[PATCH v1] arm64/mm: Make set_ptes() robust when OAs cross 48-bit boundary

[Ryan Roberts]

Since the high bits [51:48] of an OA are not stored contiguously in the
PTE, there is a theoretical bug in set_ptes(), which just adds PAGE_SIZE
to the pte to get the pte with the next pfn. This works until the pfn
crosses the 48-bit boundary, at which point we overflow into the upper
attributes.

Of course one could argue (and Matthew Wilcox has :) that we will never
see a folio cross this boundary because we only allow naturally aligned
power-of-2 allocation, so this would require a half-petabyte folio. So
its only a theoretical bug. But its better that the code is robust
regardless.

I've implemented pte_next_pfn() as part of the fix, which is an opt-in
core-mm interface. So that is now available to the core-mm, which will
be needed shortly to support forthcoming fork()-batching optimizations.

pte_pgprot() wasn't particularly optimal when compiling for 52-bit PAs,
so I've reimplemented that using PTE_ADDR_MASK. This saves 2
instructions in pte_next_pfn(); 12 down to 10. When compiling for 48-bit
addresses, the generated code is the same (5 instructions).

Fixes: 4a169d61c2ed ("arm64: implement the new page table range API")
Closes: https://lore.kernel.org/linux-mm/fdaeb9a5-d890-499a-92c8-d171df43ad01@arm.com/
Signed-off-by: Ryan Roberts <ryan.roberts at arm.com>
---

Hi All,

This applies on top of v6.8-rc1. It's a dependency for David's fork-batch
work, so it would be preferable to go through the mm tree, once it has been
acked by Catalin or Will.

Thanks,
Ryan

 arch/arm64/include/asm/pgtable.h | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 79ce70fbb751..734b39401a05 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -92,6 +92,14 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
 #define pfn_pte(pfn,prot)	\
 	__pte(__phys_to_pte_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))

+/*
+ * Select all bits except the pfn
+ */
+static inline pgprot_t pte_pgprot(pte_t pte)
+{
+	return __pgprot(pte_val(pte) & ~PTE_ADDR_MASK);
+}
+
 #define pte_none(pte)		(!pte_val(pte))
 #define pte_clear(mm,addr,ptep)	set_pte(ptep, __pte(0))
 #define pte_page(pte)		(pfn_to_page(pte_pfn(pte)))
@@ -341,6 +349,12 @@ static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages)
 		mte_sync_tags(pte, nr_pages);
 }

+#define pte_next_pfn pte_next_pfn
+static inline pte_t pte_next_pfn(pte_t pte)
+{
+	return pfn_pte(pte_pfn(pte) + 1, pte_pgprot(pte));
+}
+
 static inline void set_ptes(struct mm_struct *mm,
 			    unsigned long __always_unused addr,
 			    pte_t *ptep, pte_t pte, unsigned int nr)
@@ -354,7 +368,7 @@ static inline void set_ptes(struct mm_struct *mm,
 		if (--nr == 0)
 			break;
 		ptep++;
-		pte_val(pte) += PAGE_SIZE;
+		pte = pte_next_pfn(pte);
 	}
 }
 #define set_ptes set_ptes
@@ -433,16 +447,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 	return clear_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE));
 }

-/*
- * Select all bits except the pfn
- */
-static inline pgprot_t pte_pgprot(pte_t pte)
-{
-	unsigned long pfn = pte_pfn(pte);
-
-	return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
-}
-
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * See the comment in include/linux/pgtable.h
--
2.25.1