From d751939235b9b7bc4af15f90a3e99288a8b844a7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:35 +0100 Subject: dm: fix alloc_dax error handling in alloc_dev Make sure ->dax_dev is NULL on error so that the cleanup path doesn't trip over an ERR_PTR. Reported-by: Dan Williams Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211129102203.2243509-2-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/md') diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 662742a310cb..acc84dc1bded 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1786,8 +1786,10 @@ static struct mapped_device *alloc_dev(int minor) if (IS_ENABLED(CONFIG_DAX_DRIVER)) { md->dax_dev = alloc_dax(md, md->disk->disk_name, &dm_dax_ops, 0); - if (IS_ERR(md->dax_dev)) + if (IS_ERR(md->dax_dev)) { + md->dax_dev = NULL; goto bad; + } } format_dev_t(md->name, MKDEV(_major, minor)); -- cgit v1.2.3 From 5d2a228b9e1319ff188f9ea89006fbe575561921 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:36 +0100 Subject: dm: make the DAX support depend on CONFIG_FS_DAX The device mapper DAX support is all hanging off a block device and thus can't be used with device dax. Make it depend on CONFIG_FS_DAX instead of CONFIG_DAX_DRIVER. This also means that bdev_dax_pgoff only needs to be built under CONFIG_FS_DAX now. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Link: https://lore.kernel.org/r/20211129102203.2243509-3-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm-linear.c | 2 +- drivers/md/dm-log-writes.c | 2 +- drivers/md/dm-stripe.c | 2 +- drivers/md/dm-writecache.c | 2 +- drivers/md/dm.c | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 66ba16713f69..0a260c35aeee 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -162,7 +162,7 @@ static int linear_iterate_devices(struct dm_target *ti, return fn(ti, lc->dev, lc->start, ti->len, data); } -#if IS_ENABLED(CONFIG_DAX_DRIVER) +#if IS_ENABLED(CONFIG_FS_DAX) static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) { diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 0b3ef977ceeb..3155875d4e5b 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -901,7 +901,7 @@ static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limit limits->io_min = limits->physical_block_size; } -#if IS_ENABLED(CONFIG_DAX_DRIVER) +#if IS_ENABLED(CONFIG_FS_DAX) static int log_dax(struct log_writes_c *lc, sector_t sector, size_t bytes, struct iov_iter *i) { diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 6660b6b53d5b..f08460722029 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -300,7 +300,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; } -#if IS_ENABLED(CONFIG_DAX_DRIVER) +#if IS_ENABLED(CONFIG_FS_DAX) static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) { diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 4b8991cde223..4f31591d2d25 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -38,7 +38,7 @@ #define BITMAP_GRANULARITY PAGE_SIZE #endif -#if IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API) && IS_ENABLED(CONFIG_DAX_DRIVER) +#if IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API) && IS_ENABLED(CONFIG_FS_DAX) #define DM_WRITECACHE_HAS_PMEM #endif diff --git a/drivers/md/dm.c b/drivers/md/dm.c index acc84dc1bded..b93fcc91176e 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1783,7 +1783,7 @@ static struct mapped_device *alloc_dev(int minor) md->disk->private_data = md; sprintf(md->disk->disk_name, "dm-%d", minor); - if (IS_ENABLED(CONFIG_DAX_DRIVER)) { + if (IS_ENABLED(CONFIG_FS_DAX)) { md->dax_dev = alloc_dax(md, md->disk->disk_name, &dm_dax_ops, 0); if (IS_ERR(md->dax_dev)) { -- cgit v1.2.3 From fb08a1908cb119a4585611d91461ab6d27756b14 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:38 +0100 Subject: dax: simplify the dax_device <-> gendisk association Replace the dax_host_hash with an xarray indexed by the pointer value of the gendisk, and require explicitly calls from the block drivers that want to associate their gendisk with a dax_device. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-5-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm.c b/drivers/md/dm.c index b93fcc91176e..a8c650276b32 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1683,6 +1683,7 @@ static void cleanup_mapped_device(struct mapped_device *md) bioset_exit(&md->io_bs); if (md->dax_dev) { + dax_remove_host(md->disk); kill_dax(md->dax_dev); put_dax(md->dax_dev); md->dax_dev = NULL; @@ -1784,12 +1785,13 @@ static struct mapped_device *alloc_dev(int minor) sprintf(md->disk->disk_name, "dm-%d", minor); if (IS_ENABLED(CONFIG_FS_DAX)) { - md->dax_dev = alloc_dax(md, md->disk->disk_name, - &dm_dax_ops, 0); + md->dax_dev = alloc_dax(md, &dm_dax_ops, 0); if (IS_ERR(md->dax_dev)) { md->dax_dev = NULL; goto bad; } + if (dax_add_host(md->dax_dev, md->disk)) + goto bad; } format_dev_t(md->name, MKDEV(_major, minor)); -- cgit v1.2.3 From 7b0800d00dae8c897398abaf61e82db0d67d7afc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:42 +0100 Subject: dax: remove dax_capable Just open code the block size and dax_dev == NULL checks in the callers. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Reviewed-by: Gao Xiang [erofs] Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-9-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm-table.c | 22 +++++++++++----------- drivers/md/dm.c | 21 --------------------- drivers/md/dm.h | 4 ---- 3 files changed, 11 insertions(+), 36 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index aa173f5bdc3d..e43096cfe9e2 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -806,12 +806,14 @@ void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type) EXPORT_SYMBOL_GPL(dm_table_set_type); /* validate the dax capability of the target device span */ -int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev, +static int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - int blocksize = *(int *) data; + if (dev->dax_dev) + return false; - return !dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len); + DMDEBUG("%pg: error: dax unsupported by block device", dev->bdev); + return true; } /* Check devices support synchronous DAX */ @@ -821,8 +823,8 @@ static int device_not_dax_synchronous_capable(struct dm_target *ti, struct dm_de return !dev->dax_dev || !dax_synchronous(dev->dax_dev); } -bool dm_table_supports_dax(struct dm_table *t, - iterate_devices_callout_fn iterate_fn, int *blocksize) +static bool dm_table_supports_dax(struct dm_table *t, + iterate_devices_callout_fn iterate_fn) { struct dm_target *ti; unsigned i; @@ -835,7 +837,7 @@ bool dm_table_supports_dax(struct dm_table *t, return false; if (!ti->type->iterate_devices || - ti->type->iterate_devices(ti, iterate_fn, blocksize)) + ti->type->iterate_devices(ti, iterate_fn, NULL)) return false; } @@ -862,7 +864,6 @@ static int dm_table_determine_type(struct dm_table *t) struct dm_target *tgt; struct list_head *devices = dm_table_get_devices(t); enum dm_queue_mode live_md_type = dm_get_md_type(t->md); - int page_size = PAGE_SIZE; if (t->type != DM_TYPE_NONE) { /* target already set the table's type */ @@ -906,7 +907,7 @@ static int dm_table_determine_type(struct dm_table *t) verify_bio_based: /* We must use this table as bio-based */ t->type = DM_TYPE_BIO_BASED; - if (dm_table_supports_dax(t, device_not_dax_capable, &page_size) || + if (dm_table_supports_dax(t, device_not_dax_capable) || (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) { t->type = DM_TYPE_DAX_BIO_BASED; } @@ -1976,7 +1977,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, struct queue_limits *limits) { bool wc = false, fua = false; - int page_size = PAGE_SIZE; int r; /* @@ -2010,9 +2010,9 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, } blk_queue_write_cache(q, wc, fua); - if (dm_table_supports_dax(t, device_not_dax_capable, &page_size)) { + if (dm_table_supports_dax(t, device_not_dax_capable)) { blk_queue_flag_set(QUEUE_FLAG_DAX, q); - if (dm_table_supports_dax(t, device_not_dax_synchronous_capable, NULL)) + if (dm_table_supports_dax(t, device_not_dax_synchronous_capable)) set_dax_synchronous(t->md->dax_dev); } else diff --git a/drivers/md/dm.c b/drivers/md/dm.c index a8c650276b32..4eba27e75c23 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1027,26 +1027,6 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, return ret; } -static bool dm_dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len) -{ - struct mapped_device *md = dax_get_private(dax_dev); - struct dm_table *map; - bool ret = false; - int srcu_idx; - - map = dm_get_live_table(md, &srcu_idx); - if (!map) - goto out; - - ret = dm_table_supports_dax(map, device_not_dax_capable, &blocksize); - -out: - dm_put_live_table(md, srcu_idx); - - return ret; -} - static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { @@ -3044,7 +3024,6 @@ static const struct block_device_operations dm_rq_blk_dops = { static const struct dax_operations dm_dax_ops = { .direct_access = dm_dax_direct_access, - .dax_supported = dm_dax_supported, .copy_from_iter = dm_dax_copy_from_iter, .copy_to_iter = dm_dax_copy_to_iter, .zero_page_range = dm_dax_zero_page_range, diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 742d9c80efe1..9013dc1a7b00 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -73,10 +73,6 @@ bool dm_table_bio_based(struct dm_table *t); bool dm_table_request_based(struct dm_table *t); void dm_table_free_md_mempools(struct dm_table *t); struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t); -bool dm_table_supports_dax(struct dm_table *t, iterate_devices_callout_fn fn, - int *blocksize); -int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data); void dm_lock_md_type(struct mapped_device *md); void dm_unlock_md_type(struct mapped_device *md); -- cgit v1.2.3 From f43e0065c264b2cb001952be17c9291c68d07182 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:43 +0100 Subject: dm-linear: add a linear_dax_pgoff helper Add a helper to perform the entire remapping for DAX accesses. This helper open codes bdev_dax_pgoff given that the alignment checks have already been done by the submitting file system and don't need to be repeated. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20211129102203.2243509-10-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm-linear.c | 49 +++++++++++++++---------------------------------- 1 file changed, 15 insertions(+), 34 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 0a260c35aeee..90de42f6743a 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -163,63 +163,44 @@ static int linear_iterate_devices(struct dm_target *ti, } #if IS_ENABLED(CONFIG_FS_DAX) +static struct dax_device *linear_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff) +{ + struct linear_c *lc = ti->private; + sector_t sector = linear_map_sector(ti, *pgoff << PAGE_SECTORS_SHIFT); + + *pgoff = (get_start_sect(lc->dev->bdev) + sector) >> PAGE_SECTORS_SHIFT; + return lc->dev->dax_dev; +} + static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) { - long ret; - 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); - ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff); - if (ret) - return ret; + struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff); + return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } static size_t linear_dax_copy_from_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; + struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff); - dev_sector = linear_map_sector(ti, sector); - if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff)) - return 0; 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; + struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff); - 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); } static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { - int ret; - 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); - ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff); - if (ret) - return ret; + struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff); + return dax_zero_page_range(dax_dev, pgoff, nr_pages); } -- cgit v1.2.3 From d19bd6756e7c400e264dba853eb35c94462f4ec4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:44 +0100 Subject: dm-log-writes: add a log_writes_dax_pgoff helper Add a helper to perform the entire remapping for DAX accesses. This helper open codes bdev_dax_pgoff given that the alignment checks have already been done by the submitting file system and don't need to be repeated. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20211129102203.2243509-11-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm-log-writes.c | 42 +++++++++++++++++------------------------- 1 file changed, 17 insertions(+), 25 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 3155875d4e5b..cdb22e7a1d0d 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -947,17 +947,21 @@ static int log_dax(struct log_writes_c *lc, sector_t sector, size_t bytes, return 0; } +static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti, + pgoff_t *pgoff) +{ + struct log_writes_c *lc = ti->private; + + *pgoff += (get_start_sect(lc->dev->bdev) >> PAGE_SECTORS_SHIFT); + return lc->dev->dax_dev; +} + static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) { - struct log_writes_c *lc = ti->private; - sector_t sector = pgoff * PAGE_SECTORS; - int ret; + struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); - ret = bdev_dax_pgoff(lc->dev->bdev, sector, nr_pages * PAGE_SIZE, &pgoff); - if (ret) - return ret; - return dax_direct_access(lc->dev->dax_dev, pgoff, nr_pages, kaddr, pfn); + return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } static size_t log_writes_dax_copy_from_iter(struct dm_target *ti, @@ -966,11 +970,9 @@ static size_t log_writes_dax_copy_from_iter(struct dm_target *ti, { struct log_writes_c *lc = ti->private; sector_t sector = pgoff * PAGE_SECTORS; + struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); int err; - if (bdev_dax_pgoff(lc->dev->bdev, sector, ALIGN(bytes, PAGE_SIZE), &pgoff)) - return 0; - /* Don't bother doing anything if logging has been disabled */ if (!lc->logging_enabled) goto dax_copy; @@ -981,34 +983,24 @@ static size_t log_writes_dax_copy_from_iter(struct dm_target *ti, return 0; } dax_copy: - return dax_copy_from_iter(lc->dev->dax_dev, pgoff, addr, bytes, i); + return dax_copy_from_iter(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; + struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); - 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); + return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); } static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { - int ret; - struct log_writes_c *lc = ti->private; - sector_t sector = pgoff * PAGE_SECTORS; + struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); - ret = bdev_dax_pgoff(lc->dev->bdev, sector, nr_pages << PAGE_SHIFT, - &pgoff); - if (ret) - return ret; - return dax_zero_page_range(lc->dev->dax_dev, pgoff, - nr_pages << PAGE_SHIFT); + return dax_zero_page_range(dax_dev, pgoff, nr_pages << PAGE_SHIFT); } #else -- cgit v1.2.3 From 2a68553e8aeb3e88cb0b1042233613a3d08a700a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:45 +0100 Subject: dm-stripe: add a stripe_dax_pgoff helper Add a helper to perform the entire remapping for DAX accesses. This helper open codes bdev_dax_pgoff given that the alignment checks have already been done by the submitting file system and don't need to be repeated. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20211129102203.2243509-12-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm-stripe.c | 63 ++++++++++++-------------------------------------- 1 file changed, 15 insertions(+), 48 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index f08460722029..50dba3f39274 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -301,83 +301,50 @@ static int stripe_map(struct dm_target *ti, struct bio *bio) } #if IS_ENABLED(CONFIG_FS_DAX) -static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, - long nr_pages, void **kaddr, pfn_t *pfn) +static struct dax_device *stripe_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff) { - sector_t dev_sector, sector = pgoff * PAGE_SECTORS; struct stripe_c *sc = ti->private; - struct dax_device *dax_dev; struct block_device *bdev; + sector_t dev_sector; uint32_t stripe; - long ret; - stripe_map_sector(sc, sector, &stripe, &dev_sector); + stripe_map_sector(sc, *pgoff * PAGE_SECTORS, &stripe, &dev_sector); dev_sector += sc->stripe[stripe].physical_start; - dax_dev = sc->stripe[stripe].dev->dax_dev; bdev = sc->stripe[stripe].dev->bdev; - ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff); - if (ret) - return ret; + *pgoff = (get_start_sect(bdev) + dev_sector) >> PAGE_SECTORS_SHIFT; + return sc->stripe[stripe].dev->dax_dev; +} + +static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, + long nr_pages, void **kaddr, pfn_t *pfn) +{ + struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff); + return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } static size_t stripe_dax_copy_from_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; + struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff); - if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff)) - return 0; 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; + struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff); - 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); } static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { - int ret; - 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; + struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff); - 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; - - ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff); - if (ret) - return ret; return dax_zero_page_range(dax_dev, pgoff, nr_pages); } -- cgit v1.2.3 From cd913c76f489def1a388e3a5b10df94948ede3f5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:59 +0100 Subject: dax: return the partition offset from fs_dax_get_by_bdev Prepare for the removal of the block_device from the DAX I/O path by returning the partition offset from fs_dax_get_by_bdev so that the file systems have it at hand for use during I/O. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-26-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4eba27e75c23..4e997c02bb0a 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -637,7 +637,7 @@ static int open_table_device(struct table_device *td, dev_t dev, struct mapped_device *md) { struct block_device *bdev; - + u64 part_off; int r; BUG_ON(td->dm_dev.bdev); @@ -653,7 +653,7 @@ static int open_table_device(struct table_device *td, dev_t dev, } td->dm_dev.bdev = bdev; - td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev); + td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off); return 0; } -- cgit v1.2.3 From 30c6828a17a572aeb9e3a3bacce05fdcf1106541 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Dec 2021 09:45:07 +0100 Subject: dax: remove the DAXDEV_F_SYNC flag Remove the DAXDEV_F_SYNC flag and thus the flags argument to alloc_dax and just let the drivers call set_dax_synchronous directly. Signed-off-by: Christoph Hellwig Reviewed-by: Pankaj Gupta Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20211215084508.435401-4-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/md') diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4e997c02bb0a..f4b972af1092 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1765,7 +1765,7 @@ static struct mapped_device *alloc_dev(int minor) sprintf(md->disk->disk_name, "dm-%d", minor); if (IS_ENABLED(CONFIG_FS_DAX)) { - md->dax_dev = alloc_dax(md, &dm_dax_ops, 0); + md->dax_dev = alloc_dax(md, &dm_dax_ops); if (IS_ERR(md->dax_dev)) { md->dax_dev = NULL; goto bad; -- cgit v1.2.3 From 7ac5360cd4d02cc7e0eaf10867f599e041822f12 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Dec 2021 09:45:08 +0100 Subject: dax: remove the copy_from_iter and copy_to_iter methods These methods indirect the actual DAX read/write path. In the end pmem uses magic flush and mc safe variants and fuse and dcssblk use plain ones while device mapper picks redirects to the underlying device. Add set_dax_nocache() and set_dax_nomc() APIs to control which copy routines are used to remove indirect call from the read/write fast path as well as a lot of boilerplate code. Signed-off-by: Christoph Hellwig Reviewed-by: Vivek Goyal [virtiofs] Link: https://lore.kernel.org/r/20211215084508.435401-5-hch@lst.de Signed-off-by: Dan Williams --- drivers/md/dm-linear.c | 20 ------------ drivers/md/dm-log-writes.c | 80 ---------------------------------------------- drivers/md/dm-stripe.c | 20 ------------ drivers/md/dm.c | 52 ++---------------------------- 4 files changed, 2 insertions(+), 170 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 90de42f6743a..1b97a11d7151 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -180,22 +180,6 @@ static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } -static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct dax_device *dax_dev = linear_dax_pgoff(ti, &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 dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff); - - return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); -} - static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { @@ -206,8 +190,6 @@ static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, #else #define linear_dax_direct_access NULL -#define linear_dax_copy_from_iter NULL -#define linear_dax_copy_to_iter NULL #define linear_dax_zero_page_range NULL #endif @@ -225,8 +207,6 @@ static struct target_type linear_target = { .prepare_ioctl = linear_prepare_ioctl, .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, .dax_zero_page_range = linear_dax_zero_page_range, }; diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index cdb22e7a1d0d..139b09b06eda 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -902,51 +902,6 @@ static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limit } #if IS_ENABLED(CONFIG_FS_DAX) -static int log_dax(struct log_writes_c *lc, sector_t sector, size_t bytes, - struct iov_iter *i) -{ - struct pending_block *block; - - if (!bytes) - return 0; - - block = kzalloc(sizeof(struct pending_block), GFP_KERNEL); - if (!block) { - DMERR("Error allocating dax pending block"); - return -ENOMEM; - } - - block->data = kzalloc(bytes, GFP_KERNEL); - if (!block->data) { - DMERR("Error allocating dax data space"); - kfree(block); - return -ENOMEM; - } - - /* write data provided via the iterator */ - if (!copy_from_iter(block->data, bytes, i)) { - DMERR("Error copying dax data"); - kfree(block->data); - kfree(block); - return -EIO; - } - - /* rewind the iterator so that the block driver can use it */ - iov_iter_revert(i, bytes); - - block->datalen = bytes; - block->sector = bio_to_dev_sectors(lc, sector); - block->nr_sectors = ALIGN(bytes, lc->sectorsize) >> lc->sectorshift; - - atomic_inc(&lc->pending_blocks); - spin_lock_irq(&lc->blocks_lock); - list_add_tail(&block->list, &lc->unflushed_blocks); - spin_unlock_irq(&lc->blocks_lock); - wake_up_process(lc->log_kthread); - - return 0; -} - static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff) { @@ -964,37 +919,6 @@ static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } -static size_t log_writes_dax_copy_from_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; - struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); - int err; - - /* Don't bother doing anything if logging has been disabled */ - if (!lc->logging_enabled) - goto dax_copy; - - err = log_dax(lc, sector, bytes, i); - if (err) { - DMWARN("Error %d logging DAX write", err); - return 0; - } -dax_copy: - return dax_copy_from_iter(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 dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); - - return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); -} - static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { @@ -1005,8 +929,6 @@ static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, #else #define log_writes_dax_direct_access NULL -#define log_writes_dax_copy_from_iter NULL -#define log_writes_dax_copy_to_iter NULL #define log_writes_dax_zero_page_range NULL #endif @@ -1024,8 +946,6 @@ static struct target_type log_writes_target = { .iterate_devices = log_writes_iterate_devices, .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, .dax_zero_page_range = log_writes_dax_zero_page_range, }; diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 50dba3f39274..e566115ec0bb 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -324,22 +324,6 @@ static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } -static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct dax_device *dax_dev = stripe_dax_pgoff(ti, &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) -{ - struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff); - - return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); -} - static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { @@ -350,8 +334,6 @@ static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, #else #define stripe_dax_direct_access NULL -#define stripe_dax_copy_from_iter NULL -#define stripe_dax_copy_to_iter NULL #define stripe_dax_zero_page_range NULL #endif @@ -488,8 +470,6 @@ static struct target_type stripe_target = { .iterate_devices = stripe_iterate_devices, .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, .dax_zero_page_range = stripe_dax_zero_page_range, }; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index f4b972af1092..ce250bd274f3 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1027,54 +1027,6 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, return ret; } -static size_t dm_dax_copy_from_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_from_iter) { - ret = copy_from_iter(addr, bytes, i); - goto out; - } - ret = ti->type->dax_copy_from_iter(ti, pgoff, addr, bytes, i); - out: - dm_put_live_table(md, srcu_idx); - - 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; -} - static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages) { @@ -1770,6 +1722,8 @@ static struct mapped_device *alloc_dev(int minor) md->dax_dev = NULL; goto bad; } + set_dax_nocache(md->dax_dev); + set_dax_nomc(md->dax_dev); if (dax_add_host(md->dax_dev, md->disk)) goto bad; } @@ -3024,8 +2978,6 @@ static const struct block_device_operations dm_rq_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, .zero_page_range = dm_dax_zero_page_range, }; -- cgit v1.2.3