On 26.09.2018 15:25, Miklos Szeredi wrote:
> On Mon, Aug 27, 2018 at 06:29:56PM +0300, Kirill Tkhai wrote:
>> Currently, we take fc->lock there only to check for fc->connected.
>> But this flag is changed only on connection abort, which is very
>> rare operation. Good thing looks to make fuse_request_send_background()
>> faster, while fuse_abort_conn() slowler.
>>
>> So, we make fuse_request_send_background() lockless and mark
>> (fc->connected == 1) region as RCU-protected. Abort function
>> just uses synchronize_sched() to wait till all pending background
>> requests is being queued, and then makes ordinary abort.
>>
>> Note, that synchronize_sched() is used instead of synchronize_rcu(),
>> since we want to check for fc->connected without rcu_dereference()
>> in fuse_request_send_background() (i.e., not to add memory barriers
>> to this hot path).
>
> Apart from the inaccuracies in the above (_sched variant is for scheduling and
> NMI taking code; _sched variant requires rcu_dereference() as well;
> rcu_dereference() does not add barriers; rcu_dereference() is only for pointers,
> so we can't use it for an integer),
Writing this I was inspired by expand_fdtable(). Yes, the description confuses,
and we don't need rcu_dereference() since we do not touch memory pointed by __rcu
pointer, we have no pointer at all. synchronize_sched() guarantees:
On systems with more than one CPU, when synchronize_sched() returns,
each CPU is guaranteed to have executed a full memory barrier since the
end of its last RCU-sched read-side critical section whose beginning
preceded the call to synchronize_sched().
(and rcu_dereference() unfolds in smp_read_barrier_depends(), which I mean as
added barriers)
But it does not so matter. I'm OK with the patch you updated.
>wouldn't it be simpler to just use bg_lock
> for checking ->connected, and lock bg_lock (as well as fc->lock) when setting
> ->connected?
>
> Updated patch below (untested).
Tested it. Works for me.
Thanks,
Kirill
>
> ---
> Subject: fuse: do not take fc->lock in fuse_request_send_background()
> From: Kirill Tkhai <ktkhai@xxxxxxxxxxxxx>
> Date: Mon, 27 Aug 2018 18:29:56 +0300
>
> Currently, we take fc->lock there only to check for fc->connected.
> But this flag is changed only on connection abort, which is very
> rare operation.
>
> Signed-off-by: Kirill Tkhai <ktkhai@xxxxxxxxxxxxx>
> Signed-off-by: Miklos Szeredi <mszeredi@xxxxxxxxxx>
> ---
> fs/fuse/dev.c | 46 +++++++++++++++++++++++-----------------------
> fs/fuse/file.c | 4 +++-
> fs/fuse/fuse_i.h | 4 +---
> 3 files changed, 27 insertions(+), 27 deletions(-)
>
> --- a/fs/fuse/dev.c
> +++ b/fs/fuse/dev.c
> @@ -574,42 +574,38 @@ ssize_t fuse_simple_request(struct fuse_
> return ret;
> }
>
> -/*
> - * Called under fc->lock
> - *
> - * fc->connected must have been checked previously
> - */
> -void fuse_request_send_background_nocheck(struct fuse_conn *fc,
> - struct fuse_req *req)
> +bool fuse_request_queue_background(struct fuse_conn *fc, struct fuse_req *req)
> {
> - BUG_ON(!test_bit(FR_BACKGROUND, &req->flags));
> + bool queued = false;
> +
> + WARN_ON(!test_bit(FR_BACKGROUND, &req->flags));
> if (!test_bit(FR_WAITING, &req->flags)) {
> __set_bit(FR_WAITING, &req->flags);
> atomic_inc(&fc->num_waiting);
> }
> __set_bit(FR_ISREPLY, &req->flags);
> spin_lock(&fc->bg_lock);
> - fc->num_background++;
> - if (fc->num_background == fc->max_background)
> - fc->blocked = 1;
> - if (fc->num_background == fc->congestion_threshold && fc->sb) {
> - set_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
> - set_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
> + if (likely(fc->connected)) {
> + fc->num_background++;
> + if (fc->num_background == fc->max_background)
> + fc->blocked = 1;
> + if (fc->num_background == fc->congestion_threshold && fc->sb) {
> + set_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
> + set_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
> + }
> + list_add_tail(&req->list, &fc->bg_queue);
> + flush_bg_queue(fc);
> + queued = true;
> }
> - list_add_tail(&req->list, &fc->bg_queue);
> - flush_bg_queue(fc);
> spin_unlock(&fc->bg_lock);
> +
> + return queued;
> }
>
> void fuse_request_send_background(struct fuse_conn *fc, struct fuse_req *req)
> {
> - BUG_ON(!req->end);
> - spin_lock(&fc->lock);
> - if (fc->connected) {
> - fuse_request_send_background_nocheck(fc, req);
> - spin_unlock(&fc->lock);
> - } else {
> - spin_unlock(&fc->lock);
> + WARN_ON(!req->end);
> + if (!fuse_request_queue_background(fc, req)) {
> req->out.h.error = -ENOTCONN;
> req->end(fc, req);
> fuse_put_request(fc, req);
> @@ -2112,7 +2108,11 @@ void fuse_abort_conn(struct fuse_conn *f
> struct fuse_req *req, *next;
> LIST_HEAD(to_end);
>
> + /* Background queuing checks fc->connected under bg_lock */
> + spin_lock(&fc->bg_lock);
> fc->connected = 0;
> + spin_unlock(&fc->bg_lock);
> +
> fc->aborted = is_abort;
> fuse_set_initialized(fc);
> list_for_each_entry(fud, &fc->devices, entry) {
> --- a/fs/fuse/fuse_i.h
> +++ b/fs/fuse/fuse_i.h
> @@ -863,9 +863,7 @@ ssize_t fuse_simple_request(struct fuse_
> * Send a request in the background
> */
> void fuse_request_send_background(struct fuse_conn *fc, struct fuse_req *req);
> -
> -void fuse_request_send_background_nocheck(struct fuse_conn *fc,
> - struct fuse_req *req);
> +bool fuse_request_queue_background(struct fuse_conn *fc, struct fuse_req *req);
>
> /* Abort all requests */
> void fuse_abort_conn(struct fuse_conn *fc, bool is_abort);
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -1487,6 +1487,7 @@ __acquires(fc->lock)
> struct fuse_inode *fi = get_fuse_inode(req->inode);
> struct fuse_write_in *inarg = &req->misc.write.in;
> __u64 data_size = req->num_pages * PAGE_SIZE;
> + bool queued;
>
> if (!fc->connected)
> goto out_free;
> @@ -1502,7 +1503,8 @@ __acquires(fc->lock)
>
> req->in.args[1].size = inarg->size;
> fi->writectr++;
> - fuse_request_send_background_nocheck(fc, req);
> + queued = fuse_request_queue_background(fc, req);
> + WARN_ON(!queued);
> return;
>
> out_free:
>
