Merge tag 'libnvdimm-for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "This adds a user for the new 'bytes-remaining' updates to
  memcpy_mcsafe() that you already received through Ingo via the
  x86-dax- for-linus pull.

  Not included here, but still targeting this cycle, is support for
  handling memory media errors (poison) consumed via userspace dax
  mappings.

  Summary:

   - DAX broke a fundamental assumption of truncate of file mapped
     pages. The truncate path assumed that it is safe to disconnect a
     pinned page from a file and let the filesystem reclaim the physical
     block. With DAX the page is equivalent to the filesystem block.
     Introduce dax_layout_busy_page() to enable filesystems to wait for
     pinned DAX pages to be released. Without this wait a filesystem
     could allocate blocks under active device-DMA to a new file.

   - DAX arranges for the block layer to be bypassed and uses
     dax_direct_access() + copy_to_iter() to satisfy read(2) calls.
     However, the memcpy_mcsafe() facility is available through the pmem
     block driver. In order to safely handle media errors, via the DAX
     block-layer bypass, introduce copy_to_iter_mcsafe().

   - Fix cache management policy relative to the ACPI NFIT Platform
     Capabilities Structure to properly elide cache flushes when they
     are not necessary. The table indicates whether CPU caches are
     power-fail protected. Clarify that a deep flush is always performed
     on REQ_{FUA,PREFLUSH} requests"

* tag 'libnvdimm-for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (21 commits)
  dax: Use dax_write_cache* helpers
  libnvdimm, pmem: Do not flush power-fail protected CPU caches
  libnvdimm, pmem: Unconditionally deep flush on *sync
  libnvdimm, pmem: Complete REQ_FLUSH => REQ_PREFLUSH
  acpi, nfit: Remove ecc_unit_size
  dax: dax_insert_mapping_entry always succeeds
  libnvdimm, e820: Register all pmem resources
  libnvdimm: Debug probe times
  linvdimm, pmem: Preserve read-only setting for pmem devices
  x86, nfit_test: Add unit test for memcpy_mcsafe()
  pmem: Switch to copy_to_iter_mcsafe()
  dax: Report bytes remaining in dax_iomap_actor()
  dax: Introduce a ->copy_to_iter dax operation
  uio, lib: Fix CONFIG_ARCH_HAS_UACCESS_MCSAFE compilation
  xfs, dax: introduce xfs_break_dax_layouts()
  xfs: prepare xfs_break_layouts() for another layout type
  xfs: prepare xfs_break_layouts() to be called with XFS_MMAPLOCK_EXCL
  mm, fs, dax: handle layout changes to pinned dax mappings
  mm: fix __gup_device_huge vs unmap
  mm: introduce MEMORY_DEVICE_FS_DAX and CONFIG_DEV_PAGEMAP_OPS
  ...

1 files changed, 36 insertions, 10 deletions

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index e023d6aa22b5..68940356cad3 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -164,11 +164,6 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct 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_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 {
 	blk_status_t rc = 0;
@@ -179,7 +174,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	struct pmem_device *pmem = q->queuedata;
 	struct nd_region *nd_region = to_region(pmem);
 
-	if (bio->bi_opf & REQ_FLUSH)
+	if (bio->bi_opf & REQ_PREFLUSH)
 		nvdimm_flush(nd_region);
 
 	do_acct = nd_iostat_start(bio, &start);
@@ -264,9 +259,16 @@ 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_mcsafe(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[] = {
@@ -294,12 +296,33 @@ static void pmem_release_disk(void *__pmem)
 	put_disk(pmem->disk);
 }
 
+static void pmem_release_pgmap_ops(void *__pgmap)
+{
+	dev_pagemap_put_ops();
+}
+
+static void fsdax_pagefree(struct page *page, void *data)
+{
+	wake_up_var(&page->_refcount);
+}
+
+static int setup_pagemap_fsdax(struct device *dev, struct dev_pagemap *pgmap)
+{
+	dev_pagemap_get_ops();
+	if (devm_add_action_or_reset(dev, pmem_release_pgmap_ops, pgmap))
+		return -ENOMEM;
+	pgmap->type = MEMORY_DEVICE_FS_DAX;
+	pgmap->page_free = fsdax_pagefree;
+
+	return 0;
+}
+
 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);
-	int nid = dev_to_node(dev), fua, wbc;
+	int nid = dev_to_node(dev), fua;
 	struct resource *res = &nsio->res;
 	struct resource bb_res;
 	struct nd_pfn *nd_pfn = NULL;
@@ -335,7 +358,6 @@ 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 (!devm_request_mem_region(dev, res->start, resource_size(res),
 				dev_name(&ndns->dev))) {
@@ -353,6 +375,8 @@ static int pmem_attach_disk(struct device *dev,
 	pmem->pfn_flags = PFN_DEV;
 	pmem->pgmap.ref = &q->q_usage_counter;
 	if (is_nd_pfn(dev)) {
+		if (setup_pagemap_fsdax(dev, &pmem->pgmap))
+			return -ENOMEM;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pfn_sb = nd_pfn->pfn_sb;
 		pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
@@ -364,6 +388,8 @@ static int pmem_attach_disk(struct device *dev,
 	} else if (pmem_should_map_pages(dev)) {
 		memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res));
 		pmem->pgmap.altmap_valid = false;
+		if (setup_pagemap_fsdax(dev, &pmem->pgmap))
+			return -ENOMEM;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pmem->pfn_flags |= PFN_MAP;
 		memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
@@ -382,7 +408,7 @@ static int pmem_attach_disk(struct device *dev,
 		return PTR_ERR(addr);
 	pmem->virt_addr = addr;
 
-	blk_queue_write_cache(q, wbc, fua);
+	blk_queue_write_cache(q, true, 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));
@@ -413,7 +439,7 @@ static int pmem_attach_disk(struct device *dev,
 		put_disk(disk);
 		return -ENOMEM;
 	}
-	dax_write_cache(dax_dev, wbc);
+	dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
 	pmem->dax_dev = dax_dev;
 
 	gendev = disk_to_dev(disk);