From: Jan Kara <jack@suse.cz>
To: Dan Williams <dan.j.williams@intel.com>
Cc: Matthew Wilcox <mawilcox@microsoft.com>,
x86@kernel.org, linux-kernel@vger.kernel.org,
linux-nvdimm@lists.01.org, dm-devel@redhat.com,
viro@zeniv.linux.org.uk, linux-fsdevel@vger.kernel.org,
hch@lst.de
Subject: Re: [PATCH v3 04/14] dax, pmem: introduce an optional 'flush' dax_operation
Date: Wed, 14 Jun 2017 12:57:31 +0200 [thread overview]
Message-ID: <20170614105731.GG21506@quack2.suse.cz> (raw)
In-Reply-To: <149703984722.20620.1577767383686219477.stgit@dwillia2-desk3.amr.corp.intel.com>
On Fri 09-06-17 13:24:07, Dan Williams wrote:
> Filesystem-DAX flushes caches whenever it writes to the address returned
> through dax_direct_access() and when writing back dirty radix entries.
> That flushing is only required in the pmem case, so add a dax operation
> to allow pmem to take this extra action, but skip it for other dax
> capable devices that do not provide a flush routine.
>
> An example for this differentiation might be a volatile ram disk where
> there is no expectation of persistence. In fact the pmem driver itself might
> front such an address range specified by the NFIT. So, this "no flush"
> property might be something passed down by the bus / libnvdimm.
>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Matthew Wilcox <mawilcox@microsoft.com>
> Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Looks good to me. You can add:
Reviewed-by: Jan Kara <jack@suse.cz>
Honza
> ---
> drivers/nvdimm/pmem.c | 7 +++++++
> include/linux/dax.h | 2 ++
> 2 files changed, 9 insertions(+)
>
> diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
> index 2f3aefe565c6..823b07774244 100644
> --- a/drivers/nvdimm/pmem.c
> +++ b/drivers/nvdimm/pmem.c
> @@ -242,9 +242,16 @@ static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
> return copy_from_iter_flushcache(addr, bytes, i);
> }
>
> +static void pmem_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff,
> + void *addr, size_t size)
> +{
> + wb_cache_pmem(addr, size);
> +}
> +
> static const struct dax_operations pmem_dax_ops = {
> .direct_access = pmem_dax_direct_access,
> .copy_from_iter = pmem_copy_from_iter,
> + .flush = pmem_dax_flush,
> };
>
> static void pmem_release_queue(void *q)
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index 28e398f8c59e..407dd3ff6e54 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -19,6 +19,8 @@ struct dax_operations {
> /* copy_from_iter: dax-driver override for default copy_from_iter */
> size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
> struct iov_iter *);
> + /* flush: optional driver-specific cache management after writes */
> + void (*flush)(struct dax_device *, pgoff_t, void *, size_t);
> };
>
> #if IS_ENABLED(CONFIG_DAX)
>
--
Jan Kara <jack@suse.com>
SUSE Labs, CR
_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm
WARNING: multiple messages have this Message-ID (diff)
From: Jan Kara <jack@suse.cz>
To: Dan Williams <dan.j.williams@intel.com>
Cc: linux-nvdimm@lists.01.org,
Matthew Wilcox <mawilcox@microsoft.com>,
x86@kernel.org, linux-kernel@vger.kernel.org,
dm-devel@redhat.com, viro@zeniv.linux.org.uk,
linux-fsdevel@vger.kernel.org,
Ross Zwisler <ross.zwisler@linux.intel.com>,
hch@lst.de
Subject: Re: [PATCH v3 04/14] dax, pmem: introduce an optional 'flush' dax_operation
Date: Wed, 14 Jun 2017 12:57:31 +0200 [thread overview]
Message-ID: <20170614105731.GG21506@quack2.suse.cz> (raw)
In-Reply-To: <149703984722.20620.1577767383686219477.stgit@dwillia2-desk3.amr.corp.intel.com>
On Fri 09-06-17 13:24:07, Dan Williams wrote:
> Filesystem-DAX flushes caches whenever it writes to the address returned
> through dax_direct_access() and when writing back dirty radix entries.
> That flushing is only required in the pmem case, so add a dax operation
> to allow pmem to take this extra action, but skip it for other dax
> capable devices that do not provide a flush routine.
>
> An example for this differentiation might be a volatile ram disk where
> there is no expectation of persistence. In fact the pmem driver itself might
> front such an address range specified by the NFIT. So, this "no flush"
> property might be something passed down by the bus / libnvdimm.
>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Matthew Wilcox <mawilcox@microsoft.com>
> Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Looks good to me. You can add:
Reviewed-by: Jan Kara <jack@suse.cz>
Honza
> ---
> drivers/nvdimm/pmem.c | 7 +++++++
> include/linux/dax.h | 2 ++
> 2 files changed, 9 insertions(+)
>
> diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
> index 2f3aefe565c6..823b07774244 100644
> --- a/drivers/nvdimm/pmem.c
> +++ b/drivers/nvdimm/pmem.c
> @@ -242,9 +242,16 @@ static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
> return copy_from_iter_flushcache(addr, bytes, i);
> }
>
> +static void pmem_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff,
> + void *addr, size_t size)
> +{
> + wb_cache_pmem(addr, size);
> +}
> +
> static const struct dax_operations pmem_dax_ops = {
> .direct_access = pmem_dax_direct_access,
> .copy_from_iter = pmem_copy_from_iter,
> + .flush = pmem_dax_flush,
> };
>
> static void pmem_release_queue(void *q)
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index 28e398f8c59e..407dd3ff6e54 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -19,6 +19,8 @@ struct dax_operations {
> /* copy_from_iter: dax-driver override for default copy_from_iter */
> size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
> struct iov_iter *);
> + /* flush: optional driver-specific cache management after writes */
> + void (*flush)(struct dax_device *, pgoff_t, void *, size_t);
> };
>
> #if IS_ENABLED(CONFIG_DAX)
>
--
Jan Kara <jack@suse.com>
SUSE Labs, CR
WARNING: multiple messages have this Message-ID (diff)
From: Jan Kara <jack-AlSwsSmVLrQ@public.gmane.org>
To: Dan Williams <dan.j.williams-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Cc: Matthew Wilcox <mawilcox-0li6OtcxBFHby3iVrkZq2A@public.gmane.org>,
x86-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-nvdimm-hn68Rpc1hR1g9hUCZPvPmw@public.gmane.org,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org,
viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
hch-jcswGhMUV9g@public.gmane.org
Subject: Re: [PATCH v3 04/14] dax, pmem: introduce an optional 'flush' dax_operation
Date: Wed, 14 Jun 2017 12:57:31 +0200 [thread overview]
Message-ID: <20170614105731.GG21506@quack2.suse.cz> (raw)
In-Reply-To: <149703984722.20620.1577767383686219477.stgit-p8uTFz9XbKj2zm6wflaqv1nYeNYlB/vhral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
On Fri 09-06-17 13:24:07, Dan Williams wrote:
> Filesystem-DAX flushes caches whenever it writes to the address returned
> through dax_direct_access() and when writing back dirty radix entries.
> That flushing is only required in the pmem case, so add a dax operation
> to allow pmem to take this extra action, but skip it for other dax
> capable devices that do not provide a flush routine.
>
> An example for this differentiation might be a volatile ram disk where
> there is no expectation of persistence. In fact the pmem driver itself might
> front such an address range specified by the NFIT. So, this "no flush"
> property might be something passed down by the bus / libnvdimm.
>
> Cc: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
> Cc: Matthew Wilcox <mawilcox-0li6OtcxBFHby3iVrkZq2A@public.gmane.org>
> Cc: Ross Zwisler <ross.zwisler-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
> Signed-off-by: Dan Williams <dan.j.williams-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Looks good to me. You can add:
Reviewed-by: Jan Kara <jack-AlSwsSmVLrQ@public.gmane.org>
Honza
> ---
> drivers/nvdimm/pmem.c | 7 +++++++
> include/linux/dax.h | 2 ++
> 2 files changed, 9 insertions(+)
>
> diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
> index 2f3aefe565c6..823b07774244 100644
> --- a/drivers/nvdimm/pmem.c
> +++ b/drivers/nvdimm/pmem.c
> @@ -242,9 +242,16 @@ static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
> return copy_from_iter_flushcache(addr, bytes, i);
> }
>
> +static void pmem_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff,
> + void *addr, size_t size)
> +{
> + wb_cache_pmem(addr, size);
> +}
> +
> static const struct dax_operations pmem_dax_ops = {
> .direct_access = pmem_dax_direct_access,
> .copy_from_iter = pmem_copy_from_iter,
> + .flush = pmem_dax_flush,
> };
>
> static void pmem_release_queue(void *q)
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index 28e398f8c59e..407dd3ff6e54 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -19,6 +19,8 @@ struct dax_operations {
> /* copy_from_iter: dax-driver override for default copy_from_iter */
> size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
> struct iov_iter *);
> + /* flush: optional driver-specific cache management after writes */
> + void (*flush)(struct dax_device *, pgoff_t, void *, size_t);
> };
>
> #if IS_ENABLED(CONFIG_DAX)
>
--
Jan Kara <jack-IBi9RG/b67k@public.gmane.org>
SUSE Labs, CR
next prev parent reply other threads:[~2017-06-14 10:56 UTC|newest]
Thread overview: 117+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-06-09 20:23 [PATCH v3 00/14] pmem: stop abusing __copy_user_nocache(), and other reworks Dan Williams
2017-06-09 20:23 ` Dan Williams
2017-06-09 20:23 ` Dan Williams
2017-06-09 20:23 ` [PATCH v3 01/14] x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations Dan Williams
2017-06-09 20:23 ` Dan Williams
2017-06-09 20:23 ` Dan Williams
2017-06-18 8:28 ` Christoph Hellwig
2017-06-18 8:28 ` Christoph Hellwig
2017-06-18 8:28 ` Christoph Hellwig
2017-06-19 2:02 ` Dan Williams
2017-06-19 2:02 ` Dan Williams
2017-06-19 2:02 ` Dan Williams
2017-06-09 20:23 ` [PATCH v3 02/14] dm: add ->copy_from_iter() dax operation support Dan Williams
2017-06-09 20:23 ` Dan Williams
2017-06-09 20:23 ` Dan Williams
2017-06-15 0:46 ` Kani, Toshimitsu
2017-06-15 0:46 ` Kani, Toshimitsu
2017-06-15 0:46 ` Kani, Toshimitsu
2017-06-15 1:21 ` Kani, Toshimitsu
2017-06-15 1:21 ` Kani, Toshimitsu
2017-06-18 8:37 ` Christoph Hellwig
2017-06-18 8:37 ` Christoph Hellwig
2017-06-18 8:37 ` Christoph Hellwig
2017-06-19 2:04 ` Dan Williams
2017-06-19 2:04 ` Dan Williams
2017-06-19 2:04 ` Dan Williams
2017-06-09 20:24 ` [PATCH v3 03/14] filesystem-dax: convert to dax_copy_from_iter() Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-14 10:58 ` Jan Kara
2017-06-14 10:58 ` Jan Kara
2017-06-14 10:58 ` Jan Kara
2017-06-09 20:24 ` [PATCH v3 04/14] dax, pmem: introduce an optional 'flush' dax_operation Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-14 10:57 ` Jan Kara [this message]
2017-06-14 10:57 ` Jan Kara
2017-06-14 10:57 ` Jan Kara
2017-06-09 20:24 ` [PATCH v3 05/14] dm: add ->flush() dax operation support Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-15 1:44 ` Kani, Toshimitsu
2017-06-15 1:44 ` Kani, Toshimitsu
2017-06-15 1:44 ` Kani, Toshimitsu
2017-06-09 20:24 ` [PATCH v3 06/14] filesystem-dax: convert to dax_flush() Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-14 10:56 ` Jan Kara
2017-06-14 10:56 ` Jan Kara
2017-06-14 10:56 ` Jan Kara
2017-06-09 20:24 ` [PATCH v3 07/14] x86, dax: replace clear_pmem() with open coded memset + dax_ops->flush Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-14 10:55 ` Jan Kara
2017-06-14 10:55 ` Jan Kara
2017-06-14 10:55 ` Jan Kara
2017-06-09 20:24 ` [PATCH v3 08/14] x86, dax, libnvdimm: move wb_cache_pmem() to libnvdimm Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-12 0:29 ` [PATCH v4 " Dan Williams
2017-06-12 0:29 ` Dan Williams
2017-06-14 10:54 ` [PATCH v3 " Jan Kara
2017-06-14 10:54 ` Jan Kara
2017-06-14 16:49 ` Dan Williams
2017-06-14 16:49 ` Dan Williams
2017-06-14 16:49 ` Dan Williams
2017-06-15 8:11 ` Jan Kara
2017-06-15 8:11 ` Jan Kara
2017-06-15 8:11 ` Jan Kara
2017-06-18 8:40 ` Christoph Hellwig
2017-06-18 8:40 ` Christoph Hellwig
2017-06-18 8:40 ` Christoph Hellwig
2017-06-19 2:06 ` Dan Williams
2017-06-19 2:06 ` Dan Williams
2017-06-19 2:06 ` Dan Williams
2017-06-09 20:24 ` [PATCH v3 09/14] x86, libnvdimm, pmem: move arch_invalidate_pmem() " Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-14 10:49 ` Jan Kara
2017-06-14 10:49 ` Jan Kara
2017-06-09 20:24 ` [PATCH v3 10/14] pmem: remove global pmem api Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-14 10:48 ` Jan Kara
2017-06-14 10:48 ` Jan Kara
2017-06-14 10:48 ` Jan Kara
2017-06-09 20:24 ` [PATCH v3 11/14] libnvdimm, pmem: fix persistence warning Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-09 20:24 ` [PATCH v3 12/14] libnvdimm, nfit: enable support for volatile ranges Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-09 20:24 ` [PATCH v3 13/14] filesystem-dax: gate calls to dax_flush() on QUEUE_FLAG_WC Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-09 20:24 ` Dan Williams
2017-06-14 10:46 ` Jan Kara
2017-06-14 10:46 ` Jan Kara
2017-06-14 16:49 ` Dan Williams
2017-06-14 16:49 ` Dan Williams
2017-06-14 16:49 ` Dan Williams
2017-06-14 23:11 ` [PATCH v4 13/14] libnvdimm, pmem: gate cache management on QUEUE_FLAG_WC in pmem_dax_flush() Dan Williams
2017-06-14 23:11 ` Dan Williams
2017-06-15 8:09 ` Jan Kara
2017-06-15 8:09 ` Jan Kara
2017-06-18 8:45 ` [PATCH v3 13/14] filesystem-dax: gate calls to dax_flush() on QUEUE_FLAG_WC Christoph Hellwig
2017-06-18 8:45 ` Christoph Hellwig
2017-06-18 8:45 ` Christoph Hellwig
2017-06-19 2:07 ` Dan Williams
2017-06-19 2:07 ` Dan Williams
2017-06-19 2:07 ` Dan Williams
2017-06-09 20:25 ` [PATCH v3 14/14] libnvdimm, pmem: disable dax flushing when pmem is fronting a volatile region Dan Williams
2017-06-09 20:25 ` Dan Williams
2017-06-09 20:25 ` Dan Williams
2017-06-09 23:21 ` Dan Williams
2017-06-09 23:21 ` Dan Williams
2017-06-10 17:54 ` [PATCH v4 " Dan Williams
2017-06-10 17:54 ` Dan Williams
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=20170614105731.GG21506@quack2.suse.cz \
--to=jack@suse.cz \
--cc=dan.j.williams@intel.com \
--cc=dm-devel@redhat.com \
--cc=hch@lst.de \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvdimm@lists.01.org \
--cc=mawilcox@microsoft.com \
--cc=viro@zeniv.linux.org.uk \
--cc=x86@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 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.