Merge tag 'libnvdimm-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm and DAX updates from Dan Williams:
 "New support for clearing memory errors when a file is in DAX mode,
  alongside with some other fixes and cleanups.

  Previously it was only possible to clear these errors using a truncate
  or hole-punch operation to trigger the filesystem to reallocate the
  block, now, any page aligned write can opportunistically clear errors
  as well.

  This change spans x86/mm, nvdimm, and fs/dax, and has received the
  appropriate sign-offs. Thanks to Jane for her work on this.

  Summary:

   - Add support for clearing memory error via pwrite(2) on DAX

   - Fix 'security overwrite' support in the presence of media errors

   - Miscellaneous cleanups and fixes for nfit_test (nvdimm unit tests)"

* tag 'libnvdimm-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  pmem: implement pmem_recovery_write()
  pmem: refactor pmem_clear_poison()
  dax: add .recovery_write dax_operation
  dax: introduce DAX_RECOVERY_WRITE dax access mode
  mce: fix set_mce_nospec to always unmap the whole page
  x86/mce: relocate set{clear}_mce_nospec() functions
  acpi/nfit: rely on mce->misc to determine poison granularity
  testing: nvdimm: asm/mce.h is not needed in nfit.c
  testing: nvdimm: iomap: make __nfit_test_ioremap a macro
  nvdimm: Allow overwrite in the presence of disabled dimms
  tools/testing/nvdimm: remove unneeded flush_workqueue

3 files changed, 23 insertions, 9 deletions

diff --git a/fs/dax.c b/fs/dax.c
index 1ac12e877f4f..4155a6107fa1 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -722,7 +722,8 @@ static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter
 	int id;
 
 	id = dax_read_lock();
-	rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, &kaddr, NULL);
+	rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, DAX_ACCESS,
+				&kaddr, NULL);
 	if (rc < 0) {
 		dax_read_unlock(id);
 		return rc;
@@ -939,7 +940,7 @@ static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size,
 
 	id = dax_read_lock();
 	length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size),
-				   NULL, pfnp);
+				   DAX_ACCESS, NULL, pfnp);
 	if (length < 0) {
 		rc = length;
 		goto out;
@@ -1048,7 +1049,7 @@ static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff,
 	void *kaddr;
 	long ret;
 
-	ret = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
+	ret = dax_direct_access(dax_dev, pgoff, 1, DAX_ACCESS, &kaddr, NULL);
 	if (ret > 0) {
 		memset(kaddr + offset, 0, size);
 		dax_flush(dax_dev, kaddr + offset, size);
@@ -1165,6 +1166,7 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 		const size_t size = ALIGN(length + offset, PAGE_SIZE);
 		pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
 		ssize_t map_len;
+		bool recovery = false;
 		void *kaddr;
 
 		if (fatal_signal_pending(current)) {
@@ -1173,7 +1175,14 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 		}
 
 		map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
-				&kaddr, NULL);
+				DAX_ACCESS, &kaddr, NULL);
+		if (map_len == -EIO && iov_iter_rw(iter) == WRITE) {
+			map_len = dax_direct_access(dax_dev, pgoff,
+					PHYS_PFN(size), DAX_RECOVERY_WRITE,
+					&kaddr, NULL);
+			if (map_len > 0)
+				recovery = true;
+		}
 		if (map_len < 0) {
 			ret = map_len;
 			break;
@@ -1185,7 +1194,10 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 		if (map_len > end - pos)
 			map_len = end - pos;
 
-		if (iov_iter_rw(iter) == WRITE)
+		if (recovery)
+			xfer = dax_recovery_write(dax_dev, pgoff, kaddr,
+					map_len, iter);
+		else if (iov_iter_rw(iter) == WRITE)
 			xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr,
 					map_len, iter);
 		else
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index d7d3a7f06862..10eb50cbf398 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -1241,8 +1241,8 @@ static int fuse_dax_mem_range_init(struct fuse_conn_dax *fcd)
 	INIT_DELAYED_WORK(&fcd->free_work, fuse_dax_free_mem_worker);
 
 	id = dax_read_lock();
-	nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size), NULL,
-				     NULL);
+	nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size),
+			DAX_ACCESS, NULL, NULL);
 	dax_read_unlock(id);
 	if (nr_pages < 0) {
 		pr_debug("dax_direct_access() returned %ld\n", nr_pages);
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 86b7dbb6a0d4..8db53fa67359 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -752,7 +752,8 @@ static void virtio_fs_cleanup_vqs(struct virtio_device *vdev,
  * offset.
  */
 static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
-				    long nr_pages, void **kaddr, pfn_t *pfn)
+				    long nr_pages, enum dax_access_mode mode,
+				    void **kaddr, pfn_t *pfn)
 {
 	struct virtio_fs *fs = dax_get_private(dax_dev);
 	phys_addr_t offset = PFN_PHYS(pgoff);
@@ -772,7 +773,8 @@ static int virtio_fs_zero_page_range(struct dax_device *dax_dev,
 	long rc;
 	void *kaddr;
 
-	rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL);
+	rc = dax_direct_access(dax_dev, pgoff, nr_pages, DAX_ACCESS, &kaddr,
+			       NULL);
 	if (rc < 0)
 		return rc;
 	memset(kaddr, 0, nr_pages << PAGE_SHIFT);