Merging upstream version 4.19.269.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

10 files changed, 110 insertions, 31 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 471cc5c11..62e05b628 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1660,7 +1660,7 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
 	if (v->next_member) {
 		const struct btf_type *last_member_type;
 		const struct btf_member *last_member;
-		u16 last_member_type_id;
+		u32 last_member_type_id;
 
 		last_member = btf_type_member(v->t) + v->next_member - 1;
 		last_member_type_id = last_member->type;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e940c1f65..02e5bdb82 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2325,7 +2325,9 @@ static int bpf_task_fd_query(const union bpf_attr *attr,
 	if (attr->task_fd_query.flags != 0)
 		return -EINVAL;
 
+	rcu_read_lock();
 	task = get_pid_task(find_vpid(pid), PIDTYPE_PID);
+	rcu_read_unlock();
 	if (!task)
 		return -ENOENT;
 
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 8f7729b0a..4168e7d97 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -148,7 +148,6 @@ extern struct mutex cgroup_mutex;
 extern spinlock_t css_set_lock;
 extern struct cgroup_subsys *cgroup_subsys[];
 extern struct list_head cgroup_roots;
-extern struct file_system_type cgroup_fs_type;
 
 /* iterate across the hierarchies */
 #define for_each_root(root)						\
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index 5b9e76117..bb6ccf456 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -33,6 +33,13 @@
 
 #define GCOV_TAG_FUNCTION_LENGTH	3
 
+/* Since GCC 12.1 sizes are in BYTES and not in WORDS (4B). */
+#if (__GNUC__ >= 12)
+#define GCOV_UNIT_SIZE				4
+#else
+#define GCOV_UNIT_SIZE				1
+#endif
+
 static struct gcov_info *gcov_info_head;
 
 /**
@@ -439,12 +446,18 @@ static size_t convert_to_gcda(char *buffer, struct gcov_info *info)
 	pos += store_gcov_u32(buffer, pos, info->version);
 	pos += store_gcov_u32(buffer, pos, info->stamp);
 
+#if (__GNUC__ >= 12)
+	/* Use zero as checksum of the compilation unit. */
+	pos += store_gcov_u32(buffer, pos, 0);
+#endif
+
 	for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) {
 		fi_ptr = info->functions[fi_idx];
 
 		/* Function record. */
 		pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION);
-		pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION_LENGTH);
+		pos += store_gcov_u32(buffer, pos,
+			GCOV_TAG_FUNCTION_LENGTH * GCOV_UNIT_SIZE);
 		pos += store_gcov_u32(buffer, pos, fi_ptr->ident);
 		pos += store_gcov_u32(buffer, pos, fi_ptr->lineno_checksum);
 		pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum);
@@ -458,7 +471,8 @@ static size_t convert_to_gcda(char *buffer, struct gcov_info *info)
 			/* Counter record. */
 			pos += store_gcov_u32(buffer, pos,
 					      GCOV_TAG_FOR_COUNTER(ct_idx));
-			pos += store_gcov_u32(buffer, pos, ci_ptr->num * 2);
+			pos += store_gcov_u32(buffer, pos,
+				ci_ptr->num * 2 * GCOV_UNIT_SIZE);
 
 			for (cv_idx = 0; cv_idx < ci_ptr->num; cv_idx++) {
 				pos += store_gcov_u64(buffer, pos,
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index b2f01e61f..33aba4e2e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2172,8 +2172,11 @@ int enable_kprobe(struct kprobe *kp)
 	if (!kprobes_all_disarmed && kprobe_disabled(p)) {
 		p->flags &= ~KPROBE_FLAG_DISABLED;
 		ret = arm_kprobe(p);
-		if (ret)
+		if (ret) {
 			p->flags |= KPROBE_FLAG_DISABLED;
+			if (p != kp)
+				kp->flags |= KPROBE_FLAG_DISABLED;
+		}
 	}
 out:
 	mutex_unlock(&kprobe_mutex);
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index 5bc349805..20277ad6b 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -563,9 +563,23 @@ void klp_reverse_transition(void)
 /* Called from copy_process() during fork */
 void klp_copy_process(struct task_struct *child)
 {
-	child->patch_state = current->patch_state;
 
-	/* TIF_PATCH_PENDING gets copied in setup_thread_stack() */
+	/*
+	 * The parent process may have gone through a KLP transition since
+	 * the thread flag was copied in setup_thread_stack earlier. Bring
+	 * the task flag up to date with the parent here.
+	 *
+	 * The operation is serialized against all klp_*_transition()
+	 * operations by the tasklist_lock. The only exception is
+	 * klp_update_patch_state(current), but we cannot race with
+	 * that because we are current.
+	 */
+	if (test_tsk_thread_flag(current, TIF_PATCH_PENDING))
+		set_tsk_thread_flag(child, TIF_PATCH_PENDING);
+	else
+		clear_tsk_thread_flag(child, TIF_PATCH_PENDING);
+
+	child->patch_state = current->patch_state;
 }
 
 /*
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 6abdfdf57..6737ae6ff 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -626,7 +626,7 @@ static void power_down(void)
 	int error;
 
 	if (hibernation_mode == HIBERNATION_SUSPEND) {
-		error = suspend_devices_and_enter(PM_SUSPEND_MEM);
+		error = suspend_devices_and_enter(mem_sleep_current);
 		if (error) {
 			hibernation_mode = hibernation_ops ?
 						HIBERNATION_PLATFORM :
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 93a7bd418..4bb194f09 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2081,13 +2081,14 @@ int proc_dostring(struct ctl_table *table, int write,
 			       (char __user *)buffer, lenp, ppos);
 }
 
-static size_t proc_skip_spaces(char **buf)
+static void proc_skip_spaces(char **buf, size_t *size)
 {
-	size_t ret;
-	char *tmp = skip_spaces(*buf);
-	ret = tmp - *buf;
-	*buf = tmp;
-	return ret;
+	while (*size) {
+		if (!isspace(**buf))
+			break;
+		(*size)--;
+		(*buf)++;
+	}
 }
 
 static void proc_skip_char(char **buf, size_t *size, const char v)
@@ -2156,13 +2157,12 @@ static int proc_get_long(char **buf, size_t *size,
 			  unsigned long *val, bool *neg,
 			  const char *perm_tr, unsigned perm_tr_len, char *tr)
 {
-	int len;
 	char *p, tmp[TMPBUFLEN];
+	ssize_t len = *size;
 
-	if (!*size)
+	if (len <= 0)
 		return -EINVAL;
 
-	len = *size;
 	if (len > TMPBUFLEN - 1)
 		len = TMPBUFLEN - 1;
 
@@ -2325,7 +2325,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
 		bool neg;
 
 		if (write) {
-			left -= proc_skip_spaces(&p);
+			proc_skip_spaces(&p, &left);
 
 			if (!left)
 				break;
@@ -2356,7 +2356,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
 	if (!write && !first && left && !err)
 		err = proc_put_char(&buffer, &left, '\n');
 	if (write && !err && left)
-		left -= proc_skip_spaces(&p);
+		proc_skip_spaces(&p, &left);
 	if (write) {
 		kfree(kbuf);
 		if (first)
@@ -2405,7 +2405,7 @@ static int do_proc_douintvec_w(unsigned int *tbl_data,
 	if (IS_ERR(kbuf))
 		return -EINVAL;
 
-	left -= proc_skip_spaces(&p);
+	proc_skip_spaces(&p, &left);
 	if (!left) {
 		err = -EINVAL;
 		goto out_free;
@@ -2425,7 +2425,7 @@ static int do_proc_douintvec_w(unsigned int *tbl_data,
 	}
 
 	if (!err && left)
-		left -= proc_skip_spaces(&p);
+		proc_skip_spaces(&p, &left);
 
 out_free:
 	kfree(kbuf);
@@ -2846,7 +2846,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
 		if (write) {
 			bool neg;
 
-			left -= proc_skip_spaces(&p);
+			proc_skip_spaces(&p, &left);
 			if (!left)
 				break;
 
@@ -2879,7 +2879,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
 	if (!write && !first && left && !err)
 		err = proc_put_char(&buffer, &left, '\n');
 	if (write && !err)
-		left -= proc_skip_spaces(&p);
+		proc_skip_spaces(&p, &left);
 	if (write) {
 		kfree(kbuf);
 		if (first)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index d2272fff2..9c7795566 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1331,6 +1331,7 @@ static int ftrace_add_mod(struct trace_array *tr,
 	if (!ftrace_mod)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&ftrace_mod->list);
 	ftrace_mod->func = kstrdup(func, GFP_KERNEL);
 	ftrace_mod->module = kstrdup(module, GFP_KERNEL);
 	ftrace_mod->enable = enable;
@@ -3033,7 +3034,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count)
 		/* if we can't allocate this size, try something smaller */
 		if (!order)
 			return -ENOMEM;
-		order >>= 1;
+		order--;
 		goto again;
 	}
 
@@ -5054,8 +5055,12 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 
 		if (filter_hash) {
 			orig_hash = &iter->ops->func_hash->filter_hash;
-			if (iter->tr && !list_empty(&iter->tr->mod_trace))
-				iter->hash->flags |= FTRACE_HASH_FL_MOD;
+			if (iter->tr) {
+				if (list_empty(&iter->tr->mod_trace))
+					iter->hash->flags &= ~FTRACE_HASH_FL_MOD;
+				else
+					iter->hash->flags |= FTRACE_HASH_FL_MOD;
+			}
 		} else
 			orig_hash = &iter->ops->func_hash->notrace_hash;
 
@@ -6225,7 +6230,7 @@ void __init ftrace_init(void)
 	}
 
 	pr_info("ftrace: allocating %ld entries in %ld pages\n",
-		count, count / ENTRIES_PER_PAGE + 1);
+		count, DIV_ROUND_UP(count, ENTRIES_PER_PAGE));
 
 	last_ftrace_enabled = ftrace_enabled = 1;
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 987d3447b..5e5b0c067 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -542,8 +542,9 @@ static void rb_wake_up_waiters(struct irq_work *work)
 	struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work);
 
 	wake_up_all(&rbwork->waiters);
-	if (rbwork->wakeup_full) {
+	if (rbwork->full_waiters_pending || rbwork->wakeup_full) {
 		rbwork->wakeup_full = false;
+		rbwork->full_waiters_pending = false;
 		wake_up_all(&rbwork->full_waiters);
 	}
 }
@@ -1327,9 +1328,9 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 
 	free_buffer_page(cpu_buffer->reader_page);
 
-	rb_head_page_deactivate(cpu_buffer);
-
 	if (head) {
+		rb_head_page_deactivate(cpu_buffer);
+
 		list_for_each_entry_safe(bpage, tmp, head, list) {
 			list_del_init(&bpage->list);
 			free_buffer_page(bpage);
@@ -2156,6 +2157,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 		/* Mark the rest of the page with padding */
 		rb_event_set_padding(event);
 
+		/* Make sure the padding is visible before the write update */
+		smp_wmb();
+
 		/* Set the write back to the previous setting */
 		local_sub(length, &tail_page->write);
 		return;
@@ -2167,6 +2171,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	/* time delta must be non zero */
 	event->time_delta = 1;
 
+	/* Make sure the padding is visible before the tail_page->write update */
+	smp_wmb();
+
 	/* Set write to end of buffer */
 	length = (tail + length) - BUF_PAGE_SIZE;
 	local_sub(length, &tail_page->write);
@@ -3812,6 +3819,33 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	arch_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 
+	/*
+	 * The writer has preempt disable, wait for it. But not forever
+	 * Although, 1 second is pretty much "forever"
+	 */
+#define USECS_WAIT	1000000
+        for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) {
+		/* If the write is past the end of page, a writer is still updating it */
+		if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE))
+			break;
+
+		udelay(1);
+
+		/* Get the latest version of the reader write value */
+		smp_rmb();
+	}
+
+	/* The writer is not moving forward? Something is wrong */
+	if (RB_WARN_ON(cpu_buffer, nr_loops == USECS_WAIT))
+		reader = NULL;
+
+	/*
+	 * Make sure we see any padding after the write update
+	 * (see rb_reset_tail())
+	 */
+	smp_rmb();
+
+
 	return reader;
 }
 
@@ -4770,7 +4804,15 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 		unsigned int pos = 0;
 		unsigned int size;
 
-		if (full)
+		/*
+		 * If a full page is expected, this can still be returned
+		 * if there's been a previous partial read and the
+		 * rest of the page can be read and the commit page is off
+		 * the reader page.
+		 */
+		if (full &&
+		    (!read || (len < (commit - read)) ||
+		     cpu_buffer->reader_page == cpu_buffer->commit_page))
 			goto out_unlock;
 
 		if (len > (commit - read))