Some architectures like arm64 and s390 require USER_DS to be set for
kernel threads to access user address space, which is the whole purpose of
kthread_use_mm, but other like x86 don't. That has lead to a huge mess
where some callers are fixed up once they are tested on said
architectures, while others linger around and yet other like io_uring try
to do "clever" optimizations for what usually is just a trivial asignment
to a member in the thread_struct for most architectures.
Make kthread_use_mm set USER_DS, and kthread_unuse_mm restore to the
previous value instead.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Felipe Balbi <balbi@kernel.org>
Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: http://lkml.kernel.org/r/20200404094101.672954-7-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
bool kiocb_has_eventfd = io_data->kiocb->ki_flags & IOCB_EVENTFD;
if (io_data->read && ret > 0) {
- mm_segment_t oldfs = get_fs();
-
- set_fs(USER_DS);
kthread_use_mm(io_data->mm);
ret = ffs_copy_to_iter(io_data->buf, ret, &io_data->data);
kthread_unuse_mm(io_data->mm);
- set_fs(oldfs);
}
io_data->kiocb->ki_complete(io_data->kiocb, ret, ret);
struct vhost_dev *dev = data;
struct vhost_work *work, *work_next;
struct llist_node *node;
- mm_segment_t oldfs = get_fs();
- set_fs(USER_DS);
kthread_use_mm(dev->mm);
for (;;) {
}
}
kthread_unuse_mm(dev->mm);
- set_fs(oldfs);
return 0;
}
dropped_lock = true;
}
__set_current_state(TASK_RUNNING);
- set_fs(KERNEL_DS);
kthread_unuse_mm(worker->mm);
mmput(worker->mm);
worker->mm = NULL;
mmput(worker->mm);
worker->mm = NULL;
}
- if (!work->mm) {
- set_fs(KERNEL_DS);
+ if (!work->mm)
return;
- }
+
if (mmget_not_zero(work->mm)) {
kthread_use_mm(work->mm);
- if (!worker->mm)
- set_fs(USER_DS);
worker->mm = work->mm;
/* hang on to this mm */
work->mm = NULL;
{
struct io_ring_ctx *ctx = data;
const struct cred *old_cred;
- mm_segment_t old_fs;
DEFINE_WAIT(wait);
unsigned long timeout;
int ret = 0;
complete(&ctx->sq_thread_comp);
- old_fs = get_fs();
- set_fs(USER_DS);
old_cred = override_creds(ctx->creds);
timeout = jiffies + ctx->sq_thread_idle;
if (current->task_works)
task_work_run();
- set_fs(old_fs);
io_sq_thread_drop_mm(ctx);
revert_creds(old_cred);
unsigned long flags;
unsigned int cpu;
void *data;
+ mm_segment_t oldfs;
struct completion parked;
struct completion exited;
#ifdef CONFIG_BLK_CGROUP
if (active_mm != mm)
mmdrop(active_mm);
+
+ to_kthread(tsk)->oldfs = get_fs();
+ set_fs(USER_DS);
}
EXPORT_SYMBOL_GPL(kthread_use_mm);
WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD));
WARN_ON_ONCE(!tsk->mm);
+ set_fs(to_kthread(tsk)->oldfs);
+
task_lock(tsk);
sync_mm_rss(mm);
tsk->mm = NULL;