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()
...
#include <linux/radix-tree.h>
#include <linux/fs.h>
#include <linux/slab.h>
- #ifdef CONFIG_BLK_DEV_RAM_DAX
- #include <linux/pfn_t.h>
- #include <linux/dax.h>
- #include <linux/uio.h>
- #endif
+#include <linux/backing-dev.h>
#include <linux/uaccess.h>
disk->flags = GENHD_FL_EXT_DEVT;
sprintf(disk->disk_name, "ram%d", i);
set_capacity(disk, rd_size * 2);
+ disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
- #ifdef CONFIG_BLK_DEV_RAM_DAX
- queue_flag_set_unlocked(QUEUE_FLAG_DAX, brd->brd_queue);
- brd->dax_dev = alloc_dax(brd, disk->disk_name, &brd_dax_ops);
- if (!brd->dax_dev)
- goto out_free_inode;
- #endif
-
-
return brd;
- #ifdef CONFIG_BLK_DEV_RAM_DAX
- out_free_inode:
- kill_dax(brd->dax_dev);
- put_dax(brd->dax_dev);
- #endif
out_free_queue:
blk_cleanup_queue(brd->brd_queue);
out_free_dev:
}
EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
- static int dax_insert_mapping(struct address_space *mapping,
- struct block_device *bdev, struct dax_device *dax_dev,
- sector_t sector, size_t size, void *entry,
- struct vm_area_struct *vma, struct vm_fault *vmf)
+ static sector_t dax_iomap_sector(struct iomap *iomap, loff_t pos)
{
- unsigned long vaddr = vmf->address;
- void *ret, *kaddr;
- return iomap->blkno + (((pos & PAGE_MASK) - iomap->offset) >> 9);
++ return (iomap->addr + (pos & PAGE_MASK) - iomap->offset) >> 9;
+ }
+
+ static int dax_iomap_pfn(struct iomap *iomap, loff_t pos, size_t size,
+ pfn_t *pfnp)
+ {
+ const sector_t sector = dax_iomap_sector(iomap, pos);
pgoff_t pgoff;
+ void *kaddr;
int id, rc;
- pfn_t pfn;
+ long length;
- rc = bdev_dax_pgoff(bdev, sector, size, &pgoff);
+ rc = bdev_dax_pgoff(iomap->bdev, sector, size, &pgoff);
if (rc)
return rc;
-
id = dax_read_lock();
- rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, &pfn);
- if (rc < 0) {
- dax_read_unlock(id);
- return rc;
+ length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size),
+ &kaddr, pfnp);
+ if (length < 0) {
+ rc = length;
+ goto out;
}
+ rc = -EINVAL;
+ if (PFN_PHYS(length) < size)
+ goto out;
+ if (pfn_t_to_pfn(*pfnp) & (PHYS_PFN(size)-1))
+ goto out;
+ /* For larger pages we need devmap */
+ if (length > 1 && !pfn_t_devmap(*pfnp))
+ goto out;
+ rc = 0;
+ out:
dax_read_unlock(id);
-
- ret = dax_insert_mapping_entry(mapping, vmf, entry, sector, 0);
- if (IS_ERR(ret))
- return PTR_ERR(ret);
-
- trace_dax_insert_mapping(mapping->host, vmf, ret);
- if (vmf->flags & FAULT_FLAG_WRITE)
- return vm_insert_mixed_mkwrite(vma, vaddr, pfn);
- else
- return vm_insert_mixed(vma, vaddr, pfn);
+ return rc;
}
/*
return try_to_free_buffers(page);
}
-#ifdef CONFIG_FS_DAX
+ static bool ext4_inode_datasync_dirty(struct inode *inode)
+ {
+ journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+
+ if (journal)
+ return !jbd2_transaction_committed(journal,
+ EXT4_I(inode)->i_datasync_tid);
+ /* Any metadata buffers to write? */
+ if (!list_empty(&inode->i_mapping->private_list))
+ return true;
+ return inode->i_state & I_DIRTY_DATASYNC;
+ }
+
static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
unsigned flags, struct iomap *iomap)
{
/*
* Flags for all iomap mappings:
- */
-#define IOMAP_F_NEW 0x01 /* blocks have been newly allocated */
-/*
++ *
+ * 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_DIRTY 0x02
+#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:
projects / openwrt / staging / blogic.git / commitdiff