Merge tag 'tif-task_work.arch-2020-12-14' of git://git.kernel.dk/linux-block

Pull TIF_NOTIFY_SIGNAL updates from Jens Axboe:
 "This sits on top of of the core entry/exit and x86 entry branch from
  the tip tree, which contains the generic and x86 parts of this work.

  Here we convert the rest of the archs to support TIF_NOTIFY_SIGNAL.

  With that done, we can get rid of JOBCTL_TASK_WORK from task_work and
  signal.c, and also remove a deadlock work-around in io_uring around
  knowing that signal based task_work waking is invoked with the sighand
  wait queue head lock.

  The motivation for this work is to decouple signal notify based
  task_work, of which io_uring is a heavy user of, from sighand. The
  sighand lock becomes a huge contention point, particularly for
  threaded workloads where it's shared between threads. Even outside of
  threaded applications it's slower than it needs to be.

  Roman Gershman <romger@amazon.com> reported that his networked
  workload dropped from 1.6M QPS at 80% CPU to 1.0M QPS at 100% CPU
  after io_uring was changed to use TIF_NOTIFY_SIGNAL. The time was all
  spent hammering on the sighand lock, showing 57% of the CPU time there
  [1].

  There are further cleanups possible on top of this. One example is
  TIF_PATCH_PENDING, where a patch already exists to use
  TIF_NOTIFY_SIGNAL instead. Hopefully this will also lead to more
  consolidation, but the work stands on its own as well"

[1] https://github.com/axboe/liburing/issues/215

* tag 'tif-task_work.arch-2020-12-14' of git://git.kernel.dk/linux-block: (28 commits)
  io_uring: remove 'twa_signal_ok' deadlock work-around
  kernel: remove checking for TIF_NOTIFY_SIGNAL
  signal: kill JOBCTL_TASK_WORK
  io_uring: JOBCTL_TASK_WORK is no longer used by task_work
  task_work: remove legacy TWA_SIGNAL path
  sparc: add support for TIF_NOTIFY_SIGNAL
  riscv: add support for TIF_NOTIFY_SIGNAL
  nds32: add support for TIF_NOTIFY_SIGNAL
  ia64: add support for TIF_NOTIFY_SIGNAL
  h8300: add support for TIF_NOTIFY_SIGNAL
  c6x: add support for TIF_NOTIFY_SIGNAL
  alpha: add support for TIF_NOTIFY_SIGNAL
  xtensa: add support for TIF_NOTIFY_SIGNAL
  arm: add support for TIF_NOTIFY_SIGNAL
  microblaze: add support for TIF_NOTIFY_SIGNAL
  hexagon: add support for TIF_NOTIFY_SIGNAL
  csky: add support for TIF_NOTIFY_SIGNAL
  openrisc: add support for TIF_NOTIFY_SIGNAL
  sh: add support for TIF_NOTIFY_SIGNAL
  um: add support for TIF_NOTIFY_SIGNAL
  ...

2 files changed, 7 insertions, 6 deletions

diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 8bb9ebb71c4b..1f4659203f8c 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -52,7 +52,8 @@ STACK_SIZE  = 1 << STACK_SHIFT
 STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE
 
 _TIF_WORK	= (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
-		   _TIF_UPROBE | _TIF_GUARDED_STORAGE | _TIF_PATCH_PENDING)
+		   _TIF_UPROBE | _TIF_GUARDED_STORAGE | _TIF_PATCH_PENDING | \
+		   _TIF_NOTIFY_SIGNAL)
 _TIF_TRACE	= (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 		   _TIF_SYSCALL_TRACEPOINT)
 _CIF_WORK	= (_CIF_FPU)
@@ -486,8 +487,8 @@ ENTRY(system_call)
 #endif
 	TSTMSK	__PT_FLAGS(%r11),_PIF_SYSCALL_RESTART
 	jo	.Lsysc_syscall_restart
-	TSTMSK	__TI_flags(%r12),_TIF_SIGPENDING
-	jo	.Lsysc_sigpending
+	TSTMSK	__TI_flags(%r12),(_TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL)
+	jnz	.Lsysc_sigpending
 	TSTMSK	__TI_flags(%r12),_TIF_NOTIFY_RESUME
 	jo	.Lsysc_notify_resume
 	j	.Lsysc_return
@@ -865,8 +866,8 @@ ENTRY(io_int_handler)
 	TSTMSK	__TI_flags(%r12),_TIF_PATCH_PENDING
 	jo	.Lio_patch_pending
 #endif
-	TSTMSK	__TI_flags(%r12),_TIF_SIGPENDING
-	jo	.Lio_sigpending
+	TSTMSK	__TI_flags(%r12),(_TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL)
+	jnz	.Lio_sigpending
 	TSTMSK	__TI_flags(%r12),_TIF_NOTIFY_RESUME
 	jo	.Lio_notify_resume
 	TSTMSK	__TI_flags(%r12),_TIF_GUARDED_STORAGE
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 9e900a8977bd..b27b6c1f058d 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -472,7 +472,7 @@ void do_signal(struct pt_regs *regs)
 	current->thread.system_call =
 		test_pt_regs_flag(regs, PIF_SYSCALL) ? regs->int_code : 0;
 
-	if (get_signal(&ksig)) {
+	if (test_thread_flag(TIF_SIGPENDING) && get_signal(&ksig)) {
 		/* Whee!  Actually deliver the signal.  */
 		if (current->thread.system_call) {
 			regs->int_code = current->thread.system_call;