From: Dan Williams <dan.j.williams@intel.com> To: linux-nvdimm@lists.01.org Cc: Mike Snitzer <snitzer@redhat.com>, x86@kernel.org, linux-kernel@vger.kernel.org, viro@zeniv.linux.org.uk, linux-fsdevel@vger.kernel.org, hch@lst.de Subject: [PATCH v4 05/16] dm: add ->flush() dax operation support Date: Thu, 29 Jun 2017 10:53:24 -0700 [thread overview] Message-ID: <149875880403.10031.17595568833142352738.stgit@dwillia2-desk3.amr.corp.intel.com> (raw) In-Reply-To: <149875877608.10031.17813337234536358002.stgit@dwillia2-desk3.amr.corp.intel.com> Allow device-mapper to route flush operations to the per-target implementation. In order for the device stacking to work we need a dax_dev and a pgoff relative to that device. This gives each layer of the stack the information it needs to look up the operation pointer for the next level. This conceptually allows for an array of mixed device drivers with varying flush implementations. Reviewed-by: Toshi Kani <toshi.kani@hpe.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> --- drivers/dax/super.c | 11 +++++++++++ drivers/md/dm-linear.c | 15 +++++++++++++++ drivers/md/dm-stripe.c | 20 ++++++++++++++++++++ drivers/md/dm.c | 19 +++++++++++++++++++ include/linux/dax.h | 2 ++ include/linux/device-mapper.h | 3 +++ 6 files changed, 70 insertions(+) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index dd299e55f65d..b7729e4d351a 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -185,6 +185,17 @@ size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, } EXPORT_SYMBOL_GPL(dax_copy_from_iter); +void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, + size_t size) +{ + if (!dax_alive(dax_dev)) + return; + + if (dax_dev->ops->flush) + dax_dev->ops->flush(dax_dev, pgoff, addr, size); +} +EXPORT_SYMBOL_GPL(dax_flush); + bool dax_alive(struct dax_device *dax_dev) { lockdep_assert_held(&dax_srcu); diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 0841ec1bfbad..25e661974319 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -173,6 +173,20 @@ static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); } +static void linear_dax_flush(struct dm_target *ti, pgoff_t pgoff, void *addr, + size_t size) +{ + struct linear_c *lc = ti->private; + struct block_device *bdev = lc->dev->bdev; + struct dax_device *dax_dev = lc->dev->dax_dev; + sector_t dev_sector, sector = pgoff * PAGE_SECTORS; + + dev_sector = linear_map_sector(ti, sector); + if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(size, PAGE_SIZE), &pgoff)) + return; + dax_flush(dax_dev, pgoff, addr, size); +} + static struct target_type linear_target = { .name = "linear", .version = {1, 3, 0}, @@ -186,6 +200,7 @@ static struct target_type linear_target = { .iterate_devices = linear_iterate_devices, .direct_access = linear_dax_direct_access, .dax_copy_from_iter = linear_dax_copy_from_iter, + .dax_flush = linear_dax_flush, }; int __init dm_linear_init(void) diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 1ef914f9ca72..8e73517967b6 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -351,6 +351,25 @@ static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); } +static void stripe_dax_flush(struct dm_target *ti, pgoff_t pgoff, void *addr, + size_t size) +{ + sector_t dev_sector, sector = pgoff * PAGE_SECTORS; + struct stripe_c *sc = ti->private; + struct dax_device *dax_dev; + struct block_device *bdev; + uint32_t stripe; + + stripe_map_sector(sc, sector, &stripe, &dev_sector); + dev_sector += sc->stripe[stripe].physical_start; + dax_dev = sc->stripe[stripe].dev->dax_dev; + bdev = sc->stripe[stripe].dev->bdev; + + if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(size, PAGE_SIZE), &pgoff)) + return; + dax_flush(dax_dev, pgoff, addr, size); +} + /* * Stripe status: * @@ -471,6 +490,7 @@ static struct target_type stripe_target = { .io_hints = stripe_io_hints, .direct_access = stripe_dax_direct_access, .dax_copy_from_iter = stripe_dax_copy_from_iter, + .dax_flush = stripe_dax_flush, }; int __init dm_stripe_init(void) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 7faaceb52819..09b3efdc8abf 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -994,6 +994,24 @@ static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, return ret; } +static void dm_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, + size_t size) +{ + struct mapped_device *md = dax_get_private(dax_dev); + sector_t sector = pgoff * PAGE_SECTORS; + struct dm_target *ti; + int srcu_idx; + + ti = dm_dax_get_live_target(md, sector, &srcu_idx); + + if (!ti) + goto out; + if (ti->type->dax_flush) + ti->type->dax_flush(ti, pgoff, addr, size); + out: + dm_put_live_table(md, srcu_idx); +} + /* * A target may call dm_accept_partial_bio only from the map routine. It is * allowed for all bio types except REQ_PREFLUSH. @@ -2885,6 +2903,7 @@ static const struct block_device_operations dm_blk_dops = { static const struct dax_operations dm_dax_ops = { .direct_access = dm_dax_direct_access, .copy_from_iter = dm_dax_copy_from_iter, + .flush = dm_dax_flush, }; /* diff --git a/include/linux/dax.h b/include/linux/dax.h index 407dd3ff6e54..1f6b6072af64 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -82,6 +82,8 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); +void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, + size_t size); /* * We use lowest available bit in exceptional entry for locking, one bit for diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 11c8a0a92f9c..67bfe8ddcb32 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -134,6 +134,8 @@ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); typedef size_t (*dm_dax_copy_from_iter_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); +typedef void (*dm_dax_flush_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr, + size_t size); #define PAGE_SECTORS (PAGE_SIZE / 512) void dm_error(const char *message); @@ -184,6 +186,7 @@ struct target_type { dm_io_hints_fn io_hints; dm_dax_direct_access_fn direct_access; dm_dax_copy_from_iter_fn dax_copy_from_iter; + dm_dax_flush_fn dax_flush; /* For internal device-mapper use. */ struct list_head list; _______________________________________________ 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: Dan Williams <dan.j.williams@intel.com> To: linux-nvdimm@lists.01.org Cc: Mike Snitzer <snitzer@redhat.com>, Toshi Kani <toshi.kani@hpe.com>, x86@kernel.org, linux-kernel@vger.kernel.org, viro@zeniv.linux.org.uk, linux-fsdevel@vger.kernel.org, hch@lst.de Subject: [PATCH v4 05/16] dm: add ->flush() dax operation support Date: Thu, 29 Jun 2017 10:53:24 -0700 [thread overview] Message-ID: <149875880403.10031.17595568833142352738.stgit@dwillia2-desk3.amr.corp.intel.com> (raw) In-Reply-To: <149875877608.10031.17813337234536358002.stgit@dwillia2-desk3.amr.corp.intel.com> Allow device-mapper to route flush operations to the per-target implementation. In order for the device stacking to work we need a dax_dev and a pgoff relative to that device. This gives each layer of the stack the information it needs to look up the operation pointer for the next level. This conceptually allows for an array of mixed device drivers with varying flush implementations. Reviewed-by: Toshi Kani <toshi.kani@hpe.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> --- drivers/dax/super.c | 11 +++++++++++ drivers/md/dm-linear.c | 15 +++++++++++++++ drivers/md/dm-stripe.c | 20 ++++++++++++++++++++ drivers/md/dm.c | 19 +++++++++++++++++++ include/linux/dax.h | 2 ++ include/linux/device-mapper.h | 3 +++ 6 files changed, 70 insertions(+) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index dd299e55f65d..b7729e4d351a 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -185,6 +185,17 @@ size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, } EXPORT_SYMBOL_GPL(dax_copy_from_iter); +void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, + size_t size) +{ + if (!dax_alive(dax_dev)) + return; + + if (dax_dev->ops->flush) + dax_dev->ops->flush(dax_dev, pgoff, addr, size); +} +EXPORT_SYMBOL_GPL(dax_flush); + bool dax_alive(struct dax_device *dax_dev) { lockdep_assert_held(&dax_srcu); diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 0841ec1bfbad..25e661974319 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -173,6 +173,20 @@ static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); } +static void linear_dax_flush(struct dm_target *ti, pgoff_t pgoff, void *addr, + size_t size) +{ + struct linear_c *lc = ti->private; + struct block_device *bdev = lc->dev->bdev; + struct dax_device *dax_dev = lc->dev->dax_dev; + sector_t dev_sector, sector = pgoff * PAGE_SECTORS; + + dev_sector = linear_map_sector(ti, sector); + if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(size, PAGE_SIZE), &pgoff)) + return; + dax_flush(dax_dev, pgoff, addr, size); +} + static struct target_type linear_target = { .name = "linear", .version = {1, 3, 0}, @@ -186,6 +200,7 @@ static struct target_type linear_target = { .iterate_devices = linear_iterate_devices, .direct_access = linear_dax_direct_access, .dax_copy_from_iter = linear_dax_copy_from_iter, + .dax_flush = linear_dax_flush, }; int __init dm_linear_init(void) diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 1ef914f9ca72..8e73517967b6 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -351,6 +351,25 @@ static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); } +static void stripe_dax_flush(struct dm_target *ti, pgoff_t pgoff, void *addr, + size_t size) +{ + sector_t dev_sector, sector = pgoff * PAGE_SECTORS; + struct stripe_c *sc = ti->private; + struct dax_device *dax_dev; + struct block_device *bdev; + uint32_t stripe; + + stripe_map_sector(sc, sector, &stripe, &dev_sector); + dev_sector += sc->stripe[stripe].physical_start; + dax_dev = sc->stripe[stripe].dev->dax_dev; + bdev = sc->stripe[stripe].dev->bdev; + + if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(size, PAGE_SIZE), &pgoff)) + return; + dax_flush(dax_dev, pgoff, addr, size); +} + /* * Stripe status: * @@ -471,6 +490,7 @@ static struct target_type stripe_target = { .io_hints = stripe_io_hints, .direct_access = stripe_dax_direct_access, .dax_copy_from_iter = stripe_dax_copy_from_iter, + .dax_flush = stripe_dax_flush, }; int __init dm_stripe_init(void) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 7faaceb52819..09b3efdc8abf 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -994,6 +994,24 @@ static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, return ret; } +static void dm_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, + size_t size) +{ + struct mapped_device *md = dax_get_private(dax_dev); + sector_t sector = pgoff * PAGE_SECTORS; + struct dm_target *ti; + int srcu_idx; + + ti = dm_dax_get_live_target(md, sector, &srcu_idx); + + if (!ti) + goto out; + if (ti->type->dax_flush) + ti->type->dax_flush(ti, pgoff, addr, size); + out: + dm_put_live_table(md, srcu_idx); +} + /* * A target may call dm_accept_partial_bio only from the map routine. It is * allowed for all bio types except REQ_PREFLUSH. @@ -2885,6 +2903,7 @@ static const struct block_device_operations dm_blk_dops = { static const struct dax_operations dm_dax_ops = { .direct_access = dm_dax_direct_access, .copy_from_iter = dm_dax_copy_from_iter, + .flush = dm_dax_flush, }; /* diff --git a/include/linux/dax.h b/include/linux/dax.h index 407dd3ff6e54..1f6b6072af64 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -82,6 +82,8 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); +void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, + size_t size); /* * We use lowest available bit in exceptional entry for locking, one bit for diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 11c8a0a92f9c..67bfe8ddcb32 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -134,6 +134,8 @@ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); typedef size_t (*dm_dax_copy_from_iter_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); +typedef void (*dm_dax_flush_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr, + size_t size); #define PAGE_SECTORS (PAGE_SIZE / 512) void dm_error(const char *message); @@ -184,6 +186,7 @@ struct target_type { dm_io_hints_fn io_hints; dm_dax_direct_access_fn direct_access; dm_dax_copy_from_iter_fn dax_copy_from_iter; + dm_dax_flush_fn dax_flush; /* For internal device-mapper use. */ struct list_head list;
next prev parent reply other threads:[~2017-06-29 17:58 UTC|newest] Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top 2017-06-29 17:52 [PATCH v4 00/16] pmem: stop abusing copy_user_nocache(), and other reworks Dan Williams 2017-06-29 17:52 ` Dan Williams 2017-06-29 17:53 ` [PATCH v4 01/16] x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations Dan Williams 2017-06-29 17:53 ` Dan Williams 2017-06-29 17:53 ` [PATCH v4 02/16] dm: add ->copy_from_iter() dax operation support Dan Williams 2017-06-29 17:53 ` Dan Williams 2017-06-29 17:53 ` [PATCH v4 03/16] filesystem-dax: convert to dax_copy_from_iter() Dan Williams 2017-06-29 17:53 ` Dan Williams 2017-06-29 17:53 ` [PATCH v4 04/16] dax, pmem: introduce an optional 'flush' dax_operation Dan Williams 2017-06-29 17:53 ` Dan Williams 2017-06-29 17:53 ` Dan Williams [this message] 2017-06-29 17:53 ` [PATCH v4 05/16] dm: add ->flush() dax operation support Dan Williams 2017-06-29 17:53 ` [PATCH v4 06/16] filesystem-dax: convert to dax_flush() Dan Williams 2017-06-29 17:53 ` Dan Williams 2017-06-29 17:53 ` [PATCH v4 07/16] x86, dax: replace clear_pmem() with open coded memset + dax_ops->flush Dan Williams 2017-06-29 17:53 ` Dan Williams 2017-06-29 17:53 ` [PATCH v4 08/16] x86, dax, libnvdimm: remove wb_cache_pmem() indirection Dan Williams 2017-06-29 17:53 ` Dan Williams 2017-06-29 17:53 ` [PATCH v4 09/16] x86, libnvdimm, pmem: move arch_invalidate_pmem() to libnvdimm Dan Williams 2017-06-29 17:53 ` Dan Williams 2017-06-29 17:53 ` [PATCH v4 10/16] x86, libnvdimm, pmem: remove global pmem api Dan Williams 2017-06-29 17:53 ` Dan Williams 2017-06-29 17:53 ` [PATCH v4 11/16] libnvdimm, pmem: fix persistence warning Dan Williams 2017-06-29 17:53 ` Dan Williams 2017-06-29 17:54 ` [PATCH v4 12/16] libnvdimm, nfit: enable support for volatile ranges Dan Williams 2017-06-29 17:54 ` Dan Williams 2017-06-29 19:20 ` Linda Knippers 2017-06-29 19:20 ` Linda Knippers 2017-06-29 20:42 ` Dan Williams 2017-06-29 20:42 ` Dan Williams 2017-06-29 21:16 ` Linda Knippers 2017-06-29 21:16 ` Linda Knippers 2017-06-29 21:50 ` Dan Williams 2017-06-29 21:50 ` Dan Williams 2017-06-29 22:12 ` Linda Knippers 2017-06-29 22:12 ` Linda Knippers 2017-06-29 22:28 ` Dan Williams 2017-06-29 22:28 ` Dan Williams 2017-06-29 22:35 ` Linda Knippers 2017-06-29 22:35 ` Linda Knippers 2017-06-29 22:43 ` Dan Williams 2017-06-29 22:43 ` Dan Williams 2017-06-29 22:49 ` Linda Knippers 2017-06-29 22:49 ` Linda Knippers 2017-06-29 22:58 ` Dan Williams 2017-06-29 22:58 ` Dan Williams 2017-06-29 23:14 ` Linda Knippers 2017-06-29 23:14 ` Linda Knippers 2017-06-30 1:28 ` Dan Williams 2017-06-30 1:28 ` Dan Williams 2017-07-05 23:46 ` Kani, Toshimitsu 2017-07-05 23:46 ` Kani, Toshimitsu 2017-07-06 0:07 ` Dan Williams 2017-07-06 0:07 ` Dan Williams 2017-07-06 1:17 ` Kani, Toshimitsu 2017-07-06 1:17 ` Kani, Toshimitsu 2017-07-06 2:08 ` Dan Williams 2017-07-06 2:08 ` Dan Williams 2017-07-06 2:11 ` hch 2017-07-06 2:11 ` hch 2017-07-06 2:53 ` Oliver 2017-07-06 2:53 ` Oliver 2017-07-06 2:56 ` hch 2017-07-06 2:56 ` hch 2017-06-29 17:54 ` [PATCH v4 13/16] dax: remove default copy_from_iter fallback Dan Williams 2017-06-29 17:54 ` Dan Williams 2017-06-29 17:54 ` [PATCH v4 14/16] dax: convert to bitmask for flags Dan Williams 2017-06-29 17:54 ` Dan Williams 2017-06-29 17:54 ` [PATCH v4 15/16] libnvdimm, pmem, dax: export a cache control attribute Dan Williams 2017-06-29 17:54 ` Dan Williams 2017-06-29 17:54 ` [PATCH v4 16/16] libnvdimm, pmem: disable dax flushing when pmem is fronting a volatile region Dan Williams 2017-06-29 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=149875880403.10031.17595568833142352738.stgit@dwillia2-desk3.amr.corp.intel.com \ --to=dan.j.williams@intel.com \ --cc=hch@lst.de \ --cc=linux-fsdevel@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-nvdimm@lists.01.org \ --cc=snitzer@redhat.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: linkBe 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.