diff options
author | Jan Kara <jack@suse.cz> | 2022-06-23 09:48:30 +0200 |
---|---|---|
committer | Jens Axboe <axboe@kernel.dk> | 2022-06-27 06:29:12 -0600 |
commit | 4b838d9ee950b37bee624e301bd8e923165b1cf3 (patch) | |
tree | 6c6bbd6120095074bc73b0fafe0de664a51e8da8 /block | |
parent | fc25545e17bd74befe0b8ab2c65ac84936be5066 (diff) | |
download | linux-4b838d9ee950b37bee624e301bd8e923165b1cf3.tar.gz linux-4b838d9ee950b37bee624e301bd8e923165b1cf3.tar.bz2 linux-4b838d9ee950b37bee624e301bd8e923165b1cf3.zip |
block: Fix handling of tasks without ioprio in ioprio_get(2)
ioprio_get(2) can be asked to return the best IO priority from several
tasks (IOPRIO_WHO_PGRP, IOPRIO_WHO_USER). Currently the call treats
tasks without set IO priority as having priority
IOPRIO_CLASS_BE/IOPRIO_BE_NORM however this does not really reflect the
IO priority the task will get (which depends on task's nice value).
Fix the code to use the real IO priority task's IO will use. We have to
modify code for ioprio_get(IOPRIO_WHO_PROCESS) to keep returning
IOPRIO_CLASS_NONE priority for tasks without set IO priority as a
special case to maintain userspace visible API.
Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Tested-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20220623074840.5960-5-jack@suse.cz
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block')
-rw-r--r-- | block/ioprio.c | 30 |
1 files changed, 23 insertions, 7 deletions
diff --git a/block/ioprio.c b/block/ioprio.c index 8c46f672a0ba..32a456b45804 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -171,10 +171,31 @@ static int get_task_ioprio(struct task_struct *p) ret = security_task_getioprio(p); if (ret) goto out; - ret = IOPRIO_DEFAULT; + task_lock(p); + ret = __get_task_ioprio(p); + task_unlock(p); +out: + return ret; +} + +/* + * Return raw IO priority value as set by userspace. We use this for + * ioprio_get(pid, IOPRIO_WHO_PROCESS) so that we keep historical behavior and + * also so that userspace can distinguish unset IO priority (which just gets + * overriden based on task's nice value) from IO priority set to some value. + */ +static int get_task_raw_ioprio(struct task_struct *p) +{ + int ret; + + ret = security_task_getioprio(p); + if (ret) + goto out; task_lock(p); if (p->io_context) ret = p->io_context->ioprio; + else + ret = IOPRIO_DEFAULT; task_unlock(p); out: return ret; @@ -182,11 +203,6 @@ out: static int ioprio_best(unsigned short aprio, unsigned short bprio) { - if (!ioprio_valid(aprio)) - aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_BE_NORM); - if (!ioprio_valid(bprio)) - bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_BE_NORM); - return min(aprio, bprio); } @@ -207,7 +223,7 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who) else p = find_task_by_vpid(who); if (p) - ret = get_task_ioprio(p); + ret = get_task_raw_ioprio(p); break; case IOPRIO_WHO_PGRP: if (!who) |