Merge tag 'v5.15-rc4' into rdma.get for-next

Merged due to dependencies in following patches.

Conflict in drivers/infiniband/hw/hfi1/ipoib_tx.c resolved by hand to take
the %p change and txq stats rename together.

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

11 files changed, 83 insertions, 22 deletions

diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index d6731c32864e..9abcc33f02cf 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -368,6 +368,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 		const struct btf_type *mtype, *ptype;
 		struct bpf_prog *prog;
 		u32 moff;
+		u32 flags;
 
 		moff = btf_member_bit_offset(t, member) / 8;
 		ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL);
@@ -431,10 +432,12 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 
 		tprogs[BPF_TRAMP_FENTRY].progs[0] = prog;
 		tprogs[BPF_TRAMP_FENTRY].nr_progs = 1;
+		flags = st_ops->func_models[i].ret_size > 0 ?
+			BPF_TRAMP_F_RET_FENTRY_RET : 0;
 		err = arch_prepare_bpf_trampoline(NULL, image,
 						  st_map->image + PAGE_SIZE,
-						  &st_ops->func_models[i], 0,
-						  tprogs, NULL);
+						  &st_ops->func_models[i],
+						  flags, tprogs, NULL);
 		if (err < 0)
 			goto reset_unlock;
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9f4636d021b1..d6b7dfdd8066 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -827,7 +827,7 @@ int bpf_jit_charge_modmem(u32 pages)
 {
 	if (atomic_long_add_return(pages, &bpf_jit_current) >
 	    (bpf_jit_limit >> PAGE_SHIFT)) {
-		if (!capable(CAP_SYS_ADMIN)) {
+		if (!bpf_capable()) {
 			atomic_long_sub(pages, &bpf_jit_current);
 			return -EPERM;
 		}
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 8afa8690d288..570b0c97392a 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6574,22 +6574,29 @@ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v)
 
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 {
-	/* Don't associate the sock with unrelated interrupted task's cgroup. */
-	if (in_interrupt())
-		return;
+	struct cgroup *cgroup;
 
 	rcu_read_lock();
+	/* Don't associate the sock with unrelated interrupted task's cgroup. */
+	if (in_interrupt()) {
+		cgroup = &cgrp_dfl_root.cgrp;
+		cgroup_get(cgroup);
+		goto out;
+	}
+
 	while (true) {
 		struct css_set *cset;
 
 		cset = task_css_set(current);
 		if (likely(cgroup_tryget(cset->dfl_cgrp))) {
-			skcd->cgroup = cset->dfl_cgrp;
-			cgroup_bpf_get(cset->dfl_cgrp);
+			cgroup = cset->dfl_cgrp;
 			break;
 		}
 		cpu_relax();
 	}
+out:
+	skcd->cgroup = cgroup;
+	cgroup_bpf_get(cgroup);
 	rcu_read_unlock();
 }
 
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index bf16395b9e13..d5a61d565ad5 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -171,10 +171,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 		if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
 			handle_signal_work(regs, ti_work);
 
-		if (ti_work & _TIF_NOTIFY_RESUME) {
+		if (ti_work & _TIF_NOTIFY_RESUME)
 			tracehook_notify_resume(regs);
-			rseq_handle_notify_resume(NULL, regs);
-		}
 
 		/* Architecture specific TIF work */
 		arch_exit_to_user_mode_work(regs, ti_work);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0c000cb01eeb..f23ca260307f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3707,6 +3707,29 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx,
 	return 0;
 }
 
+static inline bool event_update_userpage(struct perf_event *event)
+{
+	if (likely(!atomic_read(&event->mmap_count)))
+		return false;
+
+	perf_event_update_time(event);
+	perf_set_shadow_time(event, event->ctx);
+	perf_event_update_userpage(event);
+
+	return true;
+}
+
+static inline void group_update_userpage(struct perf_event *group_event)
+{
+	struct perf_event *event;
+
+	if (!event_update_userpage(group_event))
+		return;
+
+	for_each_sibling_event(event, group_event)
+		event_update_userpage(event);
+}
+
 static int merge_sched_in(struct perf_event *event, void *data)
 {
 	struct perf_event_context *ctx = event->ctx;
@@ -3725,14 +3748,15 @@ static int merge_sched_in(struct perf_event *event, void *data)
 	}
 
 	if (event->state == PERF_EVENT_STATE_INACTIVE) {
+		*can_add_hw = 0;
 		if (event->attr.pinned) {
 			perf_cgroup_event_disable(event, ctx);
 			perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+		} else {
+			ctx->rotate_necessary = 1;
+			perf_mux_hrtimer_restart(cpuctx);
+			group_update_userpage(event);
 		}
-
-		*can_add_hw = 0;
-		ctx->rotate_necessary = 1;
-		perf_mux_hrtimer_restart(cpuctx);
 	}
 
 	return 0;
@@ -6324,6 +6348,8 @@ accounting:
 
 		ring_buffer_attach(event, rb);
 
+		perf_event_update_time(event);
+		perf_set_shadow_time(event, event->ctx);
 		perf_event_init_userpage(event);
 		perf_event_update_userpage(event);
 	} else {
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 19e83e9b723c..4d8fc65cf38f 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -136,7 +136,7 @@ EXPORT_SYMBOL_GPL(irq_domain_free_fwnode);
  * Allocates and initializes an irq_domain structure.
  * Returns pointer to IRQ domain, or NULL on failure.
  */
-struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size,
+struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size,
 				    irq_hw_number_t hwirq_max, int direct_max,
 				    const struct irq_domain_ops *ops,
 				    void *host_data)
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 35f7bd0fced0..6d45ac3dae7f 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -282,9 +282,17 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
 
 	if (unlikely(t->flags & PF_EXITING))
 		return;
-	ret = rseq_ip_fixup(regs);
-	if (unlikely(ret < 0))
-		goto error;
+
+	/*
+	 * regs is NULL if and only if the caller is in a syscall path.  Skip
+	 * fixup and leave rseq_cs as is so that rseq_sycall() will detect and
+	 * kill a misbehaving userspace on debug kernels.
+	 */
+	if (regs) {
+		ret = rseq_ip_fixup(regs);
+		if (unlikely(ret < 0))
+			goto error;
+	}
 	if (unlikely(rseq_update_cpu_id(t)))
 		goto error;
 	return;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 49716228efb4..17a653b67006 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -173,16 +173,22 @@ static ssize_t sched_scaling_write(struct file *filp, const char __user *ubuf,
 				   size_t cnt, loff_t *ppos)
 {
 	char buf[16];
+	unsigned int scaling;
 
 	if (cnt > 15)
 		cnt = 15;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;
+	buf[cnt] = '\0';
 
-	if (kstrtouint(buf, 10, &sysctl_sched_tunable_scaling))
+	if (kstrtouint(buf, 10, &scaling))
 		return -EINVAL;
 
+	if (scaling >= SCHED_TUNABLESCALING_END)
+		return -EINVAL;
+
+	sysctl_sched_tunable_scaling = scaling;
 	if (sched_update_scaling())
 		return -EINVAL;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ff69f245b939..f6a05d9b5443 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4936,8 +4936,12 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	/* update hierarchical throttle state */
 	walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq);
 
-	if (!cfs_rq->load.weight)
+	/* Nothing to run but something to decay (on_list)? Complete the branch */
+	if (!cfs_rq->load.weight) {
+		if (cfs_rq->on_list)
+			goto unthrottle_throttle;
 		return;
+	}
 
 	task_delta = cfs_rq->h_nr_running;
 	idle_task_delta = cfs_rq->idle_h_nr_running;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index ee736861b18f..643d412ac623 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1404,7 +1404,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clkid,
 			}
 		}
 
-		*newval += now;
+		if (*newval)
+			*newval += now;
 	}
 
 	/*
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index c221e4c3f625..fa91f398f28b 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1605,6 +1605,14 @@ static int blk_trace_remove_queue(struct request_queue *q)
 	if (bt == NULL)
 		return -EINVAL;
 
+	if (bt->trace_state == Blktrace_running) {
+		bt->trace_state = Blktrace_stopped;
+		spin_lock_irq(&running_trace_lock);
+		list_del_init(&bt->running_list);
+		spin_unlock_irq(&running_trace_lock);
+		relay_flush(bt->rchan);
+	}
+
 	put_probe_ref();
 	synchronize_rcu();
 	blk_trace_free(bt);