[PATCH] powerpc: Add missing icache flushes for hugepages

On most powerpc CPUs, the dcache and icache are not coherent so
between writing and executing a page, the caches must be flushed.
Userspace programs assume pages given to them by the kernel are icache
clean, so we must do this flush between the kernel clearing a page and
it being mapped into userspace for execute.  We were not doing this
for hugepages, this patch corrects the situation.

We use the same lazy mechanism as we use for normal pages, delaying
the flush until userspace actually attempts to execute from the page
in question.

Tested on G5.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>

3 files changed, 37 insertions, 3 deletions

diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 706e8a63ced932..a33583f3b0e7d0 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -601,7 +601,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 	/* Handle hugepage regions */
 	if (unlikely(in_hugepage_area(mm->context, ea))) {
 		DBG_LOW(" -> huge page !\n");
-		return hash_huge_page(mm, access, ea, vsid, local);
+		return hash_huge_page(mm, access, ea, vsid, local, trap);
 	}
 
 	/* Get PTE and page size from page tables */
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 8bce515dc320d0..97512b89e7b027 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -639,8 +639,36 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	return -ENOMEM;
 }
 
+/*
+ * Called by asm hashtable.S for doing lazy icache flush
+ */
+static unsigned int hash_huge_page_do_lazy_icache(unsigned long rflags,
+						  pte_t pte, int trap)
+{
+	struct page *page;
+	int i;
+
+	if (!pfn_valid(pte_pfn(pte)))
+		return rflags;
+
+	page = pte_page(pte);
+
+	/* page is dirty */
+	if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) {
+		if (trap == 0x400) {
+			for (i = 0; i < (HPAGE_SIZE / PAGE_SIZE); i++)
+				__flush_dcache_icache(page_address(page+i));
+			set_bit(PG_arch_1, &page->flags);
+		} else {
+			rflags |= HPTE_R_N;
+		}
+	}
+	return rflags;
+}
+
 int hash_huge_page(struct mm_struct *mm, unsigned long access,
-		   unsigned long ea, unsigned long vsid, int local)
+		   unsigned long ea, unsigned long vsid, int local,
+		   unsigned long trap)
 {
 	pte_t *ptep;
 	unsigned long old_pte, new_pte;
@@ -691,6 +719,11 @@ int hash_huge_page(struct mm_struct *mm, unsigned long access,
 	rflags = 0x2 | (!(new_pte & _PAGE_RW));
  	/* _PAGE_EXEC -> HW_NO_EXEC since it's inverted */
 	rflags |= ((new_pte & _PAGE_EXEC) ? 0 : HPTE_R_N);
+	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
+		/* No CPU has hugepages but lacks no execute, so we
+		 * don't need to worry about that case */
+		rflags = hash_huge_page_do_lazy_icache(rflags, __pte(old_pte),
+						       trap);
 
 	/* Check if pte already has an hpte (case 2) */
 	if (unlikely(old_pte & _PAGE_HASHPTE)) {
diff --git a/include/asm-powerpc/mmu.h b/include/asm-powerpc/mmu.h
index c1b4bbabbe97f4..29b0bb0086d3fc 100644
--- a/include/asm-powerpc/mmu.h
+++ b/include/asm-powerpc/mmu.h
@@ -220,7 +220,8 @@ extern int __hash_page_64K(unsigned long ea, unsigned long access,
 			   unsigned int local);
 struct mm_struct;
 extern int hash_huge_page(struct mm_struct *mm, unsigned long access,
-			  unsigned long ea, unsigned long vsid, int local);
+			  unsigned long ea, unsigned long vsid, int local,
+			  unsigned long trap);
 
 extern void htab_finish_init(void);
 extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,