Merge tag '5.4-rc1-4.14' of https://kernel.googlesource.com/pub/scm/l…

…inux/kernel/git/jaegeuk/f2fs-stable into neutrino-msm-hotdogb-4.14

Release 5.4-rc1-4.14
HEAD: d9b27dd ("f2fs: add a condition to detect overflow in f2fs_ioc_gc_range()")

Signed-off-by: Adam W. Willis <return.of.octobot@gmail.com>

Conflicts:
	fs/crypto/Makefile
	fs/crypto/bio.c
	fs/crypto/crypto.c
	fs/crypto/fscrypt_private.h
	fs/crypto/keyinfo.c
	fs/ext4/inode.c
	fs/ext4/ioctl.c
	fs/ext4/page-io.c
	fs/ext4/readpage.c
	fs/f2fs/data.c
	fs/f2fs/inode.c
	include/linux/fscrypt.h
	include/uapi/linux/fs.h

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -243,3 +243,18 @@ Description:
 		 - Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list
 		 - [h] means add/del hot file extension
 		 - [c] means add/del cold file extension
+
+What:		/sys/fs/f2fs/<disk>/unusable
+Date		April 2019
+Contact:	"Daniel Rosenberg" <drosen@google.com>
+Description:
+		If checkpoint=disable, it displays the number of blocks that are unusable.
+                If checkpoint=enable it displays the enumber of blocks that would be unusable
+                if checkpoint=disable were to be set.
+
+What:		/sys/fs/f2fs/<disk>/encoding
+Date		July 2019
+Contact:	"Daniel Rosenberg" <drosen@google.com>
+Description:
+		Displays name and version of the encoding set for the filesystem.
+                If no encoding is set, displays (none)

Documentation/dontdiff

@@ -177,6 +177,7 @@ mkprep
 mkregtable
 mktables
 mktree
+mkutf8data
 modpost
 modules.builtin
 modules.order
@@ -255,6 +256,7 @@ vsyscall_32.lds
 wanxlfw.inc
 uImage
 unifdef
+utf8data.h
 wakeup.bin
 wakeup.elf
 wakeup.lds

Documentation/filesystems/f2fs.txt

@@ -157,6 +157,11 @@ noinline_data          Disable the inline data feature, inline data feature is
                        enabled by default.
 data_flush             Enable data flushing before checkpoint in order to
                        persist data of regular and symlink.
+reserve_root=%d        Support configuring reserved space which is used for
+                       allocation from a privileged user with specified uid or
+                       gid, unit: 4KB, the default limit is 0.2% of user blocks.
+resuid=%d              The user ID which may use the reserved blocks.
+resgid=%d              The group ID which may use the reserved blocks.
 fault_injection=%d     Enable fault injection in all supported types with
                        specified injection rate.
 fault_type=%d          Support configuring fault injection type, should be
@@ -214,11 +219,22 @@ fsync_mode=%s          Control the policy of fsync. Currently supports "posix",
                        non-atomic files likewise "nobarrier" mount option.
 test_dummy_encryption  Enable dummy encryption, which provides a fake fscrypt
                        context. The fake fscrypt context is used by xfstests.
-checkpoint=%s          Set to "disable" to turn off checkpointing. Set to "enable"
+checkpoint=%s[:%u[%]]     Set to "disable" to turn off checkpointing. Set to "enable"
                        to reenable checkpointing. Is enabled by default. While
                        disabled, any unmounting or unexpected shutdowns will cause
                        the filesystem contents to appear as they did when the
                        filesystem was mounted with that option.
+                       While mounting with checkpoint=disabled, the filesystem must
+                       run garbage collection to ensure that all available space can
+                       be used. If this takes too much time, the mount may return
+                       EAGAIN. You may optionally add a value to indicate how much
+                       of the disk you would be willing to temporarily give up to
+                       avoid additional garbage collection. This can be given as a
+                       number of blocks, or as a percent. For instance, mounting
+                       with checkpoint=disable:100% would always succeed, but it may
+                       hide up to all remaining free space. The actual space that
+                       would be unusable can be viewed at /sys/fs/f2fs/<disk>/unusable
+                       This space is reclaimed once checkpoint=enable.
 
 ================================================================================
 DEBUGFS ENTRIES
@@ -246,11 +262,14 @@ Files in /sys/fs/f2fs/<devname>
 ..............................................................................
  File                         Content
 
- gc_max_sleep_time            This tuning parameter controls the maximum sleep
+ gc_urgent_sleep_time         This parameter controls sleep time for gc_urgent.
+                              500 ms is set by default. See above gc_urgent.
+
+ gc_min_sleep_time            This tuning parameter controls the minimum sleep
                               time for the garbage collection thread. Time is
                               in milliseconds.
 
- gc_min_sleep_time            This tuning parameter controls the minimum sleep
+ gc_max_sleep_time            This tuning parameter controls the maximum sleep
                               time for the garbage collection thread. Time is
                               in milliseconds.
 
@@ -270,9 +289,6 @@ Files in /sys/fs/f2fs/<devname>
                               to 1, background thread starts to do GC by given
                               gc_urgent_sleep_time interval.
 
- gc_urgent_sleep_time         This parameter controls sleep time for gc_urgent.
-                              500 ms is set by default. See above gc_urgent.
-
  reclaim_segments             This parameter controls the number of prefree
                               segments to be reclaimed. If the number of prefree
 			      segments is larger than the number of segments
@@ -287,7 +303,16 @@ Files in /sys/fs/f2fs/<devname>
 			      checkpoint is triggered, and issued during the
 			      checkpoint. By default, it is disabled with 0.
 
- trim_sections                This parameter controls the number of sections
+ discard_granularity	      This parameter controls the granularity of discard
+			      command size. It will issue discard commands iif
+			      the size is larger than given granularity. Its
+			      unit size is 4KB, and 4 (=16KB) is set by default.
+			      The maximum value is 128 (=512KB).
+
+ reserved_blocks	      This parameter indicates the number of blocks that
+			      f2fs reserves internally for root.
+
+ batched_trim_sections	      This parameter controls the number of sections
                               to be trimmed out in batch mode when FITRIM
                               conducts. 32 sections is set by default.
 
@@ -309,21 +334,92 @@ Files in /sys/fs/f2fs/<devname>
 			      the number is less than this value, it triggers
 			      in-place-updates.
 
+ min_seq_blocks		      This parameter controls the threshold to serialize
+			      write IOs issued by multiple threads in parallel.
+
+ min_hot_blocks		      This parameter controls the threshold to allocate
+			      a hot data log for pending data blocks to write.
+
+ min_ssr_sections	      This parameter adds the threshold when deciding
+			      SSR block allocation. If this is large, SSR mode
+			      will be enabled early.
+
+ ram_thresh                   This parameter controls the memory footprint used
+			      by free nids and cached nat entries. By default,
+			      10 is set, which indicates 10 MB / 1 GB RAM.
+
+ ra_nid_pages		      When building free nids, F2FS reads NAT blocks
+			      ahead for speed up. Default is 0.
+
+ dirty_nats_ratio	      Given dirty ratio of cached nat entries, F2FS
+			      determines flushing them in background.
+
  max_victim_search	      This parameter controls the number of trials to
 			      find a victim segment when conducting SSR and
 			      cleaning operations. The default value is 4096
 			      which covers 8GB block address range.
 
+ migration_granularity	      For large-sized sections, F2FS can stop GC given
+			      this granularity instead of reclaiming entire
+			      section.
+
  dir_level                    This parameter controls the directory level to
 			      support large directory. If a directory has a
 			      number of files, it can reduce the file lookup
 			      latency by increasing this dir_level value.
 			      Otherwise, it needs to decrease this value to
 			      reduce the space overhead. The default value is 0.
 
- ram_thresh                   This parameter controls the memory footprint used
-			      by free nids and cached nat entries. By default,
-			      10 is set, which indicates 10 MB / 1 GB RAM.
+ cp_interval		      F2FS tries to do checkpoint periodically, 60 secs
+			      by default.
+
+ idle_interval		      F2FS detects system is idle, if there's no F2FS
+			      operations during given interval, 5 secs by
+			      default.
+
+ discard_idle_interval	      F2FS detects the discard thread is idle, given
+			      time interval. Default is 5 secs.
+
+ gc_idle_interval	      F2FS detects the GC thread is idle, given time
+			      interval. Default is 5 secs.
+
+ umount_discard_timeout       When unmounting the disk, F2FS waits for finishing
+			      queued discard commands which can take huge time.
+			      This gives time out for it, 5 secs by default.
+
+ iostat_enable		      This controls to enable/disable iostat in F2FS.
+
+ readdir_ra		      This enables/disabled readahead of inode blocks
+			      in readdir, and default is enabled.
+
+ gc_pin_file_thresh	      This indicates how many GC can be failed for the
+			      pinned file. If it exceeds this, F2FS doesn't
+			      guarantee its pinning state. 2048 trials is set
+			      by default.
+
+ extension_list		      This enables to change extension_list for hot/cold
+			      files in runtime.
+
+ inject_rate		      This controls injection rate of arbitrary faults.
+
+ inject_type		      This controls injection type of arbitrary faults.
+
+ dirty_segments 	      This shows # of dirty segments.
+
+ lifetime_write_kbytes	      This shows # of data written to the disk.
+
+ features		      This shows current features enabled on F2FS.
+
+ current_reserved_blocks      This shows # of blocks currently reserved.
+
+ unusable                     If checkpoint=disable, this shows the number of
+                              blocks that are unusable.
+                              If checkpoint=enable it shows the number of blocks
+                              that would be unusable if checkpoint=disable were
+                              to be set.
+
+encoding 	              This shows the encoding used for casefolding.
+                              If casefolding is not enabled, returns (none)
 
 ================================================================================
 USAGE
@@ -656,3 +752,28 @@ algorithm.
 In order to identify whether the data in the victim segment are valid or not,
 F2FS manages a bitmap. Each bit represents the validity of a block, and the
 bitmap is composed of a bit stream covering whole blocks in main area.
+
+Fallocate(2) Policy
+-------------------
+
+The default policy follows the below posix rule.
+
+Allocating disk space
+    The default operation (i.e., mode is zero) of fallocate() allocates
+    the disk space within the range specified by offset and len.  The
+    file size (as reported by stat(2)) will be changed if offset+len is
+    greater than the file size.  Any subregion within the range specified
+    by offset and len that did not contain data before the call will be
+    initialized to zero.  This default behavior closely resembles the
+    behavior of the posix_fallocate(3) library function, and is intended
+    as a method of optimally implementing that function.
+
+However, once F2FS receives ioctl(fd, F2FS_IOC_SET_PIN_FILE) in prior to
+fallocate(fd, DEFAULT_MODE), it allocates on-disk blocks addressess having
+zero or random data, which is useful to the below scenario where:
+ 1. create(fd)
+ 2. ioctl(fd, F2FS_IOC_SET_PIN_FILE)
+ 3. fallocate(fd, 0, 0, size)
+ 4. address = fibmap(fd, offset)
+ 5. open(blkdev)
+ 6. write(blkdev, address)

Documentation/filesystems/fscrypt.rst

@@ -191,7 +191,9 @@ Currently, the following pairs of encryption modes are supported:
 If unsure, you should use the (AES-256-XTS, AES-256-CTS-CBC) pair.
 
 AES-128-CBC was added only for low-powered embedded devices with
-crypto accelerators such as CAAM or CESA that do not support XTS.
+crypto accelerators such as CAAM or CESA that do not support XTS.  To
+use AES-128-CBC, CONFIG_CRYPTO_SHA256 (or another SHA-256
+implementation) must be enabled so that ESSIV can be used.
 
 Adiantum is a (primarily) stream cipher-based mode that is fast even
 on CPUs without dedicated crypto instructions.  It's also a true
@@ -647,3 +649,42 @@ Note that the precise way that filenames are presented to userspace
 without the key is subject to change in the future.  It is only meant
 as a way to temporarily present valid filenames so that commands like
 ``rm -r`` work as expected on encrypted directories.
+
+Tests
+=====
+
+To test fscrypt, use xfstests, which is Linux's de facto standard
+filesystem test suite.  First, run all the tests in the "encrypt"
+group on the relevant filesystem(s).  For example, to test ext4 and
+f2fs encryption using `kvm-xfstests
+<https://github.com/tytso/xfstests-bld/blob/master/Documentation/kvm-quickstart.md>`_::
+
+    kvm-xfstests -c ext4,f2fs -g encrypt
+
+UBIFS encryption can also be tested this way, but it should be done in
+a separate command, and it takes some time for kvm-xfstests to set up
+emulated UBI volumes::
+
+    kvm-xfstests -c ubifs -g encrypt
+
+No tests should fail.  However, tests that use non-default encryption
+modes (e.g. generic/549 and generic/550) will be skipped if the needed
+algorithms were not built into the kernel's crypto API.  Also, tests
+that access the raw block device (e.g. generic/399, generic/548,
+generic/549, generic/550) will be skipped on UBIFS.
+
+Besides running the "encrypt" group tests, for ext4 and f2fs it's also
+possible to run most xfstests with the "test_dummy_encryption" mount
+option.  This option causes all new files to be automatically
+encrypted with a dummy key, without having to make any API calls.
+This tests the encrypted I/O paths more thoroughly.  To do this with
+kvm-xfstests, use the "encrypt" filesystem configuration::
+
+    kvm-xfstests -c ext4/encrypt,f2fs/encrypt -g auto
+
+Because this runs many more tests than "-g encrypt" does, it takes
+much longer to run; so also consider using `gce-xfstests
+<https://github.com/tytso/xfstests-bld/blob/master/Documentation/gce-xfstests.md>`_
+instead of kvm-xfstests::
+
+    gce-xfstests -c ext4/encrypt,f2fs/encrypt -g auto

fs/Kconfig

@@ -308,6 +308,7 @@ endif # NETWORK_FILESYSTEMS
 
 source "fs/nls/Kconfig"
 source "fs/dlm/Kconfig"
+source "fs/unicode/Kconfig"
 
 config FILE_TABLE_DEBUG
 	bool "Enable FILE_TABLE_DEBUG"

fs/Makefile

@@ -91,6 +91,7 @@ obj-$(CONFIG_EXPORTFS)		+= exportfs/
 obj-$(CONFIG_NFSD)		+= nfsd/
 obj-$(CONFIG_LOCKD)		+= lockd/
 obj-$(CONFIG_NLS)		+= nls/
+obj-$(CONFIG_UNICODE)		+= unicode/
 obj-$(CONFIG_SYSV_FS)		+= sysv/
 obj-$(CONFIG_CIFS)		+= cifs/
 obj-$(CONFIG_NCP_FS)		+= ncpfs/

fs/crypto/Kconfig

@@ -6,7 +6,6 @@ config FS_ENCRYPTION
 	select CRYPTO_ECB
 	select CRYPTO_XTS
 	select CRYPTO_CTS
-	select CRYPTO_SHA256
 	select KEYS
 	help
 	  Enable encryption of files and directories.  This