6 files changed, 144 insertions, 36 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 94186b6c685..3fd629d5a51 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -352,6 +352,10 @@ config CPU_PJ4
 	select ARM_THUMBEE
 	select CPU_V7
 
+config CPU_PJ4B
+	bool
+	select CPU_V7
+
 # ARMv6
 config CPU_V6
 	bool "Support ARM V6 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 6911b8b2745..c2f37390308 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -352,7 +352,8 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 		/* Unmapped register. */
 		sync_reg_offset = L2X0_DUMMY_REG;
 #endif
-		outer_cache.set_debug = pl310_set_debug;
+		if ((cache_id & L2X0_CACHE_ID_RTL_MASK) <= L2X0_CACHE_ID_RTL_R3P0)
+			outer_cache.set_debug = pl310_set_debug;
 		break;
 	case L2X0_CACHE_ID_PART_L210:
 		ways = (aux >> 13) & 0xf;
@@ -459,8 +460,8 @@ static void aurora_pa_range(unsigned long start, unsigned long end,
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&l2x0_lock, flags);
-	writel(start, l2x0_base + AURORA_RANGE_BASE_ADDR_REG);
-	writel(end, l2x0_base + offset);
+	writel_relaxed(start, l2x0_base + AURORA_RANGE_BASE_ADDR_REG);
+	writel_relaxed(end, l2x0_base + offset);
 	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 
 	cache_sync();
@@ -505,15 +506,21 @@ static void aurora_clean_range(unsigned long start, unsigned long end)
 
 static void aurora_flush_range(unsigned long start, unsigned long end)
 {
-	if (!l2_wt_override) {
-		start &= ~(CACHE_LINE_SIZE - 1);
-		end = ALIGN(end, CACHE_LINE_SIZE);
-		while (start != end) {
-			unsigned long range_end = calc_range_end(start, end);
+	start &= ~(CACHE_LINE_SIZE - 1);
+	end = ALIGN(end, CACHE_LINE_SIZE);
+	while (start != end) {
+		unsigned long range_end = calc_range_end(start, end);
+		/*
+		 * If L2 is forced to WT, the L2 will always be clean and we
+		 * just need to invalidate.
+		 */
+		if (l2_wt_override)
 			aurora_pa_range(start, range_end - CACHE_LINE_SIZE,
-					AURORA_FLUSH_RANGE_REG);
-			start = range_end;
-		}
+							AURORA_INVAL_RANGE_REG);
+		else
+			aurora_pa_range(start, range_end - CACHE_LINE_SIZE,
+							AURORA_FLUSH_RANGE_REG);
+		start = range_end;
 	}
 }
 
@@ -668,8 +675,9 @@ static void pl310_resume(void)
 static void aurora_resume(void)
 {
 	if (!(readl(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
-		writel(l2x0_saved_regs.aux_ctrl, l2x0_base + L2X0_AUX_CTRL);
-		writel(l2x0_saved_regs.ctrl, l2x0_base + L2X0_CTRL);
+		writel_relaxed(l2x0_saved_regs.aux_ctrl,
+				l2x0_base + L2X0_AUX_CTRL);
+		writel_relaxed(l2x0_saved_regs.ctrl, l2x0_base + L2X0_CTRL);
 	}
 }
 
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index cd956647c21..7539ec27506 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -44,8 +44,10 @@ ENDPROC(v7_flush_icache_all)
 ENTRY(v7_flush_dcache_louis)
 	dmb					@ ensure ordering with previous memory accesses
 	mrc	p15, 1, r0, c0, c0, 1		@ read clidr, r0 = clidr
-	ands	r3, r0, #0xe00000		@ extract LoUIS from clidr
-	mov	r3, r3, lsr #20			@ r3 = LoUIS * 2
+	ALT_SMP(ands	r3, r0, #(7 << 21))	@ extract LoUIS from clidr
+	ALT_UP(ands	r3, r0, #(7 << 27))	@ extract LoUU from clidr
+	ALT_SMP(mov	r3, r3, lsr #20)	@ r3 = LoUIS * 2
+	ALT_UP(mov	r3, r3, lsr #26)	@ r3 = LoUU * 2
 	moveq	pc, lr				@ return if level == 0
 	mov	r10, #0				@ r10 (starting level) = 0
 	b	flush_levels			@ start flushing cache levels
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 58bc3e4d3bd..076c26d4386 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -124,8 +124,6 @@ static void arm_dma_sync_single_for_device(struct device *dev,
 	__dma_page_cpu_to_dev(page, offset, size, dir);
 }
 
-static int arm_dma_set_mask(struct device *dev, u64 dma_mask);
-
 struct dma_map_ops arm_dma_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
@@ -776,25 +774,27 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 	size_t size, enum dma_data_direction dir,
 	void (*op)(const void *, size_t, int))
 {
+	unsigned long pfn;
+	size_t left = size;
+
+	pfn = page_to_pfn(page) + offset / PAGE_SIZE;
+	offset %= PAGE_SIZE;
+
 	/*
 	 * 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.
 	 */
-	size_t left = size;
 	do {
 		size_t len = left;
 		void *vaddr;
 
+		page = pfn_to_page(pfn);
+
 		if (PageHighMem(page)) {
-			if (len + offset > PAGE_SIZE) {
-				if (offset >= PAGE_SIZE) {
-					page += offset / PAGE_SIZE;
-					offset %= PAGE_SIZE;
-				}
+			if (len + offset > PAGE_SIZE)
 				len = PAGE_SIZE - offset;
-			}
 			vaddr = kmap_high_get(page);
 			if (vaddr) {
 				vaddr += offset;
@@ -811,7 +811,7 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 			op(vaddr, len, dir);
 		}
 		offset = 0;
-		page++;
+		pfn++;
 		left -= len;
 	} while (left);
 }
@@ -971,7 +971,7 @@ int dma_supported(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_supported);
 
-static int arm_dma_set_mask(struct device *dev, u64 dma_mask)
+int arm_dma_set_mask(struct device *dev, u64 dma_mask)
 {
 	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
 		return -EIO;
@@ -1036,7 +1036,8 @@ static inline void __free_iova(struct dma_iommu_mapping *mapping,
 	spin_unlock_irqrestore(&mapping->lock, flags);
 }
 
-static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, gfp_t gfp)
+static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
+					  gfp_t gfp, struct dma_attrs *attrs)
 {
 	struct page **pages;
 	int count = size >> PAGE_SHIFT;
@@ -1050,6 +1051,23 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, gfp_t
 	if (!pages)
 		return NULL;
 
+	if (dma_get_attr(DMA_ATTR_FORCE_CONTIGUOUS, attrs))
+	{
+		unsigned long order = get_order(size);
+		struct page *page;
+
+		page = dma_alloc_from_contiguous(dev, count, order);
+		if (!page)
+			goto error;
+
+		__dma_clear_buffer(page, size);
+
+		for (i = 0; i < count; i++)
+			pages[i] = page + i;
+
+		return pages;
+	}
+
 	while (count) {
 		int j, order = __fls(count);
 
@@ -1083,14 +1101,21 @@ error:
 	return NULL;
 }
 
-static int __iommu_free_buffer(struct device *dev, struct page **pages, size_t size)
+static int __iommu_free_buffer(struct device *dev, struct page **pages,
+			       size_t size, struct dma_attrs *attrs)
 {
 	int count = size >> PAGE_SHIFT;
 	int array_size = count * sizeof(struct page *);
 	int i;
-	for (i = 0; i < count; i++)
-		if (pages[i])
-			__free_pages(pages[i], 0);
+
+	if (dma_get_attr(DMA_ATTR_FORCE_CONTIGUOUS, attrs)) {
+		dma_release_from_contiguous(dev, pages[0], count);
+	} else {
+		for (i = 0; i < count; i++)
+			if (pages[i])
+				__free_pages(pages[i], 0);
+	}
+
 	if (array_size <= PAGE_SIZE)
 		kfree(pages);
 	else
@@ -1252,7 +1277,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	if (gfp & GFP_ATOMIC)
 		return __iommu_alloc_atomic(dev, size, handle);
 
-	pages = __iommu_alloc_buffer(dev, size, gfp);
+	pages = __iommu_alloc_buffer(dev, size, gfp, attrs);
 	if (!pages)
 		return NULL;
 
@@ -1273,7 +1298,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 err_mapping:
 	__iommu_remove_mapping(dev, *handle, size);
 err_buffer:
-	__iommu_free_buffer(dev, pages, size);
+	__iommu_free_buffer(dev, pages, size, attrs);
 	return NULL;
 }
 
@@ -1329,7 +1354,7 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	}
 
 	__iommu_remove_mapping(dev, handle, size);
-	__iommu_free_buffer(dev, pages, size);
+	__iommu_free_buffer(dev, pages, size, attrs);
 }
 
 static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 9f0610243bd..ce328c7f5c9 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -283,7 +283,7 @@ static struct mem_type mem_types[] = {
 	},
 	[MT_MEMORY_SO] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
-				L_PTE_MT_UNCACHED,
+				L_PTE_MT_UNCACHED | L_PTE_XN,
 		.prot_l1   = PMD_TYPE_TABLE,
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_S |
 				PMD_SECT_UNCACHED | PMD_SECT_XN,
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 42cc833aa02..3a3c015f8d5 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -169,6 +169,64 @@ __v7_ca15mp_setup:
 	orreq	r0, r0, r10			@ Enable CPU-specific SMP bits
 	mcreq	p15, 0, r0, c1, c0, 1
 #endif
+	b	__v7_setup
+
+__v7_pj4b_setup:
+#ifdef CONFIG_CPU_PJ4B
+
+/* Auxiliary Debug Modes Control 1 Register */
+#define PJ4B_STATIC_BP (1 << 2) /* Enable Static BP */
+#define PJ4B_INTER_PARITY (1 << 8) /* Disable Internal Parity Handling */
+#define PJ4B_BCK_OFF_STREX (1 << 5) /* Enable the back off of STREX instr */
+#define PJ4B_CLEAN_LINE (1 << 16) /* Disable data transfer for clean line */
+
+/* Auxiliary Debug Modes Control 2 Register */
+#define PJ4B_FAST_LDR (1 << 23) /* Disable fast LDR */
+#define PJ4B_SNOOP_DATA (1 << 25) /* Do not interleave write and snoop data */
+#define PJ4B_CWF (1 << 27) /* Disable Critical Word First feature */
+#define PJ4B_OUTSDNG_NC (1 << 29) /* Disable outstanding non cacheable rqst */
+#define PJ4B_L1_REP_RR (1 << 30) /* L1 replacement - Strict round robin */
+#define PJ4B_AUX_DBG_CTRL2 (PJ4B_SNOOP_DATA | PJ4B_CWF |\
+			    PJ4B_OUTSDNG_NC | PJ4B_L1_REP_RR)
+
+/* Auxiliary Functional Modes Control Register 0 */
+#define PJ4B_SMP_CFB (1 << 1) /* Set SMP mode. Join the coherency fabric */
+#define PJ4B_L1_PAR_CHK (1 << 2) /* Support L1 parity checking */
+#define PJ4B_BROADCAST_CACHE (1 << 8) /* Broadcast Cache and TLB maintenance */
+
+/* Auxiliary Debug Modes Control 0 Register */
+#define PJ4B_WFI_WFE (1 << 22) /* WFI/WFE - serve the DVM and back to idle */
+
+	/* Auxiliary Debug Modes Control 1 Register */
+	mrc	p15, 1,	r0, c15, c1, 1
+	orr     r0, r0, #PJ4B_CLEAN_LINE
+	orr     r0, r0, #PJ4B_BCK_OFF_STREX
+	orr     r0, r0, #PJ4B_INTER_PARITY
+	bic	r0, r0, #PJ4B_STATIC_BP
+	mcr	p15, 1,	r0, c15, c1, 1
+
+	/* Auxiliary Debug Modes Control 2 Register */
+	mrc	p15, 1,	r0, c15, c1, 2
+	bic	r0, r0, #PJ4B_FAST_LDR
+	orr	r0, r0, #PJ4B_AUX_DBG_CTRL2
+	mcr	p15, 1,	r0, c15, c1, 2
+
+	/* Auxiliary Functional Modes Control Register 0 */
+	mrc	p15, 1,	r0, c15, c2, 0
+#ifdef CONFIG_SMP
+	orr	r0, r0, #PJ4B_SMP_CFB
+#endif
+	orr	r0, r0, #PJ4B_L1_PAR_CHK
+	orr	r0, r0, #PJ4B_BROADCAST_CACHE
+	mcr	p15, 1,	r0, c15, c2, 0
+
+	/* Auxiliary Debug Modes Control 0 Register */
+	mrc	p15, 1,	r0, c15, c1, 0
+	orr	r0, r0, #PJ4B_WFI_WFE
+	mcr	p15, 1,	r0, c15, c1, 0
+
+#endif /* CONFIG_CPU_PJ4B */
+
 __v7_setup:
 	adr	r12, __v7_setup_stack		@ the local stack
 	stmia	r12, {r0-r5, r7, r9, r11, lr}
@@ -188,7 +246,8 @@ __v7_setup:
 	ldr	r10, =0x00000c08		@ Cortex-A8 primary part number
 	teq	r0, r10
 	bne	2f
-#ifdef CONFIG_ARM_ERRATA_430973
+#if defined(CONFIG_ARM_ERRATA_430973) && !defined(CONFIG_ARCH_MULTIPLATFORM)
+
 	teq	r5, #0x00100000			@ only present in r1p*
 	mrceq	p15, 0, r10, c1, c0, 1		@ read aux control register
 	orreq	r10, r10, #(1 << 6)		@ set IBE to 1
@@ -342,6 +401,16 @@ __v7_ca9mp_proc_info:
 	.long	0xff0ffff0
 	__v7_proc __v7_ca9mp_setup
 	.size	__v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
+
+	/*
+	 * Marvell PJ4B processor.
+	 */
+	.type   __v7_pj4b_proc_info, #object
+__v7_pj4b_proc_info:
+	.long	0x562f5840
+	.long	0xfffffff0
+	__v7_proc __v7_pj4b_setup
+	.size	__v7_pj4b_proc_info, . - __v7_pj4b_proc_info
 #endif	/* CONFIG_ARM_LPAE */
 
 	/*