WIP Fixed minor memory leak

(Some where legitimate test failures)

.gitignore

@@ -0,0 +1,9 @@
+# Compilation output
+*.o
+*.d
+*.a
+
+# Testing things
+blocks/
+lfs
+test.c

.travis.yml

@@ -1,48 +1,216 @@
+# Environment variables
+env:
+  global:
+    - CFLAGS=-Werror
+
+# Common test script
 script:
-    # make sure example can at least compile
-    - sed -n '/``` c/,/```/{/```/d; p;}' README.md > test.c &&
-      CFLAGS='
+  # make sure example can at least compile
+  - sed -n '/``` c/,/```/{/```/d; p;}' README.md > test.c &&
+    make all CFLAGS+="
         -Duser_provided_block_device_read=NULL
         -Duser_provided_block_device_prog=NULL
         -Duser_provided_block_device_erase=NULL
         -Duser_provided_block_device_sync=NULL
-        -include stdio.h -Werror' make all size
+        -include stdio.h"
 
-    # run tests
-    - make test
+  # run tests
+  - make test QUIET=1
 
-    # run tests with a few different configurations
-    - CFLAGS="-DLFS_READ_SIZE=1   -DLFS_PROG_SIZE=1"   make test
-    - CFLAGS="-DLFS_READ_SIZE=512 -DLFS_PROG_SIZE=512" make test
-    - CFLAGS="-DLFS_BLOCK_COUNT=1023" make test
-    - CFLAGS="-DLFS_LOOKAHEAD=2047"   make test
+  # run tests with a few different configurations
+  - make test QUIET=1 CFLAGS+="-DLFS_READ_SIZE=1      -DLFS_CACHE_SIZE=4"
+  - make test QUIET=1 CFLAGS+="-DLFS_READ_SIZE=512    -DLFS_CACHE_SIZE=512 -DLFS_BLOCK_CYCLES=16"
+  - make test QUIET=1 CFLAGS+="-DLFS_BLOCK_COUNT=1023 -DLFS_LOOKAHEAD=2048"
+
+  - make clean test QUIET=1 CFLAGS+="-DLFS_INLINE_MAX=0"
+  - make clean test QUIET=1 CFLAGS+="-DLFS_NO_INTRINSICS"
+
+  # compile and find the code size with the smallest configuration
+  - make clean size
+        OBJ="$(ls lfs*.o | tr '\n' ' ')"
+        CFLAGS+="-DLFS_NO_ASSERT -DLFS_NO_DEBUG -DLFS_NO_WARN -DLFS_NO_ERROR"
+        | tee sizes
+
+  # update status if we succeeded, compare with master if possible
+  - |
+    if [ "$TRAVIS_TEST_RESULT" -eq 0 ]
+    then
+        CURR=$(tail -n1 sizes | awk '{print $1}')
+        PREV=$(curl -u $GEKY_BOT_STATUSES https://api.github.com/repos/$TRAVIS_REPO_SLUG/status/master \
+            | jq -re "select(.sha != \"$TRAVIS_COMMIT\")
+                | .statuses[] | select(.context == \"$STAGE/$NAME\").description
+                | capture(\"code size is (?<size>[0-9]+)\").size" \
+            || echo 0)
+
+        STATUS="Passed, code size is ${CURR}B"
+        if [ "$PREV" -ne 0 ]
+        then
+            STATUS="$STATUS ($(python -c "print '%+.2f' % (100*($CURR-$PREV)/$PREV.0)")%)"
+        fi
+    fi
+
+# CI matrix
+jobs:
+  include:
+    # native testing
+    - stage: test
+      env:
+        - STAGE=test
+        - NAME=littlefs-x86
+
+    # cross-compile with ARM (thumb mode)
+    - stage: test
+      env:
+        - STAGE=test
+        - NAME=littlefs-arm
+        - CC="arm-linux-gnueabi-gcc --static -mthumb"
+        - EXEC="qemu-arm"
+      install:
+        - sudo apt-get install gcc-arm-linux-gnueabi qemu-user
+        - arm-linux-gnueabi-gcc --version
+        - qemu-arm -version
+
+    # cross-compile with PowerPC
+    - stage: test
+      env:
+        - STAGE=test
+        - NAME=littlefs-powerpc
+        - CC="powerpc-linux-gnu-gcc --static"
+        - EXEC="qemu-ppc"
+      install:
+        - sudo apt-get install gcc-powerpc-linux-gnu qemu-user
+        - powerpc-linux-gnu-gcc --version
+        - qemu-ppc -version
+
+    # cross-compile with MIPS
+    - stage: test
+      env:
+        - STAGE=test
+        - NAME=littlefs-mips
+        - CC="mips-linux-gnu-gcc --static"
+        - EXEC="qemu-mips"
+      install:
+        - sudo add-apt-repository -y "deb http://archive.ubuntu.com/ubuntu/ xenial main universe"
+        - sudo apt-get -qq update
+        - sudo apt-get install gcc-mips-linux-gnu qemu-user
+        - mips-linux-gnu-gcc --version
+        - qemu-mips -version
 
     # self-host with littlefs-fuse for fuzz test
-    - make -C littlefs-fuse
+    - stage: test
+      env:
+        - STAGE=test
+        - NAME=littlefs-fuse
+      install:
+        - sudo apt-get install libfuse-dev
+        - git clone --depth 1 https://github.com/geky/littlefs-fuse -b v2-alpha
+        - fusermount -V
+        - gcc --version
+      before_script:
+        # setup disk for littlefs-fuse
+        - rm -rf littlefs-fuse/littlefs/*
+        - cp -r $(git ls-tree --name-only HEAD) littlefs-fuse/littlefs
 
-    - littlefs-fuse/lfs --format /dev/loop0
-    - littlefs-fuse/lfs /dev/loop0 mount
+        - mkdir mount
+        - sudo chmod a+rw /dev/loop0
+        - dd if=/dev/zero bs=512 count=2048 of=disk
+        - losetup /dev/loop0 disk
+      script:
+        # self-host test
+        - make -C littlefs-fuse
 
-    - ls mount
-    - mkdir mount/littlefs
-    - cp -r $(git ls-tree --name-only HEAD) mount/littlefs
-    - cd mount/littlefs
-    - ls
-    - make -B test_dirs
+        - littlefs-fuse/lfs --format /dev/loop0
+        - littlefs-fuse/lfs /dev/loop0 mount
 
+        - ls mount
+        - mkdir mount/littlefs
+        - cp -r $(git ls-tree --name-only HEAD) mount/littlefs
+        - cd mount/littlefs
+        - ls
+        - make -B test_dirs test_files QUIET=1
+
+      # Automatically update releases
+    - stage: deploy
+      env:
+        - STAGE=deploy
+        - NAME=deploy
+      script:
+        # Find version defined in lfs.h
+        - LFS_VERSION=$(grep -ox '#define LFS_VERSION .*' lfs.h | cut -d ' ' -f3)
+        - LFS_VERSION_MAJOR=$((0xffff & ($LFS_VERSION >> 16)))
+        - LFS_VERSION_MINOR=$((0xffff & ($LFS_VERSION >>  0)))
+        # Grab latests patch from repo tags, default to 0
+        - LFS_VERSION_PATCH=$(curl -f -u "$GEKY_BOT_RELEASES"
+                https://api.github.com/repos/$TRAVIS_REPO_SLUG/git/refs
+                | jq 'map(.ref | match(
+                    "refs/tags/v'"$LFS_VERSION_MAJOR"'\\.'"$LFS_VERSION_MINOR"'\\.(.*)$")
+                    .captures[].string | tonumber + 1) | max // 0')
+        # We have our new version
+        - LFS_VERSION="v$LFS_VERSION_MAJOR.$LFS_VERSION_MINOR.$LFS_VERSION_PATCH"
+        - echo "VERSION $LFS_VERSION"
+        - |
+          # Check that we're the most recent commit
+          CURRENT_COMMIT=$(curl -f -u "$GEKY_BOT_RELEASES" \
+                https://api.github.com/repos/$TRAVIS_REPO_SLUG/commits/master \
+                | jq -re '.sha')
+          if [ "$TRAVIS_COMMIT" == "$CURRENT_COMMIT" ]
+          then
+            # Build release notes
+            PREV=$(git tag --sort=-v:refname -l "v*" | head -1)
+            if [ ! -z "$PREV" ]
+            then
+                echo "PREV $PREV"
+                CHANGES=$'### Changes\n\n'$( \
+                    git log --oneline $PREV.. --grep='^Merge' --invert-grep)
+                printf "CHANGES\n%s\n\n" "$CHANGES"
+            fi
+            # Create the release
+            curl -f -u "$GEKY_BOT_RELEASES" -X POST \
+                https://api.github.com/repos/$TRAVIS_REPO_SLUG/releases \
+                -d "{
+                    \"tag_name\": \"$LFS_VERSION\",
+                    \"target_commitish\": \"$TRAVIS_COMMIT\",
+                    \"name\": \"${LFS_VERSION%.0}\",
+                    \"body\": $(jq -sR '.' <<< "$CHANGES")
+                }"
+          fi
+
+# Manage statuses
 before_install:
-    - fusermount -V
-    - gcc --version
+  - |
+    curl -u $GEKY_BOT_STATUSES -X POST \
+        https://api.github.com/repos/$TRAVIS_REPO_SLUG/statuses/${TRAVIS_PULL_REQUEST_SHA:-$TRAVIS_COMMIT} \
+        -d "{
+            \"context\": \"$STAGE/$NAME\",
+            \"state\": \"pending\",
+            \"description\": \"${STATUS:-In progress}\",
+            \"target_url\": \"https://travis-ci.org/$TRAVIS_REPO_SLUG/jobs/$TRAVIS_JOB_ID\"
+        }"
 
-install:
-    - sudo apt-get install libfuse-dev
-    - git clone --depth 1 https://github.com/geky/littlefs-fuse
+after_failure:
+  - |
+    curl -u $GEKY_BOT_STATUSES -X POST \
+        https://api.github.com/repos/$TRAVIS_REPO_SLUG/statuses/${TRAVIS_PULL_REQUEST_SHA:-$TRAVIS_COMMIT} \
+        -d "{
+            \"context\": \"$STAGE/$NAME\",
+            \"state\": \"failure\",
+            \"description\": \"${STATUS:-Failed}\",
+            \"target_url\": \"https://travis-ci.org/$TRAVIS_REPO_SLUG/jobs/$TRAVIS_JOB_ID\"
+        }"
 
-before_script:
-    - rm -rf littlefs-fuse/littlefs/*
-    - cp -r $(git ls-tree --name-only HEAD) littlefs-fuse/littlefs
+after_success:
+  - |
+    curl -u $GEKY_BOT_STATUSES -X POST \
+        https://api.github.com/repos/$TRAVIS_REPO_SLUG/statuses/${TRAVIS_PULL_REQUEST_SHA:-$TRAVIS_COMMIT} \
+        -d "{
+            \"context\": \"$STAGE/$NAME\",
+            \"state\": \"success\",
+            \"description\": \"${STATUS:-Passed}\",
+            \"target_url\": \"https://travis-ci.org/$TRAVIS_REPO_SLUG/jobs/$TRAVIS_JOB_ID\"
+        }"
 
-    - mkdir mount
-    - sudo chmod a+rw /dev/loop0
-    - dd if=/dev/zero bs=512 count=2048 of=disk
-    - losetup /dev/loop0 disk
+# Job control
+stages:
+    - name: test
+    - name: deploy
+      if: branch = master AND type = push

DESIGN.md

@@ -1,6 +1,6 @@
 ## The design of the little filesystem
 
-The littlefs is a little fail-safe filesystem designed for embedded systems.
+A little fail-safe filesystem designed for embedded systems.
 
 ```
    | | |     .---._____
@@ -16,9 +16,9 @@ more about filesystem design by tackling the relative unsolved problem of
 managing a robust filesystem resilient to power loss on devices
 with limited RAM and ROM.
 
-The embedded systems the littlefs is targeting are usually 32bit
-microcontrollers with around 32Kbytes of RAM and 512Kbytes of ROM. These are
-often paired with SPI NOR flash chips with about 4Mbytes of flash storage.
+The embedded systems the littlefs is targeting are usually 32 bit
+microcontrollers with around 32KB of RAM and 512KB of ROM. These are
+often paired with SPI NOR flash chips with about 4MB of flash storage.
 
 Flash itself is a very interesting piece of technology with quite a bit of
 nuance. Unlike most other forms of storage, writing to flash requires two
@@ -27,22 +27,23 @@ cheap, and can be very granular. For NOR flash specifically, byte-level
 programs are quite common. Erasing, however, requires an expensive operation
 that forces the state of large blocks of memory to reset in a destructive
 reaction that gives flash its name. The [Wikipedia entry](https://en.wikipedia.org/wiki/Flash_memory)
-has more information if you are interesting in how this works.
+has more information if you are interested in how this works.
 
 This leaves us with an interesting set of limitations that can be simplified
 to three strong requirements:
 
-1. **Fail-safe** - This is actually the main goal of the littlefs and the focus
-   of this project. Embedded systems are usually designed without a shutdown
-   routine and a notable lack of user interface for recovery, so filesystems
-   targeting embedded systems should be prepared to lose power an any given
-   time.
+1. **Power-loss resilient** - This is the main goal of the littlefs and the
+   focus of this project.
+
+   Embedded systems are usually designed without a shutdown routine and a
+   notable lack of user interface for recovery, so filesystems targeting
+   embedded systems must be prepared to lose power at any given time.
 
    Despite this state of things, there are very few embedded filesystems that
-   handle power loss in a reasonable manner, and can become corrupted if the
-   user is unlucky enough.
+   handle power loss in a reasonable manner, and most can become corrupted if
+   the user is unlucky enough.
 
-2. **Wear awareness** - Due to the destructive nature of flash, most flash
+2. **Wear leveling** - Due to the destructive nature of flash, most flash
    chips have a limited number of erase cycles, usually in the order of around
    100,000 erases per block for NOR flash. Filesystems that don't take wear
    into account can easily burn through blocks used to store frequently updated
@@ -52,7 +53,8 @@ to three strong requirements:
    which stores a file allocation table (FAT) at a specific offset from the
    beginning of disk. Every block allocation will update this table, and after
    100,000 updates, the block will likely go bad, rendering the filesystem
-   unusable even if there are many more erase cycles available on the storage.
+   unusable even if there are many more erase cycles available on the storage
+   as a whole.
 
 3. **Bounded RAM/ROM** - Even with the design difficulties presented by the
    previous two limitations, we have already seen several flash filesystems
@@ -72,33 +74,32 @@ to three strong requirements:
 
 ## Existing designs?
 
-There are of course, many different existing filesystem. Heres a very rough
+There are of course, many different existing filesystem. Here is a very rough
 summary of the general ideas behind some of them.
 
 Most of the existing filesystems fall into the one big category of filesystem
 designed in the early days of spinny magnet disks. While there is a vast amount
 of interesting technology and ideas in this area, the nature of spinny magnet
-disks encourage properties such as grouping writes near each other, that don't
+disks encourage properties, such as grouping writes near each other, that don't
 make as much sense on recent storage types. For instance, on flash, write
-locality is not as important and can actually increase wear destructively.
+locality is not important and can actually increase wear.
 
 One of the most popular designs for flash filesystems is called the
 [logging filesystem](https://en.wikipedia.org/wiki/Log-structured_file_system).
 The flash filesystems [jffs](https://en.wikipedia.org/wiki/JFFS)
-and [yaffs](https://en.wikipedia.org/wiki/YAFFS) are good examples. In
-logging filesystem, data is not store in a data structure on disk, but instead
+and [yaffs](https://en.wikipedia.org/wiki/YAFFS) are good examples. In a
+logging filesystem, data is not stored in a data structure on disk, but instead
 the changes to the files are stored on disk. This has several neat advantages,
-such as the fact that the data is written in a cyclic log format naturally
+such as the fact that the data is written in a cyclic log format and naturally
 wear levels as a side effect. And, with a bit of error detection, the entire
 filesystem can easily be designed to be resilient to power loss. The
-journalling component of most modern day filesystems is actually a reduced
+journaling component of most modern day filesystems is actually a reduced
 form of a logging filesystem. However, logging filesystems have a difficulty
 scaling as the size of storage increases. And most filesystems compensate by
-caching large parts of the filesystem in RAM, a strategy that is unavailable
+caching large parts of the filesystem in RAM, a strategy that is inappropriate
 for embedded systems.
 
-Another interesting filesystem design technique that the littlefs borrows the
-most from, is the [copy-on-write (COW)](https://en.wikipedia.org/wiki/Copy-on-write).
+Another interesting filesystem design technique is that of [copy-on-write (COW)](https://en.wikipedia.org/wiki/Copy-on-write).
 A good example of this is the [btrfs](https://en.wikipedia.org/wiki/Btrfs)
 filesystem. COW filesystems can easily recover from corrupted blocks and have
 natural protection against power loss. However, if they are not designed with
@@ -108,14 +109,14 @@ where the COW data structures are synchronized.
 ## Metadata pairs
 
 The core piece of technology that provides the backbone for the littlefs is
-the concept of metadata pairs. The key idea here, is that any metadata that
+the concept of metadata pairs. The key idea here is that any metadata that
 needs to be updated atomically is stored on a pair of blocks tagged with
 a revision count and checksum. Every update alternates between these two
 pairs, so that at any time there is always a backup containing the previous
 state of the metadata.
 
 Consider a small example where each metadata pair has a revision count,
-a number as data, and the xor of the block as a quick checksum. If
+a number as data, and the XOR of the block as a quick checksum. If
 we update the data to a value of 9, and then to a value of 5, here is
 what the pair of blocks may look like after each update:
 ```
@@ -131,7 +132,7 @@ what the pair of blocks may look like after each update:
 After each update, we can find the most up to date value of data by looking
 at the revision count.
 
-Now consider what the blocks may look like if we suddenly loss power while
+Now consider what the blocks may look like if we suddenly lose power while
 changing the value of data to 5:
 ```
   block 1   block 2        block 1   block 2        block 1   block 2
@@ -150,19 +151,19 @@ check our checksum we notice that block 1 was corrupted. So we fall back to
 block 2 and use the value 9.
 
 Using this concept, the littlefs is able to update metadata blocks atomically.
-There are a few other tweaks, such as using a 32bit crc and using sequence
+There are a few other tweaks, such as using a 32 bit CRC and using sequence
 arithmetic to handle revision count overflow, but the basic concept
 is the same. These metadata pairs define the backbone of the littlefs, and the
 rest of the filesystem is built on top of these atomic updates.
 
-## Files
+## Non-meta data
 
 Now, the metadata pairs do come with some drawbacks. Most notably, each pair
 requires two blocks for each block of data. I'm sure users would be very
 unhappy if their storage was suddenly cut in half! Instead of storing
 everything in these metadata blocks, the littlefs uses a COW data structure
 for files which is in turn pointed to by a metadata block. When
-we update a file, we create a copies of any blocks that are modified until
+we update a file, we create copies of any blocks that are modified until
 the metadata blocks are updated with the new copy. Once the metadata block
 points to the new copy, we deallocate the old blocks that are no longer in use.
 
@@ -185,7 +186,7 @@ Here is what updating a one-block file may look like:
             update data in file        update metadata pair
 ```
 
-It doesn't matter if we lose power while writing block 5 with the new data,
+It doesn't matter if we lose power while writing new data to block 5,
 since the old data remains unmodified in block 4. This example also
 highlights how the atomic updates of the metadata blocks provide a
 synchronization barrier for the rest of the littlefs.
@@ -200,14 +201,14 @@ Now we could just leave files here, copying the entire file on write
 provides the synchronization without the duplicated memory requirements
 of the metadata blocks. However, we can do a bit better.
 
-## CTZ linked-lists
+## CTZ skip-lists
 
 There are many different data structures for representing the actual
 files in filesystems. Of these, the littlefs uses a rather unique [COW](https://upload.wikimedia.org/wikipedia/commons/0/0c/Cow_female_black_white.jpg)
 data structure that allows the filesystem to reuse unmodified parts of the
 file without additional metadata pairs.
 
-First lets consider storing files in a simple linked-list. What happens when
+First lets consider storing files in a simple linked-list. What happens when we
 append a block? We have to change the last block in the linked-list to point
 to this new block, which means we have to copy out the last block, and change
 the second-to-last block, and then the third-to-last, and so on until we've
@@ -224,12 +225,12 @@ Exhibit A: A linked-list
 
 To get around this, the littlefs, at its heart, stores files backwards. Each
 block points to its predecessor, with the first block containing no pointers.
-If you think about this, it makes a bit of sense. Appending blocks just point
-to their predecessor and no other blocks need to be updated. If we update
-a block in the middle, we will need to copy out the blocks that follow,
-but can reuse the blocks before the modified block. Since most file operations
-either reset the file each write or append to files, this design avoids
-copying the file in the most common cases.
+If you think about for a while, it starts to make a bit of sense. Appending
+blocks just point to their predecessor and no other blocks need to be updated.
+If we update a block in the middle, we will need to copy out the blocks that
+follow, but can reuse the blocks before the modified block. Since most file
+operations either reset the file each write or append to files, this design
+avoids copying the file in the most common cases.
 
 ```
 Exhibit B: A backwards linked-list
@@ -241,24 +242,24 @@ Exhibit B: A backwards linked-list
 ```
 
 However, a backwards linked-list does come with a rather glaring problem.
-Iterating over a file _in order_ has a runtime of O(n^2). Gah! A quadratic
-runtime to just _read_ a file? That's awful. Keep in mind reading files are
+Iterating over a file _in order_ has a runtime cost of O(n^2). Gah! A quadratic
+runtime to just _read_ a file? That's awful. Keep in mind reading files is
 usually the most common filesystem operation.
 
 To avoid this problem, the littlefs uses a multilayered linked-list. For
-every block that is divisible by a power of two, the block contains an
-additional pointer that points back by that power of two. Another way of
-thinking about this design is that there are actually many linked-lists
-threaded together, with each linked-lists skipping an increasing number
-of blocks. If you're familiar with data-structures, you may have also
-recognized that this is a deterministic skip-list.
+every nth block where n is divisible by 2^x, the block contains a pointer
+to block n-2^x. So each block contains anywhere from 1 to log2(n) pointers
+that skip to various sections of the preceding list. If you're familiar with
+data-structures, you may have recognized that this is a type of deterministic
+skip-list.
 
-To find the power of two factors efficiently, we can use the instruction
-[count trailing zeros (CTZ)](https://en.wikipedia.org/wiki/Count_trailing_zeros),
-which is where this linked-list's name comes from.
+The name comes from the use of the
+[count trailing zeros (CTZ)](https://en.wikipedia.org/wiki/Count_trailing_zeros)
+instruction, which allows us to calculate the power-of-two factors efficiently.
+For a given block n, the block contains ctz(n)+1 pointers.
 
 ```
-Exhibit C: A backwards CTZ linked-list
+Exhibit C: A backwards CTZ skip-list
 .--------.  .--------.  .--------.  .--------.  .--------.  .--------.
 | data 0 |<-| data 1 |<-| data 2 |<-| data 3 |<-| data 4 |<-| data 5 |
 |        |<-|        |--|        |<-|        |--|        |  |        |
@@ -266,6 +267,9 @@ Exhibit C: A backwards CTZ linked-list
 '--------'  '--------'  '--------'  '--------'  '--------'  '--------'
 ```
 
+The additional pointers allow us to navigate the data-structure on disk
+much more efficiently than in a singly linked-list.
+
 Taking exhibit C for example, here is the path from data block 5 to data
 block 1. You can see how data block 3 was completely skipped:
 ```
@@ -285,15 +289,132 @@ The path to data block 0 is even more quick, requiring only two jumps:
 '--------'  '--------'  '--------'  '--------'  '--------'  '--------'
 ```
 
-The CTZ linked-list has quite a few interesting properties. All of the pointers
-in the block can be found by just knowing the index in the list of the current
-block, and, with a bit of math, the amortized overhead for the linked-list is
-only two pointers per block.  Most importantly, the CTZ linked-list has a
-worst case lookup runtime of O(logn), which brings the runtime of reading a
-file down to O(n logn). Given that the constant runtime is divided by the
-amount of data we can store in a block, this is pretty reasonable.
+We can find the runtime complexity by looking at the path to any block from
+the block containing the most pointers. Every step along the path divides
+the search space for the block in half. This gives us a runtime of O(log n).
+To get to the block with the most pointers, we can perform the same steps
+backwards, which puts the runtime at O(2 log n) = O(log n). The interesting
+part about this data structure is that this optimal path occurs naturally
+if we greedily choose the pointer that covers the most distance without passing
+our target block.
 
-Here is what it might look like to update a file stored with a CTZ linked-list:
+So now we have a representation of files that can be appended trivially with
+a runtime of O(1), and can be read with a worst case runtime of O(n log n).
+Given that the the runtime is also divided by the amount of data we can store
+in a block, this is pretty reasonable.
+
+Unfortunately, the CTZ skip-list comes with a few questions that aren't
+straightforward to answer. What is the overhead? How do we handle more
+pointers than we can store in a block? How do we store the skip-list in
+a directory entry?
+
+One way to find the overhead per block is to look at the data structure as
+multiple layers of linked-lists. Each linked-list skips twice as many blocks
+as the previous linked-list. Another way of looking at it is that each 
+linked-list uses half as much storage per block as the previous linked-list.
+As we approach infinity, the number of pointers per block forms a geometric
+series. Solving this geometric series gives us an average of only 2 pointers
+per block.
+
+![overhead_per_block](https://latex.codecogs.com/svg.latex?%5Clim_%7Bn%5Cto%5Cinfty%7D%5Cfrac%7B1%7D%7Bn%7D%5Csum_%7Bi%3D0%7D%5E%7Bn%7D%5Cleft%28%5Ctext%7Bctz%7D%28i%29&plus;1%5Cright%29%20%3D%20%5Csum_%7Bi%3D0%7D%5Cfrac%7B1%7D%7B2%5Ei%7D%20%3D%202)
+
+Finding the maximum number of pointers in a block is a bit more complicated,
+but since our file size is limited by the integer width we use to store the
+size, we can solve for it. Setting the overhead of the maximum pointers equal
+to the block size we get the following equation. Note that a smaller block size
+results in more pointers, and a larger word width results in larger pointers.
+
+![maximum overhead](https://latex.codecogs.com/svg.latex?B%20%3D%20%5Cfrac%7Bw%7D%7B8%7D%5Cleft%5Clceil%5Clog_2%5Cleft%28%5Cfrac%7B2%5Ew%7D%7BB-2%5Cfrac%7Bw%7D%7B8%7D%7D%5Cright%29%5Cright%5Crceil)
+
+where:  
+B = block size in bytes  
+w = word width in bits  
+
+Solving the equation for B gives us the minimum block size for various word
+widths:  
+32 bit CTZ skip-list = minimum block size of 104 bytes  
+64 bit CTZ skip-list = minimum block size of 448 bytes  
+
+Since littlefs uses a 32 bit word size, we are limited to a minimum block
+size of 104 bytes. This is a perfectly reasonable minimum block size, with most
+block sizes starting around 512 bytes. So we can avoid additional logic to
+avoid overflowing our block's capacity in the CTZ skip-list.
+
+So, how do we store the skip-list in a directory entry? A naive approach would
+be to store a pointer to the head of the skip-list, the length of the file
+in bytes, the index of the head block in the skip-list, and the offset in the
+head block in bytes. However this is a lot of information, and we can observe
+that a file size maps to only one block index + offset pair. So it should be
+sufficient to store only the pointer and file size.
+
+But there is one problem, calculating the block index + offset pair from a
+file size doesn't have an obvious implementation.
+
+We can start by just writing down an equation. The first idea that comes to
+mind is to just use a for loop to sum together blocks until we reach our
+file size. We can write this equation as a summation:
+
+![summation1](https://latex.codecogs.com/svg.latex?N%20%3D%20%5Csum_i%5En%5Cleft%5BB-%5Cfrac%7Bw%7D%7B8%7D%5Cleft%28%5Ctext%7Bctz%7D%28i%29&plus;1%5Cright%29%5Cright%5D)
+
+where:  
+B = block size in bytes  
+w = word width in bits  
+n = block index in skip-list  
+N = file size in bytes  
+
+And this works quite well, but is not trivial to calculate. This equation
+requires O(n) to compute, which brings the entire runtime of reading a file
+to O(n^2 log n). Fortunately, the additional O(n) does not need to touch disk,
+so it is not completely unreasonable. But if we could solve this equation into
+a form that is easily computable, we can avoid a big slowdown.
+
+Unfortunately, the summation of the CTZ instruction presents a big challenge.
+How would you even begin to reason about integrating a bitwise instruction?
+Fortunately, there is a powerful tool I've found useful in these situations:
+The [On-Line Encyclopedia of Integer Sequences (OEIS)](https://oeis.org/).
+If we work out the first couple of values in our summation, we find that CTZ
+maps to [A001511](https://oeis.org/A001511), and its partial summation maps
+to [A005187](https://oeis.org/A005187), and surprisingly, both of these
+sequences have relatively trivial equations! This leads us to a rather
+unintuitive property:
+
+![mindblown](https://latex.codecogs.com/svg.latex?%5Csum_i%5En%5Cleft%28%5Ctext%7Bctz%7D%28i%29&plus;1%5Cright%29%20%3D%202n-%5Ctext%7Bpopcount%7D%28n%29)
+
+where:  
+ctz(x) = the number of trailing bits that are 0 in x  
+popcount(x) = the number of bits that are 1 in x  
+
+It's a bit bewildering that these two seemingly unrelated bitwise instructions
+are related by this property. But if we start to dissect this equation we can
+see that it does hold. As n approaches infinity, we do end up with an average
+overhead of 2 pointers as we find earlier. And popcount seems to handle the
+error from this average as it accumulates in the CTZ skip-list.
+
+Now we can substitute into the original equation to get a trivial equation
+for a file size:
+
+![summation2](https://latex.codecogs.com/svg.latex?N%20%3D%20Bn%20-%20%5Cfrac%7Bw%7D%7B8%7D%5Cleft%282n-%5Ctext%7Bpopcount%7D%28n%29%5Cright%29)
+
+Unfortunately, we're not quite done. The popcount function is non-injective,
+so we can only find the file size from the block index, not the other way
+around. However, we can solve for an n' block index that is greater than n
+with an error bounded by the range of the popcount function. We can then
+repeatedly substitute this n' into the original equation until the error
+is smaller than the integer division. As it turns out, we only need to
+perform this substitution once. Now we directly calculate our block index:
+
+![formulaforn](https://latex.codecogs.com/svg.latex?n%20%3D%20%5Cleft%5Clfloor%5Cfrac%7BN-%5Cfrac%7Bw%7D%7B8%7D%5Cleft%28%5Ctext%7Bpopcount%7D%5Cleft%28%5Cfrac%7BN%7D%7BB-2%5Cfrac%7Bw%7D%7B8%7D%7D-1%5Cright%29&plus;2%5Cright%29%7D%7BB-2%5Cfrac%7Bw%7D%7B8%7D%7D%5Cright%5Crfloor)
+
+Now that we have our block index n, we can just plug it back into the above
+equation to find the offset. However, we do need to rearrange the equation
+a bit to avoid integer overflow:
+
+![formulaforoff](https://latex.codecogs.com/svg.latex?%5Cmathit%7Boff%7D%20%3D%20N%20-%20%5Cleft%28B-2%5Cfrac%7Bw%7D%7B8%7D%5Cright%29n%20-%20%5Cfrac%7Bw%7D%7B8%7D%5Ctext%7Bpopcount%7D%28n%29)
+
+The solution involves quite a bit of math, but computers are very good at math.
+Now we can solve for both the block index and offset from the file size in O(1).
+
+Here is what it might look like to update a file stored with a CTZ skip-list:
 ```
                                       block 1   block 2
                                     .---------.---------.
@@ -367,7 +488,7 @@ v
 ## Block allocation
 
 So those two ideas provide the grounds for the filesystem. The metadata pairs
-give us directories, and the CTZ linked-lists give us files. But this leaves
+give us directories, and the CTZ skip-lists give us files. But this leaves
 one big [elephant](https://upload.wikimedia.org/wikipedia/commons/3/37/African_Bush_Elephant.jpg)
 of a question. How do we get those blocks in the first place?
 
@@ -380,16 +501,17 @@ scanned to find the most recent free list, but once the list was found the
 state of all free blocks becomes known.
 
 However, this approach had several issues:
+
 - There was a lot of nuanced logic for adding blocks to the free list without
   modifying the blocks, since the blocks remain active until the metadata is
   updated.
-- The free list had to support both additions and removals in fifo order while
+- The free list had to support both additions and removals in FIFO order while
   minimizing block erases.
 - The free list had to handle the case where the file system completely ran
   out of blocks and may no longer be able to add blocks to the free list.
 - If we used a revision count to track the most recently updated free list,
   metadata blocks that were left unmodified were ticking time bombs that would
-  cause the system to go haywire if the revision count overflowed
+  cause the system to go haywire if the revision count overflowed.
 - Every single metadata block wasted space to store these free list references.
 
 Actually, to simplify, this approach had one massive glaring issue: complexity.
@@ -419,7 +541,7 @@ would have an abhorrent runtime.
 So the littlefs compromises. It doesn't store a bitmap the size of the storage,
 but it does store a little bit-vector that contains a fixed set lookahead
 for block allocations. During a block allocation, the lookahead vector is
-checked for any free blocks, if there are none, the lookahead region jumps
+checked for any free blocks. If there are none, the lookahead region jumps
 forward and the entire filesystem is scanned for free blocks.
 
 Here's what it might look like to allocate 4 blocks on a decently busy
@@ -502,7 +624,7 @@ So, as a solution, the littlefs adopted a sort of threaded tree. Each
 directory not only contains pointers to all of its children, but also a
 pointer to the next directory. These pointers create a linked-list that
 is threaded through all of the directories in the filesystem. Since we
-only use this linked list to check for existance, the order doesn't actually
+only use this linked list to check for existence, the order doesn't actually
 matter. As an added plus, we can repurpose the pointer for the individual
 directory linked-lists and avoid using any additional space.
 
@@ -653,9 +775,17 @@ deorphan step that simply iterates through every directory in the linked-list
 and checks it against every directory entry in the filesystem to see if it
 has a parent. The deorphan step occurs on the first block allocation after
 boot, so orphans should never cause the littlefs to run out of storage
-prematurely.
+prematurely. Note that the deorphan step never needs to run in a read-only
+filesystem.
 
-And for my final trick, moving a directory:
+## The move problem
+
+Now we have a real problem. How do we move things between directories while
+remaining power resilient? Even looking at the problem from a high level,
+it seems impossible. We can update directory blocks atomically, but atomically
+updating two independent directory blocks is not an atomic operation.
+
+Here's the steps the filesystem may go through to move a directory:
 ```
          .--------.
          |root dir|-.
@@ -716,25 +846,142 @@ v
      '--------'
 ```
 
-Note that once again we don't care about the ordering of directories in the
-linked-list, so we can simply leave directories in their old positions. This
-does make the diagrams a bit hard to draw, but the littlefs doesn't really
-care.
+We can leave any orphans up to the deorphan step to collect, but that doesn't
+help the case where dir A has both dir B and the root dir as parents if we
+lose power inconveniently.
 
-It's also worth noting that once again we have an operation that isn't actually
-atomic. After we add directory A to directory B, we could lose power, leaving
-directory A as a part of both the root directory and directory B. However,
-there isn't anything inherent to the littlefs that prevents a directory from
-having multiple parents, so in this case, we just allow that to happen. Extra
-care is taken to only remove a directory from the linked-list if there are
-no parents left in the filesystem.
+Initially, you might think this is fine. Dir A _might_ end up with two parents,
+but the filesystem will still work as intended. But then this raises the
+question of what do we do when the dir A wears out? For other directory blocks
+we can update the parent pointer, but for a dir with two parents we would need
+work out how to update both parents. And the check for multiple parents would
+need to be carried out for every directory, even if the directory has never
+been moved.
+
+It also presents a bad user-experience, since the condition of ending up with
+two parents is rare, it's unlikely user-level code will be prepared. Just think
+about how a user would recover from a multi-parented directory. They can't just
+remove one directory, since remove would report the directory as "not empty".
+
+Other atomic filesystems simple COW the entire directory tree. But this
+introduces a significant bit of complexity, which leads to code size, along
+with a surprisingly expensive runtime cost during what most users assume is
+a single pointer update.
+
+Another option is to update the directory block we're moving from to point
+to the destination with a sort of predicate that we have moved if the
+destination exists. Unfortunately, the omnipresent concern of wear could
+cause any of these directory entries to change blocks, and changing the
+entry size before a move introduces complications if it spills out of
+the current directory block.
+
+So how do we go about moving a directory atomically?
+
+We rely on the improbableness of power loss.
+
+Power loss during a move is certainly possible, but it's actually relatively
+rare. Unless a device is writing to a filesystem constantly, it's unlikely that
+a power loss will occur during filesystem activity. We still need to handle
+the condition, but runtime during a power loss takes a back seat to the runtime
+during normal operations.
+
+So what littlefs does is inelegantly simple. When littlefs moves a file, it
+marks the file as "moving". This is stored as a single bit in the directory
+entry and doesn't take up much space. Then littlefs moves the directory,
+finishing with the complete remove of the "moving" directory entry.
+
+```
+         .--------.
+         |root dir|-.
+         | pair 0 | |
+.--------|        |-'
+|        '--------'
+|        .-'    '-.
+|       v          v
+|  .--------.  .--------.
+'->| dir A  |->| dir B  |
+   | pair 0 |  | pair 0 |
+   |        |  |        |
+   '--------'  '--------'
+
+|  update root directory to mark directory A as moving
+v
+
+        .----------.
+        |root dir  |-.
+        | pair 0   | |
+.-------| moving A!|-'
+|       '----------'
+|        .-'    '-.
+|       v          v
+|  .--------.  .--------.
+'->| dir A  |->| dir B  |
+   | pair 0 |  | pair 0 |
+   |        |  |        |
+   '--------'  '--------'
+
+|  update directory B to point to directory A
+v
+
+        .----------.
+        |root dir  |-.
+        | pair 0   | |
+.-------| moving A!|-'
+|       '----------'
+|    .-----'    '-.
+|    |             v
+|    |           .--------.
+|    |        .->| dir B  |
+|    |        |  | pair 0 |
+|    |        |  |        |
+|    |        |  '--------'
+|    |     .-------'
+|    v    v   |
+|  .--------. |
+'->| dir A  |-'
+   | pair 0 |
+   |        |
+   '--------'
+
+|  update root to no longer contain directory A
+v
+     .--------.
+     |root dir|-.
+     | pair 0 | |
+.----|        |-'
+|    '--------'
+|        |
+|        v
+|    .--------.
+| .->| dir B  |
+| |  | pair 0 |
+| '--|        |-.
+|    '--------' |
+|        |      |
+|        v      |
+|    .--------. |
+'--->| dir A  |-'
+     | pair 0 |
+     |        |
+     '--------'
+```
+
+Now, if we run into a directory entry that has been marked as "moved", one
+of two things is possible. Either the directory entry exists elsewhere in the
+filesystem, or it doesn't. This is a O(n) operation, but only occurs in the
+unlikely case we lost power during a move.
+
+And we can easily fix the "moved" directory entry. Since we're already scanning
+the filesystem during the deorphan step, we can also check for moved entries.
+If we find one, we either remove the "moved" marking or remove the whole entry
+if it exists elsewhere in the filesystem.
 
 ## Wear awareness
 
 So now that we have all of the pieces of a filesystem, we can look at a more
 subtle attribute of embedded storage: The wear down of flash blocks.
 
-The first concern for the littlefs, is that prefectly valid blocks can suddenly
+The first concern for the littlefs, is that perfectly valid blocks can suddenly
 become unusable. As a nice side-effect of using a COW data-structure for files,
 we can simply move on to a different block when a file write fails. All
 modifications to files are performed in copies, so we will only replace the
@@ -906,23 +1153,28 @@ develops errors and needs to be moved.
 
 ## Wear leveling
 
-The second concern for the littlefs, is that blocks in the filesystem may wear
+The second concern for the littlefs is that blocks in the filesystem may wear
 unevenly. In this situation, a filesystem may meet an early demise where
-there are no more non-corrupted blocks that aren't in use. It may be entirely
-possible that files were written once and left unmodified, wasting the
-potential erase cycles of the blocks it sits on.
+there are no more non-corrupted blocks that aren't in use. It's common to
+have files that were written once and left unmodified, wasting the potential
+erase cycles of the blocks it sits on.
 
 Wear leveling is a term that describes distributing block writes evenly to
 avoid the early termination of a flash part. There are typically two levels
 of wear leveling:
-1. Dynamic wear leveling - Blocks are distributed evenly during blocks writes.
-   Note that the issue with write-once files still exists in this case.
-2. Static wear leveling - Unmodified blocks are evicted for new block writes.
-   This provides the longest lifetime for a flash device.
+1. Dynamic wear leveling - Wear is distributed evenly across all **dynamic**
+   blocks. Usually this is accomplished by simply choosing the unused block
+   with the lowest amount of wear. Note this does not solve the problem of
+   static data.
+2. Static wear leveling - Wear is distributed evenly across all **dynamic**
+   and **static** blocks. Unmodified blocks may be evicted for new block
+   writes. This does handle the problem of static data but may lead to
+   wear amplification.
 
-Now, it's possible to use the revision count on metadata pairs to approximate
-the wear of a metadata block. And combined with the COW nature of files, the
-littlefs could provide a form of dynamic wear leveling.
+In littlefs's case, it's possible to use the revision count on metadata pairs
+to approximate the wear of a metadata block. And combined with the COW nature
+of files, littlefs could provide your usual implementation of dynamic wear
+leveling.
 
 However, the littlefs does not. This is for a few reasons. Most notably, even
 if the littlefs did implement dynamic wear leveling, this would still not
@@ -933,19 +1185,20 @@ As a flash device reaches the end of its life, the metadata blocks will
 naturally be the first to go since they are updated most often. In this
 situation, the littlefs is designed to simply move on to another set of
 metadata blocks. This travelling means that at the end of a flash device's
-life, the filesystem will have worn the device down as evenly as a dynamic
-wear leveling filesystem could anyways. Simply put, if the lifetime of flash
-is a serious concern, static wear leveling is the only valid solution.
+life, the filesystem will have worn the device down nearly as evenly as the
+usual dynamic wear leveling could. More aggressive wear leveling would come
+with a code-size cost for marginal benefit.
 
-This is a very important takeaway to note. If your storage stack uses highly
-sensitive storage such as NAND flash. In most cases you are going to be better
-off just using a [flash translation layer (FTL)](https://en.wikipedia.org/wiki/Flash_translation_layer).
+
+One important takeaway to note, if your storage stack uses highly sensitive
+storage such as NAND flash, static wear leveling is the only valid solution.
+In most cases you are going to be better off using a full [flash translation layer (FTL)](https://en.wikipedia.org/wiki/Flash_translation_layer).
 NAND flash already has many limitations that make it poorly suited for an
 embedded system: low erase cycles, very large blocks, errors that can develop
 even during reads, errors that can develop during writes of neighboring blocks.
 Managing sensitive storage such as NAND flash is out of scope for the littlefs.
 The littlefs does have some properties that may be beneficial on top of a FTL,
-such as limiting the number of writes where possible. But if you have the
+such as limiting the number of writes where possible, but if you have the
 storage requirements that necessitate the need of NAND flash, you should have
 the RAM to match and just use an FTL or flash filesystem.
 
@@ -955,18 +1208,18 @@ So, to summarize:
 
 1. The littlefs is composed of directory blocks
 2. Each directory is a linked-list of metadata pairs
-3. These metadata pairs can be updated atomically by alternative which
+3. These metadata pairs can be updated atomically by alternating which
    metadata block is active
 4. Directory blocks contain either references to other directories or files
-5. Files are represented by copy-on-write CTZ linked-lists
-6. The CTZ linked-lists support appending in O(1) and reading in O(n logn)
-7. Blocks are allocated by scanning the filesystem for used blocks in a
-   fixed-size lookahead region is that stored in a bit-vector
-8. To facilitate scanning the filesystem, all directories are part of a
+5. Files are represented by copy-on-write CTZ skip-lists which support O(1)
+   append and O(n log n) reading
+6. Blocks are allocated by scanning the filesystem for used blocks in a
+   fixed-size lookahead region that is stored in a bit-vector
+7. To facilitate scanning the filesystem, all directories are part of a
    linked-list that is threaded through the entire filesystem
-9. If a block develops an error, the littlefs allocates a new block, and
+8. If a block develops an error, the littlefs allocates a new block, and
    moves the data and references of the old block to the new.
-10. Any case where an atomic operation is not possible, it is taken care of
+9. Any case where an atomic operation is not possible, mistakes are resolved
    by a deorphan step that occurs on the first allocation after boot
 
 That's the little filesystem. Thanks for reading!

LICENSE.md

@@ -1,165 +1,24 @@
-Apache License
-Version 2.0, January 2004
-http://www.apache.org/licenses/
+Copyright (c) 2017, Arm Limited. All rights reserved.
 
-TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+Redistribution and use in source and binary forms, with or without modification,
+are permitted provided that the following conditions are met:
 
-1. Definitions.
+-  Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+-  Redistributions in binary form must reproduce the above copyright notice, this
+   list of conditions and the following disclaimer in the documentation and/or
+   other materials provided with the distribution.
+-  Neither the name of ARM nor the names of its contributors may be used to
+   endorse or promote products derived from this software without specific prior
+   written permission.
 
-"License" shall mean the terms and conditions for use, reproduction, and
-distribution as defined by Sections 1 through 9 of this document.
-
-"Licensor" shall mean the copyright owner or entity authorized by the copyright
-owner that is granting the License.
-
-"Legal Entity" shall mean the union of the acting entity and all other entities
-that control, are controlled by, or are under common control with that entity.
-For the purposes of this definition, "control" means (i) the power, direct or
-indirect, to cause the direction or management of such entity, whether by
-contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the
-outstanding shares, or (iii) beneficial ownership of such entity.
-
-"You" (or "Your") shall mean an individual or Legal Entity exercising
-permissions granted by this License.
-
-"Source" form shall mean the preferred form for making modifications, including
-but not limited to software source code, documentation source, and configuration
-files.
-
-"Object" form shall mean any form resulting from mechanical transformation or
-translation of a Source form, including but not limited to compiled object code,
-generated documentation, and conversions to other media types.
-
-"Work" shall mean the work of authorship, whether in Source or Object form, made
-available under the License, as indicated by a copyright notice that is included
-in or attached to the work (an example is provided in the Appendix below).
-
-"Derivative Works" shall mean any work, whether in Source or Object form, that
-is based on (or derived from) the Work and for which the editorial revisions,
-annotations, elaborations, or other modifications represent, as a whole, an
-original work of authorship. For the purposes of this License, Derivative Works
-shall not include works that remain separable from, or merely link (or bind by
-name) to the interfaces of, the Work and Derivative Works thereof.
-
-"Contribution" shall mean any work of authorship, including the original version
-of the Work and any modifications or additions to that Work or Derivative Works
-thereof, that is intentionally submitted to Licensor for inclusion in the Work
-by the copyright owner or by an individual or Legal Entity authorized to submit
-on behalf of the copyright owner. For the purposes of this definition,
-"submitted" means any form of electronic, verbal, or written communication sent
-to the Licensor or its representatives, including but not limited to
-communication on electronic mailing lists, source code control systems, and
-issue tracking systems that are managed by, or on behalf of, the Licensor for
-the purpose of discussing and improving the Work, but excluding communication
-that is conspicuously marked or otherwise designated in writing by the copyright
-owner as "Not a Contribution."
-
-"Contributor" shall mean Licensor and any individual or Legal Entity on behalf
-of whom a Contribution has been received by Licensor and subsequently
-incorporated within the Work.
-
-2. Grant of Copyright License.
-
-Subject to the terms and conditions of this License, each Contributor hereby
-grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free,
-irrevocable copyright license to reproduce, prepare Derivative Works of,
-publicly display, publicly perform, sublicense, and distribute the Work and such
-Derivative Works in Source or Object form.
-
-3. Grant of Patent License.
-
-Subject to the terms and conditions of this License, each Contributor hereby
-grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free,
-irrevocable (except as stated in this section) patent license to make, have
-made, use, offer to sell, sell, import, and otherwise transfer the Work, where
-such license applies only to those patent claims licensable by such Contributor
-that are necessarily infringed by their Contribution(s) alone or by combination
-of their Contribution(s) with the Work to which such Contribution(s) was
-submitted. If You institute patent litigation against any entity (including a
-cross-claim or counterclaim in a lawsuit) alleging that the Work or a
-Contribution incorporated within the Work constitutes direct or contributory
-patent infringement, then any patent licenses granted to You under this License
-for that Work shall terminate as of the date such litigation is filed.
-
-4. Redistribution.
-
-You may reproduce and distribute copies of the Work or Derivative Works thereof
-in any medium, with or without modifications, and in Source or Object form,
-provided that You meet the following conditions:
-
-You must give any other recipients of the Work or Derivative Works a copy of
-this License; and
-You must cause any modified files to carry prominent notices stating that You
-changed the files; and
-You must retain, in the Source form of any Derivative Works that You distribute,
-all copyright, patent, trademark, and attribution notices from the Source form
-of the Work, excluding those notices that do not pertain to any part of the
-Derivative Works; and
-If the Work includes a "NOTICE" text file as part of its distribution, then any
-Derivative Works that You distribute must include a readable copy of the
-attribution notices contained within such NOTICE file, excluding those notices
-that do not pertain to any part of the Derivative Works, in at least one of the
-following places: within a NOTICE text file distributed as part of the
-Derivative Works; within the Source form or documentation, if provided along
-with the Derivative Works; or, within a display generated by the Derivative
-Works, if and wherever such third-party notices normally appear. The contents of
-the NOTICE file are for informational purposes only and do not modify the
-License. You may add Your own attribution notices within Derivative Works that
-You distribute, alongside or as an addendum to the NOTICE text from the Work,
-provided that such additional attribution notices cannot be construed as
-modifying the License.
-You may add Your own copyright statement to Your modifications and may provide
-additional or different license terms and conditions for use, reproduction, or
-distribution of Your modifications, or for any such Derivative Works as a whole,
-provided Your use, reproduction, and distribution of the Work otherwise complies
-with the conditions stated in this License.
-
-5. Submission of Contributions.
-
-Unless You explicitly state otherwise, any Contribution intentionally submitted
-for inclusion in the Work by You to the Licensor shall be under the terms and
-conditions of this License, without any additional terms or conditions.
-Notwithstanding the above, nothing herein shall supersede or modify the terms of
-any separate license agreement you may have executed with Licensor regarding
-such Contributions.
-
-6. Trademarks.
-
-This License does not grant permission to use the trade names, trademarks,
-service marks, or product names of the Licensor, except as required for
-reasonable and customary use in describing the origin of the Work and
-reproducing the content of the NOTICE file.
-
-7. Disclaimer of Warranty.
-
-Unless required by applicable law or agreed to in writing, Licensor provides the
-Work (and each Contributor provides its Contributions) on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied,
-including, without limitation, any warranties or conditions of TITLE,
-NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are
-solely responsible for determining the appropriateness of using or
-redistributing the Work and assume any risks associated with Your exercise of
-permissions under this License.
-
-8. Limitation of Liability.
-
-In no event and under no legal theory, whether in tort (including negligence),
-contract, or otherwise, unless required by applicable law (such as deliberate
-and grossly negligent acts) or agreed to in writing, shall any Contributor be
-liable to You for damages, including any direct, indirect, special, incidental,
-or consequential damages of any character arising as a result of this License or
-out of the use or inability to use the Work (including but not limited to
-damages for loss of goodwill, work stoppage, computer failure or malfunction, or
-any and all other commercial damages or losses), even if such Contributor has
-been advised of the possibility of such damages.
-
-9. Accepting Warranty or Additional Liability.
-
-While redistributing the Work or Derivative Works thereof, You may choose to
-offer, and charge a fee for, acceptance of support, warranty, indemnity, or
-other liability obligations and/or rights consistent with this License. However,
-in accepting such obligations, You may act only on Your own behalf and on Your
-sole responsibility, not on behalf of any other Contributor, and only if You
-agree to indemnify, defend, and hold each Contributor harmless for any liability
-incurred by, or claims asserted against, such Contributor by reason of your
-accepting any such warranty or additional liability.
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR
+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

Makefile

@@ -1,8 +1,11 @@
-TARGET = lfs
+TARGET = lfs.a
+ifneq ($(wildcard test.c main.c),)
+override TARGET = lfs
+endif
 
-CC = gcc
-AR = ar
-SIZE = size
+CC ?= gcc
+AR ?= ar
+SIZE ?= size
 
 SRC += $(wildcard *.c emubd/*.c)
 OBJ := $(SRC:.c=.o)
@@ -11,16 +14,18 @@ ASM := $(SRC:.c=.s)
 
 TEST := $(patsubst tests/%.sh,%,$(wildcard tests/test_*))
 
+SHELL = /bin/bash -o pipefail
+
 ifdef DEBUG
-CFLAGS += -O0 -g3
+override CFLAGS += -O0 -g3
 else
-CFLAGS += -Os
+override CFLAGS += -Os
 endif
 ifdef WORD
-CFLAGS += -m$(WORD)
+override CFLAGS += -m$(WORD)
 endif
-CFLAGS += -I.
-CFLAGS += -std=c99 -Wall -pedantic
+override CFLAGS += -I.
+override CFLAGS += -std=c99 -Wall -pedantic -Wshadow -Wunused-parameter
 
 
 all: $(TARGET)
@@ -31,14 +36,21 @@ size: $(OBJ)
 	$(SIZE) -t $^
 
 .SUFFIXES:
-test: test_format test_dirs test_files test_seek test_parallel \
-	test_alloc test_paths test_orphan test_move test_corrupt
+test: test_format test_dirs test_files test_seek test_truncate \
+	test_entries test_interspersed test_alloc test_paths test_attrs \
+	test_move test_orphan test_corrupt
+	@rm test.c
 test_%: tests/test_%.sh
+
+ifdef QUIET
+	@./$< | sed -n '/^[-=]/p'
+else
 	./$<
+endif
 
 -include $(DEP)
 
-$(TARGET): $(OBJ)
+lfs: $(OBJ)
 	$(CC) $(CFLAGS) $^ $(LFLAGS) -o $@
 
 %.a: $(OBJ)

README.md

@@ -11,23 +11,17 @@ A little fail-safe filesystem designed for embedded systems.
    | | |
 ```
 
-**Fail-safe** - The littlefs is designed to work consistently with random
-power failures. During filesystem operations the storage on disk is always
-kept in a valid state. The filesystem also has strong copy-on-write garuntees.
-When updating a file, the original file will remain unmodified until the
-file is closed, or sync is called.
+**Bounded RAM/ROM** - The littlefs is designed to work with a limited amount
+of memory. Recursion is avoided and dynamic memory is limited to configurable
+buffers that can be provided statically.
 
-**Wear awareness** - While the littlefs does not implement static wear
-leveling, the littlefs takes into account write errors reported by the
-underlying block device and uses a limited form of dynamic wear leveling
-to manage blocks that go bad during the lifetime of the filesystem.
+**Power-loss resilient** - The littlefs is designed for systems that may have
+random power failures. The littlefs has strong copy-on-write guarantees and
+storage on disk is always kept in a valid state.
 
-**Bounded ram/rom** - The littlefs is designed to work in a
-limited amount of memory, recursion is avoided, and dynamic memory is kept
-to a minimum. The littlefs allocates two fixed-size buffers for general
-operations, and one fixed-size buffer per file. If there is only ever one file
-in use, all memory can be provided statically and the littlefs can be used
-in a system without dynamic memory.
+**Wear leveling** - Since the most common form of embedded storage is erodible
+flash memories, littlefs provides a form of dynamic wear leveling for systems
+that can not fit a full flash translation layer.
 
 ## Example
 
@@ -94,9 +88,9 @@ int main(void) {
 ## Usage
 
 Detailed documentation (or at least as much detail as is currently available)
-can be cound in the comments in [lfs.h](lfs.h).
+can be found in the comments in [lfs.h](lfs.h).
 
-As you may have noticed, the littlefs takes in a configuration structure that
+As you may have noticed, littlefs takes in a configuration structure that
 defines how the filesystem operates. The configuration struct provides the
 filesystem with the block device operations and dimensions, tweakable
 parameters that tradeoff memory usage for performance, and optional
@@ -104,14 +98,16 @@ static buffers if the user wants to avoid dynamic memory.
 
 The state of the littlefs is stored in the `lfs_t` type which is left up
 to the user to allocate, allowing multiple filesystems to be in use
-simultaneously. With the `lfs_t` and configuration struct, a user can either
+simultaneously. With the `lfs_t` and configuration struct, a user can
 format a block device or mount the filesystem.
 
-Once mounted, the littlefs provides a full set of posix-like file and
+Once mounted, the littlefs provides a full set of POSIX-like file and
 directory functions, with the deviation that the allocation of filesystem
-structures must be provided by the user. An important addition is that
-no file updates will actually be written to disk until a sync or close
-is called.
+structures must be provided by the user.
+
+All POSIX operations, such as remove and rename, are atomic, even in event
+of power-loss. Additionally, no file updates are actually committed to the
+filesystem until sync or close is called on the file.
 
 ## Other notes
 
@@ -119,27 +115,63 @@ All littlefs have the potential to return a negative error code. The errors
 can be either one of those found in the `enum lfs_error` in [lfs.h](lfs.h),
 or an error returned by the user's block device operations.
 
-It should also be noted that the littlefs does not do anything to insure
-that the data written to disk is machine portable. It should be fine as
-long as the machines involved share endianness and don't have really
-strange padding requirements. If the question does come up, the littlefs
-metadata should be stored on disk in little-endian format.
+In the configuration struct, the `prog` and `erase` function provided by the
+user may return a `LFS_ERR_CORRUPT` error if the implementation already can
+detect corrupt blocks. However, the wear leveling does not depend on the return
+code of these functions, instead all data is read back and checked for
+integrity.
 
-## Design
+If your storage caches writes, make sure that the provided `sync` function
+flushes all the data to memory and ensures that the next read fetches the data
+from memory, otherwise data integrity can not be guaranteed. If the `write`
+function does not perform caching, and therefore each `read` or `write` call
+hits the memory, the `sync` function can simply return 0.
 
-the littlefs was developed with the goal of learning more about filesystem
-design by tackling the relative unsolved problem of managing a robust
-filesystem resilient to power loss on devices with limited RAM and ROM.
-More detail on the solutions and tradeoffs incorporated into this filesystem
-can be found in [DESIGN.md](DESIGN.md). The specification for the layout
-of the filesystem on disk can be found in [SPEC.md](SPEC.md).
+## Reference material
+
+[DESIGN.md](DESIGN.md) - DESIGN.md contains a fully detailed dive into how
+littlefs actually works. I would encourage you to read it since the
+solutions and tradeoffs at work here are quite interesting.
+
+[SPEC.md](SPEC.md) - SPEC.md contains the on-disk specification of littlefs
+with all the nitty-gritty details. Can be useful for developing tooling.
 
 ## Testing
 
-The littlefs comes with a test suite designed to run on a pc using the
+The littlefs comes with a test suite designed to run on a PC using the
 [emulated block device](emubd/lfs_emubd.h) found in the emubd directory.
-The tests assume a linux environment and can be started with make:
+The tests assume a Linux environment and can be started with make:
 
 ``` bash
 make test
 ```
+
+## License
+
+The littlefs is provided under the [BSD-3-Clause](https://spdx.org/licenses/BSD-3-Clause.html)
+license. See [LICENSE.md](LICENSE.md) for more information. Contributions to
+this project are accepted under the same license.
+
+Individual files contain the following tag instead of the full license text.
+
+    SPDX-License-Identifier:    BSD-3-Clause
+
+This enables machine processing of license information based on the SPDX
+License Identifiers that are here available: http://spdx.org/licenses/
+
+## Related projects
+
+[Mbed OS](https://github.com/ARMmbed/mbed-os/tree/master/features/filesystem/littlefs) -
+The easiest way to get started with littlefs is to jump into [Mbed](https://os.mbed.com/),
+which already has block device drivers for most forms of embedded storage. The
+littlefs is available in Mbed OS as the [LittleFileSystem](https://os.mbed.com/docs/latest/reference/littlefilesystem.html)
+class.
+
+[littlefs-fuse](https://github.com/geky/littlefs-fuse) - A [FUSE](https://github.com/libfuse/libfuse)
+wrapper for littlefs. The project allows you to mount littlefs directly on a
+Linux machine. Can be useful for debugging littlefs if you have an SD card
+handy.
+
+[littlefs-js](https://github.com/geky/littlefs-js) - A javascript wrapper for
+littlefs. I'm not sure why you would want this, but it is handy for demos.
+You can see it in action [here](http://littlefs.geky.net/demo.html).

SPEC.md

@@ -46,7 +46,7 @@ Here's the layout of metadata blocks on disk:
 | 0x04   | 32 bits       | dir size       |
 | 0x08   | 64 bits       | tail pointer   |
 | 0x10   | size-16 bytes | dir entries    |
-| 0x00+s | 32 bits       | crc            |
+| 0x00+s | 32 bits       | CRC            |
 
 **Revision count** - Incremented every update, only the uncorrupted
 metadata-block with the most recent revision count contains the valid metadata.
@@ -75,7 +75,7 @@ Here's an example of a simple directory stored on disk:
 (32 bits) revision count = 10                    (0x0000000a)
 (32 bits) dir size       = 154 bytes, end of dir (0x0000009a)
 (64 bits) tail pointer   = 37, 36                (0x00000025, 0x00000024)
-(32 bits) crc            = 0xc86e3106
+(32 bits) CRC            = 0xc86e3106
 
 00000000: 0a 00 00 00 9a 00 00 00 25 00 00 00 24 00 00 00  ........%...$...
 00000010: 22 08 00 03 05 00 00 00 04 00 00 00 74 65 61 22  "...........tea"
@@ -121,24 +121,29 @@ Here's the layout of entries on disk:
 **Entry type** - Type of the entry, currently this is limited to the following:
 - 0x11 - file entry
 - 0x22 - directory entry
-- 0xe2 - superblock entry
+- 0x2e - superblock entry
 
-Additionally, the type is broken into two 4 bit nibbles, with the lower nibble
+Additionally, the type is broken into two 4 bit nibbles, with the upper nibble
 specifying the type's data structure used when scanning the filesystem. The
-upper nibble clarifies the type further when multiple entries share the same
+lower nibble clarifies the type further when multiple entries share the same
 data structure.
 
+The highest bit is reserved for marking the entry as "moved". If an entry
+is marked as "moved", the entry may also exist somewhere else in the
+filesystem. If the entry exists elsewhere, this entry must be treated as
+though it does not exist.
+
 **Entry length** - Length in bytes of the entry-specific data. This does
 not include the entry type size, attributes, or name. The full size in bytes
 of the entry is 4 + entry length + attribute length + name length.
 
 **Attribute length** - Length of system-specific attributes in bytes. Since
-attributes are system specific, there is not much garuntee on the values in
+attributes are system specific, there is not much guarantee on the values in
 this section, and systems are expected to work even when it is empty. See the
 [attributes](#entry-attributes) section for more details.
 
-**Name length** - Length of the entry name. Entry names are stored as utf8,
-although most systems will probably only support ascii. Entry names can not
+**Name length** - Length of the entry name. Entry names are stored as UTF8,
+although most systems will probably only support ASCII. Entry names can not
 contain '/' and can not be '.' or '..' as these are a part of the syntax of
 filesystem paths.
 
@@ -175,7 +180,7 @@ Here's the layout of the superblock entry:
 
 | offset | size                   | description                            |
 |--------|------------------------|----------------------------------------|
-| 0x00   | 8 bits                 | entry type (0xe2 for superblock entry) |
+| 0x00   | 8 bits                 | entry type (0x2e for superblock entry) |
 | 0x01   | 8 bits                 | entry length (20 bytes)                |
 | 0x02   | 8 bits                 | attribute length                       |
 | 0x03   | 8 bits                 | name length (8 bytes)                  |
@@ -208,7 +213,7 @@ Here's an example of a complete superblock:
 (32 bits) revision count   = 3                    (0x00000003)
 (32 bits) dir size         = 52 bytes, end of dir (0x00000034)
 (64 bits) tail pointer     = 3, 2                 (0x00000003, 0x00000002)
-(8 bits)  entry type       = superblock           (0xe2)
+(8 bits)  entry type       = superblock           (0x2e)
 (8 bits)  entry length     = 20 bytes             (0x14)
 (8 bits)  attribute length = 0 bytes              (0x00)
 (8 bits)  name length      = 8 bytes              (0x08)
@@ -217,10 +222,10 @@ Here's an example of a complete superblock:
 (32 bits) block count      = 1024 blocks          (0x00000400)
 (32 bits) version          = 1.1                  (0x00010001)
 (8 bytes) magic string     = littlefs
-(32 bits) crc              = 0xc50b74fa
+(32 bits) CRC              = 0xc50b74fa
 
 00000000: 03 00 00 00 34 00 00 00 03 00 00 00 02 00 00 00  ....4...........
-00000010: e2 14 00 08 03 00 00 00 02 00 00 00 00 02 00 00  ................
+00000010: 2e 14 00 08 03 00 00 00 02 00 00 00 00 02 00 00  ................
 00000020: 00 04 00 00 01 00 01 00 6c 69 74 74 6c 65 66 73  ........littlefs
 00000030: fa 74 0b c5                                      .t..
 ```
@@ -262,15 +267,19 @@ Here's an example of a directory entry:
 
 Files are stored in entries with a pointer to the head of the file and the
 size of the file. This is enough information to determine the state of the
-CTZ linked-list that is being referenced.
+CTZ skip-list that is being referenced.
 
 How files are actually stored on disk is a bit complicated. The full
-explanation of CTZ linked-lists can be found in [DESIGN.md](DESIGN.md#ctz-linked-lists).
+explanation of CTZ skip-lists can be found in [DESIGN.md](DESIGN.md#ctz-skip-lists).
 
 A terribly quick summary: For every nth block where n is divisible by 2^x,
-the block contains a pointer that points x blocks towards the beginning of the
-file. These pointers are stored in order of x in each block of the file
-immediately before the data in the block.
+the block contains a pointer to block n-2^x. These pointers are stored in
+increasing order of x in each block of the file preceding the data in the
+block.
+
+The maximum number of pointers in a block is bounded by the maximum file size
+divided by the block size. With 32 bits for file size, this results in a
+minimum block size of 104 bytes.
 
 Here's the layout of a file entry:
 
@@ -286,7 +295,7 @@ Here's the layout of a file entry:
 | 0xc+a  | name length bytes      | directory name                     |
 
 **File head** - Pointer to the block that is the head of the file's CTZ
-linked-list.
+skip-list.
 
 **File size** - Size of file in bytes.
 

emubd/lfs_emubd.c

@@ -1,8 +1,8 @@
 /*
  * Block device emulated on standard files
  *
- * Copyright (c) 2017 Christopher Haster
- * Distributed under the Apache 2.0 license
+ * Copyright (c) 2017, Arm Limited. All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
  */
 #include "emubd/lfs_emubd.h"
 
@@ -16,6 +16,41 @@
 #include <unistd.h>
 #include <assert.h>
 #include <stdbool.h>
+#include <inttypes.h>
+
+
+// Emulated block device utils
+static inline void lfs_emubd_tole32(lfs_emubd_t *emu) {
+    emu->cfg.read_size     = lfs_tole32(emu->cfg.read_size);
+    emu->cfg.prog_size     = lfs_tole32(emu->cfg.prog_size);
+    emu->cfg.block_size    = lfs_tole32(emu->cfg.block_size);
+    emu->cfg.block_count   = lfs_tole32(emu->cfg.block_count);
+
+    emu->stats.read_count  = lfs_tole32(emu->stats.read_count);
+    emu->stats.prog_count  = lfs_tole32(emu->stats.prog_count);
+    emu->stats.erase_count = lfs_tole32(emu->stats.erase_count);
+
+    for (int i = 0; i < sizeof(emu->history.blocks) /
+            sizeof(emu->history.blocks[0]); i++) {
+        emu->history.blocks[i] = lfs_tole32(emu->history.blocks[i]);
+    }
+}
+
+static inline void lfs_emubd_fromle32(lfs_emubd_t *emu) {
+    emu->cfg.read_size     = lfs_fromle32(emu->cfg.read_size);
+    emu->cfg.prog_size     = lfs_fromle32(emu->cfg.prog_size);
+    emu->cfg.block_size    = lfs_fromle32(emu->cfg.block_size);
+    emu->cfg.block_count   = lfs_fromle32(emu->cfg.block_count);
+
+    emu->stats.read_count  = lfs_fromle32(emu->stats.read_count);
+    emu->stats.prog_count  = lfs_fromle32(emu->stats.prog_count);
+    emu->stats.erase_count = lfs_fromle32(emu->stats.erase_count);
+
+    for (int i = 0; i < sizeof(emu->history.blocks) /
+            sizeof(emu->history.blocks[0]); i++) {
+        emu->history.blocks[i] = lfs_fromle32(emu->history.blocks[i]);
+    }
+}
 
 
 // Block device emulated on existing filesystem
@@ -45,20 +80,39 @@ int lfs_emubd_create(const struct lfs_config *cfg, const char *path) {
     }
 
     // Load stats to continue incrementing
-    snprintf(emu->child, LFS_NAME_MAX, "stats");
+    snprintf(emu->child, LFS_NAME_MAX, ".stats");
     FILE *f = fopen(emu->path, "r");
     if (!f) {
-        return -errno;
+        memset(&emu->stats, 0, sizeof(emu->stats));
+    } else {
+        size_t res = fread(&emu->stats, sizeof(emu->stats), 1, f);
+        lfs_emubd_fromle32(emu);
+        if (res < 1) {
+            return -errno;
+        }
+
+        err = fclose(f);
+        if (err) {
+            return -errno;
+        }
     }
 
-    size_t res = fread(&emu->stats, sizeof(emu->stats), 1, f);
-    if (res < 1) {
-        return -errno;
-    }
+    // Load history
+    snprintf(emu->child, LFS_NAME_MAX, ".history");
+    f = fopen(emu->path, "r");
+    if (!f) {
+        memset(&emu->history, 0, sizeof(emu->history));
+    } else {
+        size_t res = fread(&emu->history, sizeof(emu->history), 1, f);
+        lfs_emubd_fromle32(emu);
+        if (res < 1) {
+            return -errno;
+        }
 
-    err = fclose(f);
-    if (err) {
-        return -errno;
+        err = fclose(f);
+        if (err) {
+            return -errno;
+        }
     }
 
     return 0;
@@ -85,7 +139,7 @@ int lfs_emubd_read(const struct lfs_config *cfg, lfs_block_t block,
     memset(data, 0, size);
 
     // Read data
-    snprintf(emu->child, LFS_NAME_MAX, "%x", block);
+    snprintf(emu->child, LFS_NAME_MAX, "%" PRIx32, block);
 
     FILE *f = fopen(emu->path, "rb");
     if (!f && errno != ENOENT) {
@@ -124,11 +178,11 @@ int lfs_emubd_prog(const struct lfs_config *cfg, lfs_block_t block,
     assert(block < cfg->block_count);
 
     // Program data
-    snprintf(emu->child, LFS_NAME_MAX, "%x", block);
+    snprintf(emu->child, LFS_NAME_MAX, "%" PRIx32, block);
 
     FILE *f = fopen(emu->path, "r+b");
-    if (!f && errno != ENOENT) {
-        return -errno;
+    if (!f) {
+        return (errno == EACCES) ? 0 : -errno;
     }
 
     // Check that file was erased
@@ -160,6 +214,13 @@ int lfs_emubd_prog(const struct lfs_config *cfg, lfs_block_t block,
         return -errno;
     }
 
+    // update history and stats
+    if (block != emu->history.blocks[0]) {
+        memcpy(&emu->history.blocks[1], &emu->history.blocks[0],
+                sizeof(emu->history) - sizeof(emu->history.blocks[0]));
+        emu->history.blocks[0] = block;
+    }
+
     emu->stats.prog_count += 1;
     return 0;
 }
@@ -171,21 +232,21 @@ int lfs_emubd_erase(const struct lfs_config *cfg, lfs_block_t block) {
     assert(block < cfg->block_count);
 
     // Erase the block
-    snprintf(emu->child, LFS_NAME_MAX, "%x", block);
+    snprintf(emu->child, LFS_NAME_MAX, "%" PRIx32, block);
     struct stat st;
     int err = stat(emu->path, &st);
     if (err && errno != ENOENT) {
         return -errno;
     }
 
-    if (!err && S_ISREG(st.st_mode)) {
-        int err = unlink(emu->path);
+    if (!err && S_ISREG(st.st_mode) && (S_IWUSR & st.st_mode)) {
+        err = unlink(emu->path);
         if (err) {
             return -errno;
         }
     }
 
-    if (err || S_ISREG(st.st_mode)) {
+    if (err || (S_ISREG(st.st_mode) && (S_IWUSR & st.st_mode))) {
         FILE *f = fopen(emu->path, "w");
         if (!f) {
             return -errno;
@@ -205,13 +266,15 @@ int lfs_emubd_sync(const struct lfs_config *cfg) {
     lfs_emubd_t *emu = cfg->context;
 
     // Just write out info/stats for later lookup
-    snprintf(emu->child, LFS_NAME_MAX, "config");
+    snprintf(emu->child, LFS_NAME_MAX, ".config");
     FILE *f = fopen(emu->path, "w");
     if (!f) {
         return -errno;
     }
 
+    lfs_emubd_tole32(emu);
     size_t res = fwrite(&emu->cfg, sizeof(emu->cfg), 1, f);
+    lfs_emubd_fromle32(emu);
     if (res < 1) {
         return -errno;
     }
@@ -221,13 +284,33 @@ int lfs_emubd_sync(const struct lfs_config *cfg) {
         return -errno;
     }
 
-    snprintf(emu->child, LFS_NAME_MAX, "stats");
+    snprintf(emu->child, LFS_NAME_MAX, ".stats");
     f = fopen(emu->path, "w");
     if (!f) {
         return -errno;
     }
 
+    lfs_emubd_tole32(emu);
     res = fwrite(&emu->stats, sizeof(emu->stats), 1, f);
+    lfs_emubd_fromle32(emu);
+    if (res < 1) {
+        return -errno;
+    }
+
+    err = fclose(f);
+    if (err) {
+        return -errno;
+    }
+
+    snprintf(emu->child, LFS_NAME_MAX, ".history");
+    f = fopen(emu->path, "w");
+    if (!f) {
+        return -errno;
+    }
+
+    lfs_emubd_tole32(emu);
+    res = fwrite(&emu->history, sizeof(emu->history), 1, f);
+    lfs_emubd_fromle32(emu);
     if (res < 1) {
         return -errno;
     }
@@ -239,4 +322,3 @@ int lfs_emubd_sync(const struct lfs_config *cfg) {
 
     return 0;
 }
-

emubd/lfs_emubd.h

@@ -1,8 +1,8 @@
 /*
  * Block device emulated on standard files
  *
- * Copyright (c) 2017 Christopher Haster
- * Distributed under the Apache 2.0 license
+ * Copyright (c) 2017, Arm Limited. All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
  */
 #ifndef LFS_EMUBD_H
 #define LFS_EMUBD_H
@@ -10,6 +10,11 @@
 #include "lfs.h"
 #include "lfs_util.h"
 
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+
 
 // Config options
 #ifndef LFS_EMUBD_READ_SIZE
@@ -40,6 +45,10 @@ typedef struct lfs_emubd {
         uint64_t erase_count;
     } stats;
 
+    struct {
+        lfs_block_t blocks[4];
+    } history;
+
     struct {
         uint32_t read_size;
         uint32_t prog_size;
@@ -75,4 +84,8 @@ int lfs_emubd_erase(const struct lfs_config *cfg, lfs_block_t block);
 int lfs_emubd_sync(const struct lfs_config *cfg);
 
 
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
 #endif

lfs.h

@@ -1,8 +1,8 @@
 /*
  * The little filesystem
  *
- * Copyright (c) 2017 Christopher Haster
- * Distributed under the Apache 2.0 license
+ * Copyright (c) 2017, Arm Limited. All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
  */
 #ifndef LFS_H
 #define LFS_H
@@ -10,6 +10,28 @@
 #include <stdint.h>
 #include <stdbool.h>
 
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+
+
+/// Version info ///
+
+// Software library version
+// Major (top-nibble), incremented on backwards incompatible changes
+// Minor (bottom-nibble), incremented on feature additions
+#define LFS_VERSION 0x00020000
+#define LFS_VERSION_MAJOR (0xffff & (LFS_VERSION >> 16))
+#define LFS_VERSION_MINOR (0xffff & (LFS_VERSION >>  0))
+
+// Version of On-disk data structures
+// Major (top-nibble), incremented on backwards incompatible changes
+// Minor (bottom-nibble), incremented on feature additions
+#define LFS_DISK_VERSION 0x00020000
+#define LFS_DISK_VERSION_MAJOR (0xffff & (LFS_DISK_VERSION >> 16))
+#define LFS_DISK_VERSION_MINOR (0xffff & (LFS_DISK_VERSION >>  0))
+
 
 /// Definitions ///
 
@@ -22,48 +44,95 @@ typedef int32_t  lfs_soff_t;
 
 typedef uint32_t lfs_block_t;
 
-// Max name size in bytes
+// Maximum size of all attributes per file in bytes, may be redefined but a
+// a smaller LFS_ATTR_MAX has no benefit. Stored in 12-bits and limited
+// to <= 0xfff. Stored in superblock and must be respected by other
+// littlefs drivers.
+#ifndef LFS_ATTR_MAX
+#define LFS_ATTR_MAX 0xfff
+#endif
+
+// Maximum name size in bytes, may be redefined to reduce the size of the
+// info struct. Limited to <= LFS_ATTR_MAX. Stored in superblock and must
+// be respected by other littlefs drivers.
 #ifndef LFS_NAME_MAX
-#define LFS_NAME_MAX 255
+#define LFS_NAME_MAX 0xff
+#endif
+
+// Maximum inline file size in bytes. Large inline files require a larger
+// cache size, but if a file can be inline it does not need its own data
+// block. Limited to <= LFS_ATTR_MAX and <= cache_size. Stored in superblock
+// and must be respected by other littlefs drivers.
+#ifndef LFS_INLINE_MAX
+#define LFS_INLINE_MAX 0xfff
 #endif
 
 // Possible error codes, these are negative to allow
 // valid positive return values
 enum lfs_error {
-    LFS_ERR_OK      = 0,    // No error
-    LFS_ERR_IO      = -5,   // Error during device operation
-    LFS_ERR_CORRUPT = -52,  // Corrupted
-    LFS_ERR_NOENT   = -2,   // No directory entry
-    LFS_ERR_EXISTS  = -17,  // Entry already exists
-    LFS_ERR_NOTDIR  = -20,  // Entry is not a dir
-    LFS_ERR_ISDIR   = -21,  // Entry is a dir
-    LFS_ERR_INVAL   = -22,  // Invalid parameter
-    LFS_ERR_NOSPC   = -28,  // No space left on device
-    LFS_ERR_NOMEM   = -12,  // No more memory available
+    LFS_ERR_OK          = 0,    // No error
+    LFS_ERR_IO          = -5,   // Error during device operation
+    LFS_ERR_CORRUPT     = -84,  // Corrupted
+    LFS_ERR_NOENT       = -2,   // No directory entry
+    LFS_ERR_EXIST       = -17,  // Entry already exists
+    LFS_ERR_NOTDIR      = -20,  // Entry is not a dir
+    LFS_ERR_ISDIR       = -21,  // Entry is a dir
+    LFS_ERR_NOTEMPTY    = -39,  // Dir is not empty
+    LFS_ERR_BADF        = -9,   // Bad file number
+    LFS_ERR_INVAL       = -22,  // Invalid parameter
+    LFS_ERR_NOSPC       = -28,  // No space left on device
+    LFS_ERR_NOMEM       = -12,  // No more memory available
+    LFS_ERR_NAMETOOLONG = -36,  // File name too long
 };
 
 // File types
 enum lfs_type {
-    LFS_TYPE_REG        = 0x11,
-    LFS_TYPE_DIR        = 0x22,
-    LFS_TYPE_SUPERBLOCK = 0x2e,
+    // file types
+    LFS_TYPE_REG            = 0x001,
+    LFS_TYPE_DIR            = 0x002,
+
+    // internally used types
+    LFS_TYPE_USER           = 0x100,
+    LFS_TYPE_SUPERBLOCK     = 0x011,
+    LFS_TYPE_ROOT           = 0x012,
+    LFS_TYPE_NAME           = 0x000,
+    LFS_TYPE_DELETE         = 0x030,
+    LFS_TYPE_STRUCT         = 0x040,
+    LFS_TYPE_GLOBALS        = 0x080,
+    LFS_TYPE_TAIL           = 0x0c0,
+    LFS_TYPE_SOFTTAIL       = 0x0c0,
+    LFS_TYPE_HARDTAIL       = 0x0c1,
+    LFS_TYPE_CRC            = 0x0f0,
+
+    LFS_TYPE_DIRSTRUCT      = 0x040,
+    LFS_TYPE_INLINESTRUCT   = 0x041,
+    LFS_TYPE_CTZSTRUCT      = 0x042,
+
+    // internal chip sources
+    LFS_FROM_REGION         = 0x000,
+    LFS_FROM_DISK           = 0x200,
+    LFS_FROM_MOVE           = 0x050,
+    LFS_FROM_ATTRS          = 0x060,
+    LFS_FROM_SUPERBLOCK     = 0x070,
 };
 
 // File open flags
 enum lfs_open_flags {
     // open flags
-    LFS_O_RDONLY = 1,        // Open a file as read only
-    LFS_O_WRONLY = 2,        // Open a file as write only
-    LFS_O_RDWR   = 3,        // Open a file as read and write
-    LFS_O_CREAT  = 0x0100,   // Create a file if it does not exist
-    LFS_O_EXCL   = 0x0200,   // Fail if a file already exists
-    LFS_O_TRUNC  = 0x0400,   // Truncate the existing file to zero size
-    LFS_O_APPEND = 0x0800,   // Move to end of file on every write
+    LFS_O_RDONLY = 1,         // Open a file as read only
+    LFS_O_WRONLY = 2,         // Open a file as write only
+    LFS_O_RDWR   = 3,         // Open a file as read and write
+    LFS_O_CREAT  = 0x0100,    // Create a file if it does not exist
+    LFS_O_EXCL   = 0x0200,    // Fail if a file already exists
+    LFS_O_TRUNC  = 0x0400,    // Truncate the existing file to zero size
+    LFS_O_APPEND = 0x0800,    // Move to end of file on every write
 
     // internally used flags
-    LFS_F_DIRTY   = 0x10000, // File does not match storage
-    LFS_F_WRITING = 0x20000, // File has been written since last flush
-    LFS_F_READING = 0x40000, // File has been read since last flush
+    LFS_F_DIRTY   = 0x010000, // File does not match storage
+    LFS_F_WRITING = 0x020000, // File has been written since last flush
+    LFS_F_READING = 0x040000, // File has been read since last flush
+    LFS_F_ERRED   = 0x080000, // An error occured during write
+    LFS_F_INLINE  = 0x100000, // Currently inlined in directory entry
 };
 
 // File seek flags
@@ -87,38 +156,48 @@ struct lfs_config {
 
     // Program a region in a block. The block must have previously
     // been erased. Negative error codes are propogated to the user.
-    // The prog function must return LFS_ERR_CORRUPT if the block should
-    // be considered bad.
+    // May return LFS_ERR_CORRUPT if the block should be considered bad.
     int (*prog)(const struct lfs_config *c, lfs_block_t block,
             lfs_off_t off, const void *buffer, lfs_size_t size);
 
     // Erase a block. A block must be erased before being programmed.
     // The state of an erased block is undefined. Negative error codes
     // are propogated to the user.
+    // May return LFS_ERR_CORRUPT if the block should be considered bad.
     int (*erase)(const struct lfs_config *c, lfs_block_t block);
 
     // Sync the state of the underlying block device. Negative error codes
     // are propogated to the user.
     int (*sync)(const struct lfs_config *c);
 
-    // Minimum size of a block read. This determines the size of read buffers.
-    // This may be larger than the physical read size to improve performance
-    // by caching more of the block device.
+    // Minimum size of a block read. All read operations will be a
+    // multiple of this value.
     lfs_size_t read_size;
 
-    // Minimum size of a block program. This determines the size of program
-    // buffers. This may be larger than the physical program size to improve
-    // performance by caching more of the block device.
+    // Minimum size of a block program. All program operations will be a
+    // multiple of this value.
     lfs_size_t prog_size;
 
     // Size of an erasable block. This does not impact ram consumption and
     // may be larger than the physical erase size. However, this should be
-    // kept small as each file currently takes up an entire block .
+    // kept small as each file currently takes up an entire block.
+    // Must be a multiple of the read, program, and cache sizes.
     lfs_size_t block_size;
 
     // Number of erasable blocks on the device.
     lfs_size_t block_count;
 
+    // Number of erase cycles before we should move data to another block.
+    // May be zero to never move data, in which case no block-level
+    // wear-leveling is performed.
+    uint32_t block_cycles;
+
+    // Size of block caches. Each cache buffers a portion of a block in RAM.
+    // This determines the size of the read cache, the program cache, and a
+    // cache per file. Larger caches can improve performance by storing more
+    // data. Must be a multiple of the read and program sizes.
+    lfs_size_t cache_size;
+
     // Number of blocks to lookahead during block allocation. A larger
     // lookahead reduces the number of passes required to allocate a block.
     // The lookahead buffer requires only 1 bit per block so it can be quite
@@ -135,11 +214,25 @@ struct lfs_config {
     // lookahead block.
     void *lookahead_buffer;
 
-    // Optional, statically allocated buffer for files. Must be program sized.
-    // If enabled, only one file may be opened at a time.
-    void *file_buffer;
-};
+    // Optional upper limit on file attributes in bytes. No downside for larger
+    // attributes size but must be less than LFS_ATTR_MAX. Defaults to
+    // LFS_ATTR_MAX when zero.Stored in superblock and must be respected by
+    // other littlefs drivers.
+    lfs_size_t attr_max;
 
+    // Optional upper limit on length of file names in bytes. No downside for
+    // larger names except the size of the info struct which is controlled by
+    // the LFS_NAME_MAX define. Defaults to LFS_NAME_MAX when zero. Stored in
+    // superblock and must be respected by other littlefs drivers.
+    lfs_size_t name_max;
+
+    // Optional upper limit on inlined files in bytes. Large inline files
+    // require a larger cache size, but if a file can be inlined it does not
+    // need its own data block. Must be smaller than cache_size and less than
+    // LFS_INLINE_MAX. Defaults to min(LFS_INLINE_MAX, read_size) when zero.
+    // Stored in superblock and must be respected by other littlefs drivers.
+    lfs_size_t inline_max;
+};
 
 // File info structure
 struct lfs_info {
@@ -153,97 +246,154 @@ struct lfs_info {
     char name[LFS_NAME_MAX+1];
 };
 
+// Custom attribute structure
+struct lfs_attr {
+    // 8-bit type of attribute, provided by user and used to
+    // identify the attribute
+    uint8_t type;
+
+    // Pointer to buffer containing the attribute
+    void *buffer;
+
+    // Size of attribute in bytes, limited to LFS_ATTR_MAX
+    lfs_size_t size;
+
+    // Pointer to next attribute in linked list
+    struct lfs_attr *next;
+};
+
+// Optional configuration provided during lfs_file_opencfg
+struct lfs_file_config {
+    // Optional, statically allocated buffer for files. Must be program sized.
+    // If NULL, malloc will be used by default.
+    void *buffer;
+
+    // Optional, linked list of custom attributes related to the file. If the
+    // file is opened with read access, the attributes will be read from
+    // during the open call. If the file is opened with write access, the
+    // attributes will be written to disk every file sync or close. This
+    // write occurs atomically with update to the file's contents.
+    //
+    // Custom attributes are uniquely identified by an 8-bit type and limited
+    // to LFS_ATTR_MAX bytes. When read, if the stored attribute is smaller
+    // than the buffer, it will be padded with zeros. If the stored attribute
+    // is larger, then it will be silently truncated. If the attribute is not
+    // found, it will be created implicitly.
+    struct lfs_attr *attrs;
+};
+
 
 /// littlefs data structures ///
-typedef struct lfs_entry {
-    lfs_off_t off;
-
-    struct lfs_disk_entry {
-        uint8_t type;
-        uint8_t elen;
-        uint8_t alen;
-        uint8_t nlen;
-        union {
-            struct {
-                lfs_block_t head;
-                lfs_size_t size;
-            } file;
-            lfs_block_t dir[2];
-        } u;
-    } d;
-} lfs_entry_t;
+typedef struct lfs_mattr {
+    int32_t tag;
+    const void *buffer;
+    const struct lfs_mattr *next;
+} lfs_mattr_t;
 
 typedef struct lfs_cache {
     lfs_block_t block;
     lfs_off_t off;
+    lfs_size_t size;
     uint8_t *buffer;
 } lfs_cache_t;
 
+typedef union lfs_global {
+    uint32_t u32[3];
+    struct {
+        lfs_block_t movepair[2];
+        uint16_t moveid;
+        bool deorphaned;
+    } s;
+} lfs_global_t;
+
+typedef struct lfs_mdir {
+    lfs_block_t pair[2];
+    uint32_t rev;
+    uint32_t etag;
+    lfs_off_t off;
+    uint16_t count;
+    bool erased;
+    bool split;
+    lfs_block_t tail[2];
+    lfs_global_t locals;
+} lfs_mdir_t;
+
+typedef struct lfs_mlist {
+    struct lfs_mlist *next;
+    uint16_t id;
+    uint8_t type;
+    lfs_mdir_t m;
+} lfs_mlist_t;
+
+typedef struct lfs_dir {
+    struct lfs_dir *next;
+    uint16_t id;
+    uint8_t type;
+    lfs_mdir_t m;
+
+    lfs_off_t pos;
+    lfs_block_t head[2];
+} lfs_dir_t;
+
 typedef struct lfs_file {
     struct lfs_file *next;
-    lfs_block_t pair[2];
-    lfs_off_t poff;
+    uint16_t id;
+    uint8_t type;
+    lfs_mdir_t m;
 
-    lfs_block_t head;
-    lfs_size_t size;
+    struct lfs_ctz {
+        lfs_block_t head;
+        lfs_size_t size;
+    } ctz;
 
     uint32_t flags;
     lfs_off_t pos;
     lfs_block_t block;
     lfs_off_t off;
     lfs_cache_t cache;
+
+    const struct lfs_file_config *cfg;
 } lfs_file_t;
 
-typedef struct lfs_dir {
-    lfs_block_t pair[2];
-    lfs_off_t off;
-
-    lfs_block_t head[2];
-    lfs_off_t pos;
-
-    struct lfs_disk_dir {
-        uint32_t rev;
-        lfs_size_t size;
-        lfs_block_t tail[2];
-    } d;
-} lfs_dir_t;
-
 typedef struct lfs_superblock {
-    lfs_off_t off;
+    char magic[8];
+    uint32_t version;
 
-    struct lfs_disk_superblock {
-        uint8_t type;
-        uint8_t elen;
-        uint8_t alen;
-        uint8_t nlen;
-        lfs_block_t root[2];
-        uint32_t block_size;
-        uint32_t block_count;
-        uint32_t version;
-        char magic[8];
-    } d;
+    lfs_size_t block_size;
+    lfs_size_t block_count;
+
+    lfs_size_t attr_max;
+    lfs_size_t name_max;
+    lfs_size_t inline_max;
 } lfs_superblock_t;
 
 typedef struct lfs_free {
-    lfs_size_t lookahead;
-    lfs_block_t begin;
-    lfs_block_t end;
     lfs_block_t off;
+    lfs_block_t size;
+    lfs_block_t i;
+    lfs_block_t ack;
     uint32_t *buffer;
 } lfs_free_t;
 
 // The littlefs type
 typedef struct lfs {
-    const struct lfs_config *cfg;
-
-    lfs_block_t root[2];
-    lfs_file_t *files;
-
     lfs_cache_t rcache;
     lfs_cache_t pcache;
 
+    lfs_block_t root[2];
+    lfs_mlist_t *mlist;
+    uint32_t seed;
+
+    lfs_global_t globals;
+    lfs_global_t locals;
     lfs_free_t free;
-    bool deorphaned;
+
+    const struct lfs_config *cfg;
+    lfs_size_t block_size;
+    lfs_size_t block_count;
+    lfs_size_t attr_max;
+    lfs_size_t name_max;
+    lfs_size_t inline_max;
 } lfs_t;
 
 
@@ -252,7 +402,8 @@ typedef struct lfs {
 // Format a block device with the littlefs
 //
 // Requires a littlefs object and config struct. This clobbers the littlefs
-// object, and does not leave the filesystem mounted.
+// object, and does not leave the filesystem mounted. The config struct must
+// be zeroed for defaults and backwards compatibility.
 //
 // Returns a negative error code on failure.
 int lfs_format(lfs_t *lfs, const struct lfs_config *config);
@@ -261,7 +412,8 @@ int lfs_format(lfs_t *lfs, const struct lfs_config *config);
 //
 // Requires a littlefs object and config struct. Multiple filesystems
 // may be mounted simultaneously with multiple littlefs objects. Both
-// lfs and config must be allocated while mounted.
+// lfs and config must be allocated while mounted. The config struct must
+// be zeroed for defaults and backwards compatibility.
 //
 // Returns a negative error code on failure.
 int lfs_mount(lfs_t *lfs, const struct lfs_config *config);
@@ -285,10 +437,6 @@ int lfs_remove(lfs_t *lfs, const char *path);
 // If the destination exists, it must match the source in type.
 // If the destination is a directory, the directory must be empty.
 //
-// Note: If power loss occurs, it is possible that the file or directory
-// will exist in both the oldpath and newpath simultaneously after the
-// next mount.
-//
 // Returns a negative error code on failure.
 int lfs_rename(lfs_t *lfs, const char *oldpath, const char *newpath);
 
@@ -298,19 +446,57 @@ int lfs_rename(lfs_t *lfs, const char *oldpath, const char *newpath);
 // Returns a negative error code on failure.
 int lfs_stat(lfs_t *lfs, const char *path, struct lfs_info *info);
 
+// Get a custom attribute
+//
+// Custom attributes are uniquely identified by an 8-bit type and limited
+// to LFS_ATTR_MAX bytes. When read, if the stored attribute is smaller than
+// the buffer, it will be padded with zeros. If the stored attribute is larger,
+// then it will be silently truncated.
+//
+// Returns the size of the attribute, or a negative error code on failure.
+// Note, the returned size is the size of the attribute on disk, irrespective
+// of the size of the buffer. This can be used to dynamically allocate a buffer
+// or check for existance.
+lfs_ssize_t lfs_getattr(lfs_t *lfs, const char *path,
+        uint8_t type, void *buffer, lfs_size_t size);
+
+// Set custom attributes
+//
+// Custom attributes are uniquely identified by an 8-bit type and limited
+// to LFS_ATTR_MAX bytes. If an attribute is not found, it will be
+// implicitly created, and setting the size of an attribute to zero deletes
+// the attribute.
+//
+// Returns a negative error code on failure.
+int lfs_setattr(lfs_t *lfs, const char *path,
+        uint8_t type, const void *buffer, lfs_size_t size);
+
 
 /// File operations ///
 
 // Open a file
 //
-// The mode that the file is opened in is determined
-// by the flags, which are values from the enum lfs_open_flags
-// that are bitwise-ored together.
+// The mode that the file is opened in is determined by the flags, which
+// are values from the enum lfs_open_flags that are bitwise-ored together.
 //
 // Returns a negative error code on failure.
 int lfs_file_open(lfs_t *lfs, lfs_file_t *file,
         const char *path, int flags);
 
+// Open a file with extra configuration
+//
+// The mode that the file is opened in is determined by the flags, which
+// are values from the enum lfs_open_flags that are bitwise-ored together.
+//
+// The config struct provides additional config options per file as described
+// above. The config struct must be allocated while the file is open, and the
+// config struct must be zeroed for defaults and backwards compatibility.
+//
+// Returns a negative error code on failure.
+int lfs_file_opencfg(lfs_t *lfs, lfs_file_t *file,
+        const char *path, int flags,
+        const struct lfs_file_config *config);
+
 // Close a file
 //
 // Any pending writes are written out to storage as though
@@ -348,6 +534,11 @@ lfs_ssize_t lfs_file_write(lfs_t *lfs, lfs_file_t *file,
 lfs_soff_t lfs_file_seek(lfs_t *lfs, lfs_file_t *file,
         lfs_soff_t off, int whence);
 
+// Truncates the size of the file to the specified size
+//
+// Returns a negative error code on failure.
+int lfs_file_truncate(lfs_t *lfs, lfs_file_t *file, lfs_off_t size);
+
 // Return the position of the file
 //
 // Equivalent to lfs_file_seek(lfs, file, 0, LFS_SEEK_CUR)
@@ -414,7 +605,15 @@ lfs_soff_t lfs_dir_tell(lfs_t *lfs, lfs_dir_t *dir);
 int lfs_dir_rewind(lfs_t *lfs, lfs_dir_t *dir);
 
 
-/// Miscellaneous littlefs specific operations ///
+/// Filesystem-level filesystem operations
+
+// Finds the current size of the filesystem
+//
+// Note: Result is best effort. If files share COW structures, the returned
+// size may be larger than the filesystem actually is.
+//
+// Returns the number of allocated blocks, or a negative error code on failure.
+lfs_ssize_t lfs_fs_size(lfs_t *lfs);
 
 // Traverse through all blocks in use by the filesystem
 //
@@ -423,19 +622,40 @@ int lfs_dir_rewind(lfs_t *lfs, lfs_dir_t *dir);
 // blocks are in use or how much of the storage is available.
 //
 // Returns a negative error code on failure.
-int lfs_traverse(lfs_t *lfs, int (*cb)(void*, lfs_block_t), void *data);
+int lfs_fs_traverse(lfs_t *lfs, int (*cb)(void*, lfs_block_t), void *data);
 
-// Prunes any recoverable errors that may have occured in the filesystem
+// Get custom attributes on the filesystem
 //
-// Not needed to be called by user unless an operation is interrupted
-// but the filesystem is still mounted. This is already called on first
-// allocation.
+// Custom attributes are uniquely identified by an 8-bit type and limited
+// to LFS_ATTR_MAX bytes. When read, if the stored attribute is smaller than
+// the buffer, it will be padded with zeros. If the stored attribute is larger,
+// then it will be silently truncated.
+//
+// Note, filesystem-level attributes are not available for wear-leveling
+//
+// Returns the size of the attribute, or a negative error code on failure.
+// Note, the returned size is the size of the attribute on disk, irrespective
+// of the size of the buffer. This can be used to dynamically allocate a buffer
+// or check for existance.
+lfs_ssize_t lfs_fs_getattr(lfs_t *lfs,
+        uint8_t type, void *buffer, lfs_size_t size);
+
+// Set custom attributes on the filesystem
+//
+// Custom attributes are uniquely identified by an 8-bit type and limited
+// to LFS_ATTR_MAX bytes. If an attribute is not found, it will be
+// implicitly created, and setting the size of an attribute to zero deletes
+// the attribute.
+//
+// Note, filesystem-level attributes are not available for wear-leveling
 //
 // Returns a negative error code on failure.
-int lfs_deorphan(lfs_t *lfs);
+int lfs_fs_setattr(lfs_t *lfs,
+        uint8_t type, const void *buffer, lfs_size_t size);
 
-// TODO doc
-int lfs_deduplicate(lfs_t *lfs);
 
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
 
 #endif

lfs_util.c

@@ -1,13 +1,17 @@
 /*
  * lfs util functions
  *
- * Copyright (c) 2017 Christopher Haster
- * Distributed under the Apache 2.0 license
+ * Copyright (c) 2017, Arm Limited. All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
  */
 #include "lfs_util.h"
 
+// Only compile if user does not provide custom config
+#ifndef LFS_CONFIG
 
-void lfs_crc(uint32_t *restrict crc, const void *buffer, size_t size) {
+
+// Software CRC implementation with small lookup table
+uint32_t lfs_crc32(uint32_t crc, const void *buffer, size_t size) {
     static const uint32_t rtable[16] = {
         0x00000000, 0x1db71064, 0x3b6e20c8, 0x26d930ac,
         0x76dc4190, 0x6b6b51f4, 0x4db26158, 0x5005713c,
@@ -18,8 +22,12 @@ void lfs_crc(uint32_t *restrict crc, const void *buffer, size_t size) {
     const uint8_t *data = buffer;
 
     for (size_t i = 0; i < size; i++) {
-        *crc = (*crc >> 4) ^ rtable[(*crc ^ (data[i] >> 0)) & 0xf];
-        *crc = (*crc >> 4) ^ rtable[(*crc ^ (data[i] >> 4)) & 0xf];
+        crc = (crc >> 4) ^ rtable[(crc ^ (data[i] >> 0)) & 0xf];
+        crc = (crc >> 4) ^ rtable[(crc ^ (data[i] >> 4)) & 0xf];
     }
+
+    return crc;
 }
 
+
+#endif

lfs_util.h

@@ -1,19 +1,85 @@
 /*
  * lfs utility functions
  *
- * Copyright (c) 2017 Christopher Haster
- * Distributed under the Apache 2.0 license
+ * Copyright (c) 2017, Arm Limited. All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
  */
 #ifndef LFS_UTIL_H
 #define LFS_UTIL_H
 
-#include <stdlib.h>
+// Users can override lfs_util.h with their own configuration by defining
+// LFS_CONFIG as a header file to include (-DLFS_CONFIG=lfs_config.h).
+//
+// If LFS_CONFIG is used, none of the default utils will be emitted and must be
+// provided by the config file. To start, I would suggest copying lfs_util.h
+// and modifying as needed.
+#ifdef LFS_CONFIG
+#define LFS_STRINGIZE(x) LFS_STRINGIZE2(x)
+#define LFS_STRINGIZE2(x) #x
+#include LFS_STRINGIZE(LFS_CONFIG)
+#else
+
+// System includes
 #include <stdint.h>
+#include <stdbool.h>
+#include <string.h>
+#include <inttypes.h>
+
+#ifndef LFS_NO_MALLOC
+#include <stdlib.h>
+#endif
+#ifndef LFS_NO_ASSERT
+#include <assert.h>
+#endif
+#if !defined(LFS_NO_DEBUG) || !defined(LFS_NO_WARN) || !defined(LFS_NO_ERROR)
 #include <stdio.h>
+#endif
+
+#ifdef __cplusplus
+extern "C"
+{
+#endif
 
 
-// Builtin functions, these may be replaced by more
-// efficient implementations in the system
+// Macros, may be replaced by system specific wrappers. Arguments to these
+// macros must not have side-effects as the macros can be removed for a smaller
+// code footprint
+
+// Logging functions
+#ifndef LFS_NO_DEBUG
+#define LFS_DEBUG(fmt, ...) \
+    printf("lfs debug:%d: " fmt "\n", __LINE__, __VA_ARGS__)
+#else
+#define LFS_DEBUG(fmt, ...)
+#endif
+
+#ifndef LFS_NO_WARN
+#define LFS_WARN(fmt, ...) \
+    printf("lfs warn:%d: " fmt "\n", __LINE__, __VA_ARGS__)
+#else
+#define LFS_WARN(fmt, ...)
+#endif
+
+#ifndef LFS_NO_ERROR
+#define LFS_ERROR(fmt, ...) \
+    printf("lfs error:%d: " fmt "\n", __LINE__, __VA_ARGS__)
+#else
+#define LFS_ERROR(fmt, ...)
+#endif
+
+// Runtime assertions
+#ifndef LFS_NO_ASSERT
+#define LFS_ASSERT(test) assert(test)
+#else
+#define LFS_ASSERT(test)
+#endif
+
+
+// Builtin functions, these may be replaced by more efficient
+// toolchain-specific implementations. LFS_NO_INTRINSICS falls back to a more
+// expensive basic C implementation for debugging purposes
+
+// Min/max functions for unsigned 32-bit numbers
 static inline uint32_t lfs_max(uint32_t a, uint32_t b) {
     return (a > b) ? a : b;
 }
@@ -22,27 +88,130 @@ static inline uint32_t lfs_min(uint32_t a, uint32_t b) {
     return (a < b) ? a : b;
 }
 
-static inline uint32_t lfs_ctz(uint32_t a) {
-    return __builtin_ctz(a);
+// Align to nearest multiple of a size
+static inline uint32_t lfs_aligndown(uint32_t a, uint32_t alignment) {
+    return a - (a % alignment);
 }
 
+static inline uint32_t lfs_alignup(uint32_t a, uint32_t alignment) {
+    return lfs_aligndown(a + alignment-1, alignment);
+}
+
+// Find the next smallest power of 2 less than or equal to a
 static inline uint32_t lfs_npw2(uint32_t a) {
+#if !defined(LFS_NO_INTRINSICS) && (defined(__GNUC__) || defined(__CC_ARM))
     return 32 - __builtin_clz(a-1);
+#else
+    uint32_t r = 0;
+    uint32_t s;
+    a -= 1;
+    s = (a > 0xffff) << 4; a >>= s; r |= s;
+    s = (a > 0xff  ) << 3; a >>= s; r |= s;
+    s = (a > 0xf   ) << 2; a >>= s; r |= s;
+    s = (a > 0x3   ) << 1; a >>= s; r |= s;
+    return (r | (a >> 1)) + 1;
+#endif
 }
 
+// Count the number of trailing binary zeros in a
+// lfs_ctz(0) may be undefined
+static inline uint32_t lfs_ctz(uint32_t a) {
+#if !defined(LFS_NO_INTRINSICS) && defined(__GNUC__)
+    return __builtin_ctz(a);
+#else
+    return lfs_npw2((a & -a) + 1) - 1;
+#endif
+}
+
+// Count the number of binary ones in a
+static inline uint32_t lfs_popc(uint32_t a) {
+#if !defined(LFS_NO_INTRINSICS) && (defined(__GNUC__) || defined(__CC_ARM))
+    return __builtin_popcount(a);
+#else
+    a = a - ((a >> 1) & 0x55555555);
+    a = (a & 0x33333333) + ((a >> 2) & 0x33333333);
+    return (((a + (a >> 4)) & 0xf0f0f0f) * 0x1010101) >> 24;
+#endif
+}
+
+// Find the sequence comparison of a and b, this is the distance
+// between a and b ignoring overflow
 static inline int lfs_scmp(uint32_t a, uint32_t b) {
     return (int)(unsigned)(a - b);
 }
 
-// CRC-32 with polynomial = 0x04c11db7
-void lfs_crc(uint32_t *crc, const void *buffer, size_t size);
+// Convert between 32-bit little-endian and native order
+static inline uint32_t lfs_fromle32(uint32_t a) {
+#if !defined(LFS_NO_INTRINSICS) && ( \
+    (defined(  BYTE_ORDER  ) &&   BYTE_ORDER   ==   ORDER_LITTLE_ENDIAN  ) || \
+    (defined(__BYTE_ORDER  ) && __BYTE_ORDER   == __ORDER_LITTLE_ENDIAN  ) || \
+    (defined(__BYTE_ORDER__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__))
+    return a;
+#elif !defined(LFS_NO_INTRINSICS) && ( \
+    (defined(  BYTE_ORDER  ) &&   BYTE_ORDER   ==   ORDER_BIG_ENDIAN  ) || \
+    (defined(__BYTE_ORDER  ) && __BYTE_ORDER   == __ORDER_BIG_ENDIAN  ) || \
+    (defined(__BYTE_ORDER__) && __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__))
+    return __builtin_bswap32(a);
+#else
+    return (((uint8_t*)&a)[0] <<  0) |
+           (((uint8_t*)&a)[1] <<  8) |
+           (((uint8_t*)&a)[2] << 16) |
+           (((uint8_t*)&a)[3] << 24);
+#endif
+}
+
+static inline uint32_t lfs_tole32(uint32_t a) {
+    return lfs_fromle32(a);
+}
+
+// Convert between 16-bit little-endian and native order
+static inline uint16_t lfs_fromle16(uint16_t a) {
+#if !defined(LFS_NO_INTRINSICS) && ( \
+    (defined(  BYTE_ORDER  ) &&   BYTE_ORDER   ==   ORDER_LITTLE_ENDIAN  ) || \
+    (defined(__BYTE_ORDER  ) && __BYTE_ORDER   == __ORDER_LITTLE_ENDIAN  ) || \
+    (defined(__BYTE_ORDER__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__))
+    return a;
+#elif !defined(LFS_NO_INTRINSICS) && ( \
+    (defined(  BYTE_ORDER  ) &&   BYTE_ORDER   ==   ORDER_BIG_ENDIAN  ) || \
+    (defined(__BYTE_ORDER  ) && __BYTE_ORDER   == __ORDER_BIG_ENDIAN  ) || \
+    (defined(__BYTE_ORDER__) && __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__))
+    return __builtin_bswap16(a);
+#else
+    return (((uint8_t*)&a)[0] <<  0) |
+           (((uint8_t*)&a)[1] <<  8);
+#endif
+}
+
+static inline uint16_t lfs_tole16(uint16_t a) {
+    return lfs_fromle16(a);
+}
+
+// Calculate CRC-32 with polynomial = 0x04c11db7
+uint32_t lfs_crc32(uint32_t crc, const void *buffer, size_t size);
+
+// Allocate memory, only used if buffers are not provided to littlefs
+static inline void *lfs_malloc(size_t size) {
+#ifndef LFS_NO_MALLOC
+    return malloc(size);
+#else
+    (void)size;
+    return NULL;
+#endif
+}
+
+// Deallocate memory, only used if buffers are not provided to littlefs
+static inline void lfs_free(void *p) {
+#ifndef LFS_NO_MALLOC
+    free(p);
+#else
+    (void)p;
+#endif
+}
 
 
-// Logging functions, these may be replaced by system-specific
-// logging functions
-#define LFS_DEBUG(fmt, ...) printf("lfs debug: " fmt "\n", __VA_ARGS__)
-#define LFS_WARN(fmt, ...)  printf("lfs warn: " fmt "\n", __VA_ARGS__)
-#define LFS_ERROR(fmt, ...) printf("lfs error: " fmt "\n", __VA_ARGS__)
-
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
 
 #endif
+#endif

tests/corrupt.py

@@ -0,0 +1,43 @@
+#!/usr/bin/env python
+
+import struct
+import sys
+import os
+import argparse
+
+def corrupt(block):
+    with open(block, 'r+b') as file:
+        # skip rev
+        file.read(4)
+
+        # go to last commit
+        tag = 0
+        while True:
+            try:
+                ntag, = struct.unpack('<I', file.read(4))
+            except struct.error:
+                break
+
+            tag ^= ntag
+            file.seek(tag & 0xfff, os.SEEK_CUR)
+
+        # lob off last 3 bytes
+        file.seek(-((tag & 0xfff) + 3), os.SEEK_CUR)
+        file.truncate()
+
+def main(args):
+    if args.n or not args.blocks:
+        with open('blocks/.history', 'rb') as file:
+            for i in range(int(args.n or 1)):
+                last, = struct.unpack('<I', file.read(4))
+                args.blocks.append('blocks/%x' % last)
+
+    for block in args.blocks:
+        print 'corrupting %s' % block
+        corrupt(block)
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-n')
+    parser.add_argument('blocks', nargs='*')
+    main(parser.parse_args())

tests/debug.py

@@ -0,0 +1,98 @@
+#!/usr/bin/env python2
+
+import struct
+import binascii
+
+TYPES = {
+    (0x1ff, 0x001): 'reg',
+    (0x1ff, 0x002): 'dir',
+    (0x1ff, 0x011): 'superblock',
+    (0x1ff, 0x012): 'root',
+    (0x1ff, 0x030): 'delete',
+    (0x1f0, 0x080): 'globals',
+    (0x1ff, 0x0c0): 'tail soft',
+    (0x1ff, 0x0c1): 'tail hard',
+    (0x1ff, 0x0f0): 'crc',
+    (0x1ff, 0x040): 'struct dir',
+    (0x1ff, 0x041): 'struct inline',
+    (0x1ff, 0x042): 'struct ctz',
+    (0x100, 0x100): 'attr',
+}
+
+def typeof(type):
+    for prefix in range(9):
+        mask = 0x1ff & ~((1 << prefix)-1)
+        if (mask, type & mask) in TYPES:
+            return TYPES[mask, type & mask] + (
+                ' [%0*x]' % (prefix/4, type & ((1 << prefix)-1))
+                if prefix else '')
+    else:
+        return '[%02x]' % type
+
+def main(*blocks):
+    # find most recent block
+    file = None
+    rev = None
+    crc = None
+    versions = []
+
+    for block in blocks:
+        try:
+            nfile = open(block, 'rb')
+            ndata = nfile.read(4)
+            ncrc = binascii.crc32(ndata)
+            nrev, = struct.unpack('<I', ndata)
+
+            assert rev != nrev
+            if not file or ((rev - nrev) & 0x80000000):
+                file = nfile
+                rev = nrev
+                crc = ncrc
+
+            versions.append((nrev, '%s (rev %d)' % (block, nrev)))
+        except IOError:
+            pass
+
+    print "--- %s ---" % ', '.join(v for _,v in sorted(versions, reverse=True))
+
+    # go through each tag, print useful information
+    print "%-4s  %-8s  %-14s  %3s  %3s  %s" % (
+        'off', 'tag', 'type', 'id', 'len', 'dump')
+
+    tag = 0
+    off = 4
+    while True:
+        try:
+            data = file.read(4)
+            crc = binascii.crc32(data, crc)
+            ntag, = struct.unpack('<I', data)
+        except struct.error:
+            break
+
+        tag ^= ntag
+        off += 4
+
+        type = (tag & 0x7fc00000) >> 22
+        id   = (tag & 0x003ff000) >> 12
+        size = (tag & 0x00000fff) >> 0
+
+        data = file.read(size)
+        if type == 0x0f0:
+            crc = binascii.crc32(data[:4], crc)
+        else:
+            crc = binascii.crc32(data, crc)
+
+        print '%04x: %08x  %-14s  %3s  %3d  %-23s  %-8s' % (
+            off, tag,
+            typeof(type) + (' bad!' if type == 0x0f0 and ~crc else ''),
+            id if id != 0x3ff else '.', size,
+            ' '.join('%02x' % ord(c) for c in data[:8]),
+            ''.join(c if c >= ' ' and c <= '~' else '.' for c in data[:8]))
+
+        off += tag & 0xfff
+        if type == 0x0f0:
+            crc = 0
+
+if __name__ == "__main__":
+    import sys
+    main(*sys.argv[1:])

tests/stats.py

@@ -7,7 +7,7 @@ import os
 import re
 
 def main():
-    with open('blocks/config') as file:
+    with open('blocks/.config') as file:
         s = struct.unpack('<LLLL', file.read())
         print 'read_size: %d' % s[0]
         print 'prog_size: %d' % s[1]
@@ -18,7 +18,7 @@ def main():
         os.path.getsize(os.path.join('blocks', f))
         for f in os.listdir('blocks') if re.match('\d+', f))
 
-    with open('blocks/stats') as file:
+    with open('blocks/.stats') as file:
         s = struct.unpack('<QQQ', file.read())
         print 'read_count: %d' % s[0]
         print 'prog_count: %d' % s[1]

tests/template.fmt

@@ -7,11 +7,11 @@
 
 
 // test stuff
-void test_log(const char *s, uintmax_t v) {{
+static void test_log(const char *s, uintmax_t v) {{
     printf("%s: %jd\n", s, v);
 }}
 
-void test_assert(const char *file, unsigned line,
+static void test_assert(const char *file, unsigned line,
         const char *s, uintmax_t v, uintmax_t e) {{
     static const char *last[6] = {{0, 0}};
     if (v != e || !(last[0] == s || last[1] == s ||
@@ -37,7 +37,8 @@ void test_assert(const char *file, unsigned line,
 
 
 // utility functions for traversals
-int test_count(void *p, lfs_block_t b) {{
+static int __attribute__((used)) test_count(void *p, lfs_block_t b) {{
+    (void)b;
     unsigned *u = (unsigned*)p;
     *u += 1;
     return 0;
@@ -58,14 +59,14 @@ lfs_size_t size;
 lfs_size_t wsize;
 lfs_size_t rsize;
 
-uintmax_t res;
+uintmax_t test;
 
 #ifndef LFS_READ_SIZE
 #define LFS_READ_SIZE 16
 #endif
 
 #ifndef LFS_PROG_SIZE
-#define LFS_PROG_SIZE 16
+#define LFS_PROG_SIZE LFS_READ_SIZE
 #endif
 
 #ifndef LFS_BLOCK_SIZE
@@ -76,6 +77,14 @@ uintmax_t res;
 #define LFS_BLOCK_COUNT 1024
 #endif
 
+#ifndef LFS_BLOCK_CYCLES
+#define LFS_BLOCK_CYCLES 1024
+#endif
+
+#ifndef LFS_CACHE_SIZE
+#define LFS_CACHE_SIZE 64
+#endif
+
 #ifndef LFS_LOOKAHEAD
 #define LFS_LOOKAHEAD 128
 #endif
@@ -87,16 +96,18 @@ const struct lfs_config cfg = {{
     .erase = &lfs_emubd_erase,
     .sync  = &lfs_emubd_sync,
 
-    .read_size   = LFS_READ_SIZE,
-    .prog_size   = LFS_PROG_SIZE,
-    .block_size  = LFS_BLOCK_SIZE,
-    .block_count = LFS_BLOCK_COUNT,
-    .lookahead   = LFS_LOOKAHEAD,
+    .read_size    = LFS_READ_SIZE,
+    .prog_size    = LFS_PROG_SIZE,
+    .block_size   = LFS_BLOCK_SIZE,
+    .block_count  = LFS_BLOCK_COUNT,
+    .block_cycles = LFS_BLOCK_CYCLES,
+    .cache_size   = LFS_CACHE_SIZE,
+    .lookahead    = LFS_LOOKAHEAD,
 }};
 
 
 // Entry point
-int main() {{
+int main(void) {{
     lfs_emubd_create(&cfg, "blocks");
 
 {tests}

tests/test.py

@@ -10,26 +10,38 @@ def generate(test):
         template = file.read()
 
     lines = []
-    for line in re.split('(?<=[;{}])\n', test.read()):
+    for line in re.split('(?<=(?:.;| [{}]))\n', test.read()):
         match = re.match('(?: *\n)*( *)(.*)=>(.*);', line, re.DOTALL | re.MULTILINE)
         if match:
             tab, test, expect = match.groups()
-            lines.append(tab+'res = {test};'.format(test=test.strip()))
-            lines.append(tab+'test_assert("{name}", res, {expect});'.format(
+            lines.append(tab+'test = {test};'.format(test=test.strip()))
+            lines.append(tab+'test_assert("{name}", test, {expect});'.format(
                     name = re.match('\w*', test.strip()).group(),
                     expect = expect.strip()))
         else:
             lines.append(line)
 
+    # Create test file
     with open('test.c', 'w') as file:
         file.write(template.format(tests='\n'.join(lines)))
 
+    # Remove build artifacts to force rebuild
+    try:
+        os.remove('test.o')
+        os.remove('lfs')
+    except OSError:
+        pass
+
 def compile():
-    os.environ['CFLAGS'] = os.environ.get('CFLAGS', '') + ' -Werror'
-    subprocess.check_call(['make', '--no-print-directory', '-s'], env=os.environ)
+    subprocess.check_call([
+            os.environ.get('MAKE', 'make'),
+            '--no-print-directory', '-s'])
 
 def execute():
-    subprocess.check_call(["./lfs"])
+    if 'EXEC' in os.environ:
+        subprocess.check_call([os.environ['EXEC'], "./lfs"])
+    else:
+        subprocess.check_call(["./lfs"])
 
 def main(test=None):
     if test and not test.startswith('-'):

tests/test_alloc.sh

@@ -121,6 +121,7 @@ tests/test.py << TEST
     size = strlen("exhaustion");
     memcpy(buffer, "exhaustion", size);
     lfs_file_write(&lfs, &file[0], buffer, size) => size;
+    lfs_file_sync(&lfs, &file[0]) => 0;
 
     size = strlen("blahblahblahblah");
     memcpy(buffer, "blahblahblahblah", size);
@@ -142,6 +143,7 @@ tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
     lfs_file_open(&lfs, &file[0], "exhaustion", LFS_O_RDONLY);
     size = strlen("exhaustion");
+    lfs_file_size(&lfs, &file[0]) => size;
     lfs_file_read(&lfs, &file[0], buffer, size) => size;
     memcmp(buffer, "exhaustion", size) => 0;
     lfs_file_close(&lfs, &file[0]) => 0;
@@ -166,6 +168,7 @@ tests/test.py << TEST
     size = strlen("exhaustion");
     memcpy(buffer, "exhaustion", size);
     lfs_file_write(&lfs, &file[0], buffer, size) => size;
+    lfs_file_sync(&lfs, &file[0]) => 0;
 
     size = strlen("blahblahblahblah");
     memcpy(buffer, "blahblahblahblah", size);
@@ -187,54 +190,102 @@ tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
     lfs_file_open(&lfs, &file[0], "exhaustion", LFS_O_RDONLY);
     size = strlen("exhaustion");
+    lfs_file_size(&lfs, &file[0]) => size;
     lfs_file_read(&lfs, &file[0], buffer, size) => size;
     memcmp(buffer, "exhaustion", size) => 0;
     lfs_file_close(&lfs, &file[0]) => 0;
+    lfs_remove(&lfs, "exhaustion") => 0;
     lfs_unmount(&lfs) => 0;
 TEST
 
 echo "--- Dir exhaustion test ---"
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
-    lfs_stat(&lfs, "exhaustion", &info) => 0;
-    lfs_size_t fullsize = info.size;
-    lfs_remove(&lfs, "exhaustion") => 0;
 
-    lfs_file_open(&lfs, &file[0], "exhaustion", LFS_O_WRONLY | LFS_O_CREAT);
+    // find out max file size
+    lfs_mkdir(&lfs, "exhaustiondir") => 0;
     size = strlen("blahblahblahblah");
     memcpy(buffer, "blahblahblahblah", size);
-    for (lfs_size_t i = 0; i < fullsize - 2*512; i += size) {
+    lfs_file_open(&lfs, &file[0], "exhaustion", LFS_O_WRONLY | LFS_O_CREAT);
+    int count = 0;
+    int err;
+    while (true) {
+        err = lfs_file_write(&lfs, &file[0], buffer, size);
+        if (err < 0) {
+            break;
+        }
+
+        count += 1;
+    }
+    err => LFS_ERR_NOSPC;
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    lfs_remove(&lfs, "exhaustion") => 0;
+    lfs_remove(&lfs, "exhaustiondir") => 0;
+
+    // see if dir fits with max file size
+    lfs_file_open(&lfs, &file[0], "exhaustion", LFS_O_WRONLY | LFS_O_CREAT);
+    for (int i = 0; i < count; i++) {
         lfs_file_write(&lfs, &file[0], buffer, size) => size;
     }
     lfs_file_close(&lfs, &file[0]) => 0;
 
     lfs_mkdir(&lfs, "exhaustiondir") => 0;
     lfs_remove(&lfs, "exhaustiondir") => 0;
+    lfs_remove(&lfs, "exhaustion") => 0;
 
-    lfs_file_open(&lfs, &file[0], "exhaustion", LFS_O_WRONLY | LFS_O_APPEND);
-    size = strlen("blahblahblahblah");
-    memcpy(buffer, "blahblahblahblah", size);
-    lfs_file_write(&lfs, &file[0], buffer, size) => size;
+    // see if dir fits with > max file size
+    lfs_file_open(&lfs, &file[0], "exhaustion", LFS_O_WRONLY | LFS_O_CREAT);
+    for (int i = 0; i < count+1; i++) {
+        lfs_file_write(&lfs, &file[0], buffer, size) => size;
+    }
     lfs_file_close(&lfs, &file[0]) => 0;
 
     lfs_mkdir(&lfs, "exhaustiondir") => LFS_ERR_NOSPC;
+
+    lfs_remove(&lfs, "exhaustion") => 0;
     lfs_unmount(&lfs) => 0;
 TEST
 
 echo "--- Chained dir exhaustion test ---"
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
-    lfs_stat(&lfs, "exhaustion", &info) => 0;
-    lfs_size_t fullsize = info.size;
 
-    lfs_remove(&lfs, "exhaustion") => 0;
-    lfs_file_open(&lfs, &file[0], "exhaustion", LFS_O_WRONLY | LFS_O_CREAT);
+    // find out max file size
+    lfs_mkdir(&lfs, "exhaustiondir") => 0;
+    for (int i = 0; i < 9; i++) {
+        sprintf((char*)buffer, "dirwithanexhaustivelylongnameforpadding%d", i);
+        lfs_mkdir(&lfs, (char*)buffer) => 0;
+    }
     size = strlen("blahblahblahblah");
     memcpy(buffer, "blahblahblahblah", size);
-    for (lfs_size_t i = 0; i < fullsize - 19*512; i += size) {
+    lfs_file_open(&lfs, &file[0], "exhaustion", LFS_O_WRONLY | LFS_O_CREAT);
+    int count = 0;
+    int err;
+    while (true) {
+        err = lfs_file_write(&lfs, &file[0], buffer, size);
+        if (err < 0) {
+            break;
+        }
+
+        count += 1;
+    }
+    err => LFS_ERR_NOSPC;
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    lfs_remove(&lfs, "exhaustion") => 0;
+    lfs_remove(&lfs, "exhaustiondir") => 0;
+    for (int i = 0; i < 9; i++) {
+        sprintf((char*)buffer, "dirwithanexhaustivelylongnameforpadding%d", i);
+        lfs_remove(&lfs, (char*)buffer) => 0;
+    }
+
+    // see that chained dir fails
+    lfs_file_open(&lfs, &file[0], "exhaustion", LFS_O_WRONLY | LFS_O_CREAT);
+    for (int i = 0; i < count+1; i++) {
         lfs_file_write(&lfs, &file[0], buffer, size) => size;
     }
-    lfs_file_close(&lfs, &file[0]) => 0;
+    lfs_file_sync(&lfs, &file[0]) => 0;
 
     for (int i = 0; i < 9; i++) {
         sprintf((char*)buffer, "dirwithanexhaustivelylongnameforpadding%d", i);
@@ -243,19 +294,190 @@ tests/test.py << TEST
 
     lfs_mkdir(&lfs, "exhaustiondir") => LFS_ERR_NOSPC;
 
-    lfs_remove(&lfs, "exhaustion") => 0;
+    // shorten file to try a second chained dir
+    while (true) {
+        err = lfs_mkdir(&lfs, "exhaustiondir");
+        if (err != LFS_ERR_NOSPC) {
+            break;
+        }
+
+        lfs_ssize_t filesize = lfs_file_size(&lfs, &file[0]);
+        filesize > 0 => true;
+
+        lfs_file_truncate(&lfs, &file[0], filesize - size) => 0;
+        lfs_file_sync(&lfs, &file[0]) => 0;
+    }
+    err => 0;
+
+    lfs_mkdir(&lfs, "exhaustiondir2") => LFS_ERR_NOSPC;
+
+    lfs_file_close(&lfs, &file[0]) => 0;
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Split dir test ---"
+rm -rf blocks
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+TEST
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+
+    // create one block hole for half a directory
+    lfs_file_open(&lfs, &file[0], "bump", LFS_O_WRONLY | LFS_O_CREAT) => 0;
+    for (lfs_size_t i = 0; i < cfg.block_size; i += 2) {
+        memcpy(&buffer[i], "hi", 2);
+    }
+    lfs_file_write(&lfs, &file[0], buffer, cfg.block_size) => cfg.block_size;
+    lfs_file_close(&lfs, &file[0]) => 0;
+
     lfs_file_open(&lfs, &file[0], "exhaustion", LFS_O_WRONLY | LFS_O_CREAT);
     size = strlen("blahblahblahblah");
     memcpy(buffer, "blahblahblahblah", size);
-    for (lfs_size_t i = 0; i < fullsize - 20*512; i += size) {
+    for (lfs_size_t i = 0;
+            i < (cfg.block_count-4)*(cfg.block_size-8);
+            i += size) {
         lfs_file_write(&lfs, &file[0], buffer, size) => size;
     }
     lfs_file_close(&lfs, &file[0]) => 0;
 
-    lfs_mkdir(&lfs, "exhaustiondir") => 0;
-    lfs_mkdir(&lfs, "exhaustiondir2") => LFS_ERR_NOSPC;
+    // open hole
+    lfs_remove(&lfs, "bump") => 0;
+
+    lfs_mkdir(&lfs, "splitdir") => 0;
+    lfs_file_open(&lfs, &file[0], "splitdir/bump",
+            LFS_O_WRONLY | LFS_O_CREAT) => 0;
+    for (lfs_size_t i = 0; i < cfg.block_size; i += 2) {
+        memcpy(&buffer[i], "hi", 2);
+    }
+    lfs_file_write(&lfs, &file[0], buffer, cfg.block_size) => LFS_ERR_NOSPC;
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    lfs_unmount(&lfs) => 0;
 TEST
 
+echo "--- Outdated lookahead test ---"
+rm -rf blocks
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+
+    lfs_mount(&lfs, &cfg) => 0;
+
+    // fill completely with two files
+    lfs_file_open(&lfs, &file[0], "exhaustion1",
+            LFS_O_WRONLY | LFS_O_CREAT) => 0;
+    size = strlen("blahblahblahblah");
+    memcpy(buffer, "blahblahblahblah", size);
+    for (lfs_size_t i = 0;
+            i < ((cfg.block_count-2)/2)*(cfg.block_size-8);
+            i += size) {
+        lfs_file_write(&lfs, &file[0], buffer, size) => size;
+    }
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    lfs_file_open(&lfs, &file[0], "exhaustion2",
+            LFS_O_WRONLY | LFS_O_CREAT) => 0;
+    size = strlen("blahblahblahblah");
+    memcpy(buffer, "blahblahblahblah", size);
+    for (lfs_size_t i = 0;
+            i < ((cfg.block_count-2+1)/2)*(cfg.block_size-8);
+            i += size) {
+        lfs_file_write(&lfs, &file[0], buffer, size) => size;
+    }
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    // remount to force reset of lookahead
+    lfs_unmount(&lfs) => 0;
+
+    lfs_mount(&lfs, &cfg) => 0;
+
+    // rewrite one file
+    lfs_file_open(&lfs, &file[0], "exhaustion1",
+            LFS_O_WRONLY | LFS_O_TRUNC) => 0;
+    lfs_file_sync(&lfs, &file[0]) => 0;
+    size = strlen("blahblahblahblah");
+    memcpy(buffer, "blahblahblahblah", size);
+    for (lfs_size_t i = 0;
+            i < ((cfg.block_count-2)/2)*(cfg.block_size-8);
+            i += size) {
+        lfs_file_write(&lfs, &file[0], buffer, size) => size;
+    }
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    // rewrite second file, this requires lookahead does not
+    // use old population
+    lfs_file_open(&lfs, &file[0], "exhaustion2",
+            LFS_O_WRONLY | LFS_O_TRUNC) => 0;
+    lfs_file_sync(&lfs, &file[0]) => 0;
+    size = strlen("blahblahblahblah");
+    memcpy(buffer, "blahblahblahblah", size);
+    for (lfs_size_t i = 0;
+            i < ((cfg.block_count-2+1)/2)*(cfg.block_size-8);
+            i += size) {
+        lfs_file_write(&lfs, &file[0], buffer, size) => size;
+    }
+    lfs_file_close(&lfs, &file[0]) => 0;
+TEST
+
+echo "--- Outdated lookahead and split dir test ---"
+rm -rf blocks
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+
+    lfs_mount(&lfs, &cfg) => 0;
+
+    // fill completely with two files
+    lfs_file_open(&lfs, &file[0], "exhaustion1",
+            LFS_O_WRONLY | LFS_O_CREAT) => 0;
+    size = strlen("blahblahblahblah");
+    memcpy(buffer, "blahblahblahblah", size);
+    for (lfs_size_t i = 0;
+            i < ((cfg.block_count-2)/2)*(cfg.block_size-8);
+            i += size) {
+        lfs_file_write(&lfs, &file[0], buffer, size) => size;
+    }
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    lfs_file_open(&lfs, &file[0], "exhaustion2",
+            LFS_O_WRONLY | LFS_O_CREAT) => 0;
+    size = strlen("blahblahblahblah");
+    memcpy(buffer, "blahblahblahblah", size);
+    for (lfs_size_t i = 0;
+            i < ((cfg.block_count-2+1)/2)*(cfg.block_size-8);
+            i += size) {
+        lfs_file_write(&lfs, &file[0], buffer, size) => size;
+    }
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    // remount to force reset of lookahead
+    lfs_unmount(&lfs) => 0;
+
+    lfs_mount(&lfs, &cfg) => 0;
+
+    // rewrite one file with a hole of one block
+    lfs_file_open(&lfs, &file[0], "exhaustion1",
+            LFS_O_WRONLY | LFS_O_TRUNC) => 0;
+    lfs_file_sync(&lfs, &file[0]) => 0;
+    size = strlen("blahblahblahblah");
+    memcpy(buffer, "blahblahblahblah", size);
+    for (lfs_size_t i = 0;
+            i < ((cfg.block_count-2)/2 - 1)*(cfg.block_size-8);
+            i += size) {
+        lfs_file_write(&lfs, &file[0], buffer, size) => size;
+    }
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    // try to allocate a directory, should fail!
+    lfs_mkdir(&lfs, "split") => LFS_ERR_NOSPC;
+
+    // file should not fail
+    lfs_file_open(&lfs, &file[0], "notasplit",
+            LFS_O_WRONLY | LFS_O_CREAT) => 0;
+    lfs_file_write(&lfs, &file[0], "hi", 2) => 2;
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    lfs_unmount(&lfs) => 0;
+TEST
 
 echo "--- Results ---"
 tests/stats.py

tests/test_attrs.sh

@@ -0,0 +1,262 @@
+#!/bin/bash
+set -eu
+
+echo "=== Attr tests ==="
+rm -rf blocks
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_mkdir(&lfs, "hello") => 0;
+    lfs_file_open(&lfs, &file[0], "hello/hello",
+            LFS_O_WRONLY | LFS_O_CREAT) => 0;
+    lfs_file_write(&lfs, &file[0], "hello", strlen("hello"))
+            => strlen("hello");
+    lfs_file_close(&lfs, &file[0]);
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Set/get attribute ---"
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_setattr(&lfs, "hello", 'A', "aaaa",   4) => 0;
+    lfs_setattr(&lfs, "hello", 'B', "bbbbbb", 6) => 0;
+    lfs_setattr(&lfs, "hello", 'C', "ccccc",  5) => 0;
+    lfs_getattr(&lfs, "hello", 'A', buffer,    4) => 4;
+    lfs_getattr(&lfs, "hello", 'B', buffer+4,  6) => 6;
+    lfs_getattr(&lfs, "hello", 'C', buffer+10, 5) => 5;
+    memcmp(buffer,    "aaaa",   4) => 0;
+    memcmp(buffer+4,  "bbbbbb", 6) => 0;
+    memcmp(buffer+10, "ccccc",  5) => 0;
+
+    lfs_setattr(&lfs, "hello", 'B', "", 0) => 0;
+    lfs_getattr(&lfs, "hello", 'A', buffer,    4) => 4;
+    lfs_getattr(&lfs, "hello", 'B', buffer+4,  6) => 0;
+    lfs_getattr(&lfs, "hello", 'C', buffer+10, 5) => 5;
+    memcmp(buffer,    "aaaa",         4) => 0;
+    memcmp(buffer+4,  "\0\0\0\0\0\0", 6) => 0;
+    memcmp(buffer+10, "ccccc",        5) => 0;
+
+    lfs_setattr(&lfs, "hello", 'B', "dddddd", 6) => 0;
+    lfs_getattr(&lfs, "hello", 'A', buffer,    4) => 4;
+    lfs_getattr(&lfs, "hello", 'B', buffer+4,  6) => 6;
+    lfs_getattr(&lfs, "hello", 'C', buffer+10, 5) => 5;
+    memcmp(buffer,    "aaaa",   4) => 0;
+    memcmp(buffer+4,  "dddddd", 6) => 0;
+    memcmp(buffer+10, "ccccc",  5) => 0;
+
+    lfs_setattr(&lfs, "hello", 'B', "eee", 3) => 0;
+    lfs_getattr(&lfs, "hello", 'A', buffer,    4) => 4;
+    lfs_getattr(&lfs, "hello", 'B', buffer+4,  6) => 3;
+    lfs_getattr(&lfs, "hello", 'C', buffer+10, 5) => 5;
+    memcmp(buffer,    "aaaa",      4) => 0;
+    memcmp(buffer+4,  "eee\0\0\0", 6) => 0;
+    memcmp(buffer+10, "ccccc",     5) => 0;
+
+    lfs_setattr(&lfs, "hello", 'A', buffer, LFS_ATTR_MAX+1) => LFS_ERR_NOSPC;
+    lfs_setattr(&lfs, "hello", 'B', "fffffffff", 9) => 0;
+    lfs_getattr(&lfs, "hello", 'A', buffer,    4) => 4;
+    lfs_getattr(&lfs, "hello", 'B', buffer+4,  6) => 9;
+    lfs_getattr(&lfs, "hello", 'C', buffer+10, 5) => 5;
+
+    lfs_unmount(&lfs) => 0;
+TEST
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_getattr(&lfs, "hello", 'A', buffer,    4) => 4;
+    lfs_getattr(&lfs, "hello", 'B', buffer+4,  9) => 9;
+    lfs_getattr(&lfs, "hello", 'C', buffer+13, 5) => 5;
+    memcmp(buffer,    "aaaa",      4) => 0;
+    memcmp(buffer+4,  "fffffffff", 9) => 0;
+    memcmp(buffer+13, "ccccc",     5) => 0;
+
+    lfs_file_open(&lfs, &file[0], "hello/hello", LFS_O_RDONLY) => 0;
+    lfs_file_read(&lfs, &file[0], buffer, sizeof(buffer)) => strlen("hello");
+    memcmp(buffer, "hello", strlen("hello")) => 0;
+    lfs_file_close(&lfs, &file[0]);
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Set/get fs attribute ---"
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_fs_setattr(&lfs, 'A', "aaaa",   4) => 0;
+    lfs_fs_setattr(&lfs, 'B', "bbbbbb", 6) => 0;
+    lfs_fs_setattr(&lfs, 'C', "ccccc",  5) => 0;
+    lfs_fs_getattr(&lfs, 'A', buffer,    4) => 4;
+    lfs_fs_getattr(&lfs, 'B', buffer+4,  6) => 6;
+    lfs_fs_getattr(&lfs, 'C', buffer+10, 5) => 5;
+    memcmp(buffer,    "aaaa",   4) => 0;
+    memcmp(buffer+4,  "bbbbbb", 6) => 0;
+    memcmp(buffer+10, "ccccc",  5) => 0;
+
+    lfs_fs_setattr(&lfs, 'B', "", 0) => 0;
+    lfs_fs_getattr(&lfs, 'A', buffer,    4) => 4;
+    lfs_fs_getattr(&lfs, 'B', buffer+4,  6) => 0;
+    lfs_fs_getattr(&lfs, 'C', buffer+10, 5) => 5;
+    memcmp(buffer,    "aaaa",         4) => 0;
+    memcmp(buffer+4,  "\0\0\0\0\0\0", 6) => 0;
+    memcmp(buffer+10, "ccccc",        5) => 0;
+
+    lfs_fs_setattr(&lfs, 'B', "dddddd", 6) => 0;
+    lfs_fs_getattr(&lfs, 'A', buffer,    4) => 4;
+    lfs_fs_getattr(&lfs, 'B', buffer+4,  6) => 6;
+    lfs_fs_getattr(&lfs, 'C', buffer+10, 5) => 5;
+    memcmp(buffer,    "aaaa",   4) => 0;
+    memcmp(buffer+4,  "dddddd", 6) => 0;
+    memcmp(buffer+10, "ccccc",  5) => 0;
+
+    lfs_fs_setattr(&lfs, 'B', "eee", 3) => 0;
+    lfs_fs_getattr(&lfs, 'A', buffer,    4) => 4;
+    lfs_fs_getattr(&lfs, 'B', buffer+4,  6) => 3;
+    lfs_fs_getattr(&lfs, 'C', buffer+10, 5) => 5;
+    memcmp(buffer,    "aaaa",      4) => 0;
+    memcmp(buffer+4,  "eee\0\0\0", 6) => 0;
+    memcmp(buffer+10, "ccccc",     5) => 0;
+
+    lfs_fs_setattr(&lfs, 'A', buffer, LFS_ATTR_MAX+1) => LFS_ERR_NOSPC;
+    lfs_fs_setattr(&lfs, 'B', "fffffffff", 9) => 0;
+    lfs_fs_getattr(&lfs, 'A', buffer,    4) => 4;
+    lfs_fs_getattr(&lfs, 'B', buffer+4,  6) => 9;
+    lfs_fs_getattr(&lfs, 'C', buffer+10, 5) => 5;
+    lfs_unmount(&lfs) => 0;
+TEST
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_fs_getattr(&lfs, 'A', buffer,    4) => 4;
+    lfs_fs_getattr(&lfs, 'B', buffer+4,  9) => 9;
+    lfs_fs_getattr(&lfs, 'C', buffer+13, 5) => 5;
+    memcmp(buffer,    "aaaa",      4) => 0;
+    memcmp(buffer+4,  "fffffffff", 9) => 0;
+    memcmp(buffer+13, "ccccc",     5) => 0;
+
+    lfs_file_open(&lfs, &file[0], "hello/hello", LFS_O_RDONLY) => 0;
+    lfs_file_read(&lfs, &file[0], buffer, sizeof(buffer)) => strlen("hello");
+    memcmp(buffer, "hello", strlen("hello")) => 0;
+    lfs_file_close(&lfs, &file[0]);
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Set/get file attribute ---"
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    struct lfs_attr a1 = {'A', buffer,    4};
+    struct lfs_attr b1 = {'B', buffer+4,  6, &a1};
+    struct lfs_attr c1 = {'C', buffer+10, 5, &b1};
+    struct lfs_file_config cfg1 = {.attrs = &c1};
+
+    lfs_file_opencfg(&lfs, &file[0], "hello/hello", LFS_O_WRONLY, &cfg1) => 0;
+    memcpy(buffer,    "aaaa",   4);
+    memcpy(buffer+4,  "bbbbbb", 6);
+    memcpy(buffer+10, "ccccc",  5);
+    lfs_file_close(&lfs, &file[0]) => 0;
+    memset(buffer, 0, 15);
+    lfs_file_opencfg(&lfs, &file[0], "hello/hello", LFS_O_RDONLY, &cfg1) => 0;
+    lfs_file_close(&lfs, &file[0]) => 0;
+    memcmp(buffer,    "aaaa",   4) => 0;
+    memcmp(buffer+4,  "bbbbbb", 6) => 0;
+    memcmp(buffer+10, "ccccc",  5) => 0;
+
+    b1.size = 0;
+    lfs_file_opencfg(&lfs, &file[0], "hello/hello", LFS_O_WRONLY, &cfg1) => 0;
+    lfs_file_close(&lfs, &file[0]) => 0;
+    memset(buffer, 0, 15);
+    b1.size = 6;
+    lfs_file_opencfg(&lfs, &file[0], "hello/hello", LFS_O_RDONLY, &cfg1) => 0;
+    lfs_file_close(&lfs, &file[0]) => 0;
+    memcmp(buffer,    "aaaa",         4) => 0;
+    memcmp(buffer+4,  "\0\0\0\0\0\0", 6) => 0;
+    memcmp(buffer+10, "ccccc",        5) => 0;
+
+    b1.size = 6;
+    lfs_file_opencfg(&lfs, &file[0], "hello/hello", LFS_O_WRONLY, &cfg1) => 0;
+    memcpy(buffer+4,  "dddddd", 6);
+    lfs_file_close(&lfs, &file[0]) => 0;
+    memset(buffer, 0, 15);
+    b1.size = 6;
+    lfs_file_opencfg(&lfs, &file[0], "hello/hello", LFS_O_RDONLY, &cfg1) => 0;
+    lfs_file_close(&lfs, &file[0]) => 0;
+    memcmp(buffer,    "aaaa",   4) => 0;
+    memcmp(buffer+4,  "dddddd", 6) => 0;
+    memcmp(buffer+10, "ccccc",  5) => 0;
+
+    b1.size = 3;
+    lfs_file_opencfg(&lfs, &file[0], "hello/hello", LFS_O_WRONLY, &cfg1) => 0;
+    memcpy(buffer+4,  "eee", 3);
+    lfs_file_close(&lfs, &file[0]) => 0;
+    memset(buffer, 0, 15);
+    b1.size = 6;
+    lfs_file_opencfg(&lfs, &file[0], "hello/hello", LFS_O_RDONLY, &cfg1) => 0;
+    lfs_file_close(&lfs, &file[0]) => 0;
+    memcmp(buffer,    "aaaa",      4) => 0;
+    memcmp(buffer+4,  "eee\0\0\0", 6) => 0;
+    memcmp(buffer+10, "ccccc",     5) => 0;
+
+    a1.size = LFS_ATTR_MAX+1;
+    lfs_file_opencfg(&lfs, &file[0], "hello/hello", LFS_O_WRONLY, &cfg1)
+        => LFS_ERR_NOSPC;
+
+    struct lfs_attr a2 = {'A', buffer,    4};
+    struct lfs_attr b2 = {'B', buffer+4,  9, &a2};
+    struct lfs_attr c2 = {'C', buffer+13, 5, &b2};
+    struct lfs_file_config cfg2 = {.attrs = &c2};
+    lfs_file_opencfg(&lfs, &file[0], "hello/hello", LFS_O_RDWR, &cfg2) => 0;
+    memcpy(buffer+4,  "fffffffff", 9);
+    lfs_file_close(&lfs, &file[0]) => 0;
+    a1.size = 4;
+    lfs_file_opencfg(&lfs, &file[0], "hello/hello", LFS_O_RDONLY, &cfg1) => 0;
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    lfs_unmount(&lfs) => 0;
+TEST
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    struct lfs_attr a2 = {'A', buffer,    4};
+    struct lfs_attr b2 = {'B', buffer+4,  9, &a2};
+    struct lfs_attr c2 = {'C', buffer+13, 5, &b2};
+    struct lfs_file_config cfg2 = {.attrs = &c2};
+
+    lfs_file_opencfg(&lfs, &file[0], "hello/hello", LFS_O_RDONLY, &cfg2) => 0;
+    lfs_file_close(&lfs, &file[0]) => 0;
+    memcmp(buffer,    "aaaa",      4) => 0;
+    memcmp(buffer+4,  "fffffffff", 9) => 0;
+    memcmp(buffer+13, "ccccc",     5) => 0;
+
+    lfs_file_open(&lfs, &file[0], "hello/hello", LFS_O_RDONLY) => 0;
+    lfs_file_read(&lfs, &file[0], buffer, sizeof(buffer)) => strlen("hello");
+    memcmp(buffer, "hello", strlen("hello")) => 0;
+    lfs_file_close(&lfs, &file[0]);
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Deferred file attributes ---"
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    struct lfs_attr a1 = {'B', "gggg", 4};
+    struct lfs_attr b1 = {'C', "",     0, &a1};
+    struct lfs_attr c1 = {'D', "hhhh", 4, &b1};
+    struct lfs_file_config cfg1 = {.attrs = &c1};
+
+    lfs_file_opencfg(&lfs, &file[0], "hello/hello", LFS_O_WRONLY, &cfg1) => 0;
+
+    lfs_getattr(&lfs, "hello/hello", 'B', buffer,    9) => 9;
+    lfs_getattr(&lfs, "hello/hello", 'C', buffer+9,  9) => 5;
+    lfs_getattr(&lfs, "hello/hello", 'D', buffer+18, 9) => 0;
+    memcmp(buffer,    "fffffffff",          9) => 0;
+    memcmp(buffer+9,  "ccccc\0\0\0\0",      9) => 0;
+    memcmp(buffer+18, "\0\0\0\0\0\0\0\0\0", 9) => 0;
+
+    lfs_file_sync(&lfs, &file[0]) => 0;
+    lfs_getattr(&lfs, "hello/hello", 'B', buffer,    9) => 4;
+    lfs_getattr(&lfs, "hello/hello", 'C', buffer+9,  9) => 0;
+    lfs_getattr(&lfs, "hello/hello", 'D', buffer+18, 9) => 4;
+    memcmp(buffer,    "gggg\0\0\0\0\0",     9) => 0;
+    memcmp(buffer+9,  "\0\0\0\0\0\0\0\0\0", 9) => 0;
+    memcmp(buffer+18, "hhhh\0\0\0\0\0",     9) => 0;
+
+    lfs_file_close(&lfs, &file[0]) => 0;
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Results ---"
+tests/stats.py

tests/test_corrupt.sh

@@ -71,13 +71,25 @@ echo "--- Sanity check ---"
 rm -rf blocks
 lfs_mktree
 lfs_chktree
+BLOCKS="$(ls blocks | grep -vw '[01]')"
 
 echo "--- Block corruption ---"
-for i in {0..33}
+for b in $BLOCKS
 do 
     rm -rf blocks
     mkdir blocks
-    ln -s /dev/zero blocks/$(printf '%x' $i)
+    ln -s /dev/zero blocks/$b
+    lfs_mktree
+    lfs_chktree
+done
+
+echo "--- Block persistance ---"
+for b in $BLOCKS
+do 
+    rm -rf blocks
+    mkdir blocks
+    lfs_mktree
+    chmod a-w blocks/$b
     lfs_mktree
     lfs_chktree
 done
@@ -85,7 +97,7 @@ done
 echo "--- Big region corruption ---"
 rm -rf blocks
 mkdir blocks
-for i in {2..255}
+for i in {2..512}
 do
     ln -s /dev/zero blocks/$(printf '%x' $i)
 done
@@ -95,7 +107,7 @@ lfs_chktree
 echo "--- Alternating corruption ---"
 rm -rf blocks
 mkdir blocks
-for i in {2..511..2}
+for i in {2..1024..2}
 do
     ln -s /dev/zero blocks/$(printf '%x' $i)
 done

tests/test_dirs.sh

@@ -56,7 +56,7 @@ TEST
 echo "--- Directory failures ---"
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
-    lfs_mkdir(&lfs, "potato") => LFS_ERR_EXISTS;
+    lfs_mkdir(&lfs, "potato") => LFS_ERR_EXIST;
     lfs_dir_open(&lfs, &dir[0], "tomato") => LFS_ERR_NOENT;
     lfs_dir_open(&lfs, &dir[0], "burito") => LFS_ERR_NOTDIR;
     lfs_file_open(&lfs, &file[0], "tomato", LFS_O_RDONLY) => LFS_ERR_NOENT;
@@ -118,6 +118,7 @@ tests/test.py << TEST
         sprintf((char*)buffer, "test%d", i);
         lfs_dir_read(&lfs, &dir[0], &info) => 1;
         strcmp(info.name, (char*)buffer) => 0;
+        info.type => LFS_TYPE_DIR;
     }
     lfs_dir_read(&lfs, &dir[0], &info) => 0;
     lfs_unmount(&lfs) => 0;
@@ -126,7 +127,7 @@ TEST
 echo "--- Directory remove ---"
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
-    lfs_remove(&lfs, "potato") => LFS_ERR_INVAL;
+    lfs_remove(&lfs, "potato") => LFS_ERR_NOTEMPTY;
     lfs_remove(&lfs, "potato/sweet") => 0;
     lfs_remove(&lfs, "potato/baked") => 0;
     lfs_remove(&lfs, "potato/fried") => 0;
@@ -220,7 +221,7 @@ tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
     lfs_mkdir(&lfs, "warmpotato") => 0;
     lfs_mkdir(&lfs, "warmpotato/mushy") => 0;
-    lfs_rename(&lfs, "hotpotato", "warmpotato") => LFS_ERR_INVAL;
+    lfs_rename(&lfs, "hotpotato", "warmpotato") => LFS_ERR_NOTEMPTY;
 
     lfs_remove(&lfs, "warmpotato/mushy") => 0;
     lfs_rename(&lfs, "hotpotato", "warmpotato") => 0;
@@ -255,7 +256,7 @@ tests/test.py << TEST
     lfs_rename(&lfs, "warmpotato/baked", "coldpotato/baked") => 0;
     lfs_rename(&lfs, "warmpotato/sweet", "coldpotato/sweet") => 0;
     lfs_rename(&lfs, "warmpotato/fried", "coldpotato/fried") => 0;
-    lfs_remove(&lfs, "coldpotato") => LFS_ERR_INVAL;
+    lfs_remove(&lfs, "coldpotato") => LFS_ERR_NOTEMPTY;
     lfs_remove(&lfs, "warmpotato") => 0;
     lfs_unmount(&lfs) => 0;
 TEST
@@ -282,10 +283,53 @@ tests/test.py << TEST
     lfs_unmount(&lfs) => 0;
 TEST
 
+echo "--- Recursive remove ---"
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_remove(&lfs, "coldpotato") => LFS_ERR_NOTEMPTY;
+
+    lfs_dir_open(&lfs, &dir[0], "coldpotato") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+
+    while (true) {
+        int err = lfs_dir_read(&lfs, &dir[0], &info);
+        err >= 0 => 1;
+        if (err == 0) {
+            break;
+        }
+
+        strcpy((char*)buffer, "coldpotato/");
+        strcat((char*)buffer, info.name);
+        lfs_remove(&lfs, (char*)buffer) => 0;
+    }
+
+    lfs_remove(&lfs, "coldpotato") => 0;
+TEST
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_dir_open(&lfs, &dir[0], "/") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, ".") => 0;
+    info.type => LFS_TYPE_DIR;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "..") => 0;
+    info.type => LFS_TYPE_DIR;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "burito") => 0;
+    info.type => LFS_TYPE_REG;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "cactus") => 0;
+    info.type => LFS_TYPE_DIR;
+    lfs_dir_read(&lfs, &dir[0], &info) => 0;
+    lfs_dir_close(&lfs, &dir[0]) => 0;
+    lfs_unmount(&lfs) => 0;
+TEST
+
 echo "--- Multi-block remove ---"
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
-    lfs_remove(&lfs, "cactus") => LFS_ERR_INVAL;
+    lfs_remove(&lfs, "cactus") => LFS_ERR_NOTEMPTY;
 
     for (int i = 0; i < $LARGESIZE; i++) {
         sprintf((char*)buffer, "cactus/test%d", i);
@@ -307,9 +351,71 @@ tests/test.py << TEST
     lfs_dir_read(&lfs, &dir[0], &info) => 1;
     strcmp(info.name, "burito") => 0;
     info.type => LFS_TYPE_REG;
+    lfs_dir_read(&lfs, &dir[0], &info) => 0;
+    lfs_dir_close(&lfs, &dir[0]) => 0;
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Multi-block directory with files ---"
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_mkdir(&lfs, "prickly-pear") => 0;
+    for (int i = 0; i < $LARGESIZE; i++) {
+        sprintf((char*)buffer, "prickly-pear/test%d", i);
+        lfs_file_open(&lfs, &file[0], (char*)buffer,
+                LFS_O_WRONLY | LFS_O_CREAT) => 0;
+        size = 6;
+        memcpy(wbuffer, "Hello", size);
+        lfs_file_write(&lfs, &file[0], wbuffer, size) => size;
+        lfs_file_close(&lfs, &file[0]) => 0;
+    }
+    lfs_unmount(&lfs) => 0;
+TEST
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_dir_open(&lfs, &dir[0], "prickly-pear") => 0;
     lfs_dir_read(&lfs, &dir[0], &info) => 1;
-    strcmp(info.name, "coldpotato") => 0;
+    strcmp(info.name, ".") => 0;
     info.type => LFS_TYPE_DIR;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "..") => 0;
+    info.type => LFS_TYPE_DIR;
+    for (int i = 0; i < $LARGESIZE; i++) {
+        sprintf((char*)buffer, "test%d", i);
+        lfs_dir_read(&lfs, &dir[0], &info) => 1;
+        strcmp(info.name, (char*)buffer) => 0;
+        info.type => LFS_TYPE_REG;
+        info.size => 6;
+    }
+    lfs_dir_read(&lfs, &dir[0], &info) => 0;
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Multi-block remove with files ---"
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_remove(&lfs, "prickly-pear") => LFS_ERR_NOTEMPTY;
+
+    for (int i = 0; i < $LARGESIZE; i++) {
+        sprintf((char*)buffer, "prickly-pear/test%d", i);
+        lfs_remove(&lfs, (char*)buffer) => 0;
+    }
+
+    lfs_remove(&lfs, "prickly-pear") => 0;
+    lfs_unmount(&lfs) => 0;
+TEST
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_dir_open(&lfs, &dir[0], "/") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, ".") => 0;
+    info.type => LFS_TYPE_DIR;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "..") => 0;
+    info.type => LFS_TYPE_DIR;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "burito") => 0;
+    info.type => LFS_TYPE_REG;
     lfs_dir_read(&lfs, &dir[0], &info) => 0;
     lfs_dir_close(&lfs, &dir[0]) => 0;
     lfs_unmount(&lfs) => 0;

tests/test_entries.sh

@@ -0,0 +1,221 @@
+#!/bin/bash
+set -eu
+
+# Note: These tests are intended for 512 byte inline size at different
+# inline sizes they should still pass, but won't be testing anything
+
+echo "=== Entry tests ==="
+rm -rf blocks
+function read_file {
+cat << TEST
+
+    size = $2;
+    lfs_file_open(&lfs, &file[0], "$1", LFS_O_RDONLY) => 0;
+    lfs_file_read(&lfs, &file[0], rbuffer, size) => size;
+    memcmp(rbuffer, wbuffer, size) => 0;
+    lfs_file_close(&lfs, &file[0]) => 0;
+TEST
+}
+
+function write_file {
+cat << TEST
+
+    size = $2;
+    lfs_file_open(&lfs, &file[0], "$1",
+            LFS_O_WRONLY | LFS_O_CREAT | LFS_O_TRUNC) => 0;
+    memset(wbuffer, 'c', size);
+    lfs_file_write(&lfs, &file[0], wbuffer, size) => size;
+    lfs_file_close(&lfs, &file[0]) => 0;
+TEST
+}
+
+echo "--- Entry grow test ---"
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+
+    lfs_mount(&lfs, &cfg) => 0;
+    $(write_file "hi0" 20)
+    $(write_file "hi1" 20)
+    $(write_file "hi2" 20)
+    $(write_file "hi3" 20)
+
+    $(read_file "hi1" 20)
+    $(write_file "hi1" 200)
+
+    $(read_file "hi0" 20)
+    $(read_file "hi1" 200)
+    $(read_file "hi2" 20)
+    $(read_file "hi3" 20)
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Entry shrink test ---"
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+
+    lfs_mount(&lfs, &cfg) => 0;
+    $(write_file "hi0" 20)
+    $(write_file "hi1" 200)
+    $(write_file "hi2" 20)
+    $(write_file "hi3" 20)
+
+    $(read_file "hi1" 200)
+    $(write_file "hi1" 20)
+
+    $(read_file "hi0" 20)
+    $(read_file "hi1" 20)
+    $(read_file "hi2" 20)
+    $(read_file "hi3" 20)
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Entry spill test ---"
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+
+    lfs_mount(&lfs, &cfg) => 0;
+    $(write_file "hi0" 200)
+    $(write_file "hi1" 200)
+    $(write_file "hi2" 200)
+    $(write_file "hi3" 200)
+
+    $(read_file "hi0" 200)
+    $(read_file "hi1" 200)
+    $(read_file "hi2" 200)
+    $(read_file "hi3" 200)
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Entry push spill test ---"
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+
+    lfs_mount(&lfs, &cfg) => 0;
+    $(write_file "hi0" 200)
+    $(write_file "hi1" 20)
+    $(write_file "hi2" 200)
+    $(write_file "hi3" 200)
+
+    $(read_file "hi1" 20)
+    $(write_file "hi1" 200)
+
+    $(read_file "hi0" 200)
+    $(read_file "hi1" 200)
+    $(read_file "hi2" 200)
+    $(read_file "hi3" 200)
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Entry push spill two test ---"
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+
+    lfs_mount(&lfs, &cfg) => 0;
+    $(write_file "hi0" 200)
+    $(write_file "hi1" 20)
+    $(write_file "hi2" 200)
+    $(write_file "hi3" 200)
+    $(write_file "hi4" 200)
+
+    $(read_file "hi1" 20)
+    $(write_file "hi1" 200)
+
+    $(read_file "hi0" 200)
+    $(read_file "hi1" 200)
+    $(read_file "hi2" 200)
+    $(read_file "hi3" 200)
+    $(read_file "hi4" 200)
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Entry drop test ---"
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+
+    lfs_mount(&lfs, &cfg) => 0;
+    $(write_file "hi0" 200)
+    $(write_file "hi1" 200)
+    $(write_file "hi2" 200)
+    $(write_file "hi3" 200)
+
+    lfs_remove(&lfs, "hi1") => 0;
+    lfs_stat(&lfs, "hi1", &info) => LFS_ERR_NOENT;
+    $(read_file "hi0" 200)
+    $(read_file "hi2" 200)
+    $(read_file "hi3" 200)
+
+    lfs_remove(&lfs, "hi2") => 0;
+    lfs_stat(&lfs, "hi2", &info) => LFS_ERR_NOENT;
+    $(read_file "hi0" 200)
+    $(read_file "hi3" 200)
+
+    lfs_remove(&lfs, "hi3") => 0;
+    lfs_stat(&lfs, "hi3", &info) => LFS_ERR_NOENT;
+    $(read_file "hi0" 200)
+
+    lfs_remove(&lfs, "hi0") => 0;
+    lfs_stat(&lfs, "hi0", &info) => LFS_ERR_NOENT;
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Create too big ---"
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+
+    lfs_mount(&lfs, &cfg) => 0;
+    memset(buffer, 'm', 200);
+    buffer[200] = '\0';
+
+    size = 400;
+    lfs_file_open(&lfs, &file[0], (char*)buffer,
+            LFS_O_WRONLY | LFS_O_CREAT | LFS_O_TRUNC) => 0;
+    memset(wbuffer, 'c', size);
+    lfs_file_write(&lfs, &file[0], wbuffer, size) => size;
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    size = 400;
+    lfs_file_open(&lfs, &file[0], (char*)buffer, LFS_O_RDONLY) => 0;
+    lfs_file_read(&lfs, &file[0], rbuffer, size) => size;
+    memcmp(rbuffer, wbuffer, size) => 0;
+    lfs_file_close(&lfs, &file[0]) => 0;
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Resize too big ---"
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+
+    lfs_mount(&lfs, &cfg) => 0;
+    memset(buffer, 'm', 200);
+    buffer[200] = '\0';
+
+    size = 40;
+    lfs_file_open(&lfs, &file[0], (char*)buffer,
+            LFS_O_WRONLY | LFS_O_CREAT | LFS_O_TRUNC) => 0;
+    memset(wbuffer, 'c', size);
+    lfs_file_write(&lfs, &file[0], wbuffer, size) => size;
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    size = 40;
+    lfs_file_open(&lfs, &file[0], (char*)buffer, LFS_O_RDONLY) => 0;
+    lfs_file_read(&lfs, &file[0], rbuffer, size) => size;
+    memcmp(rbuffer, wbuffer, size) => 0;
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    size = 400;
+    lfs_file_open(&lfs, &file[0], (char*)buffer,
+            LFS_O_WRONLY | LFS_O_CREAT | LFS_O_TRUNC) => 0;
+    memset(wbuffer, 'c', size);
+    lfs_file_write(&lfs, &file[0], wbuffer, size) => size;
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    size = 400;
+    lfs_file_open(&lfs, &file[0], (char*)buffer, LFS_O_RDONLY) => 0;
+    lfs_file_read(&lfs, &file[0], rbuffer, size) => size;
+    memcmp(rbuffer, wbuffer, size) => 0;
+    lfs_file_close(&lfs, &file[0]) => 0;
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Results ---"
+tests/stats.py

tests/test_files.sh

@@ -30,11 +30,12 @@ TEST
 
 w_test() {
 tests/test.py << TEST
-    lfs_size_t size = $1;
+    size = $1;
     lfs_size_t chunk = 31;
     srand(0);
     lfs_mount(&lfs, &cfg) => 0;
-    lfs_file_open(&lfs, &file[0], "$2", LFS_O_WRONLY | LFS_O_CREAT) => 0;
+    lfs_file_open(&lfs, &file[0], "$2",
+        ${3:-LFS_O_WRONLY | LFS_O_CREAT | LFS_O_TRUNC}) => 0;
     for (lfs_size_t i = 0; i < size; i += chunk) {
         chunk = (chunk < size - i) ? chunk : size - i;
         for (lfs_size_t b = 0; b < chunk; b++) {
@@ -49,11 +50,14 @@ TEST
 
 r_test() {
 tests/test.py << TEST
-    lfs_size_t size = $1;
+    size = $1;
     lfs_size_t chunk = 29;
     srand(0);
     lfs_mount(&lfs, &cfg) => 0;
-    lfs_file_open(&lfs, &file[0], "$2", LFS_O_RDONLY) => 0;
+    lfs_stat(&lfs, "$2", &info) => 0;
+    info.type => LFS_TYPE_REG;
+    info.size => size;
+    lfs_file_open(&lfs, &file[0], "$2", ${3:-LFS_O_RDONLY}) => 0;
     for (lfs_size_t i = 0; i < size; i += chunk) {
         chunk = (chunk < size - i) ? chunk : size - i;
         lfs_file_read(&lfs, &file[0], buffer, chunk) => chunk;
@@ -78,10 +82,27 @@ echo "--- Large file test ---"
 w_test $LARGESIZE largeavacado
 r_test $LARGESIZE largeavacado
 
+echo "--- Zero file test ---"
+w_test 0 noavacado
+r_test 0 noavacado
+
+echo "--- Truncate small test ---"
+w_test $SMALLSIZE mediumavacado
+r_test $SMALLSIZE mediumavacado
+w_test $MEDIUMSIZE mediumavacado
+r_test $MEDIUMSIZE mediumavacado
+
+echo "--- Truncate zero test ---"
+w_test $SMALLSIZE noavacado
+r_test $SMALLSIZE noavacado
+w_test 0 noavacado
+r_test 0 noavacado
+
 echo "--- Non-overlap check ---"
 r_test $SMALLSIZE smallavacado
 r_test $MEDIUMSIZE mediumavacado
 r_test $LARGESIZE largeavacado
+r_test 0 noavacado
 
 echo "--- Dir check ---"
 tests/test.py << TEST
@@ -105,10 +126,33 @@ tests/test.py << TEST
     strcmp(info.name, "largeavacado") => 0;
     info.type => LFS_TYPE_REG;
     info.size => $LARGESIZE;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "noavacado") => 0;
+    info.type => LFS_TYPE_REG;
+    info.size => 0;
     lfs_dir_read(&lfs, &dir[0], &info) => 0;
     lfs_dir_close(&lfs, &dir[0]) => 0;
     lfs_unmount(&lfs) => 0;
 TEST
 
+echo "--- Many file test ---"
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+TEST
+tests/test.py << TEST
+    // Create 300 files of 6 bytes
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_mkdir(&lfs, "directory") => 0;
+    for (unsigned i = 0; i < 300; i++) {
+        snprintf((char*)buffer, sizeof(buffer), "file_%03d", i);
+        lfs_file_open(&lfs, &file[0], (char*)buffer, LFS_O_WRONLY | LFS_O_CREAT) => 0;
+        size = 6;
+        memcpy(wbuffer, "Hello", size);
+        lfs_file_write(&lfs, &file[0], wbuffer, size) => size;
+        lfs_file_close(&lfs, &file[0]) => 0;
+    }
+    lfs_unmount(&lfs) => 0;
+TEST
+
 echo "--- Results ---"
 tests/stats.py

tests/test_format.sh

@@ -9,14 +9,6 @@ tests/test.py << TEST
     lfs_format(&lfs, &cfg) => 0;
 TEST
 
-echo "--- Invalid superblocks ---"
-ln -f -s /dev/zero blocks/0
-ln -f -s /dev/zero blocks/1
-tests/test.py << TEST
-    lfs_format(&lfs, &cfg) => LFS_ERR_CORRUPT;
-TEST
-rm blocks/0 blocks/1
-
 echo "--- Basic mounting ---"
 tests/test.py << TEST
     lfs_format(&lfs, &cfg) => 0;
@@ -26,22 +18,32 @@ tests/test.py << TEST
     lfs_unmount(&lfs) => 0;
 TEST
 
-echo "--- Invalid mount ---"
+echo "--- Invalid superblocks ---"
+ln -f -s /dev/zero blocks/0
+ln -f -s /dev/zero blocks/1
 tests/test.py << TEST
-    lfs_format(&lfs, &cfg) => 0;
+    lfs_format(&lfs, &cfg) => LFS_ERR_CORRUPT;
 TEST
 rm blocks/0 blocks/1
+
+echo "--- Invalid mount ---"
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => LFS_ERR_CORRUPT;
 TEST
 
-echo "--- Valid corrupt mount ---"
+echo "--- Expanding superblock ---"
 tests/test.py << TEST
     lfs_format(&lfs, &cfg) => 0;
+    lfs_mount(&lfs, &cfg) => 0;
+    for (int i = 0; i < 100; i++) {
+        lfs_mkdir(&lfs, "dummy") => 0;
+        lfs_remove(&lfs, "dummy") => 0;
+    }
+    lfs_unmount(&lfs) => 0;
 TEST
-rm blocks/0
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
+    lfs_mkdir(&lfs, "dummy") => 0;
     lfs_unmount(&lfs) => 0;
 TEST
 

tests/test_interspersed.sh

@@ -1,13 +1,13 @@
 #!/bin/bash
 set -eu
 
-echo "=== Parallel tests ==="
+echo "=== Interspersed tests ==="
 rm -rf blocks
 tests/test.py << TEST
     lfs_format(&lfs, &cfg) => 0;
 TEST
 
-echo "--- Parallel file test ---"
+echo "--- Interspersed file test ---"
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
     lfs_file_open(&lfs, &file[0], "a", LFS_O_WRONLY | LFS_O_CREAT) => 0;
@@ -77,7 +77,7 @@ tests/test.py << TEST
     lfs_unmount(&lfs) => 0;
 TEST
 
-echo "--- Parallel remove file test ---"
+echo "--- Interspersed remove file test ---"
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
     lfs_file_open(&lfs, &file[0], "e", LFS_O_WRONLY | LFS_O_CREAT) => 0;

tests/test_move.sh

@@ -59,7 +59,7 @@ tests/test.py << TEST
     lfs_rename(&lfs, "b/hello", "c/hello") => 0;
     lfs_unmount(&lfs) => 0;
 TEST
-rm -v blocks/7
+tests/corrupt.py -n 1
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
     lfs_dir_open(&lfs, &dir[0], "b") => 0;
@@ -86,8 +86,7 @@ tests/test.py << TEST
     lfs_rename(&lfs, "c/hello", "d/hello") => 0;
     lfs_unmount(&lfs) => 0;
 TEST
-rm -v blocks/8
-rm -v blocks/a
+tests/corrupt.py -n 2
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
     lfs_dir_open(&lfs, &dir[0], "c") => 0;
@@ -108,6 +107,32 @@ tests/test.py << TEST
     lfs_unmount(&lfs) => 0;
 TEST
 
+echo "--- Move file after corrupt ---"
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_rename(&lfs, "c/hello", "d/hello") => 0;
+    lfs_unmount(&lfs) => 0;
+TEST
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_dir_open(&lfs, &dir[0], "c") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, ".") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "..") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 0;
+    lfs_dir_close(&lfs, &dir[0]) => 0;
+    lfs_dir_open(&lfs, &dir[0], "d") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, ".") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "..") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "hello") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 0;
+    lfs_unmount(&lfs) => 0;
+TEST
+
 echo "--- Move dir ---"
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
@@ -140,7 +165,7 @@ tests/test.py << TEST
     lfs_rename(&lfs, "b/hi", "c/hi") => 0;
     lfs_unmount(&lfs) => 0;
 TEST
-rm -v blocks/7
+tests/corrupt.py -n 1
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
     lfs_dir_open(&lfs, &dir[0], "b") => 0;
@@ -156,8 +181,6 @@ tests/test.py << TEST
     lfs_dir_read(&lfs, &dir[0], &info) => 1;
     strcmp(info.name, "..") => 0;
     lfs_dir_read(&lfs, &dir[0], &info) => 1;
-    strcmp(info.name, "hello") => 0;
-    lfs_dir_read(&lfs, &dir[0], &info) => 1;
     strcmp(info.name, "hi") => 0;
     lfs_dir_read(&lfs, &dir[0], &info) => 0;
     lfs_unmount(&lfs) => 0;
@@ -169,8 +192,7 @@ tests/test.py << TEST
     lfs_rename(&lfs, "c/hi", "d/hi") => 0;
     lfs_unmount(&lfs) => 0;
 TEST
-rm -v blocks/9
-rm -v blocks/a
+tests/corrupt.py -n 2
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
     lfs_dir_open(&lfs, &dir[0], "c") => 0;
@@ -179,8 +201,6 @@ tests/test.py << TEST
     lfs_dir_read(&lfs, &dir[0], &info) => 1;
     strcmp(info.name, "..") => 0;
     lfs_dir_read(&lfs, &dir[0], &info) => 1;
-    strcmp(info.name, "hello") => 0;
-    lfs_dir_read(&lfs, &dir[0], &info) => 1;
     strcmp(info.name, "hi") => 0;
     lfs_dir_read(&lfs, &dir[0], &info) => 0;
     lfs_dir_close(&lfs, &dir[0]) => 0;
@@ -189,6 +209,36 @@ tests/test.py << TEST
     strcmp(info.name, ".") => 0;
     lfs_dir_read(&lfs, &dir[0], &info) => 1;
     strcmp(info.name, "..") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "hello") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 0;
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Move dir after corrupt ---"
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_rename(&lfs, "c/hi", "d/hi") => 0;
+    lfs_unmount(&lfs) => 0;
+TEST
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_dir_open(&lfs, &dir[0], "c") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, ".") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "..") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 0;
+    lfs_dir_close(&lfs, &dir[0]) => 0;
+    lfs_dir_open(&lfs, &dir[0], "d") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, ".") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "..") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "hello") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "hi") => 0;
     lfs_dir_read(&lfs, &dir[0], &info) => 0;
     lfs_unmount(&lfs) => 0;
 TEST
@@ -199,9 +249,9 @@ tests/test.py << TEST
 
     lfs_dir_open(&lfs, &dir[0], "a/hi") => LFS_ERR_NOENT;
     lfs_dir_open(&lfs, &dir[0], "b/hi") => LFS_ERR_NOENT;
-    lfs_dir_open(&lfs, &dir[0], "d/hi") => LFS_ERR_NOENT;
+    lfs_dir_open(&lfs, &dir[0], "c/hi") => LFS_ERR_NOENT;
 
-    lfs_dir_open(&lfs, &dir[0], "c/hi") => 0;
+    lfs_dir_open(&lfs, &dir[0], "d/hi") => 0;
     lfs_dir_read(&lfs, &dir[0], &info) => 1;
     strcmp(info.name, ".") => 0;
     lfs_dir_read(&lfs, &dir[0], &info) => 1;
@@ -217,9 +267,55 @@ tests/test.py << TEST
 
     lfs_dir_open(&lfs, &dir[0], "a/hello") => LFS_ERR_NOENT;
     lfs_dir_open(&lfs, &dir[0], "b/hello") => LFS_ERR_NOENT;
-    lfs_dir_open(&lfs, &dir[0], "d/hello") => LFS_ERR_NOENT;
+    lfs_dir_open(&lfs, &dir[0], "c/hello") => LFS_ERR_NOENT;
 
-    lfs_file_open(&lfs, &file[0], "c/hello", LFS_O_RDONLY) => 0;
+    lfs_file_open(&lfs, &file[0], "d/hello", LFS_O_RDONLY) => 0;
+    lfs_file_read(&lfs, &file[0], buffer, 5) => 5;
+    memcmp(buffer, "hola\n", 5) => 0;
+    lfs_file_read(&lfs, &file[0], buffer, 8) => 8;
+    memcmp(buffer, "bonjour\n", 8) => 0;
+    lfs_file_read(&lfs, &file[0], buffer, 6) => 6;
+    memcmp(buffer, "ohayo\n", 6) => 0;
+    lfs_file_close(&lfs, &file[0]) => 0;
+
+    lfs_unmount(&lfs) => 0;
+TEST
+
+echo "--- Move state stealing ---"
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+
+    lfs_remove(&lfs, "b") => 0;
+    lfs_remove(&lfs, "c") => 0;
+
+    lfs_unmount(&lfs) => 0;
+TEST
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+
+    lfs_dir_open(&lfs, &dir[0], "a/hi") => LFS_ERR_NOENT;
+    lfs_dir_open(&lfs, &dir[0], "b") => LFS_ERR_NOENT;
+    lfs_dir_open(&lfs, &dir[0], "c") => LFS_ERR_NOENT;
+
+    lfs_dir_open(&lfs, &dir[0], "d/hi") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, ".") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "..") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "hola") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "bonjour") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 1;
+    strcmp(info.name, "ohayo") => 0;
+    lfs_dir_read(&lfs, &dir[0], &info) => 0;
+    lfs_dir_close(&lfs, &dir[0]) => 0;
+
+    lfs_dir_open(&lfs, &dir[0], "a/hello") => LFS_ERR_NOENT;
+    lfs_dir_open(&lfs, &dir[0], "b") => LFS_ERR_NOENT;
+    lfs_dir_open(&lfs, &dir[0], "c") => LFS_ERR_NOENT;
+
+    lfs_file_open(&lfs, &file[0], "d/hello", LFS_O_RDONLY) => 0;
     lfs_file_read(&lfs, &file[0], buffer, 5) => 5;
     memcmp(buffer, "hola\n", 5) => 0;
     lfs_file_read(&lfs, &file[0], buffer, 8) => 8;

tests/test_orphan.sh

@@ -15,25 +15,29 @@ tests/test.py << TEST
     lfs_mkdir(&lfs, "parent/child") => 0;
     lfs_remove(&lfs, "parent/orphan") => 0;
 TEST
-# remove most recent file, this should be the update to the previous
+# corrupt most recent commit, this should be the update to the previous
 # linked-list entry and should orphan the child
-rm -v blocks/8
+tests/corrupt.py
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
-    lfs_stat(&lfs, "parent/orphan", &info) => LFS_ERR_NOENT;
-    unsigned before = 0;
-    lfs_traverse(&lfs, test_count, &before) => 0;
-    test_log("before", before);
-
-    lfs_deorphan(&lfs) => 0;
 
     lfs_stat(&lfs, "parent/orphan", &info) => LFS_ERR_NOENT;
-    unsigned after = 0;
-    lfs_traverse(&lfs, test_count, &after) => 0;
-    test_log("after", after);
+    lfs_ssize_t before = lfs_fs_size(&lfs);
+    before => 8;
+
+    lfs_unmount(&lfs) => 0;
+    lfs_mount(&lfs, &cfg) => 0;
+
+    lfs_stat(&lfs, "parent/orphan", &info) => LFS_ERR_NOENT;
+    lfs_ssize_t orphaned = lfs_fs_size(&lfs);
+    orphaned => 8;
+
+    lfs_mkdir(&lfs, "parent/otherchild") => 0;
+
+    lfs_stat(&lfs, "parent/orphan", &info) => LFS_ERR_NOENT;
+    lfs_ssize_t deorphaned = lfs_fs_size(&lfs);
+    deorphaned => 8;
 
-    int diff = before - after;
-    diff => 2;
     lfs_unmount(&lfs) => 0;
 TEST
 

tests/test_paths.sh

@@ -90,6 +90,22 @@ tests/test.py << TEST
     lfs_unmount(&lfs) => 0;
 TEST
 
+echo "--- Trailing dot path tests ---"
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    lfs_stat(&lfs, "tea/hottea/", &info) => 0;
+    strcmp(info.name, "hottea") => 0;
+    lfs_stat(&lfs, "tea/hottea/.", &info) => 0;
+    strcmp(info.name, "hottea") => 0;
+    lfs_stat(&lfs, "tea/hottea/./.", &info) => 0;
+    strcmp(info.name, "hottea") => 0;
+    lfs_stat(&lfs, "tea/hottea/..", &info) => 0;
+    strcmp(info.name, "tea") => 0;
+    lfs_stat(&lfs, "tea/hottea/../.", &info) => 0;
+    strcmp(info.name, "tea") => 0;
+    lfs_unmount(&lfs) => 0;
+TEST
+
 echo "--- Root dot dot path tests ---"
 tests/test.py << TEST
     lfs_mount(&lfs, &cfg) => 0;
@@ -108,6 +124,10 @@ tests/test.py << TEST
     lfs_stat(&lfs, "/", &info) => 0;
     info.type => LFS_TYPE_DIR;
     strcmp(info.name, "/") => 0;
+
+    lfs_mkdir(&lfs, "/") => LFS_ERR_EXIST;
+    lfs_file_open(&lfs, &file[0], "/", LFS_O_WRONLY | LFS_O_CREAT)
+        => LFS_ERR_ISDIR;
     lfs_unmount(&lfs) => 0;
 TEST
 
@@ -119,5 +139,23 @@ tests/test.py << TEST
     lfs_unmount(&lfs) => 0;
 TEST
 
+echo "--- Max path test ---"
+tests/test.py << TEST
+    lfs_mount(&lfs, &cfg) => 0;
+    memset(buffer, 'w', LFS_NAME_MAX+1);
+    buffer[LFS_NAME_MAX+2] = '\0';
+    lfs_mkdir(&lfs, (char*)buffer) => LFS_ERR_NAMETOOLONG;
+    lfs_file_open(&lfs, &file[0], (char*)buffer,
+            LFS_O_WRONLY | LFS_O_CREAT) => LFS_ERR_NAMETOOLONG;
+
+    memcpy(buffer, "coffee/", strlen("coffee/"));
+    memset(buffer+strlen("coffee/"), 'w', LFS_NAME_MAX+1);
+    buffer[strlen("coffee/")+LFS_NAME_MAX+2] = '\0';
+    lfs_mkdir(&lfs, (char*)buffer) => LFS_ERR_NAMETOOLONG;
+    lfs_file_open(&lfs, &file[0], (char*)buffer,
+            LFS_O_WRONLY | LFS_O_CREAT) => LFS_ERR_NAMETOOLONG;
+    lfs_unmount(&lfs) => 0;
+TEST
+
 echo "--- Results ---"
 tests/stats.py

tests/test_seek.sh

@@ -133,6 +133,14 @@ tests/test.py << TEST
     lfs_file_read(&lfs, &file[0], buffer, size) => size;
     memcmp(buffer, "kittycatcat", size) => 0;
 
+    lfs_file_seek(&lfs, &file[0], 0, LFS_SEEK_CUR) => size;
+    lfs_file_read(&lfs, &file[0], buffer, size) => size;
+    memcmp(buffer, "kittycatcat", size) => 0;
+
+    lfs_file_seek(&lfs, &file[0], size, LFS_SEEK_CUR) => 3*size;
+    lfs_file_read(&lfs, &file[0], buffer, size) => size;
+    memcmp(buffer, "kittycatcat", size) => 0;
+
     lfs_file_seek(&lfs, &file[0], pos, LFS_SEEK_SET) => pos;
     lfs_file_read(&lfs, &file[0], buffer, size) => size;
     memcmp(buffer, "kittycatcat", size) => 0;
@@ -145,7 +153,7 @@ tests/test.py << TEST
     lfs_file_read(&lfs, &file[0], buffer, size) => size;
     memcmp(buffer, "kittycatcat", size) => 0;
 
-    lfs_size_t size = lfs_file_size(&lfs, &file[0]);
+    size = lfs_file_size(&lfs, &file[0]);
     lfs_file_seek(&lfs, &file[0], 0, LFS_SEEK_CUR) => size;
 
     lfs_file_close(&lfs, &file[0]) => 0;
@@ -174,6 +182,14 @@ tests/test.py << TEST
     lfs_file_read(&lfs, &file[0], buffer, size) => size;
     memcmp(buffer, "kittycatcat", size) => 0;
 
+    lfs_file_seek(&lfs, &file[0], 0, LFS_SEEK_CUR) => size;
+    lfs_file_read(&lfs, &file[0], buffer, size) => size;
+    memcmp(buffer, "kittycatcat", size) => 0;
+
+    lfs_file_seek(&lfs, &file[0], size, LFS_SEEK_CUR) => 3*size;
+    lfs_file_read(&lfs, &file[0], buffer, size) => size;
+    memcmp(buffer, "kittycatcat", size) => 0;
+
     lfs_file_seek(&lfs, &file[0], pos, LFS_SEEK_SET) => pos;
     lfs_file_read(&lfs, &file[0], buffer, size) => size;
     memcmp(buffer, "kittycatcat", size) => 0;
@@ -186,7 +202,7 @@ tests/test.py << TEST
     lfs_file_read(&lfs, &file[0], buffer, size) => size;
     memcmp(buffer, "kittycatcat", size) => 0;
 
-    lfs_size_t size = lfs_file_size(&lfs, &file[0]);
+    size = lfs_file_size(&lfs, &file[0]);
     lfs_file_seek(&lfs, &file[0], 0, LFS_SEEK_CUR) => size;
 
     lfs_file_close(&lfs, &file[0]) => 0;
@@ -227,7 +243,7 @@ tests/test.py << TEST
     lfs_file_read(&lfs, &file[0], buffer, size) => size;
     memcmp(buffer, "kittycatcat", size) => 0;
 
-    lfs_size_t size = lfs_file_size(&lfs, &file[0]);
+    size = lfs_file_size(&lfs, &file[0]);
     lfs_file_seek(&lfs, &file[0], 0, LFS_SEEK_CUR) => size;
 
     lfs_file_close(&lfs, &file[0]) => 0;
@@ -270,7 +286,7 @@ tests/test.py << TEST
     lfs_file_read(&lfs, &file[0], buffer, size) => size;
     memcmp(buffer, "kittycatcat", size) => 0;
 
-    lfs_size_t size = lfs_file_size(&lfs, &file[0]);
+    size = lfs_file_size(&lfs, &file[0]);
     lfs_file_seek(&lfs, &file[0], 0, LFS_SEEK_CUR) => size;
 
     lfs_file_close(&lfs, &file[0]) => 0;

tests/test_truncate.sh

@@ -0,0 +1,158 @@
+#!/bin/bash
+set -eu
+
+SMALLSIZE=32
+MEDIUMSIZE=2048
+LARGESIZE=8192
+
+echo "=== Truncate tests ==="
+rm -rf blocks
+tests/test.py << TEST
+    lfs_format(&lfs, &cfg) => 0;
+TEST
+
+truncate_test() {
+STARTSIZES="$1"
+STARTSEEKS="$2"
+HOTSIZES="$3"
+COLDSIZES="$4"
+tests/test.py << TEST
+    static const lfs_off_t startsizes[] = {$STARTSIZES};
+    static const lfs_off_t startseeks[] = {$STARTSEEKS};
+    static const lfs_off_t hotsizes[]   = {$HOTSIZES};
+
+    lfs_mount(&lfs, &cfg) => 0;
+
+    for (int i = 0; i < sizeof(startsizes)/sizeof(startsizes[0]); i++) {
+        sprintf((char*)buffer, "hairyhead%d", i);
+        lfs_file_open(&lfs, &file[0], (const char*)buffer,
+                LFS_O_WRONLY | LFS_O_CREAT | LFS_O_TRUNC) => 0;
+
+        strcpy((char*)buffer, "hair");
+        size = strlen((char*)buffer);
+        for (int j = 0; j < startsizes[i]; j += size) {
+            lfs_file_write(&lfs, &file[0], buffer, size) => size;
+        }
+        lfs_file_size(&lfs, &file[0]) => startsizes[i];
+
+        if (startseeks[i] != startsizes[i]) {
+            lfs_file_seek(&lfs, &file[0],
+                    startseeks[i], LFS_SEEK_SET) => startseeks[i];
+        }
+
+        lfs_file_truncate(&lfs, &file[0], hotsizes[i]) => 0;
+        lfs_file_size(&lfs, &file[0]) => hotsizes[i];
+
+        lfs_file_close(&lfs, &file[0]) => 0;
+    }
+
+    lfs_unmount(&lfs) => 0;
+TEST
+tests/test.py << TEST
+    static const lfs_off_t startsizes[] = {$STARTSIZES};
+    static const lfs_off_t hotsizes[]   = {$HOTSIZES};
+    static const lfs_off_t coldsizes[]  = {$COLDSIZES};
+
+    lfs_mount(&lfs, &cfg) => 0;
+
+    for (int i = 0; i < sizeof(startsizes)/sizeof(startsizes[0]); i++) {
+        sprintf((char*)buffer, "hairyhead%d", i);
+        lfs_file_open(&lfs, &file[0], (const char*)buffer, LFS_O_RDWR) => 0;
+        lfs_file_size(&lfs, &file[0]) => hotsizes[i];
+
+        size = strlen("hair");
+        int j = 0;
+        for (; j < startsizes[i] && j < hotsizes[i]; j += size) {
+            lfs_file_read(&lfs, &file[0], buffer, size) => size;
+            memcmp(buffer, "hair", size) => 0;
+        }
+
+        for (; j < hotsizes[i]; j += size) {
+            lfs_file_read(&lfs, &file[0], buffer, size) => size;
+            memcmp(buffer, "\0\0\0\0", size) => 0;
+        }
+
+        lfs_file_truncate(&lfs, &file[0], coldsizes[i]) => 0;
+        lfs_file_size(&lfs, &file[0]) => coldsizes[i];
+
+        lfs_file_close(&lfs, &file[0]) => 0;
+    }
+
+    lfs_unmount(&lfs) => 0;
+TEST
+tests/test.py << TEST
+    static const lfs_off_t startsizes[] = {$STARTSIZES};
+    static const lfs_off_t hotsizes[]   = {$HOTSIZES};
+    static const lfs_off_t coldsizes[]  = {$COLDSIZES};
+
+    lfs_mount(&lfs, &cfg) => 0;
+
+    for (int i = 0; i < sizeof(startsizes)/sizeof(startsizes[0]); i++) {
+        sprintf((char*)buffer, "hairyhead%d", i);
+        lfs_file_open(&lfs, &file[0], (const char*)buffer, LFS_O_RDONLY) => 0;
+        lfs_file_size(&lfs, &file[0]) => coldsizes[i];
+
+        size = strlen("hair");
+        int j = 0;
+        for (; j < startsizes[i] && j < hotsizes[i] && j < coldsizes[i];
+                j += size) {
+            lfs_file_read(&lfs, &file[0], buffer, size) => size;
+            memcmp(buffer, "hair", size) => 0;
+        }
+
+        for (; j < coldsizes[i]; j += size) {
+            lfs_file_read(&lfs, &file[0], buffer, size) => size;
+            memcmp(buffer, "\0\0\0\0", size) => 0;
+        }
+
+        lfs_file_close(&lfs, &file[0]) => 0;
+    }
+
+    lfs_unmount(&lfs) => 0;
+TEST
+}
+
+echo "--- Cold shrinking truncate ---"
+truncate_test \
+    "2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE" \
+    "2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE" \
+    "2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE" \
+    "           0,   $SMALLSIZE,  $MEDIUMSIZE,   $LARGESIZE, 2*$LARGESIZE"
+
+echo "--- Cold expanding truncate ---"
+truncate_test \
+    "           0,   $SMALLSIZE,  $MEDIUMSIZE,   $LARGESIZE, 2*$LARGESIZE" \
+    "           0,   $SMALLSIZE,  $MEDIUMSIZE,   $LARGESIZE, 2*$LARGESIZE" \
+    "           0,   $SMALLSIZE,  $MEDIUMSIZE,   $LARGESIZE, 2*$LARGESIZE" \
+    "2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE"
+
+echo "--- Warm shrinking truncate ---"
+truncate_test \
+    "2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE" \
+    "2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE" \
+    "           0,   $SMALLSIZE,  $MEDIUMSIZE,   $LARGESIZE, 2*$LARGESIZE" \
+    "           0,            0,            0,            0,            0"
+
+echo "--- Warm expanding truncate ---"
+truncate_test \
+    "           0,   $SMALLSIZE,  $MEDIUMSIZE,   $LARGESIZE, 2*$LARGESIZE" \
+    "           0,   $SMALLSIZE,  $MEDIUMSIZE,   $LARGESIZE, 2*$LARGESIZE" \
+    "2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE" \
+    "2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE"
+
+echo "--- Mid-file shrinking truncate ---"
+truncate_test \
+    "2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE" \
+    "  $LARGESIZE,   $LARGESIZE,   $LARGESIZE,   $LARGESIZE,   $LARGESIZE" \
+    "           0,   $SMALLSIZE,  $MEDIUMSIZE,   $LARGESIZE, 2*$LARGESIZE" \
+    "           0,            0,            0,            0,            0"
+
+echo "--- Mid-file expanding truncate ---"
+truncate_test \
+    "           0,   $SMALLSIZE,  $MEDIUMSIZE,   $LARGESIZE, 2*$LARGESIZE" \
+    "           0,            0,   $SMALLSIZE,  $MEDIUMSIZE,   $LARGESIZE" \
+    "2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE" \
+    "2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE, 2*$LARGESIZE"
+
+echo "--- Results ---"
+tests/stats.py