nds32: To implement these icache invalidation APIs since nds32 cores don't snoop

data cache.
This issue is found by Guo Ren. Based on the Documentation/core-api/cachetlb.rst
and it says:

"Any necessary cache flushing or other coherency operations
that need to occur should happen here.  If the processor's
instruction cache does not snoop cpu stores, it is very
likely that you will need to flush the instruction cache
for copy_to_user_page()."

"If the icache does not snoop stores then this
routine(flush_icache_range) will need to flush it."

Signed-off-by: Guo Ren <ren_guo@c-sky.com>
Signed-off-by: Greentime Hu <greentime@andestech.com>

arch/nds32/include/asm/cacheflush.h

@@ -8,6 +8,8 @@
 
 #define PG_dcache_dirty PG_arch_1
 
+void flush_icache_range(unsigned long start, unsigned long end);
+void flush_icache_page(struct vm_area_struct *vma, struct page *page);
 #ifdef CONFIG_CPU_CACHE_ALIASING
 void flush_cache_mm(struct mm_struct *mm);
 void flush_cache_dup_mm(struct mm_struct *mm);
@@ -34,13 +36,16 @@ void flush_anon_page(struct vm_area_struct *vma,
 void flush_kernel_dcache_page(struct page *page);
 void flush_kernel_vmap_range(void *addr, int size);
 void invalidate_kernel_vmap_range(void *addr, int size);
-void flush_icache_range(unsigned long start, unsigned long end);
-void flush_icache_page(struct vm_area_struct *vma, struct page *page);
 #define flush_dcache_mmap_lock(mapping)   xa_lock_irq(&(mapping)->i_pages)
 #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&(mapping)->i_pages)
 
 #else
 #include <asm-generic/cacheflush.h>
+#undef flush_icache_range
+#undef flush_icache_page
+#undef flush_icache_user_range
+void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+	                     unsigned long addr, int len);
 #endif
 
 #endif /* __NDS32_CACHEFLUSH_H__ */

arch/nds32/mm/cacheflush.c

@@ -13,6 +13,38 @@
 
 extern struct cache_info L1_cache_info[2];
 
+void flush_icache_range(unsigned long start, unsigned long end)
+{
+	unsigned long line_size, flags;
+	line_size = L1_cache_info[DCACHE].line_size;
+	start = start & ~(line_size - 1);
+	end = (end + line_size - 1) & ~(line_size - 1);
+	local_irq_save(flags);
+	cpu_cache_wbinval_range(start, end, 1);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_icache_range);
+
+void flush_icache_page(struct vm_area_struct *vma, struct page *page)
+{
+	unsigned long flags;
+	unsigned long kaddr;
+	local_irq_save(flags);
+	kaddr = (unsigned long)kmap_atomic(page);
+	cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC);
+	kunmap_atomic((void *)kaddr);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_icache_page);
+
+void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+	                     unsigned long addr, int len)
+{
+	unsigned long kaddr;
+	kaddr = (unsigned long)kmap_atomic(page) + (addr & ~PAGE_MASK);
+	flush_icache_range(kaddr, kaddr + len);
+	kunmap_atomic((void *)kaddr);
+}
 #ifndef CONFIG_CPU_CACHE_ALIASING
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 		      pte_t * pte)
@@ -318,27 +350,6 @@ void invalidate_kernel_vmap_range(void *addr, int size)
 }
 EXPORT_SYMBOL(invalidate_kernel_vmap_range);
 
-void flush_icache_range(unsigned long start, unsigned long end)
-{
-	unsigned long line_size, flags;
-	line_size = L1_cache_info[DCACHE].line_size;
-	start = start & ~(line_size - 1);
-	end = (end + line_size - 1) & ~(line_size - 1);
-	local_irq_save(flags);
-	cpu_cache_wbinval_range(start, end, 1);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(flush_icache_range);
-
-void flush_icache_page(struct vm_area_struct *vma, struct page *page)
-{
-	unsigned long flags;
-	local_irq_save(flags);
-	cpu_cache_wbinval_page((unsigned long)page_address(page),
-			       vma->vm_flags & VM_EXEC);
-	local_irq_restore(flags);
-}
-
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 		      pte_t * pte)
 {