mm: add PTE pointer parameter to flush_tlb_fix_spurious_fault()

s390 can do more fine-grained handling of spurious TLB protection faults,
when there also is the PTE pointer available.

Therefore, pass on the PTE pointer to flush_tlb_fix_spurious_fault() as an
additional parameter.

This will add no functional change to other architectures, but those with
private flush_tlb_fix_spurious_fault() implementations need to be made
aware of the new parameter.

Link: https://lkml.kernel.org/r/20230306161548.661740-1-gerald.schaefer@linux.ibm.comSigned-off-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>	[arm64]
Acked-by: Michael Ellerman <mpe@ellerman.id.au>		[powerpc]
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

arch/arm64/include/asm/pgtable.h

@@ -57,7 +57,7 @@ static inline bool arch_thp_swp_supported(void)
  * fault on one CPU which has been handled concurrently by another CPU
  * does not need to perform additional invalidation.
  */
-#define flush_tlb_fix_spurious_fault(vma, address) do { } while (0)
+#define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0)
 
 /*
  * ZERO_PAGE is a global shared page that is always zero: used

arch/mips/include/asm/pgtable.h

@@ -469,7 +469,8 @@ static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
 }
 
 static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma,
-						unsigned long address)
+						unsigned long address,
+						pte_t *ptep)
 {
 }
 

arch/powerpc/include/asm/book3s/64/tlbflush.h

@@ -121,7 +121,8 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 
 #define flush_tlb_fix_spurious_fault flush_tlb_fix_spurious_fault
 static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma,
-						unsigned long address)
+						unsigned long address,
+						pte_t *ptep)
 {
 	/*
 	 * Book3S 64 does not require spurious fault flushes because the PTE

arch/s390/include/asm/pgtable.h

@@ -1239,7 +1239,8 @@ static inline int pte_allow_rdp(pte_t old, pte_t new)
 }
 
 static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma,
-						unsigned long address)
+						unsigned long address,
+						pte_t *ptep)
 {
 	/*
 	 * RDP might not have propagated the PTE protection reset to all CPUs,
@@ -1247,11 +1248,12 @@ static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma,
 	 * NOTE: This will also be called when a racing pagetable update on
 	 * another thread already installed the correct PTE. Both cases cannot
 	 * really be distinguished.
-	 * Therefore, only do the local TLB flush when RDP can be used, to avoid
-	 * unnecessary overhead.
+	 * Therefore, only do the local TLB flush when RDP can be used, and the
+	 * PTE does not have _PAGE_PROTECT set, to avoid unnecessary overhead.
+	 * A local RDP can be used to do the flush.
 	 */
-	if (MACHINE_HAS_RDP)
-		asm volatile("ptlb" : : : "memory");
+	if (MACHINE_HAS_RDP && !(pte_val(*ptep) & _PAGE_PROTECT))
+		__ptep_rdp(address, ptep, 0, 0, 1);
 }
 #define flush_tlb_fix_spurious_fault flush_tlb_fix_spurious_fault
 

arch/x86/include/asm/pgtable.h

@@ -1097,7 +1097,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
 	clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
 }
 
-#define flush_tlb_fix_spurious_fault(vma, address) do { } while (0)
+#define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0)
 
 #define mk_pmd(page, pgprot)   pfn_pmd(page_to_pfn(page), (pgprot))
 

include/linux/pgtable.h

@@ -817,7 +817,7 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
 #endif
 
 #ifndef flush_tlb_fix_spurious_fault
-#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
+#define flush_tlb_fix_spurious_fault(vma, address, ptep) flush_tlb_page(vma, address)
 #endif
 
 /*

mm/memory.c

@@ -4944,7 +4944,8 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 		 * with threads.
 		 */
 		if (vmf->flags & FAULT_FLAG_WRITE)
-			flush_tlb_fix_spurious_fault(vmf->vma, vmf->address);
+			flush_tlb_fix_spurious_fault(vmf->vma, vmf->address,
+						     vmf->pte);
 	}
 unlock:
 	pte_unmap_unlock(vmf->pte, vmf->ptl);

mm/pgtable-generic.c

@@ -69,7 +69,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	int changed = !pte_same(*ptep, entry);
 	if (changed) {
 		set_pte_at(vma->vm_mm, address, ptep, entry);
-		flush_tlb_fix_spurious_fault(vma, address);
+		flush_tlb_fix_spurious_fault(vma, address, ptep);
 	}
 	return changed;
 }