Merge tag 'libnvdimm-for-4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm and dax updates from Dan Williams:
 "Save for a few late fixes, all of these commits have shipped in -next
  releases since before the merge window opened, and 0day has given a
  build success notification.

  The ext4 touches came from Jan, and the xfs touches have Darrick's
  reviewed-by. An xfstest for the MAP_SYNC feature has been through
  a few round of reviews and is on track to be merged.

   - Introduce MAP_SYNC and MAP_SHARED_VALIDATE, a mechanism to enable
     'userspace flush' of persistent memory updates via filesystem-dax
     mappings. It arranges for any filesystem metadata updates that may
     be required to satisfy a write fault to also be flushed ("on disk")
     before the kernel returns to userspace from the fault handler.
     Effectively every write-fault that dirties metadata completes an
     fsync() before returning from the fault handler. The new
     MAP_SHARED_VALIDATE mapping type guarantees that the MAP_SYNC flag
     is validated as supported by the filesystem's ->mmap() file
     operation.

   - Add support for the standard ACPI 6.2 label access methods that
     replace the NVDIMM_FAMILY_INTEL (vendor specific) label methods.
     This enables interoperability with environments that only implement
     the standardized methods.

   - Add support for the ACPI 6.2 NVDIMM media error injection methods.

   - Add support for the NVDIMM_FAMILY_INTEL v1.6 DIMM commands for
     latch last shutdown status, firmware update, SMART error injection,
     and SMART alarm threshold control.

   - Cleanup physical address information disclosures to be root-only.

   - Fix revalidation of the DIMM "locked label area" status to support
     dynamic unlock of the label area.

   - Expand unit test infrastructure to mock the ACPI 6.2 Translate SPA
     (system-physical-address) command and error injection commands.

  Acknowledgements that came after the commits were pushed to -next:

   - 957ac8c421ad ("dax: fix PMD faults on zero-length files"):
       Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>

   - a39e596baa07 ("xfs: support for synchronous DAX faults") and
     7b565c9f965b ("xfs: Implement xfs_filemap_pfn_mkwrite() using __xfs_filemap_fault()")
        Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>"

* tag 'libnvdimm-for-4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (49 commits)
  acpi, nfit: add 'Enable Latch System Shutdown Status' command support
  dax: fix general protection fault in dax_alloc_inode
  dax: fix PMD faults on zero-length files
  dax: stop requiring a live device for dax_flush()
  brd: remove dax support
  dax: quiet bdev_dax_supported()
  fs, dax: unify IOMAP_F_DIRTY read vs write handling policy in the dax core
  tools/testing/nvdimm: unit test clear-error commands
  acpi, nfit: validate commands against the device type
  tools/testing/nvdimm: stricter bounds checking for error injection commands
  xfs: support for synchronous DAX faults
  xfs: Implement xfs_filemap_pfn_mkwrite() using __xfs_filemap_fault()
  ext4: Support for synchronous DAX faults
  ext4: Simplify error handling in ext4_dax_huge_fault()
  dax: Implement dax_finish_sync_fault()
  dax, iomap: Add support for synchronous faults
  mm: Define MAP_SYNC and VM_SYNC flags
  dax: Allow tuning whether dax_insert_mapping_entry() dirties entry
  dax: Allow dax_iomap_fault() to return pfn
  dax: Fix comment describing dax_iomap_fault()
  ...

7 files changed, 79 insertions, 9 deletions

diff --git a/include/linux/dax.h b/include/linux/dax.h
index 895e16fcc62d..5258346c558c 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -96,7 +96,9 @@ bool dax_write_cache_enabled(struct dax_device *dax_dev);
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops);
 int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
-		    const struct iomap_ops *ops);
+		    pfn_t *pfnp, const struct iomap_ops *ops);
+int dax_finish_sync_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+			  pfn_t pfn);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 269086440071..a2b5d64ea503 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1702,6 +1702,7 @@ struct file_operations {
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
+	unsigned long mmap_supported_flags;
 	int (*open) (struct inode *, struct file *);
 	int (*flush) (struct file *, fl_owner_t id);
 	int (*release) (struct inode *, struct file *);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index ca10767ab73d..19a07de28212 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -21,9 +21,13 @@ struct vm_fault;
 
 /*
  * Flags for all iomap mappings:
+ *
+ * IOMAP_F_DIRTY indicates the inode has uncommitted metadata needed to access
+ * written data and requires fdatasync to commit them to persistent storage.
  */
 #define IOMAP_F_NEW		0x01	/* blocks have been newly allocated */
 #define IOMAP_F_BOUNDARY	0x02	/* mapping ends at metadata boundary */
+#define IOMAP_F_DIRTY		0x04	/* uncommitted metadata */
 
 /*
  * Flags that only need to be reported for IOMAP_REPORT requests:
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 606b6bce3a5b..296d1e0ea87b 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1367,6 +1367,7 @@ int jbd2_log_start_commit(journal_t *journal, tid_t tid);
 int __jbd2_log_start_commit(journal_t *journal, tid_t tid);
 int jbd2_journal_start_commit(journal_t *journal, tid_t *tid);
 int jbd2_log_wait_commit(journal_t *journal, tid_t tid);
+int jbd2_transaction_committed(journal_t *journal, tid_t tid);
 int jbd2_complete_transaction(journal_t *journal, tid_t tid);
 int jbd2_log_do_checkpoint(journal_t *journal);
 int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid);
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 3eaad2fbf284..f8109ddb5ef1 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -18,6 +18,18 @@
 #include <linux/sizes.h>
 #include <linux/types.h>
 #include <linux/uuid.h>
+#include <linux/spinlock.h>
+
+struct badrange_entry {
+	u64 start;
+	u64 length;
+	struct list_head list;
+};
+
+struct badrange {
+	struct list_head list;
+	spinlock_t lock;
+};
 
 enum {
 	/* when a dimm supports both PMEM and BLK access a label is required */
@@ -129,9 +141,12 @@ static inline struct nd_blk_region_desc *to_blk_region_desc(
 
 }
 
-int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length);
-void nvdimm_forget_poison(struct nvdimm_bus *nvdimm_bus,
-		phys_addr_t start, unsigned int len);
+void badrange_init(struct badrange *badrange);
+int badrange_add(struct badrange *badrange, u64 addr, u64 length);
+void badrange_forget(struct badrange *badrange, phys_addr_t start,
+		unsigned int len);
+int nvdimm_bus_add_badrange(struct nvdimm_bus *nvdimm_bus, u64 addr,
+		u64 length);
 struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
 		struct nvdimm_bus_descriptor *nfit_desc);
 void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c7b1d617dff6..ee073146aaa7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -199,6 +199,7 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
 #define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
+#define VM_SYNC		0x00800000	/* Synchronous page faults */
 #define VM_ARCH_1	0x01000000	/* Architecture-specific flag */
 #define VM_WIPEONFORK	0x02000000	/* Wipe VMA contents in child. */
 #define VM_DONTDUMP	0x04000000	/* Do not include in the core dump */
@@ -1191,8 +1192,9 @@ static inline void clear_page_pfmemalloc(struct page *page)
 #define VM_FAULT_RETRY	0x0400	/* ->fault blocked, must retry */
 #define VM_FAULT_FALLBACK 0x0800	/* huge page fault failed, fall back to small */
 #define VM_FAULT_DONE_COW   0x1000	/* ->fault has fully handled COW */
-
-#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
+#define VM_FAULT_NEEDDSYNC  0x2000	/* ->fault did not modify page tables
+					 * and needs fsync() to complete (for
+					 * synchronous page faults in DAX) */
 
 #define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | \
 			 VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \
@@ -1210,7 +1212,8 @@ static inline void clear_page_pfmemalloc(struct page *page)
 	{ VM_FAULT_LOCKED,		"LOCKED" }, \
 	{ VM_FAULT_RETRY,		"RETRY" }, \
 	{ VM_FAULT_FALLBACK,		"FALLBACK" }, \
-	{ VM_FAULT_DONE_COW,		"DONE_COW" }
+	{ VM_FAULT_DONE_COW,		"DONE_COW" }, \
+	{ VM_FAULT_NEEDDSYNC,		"NEEDDSYNC" }
 
 /* Encode hstate index for a hwpoisoned large page */
 #define VM_FAULT_SET_HINDEX(x) ((x) << 12)
diff --git a/include/linux/mman.h b/include/linux/mman.h
index 7c87b6652244..6a4d1caaff5c 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -8,6 +8,48 @@
 #include <linux/atomic.h>
 #include <uapi/linux/mman.h>
 
+/*
+ * Arrange for legacy / undefined architecture specific flags to be
+ * ignored by mmap handling code.
+ */
+#ifndef MAP_32BIT
+#define MAP_32BIT 0
+#endif
+#ifndef MAP_HUGE_2MB
+#define MAP_HUGE_2MB 0
+#endif
+#ifndef MAP_HUGE_1GB
+#define MAP_HUGE_1GB 0
+#endif
+#ifndef MAP_UNINITIALIZED
+#define MAP_UNINITIALIZED 0
+#endif
+#ifndef MAP_SYNC
+#define MAP_SYNC 0
+#endif
+
+/*
+ * The historical set of flags that all mmap implementations implicitly
+ * support when a ->mmap_validate() op is not provided in file_operations.
+ */
+#define LEGACY_MAP_MASK (MAP_SHARED \
+		| MAP_PRIVATE \
+		| MAP_FIXED \
+		| MAP_ANONYMOUS \
+		| MAP_DENYWRITE \
+		| MAP_EXECUTABLE \
+		| MAP_UNINITIALIZED \
+		| MAP_GROWSDOWN \
+		| MAP_LOCKED \
+		| MAP_NORESERVE \
+		| MAP_POPULATE \
+		| MAP_NONBLOCK \
+		| MAP_STACK \
+		| MAP_HUGETLB \
+		| MAP_32BIT \
+		| MAP_HUGE_2MB \
+		| MAP_HUGE_1GB)
+
 extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
 extern unsigned long sysctl_overcommit_kbytes;
@@ -64,8 +106,9 @@ static inline bool arch_validate_prot(unsigned long prot)
  * ("bit1" and "bit2" must be single bits)
  */
 #define _calc_vm_trans(x, bit1, bit2) \
+  ((!(bit1) || !(bit2)) ? 0 : \
   ((bit1) <= (bit2) ? ((x) & (bit1)) * ((bit2) / (bit1)) \
-   : ((x) & (bit1)) / ((bit1) / (bit2)))
+   : ((x) & (bit1)) / ((bit1) / (bit2))))
 
 /*
  * Combine the mmap "prot" argument into "vm_flags" used internally.
@@ -87,7 +130,8 @@ calc_vm_flag_bits(unsigned long flags)
 {
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
 	       _calc_vm_trans(flags, MAP_DENYWRITE,  VM_DENYWRITE ) |
-	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    );
+	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    ) |
+	       _calc_vm_trans(flags, MAP_SYNC,	     VM_SYNC      );
 }
 
 unsigned long vm_commit_limit(void);