1 files changed, 468 insertions, 247 deletions

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index f7099adaabc0..05785ff21a8b 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -1,37 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Persistent Memory Driver
  *
  * Copyright (c) 2014-2015, Intel Corporation.
  * Copyright (c) 2015, Christoph Hellwig <hch@lst.de>.
  * Copyright (c) 2015, Boaz Harrosh <boaz@plexistor.com>.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 
-#include <asm/cacheflush.h>
 #include <linux/blkdev.h>
+#include <linux/pagemap.h>
 #include <linux/hdreg.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
+#include <linux/set_memory.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/badblocks.h>
 #include <linux/memremap.h>
+#include <linux/kstrtox.h>
 #include <linux/vmalloc.h>
 #include <linux/blk-mq.h>
-#include <linux/pfn_t.h>
 #include <linux/slab.h>
 #include <linux/uio.h>
 #include <linux/dax.h>
 #include <linux/nd.h>
+#include <linux/mm.h>
+#include <asm/cacheflush.h>
 #include "pmem.h"
+#include "btt.h"
 #include "pfn.h"
 #include "nd.h"
 
@@ -49,269 +45,447 @@ static struct nd_region *to_region(struct pmem_device *pmem)
 	return to_nd_region(to_dev(pmem)->parent);
 }
 
-static blk_status_t pmem_clear_poison(struct pmem_device *pmem,
-		phys_addr_t offset, unsigned int len)
+static phys_addr_t pmem_to_phys(struct pmem_device *pmem, phys_addr_t offset)
 {
-	struct device *dev = to_dev(pmem);
-	sector_t sector;
-	long cleared;
-	blk_status_t rc = BLK_STS_OK;
+	return pmem->phys_addr + offset;
+}
 
-	sector = (offset - pmem->data_offset) / 512;
+static sector_t to_sect(struct pmem_device *pmem, phys_addr_t offset)
+{
+	return (offset - pmem->data_offset) >> SECTOR_SHIFT;
+}
 
-	cleared = nvdimm_clear_poison(dev, pmem->phys_addr + offset, len);
-	if (cleared < len)
-		rc = BLK_STS_IOERR;
-	if (cleared > 0 && cleared / 512) {
-		cleared /= 512;
-		dev_dbg(dev, "%s: %#llx clear %ld sector%s\n", __func__,
-				(unsigned long long) sector, cleared,
-				cleared > 1 ? "s" : "");
-		badblocks_clear(&pmem->bb, sector, cleared);
-		if (pmem->bb_state)
-			sysfs_notify_dirent(pmem->bb_state);
+static phys_addr_t to_offset(struct pmem_device *pmem, sector_t sector)
+{
+	return (sector << SECTOR_SHIFT) + pmem->data_offset;
+}
+
+static void pmem_mkpage_present(struct pmem_device *pmem, phys_addr_t offset,
+		unsigned int len)
+{
+	phys_addr_t phys = pmem_to_phys(pmem, offset);
+	unsigned long pfn_start, pfn_end, pfn;
+
+	/* only pmem in the linear map supports HWPoison */
+	if (is_vmalloc_addr(pmem->virt_addr))
+		return;
+
+	pfn_start = PHYS_PFN(phys);
+	pfn_end = pfn_start + PHYS_PFN(len);
+	for (pfn = pfn_start; pfn < pfn_end; pfn++) {
+		struct page *page = pfn_to_page(pfn);
+
+		/*
+		 * Note, no need to hold a get_dev_pagemap() reference
+		 * here since we're in the driver I/O path and
+		 * outstanding I/O requests pin the dev_pagemap.
+		 */
+		if (test_and_clear_pmem_poison(page))
+			clear_mce_nospec(pfn);
 	}
+}
 
-	arch_invalidate_pmem(pmem->virt_addr + offset, len);
+static void pmem_clear_bb(struct pmem_device *pmem, sector_t sector, long blks)
+{
+	if (blks == 0)
+		return;
+	badblocks_clear(&pmem->bb, sector, blks);
+	if (pmem->bb_state)
+		sysfs_notify_dirent(pmem->bb_state);
+}
 
-	return rc;
+static long __pmem_clear_poison(struct pmem_device *pmem,
+		phys_addr_t offset, unsigned int len)
+{
+	phys_addr_t phys = pmem_to_phys(pmem, offset);
+	long cleared = nvdimm_clear_poison(to_dev(pmem), phys, len);
+
+	if (cleared > 0) {
+		pmem_mkpage_present(pmem, offset, cleared);
+		arch_invalidate_pmem(pmem->virt_addr + offset, len);
+	}
+	return cleared;
+}
+
+static blk_status_t pmem_clear_poison(struct pmem_device *pmem,
+		phys_addr_t offset, unsigned int len)
+{
+	long cleared = __pmem_clear_poison(pmem, offset, len);
+
+	if (cleared < 0)
+		return BLK_STS_IOERR;
+
+	pmem_clear_bb(pmem, to_sect(pmem, offset), cleared >> SECTOR_SHIFT);
+	if (cleared < len)
+		return BLK_STS_IOERR;
+	return BLK_STS_OK;
 }
 
 static void write_pmem(void *pmem_addr, struct page *page,
 		unsigned int off, unsigned int len)
 {
-	void *mem = kmap_atomic(page);
-
-	memcpy_flushcache(pmem_addr, mem + off, len);
-	kunmap_atomic(mem);
+	unsigned int chunk;
+	void *mem;
+
+	while (len) {
+		mem = kmap_atomic(page);
+		chunk = min_t(unsigned int, len, PAGE_SIZE - off);
+		memcpy_flushcache(pmem_addr, mem + off, chunk);
+		kunmap_atomic(mem);
+		len -= chunk;
+		off = 0;
+		page++;
+		pmem_addr += chunk;
+	}
 }
 
 static blk_status_t read_pmem(struct page *page, unsigned int off,
 		void *pmem_addr, unsigned int len)
 {
-	int rc;
-	void *mem = kmap_atomic(page);
-
-	rc = memcpy_mcsafe(mem + off, pmem_addr, len);
-	kunmap_atomic(mem);
-	if (rc)
-		return BLK_STS_IOERR;
+	unsigned int chunk;
+	unsigned long rem;
+	void *mem;
+
+	while (len) {
+		mem = kmap_atomic(page);
+		chunk = min_t(unsigned int, len, PAGE_SIZE - off);
+		rem = copy_mc_to_kernel(mem + off, pmem_addr, chunk);
+		kunmap_atomic(mem);
+		if (rem)
+			return BLK_STS_IOERR;
+		len -= chunk;
+		off = 0;
+		page++;
+		pmem_addr += chunk;
+	}
 	return BLK_STS_OK;
 }
 
-static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
-			unsigned int len, unsigned int off, bool is_write,
-			sector_t sector)
+static blk_status_t pmem_do_read(struct pmem_device *pmem,
+			struct page *page, unsigned int page_off,
+			sector_t sector, unsigned int len)
 {
-	blk_status_t rc = BLK_STS_OK;
-	bool bad_pmem = false;
-	phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
+	blk_status_t rc;
+	phys_addr_t pmem_off = to_offset(pmem, sector);
 	void *pmem_addr = pmem->virt_addr + pmem_off;
 
 	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
-		bad_pmem = true;
-
-	if (!is_write) {
-		if (unlikely(bad_pmem))
-			rc = BLK_STS_IOERR;
-		else {
-			rc = read_pmem(page, off, pmem_addr, len);
-			flush_dcache_page(page);
-		}
-	} else {
-		/*
-		 * Note that we write the data both before and after
-		 * clearing poison.  The write before clear poison
-		 * handles situations where the latest written data is
-		 * preserved and the clear poison operation simply marks
-		 * the address range as valid without changing the data.
-		 * In this case application software can assume that an
-		 * interrupted write will either return the new good
-		 * data or an error.
-		 *
-		 * However, if pmem_clear_poison() leaves the data in an
-		 * indeterminate state we need to perform the write
-		 * after clear poison.
-		 */
-		flush_dcache_page(page);
-		write_pmem(pmem_addr, page, off, len);
-		if (unlikely(bad_pmem)) {
-			rc = pmem_clear_poison(pmem, pmem_off, len);
-			write_pmem(pmem_addr, page, off, len);
-		}
-	}
+		return BLK_STS_IOERR;
 
+	rc = read_pmem(page, page_off, pmem_addr, len);
+	flush_dcache_page(page);
 	return rc;
 }
 
-/* account for REQ_FLUSH rename, replace with REQ_PREFLUSH after v4.8-rc1 */
-#ifndef REQ_FLUSH
-#define REQ_FLUSH REQ_PREFLUSH
-#endif
+static blk_status_t pmem_do_write(struct pmem_device *pmem,
+			struct page *page, unsigned int page_off,
+			sector_t sector, unsigned int len)
+{
+	phys_addr_t pmem_off = to_offset(pmem, sector);
+	void *pmem_addr = pmem->virt_addr + pmem_off;
+
+	if (unlikely(is_bad_pmem(&pmem->bb, sector, len))) {
+		blk_status_t rc = pmem_clear_poison(pmem, pmem_off, len);
+
+		if (rc != BLK_STS_OK)
+			return rc;
+	}
+
+	flush_dcache_page(page);
+	write_pmem(pmem_addr, page, page_off, len);
+
+	return BLK_STS_OK;
+}
 
-static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
+static void pmem_submit_bio(struct bio *bio)
 {
+	int ret = 0;
 	blk_status_t rc = 0;
 	bool do_acct;
 	unsigned long start;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
-	struct pmem_device *pmem = q->queuedata;
+	struct pmem_device *pmem = bio->bi_bdev->bd_disk->private_data;
 	struct nd_region *nd_region = to_region(pmem);
 
-	if (bio->bi_opf & REQ_FLUSH)
-		nvdimm_flush(nd_region);
+	if (bio->bi_opf & REQ_PREFLUSH)
+		ret = nvdimm_flush(nd_region, bio);
 
-	do_acct = nd_iostat_start(bio, &start);
+	do_acct = blk_queue_io_stat(bio->bi_bdev->bd_disk->queue);
+	if (do_acct)
+		start = bio_start_io_acct(bio);
 	bio_for_each_segment(bvec, bio, iter) {
-		rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
-				bvec.bv_offset, op_is_write(bio_op(bio)),
-				iter.bi_sector);
+		if (op_is_write(bio_op(bio)))
+			rc = pmem_do_write(pmem, bvec.bv_page, bvec.bv_offset,
+				iter.bi_sector, bvec.bv_len);
+		else
+			rc = pmem_do_read(pmem, bvec.bv_page, bvec.bv_offset,
+				iter.bi_sector, bvec.bv_len);
 		if (rc) {
 			bio->bi_status = rc;
 			break;
 		}
 	}
 	if (do_acct)
-		nd_iostat_end(bio, start);
+		bio_end_io_acct(bio, start);
 
 	if (bio->bi_opf & REQ_FUA)
-		nvdimm_flush(nd_region);
+		ret = nvdimm_flush(nd_region, bio);
 
-	bio_endio(bio);
-	return BLK_QC_T_NONE;
-}
+	if (ret)
+		bio->bi_status = errno_to_blk_status(ret);
 
-static int pmem_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
-{
-	struct pmem_device *pmem = bdev->bd_queue->queuedata;
-	blk_status_t rc;
-
-	rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, is_write, sector);
-
-	/*
-	 * The ->rw_page interface is subtle and tricky.  The core
-	 * retries on any error, so we can only invoke page_endio() in
-	 * the successful completion case.  Otherwise, we'll see crashes
-	 * caused by double completion.
-	 */
-	if (rc == 0)
-		page_endio(page, is_write, 0);
-
-	return blk_status_to_errno(rc);
+	bio_endio(bio);
 }
 
 /* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */
 __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		unsigned long *pfn)
 {
 	resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
+	sector_t sector = PFN_PHYS(pgoff) >> SECTOR_SHIFT;
+	unsigned int num = PFN_PHYS(nr_pages) >> SECTOR_SHIFT;
+	struct badblocks *bb = &pmem->bb;
+	sector_t first_bad;
+	sector_t num_bad;
 
-	if (unlikely(is_bad_pmem(&pmem->bb, PFN_PHYS(pgoff) / 512,
-					PFN_PHYS(nr_pages))))
-		return -EIO;
-	*kaddr = pmem->virt_addr + offset;
-	*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
+	if (kaddr)
+		*kaddr = pmem->virt_addr + offset;
+	if (pfn)
+		*pfn = PHYS_PFN(pmem->phys_addr + offset);
+
+	if (bb->count &&
+	    badblocks_check(bb, sector, num, &first_bad, &num_bad)) {
+		long actual_nr;
+
+		if (mode != DAX_RECOVERY_WRITE)
+			return -EHWPOISON;
+
+		/*
+		 * Set the recovery stride is set to kernel page size because
+		 * the underlying driver and firmware clear poison functions
+		 * don't appear to handle large chunk(such as 2MiB) reliably.
+		 */
+		actual_nr = PHYS_PFN(
+			PAGE_ALIGN((first_bad - sector) << SECTOR_SHIFT));
+		dev_dbg(pmem->bb.dev, "start sector(%llu), nr_pages(%ld), first_bad(%llu), actual_nr(%ld)\n",
+				sector, nr_pages, first_bad, actual_nr);
+		if (actual_nr)
+			return actual_nr;
+		return 1;
+	}
 
 	/*
-	 * If badblocks are present, limit known good range to the
-	 * requested range.
+	 * If badblocks are present but not in the range, limit known good range
+	 * to the requested range.
 	 */
-	if (unlikely(pmem->bb.count))
+	if (bb->count)
 		return nr_pages;
 	return PHYS_PFN(pmem->size - pmem->pfn_pad - offset);
 }
 
 static const struct block_device_operations pmem_fops = {
 	.owner =		THIS_MODULE,
-	.rw_page =		pmem_rw_page,
-	.revalidate_disk =	nvdimm_revalidate_disk,
+	.submit_bio =		pmem_submit_bio,
 };
 
-static long pmem_dax_direct_access(struct dax_device *dax_dev,
-		pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn)
+static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
+				    size_t nr_pages)
 {
 	struct pmem_device *pmem = dax_get_private(dax_dev);
 
-	return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn);
+	return blk_status_to_errno(pmem_do_write(pmem, ZERO_PAGE(0), 0,
+				   PFN_PHYS(pgoff) >> SECTOR_SHIFT,
+				   PAGE_SIZE));
 }
 
-static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
+static long pmem_dax_direct_access(struct dax_device *dax_dev,
+		pgoff_t pgoff, long nr_pages, enum dax_access_mode mode,
+		void **kaddr, unsigned long *pfn)
 {
-	return copy_from_iter_flushcache(addr, bytes, i);
+	struct pmem_device *pmem = dax_get_private(dax_dev);
+
+	return __pmem_direct_access(pmem, pgoff, nr_pages, mode, kaddr, pfn);
 }
 
-static void pmem_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff,
-		void *addr, size_t size)
+/*
+ * The recovery write thread started out as a normal pwrite thread and
+ * when the filesystem was told about potential media error in the
+ * range, filesystem turns the normal pwrite to a dax_recovery_write.
+ *
+ * The recovery write consists of clearing media poison, clearing page
+ * HWPoison bit, re-enable page-wide read-write permission, flush the
+ * caches and finally write.  A competing pread thread will be held
+ * off during the recovery process since data read back might not be
+ * valid, and this is achieved by clearing the badblock records after
+ * the recovery write is complete. Competing recovery write threads
+ * are already serialized by writer lock held by dax_iomap_rw().
+ */
+static size_t pmem_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
 {
-	arch_wb_cache_pmem(addr, size);
+	struct pmem_device *pmem = dax_get_private(dax_dev);
+	size_t olen, len, off;
+	phys_addr_t pmem_off;
+	struct device *dev = pmem->bb.dev;
+	long cleared;
+
+	off = offset_in_page(addr);
+	len = PFN_PHYS(PFN_UP(off + bytes));
+	if (!is_bad_pmem(&pmem->bb, PFN_PHYS(pgoff) >> SECTOR_SHIFT, len))
+		return _copy_from_iter_flushcache(addr, bytes, i);
+
+	/*
+	 * Not page-aligned range cannot be recovered. This should not
+	 * happen unless something else went wrong.
+	 */
+	if (off || !PAGE_ALIGNED(bytes)) {
+		dev_dbg(dev, "Found poison, but addr(%p) or bytes(%#zx) not page aligned\n",
+			addr, bytes);
+		return 0;
+	}
+
+	pmem_off = PFN_PHYS(pgoff) + pmem->data_offset;
+	cleared = __pmem_clear_poison(pmem, pmem_off, len);
+	if (cleared > 0 && cleared < len) {
+		dev_dbg(dev, "poison cleared only %ld out of %zu bytes\n",
+			cleared, len);
+		return 0;
+	}
+	if (cleared < 0) {
+		dev_dbg(dev, "poison clear failed: %ld\n", cleared);
+		return 0;
+	}
+
+	olen = _copy_from_iter_flushcache(addr, bytes, i);
+	pmem_clear_bb(pmem, to_sect(pmem, pmem_off), cleared >> SECTOR_SHIFT);
+
+	return olen;
 }
 
 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,
+	.zero_page_range = pmem_dax_zero_page_range,
+	.recovery_write = pmem_recovery_write,
 };
 
-static const struct attribute_group *pmem_attribute_groups[] = {
-	&dax_attribute_group,
-	NULL,
-};
+static ssize_t write_cache_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct pmem_device *pmem = dev_to_disk(dev)->private_data;
 
-static void pmem_release_queue(void *q)
+	return sprintf(buf, "%d\n", !!dax_write_cache_enabled(pmem->dax_dev));
+}
+
+static ssize_t write_cache_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
 {
-	blk_cleanup_queue(q);
+	struct pmem_device *pmem = dev_to_disk(dev)->private_data;
+	bool write_cache;
+	int rc;
+
+	rc = kstrtobool(buf, &write_cache);
+	if (rc)
+		return rc;
+	dax_write_cache(pmem->dax_dev, write_cache);
+	return len;
 }
+static DEVICE_ATTR_RW(write_cache);
 
-static void pmem_freeze_queue(void *q)
+static umode_t dax_visible(struct kobject *kobj, struct attribute *a, int n)
 {
-	blk_freeze_queue_start(q);
+#ifndef CONFIG_ARCH_HAS_PMEM_API
+	if (a == &dev_attr_write_cache.attr)
+		return 0;
+#endif
+	return a->mode;
 }
 
+static struct attribute *dax_attributes[] = {
+	&dev_attr_write_cache.attr,
+	NULL,
+};
+
+static const struct attribute_group dax_attribute_group = {
+	.name		= "dax",
+	.attrs		= dax_attributes,
+	.is_visible	= dax_visible,
+};
+
+static const struct attribute_group *pmem_attribute_groups[] = {
+	&dax_attribute_group,
+	NULL,
+};
+
 static void pmem_release_disk(void *__pmem)
 {
 	struct pmem_device *pmem = __pmem;
 
+	dax_remove_host(pmem->disk);
 	kill_dax(pmem->dax_dev);
 	put_dax(pmem->dax_dev);
 	del_gendisk(pmem->disk);
+
 	put_disk(pmem->disk);
 }
 
+static int pmem_pagemap_memory_failure(struct dev_pagemap *pgmap,
+		unsigned long pfn, unsigned long nr_pages, int mf_flags)
+{
+	struct pmem_device *pmem =
+			container_of(pgmap, struct pmem_device, pgmap);
+	u64 offset = PFN_PHYS(pfn) - pmem->phys_addr - pmem->data_offset;
+	u64 len = nr_pages << PAGE_SHIFT;
+
+	return dax_holder_notify_failure(pmem->dax_dev, offset, len, mf_flags);
+}
+
+static const struct dev_pagemap_ops fsdax_pagemap_ops = {
+	.memory_failure		= pmem_pagemap_memory_failure,
+};
+
 static int pmem_attach_disk(struct device *dev,
 		struct nd_namespace_common *ndns)
 {
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
 	struct nd_region *nd_region = to_nd_region(dev->parent);
-	struct vmem_altmap __altmap, *altmap = NULL;
-	int nid = dev_to_node(dev), fua, wbc;
+	struct queue_limits lim = {
+		.logical_block_size	= pmem_sector_size(ndns),
+		.physical_block_size	= PAGE_SIZE,
+		.max_hw_sectors		= UINT_MAX,
+		.features		= BLK_FEAT_WRITE_CACHE |
+					  BLK_FEAT_SYNCHRONOUS,
+	};
+	int nid = dev_to_node(dev), fua;
 	struct resource *res = &nsio->res;
+	struct range bb_range;
 	struct nd_pfn *nd_pfn = NULL;
 	struct dax_device *dax_dev;
 	struct nd_pfn_sb *pfn_sb;
 	struct pmem_device *pmem;
-	struct resource pfn_res;
-	struct request_queue *q;
-	struct device *gendev;
 	struct gendisk *disk;
 	void *addr;
+	int rc;
+
+	pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
+	if (!pmem)
+		return -ENOMEM;
+
+	rc = devm_namespace_enable(dev, ndns, nd_info_block_reserve());
+	if (rc)
+		return rc;
 
 	/* while nsio_rw_bytes is active, parse a pfn info block if present */
 	if (is_nd_pfn(dev)) {
 		nd_pfn = to_nd_pfn(dev);
-		altmap = nvdimm_setup_pfn(nd_pfn, &pfn_res, &__altmap);
-		if (IS_ERR(altmap))
-			return PTR_ERR(altmap);
+		rc = nvdimm_setup_pfn(nd_pfn, &pmem->pgmap);
+		if (rc)
+			return rc;
 	}
 
 	/* we're attaching a block device, disable raw namespace access */
-	devm_nsio_disable(dev, nsio);
-
-	pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
-	if (!pmem)
-		return -ENOMEM;
+	devm_namespace_disable(dev, ndns);
 
 	dev_set_drvdata(dev, pmem);
 	pmem->phys_addr = res->start;
@@ -321,7 +495,10 @@ static int pmem_attach_disk(struct device *dev,
 		dev_warn(dev, "unable to guarantee persistence of writes\n");
 		fua = 0;
 	}
-	wbc = nvdimm_has_cache(nd_region);
+	if (fua)
+		lim.features |= BLK_FEAT_FUA;
+	if (is_nd_pfn(dev) || pmem_should_map_pages(dev))
+		lim.features |= BLK_FEAT_DAX;
 
 	if (!devm_request_mem_region(dev, res->start, resource_size(res),
 				dev_name(&ndns->dev))) {
@@ -329,119 +506,146 @@ static int pmem_attach_disk(struct device *dev,
 		return -EBUSY;
 	}
 
-	q = blk_alloc_queue_node(GFP_KERNEL, dev_to_node(dev));
-	if (!q)
-		return -ENOMEM;
-
-	if (devm_add_action_or_reset(dev, pmem_release_queue, q))
-		return -ENOMEM;
+	disk = blk_alloc_disk(&lim, nid);
+	if (IS_ERR(disk))
+		return PTR_ERR(disk);
 
-	pmem->pfn_flags = PFN_DEV;
+	pmem->disk = disk;
+	pmem->pgmap.owner = pmem;
 	if (is_nd_pfn(dev)) {
-		addr = devm_memremap_pages(dev, &pfn_res, &q->q_usage_counter,
-				altmap);
+		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
+		pmem->pgmap.ops = &fsdax_pagemap_ops;
+		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pfn_sb = nd_pfn->pfn_sb;
 		pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
-		pmem->pfn_pad = resource_size(res) - resource_size(&pfn_res);
-		pmem->pfn_flags |= PFN_MAP;
-		res = &pfn_res; /* for badblocks populate */
-		res->start += pmem->data_offset;
+		pmem->pfn_pad = resource_size(res) -
+			range_len(&pmem->pgmap.range);
+		bb_range = pmem->pgmap.range;
+		bb_range.start += pmem->data_offset;
 	} else if (pmem_should_map_pages(dev)) {
-		addr = devm_memremap_pages(dev, &nsio->res,
-				&q->q_usage_counter, NULL);
-		pmem->pfn_flags |= PFN_MAP;
-	} else
+		pmem->pgmap.range.start = res->start;
+		pmem->pgmap.range.end = res->end;
+		pmem->pgmap.nr_range = 1;
+		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
+		pmem->pgmap.ops = &fsdax_pagemap_ops;
+		addr = devm_memremap_pages(dev, &pmem->pgmap);
+		bb_range = pmem->pgmap.range;
+	} else {
 		addr = devm_memremap(dev, pmem->phys_addr,
 				pmem->size, ARCH_MEMREMAP_PMEM);
+		bb_range.start =  res->start;
+		bb_range.end = res->end;
+	}
 
-	/*
-	 * At release time the queue must be frozen before
-	 * devm_memremap_pages is unwound
-	 */
-	if (devm_add_action_or_reset(dev, pmem_freeze_queue, q))
-		return -ENOMEM;
-
-	if (IS_ERR(addr))
-		return PTR_ERR(addr);
+	if (IS_ERR(addr)) {
+		rc = PTR_ERR(addr);
+		goto out;
+	}
 	pmem->virt_addr = addr;
 
-	blk_queue_write_cache(q, wbc, fua);
-	blk_queue_make_request(q, pmem_make_request);
-	blk_queue_physical_block_size(q, PAGE_SIZE);
-	blk_queue_logical_block_size(q, pmem_sector_size(ndns));
-	blk_queue_max_hw_sectors(q, UINT_MAX);
-	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
-	queue_flag_set_unlocked(QUEUE_FLAG_DAX, q);
-	q->queuedata = pmem;
-
-	disk = alloc_disk_node(0, nid);
-	if (!disk)
-		return -ENOMEM;
-	pmem->disk = disk;
-
 	disk->fops		= &pmem_fops;
-	disk->queue		= q;
-	disk->flags		= GENHD_FL_EXT_DEVT;
+	disk->private_data	= pmem;
 	nvdimm_namespace_disk_name(ndns, disk->disk_name);
 	set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset)
 			/ 512);
 	if (devm_init_badblocks(dev, &pmem->bb))
 		return -ENOMEM;
-	nvdimm_badblocks_populate(nd_region, &pmem->bb, res);
+	nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_range);
 	disk->bb = &pmem->bb;
 
-	dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops);
-	if (!dax_dev) {
-		put_disk(disk);
-		return -ENOMEM;
+	dax_dev = alloc_dax(pmem, &pmem_dax_ops);
+	if (IS_ERR(dax_dev)) {
+		rc = PTR_ERR(dax_dev);
+		if (rc != -EOPNOTSUPP)
+			goto out;
+	} else {
+		set_dax_nocache(dax_dev);
+		set_dax_nomc(dax_dev);
+		if (is_nvdimm_sync(nd_region))
+			set_dax_synchronous(dax_dev);
+		pmem->dax_dev = dax_dev;
+		rc = dax_add_host(dax_dev, disk);
+		if (rc)
+			goto out_cleanup_dax;
+		dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
 	}
-	dax_write_cache(dax_dev, wbc);
-	pmem->dax_dev = dax_dev;
-
-	gendev = disk_to_dev(disk);
-	gendev->groups = pmem_attribute_groups;
-
-	device_add_disk(dev, disk);
+	rc = device_add_disk(dev, disk, pmem_attribute_groups);
+	if (rc)
+		goto out_remove_host;
 	if (devm_add_action_or_reset(dev, pmem_release_disk, pmem))
 		return -ENOMEM;
 
-	revalidate_disk(disk);
+	nvdimm_check_and_set_ro(disk);
 
 	pmem->bb_state = sysfs_get_dirent(disk_to_dev(disk)->kobj.sd,
 					  "badblocks");
 	if (!pmem->bb_state)
 		dev_warn(dev, "'badblocks' notification disabled\n");
-
 	return 0;
+
+out_remove_host:
+	dax_remove_host(pmem->disk);
+out_cleanup_dax:
+	kill_dax(pmem->dax_dev);
+	put_dax(pmem->dax_dev);
+out:
+	put_disk(pmem->disk);
+	return rc;
 }
 
 static int nd_pmem_probe(struct device *dev)
 {
+	int ret;
 	struct nd_namespace_common *ndns;
 
 	ndns = nvdimm_namespace_common_probe(dev);
 	if (IS_ERR(ndns))
 		return PTR_ERR(ndns);
 
-	if (devm_nsio_enable(dev, to_nd_namespace_io(&ndns->dev)))
-		return -ENXIO;
-
 	if (is_nd_btt(dev))
 		return nvdimm_namespace_attach_btt(ndns);
 
 	if (is_nd_pfn(dev))
 		return pmem_attach_disk(dev, ndns);
 
-	/* if we find a valid info-block we'll come back as that personality */
-	if (nd_btt_probe(dev, ndns) == 0 || nd_pfn_probe(dev, ndns) == 0
-			|| nd_dax_probe(dev, ndns) == 0)
+	ret = devm_namespace_enable(dev, ndns, nd_info_block_reserve());
+	if (ret)
+		return ret;
+
+	ret = nd_btt_probe(dev, ndns);
+	if (ret == 0)
 		return -ENXIO;
 
-	/* ...otherwise we're just a raw pmem device */
+	/*
+	 * We have two failure conditions here, there is no
+	 * info reserver block or we found a valid info reserve block
+	 * but failed to initialize the pfn superblock.
+	 *
+	 * For the first case consider namespace as a raw pmem namespace
+	 * and attach a disk.
+	 *
+	 * For the latter, consider this a success and advance the namespace
+	 * seed.
+	 */
+	ret = nd_pfn_probe(dev, ndns);
+	if (ret == 0)
+		return -ENXIO;
+	else if (ret == -EOPNOTSUPP)
+		return ret;
+
+	ret = nd_dax_probe(dev, ndns);
+	if (ret == 0)
+		return -ENXIO;
+	else if (ret == -EOPNOTSUPP)
+		return ret;
+
+	/* probe complete, attach handles namespace enabling */
+	devm_namespace_disable(dev, ndns);
+
 	return pmem_attach_disk(dev, ndns);
 }
 
-static int nd_pmem_remove(struct device *dev)
+static void nd_pmem_remove(struct device *dev)
 {
 	struct pmem_device *pmem = dev_get_drvdata(dev);
 
@@ -449,35 +653,30 @@ static int nd_pmem_remove(struct device *dev)
 		nvdimm_namespace_detach_btt(to_nd_btt(dev));
 	else {
 		/*
-		 * Note, this assumes device_lock() context to not race
-		 * nd_pmem_notify()
+		 * Note, this assumes device_lock() context to not
+		 * race nd_pmem_notify()
 		 */
 		sysfs_put(pmem->bb_state);
 		pmem->bb_state = NULL;
 	}
-	nvdimm_flush(to_nd_region(dev->parent));
-
-	return 0;
+	nvdimm_flush(to_nd_region(dev->parent), NULL);
 }
 
 static void nd_pmem_shutdown(struct device *dev)
 {
-	nvdimm_flush(to_nd_region(dev->parent));
+	nvdimm_flush(to_nd_region(dev->parent), NULL);
 }
 
-static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
+static void pmem_revalidate_poison(struct device *dev)
 {
 	struct nd_region *nd_region;
 	resource_size_t offset = 0, end_trunc = 0;
 	struct nd_namespace_common *ndns;
 	struct nd_namespace_io *nsio;
-	struct resource res;
 	struct badblocks *bb;
+	struct range range;
 	struct kernfs_node *bb_state;
 
-	if (event != NVDIMM_REVALIDATE_POISON)
-		return;
-
 	if (is_nd_btt(dev)) {
 		struct nd_btt *nd_btt = to_nd_btt(dev);
 
@@ -508,13 +707,44 @@ static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
 		nsio = to_nd_namespace_io(&ndns->dev);
 	}
 
-	res.start = nsio->res.start + offset;
-	res.end = nsio->res.end - end_trunc;
-	nvdimm_badblocks_populate(nd_region, bb, &res);
+	range.start = nsio->res.start + offset;
+	range.end = nsio->res.end - end_trunc;
+	nvdimm_badblocks_populate(nd_region, bb, &range);
 	if (bb_state)
 		sysfs_notify_dirent(bb_state);
 }
 
+static void pmem_revalidate_region(struct device *dev)
+{
+	struct pmem_device *pmem;
+
+	if (is_nd_btt(dev)) {
+		struct nd_btt *nd_btt = to_nd_btt(dev);
+		struct btt *btt = nd_btt->btt;
+
+		nvdimm_check_and_set_ro(btt->btt_disk);
+		return;
+	}
+
+	pmem = dev_get_drvdata(dev);
+	nvdimm_check_and_set_ro(pmem->disk);
+}
+
+static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
+{
+	switch (event) {
+	case NVDIMM_REVALIDATE_POISON:
+		pmem_revalidate_poison(dev);
+		break;
+	case NVDIMM_REVALIDATE_REGION:
+		pmem_revalidate_region(dev);
+		break;
+	default:
+		dev_WARN_ONCE(dev, 1, "notify: unknown event: %d\n", event);
+		break;
+	}
+}
+
 MODULE_ALIAS("pmem");
 MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO);
 MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM);
@@ -529,17 +759,8 @@ static struct nd_device_driver nd_pmem_driver = {
 	.type = ND_DRIVER_NAMESPACE_IO | ND_DRIVER_NAMESPACE_PMEM,
 };
 
-static int __init pmem_init(void)
-{
-	return nd_driver_register(&nd_pmem_driver);
-}
-module_init(pmem_init);
-
-static void pmem_exit(void)
-{
-	driver_unregister(&nd_pmem_driver.drv);
-}
-module_exit(pmem_exit);
+module_nd_driver(nd_pmem_driver);
 
 MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
+MODULE_DESCRIPTION("NVDIMM Persistent Memory Driver");
 MODULE_LICENSE("GPL v2");