Merge 6.3-rc5 into driver-core-next

We need the fixes in here for testing, as well as the driver core
changes for documentation updates to build on.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

kernel/bpf/btf.c

@@ -4569,6 +4569,7 @@ static int btf_datasec_resolve(struct btf_verifier_env *env,
 	struct btf *btf = env->btf;
 	u16 i;
 
+	env->resolve_mode = RESOLVE_TBD;
 	for_each_vsi_from(i, v->next_member, v->t, vsi) {
 		u32 var_type_id = vsi->type, type_id, type_size = 0;
 		const struct btf_type *var_type = btf_type_by_id(env->btf,

kernel/bpf/core.c

@@ -972,7 +972,7 @@ static int __init bpf_jit_charge_init(void)
 {
 	/* Only used as heuristic here to derive limit. */
 	bpf_jit_limit_max = bpf_jit_alloc_exec_limit();
-	bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2,
+	bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 1,
 					    PAGE_SIZE), LONG_MAX);
 	return 0;
 }

kernel/bpf/verifier.c

@@ -3826,6 +3826,8 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 						continue;
 					if (type == STACK_MISC)
 						continue;
+					if (type == STACK_INVALID && env->allow_uninit_stack)
+						continue;
 					verbose(env, "invalid read from stack off %d+%d size %d\n",
 						off, i, size);
 					return -EACCES;
@@ -3863,6 +3865,8 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 				continue;
 			if (type == STACK_ZERO)
 				continue;
+			if (type == STACK_INVALID && env->allow_uninit_stack)
+				continue;
 			verbose(env, "invalid read from stack off %d+%d size %d\n",
 				off, i, size);
 			return -EACCES;
@@ -5754,7 +5758,8 @@ static int check_stack_range_initialized(
 		stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
 		if (*stype == STACK_MISC)
 			goto mark;
-		if (*stype == STACK_ZERO) {
+		if ((*stype == STACK_ZERO) ||
+		    (*stype == STACK_INVALID && env->allow_uninit_stack)) {
 			if (clobber) {
 				/* helper can write anything into the stack */
 				*stype = STACK_MISC;
@@ -13936,6 +13941,10 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
 		if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
 			continue;
 
+		if (env->allow_uninit_stack &&
+		    old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC)
+			continue;
+
 		/* explored stack has more populated slots than current stack
 		 * and these slots were used
 		 */

kernel/compat.c

@@ -152,7 +152,7 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t,  pid, unsigned int, len,
 	if (len & (sizeof(compat_ulong_t)-1))
 		return -EINVAL;
 
-	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
 		return -ENOMEM;
 
 	ret = sched_getaffinity(pid, mask);

kernel/dma/swiotlb.c

@@ -625,8 +625,8 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index,
 	unsigned int iotlb_align_mask =
 		dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1);
 	unsigned int nslots = nr_slots(alloc_size), stride;
-	unsigned int index, wrap, count = 0, i;
 	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+	unsigned int index, slots_checked, count = 0, i;
 	unsigned long flags;
 	unsigned int slot_base;
 	unsigned int slot_index;
@@ -634,30 +634,35 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index,
 	BUG_ON(!nslots);
 	BUG_ON(area_index >= mem->nareas);
 
+	/*
+	 * For allocations of PAGE_SIZE or larger only look for page aligned
+	 * allocations.
+	 */
+	if (alloc_size >= PAGE_SIZE)
+		iotlb_align_mask &= PAGE_MASK;
+	iotlb_align_mask &= alloc_align_mask;
+
 	/*
 	 * For mappings with an alignment requirement don't bother looping to
-	 * unaligned slots once we found an aligned one.  For allocations of
-	 * PAGE_SIZE or larger only look for page aligned allocations.
+	 * unaligned slots once we found an aligned one.
 	 */
 	stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1;
-	if (alloc_size >= PAGE_SIZE)
-		stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT));
-	stride = max(stride, (alloc_align_mask >> IO_TLB_SHIFT) + 1);
 
 	spin_lock_irqsave(&area->lock, flags);
 	if (unlikely(nslots > mem->area_nslabs - area->used))
 		goto not_found;
 
 	slot_base = area_index * mem->area_nslabs;
-	index = wrap = wrap_area_index(mem, ALIGN(area->index, stride));
+	index = area->index;
 
-	do {
+	for (slots_checked = 0; slots_checked < mem->area_nslabs; ) {
 		slot_index = slot_base + index;
 
 		if (orig_addr &&
 		    (slot_addr(tbl_dma_addr, slot_index) &
 		     iotlb_align_mask) != (orig_addr & iotlb_align_mask)) {
 			index = wrap_area_index(mem, index + 1);
+			slots_checked++;
 			continue;
 		}
 
@@ -673,7 +678,8 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index,
 				goto found;
 		}
 		index = wrap_area_index(mem, index + stride);
-	} while (index != wrap);
+		slots_checked += stride;
+	}
 
 not_found:
 	spin_unlock_irqrestore(&area->lock, flags);
@@ -693,10 +699,7 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index,
 	/*
 	 * Update the indices to avoid searching in the next round.
 	 */
-	if (index + nslots < mem->area_nslabs)
-		area->index = index + nslots;
-	else
-		area->index = 0;
+	area->index = wrap_area_index(mem, index + nslots);
 	area->used += nslots;
 	spin_unlock_irqrestore(&area->lock, flags);
 	return slot_index;

kernel/entry/common.c

@@ -21,7 +21,7 @@ static __always_inline void __enter_from_user_mode(struct pt_regs *regs)
 	arch_enter_from_user_mode(regs);
 	lockdep_hardirqs_off(CALLER_ADDR0);
 
-	CT_WARN_ON(ct_state() != CONTEXT_USER);
+	CT_WARN_ON(__ct_state() != CONTEXT_USER);
 	user_exit_irqoff();
 
 	instrumentation_begin();
@@ -192,13 +192,14 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 
 static void exit_to_user_mode_prepare(struct pt_regs *regs)
 {
-	unsigned long ti_work = read_thread_flags();
+	unsigned long ti_work;
 
 	lockdep_assert_irqs_disabled();
 
 	/* Flush pending rcuog wakeup before the last need_resched() check */
 	tick_nohz_user_enter_prepare();
 
+	ti_work = read_thread_flags();
 	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
 		ti_work = exit_to_user_mode_loop(regs, ti_work);
 

kernel/events/core.c

@@ -2163,7 +2163,7 @@ static void perf_group_detach(struct perf_event *event)
 		/* Inherit group flags from the previous leader */
 		sibling->group_caps = event->group_caps;
 
-		if (!RB_EMPTY_NODE(&event->group_node)) {
+		if (sibling->attach_state & PERF_ATTACH_CONTEXT) {
 			add_event_to_groups(sibling, event->ctx);
 
 			if (sibling->state == PERF_EVENT_STATE_ACTIVE)
@@ -3872,7 +3872,7 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type)
 	if (likely(!ctx->nr_events))
 		return;
 
-	if (is_active ^ EVENT_TIME) {
+	if (!(is_active & EVENT_TIME)) {
 		/* start ctx time */
 		__update_context_time(ctx, false);
 		perf_cgroup_set_timestamp(cpuctx);
@@ -9187,7 +9187,7 @@ static void perf_event_bpf_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&bpf_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, data, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				bpf_event->event_id.header.size);
 	if (ret)
 		return;

kernel/fork.c

@@ -755,11 +755,6 @@ static void check_mm(struct mm_struct *mm)
 	for (i = 0; i < NR_MM_COUNTERS; i++) {
 		long x = percpu_counter_sum(&mm->rss_stat[i]);
 
-		if (likely(!x))
-			continue;
-
-		/* Making sure this is not due to race with CPU offlining. */
-		x = percpu_counter_sum_all(&mm->rss_stat[i]);
 		if (unlikely(x))
 			pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n",
 				 mm, resident_page_types[i], x);
@@ -2936,7 +2931,7 @@ static bool clone3_args_valid(struct kernel_clone_args *kargs)
 	 * - make the CLONE_DETACHED bit reusable for clone3
 	 * - make the CSIGNAL bits reusable for clone3
 	 */
-	if (kargs->flags & (CLONE_DETACHED | CSIGNAL))
+	if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME))))
 		return false;
 
 	if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) ==

kernel/kcsan/Makefile

@@ -16,6 +16,6 @@ obj-y := core.o debugfs.o report.o
 KCSAN_INSTRUMENT_BARRIERS_selftest.o := y
 obj-$(CONFIG_KCSAN_SELFTEST) += selftest.o
 
-CFLAGS_kcsan_test.o := $(CFLAGS_KCSAN) -g -fno-omit-frame-pointer
+CFLAGS_kcsan_test.o := $(CFLAGS_KCSAN) -fno-omit-frame-pointer
 CFLAGS_kcsan_test.o += $(DISABLE_STRUCTLEAK_PLUGIN)
 obj-$(CONFIG_KCSAN_KUNIT_TEST) += kcsan_test.o

kernel/sched/core.c

@@ -2084,6 +2084,9 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
+	if (task_on_rq_migrating(p))
+		flags |= ENQUEUE_MIGRATED;
+
 	enqueue_task(rq, p, flags);
 
 	p->on_rq = TASK_ON_RQ_QUEUED;
@@ -8414,14 +8417,14 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
 	if (len & (sizeof(unsigned long)-1))
 		return -EINVAL;
 
-	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
 		return -ENOMEM;
 
 	ret = sched_getaffinity(pid, mask);
 	if (ret == 0) {
 		unsigned int retlen = min(len, cpumask_size());
 
-		if (copy_to_user(user_mask_ptr, mask, retlen))
+		if (copy_to_user(user_mask_ptr, cpumask_bits(mask), retlen))
 			ret = -EFAULT;
 		else
 			ret = retlen;

kernel/sched/fair.c

@@ -4648,11 +4648,33 @@ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
 #endif
 }
 
+static inline bool entity_is_long_sleeper(struct sched_entity *se)
+{
+	struct cfs_rq *cfs_rq;
+	u64 sleep_time;
+
+	if (se->exec_start == 0)
+		return false;
+
+	cfs_rq = cfs_rq_of(se);
+
+	sleep_time = rq_clock_task(rq_of(cfs_rq));
+
+	/* Happen while migrating because of clock task divergence */
+	if (sleep_time <= se->exec_start)
+		return false;
+
+	sleep_time -= se->exec_start;
+	if (sleep_time > ((1ULL << 63) / scale_load_down(NICE_0_LOAD)))
+		return true;
+
+	return false;
+}
+
 static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
 	u64 vruntime = cfs_rq->min_vruntime;
-	u64 sleep_time;
 
 	/*
 	 * The 'current' period is already promised to the current tasks,
@@ -4684,13 +4706,24 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 	/*
 	 * Pull vruntime of the entity being placed to the base level of
-	 * cfs_rq, to prevent boosting it if placed backwards.  If the entity
-	 * slept for a long time, don't even try to compare its vruntime with
-	 * the base as it may be too far off and the comparison may get
-	 * inversed due to s64 overflow.
+	 * cfs_rq, to prevent boosting it if placed backwards.
+	 * However, min_vruntime can advance much faster than real time, with
+	 * the extreme being when an entity with the minimal weight always runs
+	 * on the cfs_rq. If the waking entity slept for a long time, its
+	 * vruntime difference from min_vruntime may overflow s64 and their
+	 * comparison may get inversed, so ignore the entity's original
+	 * vruntime in that case.
+	 * The maximal vruntime speedup is given by the ratio of normal to
+	 * minimal weight: scale_load_down(NICE_0_LOAD) / MIN_SHARES.
+	 * When placing a migrated waking entity, its exec_start has been set
+	 * from a different rq. In order to take into account a possible
+	 * divergence between new and prev rq's clocks task because of irq and
+	 * stolen time, we take an additional margin.
+	 * So, cutting off on the sleep time of
+	 *     2^63 / scale_load_down(NICE_0_LOAD) ~ 104 days
+	 * should be safe.
 	 */
-	sleep_time = rq_clock_task(rq_of(cfs_rq)) - se->exec_start;
-	if ((s64)sleep_time > 60LL * NSEC_PER_SEC)
+	if (entity_is_long_sleeper(se))
 		se->vruntime = vruntime;
 	else
 		se->vruntime = max_vruntime(se->vruntime, vruntime);
@@ -4770,6 +4803,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	if (flags & ENQUEUE_WAKEUP)
 		place_entity(cfs_rq, se, 0);
+	/* Entity has migrated, no longer consider this task hot */
+	if (flags & ENQUEUE_MIGRATED)
+		se->exec_start = 0;
 
 	check_schedstat_required();
 	update_stats_enqueue_fair(cfs_rq, se, flags);
@@ -7657,9 +7693,6 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 	/* Tell new CPU we are migrated */
 	se->avg.last_update_time = 0;
 
-	/* We have migrated, no longer consider this task hot */
-	se->exec_start = 0;
-
 	update_scan_period(p, new_cpu);
 }
 

kernel/trace/ftrace.c

@@ -1564,7 +1564,8 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end)
 	key.flags = end;	/* overload flags, as it is unsigned long */
 
 	for (pg = ftrace_pages_start; pg; pg = pg->next) {
-		if (end < pg->records[0].ip ||
+		if (pg->index == 0 ||
+		    end < pg->records[0].ip ||
 		    start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE))
 			continue;
 		rec = bsearch(&key, pg->records, pg->index,
@@ -2591,7 +2592,7 @@ static void call_direct_funcs(unsigned long ip, unsigned long pip,
 	arch_ftrace_set_direct_caller(fregs, addr);
 }
 
-struct ftrace_ops direct_ops = {
+static struct ftrace_ops direct_ops = {
 	.func		= call_direct_funcs,
 	.flags		= FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS
 			  | FTRACE_OPS_FL_PERMANENT,

kernel/trace/kprobe_event_gen_test.c

@@ -146,7 +146,7 @@ static int __init test_gen_kprobe_cmd(void)
 	if (trace_event_file_is_valid(gen_kprobe_test))
 		gen_kprobe_test = NULL;
 	/* We got an error after creating the event, delete it */
-	ret = kprobe_event_delete("gen_kprobe_test");
+	kprobe_event_delete("gen_kprobe_test");
 	goto out;
 }
 
@@ -211,7 +211,7 @@ static int __init test_gen_kretprobe_cmd(void)
 	if (trace_event_file_is_valid(gen_kretprobe_test))
 		gen_kretprobe_test = NULL;
 	/* We got an error after creating the event, delete it */
-	ret = kprobe_event_delete("gen_kretprobe_test");
+	kprobe_event_delete("gen_kretprobe_test");
 	goto out;
 }
 

kernel/trace/ring_buffer.c

@@ -354,10 +354,6 @@ static void rb_init_page(struct buffer_data_page *bpage)
 	local_set(&bpage->commit, 0);
 }
 
-/*
- * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing
- * this issue out.
- */
 static void free_buffer_page(struct buffer_page *bpage)
 {
 	free_page((unsigned long)bpage->page);

kernel/trace/trace.c

@@ -5167,6 +5167,8 @@ loff_t tracing_lseek(struct file *file, loff_t offset, int whence)
 static const struct file_operations tracing_fops = {
 	.open		= tracing_open,
 	.read		= seq_read,
+	.read_iter	= seq_read_iter,
+	.splice_read	= generic_file_splice_read,
 	.write		= tracing_write_stub,
 	.llseek		= tracing_lseek,
 	.release	= tracing_release,

kernel/trace/trace_events_hist.c

@@ -1331,6 +1331,9 @@ static const char *hist_field_name(struct hist_field *field,
 {
 	const char *field_name = "";
 
+	if (WARN_ON_ONCE(!field))
+		return field_name;
+
 	if (level > 1)
 		return field_name;
 
@@ -4235,6 +4238,15 @@ static int __create_val_field(struct hist_trigger_data *hist_data,
 		goto out;
 	}
 
+	/* Some types cannot be a value */
+	if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT |
+				 HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 |
+				 HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET |
+				 HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) {
+		hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str));
+		ret = -EINVAL;
+	}
+
 	hist_data->fields[val_idx] = hist_field;
 
 	++hist_data->n_vals;

kernel/trace/trace_hwlat.c

@@ -339,7 +339,7 @@ static void move_to_next_cpu(void)
 	cpumask_clear(current_mask);
 	cpumask_set_cpu(next_cpu, current_mask);
 
-	sched_setaffinity(0, current_mask);
+	set_cpus_allowed_ptr(current, current_mask);
 	return;
 
  change_mode:
@@ -446,7 +446,7 @@ static int start_single_kthread(struct trace_array *tr)
 
 	}
 
-	sched_setaffinity(kthread->pid, current_mask);
+	set_cpus_allowed_ptr(kthread, current_mask);
 
 	kdata->kthread = kthread;
 	wake_up_process(kthread);
@@ -492,6 +492,10 @@ static int start_cpu_kthread(unsigned int cpu)
 {
 	struct task_struct *kthread;
 
+	/* Do not start a new hwlatd thread if it is already running */
+	if (per_cpu(hwlat_per_cpu_data, cpu).kthread)
+		return 0;
+
 	kthread = kthread_run_on_cpu(kthread_fn, NULL, cpu, "hwlatd/%u");
 	if (IS_ERR(kthread)) {
 		pr_err(BANNER "could not start sampling thread\n");
@@ -584,9 +588,6 @@ static int start_per_cpu_kthreads(struct trace_array *tr)
 	 */
 	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
 
-	for_each_online_cpu(cpu)
-		per_cpu(hwlat_per_cpu_data, cpu).kthread = NULL;
-
 	for_each_cpu(cpu, current_mask) {
 		retval = start_cpu_kthread(cpu);
 		if (retval)

kernel/trace/trace_osnoise.c

@@ -217,7 +217,7 @@ struct osnoise_variables {
 /*
  * Per-cpu runtime information.
  */
-DEFINE_PER_CPU(struct osnoise_variables, per_cpu_osnoise_var);
+static DEFINE_PER_CPU(struct osnoise_variables, per_cpu_osnoise_var);
 
 /*
  * this_cpu_osn_var - Return the per-cpu osnoise_variables on its relative CPU
@@ -240,7 +240,7 @@ struct timerlat_variables {
 	u64			count;
 };
 
-DEFINE_PER_CPU(struct timerlat_variables, per_cpu_timerlat_var);
+static DEFINE_PER_CPU(struct timerlat_variables, per_cpu_timerlat_var);
 
 /*
  * this_cpu_tmr_var - Return the per-cpu timerlat_variables on its relative CPU
@@ -332,7 +332,7 @@ struct timerlat_sample {
 /*
  * Protect the interface.
  */
-struct mutex interface_lock;
+static struct mutex interface_lock;
 
 /*
  * Tracer data.
@@ -2239,8 +2239,8 @@ static struct trace_min_max_param osnoise_print_stack = {
 /*
  * osnoise/timerlat_period: min 100 us, max 1 s
  */
-u64 timerlat_min_period = 100;
-u64 timerlat_max_period = 1000000;
+static u64 timerlat_min_period = 100;
+static u64 timerlat_max_period = 1000000;
 static struct trace_min_max_param timerlat_period = {
 	.lock	= &interface_lock,
 	.val	= &osnoise_data.timerlat_period,

kernel/watch_queue.c

@@ -273,6 +273,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
 	if (ret < 0)
 		goto error;
 
+	ret = -ENOMEM;
 	pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL);
 	if (!pages)
 		goto error;