Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - Add 'cross-release' support to lockdep, which allows APIs like
   completions, where it's not the 'owner' who releases the lock, to be
   tracked. It's all activated automatically under
   CONFIG_PROVE_LOCKING=y.

 - Clean up (restructure) the x86 atomics op implementation to be more
   readable, in preparation of KASAN annotations. (Dmitry Vyukov)

 - Fix static keys (Paolo Bonzini)

 - Add killable versions of down_read() et al (Kirill Tkhai)

 - Rework and fix jump_label locking (Marc Zyngier, Paolo Bonzini)

 - Rework (and fix) tlb_flush_pending() barriers (Peter Zijlstra)

 - Remove smp_mb__before_spinlock() and convert its usages, introduce
   smp_mb__after_spinlock() (Peter Zijlstra)

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (56 commits)
  locking/lockdep/selftests: Fix mixed read-write ABBA tests
  sched/completion: Avoid unnecessary stack allocation for COMPLETION_INITIALIZER_ONSTACK()
  acpi/nfit: Fix COMPLETION_INITIALIZER_ONSTACK() abuse
  locking/pvqspinlock: Relax cmpxchg's to improve performance on some architectures
  smp: Avoid using two cache lines for struct call_single_data
  locking/lockdep: Untangle xhlock history save/restore from task independence
  locking/refcounts, x86/asm: Disable CONFIG_ARCH_HAS_REFCOUNT for the time being
  futex: Remove duplicated code and fix undefined behaviour
  Documentation/locking/atomic: Finish the document...
  locking/lockdep: Fix workqueue crossrelease annotation
  workqueue/lockdep: 'Fix' flush_work() annotation
  locking/lockdep/selftests: Add mixed read-write ABBA tests
  mm, locking/barriers: Clarify tlb_flush_pending() barriers
  locking/lockdep: Make CONFIG_LOCKDEP_CROSSRELEASE and CONFIG_LOCKDEP_COMPLETIONS truly non-interactive
  locking/lockdep: Explicitly initialize wq_barrier::done::map
  locking/lockdep: Rename CONFIG_LOCKDEP_COMPLETE to CONFIG_LOCKDEP_COMPLETIONS
  locking/lockdep: Reword title of LOCKDEP_CROSSRELEASE config
  locking/lockdep: Make CONFIG_LOCKDEP_CROSSRELEASE part of CONFIG_PROVE_LOCKING
  locking/refcounts, x86/asm: Implement fast refcount overflow protection
  locking/lockdep: Fix the rollback and overwrite detection logic in crossrelease
  ...

1 files changed, 109 insertions, 0 deletions

diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
new file mode 100644
index 000000000000..ff871210b9f2
--- /dev/null
+++ b/arch/x86/include/asm/refcount.h
@@ -0,0 +1,109 @@
+#ifndef __ASM_X86_REFCOUNT_H
+#define __ASM_X86_REFCOUNT_H
+/*
+ * x86-specific implementation of refcount_t. Based on PAX_REFCOUNT from
+ * PaX/grsecurity.
+ */
+#include <linux/refcount.h>
+
+/*
+ * This is the first portion of the refcount error handling, which lives in
+ * .text.unlikely, and is jumped to from the CPU flag check (in the
+ * following macros). This saves the refcount value location into CX for
+ * the exception handler to use (in mm/extable.c), and then triggers the
+ * central refcount exception. The fixup address for the exception points
+ * back to the regular execution flow in .text.
+ */
+#define _REFCOUNT_EXCEPTION				\
+	".pushsection .text.unlikely\n"			\
+	"111:\tlea %[counter], %%" _ASM_CX "\n"		\
+	"112:\t" ASM_UD0 "\n"				\
+	ASM_UNREACHABLE					\
+	".popsection\n"					\
+	"113:\n"					\
+	_ASM_EXTABLE_REFCOUNT(112b, 113b)
+
+/* Trigger refcount exception if refcount result is negative. */
+#define REFCOUNT_CHECK_LT_ZERO				\
+	"js 111f\n\t"					\
+	_REFCOUNT_EXCEPTION
+
+/* Trigger refcount exception if refcount result is zero or negative. */
+#define REFCOUNT_CHECK_LE_ZERO				\
+	"jz 111f\n\t"					\
+	REFCOUNT_CHECK_LT_ZERO
+
+/* Trigger refcount exception unconditionally. */
+#define REFCOUNT_ERROR					\
+	"jmp 111f\n\t"					\
+	_REFCOUNT_EXCEPTION
+
+static __always_inline void refcount_add(unsigned int i, refcount_t *r)
+{
+	asm volatile(LOCK_PREFIX "addl %1,%0\n\t"
+		REFCOUNT_CHECK_LT_ZERO
+		: [counter] "+m" (r->refs.counter)
+		: "ir" (i)
+		: "cc", "cx");
+}
+
+static __always_inline void refcount_inc(refcount_t *r)
+{
+	asm volatile(LOCK_PREFIX "incl %0\n\t"
+		REFCOUNT_CHECK_LT_ZERO
+		: [counter] "+m" (r->refs.counter)
+		: : "cc", "cx");
+}
+
+static __always_inline void refcount_dec(refcount_t *r)
+{
+	asm volatile(LOCK_PREFIX "decl %0\n\t"
+		REFCOUNT_CHECK_LE_ZERO
+		: [counter] "+m" (r->refs.counter)
+		: : "cc", "cx");
+}
+
+static __always_inline __must_check
+bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+{
+	GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO,
+				  r->refs.counter, "er", i, "%0", e);
+}
+
+static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r)
+{
+	GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO,
+				 r->refs.counter, "%0", e);
+}
+
+static __always_inline __must_check
+bool refcount_add_not_zero(unsigned int i, refcount_t *r)
+{
+	int c, result;
+
+	c = atomic_read(&(r->refs));
+	do {
+		if (unlikely(c == 0))
+			return false;
+
+		result = c + i;
+
+		/* Did we try to increment from/to an undesirable state? */
+		if (unlikely(c < 0 || c == INT_MAX || result < c)) {
+			asm volatile(REFCOUNT_ERROR
+				     : : [counter] "m" (r->refs.counter)
+				     : "cc", "cx");
+			break;
+		}
+
+	} while (!atomic_try_cmpxchg(&(r->refs), &c, result));
+
+	return c != 0;
+}
+
+static __always_inline __must_check bool refcount_inc_not_zero(refcount_t *r)
+{
+	return refcount_add_not_zero(1, r);
+}
+
+#endif