Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: [PATCH v3 6/9] dax: introduce a ->copy_to_iter dax operation
From:   Dan Williams <dan.j.williams@intel.com>
To:     linux-nvdimm@lists.01.org
Cc:     Ross Zwisler <ross.zwisler@linux.intel.com>,
        Mike Snitzer <snitzer@redhat.com>,
        Christoph Hellwig <hch@lst.de>, linux-kernel@vger.kernel.org,
        tony.luck@intel.com, linux-fsdevel@vger.kernel.org
Date:   Thu, 03 May 2018 17:06:37 -0700
Message-ID: <152539239729.31796.4765429575408958580.stgit@dwillia2-desk3.amr.corp.intel.com>
In-Reply-To: <152539236455.31796.7516599166555186700.stgit@dwillia2-desk3.amr.corp.intel.com>
References: <152539236455.31796.7516599166555186700.stgit@dwillia2-desk3.amr.corp.intel.com>
User-Agent: StGit/0.18-2-gc94f
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Similar to the ->copy_from_iter() operation, a platform may want to
deploy an architecture or device specific routine for handling reads
from a dax_device like /dev/pmemX. On x86 this routine will point to a
machine check safe version of copy_to_iter(). For now, add the plumbing
to device-mapper and the dax core.

Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/super.c           |   10 ++++++++++
 drivers/md/dm-linear.c        |   16 ++++++++++++++++
 drivers/md/dm-log-writes.c    |   15 +++++++++++++++
 drivers/md/dm-stripe.c        |   21 +++++++++++++++++++++
 drivers/md/dm.c               |   25 +++++++++++++++++++++++++
 drivers/nvdimm/pmem.c         |    7 +++++++
 drivers/s390/block/dcssblk.c  |    7 +++++++
 fs/dax.c                      |    3 ++-
 include/linux/dax.h           |    5 +++++
 include/linux/device-mapper.h |    5 +++--
 10 files changed, 111 insertions(+), 3 deletions(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 2b2332b605e4..31b839113399 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -282,6 +282,16 @@ size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 }
 EXPORT_SYMBOL_GPL(dax_copy_from_iter);
 
+size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+		size_t bytes, struct iov_iter *i)
+{
+	if (!dax_alive(dax_dev))
+		return 0;
+
+	return dax_dev->ops->copy_to_iter(dax_dev, pgoff, addr, bytes, i);
+}
+EXPORT_SYMBOL_GPL(dax_copy_to_iter);
+
 #ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_wb_cache_pmem(void *addr, size_t size);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 775c06d953b7..d10964d41fd7 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -185,9 +185,24 @@ 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 size_t linear_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	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(bytes, PAGE_SIZE), &pgoff))
+		return 0;
+	return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define linear_dax_direct_access NULL
 #define linear_dax_copy_from_iter NULL
+#define linear_dax_copy_to_iter NULL
 #endif
 
 static struct target_type linear_target = {
@@ -204,6 +219,7 @@ 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_copy_to_iter = linear_dax_copy_to_iter,
 };
 
 int __init dm_linear_init(void)
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index c90c7c08a77f..9ea2b0291f20 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -962,9 +962,23 @@ static size_t log_writes_dax_copy_from_iter(struct dm_target *ti,
 dax_copy:
 	return dax_copy_from_iter(lc->dev->dax_dev, pgoff, addr, bytes, i);
 }
+
+static size_t log_writes_dax_copy_to_iter(struct dm_target *ti,
+					  pgoff_t pgoff, void *addr, size_t bytes,
+					  struct iov_iter *i)
+{
+	struct log_writes_c *lc = ti->private;
+	sector_t sector = pgoff * PAGE_SECTORS;
+
+	if (bdev_dax_pgoff(lc->dev->bdev, sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
+		return 0;
+	return dax_copy_to_iter(lc->dev->dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define log_writes_dax_direct_access NULL
 #define log_writes_dax_copy_from_iter NULL
+#define log_writes_dax_copy_to_iter NULL
 #endif
 
 static struct target_type log_writes_target = {
@@ -982,6 +996,7 @@ static struct target_type log_writes_target = {
 	.io_hints = log_writes_io_hints,
 	.direct_access = log_writes_dax_direct_access,
 	.dax_copy_from_iter = log_writes_dax_copy_from_iter,
+	.dax_copy_to_iter = log_writes_dax_copy_to_iter,
 };
 
 static int __init dm_log_writes_init(void)
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index fe7fb9b1aec3..8547d7594338 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -354,9 +354,29 @@ 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 size_t stripe_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	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(bytes, PAGE_SIZE), &pgoff))
+		return 0;
+	return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define stripe_dax_direct_access NULL
 #define stripe_dax_copy_from_iter NULL
+#define stripe_dax_copy_to_iter NULL
 #endif
 
 /*
@@ -478,6 +498,7 @@ 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_copy_to_iter = stripe_dax_copy_to_iter,
 };
 
 int __init dm_stripe_init(void)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 4ea404dbcf0b..cd942905dd1e 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1088,6 +1088,30 @@ static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 	return ret;
 }
 
+static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	struct mapped_device *md = dax_get_private(dax_dev);
+	sector_t sector = pgoff * PAGE_SECTORS;
+	struct dm_target *ti;
+	long ret = 0;
+	int srcu_idx;
+
+	ti = dm_dax_get_live_target(md, sector, &srcu_idx);
+
+	if (!ti)
+		goto out;
+	if (!ti->type->dax_copy_to_iter) {
+		ret = copy_to_iter(addr, bytes, i);
+		goto out;
+	}
+	ret = ti->type->dax_copy_to_iter(ti, pgoff, addr, bytes, i);
+ out:
+	dm_put_live_table(md, srcu_idx);
+
+	return ret;
+}
+
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
  * allowed for all bio types except REQ_PREFLUSH and REQ_OP_ZONE_RESET.
@@ -3133,6 +3157,7 @@ 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,
+	.copy_to_iter = dm_dax_copy_to_iter,
 };
 
 /*
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index e023d6aa22b5..1b8ab48365de 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -264,9 +264,16 @@ static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 	return copy_from_iter_flushcache(addr, bytes, i);
 }
 
+static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	return copy_to_iter(addr, bytes, i);
+}
+
 static const struct dax_operations pmem_dax_ops = {
 	.direct_access = pmem_dax_direct_access,
 	.copy_from_iter = pmem_copy_from_iter,
+	.copy_to_iter = pmem_copy_to_iter,
 };
 
 static const struct attribute_group *pmem_attribute_groups[] = {
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 0a312e450207..29024492b8ed 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -51,9 +51,16 @@ static size_t dcssblk_dax_copy_from_iter(struct dax_device *dax_dev,
 	return copy_from_iter(addr, bytes, i);
 }
 
+static size_t dcssblk_dax_copy_to_iter(struct dax_device *dax_dev,
+		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
+{
+	return copy_to_iter(addr, bytes, i);
+}
+
 static const struct dax_operations dcssblk_dax_ops = {
 	.direct_access = dcssblk_dax_direct_access,
 	.copy_from_iter = dcssblk_dax_copy_from_iter,
+	.copy_to_iter = dcssblk_dax_copy_to_iter,
 };
 
 struct dcssblk_dev_info {
diff --git a/fs/dax.c b/fs/dax.c
index aaec72ded1b6..a64afdf7ec0d 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1057,7 +1057,8 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 			map_len = dax_copy_from_iter(dax_dev, pgoff, kaddr,
 					map_len, iter);
 		else
-			map_len = copy_to_iter(kaddr, map_len, iter);
+			map_len = dax_copy_to_iter(dax_dev, pgoff, kaddr,
+					map_len, iter);
 		if (map_len <= 0) {
 			ret = map_len ? map_len : -EFAULT;
 			break;
diff --git a/include/linux/dax.h b/include/linux/dax.h
index f9eb22ad341e..a43b396fb336 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -20,6 +20,9 @@ struct dax_operations {
 	/* copy_from_iter: required operation for fs-dax direct-i/o */
 	size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
 			struct iov_iter *);
+	/* copy_to_iter: required operation for fs-dax direct-i/o */
+	size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t,
+			struct iov_iter *);
 };
 
 extern struct attribute_group dax_attribute_group;
@@ -118,6 +121,8 @@ 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);
+size_t dax_copy_to_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, void *addr, size_t size);
 
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 31fef7c34185..6fb0808e87c8 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -133,7 +133,7 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
  */
 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,
+typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *i);
 #define PAGE_SECTORS (PAGE_SIZE / 512)
 
@@ -184,7 +184,8 @@ struct target_type {
 	dm_iterate_devices_fn iterate_devices;
 	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_copy_iter_fn dax_copy_from_iter;
+	dm_dax_copy_iter_fn dax_copy_to_iter;
 
 	/* For internal device-mapper use. */
 	struct list_head list;