Merge tag 'microblaze-v4.19-rc1' of git://git.monstr.eu/linux-2.6-microblaze

Pull arch/microblaze updates from Michal Simek:

 - use generic noncoherent direct mapping

 - use LDFLAGS instead of LD

 - pci error path fix

 - remove incorrect comments

* tag 'microblaze-v4.19-rc1' of git://git.monstr.eu/linux-2.6-microblaze:
  microblaze/PCI: Remove stale pcibios_align_resource() comment
  microblaze: delete wrong comment about machine_early_init
  microblaze: add endianness options to LDFLAGS instead of LD
  microblaze: remove consistent_sync and consistent_sync_page
  microblaze: use generic dma_noncoherent_ops
  microblaze: warn if of_iomap() failed
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 6163a39..ace5c5b 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -2,6 +2,8 @@
 	def_bool y
 	select ARCH_NO_SWAP
 	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
 	select ARCH_WANT_IPC_PARSE_VERSION
@@ -9,6 +11,8 @@
 	select TIMER_OF
 	select CLONE_BACKWARDS3
 	select COMMON_CLK
+	select DMA_NONCOHERENT_OPS
+	select DMA_NONCOHERENT_MMAP
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CPU_DEVICES
diff --git a/arch/microblaze/Makefile b/arch/microblaze/Makefile
index d269dd4b..7333036 100644
--- a/arch/microblaze/Makefile
+++ b/arch/microblaze/Makefile
@@ -40,11 +40,11 @@
 ifdef CONFIG_CPU_BIG_ENDIAN
 KBUILD_CFLAGS += -mbig-endian
 KBUILD_AFLAGS += -mbig-endian
-LD += -EB
+LDFLAGS += -EB
 else
 KBUILD_CFLAGS += -mlittle-endian
 KBUILD_AFLAGS += -mlittle-endian
-LD += -EL
+LDFLAGS += -EL
 endif
 
 CPUFLAGS-1 += $(call cc-option,-mcpu=v$(CPU_VER))
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index fe6a6c6..569ba9e 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -5,6 +5,7 @@
 generic-y += compat.h
 generic-y += device.h
 generic-y += div64.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += extable.h
diff --git a/arch/microblaze/include/asm/dma-mapping.h b/arch/microblaze/include/asm/dma-mapping.h
deleted file mode 100644
index add50c1..0000000
--- a/arch/microblaze/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Implements the generic device dma API for microblaze and the pci
- *
- * Copyright (C) 2009-2010 Michal Simek <monstr@monstr.eu>
- * Copyright (C) 2009-2010 PetaLogix
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License. See the file COPYING in the main directory of this
- * archive for more details.
- *
- * This file is base on powerpc and x86 dma-mapping.h versions
- * Copyright (C) 2004 IBM
- */
-
-#ifndef _ASM_MICROBLAZE_DMA_MAPPING_H
-#define _ASM_MICROBLAZE_DMA_MAPPING_H
-
-/*
- * Available generic sets of operations
- */
-extern const struct dma_map_ops dma_nommu_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &dma_nommu_ops;
-}
-
-#endif	/* _ASM_MICROBLAZE_DMA_MAPPING_H */
diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h
index db8b1fa..7b650ab1 100644
--- a/arch/microblaze/include/asm/pgtable.h
+++ b/arch/microblaze/include/asm/pgtable.h
@@ -553,11 +553,6 @@
 
 extern unsigned long ioremap_bot, ioremap_base;
 
-void *consistent_alloc(gfp_t gfp, size_t size, dma_addr_t *dma_handle);
-void consistent_free(size_t size, void *vaddr);
-void consistent_sync(void *vaddr, size_t size, int direction);
-void consistent_sync_page(struct page *page, unsigned long offset,
-	size_t size, int direction);
 unsigned long consistent_virt_to_pfn(void *vaddr);
 
 void setup_memory(void);
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index 3145e7d..71032cf 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -8,29 +8,15 @@
  */
 
 #include <linux/device.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/gfp.h>
 #include <linux/dma-debug.h>
 #include <linux/export.h>
 #include <linux/bug.h>
 #include <asm/cacheflush.h>
 
-static void *dma_nommu_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag,
-				       unsigned long attrs)
-{
-	return consistent_alloc(flag, size, dma_handle);
-}
-
-static void dma_nommu_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t dma_handle,
-				     unsigned long attrs)
-{
-	consistent_free(size, vaddr);
-}
-
-static inline void __dma_sync(unsigned long paddr,
-			      size_t size, enum dma_data_direction direction)
+static void __dma_sync(struct device *dev, phys_addr_t paddr, size_t size,
+		enum dma_data_direction direction)
 {
 	switch (direction) {
 	case DMA_TO_DEVICE:
@@ -45,113 +31,21 @@
 	}
 }
 
-static int dma_nommu_map_sg(struct device *dev, struct scatterlist *sgl,
-			     int nents, enum dma_data_direction direction,
-			     unsigned long attrs)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	struct scatterlist *sg;
-	int i;
-
-	/* FIXME this part of code is untested */
-	for_each_sg(sgl, sg, nents, i) {
-		sg->dma_address = sg_phys(sg);
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		__dma_sync(sg_phys(sg), sg->length, direction);
-	}
-
-	return nents;
+	__dma_sync(dev, paddr, size, dir);
 }
 
-static inline dma_addr_t dma_nommu_map_page(struct device *dev,
-					     struct page *page,
-					     unsigned long offset,
-					     size_t size,
-					     enum dma_data_direction direction,
-					     unsigned long attrs)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync(page_to_phys(page) + offset, size, direction);
-	return page_to_phys(page) + offset;
+	__dma_sync(dev, paddr, size, dir);
 }
 
-static inline void dma_nommu_unmap_page(struct device *dev,
-					 dma_addr_t dma_address,
-					 size_t size,
-					 enum dma_data_direction direction,
-					 unsigned long attrs)
-{
-/* There is not necessary to do cache cleanup
- *
- * phys_to_virt is here because in __dma_sync_page is __virt_to_phys and
- * dma_address is physical address
- */
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync(dma_address, size, direction);
-}
-
-static inline void
-dma_nommu_sync_single_for_cpu(struct device *dev,
-			       dma_addr_t dma_handle, size_t size,
-			       enum dma_data_direction direction)
-{
-	/*
-	 * It's pointless to flush the cache as the memory segment
-	 * is given to the CPU
-	 */
-
-	if (direction == DMA_FROM_DEVICE)
-		__dma_sync(dma_handle, size, direction);
-}
-
-static inline void
-dma_nommu_sync_single_for_device(struct device *dev,
-				  dma_addr_t dma_handle, size_t size,
-				  enum dma_data_direction direction)
-{
-	/*
-	 * It's pointless to invalidate the cache if the device isn't
-	 * supposed to write to the relevant region
-	 */
-
-	if (direction == DMA_TO_DEVICE)
-		__dma_sync(dma_handle, size, direction);
-}
-
-static inline void
-dma_nommu_sync_sg_for_cpu(struct device *dev,
-			   struct scatterlist *sgl, int nents,
-			   enum dma_data_direction direction)
-{
-	struct scatterlist *sg;
-	int i;
-
-	/* FIXME this part of code is untested */
-	if (direction == DMA_FROM_DEVICE)
-		for_each_sg(sgl, sg, nents, i)
-			__dma_sync(sg->dma_address, sg->length, direction);
-}
-
-static inline void
-dma_nommu_sync_sg_for_device(struct device *dev,
-			      struct scatterlist *sgl, int nents,
-			      enum dma_data_direction direction)
-{
-	struct scatterlist *sg;
-	int i;
-
-	/* FIXME this part of code is untested */
-	if (direction == DMA_TO_DEVICE)
-		for_each_sg(sgl, sg, nents, i)
-			__dma_sync(sg->dma_address, sg->length, direction);
-}
-
-static
-int dma_nommu_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
-			     void *cpu_addr, dma_addr_t handle, size_t size,
-			     unsigned long attrs)
+int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t handle, size_t size,
+		unsigned long attrs)
 {
 #ifdef CONFIG_MMU
 	unsigned long user_count = vma_pages(vma);
@@ -170,17 +64,3 @@
 	return -ENXIO;
 #endif
 }
-
-const struct dma_map_ops dma_nommu_ops = {
-	.alloc			= dma_nommu_alloc_coherent,
-	.free			= dma_nommu_free_coherent,
-	.mmap			= dma_nommu_mmap_coherent,
-	.map_sg			= dma_nommu_map_sg,
-	.map_page		= dma_nommu_map_page,
-	.unmap_page		= dma_nommu_unmap_page,
-	.sync_single_for_cpu	= dma_nommu_sync_single_for_cpu,
-	.sync_single_for_device	= dma_nommu_sync_single_for_device,
-	.sync_sg_for_cpu	= dma_nommu_sync_sg_for_cpu,
-	.sync_sg_for_device	= dma_nommu_sync_sg_for_device,
-};
-EXPORT_SYMBOL(dma_nommu_ops);
diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S
index 4655ff3..f264fdc 100644
--- a/arch/microblaze/kernel/head.S
+++ b/arch/microblaze/kernel/head.S
@@ -341,11 +341,6 @@
 	/* Initialize r31 with current task address */
 	addik	r31, r0, init_task
 
-	/*
-	 * Call platform dependent initialize function.
-	 * Please see $(ARCH)/mach-$(SUBARCH)/setup.c for
-	 * the function.
-	 */
 	addik	r11, r0, machine_early_init
 	brald	r15, r11
 	nop
diff --git a/arch/microblaze/mm/consistent.c b/arch/microblaze/mm/consistent.c
index b06c3a7..c9a278a 100644
--- a/arch/microblaze/mm/consistent.c
+++ b/arch/microblaze/mm/consistent.c
@@ -33,6 +33,7 @@
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 #include <linux/gfp.h>
+#include <linux/dma-noncoherent.h>
 
 #include <asm/pgalloc.h>
 #include <linux/io.h>
@@ -59,7 +60,8 @@
  * uncached region.  This will no doubt cause big problems if memory allocated
  * here is not also freed properly. -- JW
  */
-void *consistent_alloc(gfp_t gfp, size_t size, dma_addr_t *dma_handle)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	unsigned long order, vaddr;
 	void *ret;
@@ -154,7 +156,6 @@
 
 	return ret;
 }
-EXPORT_SYMBOL(consistent_alloc);
 
 #ifdef CONFIG_MMU
 static pte_t *consistent_virt_to_pte(void *vaddr)
@@ -178,7 +179,8 @@
 /*
  * free page(s) as defined by the above mapping.
  */
-void consistent_free(size_t size, void *vaddr)
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_addr, unsigned long attrs)
 {
 	struct page *page;
 
@@ -218,49 +220,3 @@
 	flush_tlb_all();
 #endif
 }
-EXPORT_SYMBOL(consistent_free);
-
-/*
- * make an area consistent.
- */
-void consistent_sync(void *vaddr, size_t size, int direction)
-{
-	unsigned long start;
-	unsigned long end;
-
-	start = (unsigned long)vaddr;
-
-	/* Convert start address back down to unshadowed memory region */
-#ifdef CONFIG_XILINX_UNCACHED_SHADOW
-	start &= ~UNCACHED_SHADOW_MASK;
-#endif
-	end = start + size;
-
-	switch (direction) {
-	case PCI_DMA_NONE:
-		BUG();
-	case PCI_DMA_FROMDEVICE:	/* invalidate only */
-		invalidate_dcache_range(start, end);
-		break;
-	case PCI_DMA_TODEVICE:		/* writeback only */
-		flush_dcache_range(start, end);
-		break;
-	case PCI_DMA_BIDIRECTIONAL:	/* writeback and invalidate */
-		flush_dcache_range(start, end);
-		break;
-	}
-}
-EXPORT_SYMBOL(consistent_sync);
-
-/*
- * consistent_sync_page makes memory consistent. identical
- * to consistent_sync, but takes a struct page instead of a
- * virtual address
- */
-void consistent_sync_page(struct page *page, unsigned long offset,
-	size_t size, int direction)
-{
-	unsigned long start = (unsigned long)page_address(page) + offset;
-	consistent_sync((void *)start, size, direction);
-}
-EXPORT_SYMBOL(consistent_sync_page);
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index f34346d..2ffd171 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -597,19 +597,6 @@
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pcibios_fixup_resources);
 
-/*
- * We need to avoid collisions with `mirrored' VGA ports
- * and other strange ISA hardware, so we always want the
- * addresses to be allocated in the 0x000-0x0ff region
- * modulo 0x400.
- *
- * Why? Because some silly external IO cards only decode
- * the low 10 bits of the IO address. The 0x00-0xff region
- * is reserved for motherboard devices that decode all 16
- * bits, so it's ok to allocate at, say, 0x2800-0x28ff,
- * but we want to try to avoid allocating at 0x2900-0x2bff
- * which might have be mirrored at 0x0100-0x03ff..
- */
 int pcibios_add_device(struct pci_dev *dev)
 {
 	dev->irq = of_irq_parse_and_map_pci(dev, 0, 0);
diff --git a/arch/microblaze/pci/xilinx_pci.c b/arch/microblaze/pci/xilinx_pci.c
index 14c7da5f..b800909 100644
--- a/arch/microblaze/pci/xilinx_pci.c
+++ b/arch/microblaze/pci/xilinx_pci.c
@@ -157,6 +157,7 @@
 
 	/* Set the max bus number to 255, and bus/subbus no's to 0 */
 	pci_reg = of_iomap(pci_node, 0);
+	WARN_ON(!pci_reg);
 	out_be32(pci_reg + XPLB_PCI_BUS, 0x000000ff);
 	iounmap(pci_reg);