On 2020/02/11 7:16, Mike Christie wrote:
> This patch documents the PR_SET_IO_FLUSHER and PR_GET_IO_FLUSHER
> prctl commands added to the linux kernel for 5.6 in commit:
>
> commit 8d19f1c8e1937baf74e1962aae9f90fa3aeab463
> Author: Mike Christie <mchristi@xxxxxxxxxx>
> Date: Mon Nov 11 18:19:00 2019 -0600
>
> prctl: PR_{G,S}ET_IO_FLUSHER to support controlling memory reclaim
>
> Signed-off-by: Mike Christie <mchristi@xxxxxxxxxx>
> ---
>
> V2:
> - My initial patch for this was very bad. This version is almost 100%
> taken word for word from Dave Chinner's review comments.
>
>
> man2/prctl.2 | 25 +++++++++++++++++++++++++
> 1 file changed, 25 insertions(+)
>
> diff --git a/man2/prctl.2 b/man2/prctl.2
> index 720ec04e4..b481d186b 100644
> --- a/man2/prctl.2
> +++ b/man2/prctl.2
> @@ -1381,6 +1381,30 @@ system call on Tru64).
> for information on versions and architectures.)
> Return unaligned access control bits, in the location pointed to by
> .IR "(unsigned int\ *) arg2" .
> +.TP
> +.B PR_SET_IO_FLUSHER (Since Linux 5.6)
> +An IO_FLUSHER is a user process that the kernel uses to issue IO
> +that cleans dirty page cache data and/or filesystem metadata. The
> +kernel may need to clean this memory when under memory pressure in
> +order to free it. This means there is potential for a memory reclaim
> +recursion deadlock if the user process attempts to allocate memory
> +and the kernel then blocks waiting for it to clean memory before it
> +can make reclaim progress.
> +
> +The kernel avoids these recursion problems internally via a special
> +process state that prevents recursive reclaim from issuing new IO.
> +If \fIarg2\fP is 1, the \fPPR_SET_IO_FLUSHER\fP control allows a userspace
> +process to set up this same process state and hence avoid the memory
> +reclaim recursion deadlocks in the same manner the kernel avoids them.
> +If \fIarg2\fP is 0, the process will clear the IO_FLUSHER state, and the
> +default behavior will be used.
> +
> +Examples of IO_FLUSHER applications are FUSE daemons, zoned disk
> +emulation daemons, etc."
I would replace the "zoned disk emulation daemons" part with the more
general "SCSI device emulation daemons" since for tcmu-runner at least,
most emulation handlers can potentially trigger the reclaim deadlock (e.g.
file_handler).
Apart from that, this looks good to me.
Reviewed-by: Damien Le Moal <damien.lemoal@xxxxxxx>
> +.TP
> +.B PR_GET_IO_FLUSHER (Since Linux 5.6)
> +Return as the function result 1 if the caller is in the IO_FLUSHER state and
> +0 if not.
> .SH RETURN VALUE
> On success,
> .BR PR_GET_DUMPABLE ,
> @@ -1395,6 +1419,7 @@ On success,
> .BR PR_GET_SPECULATION_CTRL ,
> .BR PR_MCE_KILL_GET ,
> .BR PR_CAP_AMBIENT + PR_CAP_AMBIENT_IS_SET ,
> +.BR PR_GET_IO_FLUSHER ,
> and (if it returns)
> .BR PR_GET_SECCOMP
> return the nonnegative values described above.
>
--
Damien Le Moal
Western Digital Research
