perf/x86: Further optimize copy_from_user_nmi()

Now that we can deal with nested NMI due to IRET re-enabling NMIs and
can deal with faults from NMI by making sure we preserve CR2 over NMIs
we can in fact simply access user-space memory from NMI context.

So rewrite copy_from_user_nmi() to use __copy_from_user_inatomic() and
rework the fault path to do the minimal required work before taking
the in_atomic() fault handler.

In particular avoid perf_sw_event() which would make perf recurse on
itself (it should be harmless as our recursion protections should be
able to deal with this -- but why tempt fate).

Also rename notify_page_fault() to kprobes_fault() as that is a much
better name; there is no notifier in it and its specific to kprobes.

Don measured that his worst case NMI path shrunk from ~300K cycles to
~150K cycles.

Cc: Stephane Eranian <eranian@google.com>
Cc: jmario@redhat.com
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: dave.hansen@linux.intel.com
Tested-by: Don Zickus <dzickus@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131024105206.GM2490@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 3aaeffc..7a517bb 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -51,7 +51,7 @@
 	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;
 
@@ -1048,7 +1048,7 @@
 			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
@@ -1060,8 +1060,28 @@
 	}
 
 	/* kprobes don't want to hook the spurious faults: */
-	if (unlikely(notify_page_fault(regs)))
+	if (unlikely(kprobes_fault(regs)))
 		return;
+
+	if (unlikely(error_code & PF_RSVD))
+		pgtable_bad(regs, error_code, address);
+
+	if (static_cpu_has(X86_FEATURE_SMAP)) {
+		if (unlikely(smap_violation(error_code, regs))) {
+			bad_area_nosemaphore(regs, error_code, address);
+			return;
+		}
+	}
+
+	/*
+	 * If we're in an interrupt, have no user context or are running
+	 * in an atomic region then we must not take the fault:
+	 */
+	if (unlikely(in_atomic() || !mm)) {
+		bad_area_nosemaphore(regs, error_code, address);
+		return;
+	}
+
 	/*
 	 * It's safe to allow irq's after cr2 has been saved and the
 	 * vmalloc fault has been handled.
@@ -1078,27 +1098,8 @@
 			local_irq_enable();
 	}
 
-	if (unlikely(error_code & PF_RSVD))
-		pgtable_bad(regs, error_code, address);
-
-	if (static_cpu_has(X86_FEATURE_SMAP)) {
-		if (unlikely(smap_violation(error_code, regs))) {
-			bad_area_nosemaphore(regs, error_code, address);
-			return;
-		}
-	}
-
 	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:
-	 */
-	if (unlikely(in_atomic() || !mm)) {
-		bad_area_nosemaphore(regs, error_code, address);
-		return;
-	}
-
 	if (error_code & PF_WRITE)
 		flags |= FAULT_FLAG_WRITE;