ANDROID: attribute page lock and waitqueue functions as sched

trace_sched_blocked_trace in CFS is really useful for debugging via
trace because it tell where the process was stuck on callstack.

For example,
           <...>-6143  ( 6136) [005] d..2    50.278987: sched_blocked_reason: pid=6136 iowait=0 caller=SyS_mprotect+0x88/0x208
           <...>-6136  ( 6136) [005] d..2    50.278990: sched_blocked_reason: pid=6142 iowait=0 caller=do_page_fault+0x1f4/0x3b0
           <...>-6142  ( 6136) [006] d..2    50.278996: sched_blocked_reason: pid=6144 iowait=0 caller=SyS_prctl+0x52c/0xb58
           <...>-6144  ( 6136) [006] d..2    50.279007: sched_blocked_reason: pid=6136 iowait=0 caller=vm_mmap_pgoff+0x74/0x104

However, sometime it gives pointless information like this.
    RenderThread-2322  ( 1805) [006] d.s3    50.319046: sched_blocked_reason: pid=6136 iowait=1 caller=__lock_page_killable+0x17c/0x220
     logd.writer-594   (  587) [002] d.s3    50.334011: sched_blocked_reason: pid=6126 iowait=1 caller=wait_on_page_bit+0x194/0x208
  kworker/u16:13-333   (  333) [007] d.s4    50.343161: sched_blocked_reason: pid=6136 iowait=1 caller=__lock_page_killable+0x17c/0x220

Such wait_on_page_bit, __lock_page_killable are pointless because it doesn't
carry on higher information to identify the callstack.

The reason is page_lock and waitqueue are special synchronization method unlike
other normal locks(mutex, spinlock).
Let's mark them as "__sched" so get_wchan which used in trace_sched_blocked_trace
could detect it and skip them. It will produce more meaningful callstack
function like this.

           <...>-2867  ( 1068) [002] d.h4   124.209701: sched_blocked_reason: pid=329 iowait=0 caller=worker_thread+0x378/0x470
           <...>-2867  ( 1068) [002] d.s3   124.209763: sched_blocked_reason: pid=8454 iowait=1 caller=__filemap_fdatawait_range+0xa0/0x104
           <...>-2867  ( 1068) [002] d.s4   124.209803: sched_blocked_reason: pid=869 iowait=0 caller=worker_thread+0x378/0x470
 ScreenDecoratio-2364  ( 1867) [002] d.s3   124.209973: sched_blocked_reason: pid=8454 iowait=1 caller=f2fs_wait_on_page_writeback+0x84/0xcc
 ScreenDecoratio-2364  ( 1867) [002] d.s4   124.209986: sched_blocked_reason: pid=869 iowait=0 caller=worker_thread+0x378/0x470
           <...>-329   (  329) [000] d..3   124.210435: sched_blocked_reason: pid=538 iowait=0 caller=worker_thread+0x378/0x470
  kworker/u16:13-538   (  538) [007] d..3   124.210450: sched_blocked_reason: pid=6 iowait=0 caller=worker_thread+0x378/0x470

Test: build pass and boot to home.
Bug: 144961676
Bug: 144713689
Bug: 172212772
Signed-off-by: Minchan Kim <minchan@google.com>
Signed-off-by: Jimmy Shiu <jimmyshiu@google.com>
Change-Id: I9c738802a16941ca767dcc37ae4463070b3fabf4
(cherry picked from commit 1e4de875d9e0cfaccf5131bcc709ae8646cdc168)
Signed-off-by: Will McVicker <willmcvicker@google.com>
This commit is contained in:
Jimmy Shiu
2020-11-03 00:16:37 +08:00
committed by Quentin Perret
parent 147a9b3d9e
commit dec0fd4a03
3 changed files with 19 additions and 16 deletions

View File

@@ -1189,7 +1189,7 @@ static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
/* How many times do we accept lock stealing from under a waiter? */
int sysctl_page_lock_unfairness = 5;
static inline int wait_on_page_bit_common(wait_queue_head_t *q,
static inline __sched int wait_on_page_bit_common(wait_queue_head_t *q,
struct page *page, int bit_nr, int state, enum behavior behavior)
{
int unfairness = sysctl_page_lock_unfairness;
@@ -1328,14 +1328,14 @@ repeat:
return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR;
}
void wait_on_page_bit(struct page *page, int bit_nr)
__sched void wait_on_page_bit(struct page *page, int bit_nr)
{
wait_queue_head_t *q = page_waitqueue(page);
wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED);
}
EXPORT_SYMBOL(wait_on_page_bit);
int wait_on_page_bit_killable(struct page *page, int bit_nr)
__sched int wait_on_page_bit_killable(struct page *page, int bit_nr)
{
wait_queue_head_t *q = page_waitqueue(page);
return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED);
@@ -1532,7 +1532,7 @@ EXPORT_SYMBOL_GPL(page_endio);
* __lock_page - get a lock on the page, assuming we need to sleep to get it
* @__page: the page to lock
*/
void __lock_page(struct page *__page)
__sched void __lock_page(struct page *__page)
{
struct page *page = compound_head(__page);
wait_queue_head_t *q = page_waitqueue(page);
@@ -1541,7 +1541,7 @@ void __lock_page(struct page *__page)
}
EXPORT_SYMBOL(__lock_page);
int __lock_page_killable(struct page *__page)
__sched int __lock_page_killable(struct page *__page)
{
struct page *page = compound_head(__page);
wait_queue_head_t *q = page_waitqueue(page);
@@ -1550,7 +1550,7 @@ int __lock_page_killable(struct page *__page)
}
EXPORT_SYMBOL_GPL(__lock_page_killable);
int __lock_page_async(struct page *page, struct wait_page_queue *wait)
__sched int __lock_page_async(struct page *page, struct wait_page_queue *wait)
{
return __wait_on_page_locked_async(page, wait, true);
}
@@ -1566,7 +1566,7 @@ int __lock_page_async(struct page *page, struct wait_page_queue *wait)
* If neither ALLOW_RETRY nor KILLABLE are set, will always return 1
* with the page locked and the mmap_lock unperturbed.
*/
int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
__sched int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
unsigned int flags)
{
if (fault_flag_allow_retry_first(flags)) {