ARM: 6380/1: Introduce __sync_icache_dcache() for VIPT caches

On SMP systems, there is a small chance of a PTE becoming visible to a
different CPU before the current cache maintenance operations in
update_mmu_cache(). To avoid this, cache maintenance must be handled in
set_pte_at() (similar to IA-64 and PowerPC).

This patch provides a unified VIPT cache handling mechanism and
implements the __sync_icache_dcache() function for ARMv6 onwards
architectures. It is called from set_pte_at() and replaces the
update_mmu_cache(). The latter is still used on VIVT hardware where a
vm_area_struct is required.

Tested-by: Rabin Vincent <rabin.vincent@stericsson.com>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

2 files changed, 32 insertions, 4 deletions

diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index ab68cf1ef80f..42e694f1d58e 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -278,9 +278,24 @@ extern struct page *empty_zero_page;
 
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
 
-#define set_pte_at(mm,addr,ptep,pteval) do { \
-        set_pte_ext(ptep, pteval, (addr) >= TASK_SIZE ? 0 : PTE_EXT_NG); \
- } while (0)
+#if __LINUX_ARM_ARCH__ < 6
+static inline void __sync_icache_dcache(pte_t pteval)
+{
+}
+#else
+extern void __sync_icache_dcache(pte_t pteval);
+#endif
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+                              pte_t *ptep, pte_t pteval)
+{
+        if (addr >= TASK_SIZE)
+                set_pte_ext(ptep, pteval, 0);
+        else {
+                __sync_icache_dcache(pteval);
+                set_pte_ext(ptep, pteval, PTE_EXT_NG);
+        }
+}
 
 /*
  * The following only work if pte_present() is true.
@@ -290,8 +305,13 @@ extern struct page *empty_zero_page;
 #define pte_write(pte)          (pte_val(pte) & L_PTE_WRITE)
 #define pte_dirty(pte)          (pte_val(pte) & L_PTE_DIRTY)
 #define pte_young(pte)          (pte_val(pte) & L_PTE_YOUNG)
+#define pte_exec(pte)           (pte_val(pte) & L_PTE_EXEC)
 #define pte_special(pte)        (0)
 
+#define pte_present_user(pte) \
+        ((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
+         (L_PTE_PRESENT | L_PTE_USER))
+
 #define PTE_BIT_FUNC(fn,op) \
 static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
 
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index 9ad329ad7458..989c9e57d92b 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -562,10 +562,18 @@ extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 /*
  * If PG_dcache_clean is not set for the page, we need to ensure that any
  * cache entries for the kernels virtual memory range are written
- * back to the page.
+ * back to the page. On ARMv6 and later, the cache coherency is handled via
+ * the set_pte_at() function.
  */
+#if __LINUX_ARM_ARCH__ < 6
 extern void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
         pte_t *ptep);
+#else
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+                                    unsigned long addr, pte_t *ptep)
+{
+}
+#endif
 
 #endif