1 files changed, 66 insertions, 41 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 654be4ae3047..9ff85bb8dd69 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -20,6 +20,9 @@
 #include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
 #include <asm/fixmap.h>			/* VSYSCALL_START		*/
 
+#define CREATE_TRACE_POINTS
+#include <asm/trace/exceptions.h>
+
 /*
  * Page fault error code bits:
  *
@@ -51,7 +54,7 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr)
 	return 0;
 }
 
-static inline int __kprobes notify_page_fault(struct pt_regs *regs)
+static inline int __kprobes kprobes_fault(struct pt_regs *regs)
 {
 	int ret = 0;
 
@@ -596,7 +599,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code,
 
 	printk(KERN_CONT " at %p\n", (void *) address);
 	printk(KERN_ALERT "IP:");
-	printk_address(regs->ip, 1);
+	printk_address(regs->ip);
 
 	dump_pagetable(address);
 }
@@ -842,23 +845,15 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 	force_sig_info_fault(SIGBUS, code, address, tsk, fault);
 }
 
-static noinline int
+static noinline void
 mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	       unsigned long address, unsigned int fault)
 {
-	/*
-	 * Pagefault was interrupted by SIGKILL. We have no reason to
-	 * continue pagefault.
-	 */
-	if (fatal_signal_pending(current)) {
-		if (!(fault & VM_FAULT_RETRY))
-			up_read(&current->mm->mmap_sem);
-		if (!(error_code & PF_USER))
-			no_context(regs, error_code, address, 0, 0);
-		return 1;
+	if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
+		up_read(&current->mm->mmap_sem);
+		no_context(regs, error_code, address, 0, 0);
+		return;
 	}
-	if (!(fault & VM_FAULT_ERROR))
-		return 0;
 
 	if (fault & VM_FAULT_OOM) {
 		/* Kernel mode? Handle exceptions or die: */
@@ -866,7 +861,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 			up_read(&current->mm->mmap_sem);
 			no_context(regs, error_code, address,
 				   SIGSEGV, SEGV_MAPERR);
-			return 1;
+			return;
 		}
 
 		up_read(&current->mm->mmap_sem);
@@ -884,7 +879,6 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 		else
 			BUG();
 	}
-	return 1;
 }
 
 static int spurious_fault_check(unsigned long error_code, pte_t *pte)
@@ -1011,9 +1005,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	unsigned long address;
 	struct mm_struct *mm;
 	int fault;
-	int write = error_code & PF_WRITE;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-					(write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	tsk = current;
 	mm = tsk->mm;
@@ -1059,7 +1051,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 			return;
 
 		/* kprobes don't want to hook the spurious faults: */
-		if (notify_page_fault(regs))
+		if (kprobes_fault(regs))
 			return;
 		/*
 		 * Don't take the mm semaphore here. If we fixup a prefetch
@@ -1071,22 +1063,8 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	}
 
 	/* kprobes don't want to hook the spurious faults: */
-	if (unlikely(notify_page_fault(regs)))
+	if (unlikely(kprobes_fault(regs)))
 		return;
-	/*
-	 * It's safe to allow irq's after cr2 has been saved and the
-	 * vmalloc fault has been handled.
-	 *
-	 * User-mode registers count as a user access even for any
-	 * potential system fault or CPU buglet:
-	 */
-	if (user_mode_vm(regs)) {
-		local_irq_enable();
-		error_code |= PF_USER;
-	} else {
-		if (regs->flags & X86_EFLAGS_IF)
-			local_irq_enable();
-	}
 
 	if (unlikely(error_code & PF_RSVD))
 		pgtable_bad(regs, error_code, address);
@@ -1098,8 +1076,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 		}
 	}
 
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
-
 	/*
 	 * If we're in an interrupt, have no user context or are running
 	 * in an atomic region then we must not take the fault:
@@ -1110,6 +1086,27 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	}
 
 	/*
+	 * It's safe to allow irq's after cr2 has been saved and the
+	 * vmalloc fault has been handled.
+	 *
+	 * User-mode registers count as a user access even for any
+	 * potential system fault or CPU buglet:
+	 */
+	if (user_mode_vm(regs)) {
+		local_irq_enable();
+		error_code |= PF_USER;
+		flags |= FAULT_FLAG_USER;
+	} else {
+		if (regs->flags & X86_EFLAGS_IF)
+			local_irq_enable();
+	}
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
+	if (error_code & PF_WRITE)
+		flags |= FAULT_FLAG_WRITE;
+
+	/*
 	 * 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
@@ -1187,9 +1184,17 @@ good_area:
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);
 
-	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
-		if (mm_fault_error(regs, error_code, address, fault))
-			return;
+	/*
+	 * If we need to retry but a fatal signal is pending, handle the
+	 * signal first. We do not need to release the mmap_sem because it
+	 * would already be released in __lock_page_or_retry in mm/filemap.c.
+	 */
+	if (unlikely((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)))
+		return;
+
+	if (unlikely(fault & VM_FAULT_ERROR)) {
+		mm_fault_error(regs, error_code, address, fault);
+		return;
 	}
 
 	/*
@@ -1230,3 +1235,23 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	__do_page_fault(regs, error_code);
 	exception_exit(prev_state);
 }
+
+static void trace_page_fault_entries(struct pt_regs *regs,
+				     unsigned long error_code)
+{
+	if (user_mode(regs))
+		trace_page_fault_user(read_cr2(), regs, error_code);
+	else
+		trace_page_fault_kernel(read_cr2(), regs, error_code);
+}
+
+dotraplinkage void __kprobes
+trace_do_page_fault(struct pt_regs *regs, unsigned long error_code)
+{
+	enum ctx_state prev_state;
+
+	prev_state = exception_enter();
+	trace_page_fault_entries(regs, error_code);
+	__do_page_fault(regs, error_code);
+	exception_exit(prev_state);
+}