Re: [PATCH 1/1] prctl.2: doc PR_SET/GET_IO_FLUSHER
From: Damien Le Moal <hidden>
Date: 2020-02-10 23:45:13
On 2020/02/11 7:16, Mike Christie wrote:
quoted hunk ↗ jump to hunk
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 [off-list ref] 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 <redacted> --- 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 <redacted>
quoted hunk ↗ jump to hunk
+.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