[PATCH v6 23/24] x86/mm: Add speculative pagefault handling

[Laurent Dufour]

From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

Try a speculative fault before acquiring mmap_sem, if it returns with
VM_FAULT_RETRY continue with the mmap_sem acquisition and do the
traditional fault.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>

[Clearing of FAULT_FLAG_ALLOW_RETRY is now done in
 handle_speculative_fault()]
[Retry with usual fault path in the case VM_ERROR is returned by
 handle_speculative_fault(). This allows signal to be delivered]
[Don't build SPF call if !CONFIG_SPF]
[Try speculative fault path only for multi threaded processes]
[Try to the VMA fetch during the speculative path in case of retry]
Signed-off-by: Laurent Dufour <ldufour@xxxxxxxxxxxxxxxxxx>
---
 arch/x86/mm/fault.c | 38 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 37 insertions(+), 1 deletion(-)

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 06fe3d51d385..8db69a116521 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1242,6 +1242,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 		unsigned long address)
 {
 	struct vm_area_struct *vma;
+#ifdef CONFIG_SPF
+	struct vm_area_struct *spf_vma = NULL;
+#endif
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	int fault, major = 0;
@@ -1339,6 +1342,27 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	if (error_code & X86_PF_INSTR)
 		flags |= FAULT_FLAG_INSTRUCTION;
 
+#ifdef CONFIG_SPF
+	if ((error_code & X86_PF_USER) && (atomic_read(&mm->mm_users) > 1)) {
+		fault = handle_speculative_fault(mm, address, flags,
+						 &spf_vma);
+
+		if (!(fault & VM_FAULT_RETRY)) {
+			if (!(fault & VM_FAULT_ERROR)) {
+				perf_sw_event(PERF_COUNT_SW_SPF, 1,
+					      regs, address);
+				goto done;
+			}
+			/*
+			 * In case of error we need the pkey value, but
+			 * can't get it from the spf_vma as it is only returned
+			 * when VM_FAULT_RETRY is returned. So we have to
+			 * retry the page fault with the mmap_sem grabbed.
+			 */
+		}
+	}
+#endif /* CONFIG_SPF */
+
 	/*
 	 * When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in
@@ -1372,7 +1396,16 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 		might_sleep();
 	}
 
-	vma = find_vma(mm, address);
+#ifdef CONFIG_SPF
+	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)) {
 		bad_area(regs, error_code, address);
 		return;
@@ -1458,6 +1491,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 		return;
 	}
 
+#ifdef CONFIG_SPF
+done:
+#endif
 	/*
 	 * Major/minor page fault accounting. If any of the events
 	 * returned VM_FAULT_MAJOR, we account it as a major fault.
-- 
2.7.4