13 files changed, 29 insertions, 20 deletions

diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 8a7f65ba14b7..94077fbd96b7 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -23,7 +23,8 @@ ENTRY(v6_early_abort)
 #ifdef CONFIG_CPU_32v6K
         clrex
 #else
-        strex   r0, r1, [sp]                    @ Clear the exclusive monitor
+        sub     r1, sp, #4                      @ Get unused stack location
+        strex   r0, r1, [r1]                    @ Clear the exclusive monitor
 #endif
         mrc     p15, 0, r1, c5, c0, 0           @ get FSR
         mrc     p15, 0, r0, c6, c0, 0           @ get FAR
diff --git a/arch/arm/mm/copypage-feroceon.c b/arch/arm/mm/copypage-feroceon.c
index c3ba6a94da0c..70997d5bee2d 100644
--- a/arch/arm/mm/copypage-feroceon.c
+++ b/arch/arm/mm/copypage-feroceon.c
@@ -13,7 +13,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 
-static void __attribute__((naked))
+static void __naked
 feroceon_copy_user_page(void *kto, const void *kfrom)
 {
         asm("\
diff --git a/arch/arm/mm/copypage-v3.c b/arch/arm/mm/copypage-v3.c
index 70ed96c8af8e..de9c06854ad7 100644
--- a/arch/arm/mm/copypage-v3.c
+++ b/arch/arm/mm/copypage-v3.c
@@ -15,7 +15,7 @@
  *
  * FIXME: do we need to handle cache stuff...
  */
-static void __attribute__((naked))
+static void __naked
 v3_copy_user_page(void *kto, const void *kfrom)
 {
         asm("\n\
diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c
index 1601698b9800..7370a7142b04 100644
--- a/arch/arm/mm/copypage-v4mc.c
+++ b/arch/arm/mm/copypage-v4mc.c
@@ -44,7 +44,7 @@ static DEFINE_SPINLOCK(minicache_lock);
  * instruction.  If your processor does not supply this, you have to write your
  * own copy_user_highpage that does the right thing.
  */
-static void __attribute__((naked))
+static void __naked
 mc_copy_user_page(void *from, void *to)
 {
         asm volatile(
diff --git a/arch/arm/mm/copypage-v4wb.c b/arch/arm/mm/copypage-v4wb.c
index 3ec93dab7656..9ab098414227 100644
--- a/arch/arm/mm/copypage-v4wb.c
+++ b/arch/arm/mm/copypage-v4wb.c
@@ -22,7 +22,7 @@
  * instruction.  If your processor does not supply this, you have to write your
  * own copy_user_highpage that does the right thing.
  */
-static void __attribute__((naked))
+static void __naked
 v4wb_copy_user_page(void *kto, const void *kfrom)
 {
         asm("\
diff --git a/arch/arm/mm/copypage-v4wt.c b/arch/arm/mm/copypage-v4wt.c
index 0f1188efae45..300efafd6643 100644
--- a/arch/arm/mm/copypage-v4wt.c
+++ b/arch/arm/mm/copypage-v4wt.c
@@ -20,7 +20,7 @@
  * dirty data in the cache.  However, we do have to ensure that
  * subsequent reads are up to date.
  */
-static void __attribute__((naked))
+static void __naked
 v4wt_copy_user_page(void *kto, const void *kfrom)
 {
         asm("\
diff --git a/arch/arm/mm/copypage-xsc3.c b/arch/arm/mm/copypage-xsc3.c
index 39a994542cad..bc4525f5ab23 100644
--- a/arch/arm/mm/copypage-xsc3.c
+++ b/arch/arm/mm/copypage-xsc3.c
@@ -29,7 +29,7 @@
  * if we eventually end up using our copied page.
  *
  */
-static void __attribute__((naked))
+static void __naked
 xsc3_mc_copy_user_page(void *kto, const void *kfrom)
 {
         asm("\
diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index d18f2397ee2d..76824d3e966a 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c
@@ -42,7 +42,7 @@ static DEFINE_SPINLOCK(minicache_lock);
  * Dcache aliasing issue.  The writes will be forwarded to the write buffer,
  * and merged as appropriate.
  */
-static void __attribute__((naked))
+static void __naked
 mc_copy_user_page(void *from, void *to)
 {
         /*
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 310e479309ef..f1ef5613ccd4 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -490,26 +490,30 @@ core_initcall(consistent_init);
  */
 void dma_cache_maint(const void *start, size_t size, int direction)
 {
-        const void *end = start + size;
+        void (*inner_op)(const void *, const void *);
+        void (*outer_op)(unsigned long, unsigned long);
 
-        BUG_ON(!virt_addr_valid(start) || !virt_addr_valid(end - 1));
+        BUG_ON(!virt_addr_valid(start) || !virt_addr_valid(start + size - 1));
 
         switch (direction) {
         case DMA_FROM_DEVICE:           /* invalidate only */
-                dmac_inv_range(start, end);
-                outer_inv_range(__pa(start), __pa(end));
+                inner_op = dmac_inv_range;
+                outer_op = outer_inv_range;
                 break;
         case DMA_TO_DEVICE:             /* writeback only */
-                dmac_clean_range(start, end);
-                outer_clean_range(__pa(start), __pa(end));
+                inner_op = dmac_clean_range;
+                outer_op = outer_clean_range;
                 break;
         case DMA_BIDIRECTIONAL:         /* writeback and invalidate */
-                dmac_flush_range(start, end);
-                outer_flush_range(__pa(start), __pa(end));
+                inner_op = dmac_flush_range;
+                outer_op = outer_flush_range;
                 break;
         default:
                 BUG();
         }
+
+        inner_op(start, start + size);
+        outer_op(__pa(start), __pa(start) + size);
 }
 EXPORT_SYMBOL(dma_cache_maint);
 
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 81d0b8772de3..bc0099d5ae85 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -66,7 +66,10 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address)
          * fault (ie, is old), we can safely ignore any issues.
          */
         if (ret && (pte_val(entry) & L_PTE_MT_MASK) != shared_pte_mask) {
-                flush_cache_page(vma, address, pte_pfn(entry));
+                unsigned long pfn = pte_pfn(entry);
+                flush_cache_page(vma, address, pfn);
+                outer_flush_range((pfn << PAGE_SHIFT),
+                                  (pfn << PAGE_SHIFT) + PAGE_SIZE);
                 pte_val(entry) &= ~L_PTE_MT_MASK;
                 pte_val(entry) |= shared_pte_mask;
                 set_pte_at(vma->vm_mm, address, pte, entry);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 34df4d9d03a6..80fd3b69ae1f 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -382,7 +382,7 @@ void __init bootmem_init(void)
         for_each_node(node)
                 bootmem_free_node(node, mi);
 
-        high_memory = __va(memend_pfn << PAGE_SHIFT);
+        high_memory = __va((memend_pfn << PAGE_SHIFT) - 1) + 1;
 
         /*
          * This doesn't seem to be used by the Linux memory manager any
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 5358fcc7f61e..f7457fea6de8 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -124,7 +124,7 @@ int valid_phys_addr_range(unsigned long addr, size_t size)
 {
         if (addr < PHYS_OFFSET)
                 return 0;
-        if (addr + size > __pa(high_memory))
+        if (addr + size >= __pa(high_memory - 1))
                 return 0;
 
         return 1;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 9b36c5cb5e9f..d4d082c5c2d4 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -693,7 +693,8 @@ static void __init sanity_check_meminfo(void)
                  * Check whether this memory bank would entirely overlap
                  * the vmalloc area.
                  */
-                if (__va(bank->start) >= VMALLOC_MIN) {
+                if (__va(bank->start) >= VMALLOC_MIN ||
+                    __va(bank->start) < PAGE_OFFSET) {
                         printk(KERN_NOTICE "Ignoring RAM at %.8lx-%.8lx "
                                "(vmalloc region overlap).\n",
                                bank->start, bank->start + bank->size - 1);