[PATCH 2/2] mm/mprotect: do not flush on permission promotion

[Nadav Amit]

From: Nadav Amit <namit@xxxxxxxxxx>

Currently, using mprotect() to unprotect a memory region or uffd to
unprotect a memory region causes a TLB flush. At least on x86, as
protection is promoted, no TLB flush is needed.

Add an arch-specific pte_may_need_flush() which tells whether a TLB
flush is needed based on the old PTE and the new one. Implement an x86
pte_may_need_flush().

For x86, PTE protection promotion or changes of software bits does
require a flush, also add logic that considers the dirty-bit. Changes to
the access-bit do not trigger a TLB flush, although architecturally they
should, as Linux considers the access-bit as a hint.

Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
Cc: Nick Piggin <npiggin@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Signed-off-by: Nadav Amit <namit@xxxxxxxxxx>
---
 arch/x86/include/asm/tlbflush.h | 40 +++++++++++++++++++++++++++++++++
 include/asm-generic/tlb.h       |  4 ++++
 mm/mprotect.c                   |  3 ++-
 3 files changed, 46 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index b587a9ee9cb2..e74d13d174d1 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -259,6 +259,46 @@ static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
 
 extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
 
+/*
+ * pte_may_need_flush() checks whether a TLB flush is necessary according to x86
+ * architectural definition. Mere promotion of permissions does not require a
+ * TLB flush. Changes of software bits does not require a TLB flush. Demotion
+ * of the access-bit also does not trigger a TLB flush (although it is required
+ * architecturally) - see the comment in ptep_clear_flush_young().
+ *
+ * Further optimizations may be possible, such as avoiding a flush when clearing
+ * the write-bit on non-dirty entries. As those do not explicitly follow the
+ * specifications, they are not implemented (at least for now).
+ */
+static inline bool pte_may_need_flush(pte_t oldpte, pte_t newpte)
+{
+	const pteval_t ignore_mask = _PAGE_SOFTW1 | _PAGE_SOFTW2 |
+				     _PAGE_SOFTW3 | _PAGE_ACCESSED;
+	const pteval_t enable_mask = _PAGE_RW | _PAGE_DIRTY | _PAGE_GLOBAL;
+	pteval_t oldval = pte_val(oldpte);
+	pteval_t newval = pte_val(newpte);
+	pteval_t diff = oldval ^ newval;
+	pteval_t disable_mask = 0;
+
+	if (IS_ENABLED(CONFIG_X86_64) || IS_ENABLED(CONFIG_X86_PAE))
+		disable_mask = _PAGE_NX;
+
+	/* new is non-present: need only if old is present */
+	if (pte_none(newpte))
+		return !pte_none(oldpte);
+
+	/*
+	 * Any change of PFN and any flag other than those that we consider
+	 * requires a flush (e.g., PAT, protection keys). To save flushes we do
+	 * not consider the access bit as it is considered by the kernel as
+	 * best-effort.
+	 */
+	return diff & ((oldval & enable_mask) |
+		       (newval & disable_mask) |
+		       ~(enable_mask | disable_mask | ignore_mask));
+}
+#define pte_may_need_flush pte_may_need_flush
+
 #endif /* !MODULE */
 
 #endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 2c68a545ffa7..5ca49f44bc38 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -654,6 +654,10 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
 	} while (0)
 #endif
 
+#ifndef pte_may_need_flush
+static inline bool pte_may_need_flush(pte_t oldpte, pte_t newpte) { return true; }
+#endif
+
 #endif /* CONFIG_MMU */
 
 #endif /* _ASM_GENERIC__TLB_H */
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 075ff94aa51c..ae79df59a7a8 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -139,7 +139,8 @@ static unsigned long change_pte_range(struct mmu_gather *tlb,
 				ptent = pte_mkwrite(ptent);
 			}
 			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
-			tlb_flush_pte_range(tlb, addr, PAGE_SIZE);
+			if (pte_may_need_flush(oldpte, ptent))
+				tlb_flush_pte_range(tlb, addr, PAGE_SIZE);
 			pages++;
 		} else if (is_swap_pte(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
-- 
2.25.1