spi: spi-fsl-dspi: Target mode improvements

Merge series from James Clark <james.clark@linaro.org>:

Improve usability of target mode by reporting FIFO errors and increasing
the buffer size when DMA is used. While we're touching DMA stuff also
switch to non-coherent memory, although this is unrelated to target
mode.

With the combination of the commit to increase the DMA buffer size and
the commit to use non-coherent memory, the host mode performance figures
are as follows on S32G3:

  # spidev_test --device /dev/spidev1.0 --bpw 8 --size <test_size> --cpha --iter 10000000 --speed 10000000

  Coherent (4096 byte transfers): 6534 kbps
  Non-coherent:                   7347 kbps

  Coherent (16 byte transfers):    447 kbps
  Non-coherent:                    448 kbps

Just for comparison running the same test in XSPI mode:

  4096 byte transfers:            2143 kbps
  16 byte transfers:               637 kbps

These tests required hacking S32G3 to use DMA in host mode, although
the figures should be representative of target mode too where DMA is
used. And the other devices that use DMA in host mode should see similar
improvements.

18 files changed, 119 insertions, 54 deletions

diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 2ee603a98813..1224dd937df0 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -97,6 +97,7 @@ config KEXEC_JUMP
 config KEXEC_HANDOVER
 	bool "kexec handover"
 	depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE
+	depends on !DEFERRED_STRUCT_PAGE_INIT
 	select MEMBLOCK_KHO_SCRATCH
 	select KEXEC_FILE
 	select DEBUG_FS
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index f74d04429a29..27adb04df675 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -280,7 +280,7 @@ static inline void check_insane_mems_config(nodemask_t *nodes)
 {
 	if (!cpusets_insane_config() &&
 		movable_only_nodes(nodes)) {
-		static_branch_enable(&cpusets_insane_config_key);
+		static_branch_enable_cpuslocked(&cpusets_insane_config_key);
 		pr_info("Unsupported (movable nodes only) cpuset configuration detected (nmask=%*pbl)!\n"
 			"Cpuset allocations might fail even with a lot of memory available.\n",
 			nodemask_pr_args(nodes));
@@ -1843,7 +1843,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 			if (is_partition_valid(cs))
 				adding = cpumask_and(tmp->addmask,
 						xcpus, parent->effective_xcpus);
-		} else if (is_partition_invalid(cs) &&
+		} else if (is_partition_invalid(cs) && !cpumask_empty(xcpus) &&
 			   cpumask_subset(xcpus, parent->effective_xcpus)) {
 			struct cgroup_subsys_state *css;
 			struct cpuset *child;
@@ -3358,14 +3358,12 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf,
 	else
 		return -EINVAL;
 
-	css_get(&cs->css);
 	cpus_read_lock();
 	mutex_lock(&cpuset_mutex);
 	if (is_cpuset_online(cs))
 		retval = update_prstate(cs, val);
 	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
-	css_put(&cs->css);
 	return retval ?: nbytes;
 }
 
@@ -3870,9 +3868,10 @@ retry:
 		partcmd = partcmd_invalidate;
 	/*
 	 * On the other hand, an invalid partition root may be transitioned
-	 * back to a regular one.
+	 * back to a regular one with a non-empty effective xcpus.
 	 */
-	else if (is_partition_valid(parent) && is_partition_invalid(cs))
+	else if (is_partition_valid(parent) && is_partition_invalid(cs) &&
+		 !cpumask_empty(cs->effective_xcpus))
 		partcmd = partcmd_update;
 
 	if (partcmd >= 0) {
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 981e2f77ad4e..a198e40c799b 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -479,6 +479,9 @@ void css_rstat_exit(struct cgroup_subsys_state *css)
 	if (!css_uses_rstat(css))
 		return;
 
+	if (!css->rstat_cpu)
+		return;
+
 	css_rstat_flush(css);
 
 	/* sanity check */
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 67af8a55185d..d9b9dcba6ff7 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -483,8 +483,6 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem)
 		pr_err("Reserved memory: unable to setup CMA region\n");
 		return err;
 	}
-	/* Architecture specific contiguous memory fixup. */
-	dma_contiguous_early_fixup(rmem->base, rmem->size);
 
 	if (default_cma)
 		dma_contiguous_default_area = cma;
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 7b04f7575796..ee45dee33d49 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -102,8 +102,8 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 
 #ifdef CONFIG_DMA_DIRECT_REMAP
 	addr = dma_common_contiguous_remap(page, pool_size,
-					   pgprot_dmacoherent(PAGE_KERNEL),
-					   __builtin_return_address(0));
+			pgprot_decrypted(pgprot_dmacoherent(PAGE_KERNEL)),
+			__builtin_return_address(0));
 	if (!addr)
 		goto free_page;
 #else
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8060c2857bb2..872122e074e5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2665,6 +2665,9 @@ static void perf_log_itrace_start(struct perf_event *event);
 
 static void perf_event_unthrottle(struct perf_event *event, bool start)
 {
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return;
+
 	event->hw.interrupts = 0;
 	if (start)
 		event->pmu->start(event, 0);
@@ -2674,6 +2677,9 @@ static void perf_event_unthrottle(struct perf_event *event, bool start)
 
 static void perf_event_throttle(struct perf_event *event)
 {
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return;
+
 	event->hw.interrupts = MAX_INTERRUPTS;
 	event->pmu->stop(event, 0);
 	if (event == event->group_leader)
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index e49743ae52c5..ecd1ac210dbd 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -144,14 +144,34 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn,
 				unsigned int order)
 {
 	struct kho_mem_phys_bits *bits;
-	struct kho_mem_phys *physxa;
+	struct kho_mem_phys *physxa, *new_physxa;
 	const unsigned long pfn_high = pfn >> order;
 
 	might_sleep();
 
-	physxa = xa_load_or_alloc(&track->orders, order, sizeof(*physxa));
-	if (IS_ERR(physxa))
-		return PTR_ERR(physxa);
+	physxa = xa_load(&track->orders, order);
+	if (!physxa) {
+		int err;
+
+		new_physxa = kzalloc(sizeof(*physxa), GFP_KERNEL);
+		if (!new_physxa)
+			return -ENOMEM;
+
+		xa_init(&new_physxa->phys_bits);
+		physxa = xa_cmpxchg(&track->orders, order, NULL, new_physxa,
+				    GFP_KERNEL);
+
+		err = xa_err(physxa);
+		if (err || physxa) {
+			xa_destroy(&new_physxa->phys_bits);
+			kfree(new_physxa);
+
+			if (err)
+				return err;
+		} else {
+			physxa = new_physxa;
+		}
+	}
 
 	bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS,
 				sizeof(*bits));
@@ -544,6 +564,7 @@ err_free_scratch_areas:
 err_free_scratch_desc:
 	memblock_free(kho_scratch, kho_scratch_cnt * sizeof(*kho_scratch));
 err_disable_kho:
+	pr_warn("Failed to reserve scratch area, disabling kexec handover\n");
 	kho_enable = false;
 }
 
diff --git a/kernel/params.c b/kernel/params.c
index b92d64161b75..b96cfd693c99 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -513,13 +513,14 @@ EXPORT_SYMBOL(param_array_ops);
 int param_set_copystring(const char *val, const struct kernel_param *kp)
 {
 	const struct kparam_string *kps = kp->str;
+	const size_t len = strnlen(val, kps->maxlen);
 
-	if (strnlen(val, kps->maxlen) == kps->maxlen) {
+	if (len == kps->maxlen) {
 		pr_err("%s: string doesn't fit in %u chars.\n",
 		       kp->name, kps->maxlen-1);
 		return -ENOSPC;
 	}
-	strcpy(kps->string, val);
+	memcpy(kps->string, val, len + 1);
 	return 0;
 }
 EXPORT_SYMBOL(param_set_copystring);
@@ -841,7 +842,7 @@ static void __init param_sysfs_builtin(void)
 		dot = strchr(kp->name, '.');
 		if (!dot) {
 			/* This happens for core_param() */
-			strcpy(modname, "kernel");
+			strscpy(modname, "kernel");
 			name_len = 0;
 		} else {
 			name_len = dot - kp->name + 1;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e2d51f4306b3..f25301267e47 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1496,10 +1496,12 @@ throttle:
 		}
 
 		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se))) {
-			if (dl_server(dl_se))
-				enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
-			else
+			if (dl_server(dl_se)) {
+				replenish_dl_new_period(dl_se, rq);
+				start_dl_timer(dl_se);
+			} else {
 				enqueue_task_dl(rq, dl_task_of(dl_se), ENQUEUE_REPLENISH);
+			}
 		}
 
 		if (!is_leftmost(dl_se, &rq->dl))
@@ -1611,7 +1613,7 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
 static bool dl_server_stopped(struct sched_dl_entity *dl_se)
 {
 	if (!dl_se->dl_server_active)
-		return false;
+		return true;
 
 	if (dl_se->dl_server_idle) {
 		dl_server_stop(dl_se);
@@ -1849,7 +1851,9 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 	u64 deadline = dl_se->deadline;
 
 	dl_rq->dl_nr_running++;
-	add_nr_running(rq_of_dl_rq(dl_rq), 1);
+
+	if (!dl_server(dl_se))
+		add_nr_running(rq_of_dl_rq(dl_rq), 1);
 
 	inc_dl_deadline(dl_rq, deadline);
 }
@@ -1859,7 +1863,9 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 	WARN_ON(!dl_rq->dl_nr_running);
 	dl_rq->dl_nr_running--;
-	sub_nr_running(rq_of_dl_rq(dl_rq), 1);
+
+	if (!dl_server(dl_se))
+		sub_nr_running(rq_of_dl_rq(dl_rq), 1);
 
 	dec_dl_deadline(dl_rq, dl_se->deadline);
 }
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 3f06ab84d53f..02e16b70a790 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -376,10 +376,8 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 			return  -EINVAL;
 		}
 
-		if (rq->cfs.h_nr_queued) {
-			update_rq_clock(rq);
-			dl_server_stop(&rq->fair_server);
-		}
+		update_rq_clock(rq);
+		dl_server_stop(&rq->fair_server);
 
 		retval = dl_server_apply_params(&rq->fair_server, runtime, period, 0);
 		if (retval)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 7dedc9a16281..4ae32ef179dd 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -5749,6 +5749,9 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 			__setscheduler_class(p->policy, p->prio);
 		struct sched_enq_and_set_ctx ctx;
 
+		if (!tryget_task_struct(p))
+			continue;
+
 		if (old_class != new_class && p->se.sched_delayed)
 			dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
 
@@ -5761,6 +5764,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 		sched_enq_and_set_task(&ctx);
 
 		check_class_changed(task_rq(p), p, old_class, p->prio);
+		put_task_struct(p);
 	}
 	scx_task_iter_stop(&sti);
 	percpu_up_write(&scx_fork_rwsem);
diff --git a/kernel/signal.c b/kernel/signal.c
index e2c928de7d2c..fe9190d84f28 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -4067,6 +4067,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 {
 	struct pid *pid;
 	enum pid_type type;
+	int ret;
 
 	/* Enforce flags be set to 0 until we add an extension. */
 	if (flags & ~PIDFD_SEND_SIGNAL_FLAGS)
@@ -4108,7 +4109,10 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 	}
 	}
 
-	return do_pidfd_send_signal(pid, sig, type, info, flags);
+	ret = do_pidfd_send_signal(pid, sig, type, info, flags);
+	put_pid(pid);
+
+	return ret;
 }
 
 static int
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index f4d200f0c610..2a42c1036ea8 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -1397,6 +1397,7 @@ error:
 		ftrace_graph_active--;
 		gops->saved_func = NULL;
 		fgraph_lru_release_index(i);
+		unregister_pm_notifier(&ftrace_suspend_notifier);
 	}
 	return ret;
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 00b76d450a89..a69067367c29 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4661,13 +4661,17 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 	        } else {
 			iter->hash = alloc_and_copy_ftrace_hash(size_bits, hash);
 		}
+	} else {
+		if (hash)
+			iter->hash = alloc_and_copy_ftrace_hash(hash->size_bits, hash);
+		else
+			iter->hash = EMPTY_HASH;
+	}
 
-		if (!iter->hash) {
-			trace_parser_put(&iter->parser);
-			goto out_unlock;
-		}
-	} else
-		iter->hash = hash;
+	if (!iter->hash) {
+		trace_parser_put(&iter->parser);
+		goto out_unlock;
+	}
 
 	ret = 0;
 
@@ -6543,9 +6547,6 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 		ftrace_hash_move_and_update_ops(iter->ops, orig_hash,
 						      iter->hash, filter_hash);
 		mutex_unlock(&ftrace_lock);
-	} else {
-		/* For read only, the hash is the ops hash */
-		iter->hash = NULL;
 	}
 
 	mutex_unlock(&iter->ops->func_hash->regex_lock);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bb71a0dc9d69..43460949ad3f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -7666,7 +7666,7 @@ static __init int test_ringbuffer(void)
 	rb_test_started = true;
 
 	set_current_state(TASK_INTERRUPTIBLE);
-	/* Just run for 10 seconds */;
+	/* Just run for 10 seconds */
 	schedule_timeout(10 * HZ);
 
 	kthread_stop(rb_hammer);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4283ed4e8f59..1b7db732c0b1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1816,7 +1816,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 
 	ret = get_user(ch, ubuf++);
 	if (ret)
-		return ret;
+		goto fail;
 
 	read++;
 	cnt--;
@@ -1830,7 +1830,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 		while (cnt && isspace(ch)) {
 			ret = get_user(ch, ubuf++);
 			if (ret)
-				return ret;
+				goto fail;
 			read++;
 			cnt--;
 		}
@@ -1848,12 +1848,14 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 	while (cnt && !isspace(ch) && ch) {
 		if (parser->idx < parser->size - 1)
 			parser->buffer[parser->idx++] = ch;
-		else
-			return -EINVAL;
+		else {
+			ret = -EINVAL;
+			goto fail;
+		}
 
 		ret = get_user(ch, ubuf++);
 		if (ret)
-			return ret;
+			goto fail;
 		read++;
 		cnt--;
 	}
@@ -1868,11 +1870,15 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 		/* Make sure the parsed string always terminates with '\0'. */
 		parser->buffer[parser->idx] = 0;
 	} else {
-		return -EINVAL;
+		ret = -EINVAL;
+		goto fail;
 	}
 
 	*ppos += read;
 	return read;
+fail:
+	trace_parser_fail(parser);
+	return ret;
 }
 
 /* TODO add a seq_buf_to_buffer() */
@@ -10632,10 +10638,10 @@ static void ftrace_dump_one(struct trace_array *tr, enum ftrace_dump_mode dump_m
 			ret = print_trace_line(&iter);
 			if (ret != TRACE_TYPE_NO_CONSUME)
 				trace_consume(&iter);
+
+			trace_printk_seq(&iter.seq);
 		}
 		touch_nmi_watchdog();
-
-		trace_printk_seq(&iter.seq);
 	}
 
 	if (!cnt)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 1dbf1d3cf2f1..5f4bed5842f9 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1292,6 +1292,7 @@ bool ftrace_event_is_function(struct trace_event_call *call);
  */
 struct trace_parser {
 	bool		cont;
+	bool		fail;
 	char		*buffer;
 	unsigned	idx;
 	unsigned	size;
@@ -1299,7 +1300,7 @@ struct trace_parser {
 
 static inline bool trace_parser_loaded(struct trace_parser *parser)
 {
-	return (parser->idx != 0);
+	return !parser->fail && parser->idx != 0;
 }
 
 static inline bool trace_parser_cont(struct trace_parser *parser)
@@ -1313,6 +1314,11 @@ static inline void trace_parser_clear(struct trace_parser *parser)
 	parser->idx = 0;
 }
 
+static inline void trace_parser_fail(struct trace_parser *parser)
+{
+	parser->fail = true;
+}
+
 extern int trace_parser_get_init(struct trace_parser *parser, int size);
 extern void trace_parser_put(struct trace_parser *parser);
 extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
@@ -2204,7 +2210,7 @@ static inline bool is_good_system_name(const char *name)
 static inline void sanitize_event_name(char *name)
 {
 	while (*name++ != '\0')
-		if (*name == ':' || *name == '.')
+		if (*name == ':' || *name == '.' || *name == '*')
 			*name = '_';
 }
 
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 66e1a527cf1a..a7f4b9a47a71 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -27,14 +27,21 @@ struct fgraph_cpu_data {
 	unsigned long	enter_funcs[FTRACE_RETFUNC_DEPTH];
 };
 
+struct fgraph_ent_args {
+	struct ftrace_graph_ent_entry	ent;
+	/* Force the sizeof of args[] to have FTRACE_REGS_MAX_ARGS entries */
+	unsigned long			args[FTRACE_REGS_MAX_ARGS];
+};
+
 struct fgraph_data {
 	struct fgraph_cpu_data __percpu *cpu_data;
 
 	/* Place to preserve last processed entry. */
 	union {
-		struct ftrace_graph_ent_entry	ent;
+		struct fgraph_ent_args		ent;
+		/* TODO allow retaddr to have args */
 		struct fgraph_retaddr_ent_entry	rent;
-	} ent;
+	};
 	struct ftrace_graph_ret_entry	ret;
 	int				failed;
 	int				cpu;
@@ -627,10 +634,13 @@ get_return_for_leaf(struct trace_iterator *iter,
 			 * Save current and next entries for later reference
 			 * if the output fails.
 			 */
-			if (unlikely(curr->ent.type == TRACE_GRAPH_RETADDR_ENT))
-				data->ent.rent = *(struct fgraph_retaddr_ent_entry *)curr;
-			else
-				data->ent.ent = *curr;
+			if (unlikely(curr->ent.type == TRACE_GRAPH_RETADDR_ENT)) {
+				data->rent = *(struct fgraph_retaddr_ent_entry *)curr;
+			} else {
+				int size = min((int)sizeof(data->ent), (int)iter->ent_size);
+
+				memcpy(&data->ent, curr, size);
+			}
 			/*
 			 * If the next event is not a return type, then
 			 * we only care about what type it is. Otherwise we can