#!/bin/sh
# Mutation-test the SchFS suites: inject a bug, confirm the tests report it,
# restore. A test that cannot fail is worse than no test, because it is
# believed. Run by hand; not part of the normal build.
#
# Every mutation is verified to have actually changed the file before the
# suite runs. A sed pattern that silently stops matching -- after a refactor,
# say -- would otherwise look exactly like a passing mutation test, which is
# the same failure this script exists to catch.
set -e

# Run from anywhere. This used to `cd /mnt/d/DEV/SchOS` -- an absolute WSL path
# from the Windows machine this was written on, which meant the script could not
# run on any other checkout at all.
script_dir=$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)
repo=$(CDPATH= cd -- "$script_dir/../.." && pwd)
cd "$repo"


# Where the host tools land. These moved to build/tools/ in the bt/ -> tools/
# migration and this script kept the old names; make then answered "No rule to
# make target", which the harness reported as "rejected at compile time". Every
# mutation looked handled and not one of them ever reached a test.
MKSCHFS=build/tools/mkschfs
FSCK=build/tools/schfs_fsck
OBJT=build/tools/schfs_objtest

OBJ=kernel/fs/schfs/obj.c
OBJW=kernel/fs/schfs/objw.c
SPACE=kernel/fs/schfs/space.c
MK=tools/mkschfs.c
cp $OBJ /tmp/obj.orig
cp $OBJW /tmp/objw.orig
cp $SPACE /tmp/space.orig
cp $MK /tmp/mk.orig

restore() {
    cp /tmp/obj.orig $OBJ
    cp /tmp/objw.orig $OBJW
    cp /tmp/space.orig $SPACE
    cp /tmp/mk.orig $MK
}
trap restore EXIT

FAILED=0

# Quote the line that says why, falling back to the last thing the suite said.
# Two mutations used to report a bare "caught:" with nothing after it -- the
# suite had failed, but nothing in it matched the patterns below, so the
# evidence was an exit status and an empty string.
why() {
    line=$(grep -aE 'FAIL|Only in|differ|loop|error|assert' "$1" | head -1)
    [ -n "$line" ] || line=$(grep -av '^[[:space:]]*$' "$1" | tail -1)
    printf '%s' "$line" | sed 's/^ *//'
}

# try <description> <file> <sed-expression> [suite]
#
# suite is "image" (the default: build an image and diff it against the source
# tree) or "obj" (the in-memory object-layer test). They catch different things:
# the image round-trip cannot see a bug that only shows up after a delete,
# because it never deletes anything.
try() {
    desc=$1; file=$2; expr=$3; suite=${4:-image}
    restore
    before=$(cksum < "$file")
    sed -i "$expr" "$file"
    after=$(cksum < "$file")

    echo "mutation: $desc"
    if [ "$before" = "$after" ]; then
        echo "  BROKEN MUTATION -- the pattern no longer matches anything"
        FAILED=1
        return
    fi

    if [ "$suite" = obj ]; then
        if ! make "$OBJT" > /tmp/mk.log 2>&1; then
            echo "  rejected at compile time"
            sed -n '$p' /tmp/mk.log | sed 's/^/    /'
            return
        fi
        if "./$OBJT" > /tmp/rt.log 2>&1; then
            echo "  NOT CAUGHT -- the suite passed with this bug present"
            FAILED=1
        else
            echo "  caught: $(why /tmp/rt.log)"
        fi
        return
    fi

    if ! make "$MKSCHFS" "$FSCK" > /tmp/mk.log 2>&1; then
        echo "  rejected at compile time"
        sed -n '$p' /tmp/mk.log | sed 's/^/    /'
        return
    fi
    if sh tools/posix/schfs_roundtrip.sh "./$MKSCHFS" "./$FSCK" \
            > /tmp/rt.log 2>&1; then
        echo "  NOT CAUGHT -- the suite passed with this bug present"
        FAILED=1
    else
        echo "  caught: $(why /tmp/rt.log)"
    fi
}

# Reads run past end-of-file, so every file comes back padded.
try "file_read ignores the end-of-file clamp" $OBJ \
    's|if (off + n > in.size)|if (0)|'

# The dirent walk skips forward too far, losing entries in any packed list.
try "dirent_walk advances past the next entry" $OBJ \
    's|        off += step;|        off += step + 8;|'

# Directory lookup returns the neighbouring object.
try "dir_lookup returns the wrong objectid" $OBJ \
    's|    f->ino  = d->objectid;|    f->ino  = d->objectid + 1;|'

# Every extent points one block past its data.
#
# Note this replaced an earlier mutation that shortened the extent by a block.
# That one was NOT caught, and correctly so: an extent covering too little just
# leaves the tail unmapped, and schfs_file_append then allocates it separately,
# so the file still reads back byte for byte. The design absorbs it. Pointing
# at the wrong block cannot be absorbed.
try "extents point one block past their data" $OBJW \
    's|    e.disk_block = first;|    e.disk_block = first + 1;|'

# Copy-on-write splits an extent into head, replacement and tail. Losing the
# tail leaves everything after the rewritten block unmapped, so it silently
# reads back as zeros -- data loss that looks exactly like a sparse file.
try "an overwrite drops the tail of the extent it split" $OBJW \
    's|    if (fblk + 1 < start + e.nblocks) {|    if (0) {|' obj

# Truncating down and growing again must read zeros. Skipping the zeroing of
# the partial last block hands back whatever the file used to hold there --
# which, across a delete and a reallocation, is somebody else's data.
try "truncate leaves stale bytes in the last partial block" $OBJW \
    's|                memset((char \*)dblk + tail, 0, SCHFS_BLKSIZE - tail);|                /* mutated */;|' obj

# Deferred frees never rejoin the free map, so every delete leaks. Nothing that
# only reads or only writes can see this; it takes a test that deletes
# everything and then checks the free count.
try "committed frees are never returned to the free map" $SPACE \
    's|            inuse\[w\] &= ~pend\[w\];|            /* mutated */;|' obj

# Hard links are not counted, so dedup is indistinguishable from duplication
# and only the explicit nlink assertion can tell the difference.
try "hard links do not bump nlink" $MK \
    's|^    in.nlink++;|    /* mutated */;|'

# Data checksums cover only the head of a block, so tail corruption is missed.
try "data checksum covers only the first 16 bytes" $OBJW \
    's|uint32_t c = schfs_crc32c(0, data, SCHFS_BLKSIZE);|uint32_t c = schfs_crc32c(0, data, 16);|'

restore
make build/mkschfs build/schfs_fsck > /dev/null 2>&1
echo
if [ $FAILED -eq 0 ]; then
    echo "all mutations were caught"
else
    echo "SOME MUTATIONS WERE NOT CAUGHT -- the suite has a blind spot"
    exit 1
fi