powerpc/mm: Differentiate between hugetlb and THP during page walk

We need to properly identify whether a hugepage is an explicit or
a transparent hugepage in follow_huge_addr(). We used to depend
on hugepage shift argument to do that. But in some case that can
result in wrong results. For ex:

On finding a transparent hugepage we set hugepage shift to PMD_SHIFT.
But we can end up clearing the thp pte, via pmdp_huge_get_and_clear.
We do prevent reusing the pfn page via the usage of
kick_all_cpus_sync(). But that happens after we updated the pte to 0.
Hence in follow_huge_addr() we can find hugepage shift set, but transparent
huge page check fail for a thp pte.

NOTE: We fixed a variant of this race against thp split in commit
691e95fd7396905a38d98919e9c150dbc3ea21a3
("powerpc/mm/thp: Make page table walk safe against thp split/collapse")

Without this patch, we may hit the BUG_ON(flags & FOLL_GET) in
follow_page_mask occasionally.

In the long term, we may want to switch ppc64 64k page size config to
enable CONFIG_ARCH_WANT_GENERAL_HUGETLB

Reported-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

3 files changed, 13 insertions, 4 deletions

diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index a82f534..ba3342b 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -14,6 +14,7 @@
 
 #include <asm/asm-compat.h>
 #include <asm/page.h>
+#include <asm/bug.h>
 
 /*
  * This is necessary to get the definition of PGTABLE_RANGE which we
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index fa1dfb7..3245f2d 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -437,9 +437,9 @@ static inline char *get_hpte_slot_array(pmd_t *pmdp)
 
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 				   pmd_t *pmdp, unsigned long old_pmd);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
 extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
 extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot);
@@ -479,6 +479,14 @@ static inline int pmd_trans_splitting(pmd_t pmd)
 }
 
 extern int has_transparent_hugepage(void);
+#else
+static inline void hpte_do_hugepage_flush(struct mm_struct *mm,
+					  unsigned long addr, pmd_t *pmdp,
+					  unsigned long old_pmd)
+{
+
+	WARN(1, "%s called with THP disabled\n", __func__);
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 static inline int pmd_large(pmd_t pmd)
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 0717693..b64b421 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -259,15 +259,15 @@ extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 #define has_transparent_hugepage() 0
 #endif
 pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
-				 unsigned *shift);
+				   bool *is_thp, unsigned *shift);
 static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
-					       unsigned *shift)
+					       bool *is_thp, unsigned *shift)
 {
 	if (!arch_irqs_disabled()) {
 		pr_info("%s called with irq enabled\n", __func__);
 		dump_stack();
 	}
-	return __find_linux_pte_or_hugepte(pgdir, ea, shift);
+	return __find_linux_pte_or_hugepte(pgdir, ea, is_thp, shift);
 }
 #endif /* __ASSEMBLY__ */