Merge tag 'arc-v3.10-rc1-part2' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc

Pull second set of arc arch updates from Vineet Gupta:
 "Aliasing VIPT dcache support for ARC

  I'm satisified with testing, specially with fuse which has
  historically given grief to VIPT arches (ARM/PARISC...)"

* tag 'arc-v3.10-rc1-part2' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc:
  ARC: [TB10x] Remove GENERIC_GPIO
  ARC: [mm] Aliasing VIPT dcache support 4/4
  ARC: [mm] Aliasing VIPT dcache support 3/4
  ARC: [mm] Aliasing VIPT dcache support 2/4
  ARC: [mm] Aliasing VIPT dcache support 1/4
  ARC: [mm] refactor the core (i|d)cache line ops loops
  ARC: [mm] serious bug in vaddr based icache flush

13 files changed, 377 insertions, 74 deletions

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 491ae7923b10..5917099470ea 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -182,6 +182,10 @@ config ARC_CACHE_PAGES
 	  Note that Global I/D ENABLE + Per Page DISABLE works but corollary
 	  Global DISABLE + Per Page ENABLE won't work
 
+config ARC_CACHE_VIPT_ALIASING
+	bool "Support VIPT Aliasing D$"
+	default n
+
 endif	#ARC_CACHE
 
 config ARC_HAS_ICCM
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 48af742f8b5a..d8dd660898b9 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -32,7 +32,6 @@ generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sembuf.h
 generic-y += shmbuf.h
-generic-y += shmparam.h
 generic-y += siginfo.h
 generic-y += socket.h
 generic-y += sockios.h
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 6632273861fd..d5555fe4742a 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -55,9 +55,6 @@
 	: "r"(data), "r"(ptr));		\
 })
 
-/* used to give SHMLBA a value to avoid Cache Aliasing */
-extern unsigned int ARC_shmlba;
-
 #define ARCH_DMA_MINALIGN      L1_CACHE_BYTES
 
 /*
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index ee1f6eae82d2..9f841af41092 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -19,6 +19,7 @@
 #define _ASM_CACHEFLUSH_H
 
 #include <linux/mm.h>
+#include <asm/shmparam.h>
 
 /*
  * Semantically we need this because icache doesn't snoop dcache/dma.
@@ -33,7 +34,9 @@ void flush_cache_all(void);
 void flush_icache_range(unsigned long start, unsigned long end);
 void __sync_icache_dcache(unsigned long paddr, unsigned long vaddr, int len);
 void __inv_icache_page(unsigned long paddr, unsigned long vaddr);
-void __flush_dcache_page(unsigned long paddr);
+void ___flush_dcache_page(unsigned long paddr, unsigned long vaddr);
+#define __flush_dcache_page(p, v)	\
+		___flush_dcache_page((unsigned long)p, (unsigned long)v)
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 
@@ -50,18 +53,55 @@ void dma_cache_wback(unsigned long start, unsigned long sz);
 #define flush_cache_vmap(start, end)		flush_cache_all()
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
-/*
- * VM callbacks when entire/range of user-space V-P mappings are
- * torn-down/get-invalidated
- *
- * Currently we don't support D$ aliasing configs for our VIPT caches
- * NOPS for VIPT Cache with non-aliasing D$ configurations only
- */
-#define flush_cache_dup_mm(mm)			/* called on fork */
+#define flush_cache_dup_mm(mm)			/* called on fork (VIVT only) */
+
+#ifndef CONFIG_ARC_CACHE_VIPT_ALIASING
+
 #define flush_cache_mm(mm)			/* called on munmap/exit */
 #define flush_cache_range(mm, u_vstart, u_vend)
 #define flush_cache_page(vma, u_vaddr, pfn)	/* PF handling/COW-break */
 
+#else	/* VIPT aliasing dcache */
+
+/* To clear out stale userspace mappings */
+void flush_cache_mm(struct mm_struct *mm);
+void flush_cache_range(struct vm_area_struct *vma,
+	unsigned long start,unsigned long end);
+void flush_cache_page(struct vm_area_struct *vma,
+	unsigned long user_addr, unsigned long page);
+
+/*
+ * To make sure that userspace mapping is flushed to memory before
+ * get_user_pages() uses a kernel mapping to access the page
+ */
+#define ARCH_HAS_FLUSH_ANON_PAGE
+void flush_anon_page(struct vm_area_struct *vma,
+	struct page *page, unsigned long u_vaddr);
+
+#endif	/* CONFIG_ARC_CACHE_VIPT_ALIASING */
+
+/*
+ * Simple wrapper over config option
+ * Bootup code ensures that hardware matches kernel configuration
+ */
+static inline int cache_is_vipt_aliasing(void)
+{
+#ifdef CONFIG_ARC_CACHE_VIPT_ALIASING
+	return 1;
+#else
+	return 0;
+#endif
+}
+
+#define CACHE_COLOR(addr)	(((unsigned long)(addr) >> (PAGE_SHIFT)) & 3)
+
+/*
+ * checks if two addresses (after page aligning) index into same cache set
+ */
+#define addr_not_cache_congruent(addr1, addr2)				\
+	cache_is_vipt_aliasing() ? 					\
+		(CACHE_COLOR(addr1) != CACHE_COLOR(addr2)) : 0		\
+
 #define copy_to_user_page(vma, page, vaddr, dst, src, len)		\
 do {									\
 	memcpy(dst, src, len);						\
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
index bdf546104551..374a35514116 100644
--- a/arch/arc/include/asm/page.h
+++ b/arch/arc/include/asm/page.h
@@ -16,13 +16,27 @@
 #define get_user_page(vaddr)		__get_free_page(GFP_KERNEL)
 #define free_user_page(page, addr)	free_page(addr)
 
-/* TBD: for now don't worry about VIPT D$ aliasing */
 #define clear_page(paddr)		memset((paddr), 0, PAGE_SIZE)
 #define copy_page(to, from)		memcpy((to), (from), PAGE_SIZE)
 
+#ifndef CONFIG_ARC_CACHE_VIPT_ALIASING
+
 #define clear_user_page(addr, vaddr, pg)	clear_page(addr)
 #define copy_user_page(vto, vfrom, vaddr, pg)	copy_page(vto, vfrom)
 
+#else	/* VIPT aliasing dcache */
+
+struct vm_area_struct;
+struct page;
+
+#define __HAVE_ARCH_COPY_USER_HIGHPAGE
+
+void copy_user_highpage(struct page *to, struct page *from,
+			unsigned long u_vaddr, struct vm_area_struct *vma);
+void clear_user_page(void *to, unsigned long u_vaddr, struct page *page);
+
+#endif	/* CONFIG_ARC_CACHE_VIPT_ALIASING */
+
 #undef STRICT_MM_TYPECHECKS
 
 #ifdef STRICT_MM_TYPECHECKS
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index b7e36684c091..1cc4720faccb 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -395,6 +395,9 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
 
 #include <asm-generic/pgtable.h>
 
+/* to cope with aliasing VIPT cache */
+#define HAVE_ARCH_UNMAPPED_AREA
+
 /*
  * No page table caches to initialise
  */
diff --git a/arch/arc/include/asm/shmparam.h b/arch/arc/include/asm/shmparam.h
new file mode 100644
index 000000000000..fffeecc04270
--- /dev/null
+++ b/arch/arc/include/asm/shmparam.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ARC_ASM_SHMPARAM_H
+#define __ARC_ASM_SHMPARAM_H
+
+/* Handle upto 2 cache bins */
+#define	SHMLBA	(2 * PAGE_SIZE)
+
+/* Enforce SHMLBA in shmat */
+#define __ARCH_FORCE_SHMLBA
+
+#endif
diff --git a/arch/arc/include/asm/tlb.h b/arch/arc/include/asm/tlb.h
index fe91719866a5..85b6df839bd7 100644
--- a/arch/arc/include/asm/tlb.h
+++ b/arch/arc/include/asm/tlb.h
@@ -30,13 +30,20 @@ do {						\
 /*
  * This pair is called at time of munmap/exit to flush cache and TLB entries
  * for mappings being torn down.
- * 1) cache-flush part -implemented via tlb_start_vma( ) can be NOP (for now)
- *    as we don't support aliasing configs in our VIPT D$.
+ * 1) cache-flush part -implemented via tlb_start_vma( ) for VIPT aliasing D$
  * 2) tlb-flush part - implemted via tlb_end_vma( ) flushes the TLB range
  *
  * Note, read http://lkml.org/lkml/2004/1/15/6
  */
+#ifndef CONFIG_ARC_CACHE_VIPT_ALIASING
 #define tlb_start_vma(tlb, vma)
+#else
+#define tlb_start_vma(tlb, vma)						\
+do {									\
+	if (!tlb->fullmm)						\
+		flush_cache_range(vma, vma->vm_start, vma->vm_end);	\
+} while(0)
+#endif
 
 #define tlb_end_vma(tlb, vma)						\
 do {									\
diff --git a/arch/arc/mm/Makefile b/arch/arc/mm/Makefile
index 168dc146a8f6..ac95cc239c1e 100644
--- a/arch/arc/mm/Makefile
+++ b/arch/arc/mm/Makefile
@@ -7,4 +7,4 @@
 #
 
 obj-y	:= extable.o ioremap.o dma.o fault.o init.o
-obj-y	+= tlb.o tlbex.o cache_arc700.o
+obj-y	+= tlb.o tlbex.o cache_arc700.o mmap.o
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index c854cf95f706..2f12bca8aef3 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -68,6 +68,7 @@
 #include <linux/mmu_context.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/pagemap.h>
 #include <asm/cacheflush.h>
 #include <asm/cachectl.h>
 #include <asm/setup.h>
@@ -138,6 +139,7 @@ void __cpuinit arc_cache_init(void)
 	struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
 	struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache;
 	int way_pg_ratio = way_pg_ratio;
+	int dcache_does_alias;
 	char str[256];
 
 	printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
@@ -184,9 +186,13 @@ chk_dc:
 		panic("Cache H/W doesn't match kernel Config");
 	}
 
+	dcache_does_alias = (dc->sz / ARC_DCACHE_WAYS) > PAGE_SIZE;
+
 	/* check for D-Cache aliasing */
-	if ((dc->sz / ARC_DCACHE_WAYS) > PAGE_SIZE)
-		panic("D$ aliasing not handled right now\n");
+	if (dcache_does_alias && !cache_is_vipt_aliasing())
+		panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+	else if (!dcache_does_alias && cache_is_vipt_aliasing())
+		panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n");
 #endif
 
 	/* Set the default Invalidate Mode to "simpy discard dirty lines"
@@ -269,47 +275,57 @@ static inline void __dc_entire_op(const int cacheop)
  * Per Line Operation on D-Cache
  * Doesn't deal with type-of-op/IRQ-disabling/waiting-for-flush-to-complete
  * It's sole purpose is to help gcc generate ZOL
+ * (aliasing VIPT dcache flushing needs both vaddr and paddr)
  */
-static inline void __dc_line_loop(unsigned long start, unsigned long sz,
-					  int aux_reg)
+static inline void __dc_line_loop(unsigned long paddr, unsigned long vaddr,
+				  unsigned long sz, const int aux_reg)
 {
-	int num_lines, slack;
+	int num_lines;
 
 	/* Ensure we properly floor/ceil the non-line aligned/sized requests
-	 * and have @start - aligned to cache line and integral @num_lines.
+	 * and have @paddr - aligned to cache line and integral @num_lines.
 	 * This however can be avoided for page sized since:
-	 *  -@start will be cache-line aligned already (being page aligned)
+	 *  -@paddr will be cache-line aligned already (being page aligned)
 	 *  -@sz will be integral multiple of line size (being page sized).
 	 */
 	if (!(__builtin_constant_p(sz) && sz == PAGE_SIZE)) {
-		slack = start & ~DCACHE_LINE_MASK;
-		sz += slack;
-		start -= slack;
+		sz += paddr & ~DCACHE_LINE_MASK;
+		paddr &= DCACHE_LINE_MASK;
+		vaddr &= DCACHE_LINE_MASK;
 	}
 
 	num_lines = DIV_ROUND_UP(sz, ARC_DCACHE_LINE_LEN);
 
+#if (CONFIG_ARC_MMU_VER <= 2)
+	paddr |= (vaddr >> PAGE_SHIFT) & 0x1F;
+#endif
+
 	while (num_lines-- > 0) {
 #if (CONFIG_ARC_MMU_VER > 2)
 		/*
 		 * Just as for I$, in MMU v3, D$ ops also require
 		 * "tag" bits in DC_PTAG, "index" bits in FLDL,IVDL ops
-		 * But we pass phy addr for both. This works since Linux
-		 * doesn't support aliasing configs for D$, yet.
-		 * Thus paddr is enough to provide both tag and index.
 		 */
-		write_aux_reg(ARC_REG_DC_PTAG, start);
+		write_aux_reg(ARC_REG_DC_PTAG, paddr);
+
+		write_aux_reg(aux_reg, vaddr);
+		vaddr += ARC_DCACHE_LINE_LEN;
+#else
+		/* paddr contains stuffed vaddrs bits */
+		write_aux_reg(aux_reg, paddr);
 #endif
-		write_aux_reg(aux_reg, start);
-		start += ARC_DCACHE_LINE_LEN;
+		paddr += ARC_DCACHE_LINE_LEN;
 	}
 }
 
+/* For kernel mappings cache operation: index is same as paddr */
+#define __dc_line_op_k(p, sz, op)	__dc_line_op(p, p, sz, op)
+
 /*
  * D-Cache : Per Line INV (discard or wback+discard) or FLUSH (wback)
  */
-static inline void __dc_line_op(unsigned long start, unsigned long sz,
-					const int cacheop)
+static inline void __dc_line_op(unsigned long paddr, unsigned long vaddr,
+				unsigned long sz, const int cacheop)
 {
 	unsigned long flags, tmp = tmp;
 	int aux;
@@ -332,7 +348,7 @@ static inline void __dc_line_op(unsigned long start, unsigned long sz,
 	else
 		aux = ARC_REG_DC_FLDL;
 
-	__dc_line_loop(start, sz, aux);
+	__dc_line_loop(paddr, vaddr, sz, aux);
 
 	if (cacheop & OP_FLUSH)	/* flush / flush-n-inv both wait */
 		wait_for_flush();
@@ -347,7 +363,8 @@ static inline void __dc_line_op(unsigned long start, unsigned long sz,
 #else
 
 #define __dc_entire_op(cacheop)
-#define __dc_line_op(start, sz, cacheop)
+#define __dc_line_op(paddr, vaddr, sz, cacheop)
+#define __dc_line_op_k(paddr, sz, cacheop)
 
 #endif /* CONFIG_ARC_HAS_DCACHE */
 
@@ -399,49 +416,45 @@ static inline void __dc_line_op(unsigned long start, unsigned long sz,
 /***********************************************************
  * Machine specific helper for per line I-Cache invalidate.
  */
-static void __ic_line_inv_vaddr(unsigned long phy_start, unsigned long vaddr,
+static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr,
 				unsigned long sz)
 {
 	unsigned long flags;
-	int num_lines, slack;
-	unsigned int addr;
+	int num_lines;
 
 	/*
 	 * Ensure we properly floor/ceil the non-line aligned/sized requests:
 	 * However page sized flushes can be compile time optimised.
-	 *  -@phy_start will be cache-line aligned already (being page aligned)
+	 *  -@paddr will be cache-line aligned already (being page aligned)
 	 *  -@sz will be integral multiple of line size (being page sized).
 	 */
 	if (!(__builtin_constant_p(sz) && sz == PAGE_SIZE)) {
-		slack = phy_start & ~ICACHE_LINE_MASK;
-		sz += slack;
-		phy_start -= slack;
+		sz += paddr & ~ICACHE_LINE_MASK;
+		paddr &= ICACHE_LINE_MASK;
+		vaddr &= ICACHE_LINE_MASK;
 	}
 
 	num_lines = DIV_ROUND_UP(sz, ARC_ICACHE_LINE_LEN);
 
-#if (CONFIG_ARC_MMU_VER > 2)
-	vaddr &= ~ICACHE_LINE_MASK;
-	addr = phy_start;
-#else
+#if (CONFIG_ARC_MMU_VER <= 2)
 	/* bits 17:13 of vaddr go as bits 4:0 of paddr */
-	addr = phy_start | ((vaddr >> 13) & 0x1F);
+	paddr |= (vaddr >> PAGE_SHIFT) & 0x1F;
 #endif
 
 	local_irq_save(flags);
 	while (num_lines-- > 0) {
 #if (CONFIG_ARC_MMU_VER > 2)
 		/* tag comes from phy addr */
-		write_aux_reg(ARC_REG_IC_PTAG, addr);
+		write_aux_reg(ARC_REG_IC_PTAG, paddr);
 
 		/* index bits come from vaddr */
 		write_aux_reg(ARC_REG_IC_IVIL, vaddr);
 		vaddr += ARC_ICACHE_LINE_LEN;
 #else
 		/* paddr contains stuffed vaddrs bits */
-		write_aux_reg(ARC_REG_IC_IVIL, addr);
+		write_aux_reg(ARC_REG_IC_IVIL, paddr);
 #endif
-		addr += ARC_ICACHE_LINE_LEN;
+		paddr += ARC_ICACHE_LINE_LEN;
 	}
 	local_irq_restore(flags);
 }
@@ -457,29 +470,66 @@ static void __ic_line_inv_vaddr(unsigned long phy_start, unsigned long vaddr,
  * Exported APIs
  */
 
+/*
+ * Handle cache congruency of kernel and userspace mappings of page when kernel
+ * writes-to/reads-from
+ *
+ * The idea is to defer flushing of kernel mapping after a WRITE, possible if:
+ *  -dcache is NOT aliasing, hence any U/K-mappings of page are congruent
+ *  -U-mapping doesn't exist yet for page (finalised in update_mmu_cache)
+ *  -In SMP, if hardware caches are coherent
+ *
+ * There's a corollary case, where kernel READs from a userspace mapped page.
+ * If the U-mapping is not congruent to to K-mapping, former needs flushing.
+ */
 void flush_dcache_page(struct page *page)
 {
-	/* Make a note that dcache is not yet flushed for this page */
-	set_bit(PG_arch_1, &page->flags);
+	struct address_space *mapping;
+
+	if (!cache_is_vipt_aliasing()) {
+		set_bit(PG_arch_1, &page->flags);
+		return;
+	}
+
+	/* don't handle anon pages here */
+	mapping = page_mapping(page);
+	if (!mapping)
+		return;
+
+	/*
+	 * pagecache page, file not yet mapped to userspace
+	 * Make a note that K-mapping is dirty
+	 */
+	if (!mapping_mapped(mapping)) {
+		set_bit(PG_arch_1, &page->flags);
+	} else if (page_mapped(page)) {
+
+		/* kernel reading from page with U-mapping */
+		void *paddr = page_address(page);
+		unsigned long vaddr = page->index << PAGE_CACHE_SHIFT;
+
+		if (addr_not_cache_congruent(paddr, vaddr))
+			__flush_dcache_page(paddr, vaddr);
+	}
 }
 EXPORT_SYMBOL(flush_dcache_page);
 
 
 void dma_cache_wback_inv(unsigned long start, unsigned long sz)
 {
-	__dc_line_op(start, sz, OP_FLUSH_N_INV);
+	__dc_line_op_k(start, sz, OP_FLUSH_N_INV);
 }
 EXPORT_SYMBOL(dma_cache_wback_inv);
 
 void dma_cache_inv(unsigned long start, unsigned long sz)
 {
-	__dc_line_op(start, sz, OP_INV);
+	__dc_line_op_k(start, sz, OP_INV);
 }
 EXPORT_SYMBOL(dma_cache_inv);
 
 void dma_cache_wback(unsigned long start, unsigned long sz)
 {
-	__dc_line_op(start, sz, OP_FLUSH);
+	__dc_line_op_k(start, sz, OP_FLUSH);
 }
 EXPORT_SYMBOL(dma_cache_wback);
 
@@ -560,7 +610,7 @@ void __sync_icache_dcache(unsigned long paddr, unsigned long vaddr, int len)
 
 	local_irq_save(flags);
 	__ic_line_inv_vaddr(paddr, vaddr, len);
-	__dc_line_op(paddr, len, OP_FLUSH);
+	__dc_line_op(paddr, vaddr, len, OP_FLUSH);
 	local_irq_restore(flags);
 }
 
@@ -570,9 +620,13 @@ void __inv_icache_page(unsigned long paddr, unsigned long vaddr)
 	__ic_line_inv_vaddr(paddr, vaddr, PAGE_SIZE);
 }
 
-void __flush_dcache_page(unsigned long paddr)
+/*
+ * wrapper to clearout kernel or userspace mappings of a page
+ * For kernel mappings @vaddr == @paddr
+ */
+void ___flush_dcache_page(unsigned long paddr, unsigned long vaddr)
 {
-	__dc_line_op(paddr, PAGE_SIZE, OP_FLUSH_N_INV);
+	__dc_line_op(paddr, vaddr & PAGE_MASK, PAGE_SIZE, OP_FLUSH_N_INV);
 }
 
 void flush_icache_all(void)
@@ -601,6 +655,87 @@ noinline void flush_cache_all(void)
 
 }
 
+#ifdef CONFIG_ARC_CACHE_VIPT_ALIASING
+
+void flush_cache_mm(struct mm_struct *mm)
+{
+	flush_cache_all();
+}
+
+void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr,
+		      unsigned long pfn)
+{
+	unsigned int paddr = pfn << PAGE_SHIFT;
+
+	__sync_icache_dcache(paddr, u_vaddr, PAGE_SIZE);
+}
+
+void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
+		       unsigned long end)
+{
+	flush_cache_all();
+}
+
+void copy_user_highpage(struct page *to, struct page *from,
+	unsigned long u_vaddr, struct vm_area_struct *vma)
+{
+	void *kfrom = page_address(from);
+	void *kto = page_address(to);
+	int clean_src_k_mappings = 0;
+
+	/*
+	 * If SRC page was already mapped in userspace AND it's U-mapping is
+	 * not congruent with K-mapping, sync former to physical page so that
+	 * K-mapping in memcpy below, sees the right data
+	 *
+	 * Note that while @u_vaddr refers to DST page's userspace vaddr, it is
+	 * equally valid for SRC page as well
+	 */
+	if (page_mapped(from) && addr_not_cache_congruent(kfrom, u_vaddr)) {
+		__flush_dcache_page(kfrom, u_vaddr);
+		clean_src_k_mappings = 1;
+	}
+
+	copy_page(kto, kfrom);
+
+	/*
+	 * Mark DST page K-mapping as dirty for a later finalization by
+	 * update_mmu_cache(). Although the finalization could have been done
+	 * here as well (given that both vaddr/paddr are available).
+	 * But update_mmu_cache() already has code to do that for other
+	 * non copied user pages (e.g. read faults which wire in pagecache page
+	 * directly).
+	 */
+	set_bit(PG_arch_1, &to->flags);
+
+	/*
+	 * if SRC was already usermapped and non-congruent to kernel mapping
+	 * sync the kernel mapping back to physical page
+	 */
+	if (clean_src_k_mappings) {
+		__flush_dcache_page(kfrom, kfrom);
+	} else {
+		set_bit(PG_arch_1, &from->flags);
+	}
+}
+
+void clear_user_page(void *to, unsigned long u_vaddr, struct page *page)
+{
+	clear_page(to);
+	set_bit(PG_arch_1, &page->flags);
+}
+
+void flush_anon_page(struct vm_area_struct *vma, struct page *page,
+		     unsigned long u_vaddr)
+{
+	/* TBD: do we really need to clear the kernel mapping */
+	__flush_dcache_page(page_address(page), u_vaddr);
+	__flush_dcache_page(page_address(page), page_address(page));
+
+}
+
+#endif
+
 /**********************************************************************
  * Explicit Cache flush request from user space via syscall
  * Needed for JITs which generate code on the fly
diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c
new file mode 100644
index 000000000000..2e06d56e987b
--- /dev/null
+++ b/arch/arc/mm/mmap.c
@@ -0,0 +1,78 @@
+/*
+ * ARC700 mmap
+ *
+ * (started from arm version - for VIPT alias handling)
+ *
+ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/sched.h>
+#include <asm/cacheflush.h>
+
+#define COLOUR_ALIGN(addr, pgoff)			\
+	((((addr) + SHMLBA - 1) & ~(SHMLBA - 1)) +	\
+	 (((pgoff) << PAGE_SHIFT) & (SHMLBA - 1)))
+
+/*
+ * Ensure that shared mappings are correctly aligned to
+ * avoid aliasing issues with VIPT caches.
+ * We need to ensure that
+ * a specific page of an object is always mapped at a multiple of
+ * SHMLBA bytes.
+ */
+unsigned long
+arch_get_unmapped_area(struct file *filp, unsigned long addr,
+		unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int do_align = 0;
+	int aliasing = cache_is_vipt_aliasing();
+	struct vm_unmapped_area_info info;
+
+	/*
+	 * We only need to do colour alignment if D cache aliases.
+	 */
+	if (aliasing)
+		do_align = filp || (flags & MAP_SHARED);
+
+	/*
+	 * We enforce the MAP_FIXED case.
+	 */
+	if (flags & MAP_FIXED) {
+		if (aliasing && flags & MAP_SHARED &&
+		    (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
+			return -EINVAL;
+		return addr;
+	}
+
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	if (addr) {
+		if (do_align)
+			addr = COLOUR_ALIGN(addr, pgoff);
+		else
+			addr = PAGE_ALIGN(addr);
+
+		vma = find_vma(mm, addr);
+		if (TASK_SIZE - len >= addr &&
+		    (!vma || addr + len <= vma->vm_start))
+			return addr;
+	}
+
+	info.flags = 0;
+	info.length = len;
+	info.low_limit = mm->mmap_base;
+	info.high_limit = TASK_SIZE;
+	info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
+	info.align_offset = pgoff << PAGE_SHIFT;
+	return vm_unmapped_area(&info);
+}
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index 003d69ac6ffa..066145b5f348 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -421,25 +421,40 @@ void create_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
 /*
  * Called at the end of pagefault, for a userspace mapped page
  *  -pre-install the corresponding TLB entry into MMU
- *  -Finalize the delayed D-cache flush (wback+inv kernel mapping)
+ *  -Finalize the delayed D-cache flush of kernel mapping of page due to
+ *  	flush_dcache_page(), copy_user_page()
+ *
+ * Note that flush (when done) involves both WBACK - so physical page is
+ * in sync as well as INV - so any non-congruent aliases don't remain
  */
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned,
 		      pte_t *ptep)
 {
 	unsigned long vaddr = vaddr_unaligned & PAGE_MASK;
+	unsigned long paddr = pte_val(*ptep) & PAGE_MASK;
 
 	create_tlb(vma, vaddr, ptep);
 
-	/* icache doesn't snoop dcache, thus needs to be made coherent here */
-	if (vma->vm_flags & VM_EXEC) {
+	/*
+	 * Exec page : Independent of aliasing/page-color considerations,
+	 *	       since icache doesn't snoop dcache on ARC, any dirty
+	 *	       K-mapping of a code page needs to be wback+inv so that
+	 *	       icache fetch by userspace sees code correctly.
+	 * !EXEC page: If K-mapping is NOT congruent to U-mapping, flush it
+	 *	       so userspace sees the right data.
+	 *  (Avoids the flush for Non-exec + congruent mapping case)
+	 */
+	if (vma->vm_flags & VM_EXEC || addr_not_cache_congruent(paddr, vaddr)) {
 		struct page *page = pfn_to_page(pte_pfn(*ptep));
 
-		/* if page was dcache dirty, flush now */
 		int dirty = test_and_clear_bit(PG_arch_1, &page->flags);
 		if (dirty) {
-			unsigned long paddr =  pte_val(*ptep) & PAGE_MASK;
-			__flush_dcache_page(paddr);
-			__inv_icache_page(paddr, vaddr);
+			/* wback + inv dcache lines */
+			__flush_dcache_page(paddr, paddr);
+
+			/* invalidate any existing icache lines */
+			if (vma->vm_flags & VM_EXEC)
+				__inv_icache_page(paddr, vaddr);
 		}
 	}
 }
diff --git a/arch/arc/plat-tb10x/Kconfig b/arch/arc/plat-tb10x/Kconfig
index 4e121272c4e5..1d3452100f1f 100644
--- a/arch/arc/plat-tb10x/Kconfig
+++ b/arch/arc/plat-tb10x/Kconfig
@@ -27,10 +27,3 @@ menuconfig ARC_PLAT_TB10X
 	  Abilis Systems. TB10x is based on the ARC700 CPU architecture.
 	  Say Y if you are building a kernel for one of the SOCs in this
 	  series (e.g. TB100 or TB101). If in doubt say N.
-
-if ARC_PLAT_TB10X
-
-config GENERIC_GPIO
-	def_bool y
-
-endif