[PATCH v2 20/20] 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 WM_FAULT_RETRY, the mmap_sem is acquired and the
traditional page fault processing is done.

Support is only provide for BOOK3S_64 currently because:
- require CONFIG_PPC_STD_MMU because checks done in
  set_access_flags_filter()
- require BOOK3S because we can't support for book3e_hugetlb_preload()
  called by update_mmu_cache()

Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/pgtable.h |  5 +++++
 arch/powerpc/mm/fault.c                      | 30 +++++++++++++++++++++++++++-
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 818a58fc3f4f..897f8b9f67e6 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -313,6 +313,11 @@ extern unsigned long pci_io_base;
 /* Advertise support for _PAGE_SPECIAL */
 #define __HAVE_ARCH_PTE_SPECIAL
 
+/* Advertise that we call the Speculative Page Fault handler */
+#if defined(CONFIG_PPC_BOOK3S_64)
+#define __HAVE_ARCH_CALL_SPF
+#endif
+
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 4c422632047b..7b3cc4c30eab 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -291,9 +291,36 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (is_write && is_user)
 		store_update_sp = store_updates_sp(regs);
 
-	if (is_user)
+	if (is_user) {
 		flags |= FAULT_FLAG_USER;
 
+#if defined(__HAVE_ARCH_CALL_SPF)
+		/* let's try a speculative page fault without grabbing the
+		 * mmap_sem.
+		 */
+
+		/*
+		 * flags is set later based on the VMA's flags, for the common
+		 * speculative service, we need some flags to be set.
+		 */
+		if (is_write)
+			flags |= FAULT_FLAG_WRITE;
+
+		fault = handle_speculative_fault(mm, address, flags);
+		if (!(fault & VM_FAULT_RETRY || fault & VM_FAULT_ERROR)) {
+			perf_sw_event(PERF_COUNT_SW_SPF_DONE, 1,
+				      regs, address);
+			goto done;
+		}
+
+		/*
+		 * Resetting flags since the following code assumes
+		 * FAULT_FLAG_WRITE is not set.
+		 */
+		flags &= ~FAULT_FLAG_WRITE;
+#endif /* defined(__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 the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -479,6 +506,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 			rc = 0;
 	}
 
+done:
 	/*
 	 * Major/minor page fault accounting.
 	 */
-- 
2.7.4