Merge tag 'mips_4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux

Pull MIPS updates from Paul Burton:
 "Here are the main MIPS changes for 4.19.

  An overview of the general architecture changes:

   - Massive DMA ops refactoring from Christoph Hellwig (huzzah for
     deleting crufty code!).

   - We introduce NT_MIPS_DSP & NT_MIPS_FP_MODE ELF notes &
     corresponding regsets to expose DSP ASE & floating point mode state
     respectively, both for live debugging & core dumps.

   - We better optimize our code by hard-coding cpu_has_* macros at
     compile time where their values are known due to the ISA revision
     that the kernel build is targeting.

   - The EJTAG exception handler now better handles SMP systems, where
     it was previously possible for CPUs to clobber a register value
     saved by another CPU.

   - Our implementation of memset() gained a couple of fixes for MIPSr6
     systems to return correct values in some cases where stores fault.

   - We now implement ioremap_wc() using the uncached-accelerated cache
     coherency attribute where supported, which is detected during boot,
     and fall back to plain uncached access where necessary. The
     MIPS-specific (and unused in tree) ioremap_uncached_accelerated() &
     ioremap_cacheable_cow() are removed.

   - The prctl(PR_SET_FP_MODE, ...) syscall is better supported for SMP
     systems by reworking the way we ensure remote CPUs that may be
     running threads within the affected process switch mode.

   - Systems using the MIPS Coherence Manager will now set the
     MIPS_IC_SNOOPS_REMOTE flag to avoid some unnecessary cache
     maintenance overhead when flushing the icache.

   - A few fixes were made for building with clang/LLVM, which now
     sucessfully builds kernels for many of our platforms.

   - Miscellaneous cleanups all over.

  And some platform-specific changes:

   - ar7 gained stubs for a few clock API functions to fix build
     failures for some drivers.

   - ath79 gained support for a few new SoCs, a few fixes & better
     gpio-keys support.

   - Ci20 now exposes its SPI bus using the spi-gpio driver.

   - The generic platform can now auto-detect a suitable value for
     PHYS_OFFSET based upon the memory map described by the device tree,
     allowing us to avoid wasting memory on page book-keeping for
     systems where RAM starts at a non-zero physical address.

   - Ingenic systems using the jz4740 platform code now link their
     vmlinuz higher to allow for kernels of a realistic size.

   - Loongson32 now builds the kernel targeting MIPSr1 rather than
     MIPSr2 to avoid CPU errata.

   - Loongson64 gains a couple of fixes, a workaround for a write
     buffering issue & support for the Loongson 3A R3.1 CPU.

   - Malta now uses the piix4-poweroff driver to handle powering down.

   - Microsemi Ocelot gained support for its SPI bus & NOR flash, its
     second MDIO bus and can now be supported by a FIT/.itb image.

   - Octeon saw a bunch of header cleanups which remove a lot of
     duplicate or unused code"

* tag 'mips_4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux: (123 commits)
  MIPS: Remove remnants of UASM_ISA
  MIPS: netlogic: xlr: Remove erroneous check in nlm_fmn_send()
  MIPS: VDSO: Force link endianness
  MIPS: Always specify -EB or -EL when using clang
  MIPS: Use dins to simplify __write_64bit_c0_split()
  MIPS: Use read-write output operand in __write_64bit_c0_split()
  MIPS: Avoid using array as parameter to write_c0_kpgd()
  MIPS: vdso: Allow clang's --target flag in VDSO cflags
  MIPS: genvdso: Remove GOT checks
  MIPS: Remove obsolete MIPS checks for DST node "chosen@0"
  MIPS: generic: Remove input symbols from defconfig
  MIPS: Delete unused code in linux32.c
  MIPS: Remove unused sys_32_mmap2
  MIPS: Remove nabi_no_regargs
  mips: dts: mscc: enable spi and NOR flash support on ocelot PCB123
  mips: dts: mscc: Add spi on Ocelot
  MIPS: Loongson: Merge load addresses
  MIPS: Loongson: Set Loongson32 to MIPS32R1
  MIPS: mscc: ocelot: add interrupt controller properties to GPIO controller
  MIPS: generic: Select MIPS_AUTO_PFN_OFFSET
  ...

9 files changed, 227 insertions, 429 deletions

diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index c463bdad45c7..3e5bb203c95a 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the Linux/MIPS-specific parts of the memory manager.
 #
 
-obj-y				+= cache.o dma-default.o extable.o fault.o \
+obj-y				+= cache.o extable.o fault.o \
 				   gup.o init.o mmap.o page.o page-funcs.o \
 				   pgtable.o tlbex.o tlbex-fault.o tlb-funcs.o
 
@@ -17,6 +17,7 @@ obj-$(CONFIG_32BIT)		+= ioremap.o pgtable-32.o
 obj-$(CONFIG_64BIT)		+= pgtable-64.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
+obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-noncoherent.o
 
 obj-$(CONFIG_CPU_R4K_CACHE_TLB) += c-r4k.o cex-gen.o tlb-r4k.o
 obj-$(CONFIG_CPU_R3000)		+= c-r3k.o tlb-r3k.o
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index e12dfa48b478..a9ef057c79fe 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -830,12 +830,13 @@ static void r4k_flush_icache_user_range(unsigned long start, unsigned long end)
 	return __r4k_flush_icache_range(start, end, true);
 }
 
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
 
 static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 {
 	/* Catch bad driver code */
-	BUG_ON(size == 0);
+	if (WARN_ON(size == 0))
+		return;
 
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
@@ -871,7 +872,8 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 {
 	/* Catch bad driver code */
-	BUG_ON(size == 0);
+	if (WARN_ON(size == 0))
+		return;
 
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
@@ -904,7 +906,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 	bc_inv(addr, size);
 	__sync();
 }
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
 
 struct flush_cache_sigtramp_args {
 	struct mm_struct *mm;
@@ -1505,6 +1507,14 @@ static void probe_pcache(void)
 	if (c->dcache.flags & MIPS_CACHE_PINDEX)
 		c->dcache.flags &= ~MIPS_CACHE_ALIASES;
 
+	/*
+	 * In systems with CM the icache fills from L2 or closer caches, and
+	 * thus sees remote stores without needing to write them back any
+	 * further than that.
+	 */
+	if (mips_cm_present())
+		c->icache.flags |= MIPS_IC_SNOOPS_REMOTE;
+
 	switch (current_cpu_type()) {
 	case CPU_20KC:
 		/*
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index 0d3c656feba0..70a523151ff3 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -56,7 +56,7 @@ EXPORT_SYMBOL_GPL(local_flush_data_cache_page);
 EXPORT_SYMBOL(flush_data_cache_page);
 EXPORT_SYMBOL(flush_icache_all);
 
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
 
 /* DMA cache operations. */
 void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
@@ -65,7 +65,7 @@ void (*_dma_cache_inv)(unsigned long start, unsigned long size);
 
 EXPORT_SYMBOL(_dma_cache_wback_inv);
 
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
 
 /*
  * We could optimize the case where the cache argument is not BCACHE but
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
deleted file mode 100644
index f9fef0028ca2..000000000000
--- a/arch/mips/mm/dma-default.c
+++ /dev/null
@@ -1,404 +0,0 @@
-/*
- * 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.
- *
- * Copyright (C) 2000  Ani Joshi <ajoshi@unixbox.com>
- * Copyright (C) 2000, 2001, 06	 Ralf Baechle <ralf@linux-mips.org>
- * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
- */
-
-#include <linux/types.h>
-#include <linux/dma-mapping.h>
-#include <linux/mm.h>
-#include <linux/export.h>
-#include <linux/scatterlist.h>
-#include <linux/string.h>
-#include <linux/gfp.h>
-#include <linux/highmem.h>
-#include <linux/dma-contiguous.h>
-
-#include <asm/cache.h>
-#include <asm/cpu-type.h>
-#include <asm/io.h>
-
-#include <dma-coherence.h>
-
-#if defined(CONFIG_DMA_MAYBE_COHERENT) && !defined(CONFIG_DMA_PERDEV_COHERENT)
-/* User defined DMA coherency from command line. */
-enum coherent_io_user_state coherentio = IO_COHERENCE_DEFAULT;
-EXPORT_SYMBOL_GPL(coherentio);
-int hw_coherentio = 0;	/* Actual hardware supported DMA coherency setting. */
-
-static int __init setcoherentio(char *str)
-{
-	coherentio = IO_COHERENCE_ENABLED;
-	pr_info("Hardware DMA cache coherency (command line)\n");
-	return 0;
-}
-early_param("coherentio", setcoherentio);
-
-static int __init setnocoherentio(char *str)
-{
-	coherentio = IO_COHERENCE_DISABLED;
-	pr_info("Software DMA cache coherency (command line)\n");
-	return 0;
-}
-early_param("nocoherentio", setnocoherentio);
-#endif
-
-static inline struct page *dma_addr_to_page(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	return pfn_to_page(
-		plat_dma_addr_to_phys(dev, dma_addr) >> PAGE_SHIFT);
-}
-
-/*
- * The affected CPUs below in 'cpu_needs_post_dma_flush()' can
- * speculatively fill random cachelines with stale data at any time,
- * requiring an extra flush post-DMA.
- *
- * Warning on the terminology - Linux calls an uncached area coherent;
- * MIPS terminology calls memory areas with hardware maintained coherency
- * coherent.
- *
- * Note that the R14000 and R16000 should also be checked for in this
- * condition.  However this function is only called on non-I/O-coherent
- * systems and only the R10000 and R12000 are used in such systems, the
- * SGI IP28 Indigo² rsp. SGI IP32 aka O2.
- */
-static inline bool cpu_needs_post_dma_flush(struct device *dev)
-{
-	if (plat_device_is_coherent(dev))
-		return false;
-
-	switch (boot_cpu_type()) {
-	case CPU_R10000:
-	case CPU_R12000:
-	case CPU_BMIPS5000:
-		return true;
-
-	default:
-		/*
-		 * Presence of MAARs suggests that the CPU supports
-		 * speculatively prefetching data, and therefore requires
-		 * the post-DMA flush/invalidate.
-		 */
-		return cpu_has_maar;
-	}
-}
-
-static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
-{
-	gfp_t dma_flag;
-
-#ifdef CONFIG_ISA
-	if (dev == NULL)
-		dma_flag = __GFP_DMA;
-	else
-#endif
-#if defined(CONFIG_ZONE_DMA32) && defined(CONFIG_ZONE_DMA)
-	     if (dev == NULL || dev->coherent_dma_mask < DMA_BIT_MASK(32))
-			dma_flag = __GFP_DMA;
-	else if (dev->coherent_dma_mask < DMA_BIT_MASK(64))
-			dma_flag = __GFP_DMA32;
-	else
-#endif
-#if defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_ZONE_DMA)
-	     if (dev == NULL || dev->coherent_dma_mask < DMA_BIT_MASK(64))
-		dma_flag = __GFP_DMA32;
-	else
-#endif
-#if defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32)
-	     if (dev == NULL ||
-		 dev->coherent_dma_mask < DMA_BIT_MASK(sizeof(phys_addr_t) * 8))
-		dma_flag = __GFP_DMA;
-	else
-#endif
-		dma_flag = 0;
-
-	/* Don't invoke OOM killer */
-	gfp |= __GFP_NORETRY;
-
-	return gfp | dma_flag;
-}
-
-static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	void *ret;
-	struct page *page = NULL;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	gfp = massage_gfp_flags(dev, gfp);
-
-	if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp))
-		page = dma_alloc_from_contiguous(dev, count, get_order(size),
-						 gfp);
-	if (!page)
-		page = alloc_pages(gfp, get_order(size));
-
-	if (!page)
-		return NULL;
-
-	ret = page_address(page);
-	memset(ret, 0, size);
-	*dma_handle = plat_map_dma_mem(dev, ret, size);
-	if (!(attrs & DMA_ATTR_NON_CONSISTENT) &&
-	    !plat_device_is_coherent(dev)) {
-		dma_cache_wback_inv((unsigned long) ret, size);
-		ret = UNCAC_ADDR(ret);
-	}
-
-	return ret;
-}
-
-static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
-	dma_addr_t dma_handle, unsigned long attrs)
-{
-	unsigned long addr = (unsigned long) vaddr;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct page *page = NULL;
-
-	plat_unmap_dma_mem(dev, dma_handle, size, DMA_BIDIRECTIONAL);
-
-	if (!(attrs & DMA_ATTR_NON_CONSISTENT) && !plat_device_is_coherent(dev))
-		addr = CAC_ADDR(addr);
-
-	page = virt_to_page((void *) addr);
-
-	if (!dma_release_from_contiguous(dev, page, count))
-		__free_pages(page, get_order(size));
-}
-
-static int mips_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-	void *cpu_addr, dma_addr_t dma_addr, size_t size,
-	unsigned long attrs)
-{
-	unsigned long user_count = vma_pages(vma);
-	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long addr = (unsigned long)cpu_addr;
-	unsigned long off = vma->vm_pgoff;
-	unsigned long pfn;
-	int ret = -ENXIO;
-
-	if (!plat_device_is_coherent(dev))
-		addr = CAC_ADDR(addr);
-
-	pfn = page_to_pfn(virt_to_page((void *)addr));
-
-	if (attrs & DMA_ATTR_WRITE_COMBINE)
-		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-	else
-		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-
-	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
-		return ret;
-
-	if (off < count && user_count <= (count - off)) {
-		ret = remap_pfn_range(vma, vma->vm_start,
-				      pfn + off,
-				      user_count << PAGE_SHIFT,
-				      vma->vm_page_prot);
-	}
-
-	return ret;
-}
-
-static inline void __dma_sync_virtual(void *addr, size_t size,
-	enum dma_data_direction direction)
-{
-	switch (direction) {
-	case DMA_TO_DEVICE:
-		dma_cache_wback((unsigned long)addr, size);
-		break;
-
-	case DMA_FROM_DEVICE:
-		dma_cache_inv((unsigned long)addr, size);
-		break;
-
-	case DMA_BIDIRECTIONAL:
-		dma_cache_wback_inv((unsigned long)addr, size);
-		break;
-
-	default:
-		BUG();
-	}
-}
-
-/*
- * A single sg entry may refer to multiple physically contiguous
- * pages. But we still need to process highmem pages individually.
- * If highmem is not configured then the bulk of this loop gets
- * optimized out.
- */
-static inline void __dma_sync(struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction)
-{
-	size_t left = size;
-
-	do {
-		size_t len = left;
-
-		if (PageHighMem(page)) {
-			void *addr;
-
-			if (offset + len > PAGE_SIZE) {
-				if (offset >= PAGE_SIZE) {
-					page += offset >> PAGE_SHIFT;
-					offset &= ~PAGE_MASK;
-				}
-				len = PAGE_SIZE - offset;
-			}
-
-			addr = kmap_atomic(page);
-			__dma_sync_virtual(addr + offset, len, direction);
-			kunmap_atomic(addr);
-		} else
-			__dma_sync_virtual(page_address(page) + offset,
-					   size, direction);
-		offset = 0;
-		page++;
-		left -= len;
-	} while (left);
-}
-
-static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction, unsigned long attrs)
-{
-	if (cpu_needs_post_dma_flush(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync(dma_addr_to_page(dev, dma_addr),
-			   dma_addr & ~PAGE_MASK, size, direction);
-	plat_post_dma_flush(dev);
-	plat_unmap_dma_mem(dev, dma_addr, size, direction);
-}
-
-static int mips_dma_map_sg(struct device *dev, struct scatterlist *sglist,
-	int nents, enum dma_data_direction direction, unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i) {
-		if (!plat_device_is_coherent(dev) &&
-		    !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-#ifdef CONFIG_NEED_SG_DMA_LENGTH
-		sg->dma_length = sg->length;
-#endif
-		sg->dma_address = plat_map_dma_mem_page(dev, sg_page(sg)) +
-				  sg->offset;
-	}
-
-	return nents;
-}
-
-static dma_addr_t mips_dma_map_page(struct device *dev, struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction,
-	unsigned long attrs)
-{
-	if (!plat_device_is_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync(page, offset, size, direction);
-
-	return plat_map_dma_mem_page(dev, page) + offset;
-}
-
-static void mips_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
-	int nhwentries, enum dma_data_direction direction,
-	unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nhwentries, i) {
-		if (!plat_device_is_coherent(dev) &&
-		    !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-		    direction != DMA_TO_DEVICE)
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-		plat_unmap_dma_mem(dev, sg->dma_address, sg->length, direction);
-	}
-}
-
-static void mips_dma_sync_single_for_cpu(struct device *dev,
-	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
-	if (cpu_needs_post_dma_flush(dev))
-		__dma_sync(dma_addr_to_page(dev, dma_handle),
-			   dma_handle & ~PAGE_MASK, size, direction);
-	plat_post_dma_flush(dev);
-}
-
-static void mips_dma_sync_single_for_device(struct device *dev,
-	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
-	if (!plat_device_is_coherent(dev))
-		__dma_sync(dma_addr_to_page(dev, dma_handle),
-			   dma_handle & ~PAGE_MASK, size, direction);
-}
-
-static void mips_dma_sync_sg_for_cpu(struct device *dev,
-	struct scatterlist *sglist, int nelems,
-	enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	if (cpu_needs_post_dma_flush(dev)) {
-		for_each_sg(sglist, sg, nelems, i) {
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-		}
-	}
-	plat_post_dma_flush(dev);
-}
-
-static void mips_dma_sync_sg_for_device(struct device *dev,
-	struct scatterlist *sglist, int nelems,
-	enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	if (!plat_device_is_coherent(dev)) {
-		for_each_sg(sglist, sg, nelems, i) {
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-		}
-	}
-}
-
-static int mips_dma_supported(struct device *dev, u64 mask)
-{
-	return plat_dma_supported(dev, mask);
-}
-
-static void mips_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-			 enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	if (!plat_device_is_coherent(dev))
-		__dma_sync_virtual(vaddr, size, direction);
-}
-
-static const struct dma_map_ops mips_default_dma_map_ops = {
-	.alloc = mips_dma_alloc_coherent,
-	.free = mips_dma_free_coherent,
-	.mmap = mips_dma_mmap,
-	.map_page = mips_dma_map_page,
-	.unmap_page = mips_dma_unmap_page,
-	.map_sg = mips_dma_map_sg,
-	.unmap_sg = mips_dma_unmap_sg,
-	.sync_single_for_cpu = mips_dma_sync_single_for_cpu,
-	.sync_single_for_device = mips_dma_sync_single_for_device,
-	.sync_sg_for_cpu = mips_dma_sync_sg_for_cpu,
-	.sync_sg_for_device = mips_dma_sync_sg_for_device,
-	.dma_supported = mips_dma_supported,
-	.cache_sync = mips_dma_cache_sync,
-};
-
-const struct dma_map_ops *mips_dma_map_ops = &mips_default_dma_map_ops;
-EXPORT_SYMBOL(mips_dma_map_ops);
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
new file mode 100644
index 000000000000..2aca1236af36
--- /dev/null
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000  Ani Joshi <ajoshi@unixbox.com>
+ * Copyright (C) 2000, 2001, 06	 Ralf Baechle <ralf@linux-mips.org>
+ * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
+ */
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/dma-contiguous.h>
+#include <linux/highmem.h>
+
+#include <asm/cache.h>
+#include <asm/cpu-type.h>
+#include <asm/dma-coherence.h>
+#include <asm/io.h>
+
+#ifdef CONFIG_DMA_PERDEV_COHERENT
+static inline int dev_is_coherent(struct device *dev)
+{
+	return dev->archdata.dma_coherent;
+}
+#else
+static inline int dev_is_coherent(struct device *dev)
+{
+	switch (coherentio) {
+	default:
+	case IO_COHERENCE_DEFAULT:
+		return hw_coherentio;
+	case IO_COHERENCE_ENABLED:
+		return 1;
+	case IO_COHERENCE_DISABLED:
+		return 0;
+	}
+}
+#endif /* CONFIG_DMA_PERDEV_COHERENT */
+
+/*
+ * The affected CPUs below in 'cpu_needs_post_dma_flush()' can speculatively
+ * fill random cachelines with stale data at any time, requiring an extra
+ * flush post-DMA.
+ *
+ * Warning on the terminology - Linux calls an uncached area coherent;  MIPS
+ * terminology calls memory areas with hardware maintained coherency coherent.
+ *
+ * Note that the R14000 and R16000 should also be checked for in this condition.
+ * However this function is only called on non-I/O-coherent systems and only the
+ * R10000 and R12000 are used in such systems, the SGI IP28 Indigo² rsp.
+ * SGI IP32 aka O2.
+ */
+static inline bool cpu_needs_post_dma_flush(struct device *dev)
+{
+	if (dev_is_coherent(dev))
+		return false;
+
+	switch (boot_cpu_type()) {
+	case CPU_R10000:
+	case CPU_R12000:
+	case CPU_BMIPS5000:
+		return true;
+	default:
+		/*
+		 * Presence of MAARs suggests that the CPU supports
+		 * speculatively prefetching data, and therefore requires
+		 * the post-DMA flush/invalidate.
+		 */
+		return cpu_has_maar;
+	}
+}
+
+void *arch_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+	void *ret;
+
+	ret = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
+	if (!ret)
+		return NULL;
+
+	if (!dev_is_coherent(dev) && !(attrs & DMA_ATTR_NON_CONSISTENT)) {
+		dma_cache_wback_inv((unsigned long) ret, size);
+		ret = (void *)UNCAC_ADDR(ret);
+	}
+
+	return ret;
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_addr, unsigned long attrs)
+{
+	if (!(attrs & DMA_ATTR_NON_CONSISTENT) && !dev_is_coherent(dev))
+		cpu_addr = (void *)CAC_ADDR((unsigned long)cpu_addr);
+	dma_direct_free(dev, size, cpu_addr, dma_addr, attrs);
+}
+
+int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	unsigned long user_count = vma_pages(vma);
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long addr = (unsigned long)cpu_addr;
+	unsigned long off = vma->vm_pgoff;
+	unsigned long pfn;
+	int ret = -ENXIO;
+
+	if (!dev_is_coherent(dev))
+		addr = CAC_ADDR(addr);
+
+	pfn = page_to_pfn(virt_to_page((void *)addr));
+
+	if (attrs & DMA_ATTR_WRITE_COMBINE)
+		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	else
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off < count && user_count <= (count - off)) {
+		ret = remap_pfn_range(vma, vma->vm_start,
+				      pfn + off,
+				      user_count << PAGE_SHIFT,
+				      vma->vm_page_prot);
+	}
+
+	return ret;
+}
+
+static inline void dma_sync_virt(void *addr, size_t size,
+		enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		dma_cache_wback((unsigned long)addr, size);
+		break;
+
+	case DMA_FROM_DEVICE:
+		dma_cache_inv((unsigned long)addr, size);
+		break;
+
+	case DMA_BIDIRECTIONAL:
+		dma_cache_wback_inv((unsigned long)addr, size);
+		break;
+
+	default:
+		BUG();
+	}
+}
+
+/*
+ * A single sg entry may refer to multiple physically contiguous pages.  But
+ * we still need to process highmem pages individually.  If highmem is not
+ * configured then the bulk of this loop gets optimized out.
+ */
+static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
+	unsigned long offset = paddr & ~PAGE_MASK;
+	size_t left = size;
+
+	do {
+		size_t len = left;
+
+		if (PageHighMem(page)) {
+			void *addr;
+
+			if (offset + len > PAGE_SIZE) {
+				if (offset >= PAGE_SIZE) {
+					page += offset >> PAGE_SHIFT;
+					offset &= ~PAGE_MASK;
+				}
+				len = PAGE_SIZE - offset;
+			}
+
+			addr = kmap_atomic(page);
+			dma_sync_virt(addr + offset, len, dir);
+			kunmap_atomic(addr);
+		} else
+			dma_sync_virt(page_address(page) + offset, size, dir);
+		offset = 0;
+		page++;
+		left -= len;
+	} while (left);
+}
+
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	if (!dev_is_coherent(dev))
+		dma_sync_phys(paddr, size, dir);
+}
+
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	if (cpu_needs_post_dma_flush(dev))
+		dma_sync_phys(paddr, size, dir);
+}
+
+void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		enum dma_data_direction direction)
+{
+	BUG_ON(direction == DMA_NONE);
+
+	if (!dev_is_coherent(dev))
+		dma_sync_virt(vaddr, size, direction);
+}
diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c
index d5d02993aa21..56e4f8bffd4c 100644
--- a/arch/mips/mm/page.c
+++ b/arch/mips/mm/page.c
@@ -623,21 +623,6 @@ struct dmadscr {
 	u64 pad_b;
 } ____cacheline_aligned_in_smp page_descr[DM_NUM_CHANNELS];
 
-void sb1_dma_init(void)
-{
-	int i;
-
-	for (i = 0; i < DM_NUM_CHANNELS; i++) {
-		const u64 base_val = CPHYSADDR((unsigned long)&page_descr[i]) |
-				     V_DM_DSCR_BASE_RINGSZ(1);
-		void *base_reg = IOADDR(A_DM_REGISTER(i, R_DM_DSCR_BASE));
-
-		__raw_writeq(base_val, base_reg);
-		__raw_writeq(base_val | M_DM_DSCR_BASE_RESET, base_reg);
-		__raw_writeq(base_val | M_DM_DSCR_BASE_ENABL, base_reg);
-	}
-}
-
 void clear_page(void *page)
 {
 	u64 to_phys = CPHYSADDR((unsigned long)page);
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 79b9f2ad3ff5..49312a14cd17 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -1509,7 +1509,7 @@ static void setup_pw(void)
 #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	write_c0_pwctl(1 << 6 | psn);
 #endif
-	write_c0_kpgd(swapper_pg_dir);
+	write_c0_kpgd((long)swapper_pg_dir);
 	kscratch_used_mask |= (1 << 7); /* KScratch6 is used for KPGD */
 }
 
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index 9bb6baa45da3..24e5b0d06899 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -19,7 +19,6 @@
 #include <asm/inst.h>
 #include <asm/elf.h>
 #include <asm/bugs.h>
-#define UASM_ISA	_UASM_ISA_MICROMIPS
 #include <asm/uasm.h>
 
 #define RS_MASK		0x1f
diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c
index 9fea6c6bbf49..60ceb93c71a0 100644
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@@ -19,7 +19,6 @@
 #include <asm/inst.h>
 #include <asm/elf.h>
 #include <asm/bugs.h>
-#define UASM_ISA	_UASM_ISA_CLASSIC
 #include <asm/uasm.h>
 
 #define RS_MASK		0x1f