arm64: Fix barriers used for page table modifications

The architecture specification states that both DSB and ISB are required
between page table modifications and subsequent memory accesses using the
corresponding virtual address. When TLB invalidation takes place, the
tlb_flush_* functions already have the necessary barriers. However, there are
other functions like create_mapping() for which this is not the case.

The patch adds the DSB+ISB instructions in the set_pte() function for
valid kernel mappings. The invalid pte case is handled by tlb_flush_*
and the user mappings in general have a corresponding update_mmu_cache()
call containing a DSB. Even when update_mmu_cache() isn't called, the
kernel can still cope with an unlikely spurious page fault by
re-executing the instruction.

In addition, the set_pmd, set_pud() functions gain an ISB for
architecture compliance when block mappings are created.

Signed-off-by: Catalin Marinas <[e-mail]>
Reported-by: Leif Lindholm <[e-mail]>
Acked-by: Steve Capper <[e-mail]>
Cc: Will Deacon <[e-mail]>
Cc: <[e-mail]>

arch/arm64/include/asm/cacheflush.h

···
 #define flush_icache_page(vma,page)	do { } while (0)
 
 /*
- * flush_cache_vmap() is used when creating mappings (eg, via vmap,
- * vmalloc, ioremap etc) in kernel space for pages.  On non-VIPT
- * caches, since the direct-mappings of these pages may contain cached
- * data, we need to do a full cache flush to ensure that writebacks
- * don't corrupt data placed into these pages via the new mappings.
+ * Not required on AArch64 (PIPT or VIPT non-aliasing D-cache).
  */
 static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 {
-	/*
-	 * set_pte_at() called from vmap_pte_range() does not
-	 * have a DSB after cleaning the cache line.
-	 */
-	dsb(ish);
 }
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)

arch/arm64/include/asm/pgtable.h

···
 
 #define pte_valid_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
+#define pte_valid_not_user(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
···
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
 	*ptep = pte;
+
+	/*
+	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
+	 * or update_mmu_cache() have the necessary barriers.
+	 */
+	if (pte_valid_not_user(pte)) {
+		dsb(ishst);
+		isb();
+	}
 }
 
 extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
···
 {
 	*pmdp = pmd;
 	dsb(ishst);
+	isb();
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
···
 {
 	*pudp = pud;
 	dsb(ishst);
+	isb();
 }
 
 static inline void pud_clear(pud_t *pudp)

arch/arm64/include/asm/tlbflush.h

···
 	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
 		asm("tlbi vaae1is, %0" : : "r"(addr));
 	dsb(ish);
+	isb();
 }
 
 /*
···
 				    unsigned long addr, pte_t *ptep)
 {
 	/*
-	 * set_pte() does not have a DSB, so make sure that the page table
-	 * write is visible.
+	 * set_pte() does not have a DSB for user mappings, so make sure that
+	 * the page table write is visible.
 	 */
 	dsb(ishst);
 }