[PATCH v10 25/25] powerpc/mm: add speculative page fault

[Laurent Dufour <ldufour@linux.vnet.ibm.com>]

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.

Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
---
 arch/powerpc/mm/fault.c | 33 +++++++++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index c01d627e687a..37191147026e 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -464,6 +464,26 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (is_exec)
 		flags |= FAULT_FLAG_INSTRUCTION;
 
+	if (IS_ENABLED(CONFIG_SPECULATIVE_PAGE_FAULT)) {
+		fault = handle_speculative_fault(mm, address, flags, &vma);
+		/*
+		 * Page fault is done if VM_FAULT_RETRY is not returned.
+		 * But if the memory protection keys are active, we don't know
+		 * if the fault is due to key mistmatch or due to a
+		 * classic protection check.
+		 * To differentiate that, we will need the VMA we no
+		 * more have, so let's retry with the mmap_sem held.
+		 */
+		if (fault != VM_FAULT_RETRY &&
+		    (IS_ENABLED(CONFIG_PPC_MEM_KEYS) &&
+		     fault != VM_FAULT_SIGSEGV)) {
+			perf_sw_event(PERF_COUNT_SW_SPF, 1, regs, address);
+			goto done;
+		}
+	} else {
+		vma = NULL;
+	}
+
 	/* 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
@@ -494,7 +514,8 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 		might_sleep();
 	}
 
-	vma = find_vma(mm, address);
+	if (!vma || !can_reuse_spf_vma(vma, address))
+		vma = find_vma(mm, address);
 	if (unlikely(!vma))
 		return bad_area(regs, address);
 	if (likely(vma->vm_start <= address))
@@ -551,8 +572,15 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 			 */
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
-			if (!fatal_signal_pending(current))
+			if (!fatal_signal_pending(current)) {
+				/*
+				 * Do not try to reuse this vma and fetch it
+				 * again since we will release the mmap_sem.
+				 */
+				if (IS_ENABLED(CONFIG_SPECULATIVE_PAGE_FAULT))
+					vma = NULL;
 				goto retry;
+			}
 		}
 
 		/*
@@ -564,6 +592,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	up_read(&current->mm->mmap_sem);
 
+done:
 	if (unlikely(fault & VM_FAULT_ERROR))
 		return mm_fault_error(regs, address, fault);
 
-- 
2.7.4