Merge branch 'for-linus' of master.kernel.org:/home/rmk/linux-2.6-arm

* 'for-linus' of master.kernel.org:/home/rmk/linux-2.6-arm: (100 commits)
  ARM: Eliminate decompressor -Dstatic= PIC hack
  ARM: 5958/1: ARM: U300: fix inverted clk round rate
  ARM: 5956/1: misplaced parentheses
  ARM: 5955/1: ep93xx: move timer defines into core.c and document
  ARM: 5954/1: ep93xx: move gpio interrupt support to gpio.c
  ARM: 5953/1: ep93xx: fix broken build of clock.c
  ARM: 5952/1: ARM: MM: Add ARM_L1_CACHE_SHIFT_6 for handle inside each ARCH Kconfig
  ARM: 5949/1: NUC900 add gpio virtual memory map
  ARM: 5948/1: Enable timer0 to time4 clock support for nuc910
  ARM: 5940/2: ARM: MMCI: remove custom DBG macro and printk
  ARM: make_coherent(): fix problems with highpte, part 2
  MM: Pass a PTE pointer to update_mmu_cache() rather than the PTE itself
  ARM: 5945/1: ep93xx: include correct irq.h in core.c
  ARM: 5933/1: amba-pl011: support hardware flow control
  ARM: 5930/1: Add PKMAP area description to memory.txt.
  ARM: 5929/1: Add checks to detect overlap of memory regions.
  ARM: 5928/1: Change type of VMALLOC_END to unsigned long.
  ARM: 5927/1: Make delimiters of DMA area globally visibly.
  ARM: 5926/1: Add "Virtual kernel memory..." printout.
  ARM: 5920/1: OMAP4: Enable L2 Cache
  ...

Fix up trivial conflict in arch/arm/mach-mx25/clock.c

41 files changed, 1143 insertions, 361 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index baf638487a2..c4ed9f93f64 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -399,7 +399,7 @@ config CPU_V6
 config CPU_32v6K
 	bool "Support ARM V6K processor extensions" if !SMP
 	depends on CPU_V6
-	default y if SMP && !ARCH_MX3
+	default y if SMP && !(ARCH_MX3 || ARCH_OMAP2)
 	help
 	  Say Y here if your ARMv6 processor supports the 'K' extension.
 	  This enables the kernel to use some instructions not present
@@ -410,7 +410,7 @@ config CPU_32v6K
 # ARMv7
 config CPU_V7
 	bool "Support ARM V7 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
-	select CPU_32v6K
+	select CPU_32v6K if !ARCH_OMAP2
 	select CPU_32v7
 	select CPU_ABRT_EV7
 	select CPU_PABRT_V7
@@ -754,7 +754,7 @@ config CACHE_FEROCEON_L2_WRITETHROUGH
 config CACHE_L2X0
 	bool "Enable the L2x0 outer cache controller"
 	depends on REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP || MACH_REALVIEW_PB1176 || \
-		   REALVIEW_EB_A9MP || ARCH_MX35 || ARCH_MX31 || MACH_REALVIEW_PBX || ARCH_NOMADIK
+		   REALVIEW_EB_A9MP || ARCH_MX35 || ARCH_MX31 || MACH_REALVIEW_PBX || ARCH_NOMADIK || ARCH_OMAP4
 	default y
 	select OUTER_CACHE
 	help
@@ -779,5 +779,5 @@ config CACHE_XSC3L2
 
 config ARM_L1_CACHE_SHIFT
 	int
-	default 6 if ARCH_OMAP3 || ARCH_S5PC1XX
+	default 6 if ARM_L1_CACHE_SHIFT_6
 	default 5
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 62820eda84d..edddd66faac 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -901,11 +901,7 @@ static int __init alignment_init(void)
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry *res;
 
-	res = proc_mkdir("cpu", NULL);
-	if (!res)
-		return -ENOMEM;
-
-	res = create_proc_entry("alignment", S_IWUSR | S_IRUGO, res);
+	res = create_proc_entry("cpu/alignment", S_IWUSR | S_IRUGO, NULL);
 	if (!res)
 		return -ENOMEM;
 
diff --git a/arch/arm/mm/cache-fa.S b/arch/arm/mm/cache-fa.S
index a89444a3c01..7148e53e607 100644
--- a/arch/arm/mm/cache-fa.S
+++ b/arch/arm/mm/cache-fa.S
@@ -157,7 +157,7 @@ ENTRY(fa_flush_kern_dcache_area)
  *	- start  - virtual start address
  *	- end	 - virtual end address
  */
-ENTRY(fa_dma_inv_range)
+fa_dma_inv_range:
 	tst	r0, #CACHE_DLINESIZE - 1
 	bic	r0, r0, #CACHE_DLINESIZE - 1
 	mcrne	p15, 0, r0, c7, c14, 1		@ clean & invalidate D entry
@@ -180,7 +180,7 @@ ENTRY(fa_dma_inv_range)
  *	- start  - virtual start address
  *	- end	 - virtual end address
  */
-ENTRY(fa_dma_clean_range)
+fa_dma_clean_range:
 	bic	r0, r0, #CACHE_DLINESIZE - 1
 1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 	add	r0, r0, #CACHE_DLINESIZE
@@ -205,6 +205,30 @@ ENTRY(fa_dma_flush_range)
 	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer
 	mov	pc, lr
 
+/*
+ *	dma_map_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(fa_dma_map_area)
+	add	r1, r1, r0
+	cmp	r2, #DMA_TO_DEVICE
+	beq	fa_dma_clean_range
+	bcs	fa_dma_inv_range
+	b	fa_dma_flush_range
+ENDPROC(fa_dma_map_area)
+
+/*
+ *	dma_unmap_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(fa_dma_unmap_area)
+	mov	pc, lr
+ENDPROC(fa_dma_unmap_area)
+
 	__INITDATA
 
 	.type	fa_cache_fns, #object
@@ -215,7 +239,7 @@ ENTRY(fa_cache_fns)
 	.long	fa_coherent_kern_range
 	.long	fa_coherent_user_range
 	.long	fa_flush_kern_dcache_area
-	.long	fa_dma_inv_range
-	.long	fa_dma_clean_range
+	.long	fa_dma_map_area
+	.long	fa_dma_unmap_area
 	.long	fa_dma_flush_range
 	.size	fa_cache_fns, . - fa_cache_fns
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index cb8fc6573b1..07334632d3e 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -42,6 +42,57 @@ static inline void cache_sync(void)
 	cache_wait(base + L2X0_CACHE_SYNC, 1);
 }
 
+static inline void l2x0_clean_line(unsigned long addr)
+{
+	void __iomem *base = l2x0_base;
+	cache_wait(base + L2X0_CLEAN_LINE_PA, 1);
+	writel(addr, base + L2X0_CLEAN_LINE_PA);
+}
+
+static inline void l2x0_inv_line(unsigned long addr)
+{
+	void __iomem *base = l2x0_base;
+	cache_wait(base + L2X0_INV_LINE_PA, 1);
+	writel(addr, base + L2X0_INV_LINE_PA);
+}
+
+#ifdef CONFIG_PL310_ERRATA_588369
+static void debug_writel(unsigned long val)
+{
+	extern void omap_smc1(u32 fn, u32 arg);
+
+	/*
+	 * Texas Instrument secure monitor api to modify the
+	 * PL310 Debug Control Register.
+	 */
+	omap_smc1(0x100, val);
+}
+
+static inline void l2x0_flush_line(unsigned long addr)
+{
+	void __iomem *base = l2x0_base;
+
+	/* Clean by PA followed by Invalidate by PA */
+	cache_wait(base + L2X0_CLEAN_LINE_PA, 1);
+	writel(addr, base + L2X0_CLEAN_LINE_PA);
+	cache_wait(base + L2X0_INV_LINE_PA, 1);
+	writel(addr, base + L2X0_INV_LINE_PA);
+}
+#else
+
+/* Optimised out for non-errata case */
+static inline void debug_writel(unsigned long val)
+{
+}
+
+static inline void l2x0_flush_line(unsigned long addr)
+{
+	void __iomem *base = l2x0_base;
+	cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1);
+	writel(addr, base + L2X0_CLEAN_INV_LINE_PA);
+}
+#endif
+
 static inline void l2x0_inv_all(void)
 {
 	unsigned long flags;
@@ -62,23 +113,24 @@ static void l2x0_inv_range(unsigned long start, unsigned long end)
 	spin_lock_irqsave(&l2x0_lock, flags);
 	if (start & (CACHE_LINE_SIZE - 1)) {
 		start &= ~(CACHE_LINE_SIZE - 1);
-		cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1);
-		writel(start, base + L2X0_CLEAN_INV_LINE_PA);
+		debug_writel(0x03);
+		l2x0_flush_line(start);
+		debug_writel(0x00);
 		start += CACHE_LINE_SIZE;
 	}
 
 	if (end & (CACHE_LINE_SIZE - 1)) {
 		end &= ~(CACHE_LINE_SIZE - 1);
-		cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1);
-		writel(end, base + L2X0_CLEAN_INV_LINE_PA);
+		debug_writel(0x03);
+		l2x0_flush_line(end);
+		debug_writel(0x00);
 	}
 
 	while (start < end) {
 		unsigned long blk_end = start + min(end - start, 4096UL);
 
 		while (start < blk_end) {
-			cache_wait(base + L2X0_INV_LINE_PA, 1);
-			writel(start, base + L2X0_INV_LINE_PA);
+			l2x0_inv_line(start);
 			start += CACHE_LINE_SIZE;
 		}
 
@@ -103,8 +155,7 @@ static void l2x0_clean_range(unsigned long start, unsigned long end)
 		unsigned long blk_end = start + min(end - start, 4096UL);
 
 		while (start < blk_end) {
-			cache_wait(base + L2X0_CLEAN_LINE_PA, 1);
-			writel(start, base + L2X0_CLEAN_LINE_PA);
+			l2x0_clean_line(start);
 			start += CACHE_LINE_SIZE;
 		}
 
@@ -128,11 +179,12 @@ static void l2x0_flush_range(unsigned long start, unsigned long end)
 	while (start < end) {
 		unsigned long blk_end = start + min(end - start, 4096UL);
 
+		debug_writel(0x03);
 		while (start < blk_end) {
-			cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1);
-			writel(start, base + L2X0_CLEAN_INV_LINE_PA);
+			l2x0_flush_line(start);
 			start += CACHE_LINE_SIZE;
 		}
+		debug_writel(0x00);
 
 		if (blk_end < end) {
 			spin_unlock_irqrestore(&l2x0_lock, flags);
diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S
index 2a482731ea3..c2ff3c599fe 100644
--- a/arch/arm/mm/cache-v3.S
+++ b/arch/arm/mm/cache-v3.S
@@ -84,20 +84,6 @@ ENTRY(v3_flush_kern_dcache_area)
 	/* FALLTHROUGH */
 
 /*
- *	dma_inv_range(start, end)
- *
- *	Invalidate (discard) the specified virtual address range.
- *	May not write back any entries.  If 'start' or 'end'
- *	are not cache line aligned, those lines must be written
- *	back.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v3_dma_inv_range)
-	/* FALLTHROUGH */
-
-/*
  *	dma_flush_range(start, end)
  *
  *	Clean and invalidate the specified virtual address range.
@@ -108,18 +94,29 @@ ENTRY(v3_dma_inv_range)
 ENTRY(v3_dma_flush_range)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c0, 0		@ flush ID cache
+	mov	pc, lr
+
+/*
+ *	dma_unmap_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(v3_dma_unmap_area)
+	teq	r2, #DMA_TO_DEVICE
+	bne	v3_dma_flush_range
 	/* FALLTHROUGH */
 
 /*
- *	dma_clean_range(start, end)
- *
- *	Clean (write back) the specified virtual address range.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
+ *	dma_map_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
  */
-ENTRY(v3_dma_clean_range)
+ENTRY(v3_dma_map_area)
 	mov	pc, lr
+ENDPROC(v3_dma_unmap_area)
+ENDPROC(v3_dma_map_area)
 
 	__INITDATA
 
@@ -131,7 +128,7 @@ ENTRY(v3_cache_fns)
 	.long	v3_coherent_kern_range
 	.long	v3_coherent_user_range
 	.long	v3_flush_kern_dcache_area
-	.long	v3_dma_inv_range
-	.long	v3_dma_clean_range
+	.long	v3_dma_map_area
+	.long	v3_dma_unmap_area
 	.long	v3_dma_flush_range
 	.size	v3_cache_fns, . - v3_cache_fns
diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S
index 5c7da3e372e..4810f7e3e81 100644
--- a/arch/arm/mm/cache-v4.S
+++ b/arch/arm/mm/cache-v4.S
@@ -94,20 +94,6 @@ ENTRY(v4_flush_kern_dcache_area)
 	/* FALLTHROUGH */
 
 /*
- *	dma_inv_range(start, end)
- *
- *	Invalidate (discard) the specified virtual address range.
- *	May not write back any entries.  If 'start' or 'end'
- *	are not cache line aligned, those lines must be written
- *	back.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v4_dma_inv_range)
-	/* FALLTHROUGH */
-
-/*
  *	dma_flush_range(start, end)
  *
  *	Clean and invalidate the specified virtual address range.
@@ -120,18 +106,29 @@ ENTRY(v4_dma_flush_range)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c7, 0		@ flush ID cache
 #endif
+	mov	pc, lr
+
+/*
+ *	dma_unmap_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(v4_dma_unmap_area)
+	teq	r2, #DMA_TO_DEVICE
+	bne	v4_dma_flush_range
 	/* FALLTHROUGH */
 
 /*
- *	dma_clean_range(start, end)
- *
- *	Clean (write back) the specified virtual address range.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
+ *	dma_map_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
  */
-ENTRY(v4_dma_clean_range)
+ENTRY(v4_dma_map_area)
 	mov	pc, lr
+ENDPROC(v4_dma_unmap_area)
+ENDPROC(v4_dma_map_area)
 
 	__INITDATA
 
@@ -143,7 +140,7 @@ ENTRY(v4_cache_fns)
 	.long	v4_coherent_kern_range
 	.long	v4_coherent_user_range
 	.long	v4_flush_kern_dcache_area
-	.long	v4_dma_inv_range
-	.long	v4_dma_clean_range
+	.long	v4_dma_map_area
+	.long	v4_dma_unmap_area
 	.long	v4_dma_flush_range
 	.size	v4_cache_fns, . - v4_cache_fns
diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S
index 3dbedf1ec0e..df8368afa10 100644
--- a/arch/arm/mm/cache-v4wb.S
+++ b/arch/arm/mm/cache-v4wb.S
@@ -173,7 +173,7 @@ ENTRY(v4wb_coherent_user_range)
  *	- start  - virtual start address
  *	- end	 - virtual end address
  */
-ENTRY(v4wb_dma_inv_range)
+v4wb_dma_inv_range:
 	tst	r0, #CACHE_DLINESIZE - 1
 	bic	r0, r0, #CACHE_DLINESIZE - 1
 	mcrne	p15, 0, r0, c7, c10, 1		@ clean D entry
@@ -194,7 +194,7 @@ ENTRY(v4wb_dma_inv_range)
  *	- start  - virtual start address
  *	- end	 - virtual end address
  */
-ENTRY(v4wb_dma_clean_range)
+v4wb_dma_clean_range:
 	bic	r0, r0, #CACHE_DLINESIZE - 1
 1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 	add	r0, r0, #CACHE_DLINESIZE
@@ -216,6 +216,30 @@ ENTRY(v4wb_dma_clean_range)
 	.globl	v4wb_dma_flush_range
 	.set	v4wb_dma_flush_range, v4wb_coherent_kern_range
 
+/*
+ *	dma_map_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(v4wb_dma_map_area)
+	add	r1, r1, r0
+	cmp	r2, #DMA_TO_DEVICE
+	beq	v4wb_dma_clean_range
+	bcs	v4wb_dma_inv_range
+	b	v4wb_dma_flush_range
+ENDPROC(v4wb_dma_map_area)
+
+/*
+ *	dma_unmap_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(v4wb_dma_unmap_area)
+	mov	pc, lr
+ENDPROC(v4wb_dma_unmap_area)
+
 	__INITDATA
 
 	.type	v4wb_cache_fns, #object
@@ -226,7 +250,7 @@ ENTRY(v4wb_cache_fns)
 	.long	v4wb_coherent_kern_range
 	.long	v4wb_coherent_user_range
 	.long	v4wb_flush_kern_dcache_area
-	.long	v4wb_dma_inv_range
-	.long	v4wb_dma_clean_range
+	.long	v4wb_dma_map_area
+	.long	v4wb_dma_unmap_area
 	.long	v4wb_dma_flush_range
 	.size	v4wb_cache_fns, . - v4wb_cache_fns
diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S
index b3b7410270b..45c70312f43 100644
--- a/arch/arm/mm/cache-v4wt.S
+++ b/arch/arm/mm/cache-v4wt.S
@@ -142,23 +142,12 @@ ENTRY(v4wt_flush_kern_dcache_area)
  *	- start  - virtual start address
  *	- end	 - virtual end address
  */
-ENTRY(v4wt_dma_inv_range)
+v4wt_dma_inv_range:
 	bic	r0, r0, #CACHE_DLINESIZE - 1
 1:	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D entry
 	add	r0, r0, #CACHE_DLINESIZE
 	cmp	r0, r1
 	blo	1b
-	/* FALLTHROUGH */
-
-/*
- *	dma_clean_range(start, end)
- *
- *	Clean the specified virtual address range.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v4wt_dma_clean_range)
 	mov	pc, lr
 
 /*
@@ -172,6 +161,29 @@ ENTRY(v4wt_dma_clean_range)
 	.globl	v4wt_dma_flush_range
 	.equ	v4wt_dma_flush_range, v4wt_dma_inv_range
 
+/*
+ *	dma_unmap_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(v4wt_dma_unmap_area)
+	add	r1, r1, r0
+	teq	r2, #DMA_TO_DEVICE
+	bne	v4wt_dma_inv_range
+	/* FALLTHROUGH */
+
+/*
+ *	dma_map_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(v4wt_dma_map_area)
+	mov	pc, lr
+ENDPROC(v4wt_dma_unmap_area)
+ENDPROC(v4wt_dma_map_area)
+
 	__INITDATA
 
 	.type	v4wt_cache_fns, #object
@@ -182,7 +194,7 @@ ENTRY(v4wt_cache_fns)
 	.long	v4wt_coherent_kern_range
 	.long	v4wt_coherent_user_range
 	.long	v4wt_flush_kern_dcache_area
-	.long	v4wt_dma_inv_range
-	.long	v4wt_dma_clean_range
+	.long	v4wt_dma_map_area
+	.long	v4wt_dma_unmap_area
 	.long	v4wt_dma_flush_range
 	.size	v4wt_cache_fns, . - v4wt_cache_fns
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 4ba0a24ce6f..9d89c67a1cc 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -195,7 +195,7 @@ ENTRY(v6_flush_kern_dcache_area)
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
  */
-ENTRY(v6_dma_inv_range)
+v6_dma_inv_range:
 	tst	r0, #D_CACHE_LINE_SIZE - 1
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 #ifdef HARVARD_CACHE
@@ -228,7 +228,7 @@ ENTRY(v6_dma_inv_range)
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
  */
-ENTRY(v6_dma_clean_range)
+v6_dma_clean_range:
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 1:
 #ifdef HARVARD_CACHE
@@ -263,6 +263,32 @@ ENTRY(v6_dma_flush_range)
 	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer
 	mov	pc, lr
 
+/*
+ *	dma_map_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(v6_dma_map_area)
+	add	r1, r1, r0
+	teq	r2, #DMA_FROM_DEVICE
+	beq	v6_dma_inv_range
+	b	v6_dma_clean_range
+ENDPROC(v6_dma_map_area)
+
+/*
+ *	dma_unmap_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(v6_dma_unmap_area)
+	add	r1, r1, r0
+	teq	r2, #DMA_TO_DEVICE
+	bne	v6_dma_inv_range
+	mov	pc, lr
+ENDPROC(v6_dma_unmap_area)
+
 	__INITDATA
 
 	.type	v6_cache_fns, #object
@@ -273,7 +299,7 @@ ENTRY(v6_cache_fns)
 	.long	v6_coherent_kern_range
 	.long	v6_coherent_user_range
 	.long	v6_flush_kern_dcache_area
-	.long	v6_dma_inv_range
-	.long	v6_dma_clean_range
+	.long	v6_dma_map_area
+	.long	v6_dma_unmap_area
 	.long	v6_dma_flush_range
 	.size	v6_cache_fns, . - v6_cache_fns
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 9073db849fb..bcd64f26587 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -216,7 +216,7 @@ ENDPROC(v7_flush_kern_dcache_area)
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
  */
-ENTRY(v7_dma_inv_range)
+v7_dma_inv_range:
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	tst	r0, r3
@@ -240,7 +240,7 @@ ENDPROC(v7_dma_inv_range)
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
  */
-ENTRY(v7_dma_clean_range)
+v7_dma_clean_range:
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r0, r0, r3
@@ -271,6 +271,32 @@ ENTRY(v7_dma_flush_range)
 	mov	pc, lr
 ENDPROC(v7_dma_flush_range)
 
+/*
+ *	dma_map_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(v7_dma_map_area)
+	add	r1, r1, r0
+	teq	r2, #DMA_FROM_DEVICE
+	beq	v7_dma_inv_range
+	b	v7_dma_clean_range
+ENDPROC(v7_dma_map_area)
+
+/*
+ *	dma_unmap_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(v7_dma_unmap_area)
+	add	r1, r1, r0
+	teq	r2, #DMA_TO_DEVICE
+	bne	v7_dma_inv_range
+	mov	pc, lr
+ENDPROC(v7_dma_unmap_area)
+
 	__INITDATA
 
 	.type	v7_cache_fns, #object
@@ -281,7 +307,7 @@ ENTRY(v7_cache_fns)
 	.long	v7_coherent_kern_range
 	.long	v7_coherent_user_range
 	.long	v7_flush_kern_dcache_area
-	.long	v7_dma_inv_range
-	.long	v7_dma_clean_range
+	.long	v7_dma_map_area
+	.long	v7_dma_unmap_area
 	.long	v7_dma_flush_range
 	.size	v7_cache_fns, . - v7_cache_fns
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index a9e22e31eaa..b0ee9ba3cfa 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -10,12 +10,17 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/percpu.h>
 
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
 
 static DEFINE_SPINLOCK(cpu_asid_lock);
 unsigned int cpu_last_asid = ASID_FIRST_VERSION;
+#ifdef CONFIG_SMP
+DEFINE_PER_CPU(struct mm_struct *, current_mm);
+#endif
 
 /*
  * We fork()ed a process, and we need a new context for the child
@@ -26,13 +31,109 @@ unsigned int cpu_last_asid = ASID_FIRST_VERSION;
 void __init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
 	mm->context.id = 0;
+	spin_lock_init(&mm->context.id_lock);
 }
 
+static void flush_context(void)
+{
+	/* set the reserved ASID before flushing the TLB */
+	asm("mcr	p15, 0, %0, c13, c0, 1\n" : : "r" (0));
+	isb();
+	local_flush_tlb_all();
+	if (icache_is_vivt_asid_tagged()) {
+		__flush_icache_all();
+		dsb();
+	}
+}
+
+#ifdef CONFIG_SMP
+
+static void set_mm_context(struct mm_struct *mm, unsigned int asid)
+{
+	unsigned long flags;
+
+	/*
+	 * Locking needed for multi-threaded applications where the
+	 * same mm->context.id could be set from different CPUs during
+	 * the broadcast. This function is also called via IPI so the
+	 * mm->context.id_lock has to be IRQ-safe.
+	 */
+	spin_lock_irqsave(&mm->context.id_lock, flags);
+	if (likely((mm->context.id ^ cpu_last_asid) >> ASID_BITS)) {
+		/*
+		 * Old version of ASID found. Set the new one and
+		 * reset mm_cpumask(mm).
+		 */
+		mm->context.id = asid;
+		cpumask_clear(mm_cpumask(mm));
+	}
+	spin_unlock_irqrestore(&mm->context.id_lock, flags);
+
+	/*
+	 * Set the mm_cpumask(mm) bit for the current CPU.
+	 */
+	cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+}
+
+/*
+ * Reset the ASID on the current CPU. This function call is broadcast
+ * from the CPU handling the ASID rollover and holding cpu_asid_lock.
+ */
+static void reset_context(void *info)
+{
+	unsigned int asid;
+	unsigned int cpu = smp_processor_id();
+	struct mm_struct *mm = per_cpu(current_mm, cpu);
+
+	/*
+	 * Check if a current_mm was set on this CPU as it might still
+	 * be in the early booting stages and using the reserved ASID.
+	 */
+	if (!mm)
+		return;
+
+	smp_rmb();
+	asid = cpu_last_asid + cpu + 1;
+
+	flush_context();
+	set_mm_context(mm, asid);
+
+	/* set the new ASID */
+	asm("mcr	p15, 0, %0, c13, c0, 1\n" : : "r" (mm->context.id));
+	isb();
+}
+
+#else
+
+static inline void set_mm_context(struct mm_struct *mm, unsigned int asid)
+{
+	mm->context.id = asid;
+	cpumask_copy(mm_cpumask(mm), cpumask_of(smp_processor_id()));
+}
+
+#endif
+
 void __new_context(struct mm_struct *mm)
 {
 	unsigned int asid;
 
 	spin_lock(&cpu_asid_lock);
+#ifdef CONFIG_SMP
+	/*
+	 * Check the ASID again, in case the change was broadcast from
+	 * another CPU before we acquired the lock.
+	 */
+	if (unlikely(((mm->context.id ^ cpu_last_asid) >> ASID_BITS) == 0)) {
+		cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+		spin_unlock(&cpu_asid_lock);
+		return;
+	}
+#endif
+	/*
+	 * At this point, it is guaranteed that the current mm (with
+	 * an old ASID) isn't active on any other CPU since the ASIDs
+	 * are changed simultaneously via IPI.
+	 */
 	asid = ++cpu_last_asid;
 	if (asid == 0)
 		asid = cpu_last_asid = ASID_FIRST_VERSION;
@@ -42,20 +143,15 @@ void __new_context(struct mm_struct *mm)
 	 * to start a new version and flush the TLB.
 	 */
 	if (unlikely((asid & ~ASID_MASK) == 0)) {
-		asid = ++cpu_last_asid;
-		/* set the reserved ASID before flushing the TLB */
-		asm("mcr	p15, 0, %0, c13, c0, 1	@ set reserved context ID\n"
-		    :
-		    : "r" (0));
-		isb();
-		flush_tlb_all();
-		if (icache_is_vivt_asid_tagged()) {
-			__flush_icache_all();
-			dsb();
-		}
+		asid = cpu_last_asid + smp_processor_id() + 1;
+		flush_context();
+#ifdef CONFIG_SMP
+		smp_w