed, ed->dma);
 }
 
diff --git a/drivers/usb/host/ohci-sm501.c b/drivers/usb/host/ohci-sm501.c
index c26228c25f99..c158cda9e4b9 100644
--- a/drivers/usb/host/ohci-sm501.c
+++ b/drivers/usb/host/ohci-sm501.c
@@ -49,7 +49,7 @@ static const struct hc_driver ohci_sm501_hc_driver = {
 	 * generic hardware linkage
 	 */
 	.irq =			ohci_irq,
-	.flags =		HCD_USB11 | HCD_MEMORY | HCD_LOCAL_MEM,
+	.flags =		HCD_USB11 | HCD_MEMORY,
 
 	/*
 	 * basic lifecycle operations
@@ -110,40 +110,18 @@ static int ohci_hcd_sm501_drv_probe(struct platform_device *pdev)
 		goto err0;
 	}
 
-	/* The sm501 chip is equipped with local memory that may be used
-	 * by on-chip devices such as the video controller and the usb host.
-	 * This driver uses dma_declare_coherent_memory() to make sure
-	 * usb allocations with dma_alloc_coherent() allocate from
-	 * this local memory. The dma_handle returned by dma_alloc_coherent()
-	 * will be an offset starting from 0 for the first local memory byte.
-	 *
-	 * So as long as data is allocated using dma_alloc_coherent() all is
-	 * fine. This is however not always the case - buffers may be allocated
-	 * using kmalloc() - so the usb core needs to be told that it must copy
-	 * data into our local memory if the buffers happen to be placed in
-	 * regular memory. The HCD_LOCAL_MEM flag does just that.
-	 */
-
-	retval = dma_declare_coherent_memory(dev, mem->start,
-					 mem->start - mem->parent->start,
-					 resource_size(mem));
-	if (retval) {
-		dev_err(dev, "cannot declare coherent memory\n");
-		goto err1;
-	}
-
 	/* allocate, reserve and remap resources for registers */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (res == NULL) {
 		dev_err(dev, "no resource definition for registers\n");
 		retval = -ENOENT;
-		goto err2;
+		goto err1;
 	}
 
 	hcd = usb_create_hcd(driver, &pdev->dev, dev_name(&pdev->dev));
 	if (!hcd) {
 		retval = -ENOMEM;
-		goto err2;
+		goto err1;
 	}
 
 	hcd->rsrc_start = res->start;
@@ -164,6 +142,25 @@ static int ohci_hcd_sm501_drv_probe(struct platform_device *pdev)
 
 	ohci_hcd_init(hcd_to_ohci(hcd));
 
+	/* The sm501 chip is equipped with local memory that may be used
+	 * by on-chip devices such as the video controller and the usb host.
+	 * This driver uses genalloc so that usb allocations with
+	 * gen_pool_dma_alloc() allocate from this local memory. The dma_handle
+	 * returned by gen_pool_dma_alloc() will be an offset starting from 0
+	 * for the first local memory byte.
+	 *
+	 * So as long as data is allocated using gen_pool_dma_alloc() all is
+	 * fine. This is however not always the case - buffers may be allocated
+	 * using kmalloc() - so the usb core needs to be told that it must copy
+	 * data into our local memory if the buffers happen to be placed in
+	 * regular memory. A non-null hcd->localmem_pool initialized by the
+	 * the call to usb_hcd_setup_local_mem() below does just that.
+	 */
+
+	if (usb_hcd_setup_local_mem(hcd, mem->start,
+				    mem->start - mem->parent->start,
+				    resource_size(mem)) < 0)
+		goto err5;
 	retval = usb_add_hcd(hcd, irq, IRQF_SHARED);
 	if (retval)
 		goto err5;
@@ -181,8 +178,6 @@ err4:
 	release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
 err3:
 	usb_put_hcd(hcd);
-err2:
-	dma_release_declared_memory(dev);
 err1:
 	release_mem_region(mem->start, resource_size(mem));
 err0:
@@ -197,7 +192,6 @@ static int ohci_hcd_sm501_drv_remove(struct platform_device *pdev)
 	usb_remove_hcd(hcd);
 	release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
 	usb_put_hcd(hcd);
-	dma_release_declared_memory(&pdev->dev);
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 	if (mem)
 		release_mem_region(mem->start, resource_size(mem));
diff --git a/drivers/usb/host/ohci-tmio.c b/drivers/usb/host/ohci-tmio.c
index f88a0370659f..d5a293a707b6 100644
--- a/drivers/usb/host/ohci-tmio.c
+++ b/drivers/usb/host/ohci-tmio.c
@@ -153,7 +153,7 @@ static const struct hc_driver ohci_tmio_hc_driver = {
 
 	/* generic hardware linkage */
 	.irq =			ohci_irq,
-	.flags =		HCD_USB11 | HCD_MEMORY | HCD_LOCAL_MEM,
+	.flags =		HCD_USB11 | HCD_MEMORY,
 
 	/* basic lifecycle operations */
 	.start =		ohci_tmio_start,
@@ -224,11 +224,6 @@ static int ohci_hcd_tmio_drv_probe(struct platform_device *dev)
 		goto err_ioremap_regs;
 	}
 
-	ret = dma_declare_coherent_memory(&dev->dev, sram->start, sram->start,
-				resource_size(sram));
-	if (ret)
-		goto err_dma_declare;
-
 	if (cell->enable) {
 		ret = cell->enable(dev);
 		if (ret)
@@ -239,6 +234,11 @@ static int ohci_hcd_tmio_drv_probe(struct platform_device *dev)
 	ohci = hcd_to_ohci(hcd);
 	ohci_hcd_init(ohci);
 
+	ret = usb_hcd_setup_local_mem(hcd, sram->start, sram->start,
+				      resource_size(sram));
+	if (ret < 0)
+		goto err_enable;
+
 	ret = usb_add_hcd(hcd, irq, 0);
 	if (ret)
 		goto err_add_hcd;
@@ -254,8 +254,6 @@ err_add_hcd:
 	if (cell->disable)
 		cell->disable(dev);
 err_enable:
-	dma_release_declared_memory(&dev->dev);
-err_dma_declare:
 	iounmap(hcd->regs);
 err_ioremap_regs:
 	iounmap(tmio->ccr);
@@ -276,7 +274,6 @@ static int ohci_hcd_tmio_drv_remove(struct platform_device *dev)
 	tmio_stop_hc(dev);
 	if (cell->disable)
 		cell->disable(dev);
-	dma_release_declared_memory(&dev->dev);
 	iounmap(hcd->regs);
 	iounmap(tmio->ccr);
 	usb_put_hcd(hcd);
diff --git a/drivers/usb/host/ohci.h b/drivers/usb/host/ohci.h
index ef4813bfc5bf..b015b00774b2 100644
--- a/drivers/usb/host/ohci.h
+++ b/drivers/usb/host/ohci.h
@@ -385,6 +385,8 @@ struct ohci_hcd {
 
 	/*
 	 * memory management for queue data structures
+	 *
+	 * @td_cache and @ed_cache are %NULL if &usb_hcd.localmem_pool is used.
 	 */
 	struct dma_pool		*td_cache;
 	struct dma_pool		*ed_cache;
diff --git a/drivers/usb/host/uhci-hcd.c b/drivers/usb/host/uhci-hcd.c
index 98deb5f64268..03bc59755123 100644
--- a/drivers/usb/host/uhci-hcd.c
+++ b/drivers/usb/host/uhci-hcd.c
@@ -581,7 +581,7 @@ static int uhci_start(struct usb_hcd *hcd)
 
 	hcd->uses_new_polling = 1;
 	/* Accept arbitrarily long scatter-gather lists */
-	if (!(hcd->driver->flags & HCD_LOCAL_MEM))
+	if (!hcd->localmem_pool)
 		hcd->self.sg_tablesize = ~0;
 
 	spin_lock_init(&uhci->lock);
diff --git a/drivers/video/fbdev/au1100fb.c b/drivers/video/fbdev/au1100fb.c
index 0adf0683cf08..99941ae1f3a1 100644
--- a/drivers/video/fbdev/au1100fb.c
+++ b/drivers/video/fbdev/au1100fb.c
@@ -340,14 +340,12 @@ int au1100fb_fb_pan_display(struct fb_var_screeninfo *var, struct fb_info *fbi)
  */
 int au1100fb_fb_mmap(struct fb_info *fbi, struct vm_area_struct *vma)
 {
-	struct au1100fb_device *fbdev;
-
-	fbdev = to_au1100fb_device(fbi);
+	struct au1100fb_device *fbdev = to_au1100fb_device(fbi);
 
-	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	pgprot_val(vma->vm_page_prot) |= (6 << 9); //CCA=6
 
-	return vm_iomap_memory(vma, fbdev->fb_phys, fbdev->fb_len);
+	return dma_mmap_coherent(fbdev->dev, vma, fbdev->fb_mem, fbdev->fb_phys,
+			fbdev->fb_len);
 }
 
 static struct fb_ops au1100fb_ops =
@@ -412,7 +410,6 @@ static int au1100fb_drv_probe(struct platform_device *dev)
 {
 	struct au1100fb_device *fbdev;
 	struct resource *regs_res;
-	unsigned long page;
 	struct clk *c;
 
 	/* Allocate new device private */
@@ -424,6 +421,7 @@ static int au1100fb_drv_probe(struct platform_device *dev)
 		goto failed;
 
 	platform_set_drvdata(dev, (void *)fbdev);
+	fbdev->dev = &dev->dev;
 
 	/* Allocate region for our registers and map them */
 	regs_res = platform_get_resource(dev, IORESOURCE_MEM, 0);
@@ -472,20 +470,6 @@ static int au1100fb_drv_probe(struct platform_device *dev)
 	au1100fb_fix.smem_start = fbdev->fb_phys;
 	au1100fb_fix.smem_len = fbdev->fb_len;
 
-	/*
-	 * Set page reserved so that mmap will work. This is necessary
-	 * since we'll be remapping normal memory.
-	 */
-	for (page = (unsigned long)fbdev->fb_mem;
-	     page < PAGE_ALIGN((unsigned long)fbdev->fb_mem + fbdev->fb_len);
-	     page += PAGE_SIZE) {
-#ifdef CONFIG_DMA_NONCOHERENT
-		SetPageReserved(virt_to_page(CAC_ADDR((void *)page)));
-#else
-		SetPageReserved(virt_to_page(page));
-#endif
-	}
-
 	print_dbg("Framebuffer memory map at %p", fbdev->fb_mem);
 	print_dbg("phys=0x%08x, size=%dK", fbdev->fb_phys, fbdev->fb_len / 1024);
 
diff --git a/drivers/video/fbdev/au1100fb.h b/drivers/video/fbdev/au1100fb.h
index 9af19939a9c6..e7239bceefd3 100644
--- a/drivers/video/fbdev/au1100fb.h
+++ b/drivers/video/fbdev/au1100fb.h
@@ -110,6 +110,7 @@ struct au1100fb_device {
 	dma_addr_t    		fb_phys;
 	int			panel_idx;
 	struct clk		*lcdclk;
+	struct device		*dev;
 };
 
 /********************************************************************/