[RFC][PATCH 7/8] mm,x86: speculative pagefault support

[Peter Zijlstra]

Implement the x86 architecture support for speculative pagefaults.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
---
 arch/x86/mm/fault.c |   31 +++++++++++--------------------
 arch/x86/mm/gup.c   |   10 ++++++++++
 2 files changed, 21 insertions(+), 20 deletions(-)

Index: linux-2.6/arch/x86/mm/fault.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/fault.c
+++ linux-2.6/arch/x86/mm/fault.c
@@ -777,30 +777,13 @@ bad_area_access_error(struct pt_regs *re
 	__bad_area(regs, error_code, address, SEGV_ACCERR);
 }
 
-/* TODO: fixup for "mm-invoke-oom-killer-from-page-fault.patch" */
-static void
-out_of_memory(struct pt_regs *regs, unsigned long error_code,
-	      unsigned long address)
-{
-	/*
-	 * We ran out of memory, call the OOM killer, and return the userspace
-	 * (which will retry the fault, or kill us if we got oom-killed):
-	 */
-	up_read(&current->mm->mmap_sem);
-
-	pagefault_out_of_memory();
-}
-
 static void
 do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 	  unsigned int fault)
 {
 	struct task_struct *tsk = current;
-	struct mm_struct *mm = tsk->mm;
 	int code = BUS_ADRERR;
 
-	up_read(&mm->mmap_sem);
-
 	/* Kernel mode? Handle exceptions or die: */
 	if (!(error_code & PF_USER))
 		no_context(regs, error_code, address);
@@ -829,7 +812,7 @@ mm_fault_error(struct pt_regs *regs, uns
 	       unsigned long address, unsigned int fault)
 {
 	if (fault & VM_FAULT_OOM) {
-		out_of_memory(regs, error_code, address);
+		pagefault_out_of_memory();
 	} else {
 		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON))
 			do_sigbus(regs, error_code, address, fault);
@@ -1040,6 +1023,14 @@ do_page_fault(struct pt_regs *regs, unsi
 		return;
 	}
 
+	if (error_code & PF_USER) {
+		fault = handle_speculative_fault(mm, address,
+				error_code & PF_WRITE ? FAULT_FLAG_WRITE : 0);
+
+		if (!(fault & VM_FAULT_RETRY))
+			goto done;
+	}
+
 	/*
 	 * When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in
@@ -1119,6 +1110,8 @@ good_area:
 	 */
 	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
 
+	up_read(&mm->mmap_sem);
+done:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		mm_fault_error(regs, error_code, address, fault);
 		return;
@@ -1135,6 +1128,4 @@ good_area:
 	}
 
 	check_v8086_mode(regs, address, tsk);
-
-	up_read(&mm->mmap_sem);
 }
Index: linux-2.6/arch/x86/mm/gup.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/gup.c
+++ linux-2.6/arch/x86/mm/gup.c
@@ -373,3 +373,13 @@ slow_irqon:
 		return ret;
 	}
 }
+
+void pin_page_tables(void)
+{
+	local_irq_disable();
+}
+
+void unpin_page_tables(void)
+{
+	local_irq_enable();
+}

-- 

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/