io-uring.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Pavel Begunkov <asml.silence@gmail.com>
To: Bijan Mottahedeh <bijan.mottahedeh@oracle.com>,
	axboe@kernel.dk, io-uring@vger.kernel.org
Subject: Re: [PATCH v3 08/13] io_uring: implement fixed buffers registration similar to fixed files
Date: Tue, 5 Jan 2021 02:43:25 +0000	[thread overview]
Message-ID: <f0bff3b0-f27e-80fe-9a58-dfeb347a7e61@gmail.com> (raw)
In-Reply-To: <1608314848-67329-9-git-send-email-bijan.mottahedeh@oracle.com>

On 18/12/2020 18:07, Bijan Mottahedeh wrote:
> Apply fixed_rsrc functionality for fixed buffers support.

git generated a pretty messy diff...

Because it's do quiesce, fixed read/write access buffers from asynchronous
contexts without synchronisation. That won't work anymore, so

1. either we save it in advance, that would require extra req_async
allocation for linked fixed rw

2. or synchronise whenever async. But that would mean that a request
may get and do IO on two different buffers, that's rotten.

3. do mixed -- lazy, but if do IO then alloc.

3.5 also "synchronise" there would mean uring_lock, that's not welcome,
but we can probably do rcu.

Let me think of a patch...

[...]
> @@ -8373,7 +8433,13 @@ static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages,
>  
>  	/* check previously registered pages */
>  	for (i = 0; i < ctx->nr_user_bufs; i++) {
> -		struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
> +		struct fixed_rsrc_table *table;
> +		struct io_mapped_ubuf *imu;
> +		unsigned int index;
> +
> +		table = &ctx->buf_data->table[i >> IORING_BUF_TABLE_SHIFT];
> +		index = i & IORING_BUF_TABLE_MASK;
> +		imu = &table->bufs[index];

io_buf_from_index() may tak buf_data, so can be reused.

>  
>  		for (j = 0; j < imu->nr_bvecs; j++) {
>  			if (!PageCompound(imu->bvec[j].bv_page))
> @@ -8508,19 +8574,79 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
>  	return ret;
>  }
>  
> -static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args)
> +static void io_free_buf_tables(struct fixed_rsrc_data *buf_data,
> +			       unsigned int nr_tables)
>  {
> -	if (ctx->user_bufs)
> -		return -EBUSY;
> -	if (!nr_args || nr_args > UIO_MAXIOV)
> -		return -EINVAL;
> +	int i;
>  
> -	ctx->user_bufs = kcalloc(nr_args, sizeof(struct io_mapped_ubuf),
> -					GFP_KERNEL);
> -	if (!ctx->user_bufs)
> -		return -ENOMEM;
> +	for (i = 0; i < nr_tables; i++) {
> +		struct fixed_rsrc_table *table = &buf_data->table[i];
>  
> -	return 0;
> +		kfree(table->bufs);
> +	}
> +}
> +
> +static int io_alloc_buf_tables(struct fixed_rsrc_data *buf_data,
> +			       unsigned int nr_tables, unsigned int nr_bufs)
> +{
> +	int i;
> +		

trailing tabs

> +	for (i = 0; i < nr_tables; i++) {
> +		struct fixed_rsrc_table *table = &buf_data->table[i];
> +		unsigned int this_bufs;
> +
> +		this_bufs = min(nr_bufs, IORING_MAX_BUFS_TABLE);
> +		table->bufs = kcalloc(this_bufs, sizeof(struct io_mapped_ubuf),
> +				      GFP_KERNEL);
> +		if (!table->bufs)
> +			break;
> +		nr_bufs -= this_bufs;
> +	}
> +
> +	if (i == nr_tables)
> +		return 0;
> +
> +	io_free_buf_tables(buf_data, nr_tables);

Would work because kcalloc() zeroed buf_data->table, but

io_free_buf_tables(buf_data, __i__);

> +	return 1;
> +}
> +
[...]
>  static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
>  				   unsigned int nr_args)
>  {
>  	int i, ret;
>  	struct iovec iov;
>  	struct page *last_hpage = NULL;
> +	struct fixed_rsrc_ref_node *ref_node;
> +	struct fixed_rsrc_data *buf_data;
>  
> -	ret = io_buffers_map_alloc(ctx, nr_args);
> -	if (ret)
> -		return ret;
> +	if (ctx->nr_user_bufs)
> +		return -EBUSY;
>  
> -	for (i = 0; i < nr_args; i++) {
> -		struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
> +	buf_data = io_buffers_map_alloc(ctx, nr_args);
> +	if (IS_ERR(buf_data))
> +		return PTR_ERR(buf_data);
> +
> +	for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) {
> +		struct fixed_rsrc_table *table;
> +		struct io_mapped_ubuf *imu;
> +		unsigned int index;
>  
>  		ret = io_copy_iov(ctx, &iov, arg, i);
>  		if (ret)
>  			break;
>  
> +		/* allow sparse sets */
> +		if (!iov.iov_base && !iov.iov_len)
> +			continue;
> +
>  		ret = io_buffer_validate(&iov);
>  		if (ret)
>  			break;
>  
> +		table = &buf_data->table[i >> IORING_BUF_TABLE_SHIFT];

same, io_buf_from_index() can be reused

> +		index = i & IORING_BUF_TABLE_MASK;
> +		imu = &table->bufs[index];
> +
>  		ret = io_sqe_buffer_register(ctx, &iov, imu, &last_hpage);
>  		if (ret)
>  			break;
> +	}
>  
[...]
> @@ -9854,6 +10023,7 @@ static bool io_register_op_must_quiesce(int op)
>  	switch (op) {
>  	case IORING_UNREGISTER_FILES:
>  	case IORING_REGISTER_FILES_UPDATE:
> +	case IORING_UNREGISTER_BUFFERS:

what about REGISTER_BUFFERS? 

>  	case IORING_REGISTER_PROBE:
>  	case IORING_REGISTER_PERSONALITY:
>  	case IORING_UNREGISTER_PERSONALITY:
> 

-- 
Pavel Begunkov

  reply	other threads:[~2021-01-05  2:47 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-18 18:07 [PATCH v3 00/13] io_uring: buffer registration enhancements Bijan Mottahedeh
2020-12-18 18:07 ` [PATCH v3 01/13] io_uring: modularize io_sqe_buffer_register Bijan Mottahedeh
2021-01-04 21:54   ` Pavel Begunkov
2021-01-06 19:46     ` Bijan Mottahedeh
2020-12-18 18:07 ` [PATCH v3 02/13] io_uring: modularize io_sqe_buffers_register Bijan Mottahedeh
2021-01-04 21:48   ` Pavel Begunkov
2020-12-18 18:07 ` [PATCH v3 03/13] io_uring: rename file related variables to rsrc Bijan Mottahedeh
2021-01-05  1:53   ` Pavel Begunkov
2021-01-06 19:46     ` Bijan Mottahedeh
2020-12-18 18:07 ` [PATCH v3 04/13] io_uring: generalize io_queue_rsrc_removal Bijan Mottahedeh
2020-12-18 18:07 ` [PATCH v3 05/13] io_uring: separate ref_list from fixed_rsrc_data Bijan Mottahedeh
2020-12-18 18:07 ` [PATCH v3 06/13] io_uring: generalize fixed_file_ref_node functionality Bijan Mottahedeh
2020-12-18 18:07 ` [PATCH v3 07/13] io_uring: add rsrc_ref locking routines Bijan Mottahedeh
2020-12-18 18:07 ` [PATCH v3 08/13] io_uring: implement fixed buffers registration similar to fixed files Bijan Mottahedeh
2021-01-05  2:43   ` Pavel Begunkov [this message]
2021-01-06 19:46     ` Bijan Mottahedeh
2021-01-06 22:22       ` Pavel Begunkov
2021-01-07  2:37       ` Pavel Begunkov
2021-01-07 21:21         ` Bijan Mottahedeh
2021-01-07 21:37           ` Pavel Begunkov
2021-01-07 22:14             ` Bijan Mottahedeh
2021-01-07 22:33               ` Pavel Begunkov
2021-01-07 23:10                 ` Pavel Begunkov
2021-01-08  1:53                   ` Bijan Mottahedeh
2021-01-11  5:12                     ` Pavel Begunkov
2021-01-08  0:17                 ` Bijan Mottahedeh
2020-12-18 18:07 ` [PATCH v3 09/13] io_uring: create common fixed_rsrc_ref_node handling routines Bijan Mottahedeh
2020-12-18 18:07 ` [PATCH v3 10/13] io_uring: generalize files_update functionlity to rsrc_update Bijan Mottahedeh
2020-12-18 18:07 ` [PATCH v3 11/13] io_uring: support buffer registration updates Bijan Mottahedeh
2020-12-18 18:07 ` [PATCH v3 12/13] io_uring: create common fixed_rsrc_data allocation routines Bijan Mottahedeh
2020-12-18 18:07 ` [PATCH v3 13/13] io_uring: support buffer registration sharing Bijan Mottahedeh
2021-01-04 17:09 ` [PATCH v3 00/13] io_uring: buffer registration enhancements Bijan Mottahedeh

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=f0bff3b0-f27e-80fe-9a58-dfeb347a7e61@gmail.com \
    --to=asml.silence@gmail.com \
    --cc=axboe@kernel.dk \
    --cc=bijan.mottahedeh@oracle.com \
    --cc=io-uring@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).