Re: [PATCH v1] PM: suspend: clean up redundant filesystems_freeze/thaw handling

From: Zihuan Zhang
Date: Wed Jul 16 2025 - 20:37:57 EST



在 2025/7/16 20:23, Rafael J. Wysocki 写道:
On Wed, Jul 16, 2025 at 4:04 AM Zihuan Zhang <zhangzihuan@xxxxxxxxxx> wrote:

在 2025/7/15 20:48, Rafael J. Wysocki 写道:
On Tue, Jul 15, 2025 at 8:12 AM Zihuan Zhang <zhangzihuan@xxxxxxxxxx> wrote:
Hi Rafael,

在 2025/7/15 01:57, Rafael J. Wysocki 写道:
Hi,

On Mon, Jul 14, 2025 at 10:44 AM Zihuan Zhang <zhangzihuan@xxxxxxxxxx> wrote:
Hi Rafael,

Just a gentle ping on this patch.
I've lost track of it for some reason, sorry.

I realized I forgot to mention an important motivation in the changelog:
calling filesystems_freeze() twice (from both suspend_prepare() and
enter_state()) lead to a black screen and make the system unable to resume..

This patch avoids the duplicate call and resolves that issue.
Now applied as a fix for 6.16-rc7, thank you!
Thanks for the reply!

Just a quick follow-up question — we noticed that even when the “freeze
filesystems” feature is not enabled, the current code still calls
filesystems_thaw().

Do you think it would make sense to guard this with a static key (or
another mechanism) to avoid unnecessary overhead?
Possibly, if this overhead is significant, but is it?
We've done some testing using ftrace to measure the overhead of
filesystems_thaw(). When freeze_filesystems is not enabled, the overhead
is typically around 15–40 microseconds.
So this is the time that can be saved by adding a
filesystem_freeze_enabled check before calling filesystems_thaw()
IIUC.

I'd say don't bother.


Understood, thanks!


However, when freeze is enabled, we observed that filesystems_thaw() can
take over 3 seconds to complete (e.g., 3,450,644 us in one test case).

freeze_filesystems not enabled:

# tracer: function_graph
#
# CPU DURATION FUNCTION CALLS
# | | | | | | |
4) + 15.740 us | filesystems_thaw();
11) + 16.894 us | filesystems_thaw();
10) + 17.805 us | filesystems_thaw();
8) + 37.762 us | filesystems_thaw();
------------------------------------------
11) systemd-54512 => systemd-66433
------------------------------------------

11) + 15.167 us | filesystems_thaw();
6) + 16.760 us | filesystems_thaw();
7) + 14.870 us | filesystems_thaw();
3) + 16.171 us | filesystems_thaw();
1) + 16.461 us | filesystems_thaw();
------------------------------------------
3) systemd-71984 => systemd-73036
------------------------------------------

3) + 28.314 us | filesystems_thaw();

freeze_filesystems enabled:

10) | filesystems_thaw() {
2) $ 3450644 us | } /* filesystems_thaw */
------------------------------------------
1) systemd-72561 => systemd-99210
------------------------------------------

1) | filesystems_thaw() {
------------------------------------------
7) systemd-71501 => systemd-99210
------------------------------------------

7) $ 3429306 us | } /* filesystems_thaw */
------------------------------------------
7) systemd-99210 => systemd-100028
------------------------------------------

7) | filesystems_thaw() {
------------------------------------------
4) systemd-53278 => systemd-100028
------------------------------------------

4) $ 3270122 us | } /* filesystems_thaw */
------------------------------------------
7) systemd-100028 => systemd-100720
------------------------------------------

7) $ 3446496 us | filesystems_thaw();
------------------------------------------
7) systemd-100720 => systemd-112075
------------------------------------------

7) | filesystems_thaw() {
------------------------------------------
11) systemd-66433 => systemd-112075
------------------------------------------

11) $ 3454117 us | } /* filesystems_thaw */