arm64/mm: wire up PTE_CONT for user mappings

With the ptep API sufficiently refactored, we can now introduce a new
"contpte" API layer, which transparently manages the PTE_CONT bit for user
mappings.

In this initial implementation, only suitable batches of PTEs, set via
set_ptes(), are mapped with the PTE_CONT bit.  Any subsequent modification
of individual PTEs will cause an "unfold" operation to repaint the contpte
block as individual PTEs before performing the requested operation. 
While, a modification of a single PTE could cause the block of PTEs to
which it belongs to become eligible for "folding" into a contpte entry,
"folding" is not performed in this initial implementation due to the costs
of checking the requirements are met.  Due to this, contpte mappings will
degrade back to normal pte mappings over time if/when protections are
changed.  This will be solved in a future patch.

Since a contpte block only has a single access and dirty bit, the semantic
here changes slightly; when getting a pte (e.g.  ptep_get()) that is part
of a contpte mapping, the access and dirty information are pulled from the
block (so all ptes in the block return the same access/dirty info).  When
changing the access/dirty info on a pte (e.g.  ptep_set_access_flags())
that is part of a contpte mapping, this change will affect the whole
contpte block.  This is works fine in practice since we guarantee that
only a single folio is mapped by a contpte block, and the core-mm tracks
access/dirty information per folio.

In order for the public functions, which used to be pure inline, to
continue to be callable by modules, export all the contpte_* symbols that
are now called by those public inline functions.

The feature is enabled/disabled with the ARM64_CONTPTE Kconfig parameter
at build time.  It defaults to enabled as long as its dependency,
TRANSPARENT_HUGEPAGE is also enabled.  The core-mm depends upon
TRANSPARENT_HUGEPAGE to be able to allocate large folios, so if its not
enabled, then there is no chance of meeting the physical contiguity
requirement for contpte mappings.

Link: https://lkml.kernel.org/r/20240215103205.2607016-13-ryan.roberts@arm.com
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Morse <james.morse@arm.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 167 insertions, 0 deletions

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 7336d40a893a..831099cfc96b 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -134,6 +134,10 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
 #define pte_valid_not_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN))
 /*
+ * Returns true if the pte is valid and has the contiguous bit set.
+ */
+#define pte_valid_cont(pte)	(pte_valid(pte) && pte_cont(pte))
+/*
  * Could the pte be present in the TLB? We must check mm_tlb_flush_pending
  * so that we don't erroneously return false for pages that have been
  * remapped as PROT_NONE but are yet to be flushed from the TLB.
@@ -1128,6 +1132,167 @@ extern void ptep_modify_prot_commit(struct vm_area_struct *vma,
 				    unsigned long addr, pte_t *ptep,
 				    pte_t old_pte, pte_t new_pte);
 
+#ifdef CONFIG_ARM64_CONTPTE
+
+/*
+ * The contpte APIs are used to transparently manage the contiguous bit in ptes
+ * where it is possible and makes sense to do so. The PTE_CONT bit is considered
+ * a private implementation detail of the public ptep API (see below).
+ */
+extern void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte);
+extern pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte);
+extern pte_t contpte_ptep_get_lockless(pte_t *orig_ptep);
+extern void contpte_set_ptes(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte, unsigned int nr);
+extern int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
+				unsigned long addr, pte_t *ptep);
+extern int contpte_ptep_clear_flush_young(struct vm_area_struct *vma,
+				unsigned long addr, pte_t *ptep);
+extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
+				unsigned long addr, pte_t *ptep,
+				pte_t entry, int dirty);
+
+static inline void contpte_try_unfold(struct mm_struct *mm, unsigned long addr,
+					pte_t *ptep, pte_t pte)
+{
+	if (unlikely(pte_valid_cont(pte)))
+		__contpte_try_unfold(mm, addr, ptep, pte);
+}
+
+/*
+ * The below functions constitute the public API that arm64 presents to the
+ * core-mm to manipulate PTE entries within their page tables (or at least this
+ * is the subset of the API that arm64 needs to implement). These public
+ * versions will automatically and transparently apply the contiguous bit where
+ * it makes sense to do so. Therefore any users that are contig-aware (e.g.
+ * hugetlb, kernel mapper) should NOT use these APIs, but instead use the
+ * private versions, which are prefixed with double underscore. All of these
+ * APIs except for ptep_get_lockless() are expected to be called with the PTL
+ * held. Although the contiguous bit is considered private to the
+ * implementation, it is deliberately allowed to leak through the getters (e.g.
+ * ptep_get()), back to core code. This is required so that pte_leaf_size() can
+ * provide an accurate size for perf_get_pgtable_size(). But this leakage means
+ * its possible a pte will be passed to a setter with the contiguous bit set, so
+ * we explicitly clear the contiguous bit in those cases to prevent accidentally
+ * setting it in the pgtable.
+ */
+
+#define ptep_get ptep_get
+static inline pte_t ptep_get(pte_t *ptep)
+{
+	pte_t pte = __ptep_get(ptep);
+
+	if (likely(!pte_valid_cont(pte)))
+		return pte;
+
+	return contpte_ptep_get(ptep, pte);
+}
+
+#define ptep_get_lockless ptep_get_lockless
+static inline pte_t ptep_get_lockless(pte_t *ptep)
+{
+	pte_t pte = __ptep_get(ptep);
+
+	if (likely(!pte_valid_cont(pte)))
+		return pte;
+
+	return contpte_ptep_get_lockless(ptep);
+}
+
+static inline void set_pte(pte_t *ptep, pte_t pte)
+{
+	/*
+	 * We don't have the mm or vaddr so cannot unfold contig entries (since
+	 * it requires tlb maintenance). set_pte() is not used in core code, so
+	 * this should never even be called. Regardless do our best to service
+	 * any call and emit a warning if there is any attempt to set a pte on
+	 * top of an existing contig range.
+	 */
+	pte_t orig_pte = __ptep_get(ptep);
+
+	WARN_ON_ONCE(pte_valid_cont(orig_pte));
+	__set_pte(ptep, pte_mknoncont(pte));
+}
+
+#define set_ptes set_ptes
+static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte, unsigned int nr)
+{
+	pte = pte_mknoncont(pte);
+
+	if (likely(nr == 1)) {
+		contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
+		__set_ptes(mm, addr, ptep, pte, 1);
+	} else {
+		contpte_set_ptes(mm, addr, ptep, pte, nr);
+	}
+}
+
+static inline void pte_clear(struct mm_struct *mm,
+				unsigned long addr, pte_t *ptep)
+{
+	contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
+	__pte_clear(mm, addr, ptep);
+}
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+				unsigned long addr, pte_t *ptep)
+{
+	contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
+	return __ptep_get_and_clear(mm, addr, ptep);
+}
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+				unsigned long addr, pte_t *ptep)
+{
+	pte_t orig_pte = __ptep_get(ptep);
+
+	if (likely(!pte_valid_cont(orig_pte)))
+		return __ptep_test_and_clear_young(vma, addr, ptep);
+
+	return contpte_ptep_test_and_clear_young(vma, addr, ptep);
+}
+
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
+				unsigned long addr, pte_t *ptep)
+{
+	pte_t orig_pte = __ptep_get(ptep);
+
+	if (likely(!pte_valid_cont(orig_pte)))
+		return __ptep_clear_flush_young(vma, addr, ptep);
+
+	return contpte_ptep_clear_flush_young(vma, addr, ptep);
+}
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm,
+				unsigned long addr, pte_t *ptep)
+{
+	contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
+	__ptep_set_wrprotect(mm, addr, ptep);
+}
+
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+static inline int ptep_set_access_flags(struct vm_area_struct *vma,
+				unsigned long addr, pte_t *ptep,
+				pte_t entry, int dirty)
+{
+	pte_t orig_pte = __ptep_get(ptep);
+
+	entry = pte_mknoncont(entry);
+
+	if (likely(!pte_valid_cont(orig_pte)))
+		return __ptep_set_access_flags(vma, addr, ptep, entry, dirty);
+
+	return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty);
+}
+
+#else /* CONFIG_ARM64_CONTPTE */
+
 #define ptep_get				__ptep_get
 #define set_pte					__set_pte
 #define set_ptes				__set_ptes
@@ -1143,6 +1308,8 @@ extern void ptep_modify_prot_commit(struct vm_area_struct *vma,
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 #define ptep_set_access_flags			__ptep_set_access_flags
 
+#endif /* CONFIG_ARM64_CONTPTE */
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_PGTABLE_H */