[RFC PATCH -next] mm: fix softlockup by replacing tasklist_lock with RCU in for_each_process()

[Tong Tiangen]

We found a softlock issue in our test, analyzed the logs, and found that
the relevant CPU call trace as follows:

CPU0:
  _do_fork
    -> copy_process()
      -> write_lock_irq(&tasklist_lock)  //Disable irq,waiting for
      					 //tasklist_lock

CPU1:
  wp_page_copy()
    ->pte_offset_map_lock()
      -> spin_lock(&page->ptl);        //Hold page->ptl
    -> ptep_clear_flush()
      -> flush_tlb_others() ...
        -> smp_call_function_many()
          -> arch_send_call_function_ipi_mask()
            -> csd_lock_wait()         //Waiting for other CPUs respond
	                               //IPI

CPU2:
  collect_procs_anon()
    -> read_lock(&tasklist_lock)       //Hold tasklist_lock
      ->for_each_process(tsk)
        -> page_mapped_in_vma()
          -> page_vma_mapped_walk()
	    -> map_pte()
              ->spin_lock(&page->ptl)  //Waiting for page->ptl

We can see that CPU1 waiting for CPU0 respond IPI，CPU0 waiting for CPU2
unlock tasklist_lock, CPU2 waiting for CPU1 unlock page->ptl. As a result,
softlockup is triggered.

For collect_procs_anon(), we will not modify the tasklist, but only perform
read traversal. Therefore, we can use rcu lock instead of spin lock
tasklist_lock, from this, we can break the softlock chain above.

The same logic can also be applied to:
 - collect_procs_file()
 - collect_procs_fsdax()
 - collect_procs_ksm()
 - find_early_kill_thread()

Signed-off-by: Tong Tiangen <tongtiangen@xxxxxxxxxx>
---
 mm/ksm.c            |  4 ++--
 mm/memory-failure.c | 36 ++++++++++++++++++++++--------------
 2 files changed, 24 insertions(+), 16 deletions(-)

diff --git a/mm/ksm.c b/mm/ksm.c
index 6b7b8928fb96..dcbc0c7f68e7 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2919,7 +2919,7 @@ void collect_procs_ksm(struct page *page, struct list_head *to_kill,
 		struct anon_vma *av = rmap_item->anon_vma;
 
 		anon_vma_lock_read(av);
-		read_lock(&tasklist_lock);
+		rcu_read_lock();
 		for_each_process(tsk) {
 			struct anon_vma_chain *vmac;
 			unsigned long addr;
@@ -2938,7 +2938,7 @@ void collect_procs_ksm(struct page *page, struct list_head *to_kill,
 				}
 			}
 		}
-		read_unlock(&tasklist_lock);
+		rcu_read_unlock();
 		anon_vma_unlock_read(av);
 	}
 }
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 7b01fffe7a79..6a02706043f4 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -546,24 +546,32 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail,
  * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO)
  * on behalf of the thread group. Return task_struct of the (first found)
  * dedicated thread if found, and return NULL otherwise.
- *
- * We already hold read_lock(&tasklist_lock) in the caller, so we don't
- * have to call rcu_read_lock/unlock() in this function.
  */
 static struct task_struct *find_early_kill_thread(struct task_struct *tsk)
 {
 	struct task_struct *t;
+	bool find = false;
 
+	rcu_read_lock();
 	for_each_thread(tsk, t) {
 		if (t->flags & PF_MCE_PROCESS) {
-			if (t->flags & PF_MCE_EARLY)
-				return t;
+			if (t->flags & PF_MCE_EARLY) {
+				find = true;
+				break;
+			}
 		} else {
-			if (sysctl_memory_failure_early_kill)
-				return t;
+			if (sysctl_memory_failure_early_kill) {
+				find = true;
+				break;
+			}
 		}
 	}
-	return NULL;
+	rcu_read_unlock();
+
+	if (!find)
+		t = NULL;
+
+	return t;
 }
 
 /*
@@ -609,7 +617,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 		return;
 
 	pgoff = page_to_pgoff(page);
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	for_each_process(tsk) {
 		struct anon_vma_chain *vmac;
 		struct task_struct *t = task_early_kill(tsk, force_early);
@@ -626,7 +634,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 			add_to_kill_anon_file(t, page, vma, to_kill);
 		}
 	}
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 	anon_vma_unlock_read(av);
 }
 
@@ -642,7 +650,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	pgoff_t pgoff;
 
 	i_mmap_lock_read(mapping);
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	pgoff = page_to_pgoff(page);
 	for_each_process(tsk) {
 		struct task_struct *t = task_early_kill(tsk, force_early);
@@ -662,7 +670,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 				add_to_kill_anon_file(t, page, vma, to_kill);
 		}
 	}
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 	i_mmap_unlock_read(mapping);
 }
 
@@ -685,7 +693,7 @@ static void collect_procs_fsdax(struct page *page,
 	struct task_struct *tsk;
 
 	i_mmap_lock_read(mapping);
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	for_each_process(tsk) {
 		struct task_struct *t = task_early_kill(tsk, true);
 
@@ -696,7 +704,7 @@ static void collect_procs_fsdax(struct page *page,
 				add_to_kill_fsdax(t, page, vma, to_kill, pgoff);
 		}
 	}
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 	i_mmap_unlock_read(mapping);
 }
 #endif /* CONFIG_FS_DAX */
-- 
2.25.1