summaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-11-17 09:51:57 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-11-17 09:51:57 -0800
commita3841f94c7ecb3ede0f888d3fcfe8fb6368ddd7a (patch)
tree6625eedf10d0672068ee218bb893a5a0e1803df2 /fs/ext4
parentadeba81ac2a6451f44545874da3d181081f0ab04 (diff)
parent4247f24c23589bcc3bc3490515ef8c9497e9ae55 (diff)
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() ...
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/file.c26
-rw-r--r--fs/ext4/inode.c15
2 files changed, 35 insertions, 6 deletions
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index ad204d2724ac..a0ae27b1bc66 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -28,6 +28,7 @@
#include <linux/quotaops.h>
#include <linux/pagevec.h>
#include <linux/uio.h>
+#include <linux/mman.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -297,6 +298,7 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
*/
bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
(vmf->vma->vm_flags & VM_SHARED);
+ pfn_t pfn;
if (write) {
sb_start_pagefault(sb);
@@ -304,16 +306,20 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
down_read(&EXT4_I(inode)->i_mmap_sem);
handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
EXT4_DATA_TRANS_BLOCKS(sb));
+ if (IS_ERR(handle)) {
+ up_read(&EXT4_I(inode)->i_mmap_sem);
+ sb_end_pagefault(sb);
+ return VM_FAULT_SIGBUS;
+ }
} else {
down_read(&EXT4_I(inode)->i_mmap_sem);
}
- if (!IS_ERR(handle))
- result = dax_iomap_fault(vmf, pe_size, &ext4_iomap_ops);
- else
- result = VM_FAULT_SIGBUS;
+ result = dax_iomap_fault(vmf, pe_size, &pfn, &ext4_iomap_ops);
if (write) {
- if (!IS_ERR(handle))
- ext4_journal_stop(handle);
+ ext4_journal_stop(handle);
+ /* Handling synchronous page fault? */
+ if (result & VM_FAULT_NEEDDSYNC)
+ result = dax_finish_sync_fault(vmf, pe_size, pfn);
up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(sb);
} else {
@@ -351,6 +357,13 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
+ /*
+ * We don't support synchronous mappings for non-DAX files. At least
+ * until someone comes with a sensible use case.
+ */
+ if (!IS_DAX(file_inode(file)) && (vma->vm_flags & VM_SYNC))
+ return -EOPNOTSUPP;
+
file_accessed(file);
if (IS_DAX(file_inode(file))) {
vma->vm_ops = &ext4_dax_vm_ops;
@@ -469,6 +482,7 @@ const struct file_operations ext4_file_operations = {
.compat_ioctl = ext4_compat_ioctl,
#endif
.mmap = ext4_file_mmap,
+ .mmap_supported_flags = MAP_SYNC,
.open = ext4_file_open,
.release = ext4_release_file,
.fsync = ext4_sync_file,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 8d2b582fb141..0992d76f7ab1 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3384,6 +3384,19 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
return try_to_free_buffers(page);
}
+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)
{
@@ -3497,6 +3510,8 @@ retry:
}
iomap->flags = 0;
+ if (ext4_inode_datasync_dirty(inode))
+ iomap->flags |= IOMAP_F_DIRTY;
iomap->bdev = inode->i_sb->s_bdev;
iomap->dax_dev = sbi->s_daxdev;
iomap->offset = first_block << blkbits;