All of lore.kernel.org
 help / color / mirror / Atom feed
From: Dave Kleikamp <dave.kleikamp-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
To: Ming Lei <ming.lei-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>,
	Jens Axboe <axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>,
	linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Cc: Zach Brown <zab-ugsP4Wv/S6ZeoWH0uzbU5w@public.gmane.org>,
	Christoph Hellwig <hch-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>,
	Maxim Patlasov
	<mpatlasov-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>,
	Andrew Morton
	<akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>,
	Alexander Viro
	<viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org>,
	Tejun Heo <tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
	Dave Chinner <david-FqsqvQoI3Ljby3iVrkZq2A@public.gmane.org>,
	linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH v8 4/6] block: loop: prepare for supporing direct IO
Date: Thu, 30 Jul 2015 10:30:55 -0500	[thread overview]
Message-ID: <55BA432F.3050603@oracle.com> (raw)
In-Reply-To: <1438256184-23645-5-git-send-email-ming.lei-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>

On 07/30/2015 06:36 AM, Ming Lei wrote:
> This patches provides one interface for enabling direct IO
> from user space:
> 
> 	- userspace(such as losetup) can pass 'file' which is
> 	opened/fcntl as O_DIRECT
> 
> Also __loop_update_dio() is introduced to check if direct I/O
> can be used on current loop setting.
> 
> The last big change is to introduce LO_FLAGS_DIRECT_IO flag
> for userspace to know if direct IO is used to access backing
> file.

lo->use_dio and LO_FLAGS_DIRECT_IO seem redundant. Wouldn't it be
simpler to use one or the other?

> 
> Cc: linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> Signed-off-by: Ming Lei <ming.lei-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>
> ---
>  drivers/block/loop.c      | 63 ++++++++++++++++++++++++++++++++++++++++++++++-
>  drivers/block/loop.h      |  2 ++
>  include/uapi/linux/loop.h |  1 +
>  3 files changed, 65 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/block/loop.c b/drivers/block/loop.c
> index 1875aad..799cc23 100644
> --- a/drivers/block/loop.c
> +++ b/drivers/block/loop.c
> @@ -164,6 +164,47 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file)
>  	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
>  }
>  
> +static void __loop_update_dio(struct loop_device *lo, bool dio)
> +{
> +	struct file *file = lo->lo_backing_file;
> +	struct inode *inode = file->f_mapping->host;
> +	bool use_dio;
> +	unsigned dio_align = inode->i_sb->s_bdev ?
> +		(bdev_io_min(inode->i_sb->s_bdev) - 1) : 0;
> +
> +	/*
> +	 * We support direct I/O only if lo_offset is aligned
> +	 * with the min I/O size of backing device.
> +	 *
> +	 * Request's offset and size will be checked in I/O path.
> +	 */
> +	if (dio) {
> +		if (!dio_align || (lo->lo_offset & dio_align))
> +			use_dio = false;
> +		else
> +			use_dio = true;
> +	} else {
> +		use_dio = false;
> +	}
> +
> +	/* flush dirty pages before changing direct IO */
> +	vfs_fsync(file, 0);
> +
> +	/*
> +	 * The flag of LO_FLAGS_DIRECT_IO is handled similarly with
> +	 * LO_FLAGS_READ_ONLY, both are set from kernel, and losetup
> +	 * will get updated by ioctl(LOOP_GET_STATUS)
> +	 */
> +	blk_mq_freeze_queue(lo->lo_queue);
> +	lo->use_dio = use_dio;
> +	lo->dio_align = dio_align;
> +	if (use_dio)
> +		lo->lo_flags |= LO_FLAGS_DIRECT_IO;
> +	else
> +		lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
> +	blk_mq_unfreeze_queue(lo->lo_queue);
> +}
> +
>  static int
>  figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
>  {
> @@ -173,8 +214,12 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
>  
>  	if (unlikely((loff_t)x != size))
>  		return -EFBIG;
> -	if (lo->lo_offset != offset)
> +	if (lo->lo_offset != offset) {
>  		lo->lo_offset = offset;
> +
> +		/* update dio if lo_offset is changed*/
> +		__loop_update_dio(lo, lo->use_dio);
> +	}
>  	if (lo->lo_sizelimit != sizelimit)
>  		lo->lo_sizelimit = sizelimit;
>  	set_capacity(lo->lo_disk, x);
> @@ -421,6 +466,11 @@ struct switch_request {
>  	struct completion wait;
>  };
>  
> +static inline void loop_update_dio(struct loop_device *lo)
> +{
> +	__loop_update_dio(lo, io_is_direct(lo->lo_backing_file));
> +}
> +
>  /*
>   * Do the actual switch; called from the BIO completion routine
>   */
> @@ -441,6 +491,7 @@ static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
>  		mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
>  	lo->old_gfp_mask = mapping_gfp_mask(mapping);
>  	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
> +	loop_update_dio(lo);
>  }
>  
>  /*
> @@ -627,11 +678,19 @@ static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf)
>  	return sprintf(buf, "%s\n", partscan ? "1" : "0");
>  }
>  
> +static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf)
> +{
> +	int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO);
> +
> +	return sprintf(buf, "%s\n", dio ? "1" : "0");
> +}
> +
>  LOOP_ATTR_RO(backing_file);
>  LOOP_ATTR_RO(offset);
>  LOOP_ATTR_RO(sizelimit);
>  LOOP_ATTR_RO(autoclear);
>  LOOP_ATTR_RO(partscan);
> +LOOP_ATTR_RO(dio);
>  
>  static struct attribute *loop_attrs[] = {
>  	&loop_attr_backing_file.attr,
> @@ -639,6 +698,7 @@ static struct attribute *loop_attrs[] = {
>  	&loop_attr_sizelimit.attr,
>  	&loop_attr_autoclear.attr,
>  	&loop_attr_partscan.attr,
> +	&loop_attr_dio.attr,
>  	NULL,
>  };
>  
> @@ -783,6 +843,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
>  	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
>  		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
>  
> +	loop_update_dio(lo);
>  	set_capacity(lo->lo_disk, size);
>  	bd_set_size(bdev, size << 9);
>  	loop_sysfs_init(lo);
> diff --git a/drivers/block/loop.h b/drivers/block/loop.h
> index b6c7d21..63f8e14 100644
> --- a/drivers/block/loop.h
> +++ b/drivers/block/loop.h
> @@ -58,6 +58,8 @@ struct loop_device {
>  	struct mutex		lo_ctl_mutex;
>  	struct kthread_worker	worker;
>  	struct task_struct	*worker_task;
> +	unsigned		dio_align;
> +	bool			use_dio;
>  
>  	struct request_queue	*lo_queue;
>  	struct blk_mq_tag_set	tag_set;
> diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h
> index e0cecd2..949851c 100644
> --- a/include/uapi/linux/loop.h
> +++ b/include/uapi/linux/loop.h
> @@ -21,6 +21,7 @@ enum {
>  	LO_FLAGS_READ_ONLY	= 1,
>  	LO_FLAGS_AUTOCLEAR	= 4,
>  	LO_FLAGS_PARTSCAN	= 8,
> +	LO_FLAGS_DIRECT_IO	= 16,
>  };
>  
>  #include <asm/posix_types.h>	/* for __kernel_old_dev_t */
> 

WARNING: multiple messages have this Message-ID (diff)
From: Dave Kleikamp <dave.kleikamp@oracle.com>
To: Ming Lei <ming.lei@canonical.com>, Jens Axboe <axboe@kernel.dk>,
	linux-kernel@vger.kernel.org
Cc: Zach Brown <zab@zabbo.net>, Christoph Hellwig <hch@infradead.org>,
	Maxim Patlasov <mpatlasov@parallels.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Tejun Heo <tj@kernel.org>, Dave Chinner <david@fromorbit.com>,
	linux-api@vger.kernel.org
Subject: Re: [PATCH v8 4/6] block: loop: prepare for supporing direct IO
Date: Thu, 30 Jul 2015 10:30:55 -0500	[thread overview]
Message-ID: <55BA432F.3050603@oracle.com> (raw)
In-Reply-To: <1438256184-23645-5-git-send-email-ming.lei@canonical.com>

On 07/30/2015 06:36 AM, Ming Lei wrote:
> This patches provides one interface for enabling direct IO
> from user space:
> 
> 	- userspace(such as losetup) can pass 'file' which is
> 	opened/fcntl as O_DIRECT
> 
> Also __loop_update_dio() is introduced to check if direct I/O
> can be used on current loop setting.
> 
> The last big change is to introduce LO_FLAGS_DIRECT_IO flag
> for userspace to know if direct IO is used to access backing
> file.

lo->use_dio and LO_FLAGS_DIRECT_IO seem redundant. Wouldn't it be
simpler to use one or the other?

> 
> Cc: linux-api@vger.kernel.org
> Signed-off-by: Ming Lei <ming.lei@canonical.com>
> ---
>  drivers/block/loop.c      | 63 ++++++++++++++++++++++++++++++++++++++++++++++-
>  drivers/block/loop.h      |  2 ++
>  include/uapi/linux/loop.h |  1 +
>  3 files changed, 65 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/block/loop.c b/drivers/block/loop.c
> index 1875aad..799cc23 100644
> --- a/drivers/block/loop.c
> +++ b/drivers/block/loop.c
> @@ -164,6 +164,47 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file)
>  	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
>  }
>  
> +static void __loop_update_dio(struct loop_device *lo, bool dio)
> +{
> +	struct file *file = lo->lo_backing_file;
> +	struct inode *inode = file->f_mapping->host;
> +	bool use_dio;
> +	unsigned dio_align = inode->i_sb->s_bdev ?
> +		(bdev_io_min(inode->i_sb->s_bdev) - 1) : 0;
> +
> +	/*
> +	 * We support direct I/O only if lo_offset is aligned
> +	 * with the min I/O size of backing device.
> +	 *
> +	 * Request's offset and size will be checked in I/O path.
> +	 */
> +	if (dio) {
> +		if (!dio_align || (lo->lo_offset & dio_align))
> +			use_dio = false;
> +		else
> +			use_dio = true;
> +	} else {
> +		use_dio = false;
> +	}
> +
> +	/* flush dirty pages before changing direct IO */
> +	vfs_fsync(file, 0);
> +
> +	/*
> +	 * The flag of LO_FLAGS_DIRECT_IO is handled similarly with
> +	 * LO_FLAGS_READ_ONLY, both are set from kernel, and losetup
> +	 * will get updated by ioctl(LOOP_GET_STATUS)
> +	 */
> +	blk_mq_freeze_queue(lo->lo_queue);
> +	lo->use_dio = use_dio;
> +	lo->dio_align = dio_align;
> +	if (use_dio)
> +		lo->lo_flags |= LO_FLAGS_DIRECT_IO;
> +	else
> +		lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
> +	blk_mq_unfreeze_queue(lo->lo_queue);
> +}
> +
>  static int
>  figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
>  {
> @@ -173,8 +214,12 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
>  
>  	if (unlikely((loff_t)x != size))
>  		return -EFBIG;
> -	if (lo->lo_offset != offset)
> +	if (lo->lo_offset != offset) {
>  		lo->lo_offset = offset;
> +
> +		/* update dio if lo_offset is changed*/
> +		__loop_update_dio(lo, lo->use_dio);
> +	}
>  	if (lo->lo_sizelimit != sizelimit)
>  		lo->lo_sizelimit = sizelimit;
>  	set_capacity(lo->lo_disk, x);
> @@ -421,6 +466,11 @@ struct switch_request {
>  	struct completion wait;
>  };
>  
> +static inline void loop_update_dio(struct loop_device *lo)
> +{
> +	__loop_update_dio(lo, io_is_direct(lo->lo_backing_file));
> +}
> +
>  /*
>   * Do the actual switch; called from the BIO completion routine
>   */
> @@ -441,6 +491,7 @@ static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
>  		mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
>  	lo->old_gfp_mask = mapping_gfp_mask(mapping);
>  	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
> +	loop_update_dio(lo);
>  }
>  
>  /*
> @@ -627,11 +678,19 @@ static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf)
>  	return sprintf(buf, "%s\n", partscan ? "1" : "0");
>  }
>  
> +static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf)
> +{
> +	int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO);
> +
> +	return sprintf(buf, "%s\n", dio ? "1" : "0");
> +}
> +
>  LOOP_ATTR_RO(backing_file);
>  LOOP_ATTR_RO(offset);
>  LOOP_ATTR_RO(sizelimit);
>  LOOP_ATTR_RO(autoclear);
>  LOOP_ATTR_RO(partscan);
> +LOOP_ATTR_RO(dio);
>  
>  static struct attribute *loop_attrs[] = {
>  	&loop_attr_backing_file.attr,
> @@ -639,6 +698,7 @@ static struct attribute *loop_attrs[] = {
>  	&loop_attr_sizelimit.attr,
>  	&loop_attr_autoclear.attr,
>  	&loop_attr_partscan.attr,
> +	&loop_attr_dio.attr,
>  	NULL,
>  };
>  
> @@ -783,6 +843,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
>  	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
>  		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
>  
> +	loop_update_dio(lo);
>  	set_capacity(lo->lo_disk, size);
>  	bd_set_size(bdev, size << 9);
>  	loop_sysfs_init(lo);
> diff --git a/drivers/block/loop.h b/drivers/block/loop.h
> index b6c7d21..63f8e14 100644
> --- a/drivers/block/loop.h
> +++ b/drivers/block/loop.h
> @@ -58,6 +58,8 @@ struct loop_device {
>  	struct mutex		lo_ctl_mutex;
>  	struct kthread_worker	worker;
>  	struct task_struct	*worker_task;
> +	unsigned		dio_align;
> +	bool			use_dio;
>  
>  	struct request_queue	*lo_queue;
>  	struct blk_mq_tag_set	tag_set;
> diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h
> index e0cecd2..949851c 100644
> --- a/include/uapi/linux/loop.h
> +++ b/include/uapi/linux/loop.h
> @@ -21,6 +21,7 @@ enum {
>  	LO_FLAGS_READ_ONLY	= 1,
>  	LO_FLAGS_AUTOCLEAR	= 4,
>  	LO_FLAGS_PARTSCAN	= 8,
> +	LO_FLAGS_DIRECT_IO	= 16,
>  };
>  
>  #include <asm/posix_types.h>	/* for __kernel_old_dev_t */
> 

  parent reply	other threads:[~2015-07-30 15:30 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-07-30 11:36 [PATCH v8 0/6] block: loop: improve loop with AIO Ming Lei
2015-07-30 11:36 ` [PATCH v8 1/6] fs: direct-io: don't dirtying pages for ITER_BVEC/ITER_KVEC direct read Ming Lei
2015-07-30 11:36 ` [PATCH v8 2/6] block: loop: set QUEUE_FLAG_NOMERGES for request queue of loop Ming Lei
2015-07-30 11:36 ` [PATCH v8 3/6] block: loop: use kthread_work Ming Lei
2015-07-30 11:36 ` [PATCH v8 4/6] block: loop: prepare for supporing direct IO Ming Lei
     [not found]   ` <1438256184-23645-5-git-send-email-ming.lei-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>
2015-07-30 15:09     ` Christoph Hellwig
2015-07-30 15:09       ` Christoph Hellwig
2015-07-30 15:21       ` Ming Lei
2015-07-30 15:30     ` Dave Kleikamp [this message]
2015-07-30 15:30       ` Dave Kleikamp
     [not found]       ` <55BA432F.3050603-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2015-07-30 15:45         ` Ming Lei
2015-07-30 15:45           ` Ming Lei
2015-07-30 11:36 ` [PATCH v8 5/6] block: loop: introduce ioctl command of LOOP_SET_DIRECT_IO Ming Lei
2015-07-30 11:36 ` [PATCH v8 6/6] block: loop: support DIO & AIO Ming Lei
2015-07-30 16:42   ` Christoph Hellwig
2015-07-31  3:13     ` Ming Lei

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=55BA432F.3050603@oracle.com \
    --to=dave.kleikamp-qhclzuegtsvqt0dzr+alfa@public.gmane.org \
    --cc=akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org \
    --cc=axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org \
    --cc=david-FqsqvQoI3Ljby3iVrkZq2A@public.gmane.org \
    --cc=hch-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org \
    --cc=linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=ming.lei-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org \
    --cc=mpatlasov-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org \
    --cc=tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
    --cc=viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org \
    --cc=zab-ugsP4Wv/S6ZeoWH0uzbU5w@public.gmane.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.