Merge branch 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:
 "Included in this update are:

   - Patches from Gregory Clement to fix the coherent DMA cases in our
     dma-mapping code.

   - A number of CPU errata updates and fixes.

   - ARM cpuidle improvements from Jisheng Zhang.

   - Fix from Kees for the location of _etext.

   - Cleanups from Masahiro Yamada to avoid duplicated messages during
     the kernel build, and remove CONFIG_ARCH_HAS_BARRIERS.

   - Remove a udelay loop limitation, allowing for faster CPUs to
     calibrate the delay correctly.

   - Cleanup some left-overs from the SW PAN implementation.

   - Ensure that a modified address limit is not visible to exception
     handlers"

* 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (21 commits)
  ARM: 8586/1: cpuidle: make arm_cpuidle_suspend() a bit more efficient
  ARM: 8585/1: cpuidle: fix !cpuidle_ops[cpu].init case during init
  ARM: 8561/4: dma-mapping: Fix the coherent case when iommu is used
  ARM: 8561/3: dma-mapping: Don't use outer_flush_range when the L2C is coherent
  ARM: 8560/1: errata: Workaround errata A12 825619 / A17 852421
  ARM: 8559/1: errata: Workaround erratum A12 821420
  ARM: 8558/1: errata: Workaround errata A12 818325/852422 A17 852423
  ARM: save and reset the address limit when entering an exception
  ARM: 8577/1: Fix Cortex-A15 798181 errata initialization
  ARM: 8584/1: floppy: avoid gcc-6 warning
  ARM: 8583/1: mm: fix location of _etext
  ARM: 8582/1: remove unused CONFIG_ARCH_HAS_BARRIERS
  ARM: 8306/1: loop_udelay: remove bogomips value limitation
  ARM: 8581/1: add missing <asm/prom.h> to arch/arm/kernel/devtree.c
  ARM: 8576/1: avoid duplicating "Kernel: arch/arm/boot/*Image is ready"
  ARM: 8556/1: on a generic DT system: do not touch l2x0
  ARM: uaccess: remove put_user() code duplication
  ARM: 8580/1: Remove orphaned __addr_ok() definition
  ARM: get rid of horrible *(unsigned int *)(regs + 1)
  ARM: introduce svc_pt_regs structure
  ...

3 files changed, 148 insertions, 45 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index cb569b65a54d..d15a7fe51618 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -1025,12 +1025,6 @@ config ARM_DMA_MEM_BUFFERABLE
 
 	  You are recommended say 'Y' here and debug any affected drivers.
 
-config ARCH_HAS_BARRIERS
-	bool
-	help
-	  This option allows the use of custom mandatory barriers
-	  included via the mach/barriers.h file.
-
 config ARM_HEAVY_MB
 	bool
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ff7ed5697d3e..b7eed75960fe 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -49,6 +49,7 @@ struct arm_dma_alloc_args {
 	pgprot_t prot;
 	const void *caller;
 	bool want_vaddr;
+	int coherent_flag;
 };
 
 struct arm_dma_free_args {
@@ -59,6 +60,9 @@ struct arm_dma_free_args {
 	bool want_vaddr;
 };
 
+#define NORMAL	    0
+#define COHERENT    1
+
 struct arm_dma_allocator {
 	void *(*alloc)(struct arm_dma_alloc_args *args,
 		       struct page **ret_page);
@@ -272,7 +276,7 @@ static u64 get_coherent_dma_mask(struct device *dev)
 	return mask;
 }
 
-static void __dma_clear_buffer(struct page *page, size_t size)
+static void __dma_clear_buffer(struct page *page, size_t size, int coherent_flag)
 {
 	/*
 	 * Ensure that the allocated pages are zeroed, and that any data
@@ -284,17 +288,21 @@ static void __dma_clear_buffer(struct page *page, size_t size)
 		while (size > 0) {
 			void *ptr = kmap_atomic(page);
 			memset(ptr, 0, PAGE_SIZE);
-			dmac_flush_range(ptr, ptr + PAGE_SIZE);
+			if (coherent_flag != COHERENT)
+				dmac_flush_range(ptr, ptr + PAGE_SIZE);
 			kunmap_atomic(ptr);
 			page++;
 			size -= PAGE_SIZE;
 		}
-		outer_flush_range(base, end);
+		if (coherent_flag != COHERENT)
+			outer_flush_range(base, end);
 	} else {
 		void *ptr = page_address(page);
 		memset(ptr, 0, size);
-		dmac_flush_range(ptr, ptr + size);
-		outer_flush_range(__pa(ptr), __pa(ptr) + size);
+		if (coherent_flag != COHERENT) {
+			dmac_flush_range(ptr, ptr + size);
+			outer_flush_range(__pa(ptr), __pa(ptr) + size);
+		}
 	}
 }
 
@@ -302,7 +310,8 @@ static void __dma_clear_buffer(struct page *page, size_t size)
  * Allocate a DMA buffer for 'dev' of size 'size' using the
  * specified gfp mask.  Note that 'size' must be page aligned.
  */
-static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gfp)
+static struct page *__dma_alloc_buffer(struct device *dev, size_t size,
+				       gfp_t gfp, int coherent_flag)
 {
 	unsigned long order = get_order(size);
 	struct page *page, *p, *e;
@@ -318,7 +327,7 @@ static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gf
 	for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++)
 		__free_page(p);
 
-	__dma_clear_buffer(page, size);
+	__dma_clear_buffer(page, size, coherent_flag);
 
 	return page;
 }
@@ -340,7 +349,8 @@ static void __dma_free_buffer(struct page *page, size_t size)
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
 				     pgprot_t prot, struct page **ret_page,
-				     const void *caller, bool want_vaddr);
+				     const void *caller, bool want_vaddr,
+				     int coherent_flag);
 
 static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 				 pgprot_t prot, struct page **ret_page,
@@ -405,10 +415,13 @@ static int __init atomic_pool_init(void)
 	atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
 	if (!atomic_pool)
 		goto out;
-
+	/*
+	 * The atomic pool is only used for non-coherent allocations
+	 * so we must pass NORMAL for coherent_flag.
+	 */
 	if (dev_get_cma_area(NULL))
 		ptr = __alloc_from_contiguous(NULL, atomic_pool_size, prot,
-					      &page, atomic_pool_init, true);
+				      &page, atomic_pool_init, true, NORMAL);
 	else
 		ptr = __alloc_remap_buffer(NULL, atomic_pool_size, gfp, prot,
 					   &page, atomic_pool_init, true);
@@ -522,7 +535,11 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 {
 	struct page *page;
 	void *ptr = NULL;
-	page = __dma_alloc_buffer(dev, size, gfp);
+	/*
+	 * __alloc_remap_buffer is only called when the device is
+	 * non-coherent
+	 */
+	page = __dma_alloc_buffer(dev, size, gfp, NORMAL);
 	if (!page)
 		return NULL;
 	if (!want_vaddr)
@@ -577,7 +594,8 @@ static int __free_from_pool(void *start, size_t size)
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
 				     pgprot_t prot, struct page **ret_page,
-				     const void *caller, bool want_vaddr)
+				     const void *caller, bool want_vaddr,
+				     int coherent_flag)
 {
 	unsigned long order = get_order(size);
 	size_t count = size >> PAGE_SHIFT;
@@ -588,7 +606,7 @@ static void *__alloc_from_contiguous(struct device *dev, size_t size,
 	if (!page)
 		return NULL;
 
-	__dma_clear_buffer(page, size);
+	__dma_clear_buffer(page, size, coherent_flag);
 
 	if (!want_vaddr)
 		goto out;
@@ -638,7 +656,7 @@ static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot)
 #define __get_dma_pgprot(attrs, prot)				__pgprot(0)
 #define __alloc_remap_buffer(dev, size, gfp, prot, ret, c, wv)	NULL
 #define __alloc_from_pool(size, ret_page)			NULL
-#define __alloc_from_contiguous(dev, size, prot, ret, c, wv)	NULL
+#define __alloc_from_contiguous(dev, size, prot, ret, c, wv, coherent_flag)	NULL
 #define __free_from_pool(cpu_addr, size)			do { } while (0)
 #define __free_from_contiguous(dev, page, cpu_addr, size, wv)	do { } while (0)
 #define __dma_free_remap(cpu_addr, size)			do { } while (0)
@@ -649,7 +667,8 @@ static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp,
 				   struct page **ret_page)
 {
 	struct page *page;
-	page = __dma_alloc_buffer(dev, size, gfp);
+	/* __alloc_simple_buffer is only called when the device is coherent */
+	page = __dma_alloc_buffer(dev, size, gfp, COHERENT);
 	if (!page)
 		return NULL;
 
@@ -679,7 +698,7 @@ static void *cma_allocator_alloc(struct arm_dma_alloc_args *args,
 {
 	return __alloc_from_contiguous(args->dev, args->size, args->prot,
 				       ret_page, args->caller,
-				       args->want_vaddr);
+				       args->want_vaddr, args->coherent_flag);
 }
 
 static void cma_allocator_free(struct arm_dma_free_args *args)
@@ -746,6 +765,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		.prot = prot,
 		.caller = caller,
 		.want_vaddr = !dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs),
+		.coherent_flag = is_coherent ? COHERENT : NORMAL,
 	};
 
 #ifdef CONFIG_DMA_API_DEBUG
@@ -1253,7 +1273,8 @@ static inline void __free_iova(struct dma_iommu_mapping *mapping,
 static const int iommu_order_array[] = { 9, 8, 4, 0 };
 
 static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
-					  gfp_t gfp, struct dma_attrs *attrs)
+					  gfp_t gfp, struct dma_attrs *attrs,
+					  int coherent_flag)
 {
 	struct page **pages;
 	int count = size >> PAGE_SHIFT;
@@ -1277,7 +1298,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
 		if (!page)
 			goto error;
 
-		__dma_clear_buffer(page, size);
+		__dma_clear_buffer(page, size, coherent_flag);
 
 		for (i = 0; i < count; i++)
 			pages[i] = page + i;
@@ -1327,7 +1348,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
 				pages[i + j] = pages[i] + j;
 		}
 
-		__dma_clear_buffer(pages[i], PAGE_SIZE << order);
+		__dma_clear_buffer(pages[i], PAGE_SIZE << order, coherent_flag);
 		i += 1 << order;
 		count -= 1 << order;
 	}
@@ -1455,13 +1476,16 @@ static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
 	return NULL;
 }
 
-static void *__iommu_alloc_atomic(struct device *dev, size_t size,
-				  dma_addr_t *handle)
+static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
+				  dma_addr_t *handle, int coherent_flag)
 {
 	struct page *page;
 	void *addr;
 
-	addr = __alloc_from_pool(size, &page);
+	if (coherent_flag  == COHERENT)
+		addr = __alloc_simple_buffer(dev, size, gfp, &page);
+	else
+		addr = __alloc_from_pool(size, &page);
 	if (!addr)
 		return NULL;
 
@@ -1477,14 +1501,18 @@ err_mapping:
 }
 
 static void __iommu_free_atomic(struct device *dev, void *cpu_addr,
-				dma_addr_t handle, size_t size)
+			dma_addr_t handle, size_t size, int coherent_flag)
 {
 	__iommu_remove_mapping(dev, handle, size);
-	__free_from_pool(cpu_addr, size);
+	if (coherent_flag == COHERENT)
+		__dma_free_buffer(virt_to_page(cpu_addr), size);
+	else
+		__free_from_pool(cpu_addr, size);
 }
 
-static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
-	    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
+	    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs,
+	    int coherent_flag)
 {
 	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
 	struct page **pages;
@@ -1493,8 +1521,9 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	*handle = DMA_ERROR_CODE;
 	size = PAGE_ALIGN(size);
 
-	if (!gfpflags_allow_blocking(gfp))
-		return __iommu_alloc_atomic(dev, size, handle);
+	if (coherent_flag  == COHERENT || !gfpflags_allow_blocking(gfp))
+		return __iommu_alloc_simple(dev, size, gfp, handle,
+					    coherent_flag);
 
 	/*
 	 * Following is a work-around (a.k.a. hack) to prevent pages
@@ -1505,7 +1534,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	 */
 	gfp &= ~(__GFP_COMP);
 
-	pages = __iommu_alloc_buffer(dev, size, gfp, attrs);
+	pages = __iommu_alloc_buffer(dev, size, gfp, attrs, coherent_flag);
 	if (!pages)
 		return NULL;
 
@@ -1530,7 +1559,19 @@ err_buffer:
 	return NULL;
 }
 
-static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
+		    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+{
+	return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, NORMAL);
+}
+
+static void *arm_coherent_iommu_alloc_attrs(struct device *dev, size_t size,
+		    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+{
+	return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, COHERENT);
+}
+
+static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 		    void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		    struct dma_attrs *attrs)
 {
@@ -1540,8 +1581,6 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long off = vma->vm_pgoff;
 
-	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-
 	if (!pages)
 		return -ENXIO;
 
@@ -1562,19 +1601,34 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 
 	return 0;
 }
+static int arm_iommu_mmap_attrs(struct device *dev,
+		struct vm_area_struct *vma, void *cpu_addr,
+		dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
+
+	return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
+
+static int arm_coherent_iommu_mmap_attrs(struct device *dev,
+		struct vm_area_struct *vma, void *cpu_addr,
+		dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+	return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
 
 /*
  * free a page as defined by the above mapping.
  * Must not be called with IRQs disabled.
  */
-void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
-			  dma_addr_t handle, struct dma_attrs *attrs)
+void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+	dma_addr_t handle, struct dma_attrs *attrs, int coherent_flag)
 {
 	struct page **pages;
 	size = PAGE_ALIGN(size);
 
-	if (__in_atomic_pool(cpu_addr, size)) {
-		__iommu_free_atomic(dev, cpu_addr, handle, size);
+	if (coherent_flag == COHERENT || __in_atomic_pool(cpu_addr, size)) {
+		__iommu_free_atomic(dev, cpu_addr, handle, size, coherent_flag);
 		return;
 	}
 
@@ -1593,6 +1647,18 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	__iommu_free_buffer(dev, pages, size, attrs);
 }
 
+void arm_iommu_free_attrs(struct device *dev, size_t size,
+		    void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs)
+{
+	__arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, NORMAL);
+}
+
+void arm_coherent_iommu_free_attrs(struct device *dev, size_t size,
+		    void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs)
+{
+	__arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, COHERENT);
+}
+
 static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
 				 void *cpu_addr, dma_addr_t dma_addr,
 				 size_t size, struct dma_attrs *attrs)
@@ -1997,9 +2063,9 @@ struct dma_map_ops iommu_ops = {
 };
 
 struct dma_map_ops iommu_coherent_ops = {
-	.alloc		= arm_iommu_alloc_attrs,
-	.free		= arm_iommu_free_attrs,
-	.mmap		= arm_iommu_mmap_attrs,
+	.alloc		= arm_coherent_iommu_alloc_attrs,
+	.free		= arm_coherent_iommu_free_attrs,
+	.mmap		= arm_coherent_iommu_mmap_attrs,
 	.get_sgtable	= arm_iommu_get_sgtable,
 
 	.map_page	= arm_coherent_iommu_map_page,
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 6fcaac8e200f..a7123b4e129d 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -362,6 +362,39 @@ __ca15_errata:
 #endif
 	b	__errata_finish
 
+__ca12_errata:
+#ifdef CONFIG_ARM_ERRATA_818325_852422
+	mrc	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orr	r10, r10, #1 << 12		@ set bit #12
+	mcr	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_821420
+	mrc	p15, 0, r10, c15, c0, 2		@ read internal feature reg
+	orr	r10, r10, #1 << 1		@ set bit #1
+	mcr	p15, 0, r10, c15, c0, 2		@ write internal feature reg
+#endif
+#ifdef CONFIG_ARM_ERRATA_825619
+	mrc	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orr	r10, r10, #1 << 24		@ set bit #24
+	mcr	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+	b	__errata_finish
+
+__ca17_errata:
+#ifdef CONFIG_ARM_ERRATA_852421
+	cmp	r6, #0x12			@ only present up to r1p2
+	mrcle	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orrle	r10, r10, #1 << 24		@ set bit #24
+	mcrle	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_852423
+	cmp	r6, #0x12			@ only present up to r1p2
+	mrcle	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orrle	r10, r10, #1 << 12		@ set bit #12
+	mcrle	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+	b	__errata_finish
+
 __v7_pj4b_setup:
 #ifdef CONFIG_CPU_PJ4B
 
@@ -443,6 +476,16 @@ __v7_setup_cont:
 	teq	r0, r10
 	beq	__ca9_errata
 
+	/* Cortex-A12 Errata */
+	ldr	r10, =0x00000c0d		@ Cortex-A12 primary part number
+	teq	r0, r10
+	beq	__ca12_errata
+
+	/* Cortex-A17 Errata */
+	ldr	r10, =0x00000c0e		@ Cortex-A17 primary part number
+	teq	r0, r10
+	beq	__ca17_errata
+
 	/* Cortex-A15 Errata */
 	ldr	r10, =0x00000c0f		@ Cortex-A15 primary part number
 	teq	r0, r10