Merge branch 'sg_nents' into rdma.git for-next

From Maor Gottlieb
====================

Fix the use of nents and orig_nents in the sg table append helpers. The
nents should be used by the DMA layer to store the number of DMA mapped
sges, the orig_nents is the number of CPU sges.

Since the sg append logic doesn't always create a SGL with exactly
orig_nents entries store a total_nents as well to allow the table to be
properly free'd and reorganize the freeing logic to share across all the
use cases.

====================

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

* 'sg_nents':
  RDMA: Use the sg_table directly and remove the opencoded version from umem
  lib/scatterlist: Fix wrong update of orig_nents
  lib/scatterlist: Provide a dedicated function to support table append

3 files changed, 7 insertions, 9 deletions

diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c
index 313d4547cbc7..d998a76fb542 100644
--- a/kernel/rcu/refscale.c
+++ b/kernel/rcu/refscale.c
@@ -487,13 +487,13 @@ ref_scale_reader(void *arg)
 	s64 duration;
 
 	VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: task started", me);
-	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+	WARN_ON_ONCE(set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)));
 	set_user_nice(current, MAX_NICE);
 	atomic_inc(&n_init);
 	if (holdoff)
 		schedule_timeout_interruptible(holdoff * HZ);
 repeat:
-	VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, smp_processor_id());
+	VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, raw_smp_processor_id());
 
 	// Wait for signal that this reader can start.
 	wait_event(rt->wq, (atomic_read(&nreaders_exp) && smp_load_acquire(&rt->start_reader)) ||
@@ -503,7 +503,7 @@ repeat:
 		goto end;
 
 	// Make sure that the CPU is affinitized appropriately during testing.
-	WARN_ON_ONCE(smp_processor_id() != me);
+	WARN_ON_ONCE(raw_smp_processor_id() != me);
 
 	WRITE_ONCE(rt->start_reader, 0);
 	if (!atomic_dec_return(&n_started))
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 03a118d1c003..8536c55df514 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -953,10 +953,9 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg)
 		in_qs = likely(!t->trc_reader_nesting);
 	}
 
-	// Mark as checked.  Because this is called from the grace-period
-	// kthread, also remove the task from the holdout list.
+	// Mark as checked so that the grace-period kthread will
+	// remove it from the holdout list.
 	t->trc_reader_checked = true;
-	trc_del_holdout(t);
 
 	if (in_qs)
 		return true;  // Already in quiescent state, done!!!
@@ -983,7 +982,6 @@ static void trc_wait_for_one_reader(struct task_struct *t,
 	// The current task had better be in a quiescent state.
 	if (t == current) {
 		t->trc_reader_checked = true;
-		trc_del_holdout(t);
 		WARN_ON_ONCE(t->trc_reader_nesting);
 		return;
 	}
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 3f937b20814f..6c76988cc019 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -795,9 +795,9 @@ void show_rcu_gp_kthreads(void)
 	jr = j - data_race(rcu_state.gp_req_activity);
 	js = j - data_race(rcu_state.gp_start);
 	jw = j - data_race(rcu_state.gp_wake_time);
-	pr_info("%s: wait state: %s(%d) ->state: %#lx ->rt_priority %u delta ->gp_start %lu ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_max %lu ->gp_flags %#x\n",
+	pr_info("%s: wait state: %s(%d) ->state: %#x ->rt_priority %u delta ->gp_start %lu ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_max %lu ->gp_flags %#x\n",
 		rcu_state.name, gp_state_getname(rcu_state.gp_state),
-		rcu_state.gp_state, t ? t->__state : 0x1ffffL, t ? t->rt_priority : 0xffU,
+		rcu_state.gp_state, t ? t->__state : 0x1ffff, t ? t->rt_priority : 0xffU,
 		js, ja, jr, jw, (long)data_race(rcu_state.gp_wake_seq),
 		(long)data_race(rcu_state.gp_seq),
 		(long)data_race(rcu_get_root()->gp_seq_needed),