Hi,
Based on my browsing through the kernel code, it appears that the
page->wait queue is not protected by any spinlocks. This means that
multiple processes running on SMP can simultaneously call "wait_on_page".
If the page is locked already, those processes would all be
put into the wait queue. Without a spinlock to protect the page wait queue
access, the queue can be messed up. Is this correct? Am I missing
anything here?
I have not seen any problems that may be caused by this, but this probably
doesn't mean that the problem does not exist.
I'd appreciate any clarifications. It's certainly highly likely that I made
a wrong observation here. Thanks in advance.
Ying
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sat Apr 15 2000 - 21:00:19 EST