Merging upstream version 4.19.289.

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

8 files changed, 62 insertions, 21 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 61f3a31ab..a48de55f5 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5936,7 +5936,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 					insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH,
 									insn->dst_reg,
 									shift);
-				insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg,
+				insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg,
 								(1ULL << size * 8) - 1);
 			}
 		}
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index a8185cdb8..6322b5652 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1652,7 +1652,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 {
 	struct cgroup *dcgrp = &dst_root->cgrp;
 	struct cgroup_subsys *ss;
-	int ssid, i, ret;
+	int ssid, ret;
 	u16 dfl_disable_ss_mask = 0;
 
 	lockdep_assert_held(&cgroup_mutex);
@@ -1696,7 +1696,8 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 		struct cgroup_root *src_root = ss->root;
 		struct cgroup *scgrp = &src_root->cgrp;
 		struct cgroup_subsys_state *css = cgroup_css(scgrp, ss);
-		struct css_set *cset;
+		struct css_set *cset, *cset_pos;
+		struct css_task_iter *it;
 
 		WARN_ON(!css || cgroup_css(dcgrp, ss));
 
@@ -1714,9 +1715,22 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 		css->cgroup = dcgrp;
 
 		spin_lock_irq(&css_set_lock);
-		hash_for_each(css_set_table, i, cset, hlist)
+		WARN_ON(!list_empty(&dcgrp->e_csets[ss->id]));
+		list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id],
+					 e_cset_node[ss->id]) {
 			list_move_tail(&cset->e_cset_node[ss->id],
 				       &dcgrp->e_csets[ss->id]);
+			/*
+			 * all css_sets of scgrp together in same order to dcgrp,
+			 * patch in-flight iterators to preserve correct iteration.
+			 * since the iterator is always advanced right away and
+			 * finished when it->cset_pos meets it->cset_head, so only
+			 * update it->cset_head is enough here.
+			 */
+			list_for_each_entry(it, &cset->task_iters, iters_node)
+				if (it->cset_head == &scgrp->e_csets[ss->id])
+					it->cset_head = &dcgrp->e_csets[ss->id];
+		}
 		spin_unlock_irq(&css_set_lock);
 
 		/* default hierarchy doesn't enable controllers by default */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 72ed3f3d0..2bf4b6b10 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7843,8 +7843,8 @@ __perf_event_account_interrupt(struct perf_event *event, int throttle)
 		hwc->interrupts = 1;
 	} else {
 		hwc->interrupts++;
-		if (unlikely(throttle
-			     && hwc->interrupts >= max_samples_per_tick)) {
+		if (unlikely(throttle &&
+			     hwc->interrupts > max_samples_per_tick)) {
 			__this_cpu_inc(perf_throttled_count);
 			tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS);
 			hwc->interrupts = MAX_INTERRUPTS;
diff --git a/kernel/extable.c b/kernel/extable.c
index 6a5b61ebc..b3ca75d6b 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -46,7 +46,8 @@ u32 __initdata __visible main_extable_sort_needed = 1;
 /* Sort the kernel's built-in exception table */
 void __init sort_main_extable(void)
 {
-	if (main_extable_sort_needed && __stop___ex_table > __start___ex_table) {
+	if (main_extable_sort_needed &&
+	    &__stop___ex_table > &__start___ex_table) {
 		pr_notice("Sorting __ex_table...\n");
 		sort_extable(__start___ex_table, __stop___ex_table);
 	}
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index ab1934a2b..416c1e0fd 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -793,10 +793,22 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi,
 		}
 
 		offset = ALIGN(offset, align);
+
+		/*
+		 * Check if the segment contains the entry point, if so,
+		 * calculate the value of image->start based on it.
+		 * If the compiler has produced more than one .text section
+		 * (Eg: .text.hot), they are generally after the main .text
+		 * section, and they shall not be used to calculate
+		 * image->start. So do not re-calculate image->start if it
+		 * is not set to the initial value, and warn the user so they
+		 * have a chance to fix their purgatory's linker script.
+		 */
 		if (sechdrs[i].sh_flags & SHF_EXECINSTR &&
 		    pi->ehdr->e_entry >= sechdrs[i].sh_addr &&
 		    pi->ehdr->e_entry < (sechdrs[i].sh_addr
-					 + sechdrs[i].sh_size)) {
+					 + sechdrs[i].sh_size) &&
+		    !WARN_ON(kbuf->image->start != pi->ehdr->e_entry)) {
 			kbuf->image->start -= sechdrs[i].sh_addr;
 			kbuf->image->start += kbuf->mem + offset;
 		}
diff --git a/kernel/relay.c b/kernel/relay.c
index b7aa7df43..e6f70f4c4 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -997,14 +997,14 @@ static void relay_file_read_consume(struct rchan_buf *buf,
 /*
  *	relay_file_read_avail - boolean, are there unconsumed bytes available?
  */
-static int relay_file_read_avail(struct rchan_buf *buf, size_t read_pos)
+static int relay_file_read_avail(struct rchan_buf *buf)
 {
 	size_t subbuf_size = buf->chan->subbuf_size;
 	size_t n_subbufs = buf->chan->n_subbufs;
 	size_t produced = buf->subbufs_produced;
 	size_t consumed = buf->subbufs_consumed;
 
-	relay_file_read_consume(buf, read_pos, 0);
+	relay_file_read_consume(buf, 0, 0);
 
 	consumed = buf->subbufs_consumed;
 
@@ -1065,23 +1065,21 @@ static size_t relay_file_read_subbuf_avail(size_t read_pos,
 
 /**
  *	relay_file_read_start_pos - find the first available byte to read
- *	@read_pos: file read position
  *	@buf: relay channel buffer
  *
- *	If the @read_pos is in the middle of padding, return the
+ *	If the read_pos is in the middle of padding, return the
  *	position of the first actually available byte, otherwise
  *	return the original value.
  */
-static size_t relay_file_read_start_pos(size_t read_pos,
-					struct rchan_buf *buf)
+static size_t relay_file_read_start_pos(struct rchan_buf *buf)
 {
 	size_t read_subbuf, padding, padding_start, padding_end;
 	size_t subbuf_size = buf->chan->subbuf_size;
 	size_t n_subbufs = buf->chan->n_subbufs;
 	size_t consumed = buf->subbufs_consumed % n_subbufs;
+	size_t read_pos = (consumed * subbuf_size + buf->bytes_consumed)
+			% (n_subbufs * subbuf_size);
 
-	if (!read_pos)
-		read_pos = consumed * subbuf_size + buf->bytes_consumed;
 	read_subbuf = read_pos / subbuf_size;
 	padding = buf->padding[read_subbuf];
 	padding_start = (read_subbuf + 1) * subbuf_size - padding;
@@ -1137,10 +1135,10 @@ static ssize_t relay_file_read(struct file *filp,
 	do {
 		void *from;
 
-		if (!relay_file_read_avail(buf, *ppos))
+		if (!relay_file_read_avail(buf))
 			break;
 
-		read_start = relay_file_read_start_pos(*ppos, buf);
+		read_start = relay_file_read_start_pos(buf);
 		avail = relay_file_read_subbuf_avail(read_start, buf);
 		if (!avail)
 			break;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 48403fb65..25c6efa2c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -199,6 +199,11 @@ static bool check_tick_dependency(atomic_t *dep)
 		return true;
 	}
 
+	if (val & TICK_DEP_MASK_RCU) {
+		trace_tick_stop(0, TICK_DEP_MASK_RCU);
+		return true;
+	}
+
 	return false;
 }
 
@@ -325,6 +330,7 @@ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit)
 		preempt_enable();
 	}
 }
+EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu);
 
 void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
 {
@@ -332,6 +338,7 @@ void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
 
 	atomic_andnot(BIT(bit), &ts->tick_dep_mask);
 }
+EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu);
 
 /*
  * Set a per-task tick dependency. Posix CPU timers need this in order to elapse
@@ -399,7 +406,7 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask)
 	tick_nohz_full_running = true;
 }
 
-static int tick_nohz_cpu_down(unsigned int cpu)
+bool tick_nohz_cpu_hotpluggable(unsigned int cpu)
 {
 	/*
 	 * The boot CPU handles housekeeping duty (unbound timers,
@@ -407,8 +414,13 @@ static int tick_nohz_cpu_down(unsigned int cpu)
 	 * CPUs. It must remain online when nohz full is enabled.
 	 */
 	if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
-		return -EBUSY;
-	return 0;
+		return false;
+	return true;
+}
+
+static int tick_nohz_cpu_down(unsigned int cpu)
+{
+	return tick_nohz_cpu_hotpluggable(cpu) ? 0 : -EBUSY;
 }
 
 void __init tick_nohz_init(void)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 37fade510..ba8b72f9c 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1326,6 +1326,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 	struct list_head *head = cpu_buffer->pages;
 	struct buffer_page *bpage, *tmp;
 
+	irq_work_sync(&cpu_buffer->irq_work.work);
+
 	free_buffer_page(cpu_buffer->reader_page);
 
 	if (head) {
@@ -1431,6 +1433,8 @@ ring_buffer_free(struct ring_buffer *buffer)
 
 	cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
 
+	irq_work_sync(&buffer->irq_work.work);
+
 	for_each_buffer_cpu(buffer, cpu)
 		rb_free_cpu_buffer(buffer->buffers[cpu]);