Travis: Toolchain only depends on headers, not impls

When libstdc++ was added in 4977fd22b874fb9d6d089665e36badd03bcde827, just calling
'make install' was the easiest way to install the headers. And the headers are all
that is needed for libstdc++ to determine the ABI. Since then, BuildIt.sh was
rewritten again and again, and somehow everyone just silently assumed that
libstdc++ also depends on libc.a and libm.a, because surely it does?

Turns out, it doesn't! This massively reduces the dependencies of libstdc++,
hopefully meaning that the Toolchain doesn't need to be rebuilt so often on Travis.

Furthermore, the old method of trying to determine the dependency tree with
bash/grep/etc. has finally broken anyways:

    https://travis-ci.com/github/SerenityOS/serenity/builds/179805569#L567

In summary, this should eliminate most of the Toolchain rebuilds on Travis,
and therefore make Travis build blazingly fast! :^)

2 files changed, 35 insertions, 92 deletions

diff --git a/Toolchain/BuildIt.sh b/Toolchain/BuildIt.sh
index c5a22fd67a..19c535a2ab 100755
--- a/Toolchain/BuildIt.sh
+++ b/Toolchain/BuildIt.sh
@@ -19,10 +19,10 @@ MAKE="make"
 MD5SUM="md5sum"
 NPROC="nproc"
 
-# Each cache entry is 70 MB. 10 entries are 700 MiB.
+# Each cache entry is 70 MB. 5 entries are 350 MiB.
 # It seems that Travis starts having trouble around a total
 # cache size of 9 GiB, so I think this is a good amount.
-KEEP_CACHE_COUNT=10
+KEEP_CACHE_COUNT=5
 
 if command -v ginstall &>/dev/null; then
     INSTALL=ginstall
@@ -76,19 +76,27 @@ GCC_BASE_URL="http://ftp.gnu.org/gnu/gcc"
 pushd "$DIR"
     if [ "${TRY_USE_LOCAL_TOOLCHAIN}" = "y" ] ; then
         echo "Checking cached toolchain:"
-
-        DEPS_CONFIG="
+        # TODO: This is still overly pessimistic.
+        DEPS_CONFIG="\
             uname=$(uname),TARGET=${TARGET},
             BuildItHash=$($MD5SUM "$(basename "$0")"),
             MAKE=${MAKE},MD5SUM=${MD5SUM},NPROC=${NPROC},
             CC=${CC},CXX=${CXX},with_gmp=${with_gmp},LDFLAGS=${LDFLAGS},
             BINUTILS_VERSION=${BINUTILS_VERSION},BINUTILS_MD5SUM=${BINUTILS_MD5SUM},
             GCC_VERSION=${GCC_VERSION},GCC_MD5SUM=${GCC_MD5SUM}"
-        echo "Config is:${DEPS_CONFIG}"
         if ! DEPS_HASH=$("$DIR/ComputeDependenciesHash.sh" "$MD5SUM" <<<"${DEPS_CONFIG}"); then
+            # Make it stand out more
+            echo
+            echo
+            echo
+            echo
             echo "Dependency hashing failed"
             echo "Will rebuild toolchain from scratch, and NOT SAVE THE RESULT."
             echo "Someone should look into this, but for now it'll work, albeit inefficient."
+            echo
+            echo
+            echo
+            echo
             # Should be empty anyway, but just to make sure:
             DEPS_HASH=""
         elif [ -r "Cache/ToolchainLocal_${DEPS_HASH}.tar.gz" ] ; then
@@ -238,12 +246,10 @@ pushd "$DIR/Build/"
         echo "XXX install gcc and libgcc"
         "$MAKE" install-gcc install-target-libgcc || exit 1
 
-        echo "XXX serenity libc and libm"
+        echo "XXX serenity libc and libm headers"
         mkdir -p "$BUILD"
         pushd "$BUILD"
-            CXXFLAGS="-DBUILDING_SERENITY_TOOLCHAIN" cmake ..
-            cmake --build . --target LibC
-            "$INSTALL" -D Libraries/LibC/libc.a Libraries/LibM/libm.a Root/usr/lib/
+            mkdir -p Root/usr/include/
             SRC_ROOT=$(realpath "$DIR"/..)
             FILES=$(find "$SRC_ROOT"/Libraries/LibC "$SRC_ROOT"/Libraries/LibM -name '*.h' -print)
             for header in $FILES; do
diff --git a/Toolchain/ComputeDependenciesHash.sh b/Toolchain/ComputeDependenciesHash.sh
index 0da2cf2a76..3a4ba36889 100755
--- a/Toolchain/ComputeDependenciesHash.sh
+++ b/Toolchain/ComputeDependenciesHash.sh
@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-set -eu
+set -euo pipefail
 # This file will need to be run in bash, for now.
 
 if [ $# -lt 1 ] ; then
@@ -23,89 +23,26 @@ function finish {
 }
 trap finish EXIT
 
-# libstdc++ depends on libc and libm, so we pessimistically assume it depends
-# on *all* of their implementation and recursive dependencies.
-# Scan all files for potential dependencies.
-# Thinking in graphs, this computes the edge list:
-cat <(find AK/ Libraries/ Services/ Kernel/ -name '*.h') \
-    <(find Libraries/LibC/ Libraries/LibM/ -name '*.cpp' ! -name 'Test*.cpp' ) | \
-    xargs grep -F '#include ' | \
-    sed -r \
-        -e 's,^(.*/)([^/]+:)#include "(.*)",\1\2\1\3,' \
-        -e 's^#include <(Kernel/.*)>^\1^' \
-        -e 's^#include <(AK/.*)>^\1^' \
-        -e 's^#include <(Lib[A-Za-z]+/.*)>^Libraries/\1^' \
-        -e 's^#include <((bits|netinet|sys|arpa|net)/.*)>^Libraries/LibC/\1^' \
-        -e 's^#include <fd_set.h>^Libraries/LibC/fd_set.h^' \
-        -e 's^#include <([a-z]{3,10}(_numbers)?\.h)>^Libraries/LibC/\1^' \
-        -e 's^#include <([A-Z][a-z]+Server/.*)>^Services/\1^' \
-        -e 's^#include <(.*)>^UNRESOLVED_I/\1^' \
-        -e 's^#include "(.*)"^UNRESOLVED_L/\1^' > "${DEPLIST_FILE}"
-# Some #include's cannot be resolved, like <chrono>. However, these are only
-# a problem if they turn up as a transitive dependency of libc and libm.
-# We will check for that when the time comes.
-
-# The initial guess is pessimistic: *all* of libc and libm.
-FILE_LIST=$(find Libraries/LibC/ Libraries/LibM/ \( -name '*.cpp' -o -name '*.c' -o -name '*.h' \) ! -name 'Test*')
-echo "$0: Exploring dependencies of libstdc++" >&2
-FILE_LIST_COMPLETE="n"
-# In each iteration, we extend FILE_LIST by the dependencies not listed yet in
-# FILE_LIST.  Note that the results are always semantically the same,
-# but the order depends on the initial `find` runs.
-for _ in $(seq 10) ; do
-    FILE_REGEX=$(echo "${FILE_LIST}" | sed -zr -e 's,\n$,,' -e 's,\.,\\.,g' -e 's,\n,|,g')
-    FURTHER_FILE_LIST=$(grep -P "^(${FILE_REGEX}):" "${DEPLIST_FILE}" | grep -Pv ":(${FILE_REGEX})\$" | sed -re 's,^.*:(.*)$,\1,' | sort -u)
-    if [ -n "${FURTHER_FILE_LIST}" ] ; then
-        # FILE_LIST should grow to a maximum of "number of all .cpp and .c and .h files",
-        # i.e. roughly 700 lines.  This should be managable, even as the project grows.
-        FILE_LIST="${FILE_LIST}
-${FURTHER_FILE_LIST}"
-    else
-        FILE_LIST_COMPLETE="y"
-        break
-    fi
-done
-FURTHER_FILE_LIST=""
-FILE_REGEX=""
-if [ "${FILE_LIST_COMPLETE}" != "y" ] ; then
-    # Dependency chains might grow very long. Also, if for some reason we fail
-    # to filter out the already listed files, the FILE_LIST would grow
-    # exponentially. Both of these unpleasant cases are handled by capping the
-    # iteration count to 10 and giving up:
-    echo "$0: Dependencies don't seem to converge, giving up." >&2
-    exit 1
-fi
-
-# Sort for reproducability,
-FILE_LIST=$(echo "${FILE_LIST}" | LC_ALL=C sort -u)
-if grep -F 'UNRESOLVED' <<EOLIST >&2 ; then
-${FILE_LIST}
-EOLIST
-    echo "$0: Unresolved dependency, giving up."
-    exit 1
-fi
-
-echo "$0: Computing hashes" >&2
-# "$@" is the md5sum invocation. The piping might hide non-zero exit-codes,
+# First, capture the caller's input.
+echo "$0: Configuration:" >&2
+cat /dev/stdin | tee /dev/stderr > "${DEPLIST_FILE}"
+# "$@" is the md5sum invocation.
+"$@" Toolchain/ComputeDependenciesHash.sh | tee /dev/stderr >> "${DEPLIST_FILE}"
+
+# libstdc++ depends on the *headers* of libc, so we pessimistically assume it depends
+# on *all* of them.
+# This list of files can be cut down considerably:
+#     strace -ff -e trace=file "make install-target-libstdc++-v3" 2>&1 >/dev/null | perl -ne 's/^[^"]+"(([^\\"]|\\[\\"nt])*)".*/$1/ && print' | sort -u | grep -P 'serenity/Build/Root/usr/include/.*\.h$'
+# However, we don't want to risk breaking the build when we upgrade gcc in the future.
+#
+# If you want to further cut down the Toolchain rebuilds on Travis,
+# one way would be to reduce this list somehow.
+cd Libraries/LibC/
+find -name '*.h' | sort | xargs "$@" | tee /dev/stderr >> "${DEPLIST_FILE}"
+
+# The piping might hide non-zero exit-codes,
 # but thankfully only the first command can reasonably fail.
-# Also, abuse the deplist file as a temporary buffer.
-cat /dev/stdin > "${DEPLIST_FILE}"
-HASHES=$(xargs "$@" <<EOLIST
-${FILE_LIST}
-Toolchain/ComputeDependenciesHash.sh
-${DEPLIST_FILE}
-EOLIST
-)
-# Caller (probably BuildIt.sh) should inject it's own hash via stdin.
-
-# Mask the temporary (= non-reproducable) name of the DEPLIST_FILE:
-HASHES=$(echo "${HASHES}" | sed -re 's,/tmp/serenity_deps_........\.lst,CONFIG,')
-
-echo "$0: Hashes are:" >&2
-echo "${HASHES}" >&2
 echo "$0: Toolchain hash:" >&2
-cat <<EOHASH | "$@" - | cut -f1 -d' ' | tee /dev/stderr
-${HASHES}
-EOHASH
+"$@" "${DEPLIST_FILE}" | cut -f1 -d' ' | tee /dev/stderr
 
 echo "$0: Great success!" >&2