ARM: 9328/1: mm: try VMA lock-based page fault handling first

Attempt VMA lock-based page fault handling first, and fall back to the
existing mmap_lock-based handling if that fails, the ebizzy benchmark
shows 25% improvement on qemu with 2 cpus.
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>

arch/arm/Kconfig

@@ -35,6 +35,7 @@ config ARM
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_HUGETLBFS if ARM_LPAE
+	select ARCH_SUPPORTS_PER_VMA_LOCK
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_MEMTEST

arch/arm/mm/fault.c

@@ -278,6 +278,35 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 
+	if (!(flags & FAULT_FLAG_USER))
+		goto lock_mmap;
+
+	vma = lock_vma_under_rcu(mm, addr);
+	if (!vma)
+		goto lock_mmap;
+
+	if (!(vma->vm_flags & vm_flags)) {
+		vma_end_read(vma);
+		goto lock_mmap;
+	}
+	fault = handle_mm_fault(vma, addr, flags | FAULT_FLAG_VMA_LOCK, regs);
+	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+		vma_end_read(vma);
+
+	if (!(fault & VM_FAULT_RETRY)) {
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		goto done;
+	}
+	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+
+	/* Quick path to respond to signals */
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			goto no_context;
+		return 0;
+	}
+lock_mmap:
+
 retry:
 	vma = lock_mm_and_find_vma(mm, addr, regs);
 	if (unlikely(!vma)) {
@@ -316,6 +345,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	}
 
 	mmap_read_unlock(mm);
+done:
 
 	/*
 	 * Handle the "normal" case first - VM_FAULT_MAJOR