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
  ...

8 files changed, 217 insertions, 52 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index 40cdae75e3b4..ab2d96d1abee 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -38,6 +38,7 @@ config FS_DAX
 	bool "Direct Access (DAX) support"
 	depends on MMU
 	depends on !(ARM || MIPS || SPARC)
+	select DEV_PAGEMAP_OPS if (ZONE_DEVICE && !FS_DAX_LIMITED)
 	select FS_IOMAP
 	select DAX
 	help
diff --git a/fs/dax.c b/fs/dax.c
index 08656a2f2aa6..641192808bb6 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -351,6 +351,19 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping,
 	}
 }
 
+static struct page *dax_busy_page(void *entry)
+{
+	unsigned long pfn;
+
+	for_each_mapped_pfn(entry, pfn) {
+		struct page *page = pfn_to_page(pfn);
+
+		if (page_ref_count(page) > 1)
+			return page;
+	}
+	return NULL;
+}
+
 /*
  * Find radix tree entry at given index. If it points to an exceptional entry,
  * return it with the radix tree entry locked. If the radix tree doesn't
@@ -492,6 +505,90 @@ restart:
 	return entry;
 }
 
+/**
+ * dax_layout_busy_page - find first pinned page in @mapping
+ * @mapping: address space to scan for a page with ref count > 1
+ *
+ * DAX requires ZONE_DEVICE mapped pages. These pages are never
+ * 'onlined' to the page allocator so they are considered idle when
+ * page->count == 1. A filesystem uses this interface to determine if
+ * any page in the mapping is busy, i.e. for DMA, or other
+ * get_user_pages() usages.
+ *
+ * It is expected that the filesystem is holding locks to block the
+ * establishment of new mappings in this address_space. I.e. it expects
+ * to be able to run unmap_mapping_range() and subsequently not race
+ * mapping_mapped() becoming true.
+ */
+struct page *dax_layout_busy_page(struct address_space *mapping)
+{
+	pgoff_t	indices[PAGEVEC_SIZE];
+	struct page *page = NULL;
+	struct pagevec pvec;
+	pgoff_t	index, end;
+	unsigned i;
+
+	/*
+	 * In the 'limited' case get_user_pages() for dax is disabled.
+	 */
+	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
+		return NULL;
+
+	if (!dax_mapping(mapping) || !mapping_mapped(mapping))
+		return NULL;
+
+	pagevec_init(&pvec);
+	index = 0;
+	end = -1;
+
+	/*
+	 * If we race get_user_pages_fast() here either we'll see the
+	 * elevated page count in the pagevec_lookup and wait, or
+	 * get_user_pages_fast() will see that the page it took a reference
+	 * against is no longer mapped in the page tables and bail to the
+	 * get_user_pages() slow path.  The slow path is protected by
+	 * pte_lock() and pmd_lock(). New references are not taken without
+	 * holding those locks, and unmap_mapping_range() will not zero the
+	 * pte or pmd without holding the respective lock, so we are
+	 * guaranteed to either see new references or prevent new
+	 * references from being established.
+	 */
+	unmap_mapping_range(mapping, 0, 0, 1);
+
+	while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
+				min(end - index, (pgoff_t)PAGEVEC_SIZE),
+				indices)) {
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *pvec_ent = pvec.pages[i];
+			void *entry;
+
+			index = indices[i];
+			if (index >= end)
+				break;
+
+			if (!radix_tree_exceptional_entry(pvec_ent))
+				continue;
+
+			xa_lock_irq(&mapping->i_pages);
+			entry = get_unlocked_mapping_entry(mapping, index, NULL);
+			if (entry)
+				page = dax_busy_page(entry);
+			put_unlocked_mapping_entry(mapping, index, entry);
+			xa_unlock_irq(&mapping->i_pages);
+			if (page)
+				break;
+		}
+		pagevec_remove_exceptionals(&pvec);
+		pagevec_release(&pvec);
+		index++;
+
+		if (page)
+			break;
+	}
+	return page;
+}
+EXPORT_SYMBOL_GPL(dax_layout_busy_page);
+
 static int __dax_invalidate_mapping_entry(struct address_space *mapping,
 					  pgoff_t index, bool trunc)
 {
@@ -912,7 +1009,6 @@ static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry,
 	unsigned long vaddr = vmf->address;
 	vm_fault_t ret = VM_FAULT_NOPAGE;
 	struct page *zero_page;
-	void *entry2;
 	pfn_t pfn;
 
 	zero_page = ZERO_PAGE(0);
@@ -922,13 +1018,8 @@ static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry,
 	}
 
 	pfn = page_to_pfn_t(zero_page);
-	entry2 = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
-			RADIX_DAX_ZERO_PAGE, false);
-	if (IS_ERR(entry2)) {
-		ret = VM_FAULT_SIGBUS;
-		goto out;
-	}
-
+	dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_ZERO_PAGE,
+			false);
 	ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
 out:
 	trace_dax_load_hole(inode, vmf, ret);
@@ -991,6 +1082,7 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	struct iov_iter *iter = data;
 	loff_t end = pos + length, done = 0;
 	ssize_t ret = 0;
+	size_t xfer;
 	int id;
 
 	if (iov_iter_rw(iter) == READ) {
@@ -1054,18 +1146,20 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		 * vfs_write(), depending on which operation we are doing.
 		 */
 		if (iov_iter_rw(iter) == WRITE)
-			map_len = dax_copy_from_iter(dax_dev, pgoff, kaddr,
+			xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr,
 					map_len, iter);
 		else
-			map_len = copy_to_iter(kaddr, map_len, iter);
-		if (map_len <= 0) {
-			ret = map_len ? map_len : -EFAULT;
-			break;
-		}
+			xfer = dax_copy_to_iter(dax_dev, pgoff, kaddr,
+					map_len, iter);
 
-		pos += map_len;
-		length -= map_len;
-		done += map_len;
+		pos += xfer;
+		length -= xfer;
+		done += xfer;
+
+		if (xfer == 0)
+			ret = -EFAULT;
+		if (xfer < map_len)
+			break;
 	}
 	dax_read_unlock(id);
 
@@ -1240,10 +1334,6 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 
 		entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
 						 0, write && !sync);
-		if (IS_ERR(entry)) {
-			error = PTR_ERR(entry);
-			goto error_finish_iomap;
-		}
 
 		/*
 		 * If we are doing synchronous page fault and inode needs fsync,
@@ -1324,8 +1414,6 @@ static vm_fault_t dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
 	pfn = page_to_pfn_t(zero_page);
 	ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
 			RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false);
-	if (IS_ERR(ret))
-		goto fallback;
 
 	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
 	if (!pmd_none(*(vmf->pmd))) {
@@ -1447,8 +1535,6 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 
 		entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
 						RADIX_DAX_PMD, write && !sync);
-		if (IS_ERR(entry))
-			goto finish_iomap;
 
 		/*
 		 * If we are doing synchronous page fault and inode needs fsync,
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 0e3fb8978344..bed07dfbb85e 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -312,7 +312,7 @@ restart:
 	if (error <= 0)
 		return error;
 
-	error = xfs_break_layouts(inode, iolock);
+	error = xfs_break_layouts(inode, iolock, BREAK_WRITE);
 	if (error)
 		return error;
 
@@ -731,6 +731,69 @@ xfs_file_write_iter(
 	return xfs_file_buffered_aio_write(iocb, from);
 }
 
+static void
+xfs_wait_dax_page(
+	struct inode		*inode,
+	bool			*did_unlock)
+{
+	struct xfs_inode        *ip = XFS_I(inode);
+
+	*did_unlock = true;
+	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
+	schedule();
+	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
+}
+
+static int
+xfs_break_dax_layouts(
+	struct inode		*inode,
+	uint			iolock,
+	bool			*did_unlock)
+{
+	struct page		*page;
+
+	ASSERT(xfs_isilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL));
+
+	page = dax_layout_busy_page(inode->i_mapping);
+	if (!page)
+		return 0;
+
+	return ___wait_var_event(&page->_refcount,
+			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
+			0, 0, xfs_wait_dax_page(inode, did_unlock));
+}
+
+int
+xfs_break_layouts(
+	struct inode		*inode,
+	uint			*iolock,
+	enum layout_break_reason reason)
+{
+	bool			retry;
+	int			error;
+
+	ASSERT(xfs_isilocked(XFS_I(inode), XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
+
+	do {
+		retry = false;
+		switch (reason) {
+		case BREAK_UNMAP:
+			error = xfs_break_dax_layouts(inode, *iolock, &retry);
+			if (error || retry)
+				break;
+			/* fall through */
+		case BREAK_WRITE:
+			error = xfs_break_leased_layouts(inode, iolock, &retry);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			error = -EINVAL;
+		}
+	} while (error == 0 && retry);
+
+	return error;
+}
+
 #define	XFS_FALLOC_FL_SUPPORTED						\
 		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
 		 FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |	\
@@ -747,7 +810,7 @@ xfs_file_fallocate(
 	struct xfs_inode	*ip = XFS_I(inode);
 	long			error;
 	enum xfs_prealloc_flags	flags = 0;
-	uint			iolock = XFS_IOLOCK_EXCL;
+	uint			iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	loff_t			new_size = 0;
 	bool			do_file_insert = false;
 
@@ -757,13 +820,10 @@ xfs_file_fallocate(
 		return -EOPNOTSUPP;
 
 	xfs_ilock(ip, iolock);
-	error = xfs_break_layouts(inode, &iolock);
+	error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
 	if (error)
 		goto out_unlock;
 
-	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
-	iolock |= XFS_MMAPLOCK_EXCL;
-
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		error = xfs_free_file_space(ip, offset, len);
 		if (error)
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 00fee6824745..a91d9fb1effc 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -379,6 +379,20 @@ static inline void xfs_ifunlock(struct xfs_inode *ip)
 					>> XFS_ILOCK_SHIFT)
 
 /*
+ * Layouts are broken in the BREAK_WRITE case to ensure that
+ * layout-holders do not collide with local writes. Additionally,
+ * layouts are broken in the BREAK_UNMAP case to make sure the
+ * layout-holder has a consistent view of the file's extent map. While
+ * BREAK_WRITE breaks can be satisfied by recalling FL_LAYOUT leases,
+ * BREAK_UNMAP breaks additionally require waiting for busy dax-pages to
+ * go idle.
+ */
+enum layout_break_reason {
+        BREAK_WRITE,
+        BREAK_UNMAP,
+};
+
+/*
  * For multiple groups support: if S_ISGID bit is set in the parent
  * directory, group of new file is set to that of the parent, and
  * new subdirectory gets S_ISGID bit from parent.
@@ -453,6 +467,8 @@ enum xfs_prealloc_flags {
 
 int	xfs_update_prealloc_flags(struct xfs_inode *ip,
 				  enum xfs_prealloc_flags flags);
+int	xfs_break_layouts(struct inode *inode, uint *iolock,
+		enum layout_break_reason reason);
 
 /* from xfs_iops.c */
 extern void xfs_setup_inode(struct xfs_inode *ip);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 5dd9e22b4a4c..32b680522abd 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -39,7 +39,6 @@
 #include "xfs_icache.h"
 #include "xfs_symlink.h"
 #include "xfs_trans.h"
-#include "xfs_pnfs.h"
 #include "xfs_acl.h"
 #include "xfs_btree.h"
 #include <linux/fsmap.h>
@@ -614,7 +613,7 @@ xfs_ioc_space(
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct iattr		iattr;
 	enum xfs_prealloc_flags	flags = 0;
-	uint			iolock = XFS_IOLOCK_EXCL;
+	uint			iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	int			error;
 
 	/*
@@ -644,13 +643,10 @@ xfs_ioc_space(
 		return error;
 
 	xfs_ilock(ip, iolock);
-	error = xfs_break_layouts(inode, &iolock);
+	error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
 	if (error)
 		goto out_unlock;
 
-	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
-	iolock |= XFS_MMAPLOCK_EXCL;
-
 	switch (bf->l_whence) {
 	case 0: /*SEEK_SET*/
 		break;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index b0eb49bb4918..3b4be06fdaa5 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -37,7 +37,6 @@
 #include "xfs_da_btree.h"
 #include "xfs_dir2.h"
 #include "xfs_trans_space.h"
-#include "xfs_pnfs.h"
 #include "xfs_iomap.h"
 
 #include <linux/capability.h>
@@ -1030,14 +1029,19 @@ xfs_vn_setattr(
 	int			error;
 
 	if (iattr->ia_valid & ATTR_SIZE) {
-		struct xfs_inode	*ip = XFS_I(d_inode(dentry));
-		uint			iolock = XFS_IOLOCK_EXCL;
+		struct inode		*inode = d_inode(dentry);
+		struct xfs_inode	*ip = XFS_I(inode);
+		uint			iolock;
 
-		error = xfs_break_layouts(d_inode(dentry), &iolock);
-		if (error)
+		xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
+		iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
+
+		error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
+		if (error) {
+			xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 			return error;
+		}
 
-		xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
 		error = xfs_vn_setattr_size(dentry, iattr);
 		xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 	} else {
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index aa6c5c193f45..f44c3599527d 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -31,19 +31,20 @@
  * rules in the page fault path we don't bother.
  */
 int
-xfs_break_layouts(
+xfs_break_leased_layouts(
 	struct inode		*inode,
-	uint			*iolock)
+	uint			*iolock,
+	bool			*did_unlock)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	int			error;
 
-	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
-
 	while ((error = break_layout(inode, false) == -EWOULDBLOCK)) {
 		xfs_iunlock(ip, *iolock);
+		*did_unlock = true;
 		error = break_layout(inode, true);
-		*iolock = XFS_IOLOCK_EXCL;
+		*iolock &= ~XFS_IOLOCK_SHARED;
+		*iolock |= XFS_IOLOCK_EXCL;
 		xfs_ilock(ip, *iolock);
 	}
 
@@ -120,8 +121,8 @@ xfs_fs_map_blocks(
 	 * Lock out any other I/O before we flush and invalidate the pagecache,
 	 * and then hand out a layout to the remote system.  This is very
 	 * similar to direct I/O, except that the synchronization is much more
-	 * complicated.  See the comment near xfs_break_layouts for a detailed
-	 * explanation.
+	 * complicated.  See the comment near xfs_break_leased_layouts
+	 * for a detailed explanation.
 	 */
 	xfs_ilock(ip, XFS_IOLOCK_EXCL);
 
diff --git a/fs/xfs/xfs_pnfs.h b/fs/xfs/xfs_pnfs.h
index bf45951e28fe..940c6c2ad88c 100644
--- a/fs/xfs/xfs_pnfs.h
+++ b/fs/xfs/xfs_pnfs.h
@@ -9,10 +9,11 @@ int xfs_fs_map_blocks(struct inode *inode, loff_t offset, u64 length,
 int xfs_fs_commit_blocks(struct inode *inode, struct iomap *maps, int nr_maps,
 		struct iattr *iattr);
 
-int xfs_break_layouts(struct inode *inode, uint *iolock);
+int xfs_break_leased_layouts(struct inode *inode, uint *iolock,
+		bool *did_unlock);
 #else
 static inline int
-xfs_break_layouts(struct inode *inode, uint *iolock)
+xfs_break_leased_layouts(struct inode *inode, uint *iolock, bool *did_unlock)
 {
 	return 0;
 }