[PATCH v7 24/24] powerpc/mm: Add speculative page fault

[Laurent Dufour]

This patch enable the speculative page fault on the PowerPC
architecture.

This will try a speculative page fault without holding the mmap_sem,
if it returns with VM_FAULT_RETRY, the mmap_sem is acquired and the
traditional page fault processing is done.

The speculative path is only tried for multithreaded process as there is no
risk of contention on the mmap_sem otherwise.

Build on if CONFIG_SPECULATIVE_PAGE_FAULT is defined (currently for
BOOK3S_64 && SMP).

Signed-off-by: Laurent Dufour <lduf...@linux.vnet.ibm.com>
---
 arch/powerpc/mm/fault.c | 31 ++++++++++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 866446cf2d9a..104f3cc86b51 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -392,6 +392,9 @@ static int __do_page_fault(struct pt_regs *regs, unsigned 
long address,
                           unsigned long error_code)
 {
        struct vm_area_struct * vma;
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+       struct vm_area_struct *spf_vma = NULL;
+#endif
        struct mm_struct *mm = current->mm;
        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
        int is_exec = TRAP(regs) == 0x400;
@@ -459,6 +462,20 @@ static int __do_page_fault(struct pt_regs *regs, unsigned 
long address,
        if (is_exec)
                flags |= FAULT_FLAG_INSTRUCTION;
 
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+       if (is_user && (atomic_read(&mm->mm_users) > 1)) {
+               /* let's try a speculative page fault without grabbing the
+                * mmap_sem.
+                */
+               fault = handle_speculative_fault(mm, address, flags, &spf_vma);
+               if (!(fault & VM_FAULT_RETRY)) {
+                       perf_sw_event(PERF_COUNT_SW_SPF, 1,
+                                     regs, address);
+                       goto done;
+               }
+       }
+#endif /* CONFIG_SPECULATIVE_PAGE_FAULT */
+
        /* When running in the kernel we expect faults to occur only to
         * addresses in user space.  All other faults represent errors in the
         * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -489,7 +506,16 @@ static int __do_page_fault(struct pt_regs *regs, unsigned 
long address,
                might_sleep();
        }
 
-       vma = find_vma(mm, address);
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+       if (spf_vma) {
+               if (can_reuse_spf_vma(spf_vma, address))
+                       vma = spf_vma;
+               else
+                       vma =  find_vma(mm, address);
+               spf_vma = NULL;
+       } else
+#endif
+               vma = find_vma(mm, address);
        if (unlikely(!vma))
                return bad_area(regs, address);
        if (likely(vma->vm_start <= address))
@@ -568,6 +594,9 @@ static int __do_page_fault(struct pt_regs *regs, unsigned 
long address,
 
        up_read(&current->mm->mmap_sem);
 
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+done:
+#endif
        if (unlikely(fault & VM_FAULT_ERROR))
                return mm_fault_error(regs, address, fault);
 
-- 
2.7.4