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, 37 insertions, 8 deletions

diff --git a/include/linux/dax.h b/include/linux/dax.h
index 9fc5f99a0ae2..e7b81634c52a 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -14,6 +14,11 @@ struct iomap_ops;
 struct iomap_iter;
 struct iomap;
 
+enum dax_access_mode {
+	DAX_ACCESS,
+	DAX_RECOVERY_WRITE,
+};
+
 struct dax_operations {
 	/*
 	 * direct_access: translate a device-relative
@@ -21,7 +26,7 @@ struct dax_operations {
 	 * number of pages available for DAX at that pfn.
 	 */
 	long (*direct_access)(struct dax_device *, pgoff_t, long,
-			void **, pfn_t *);
+			enum dax_access_mode, void **, pfn_t *);
 	/*
 	 * Validate whether this device is usable as an fsdax backing
 	 * device.
@@ -30,6 +35,12 @@ struct dax_operations {
 			sector_t, sector_t);
 	/* zero_page_range: required operation. Zero page range   */
 	int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
+	/*
+	 * recovery_write: recover a poisoned range by DAX device driver
+	 * capable of clearing poison.
+	 */
+	size_t (*recovery_write)(struct dax_device *dax_dev, pgoff_t pgoff,
+			void *addr, size_t bytes, struct iov_iter *iter);
 };
 
 #if IS_ENABLED(CONFIG_DAX)
@@ -40,6 +51,8 @@ void dax_write_cache(struct dax_device *dax_dev, bool wc);
 bool dax_write_cache_enabled(struct dax_device *dax_dev);
 bool dax_synchronous(struct dax_device *dax_dev);
 void set_dax_synchronous(struct dax_device *dax_dev);
+size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i);
 /*
  * Check if given mapping is supported by the file / underlying device.
  */
@@ -87,6 +100,11 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 {
 	return !(vma->vm_flags & VM_SYNC);
 }
+static inline size_t dax_recovery_write(struct dax_device *dax_dev,
+		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
+{
+	return 0;
+}
 #endif
 
 void set_dax_nocache(struct dax_device *dax_dev);
@@ -178,7 +196,7 @@ static inline void dax_read_unlock(int id)
 bool dax_alive(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
-		void **kaddr, pfn_t *pfn);
+		enum dax_access_mode mode, void **kaddr, pfn_t *pfn);
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
 size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index c2a3758c4aaa..47a01c7cffdf 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -20,6 +20,7 @@ struct dm_table;
 struct dm_report_zones_args;
 struct mapped_device;
 struct bio_vec;
+enum dax_access_mode;
 
 /*
  * Type of table, mapped_device's mempool and request_queue
@@ -146,10 +147,19 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
  * >= 0 : the number of bytes accessible at the address
  */
 typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn);
+		long nr_pages, enum dax_access_mode node, void **kaddr,
+		pfn_t *pfn);
 typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff,
 		size_t nr_pages);
 
+/*
+ * Returns:
+ * != 0 : number of bytes transferred
+ * 0    : recovery write failed
+ */
+typedef size_t (*dm_dax_recovery_write_fn)(struct dm_target *ti, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i);
+
 void dm_error(const char *message);
 
 struct dm_dev {
@@ -199,6 +209,7 @@ struct target_type {
 	dm_io_hints_fn io_hints;
 	dm_dax_direct_access_fn direct_access;
 	dm_dax_zero_page_range_fn dax_zero_page_range;
+	dm_dax_recovery_write_fn dax_recovery_write;
 
 	/* For internal device-mapper use. */
 	struct list_head list;
diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h
index f36be5166c19..369769ce7399 100644
--- a/include/linux/set_memory.h
+++ b/include/linux/set_memory.h
@@ -42,14 +42,14 @@ static inline bool can_set_direct_map(void)
 #endif
 #endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */
 
-#ifndef set_mce_nospec
-static inline int set_mce_nospec(unsigned long pfn, bool unmap)
+#ifdef CONFIG_X86_64
+int set_mce_nospec(unsigned long pfn);
+int clear_mce_nospec(unsigned long pfn);
+#else
+static inline int set_mce_nospec(unsigned long pfn)
 {
 	return 0;
 }
-#endif
-
-#ifndef clear_mce_nospec
 static inline int clear_mce_nospec(unsigned long pfn)
 {
 	return 0;