powerpc: Only enable TLE with PPC_FEATURE2_HTM_NOSC

Linux from 3.9 through 4.2 does not abort HTM transaction on syscalls,
instead it suspend and resume it when leaving the kernel.  The
side-effects of the syscall will always remain visible, even if the
transaction is aborted.  This is an issue when transaction is used along
with futex syscall, on pthread_cond_wait for instance, where the futex
call might succeed but the transaction is rolled back leading the
pthread_cond object in an inconsistent state.

Glibc used to prevent it by always aborting a transaction before issuing
a syscall.  Linux 4.2 also decided to abort active transaction in
syscalls which makes the glibc workaround superfluous.  Worse, glibc
transaction abortion leads to a performance issue on recent kernels
where the HTM state is saved/restore lazily (v4.9).  By aborting a
transaction on every syscalls, regardless whether a transaction has being
initiated before, GLIBS makes the kernel always save/restore HTM state
(it can not even lazily disable it after a certain number of syscall
iterations).

Because of this shortcoming, Transactional Lock Elision is just enabled
when it has been explicitly set (either by tunables of by a configure
switch) and if kernel aborts HTM transactions on syscalls
(PPC_FEATURE2_HTM_NOSC).  It is reported that using simple benchmark [1],
the context-switch is about 5% faster by not issuing a tabort in every
syscall in newer kernels.

Checked on powerpc64le-linux-gnu with 4.4.0 kernel (Ubuntu 16.04).

	* NEWS: Add note about new TLE support on powerpc64le.
	* sysdeps/powerpc/nptl/tcb-offsets.sym (TM_CAPABLE): Remove.
	* sysdeps/powerpc/nptl/tls.h (tcbhead_t): Rename tm_capable to
	__ununsed1.
	(TLS_INIT_TP, TLS_DEFINE_INIT_TP): Remove tm_capable setup.
	(THREAD_GET_TM_CAPABLE, THREAD_SET_TM_CAPABLE): Remove macros.
	* sysdeps/powerpc/powerpc32/sysdep.h,
	sysdeps/powerpc/powerpc64/sysdep.h (ABORT_TRANSACTION_IMPL,
	ABORT_TRANSACTION): Remove macros.
	* sysdeps/powerpc/sysdep.h (ABORT_TRANSACTION): Likewise.
	* sysdeps/unix/sysv/linux/powerpc/elision-conf.c (elision_init): Set
	__pthread_force_elision iff PPC_FEATURE2_HTM_NOSC is set.
	* sysdeps/unix/sysv/linux/powerpc/powerpc32/sysdep.h,
	sysdeps/unix/sysv/linux/powerpc/powerpc64/sysdep.h
	sysdeps/unix/sysv/linux/powerpc/syscall.S (ABORT_TRANSACTION): Remove
	usage.
	* sysdeps/unix/sysv/linux/powerpc/not-errno.h: Remove file.

Reported-by: Breno Leitão <leitao@debian.org>

2 files changed, 1 insertions, 13 deletions

diff --git a/sysdeps/powerpc/nptl/tcb-offsets.sym b/sysdeps/powerpc/nptl/tcb-offsets.sym
index e5bb2b3..4c01615 100644
--- a/sysdeps/powerpc/nptl/tcb-offsets.sym
+++ b/sysdeps/powerpc/nptl/tcb-offsets.sym
@@ -21,7 +21,6 @@ DSO_SLOT2			(offsetof (tcbhead_t, dso_slot2) - TLS_TCB_OFFSET - sizeof (tcbhead_
 #ifdef __powerpc64__
 TCB_AT_PLATFORM			(offsetof (tcbhead_t, at_platform) - TLS_TCB_OFFSET - sizeof(tcbhead_t))
 #endif
-TM_CAPABLE			(offsetof (tcbhead_t, tm_capable) - TLS_TCB_OFFSET - sizeof (tcbhead_t))
 #ifndef __powerpc64__
 TCB_AT_PLATFORM			(offsetof (tcbhead_t, at_platform) - TLS_TCB_OFFSET - sizeof(tcbhead_t))
 PADDING				(offsetof (tcbhead_t, padding) - TLS_TCB_OFFSET - sizeof(tcbhead_t))
diff --git a/sysdeps/powerpc/nptl/tls.h b/sysdeps/powerpc/nptl/tls.h
index f88fed5..8317ca7 100644
--- a/sysdeps/powerpc/nptl/tls.h
+++ b/sysdeps/powerpc/nptl/tls.h
@@ -67,8 +67,7 @@ typedef struct
   uint32_t padding;
   uint32_t at_platform;
 #endif
-  /* Indicate if HTM capable (ISA 2.07).  */
-  uint32_t tm_capable;
+  uint32_t __unused;
   /* Reservation for AT_PLATFORM data - powerpc64.  */
 #ifdef __powerpc64__
   uint32_t at_platform;
@@ -142,7 +141,6 @@ register void *__thread_register __asm__ ("r13");
 # define TLS_INIT_TP(tcbp) \
   ({ 									      \
     __thread_register = (void *) (tcbp) + TLS_TCB_OFFSET;		      \
-    THREAD_SET_TM_CAPABLE (__tcb_hwcap & PPC_FEATURE2_HAS_HTM ? 1 : 0);	      \
     THREAD_SET_HWCAP (__tcb_hwcap);					      \
     THREAD_SET_AT_PLATFORM (__tcb_platform);				      \
     NULL;								      \
@@ -151,8 +149,6 @@ register void *__thread_register __asm__ ("r13");
 /* Value passed to 'clone' for initialization of the thread register.  */
 # define TLS_DEFINE_INIT_TP(tp, pd) \
     void *tp = (void *) (pd) + TLS_TCB_OFFSET + TLS_PRE_TCB_SIZE;	      \
-    (((tcbhead_t *) ((char *) tp - TLS_TCB_OFFSET))[-1].tm_capable) =	      \
-      THREAD_GET_TM_CAPABLE ();						      \
     (((tcbhead_t *) ((char *) tp - TLS_TCB_OFFSET))[-1].hwcap) =	      \
       THREAD_GET_HWCAP ();						      \
     (((tcbhead_t *) ((char *) tp - TLS_TCB_OFFSET))[-1].at_platform) =	      \
@@ -210,13 +206,6 @@ register void *__thread_register __asm__ ("r13");
 		     + TLS_PRE_TCB_SIZE))[-1].pointer_guard		      \
      = THREAD_GET_POINTER_GUARD())
 
-/* tm_capable field in TCB head.  */
-# define THREAD_GET_TM_CAPABLE() \
-    (((tcbhead_t *) ((char *) __thread_register				      \
-		     - TLS_TCB_OFFSET))[-1].tm_capable)
-# define THREAD_SET_TM_CAPABLE(value) \
-    (THREAD_GET_TM_CAPABLE () = (value))
-
 /* hwcap field in TCB head.  */
 # define THREAD_GET_HWCAP() \
     (((tcbhead_t *) ((char *) __thread_register				      \