[PATCH v3 19/20] 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]
Signed-off-by: Laurent Dufour <ldufour@xxxxxxxxxxxxxxxxxx>
---
 arch/x86/include/asm/pgtable_types.h |  7 +++++++
 arch/x86/mm/fault.c                  | 19 +++++++++++++++++++
 2 files changed, 26 insertions(+)

diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index f1492473f10e..aadc8ecb91fb 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -257,6 +257,13 @@ enum page_cache_mode {
 #define PGD_IDENT_ATTR	 0x001		/* PRESENT (no other attributes) */
 #endif
 
+/*
+ * Advertise that we call the Speculative Page Fault handler.
+ */
+#ifdef CONFIG_X86_64
+#define __HAVE_ARCH_CALL_SPF
+#endif
+
 #ifdef CONFIG_X86_32
 # include <asm/pgtable_32_types.h>
 #else
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index b836a7274e12..652af5524f42 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1365,6 +1365,24 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	if (error_code & PF_INSTR)
 		flags |= FAULT_FLAG_INSTRUCTION;
 
+#ifdef __HAVE_ARCH_CALL_SPF
+	if (error_code & PF_USER) {
+		fault = handle_speculative_fault(mm, address, flags);
+
+		/*
+		 * We also check against VM_FAULT_ERROR because we have to
+		 * raise a signal by calling later mm_fault_error() which
+		 * requires the vma pointer to be set. So in that case,
+		 * we fall through the normal path.
+		 */
+		if (!(fault & VM_FAULT_RETRY || fault & VM_FAULT_ERROR)) {
+			perf_sw_event(PERF_COUNT_SW_SPF, 1,
+				      regs, address);
+			goto done;
+		}
+	}
+#endif /* __HAVE_ARCH_CALL_SPF */
+
 	/*
 	 * When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in
@@ -1474,6 +1492,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 		return;
 	}
 
+done:
 	/*
 	 * Major/minor page fault accounting. If any of the events
 	 * returned VM_FAULT_MAJOR, we account it as a major fault.
-- 
2.7.4