delayacct: support re-entrance detection of thrashing accounting

Once upon a time, we only support accounting thrashing of page cache. 
Then Joonsoo introduced workingset detection for anonymous pages and we
gained the ability to account thrashing of them[1].

For page cache thrashing accounting, there is no suitable place to do it
in fs level likes swap_readpage().  So we have to do it in
folio_wait_bit_common().

Then for anonymous pages thrashing accounting, we have to do it in both
swap_readpage() and folio_wait_bit_common().  This likes PSI, so we should
let thrashing accounting supports re-entrance detection.

This patch is to prepare complete thrashing accounting, and is based on
patch "filemap: make the accounting of thrashing more consistent".

[1] commit aae466b0 ("mm/swap: implement workingset detection for anonymous LRU")

Link: https://lkml.kernel.org/r/20220815071134.74551-1-yang.yang29@zte.com.cnSigned-off-by: Yang Yang <yang.yang29@zte.com.cn>
Signed-off-by: CGEL ZTE <cgel.zte@gmail.com>
Reviewed-by: Ran Xiaokai <ran.xiaokai@zte.com.cn>
Reviewed-by: wangyong <wang.yong12@zte.com.cn>
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/delayacct.h

@@ -73,8 +73,8 @@ extern int delayacct_add_tsk(struct taskstats *, struct task_struct *);
 extern __u64 __delayacct_blkio_ticks(struct task_struct *);
 extern void __delayacct_freepages_start(void);
 extern void __delayacct_freepages_end(void);
-extern void __delayacct_thrashing_start(void);
-extern void __delayacct_thrashing_end(void);
+extern void __delayacct_thrashing_start(bool *in_thrashing);
+extern void __delayacct_thrashing_end(bool *in_thrashing);
 extern void __delayacct_swapin_start(void);
 extern void __delayacct_swapin_end(void);
 extern void __delayacct_compact_start(void);
@@ -143,22 +143,22 @@ static inline void delayacct_freepages_end(void)
 		__delayacct_freepages_end();
 }
 
-static inline void delayacct_thrashing_start(void)
+static inline void delayacct_thrashing_start(bool *in_thrashing)
 {
 	if (!static_branch_unlikely(&delayacct_key))
 		return;
 
 	if (current->delays)
-		__delayacct_thrashing_start();
+		__delayacct_thrashing_start(in_thrashing);
 }
 
-static inline void delayacct_thrashing_end(void)
+static inline void delayacct_thrashing_end(bool *in_thrashing)
 {
 	if (!static_branch_unlikely(&delayacct_key))
 		return;
 
 	if (current->delays)
-		__delayacct_thrashing_end();
+		__delayacct_thrashing_end(in_thrashing);
 }
 
 static inline void delayacct_swapin_start(void)
@@ -237,9 +237,9 @@ static inline void delayacct_freepages_start(void)
 {}
 static inline void delayacct_freepages_end(void)
 {}
-static inline void delayacct_thrashing_start(void)
+static inline void delayacct_thrashing_start(bool *in_thrashing)
 {}
-static inline void delayacct_thrashing_end(void)
+static inline void delayacct_thrashing_end(bool *in_thrashing)
 {}
 static inline void delayacct_swapin_start(void)
 {}

include/linux/sched.h

@@ -944,6 +944,10 @@ struct task_struct {
 #ifdef	CONFIG_CPU_SUP_INTEL
 	unsigned			reported_split_lock:1;
 #endif
+#ifdef CONFIG_TASK_DELAY_ACCT
+	/* delay due to memory thrashing */
+	unsigned                        in_thrashing:1;
+#endif
 
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 

kernel/delayacct.c

@@ -214,13 +214,22 @@ void __delayacct_freepages_end(void)
 		      &current->delays->freepages_count);
 }
 
-void __delayacct_thrashing_start(void)
+void __delayacct_thrashing_start(bool *in_thrashing)
 {
+	*in_thrashing = !!current->in_thrashing;
+	if (*in_thrashing)
+		return;
+
+	current->in_thrashing = 1;
 	current->delays->thrashing_start = local_clock();
 }
 
-void __delayacct_thrashing_end(void)
+void __delayacct_thrashing_end(bool *in_thrashing)
 {
+	if (*in_thrashing)
+		return;
+
+	current->in_thrashing = 0;
 	delayacct_end(&current->delays->lock,
 		      &current->delays->thrashing_start,
 		      &current->delays->thrashing_delay,

mm/filemap.c

@@ -1222,10 +1222,11 @@ static inline int folio_wait_bit_common(struct folio *folio, int bit_nr,
 	wait_queue_entry_t *wait = &wait_page.wait;
 	bool thrashing = false;
 	unsigned long pflags;
+	bool in_thrashing;
 
 	if (bit_nr == PG_locked &&
 	    !folio_test_uptodate(folio) && folio_test_workingset(folio)) {
-		delayacct_thrashing_start();
+		delayacct_thrashing_start(&in_thrashing);
 		psi_memstall_enter(&pflags);
 		thrashing = true;
 	}
@@ -1325,7 +1326,7 @@ static inline int folio_wait_bit_common(struct folio *folio, int bit_nr,
 	finish_wait(q, wait);
 
 	if (thrashing) {
-		delayacct_thrashing_end();
+		delayacct_thrashing_end(&in_thrashing);
 		psi_memstall_leave(&pflags);
 	}
 
@@ -1374,12 +1375,13 @@ void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep,
 	wait_queue_entry_t *wait = &wait_page.wait;
 	bool thrashing = false;
 	unsigned long pflags;
+	bool in_thrashing;
 	wait_queue_head_t *q;
 	struct folio *folio = page_folio(pfn_swap_entry_to_page(entry));
 
 	q = folio_waitqueue(folio);
 	if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) {
-		delayacct_thrashing_start();
+		delayacct_thrashing_start(&in_thrashing);
 		psi_memstall_enter(&pflags);
 		thrashing = true;
 	}
@@ -1426,7 +1428,7 @@ void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep,
 	finish_wait(q, wait);
 
 	if (thrashing) {
-		delayacct_thrashing_end();
+		delayacct_thrashing_end(&in_thrashing);
 		psi_memstall_leave(&pflags);
 	}
 }