PVF worker: Maintain lists of used syscalls (#1663)

Co-authored-by: Mira Ressel <mira@parity.io>

.cargo/config.toml

@@ -37,3 +37,8 @@ rustflags = [
   "-Aclippy::extra-unused-type-parameters", # stylistic
   "-Aclippy::default_constructed_unit_structs", # stylistic
 ]
+
+[env]
+# Needed for musl builds so user doesn't have to install musl-tools.
+CC_x86_64_unknown_linux_musl = { value = ".cargo/musl-gcc", force = true, relative = true }
+CXX_x86_64_unknown_linux_musl = { value = ".cargo/musl-g++", force = true, relative = true }

.cargo/musl-g++

@@ -0,0 +1,7 @@
+#!/bin/sh
+
+# Wrapper for building with musl.
+#
+# See comments for musl-gcc in this repo.
+
+g++ "$@"

.cargo/musl-gcc

@@ -0,0 +1,13 @@
+#!/bin/sh
+
+# Wrapper for building with musl.
+#
+# musl unfortunately requires a musl-enabled C compiler (musl-gcc) to be
+# installed, which can be kind of a pain to get installed depending on the
+# distro. That's not a very good user experience.
+#
+# The real musl-gcc wrapper sets the correct system include paths for linking
+# with musl libc library. Since this is not actually used to link any binaries
+# it should most likely work just fine.
+
+gcc "$@"

.gitlab/pipeline/test.yml

@@ -503,3 +503,23 @@ cargo-hfuzz:
     - cargo hfuzz build
     - for target in $(cargo read-manifest | jq -r '.targets | .[] | .name'); do
       cargo hfuzz run "$target" || { printf "fuzzing failure for %s\n" "$target"; exit 1; }; done
+
+# cf https://github.com/paritytech/polkadot-sdk/issues/1652
+test-syscalls:
+  stage: test
+  extends:
+    - .docker-env
+    - .common-refs
+    - .run-immediately
+  variables:
+    SKIP_WASM_BUILD: 1
+  script:
+    - cargo build --locked --profile production --target x86_64-unknown-linux-musl --bin polkadot-execute-worker --bin polkadot-prepare-worker
+    - cd polkadot/scripts/list-syscalls
+    - ./list-syscalls.rb ../../../target/x86_64-unknown-linux-musl/production/polkadot-execute-worker --only-used-syscalls | diff -u execute-worker-syscalls -
+    - ./list-syscalls.rb ../../../target/x86_64-unknown-linux-musl/production/polkadot-prepare-worker --only-used-syscalls | diff -u prepare-worker-syscalls -
+  after_script:
+    - if [[ "$CI_JOB_STATUS" == "failed" ]]; then
+        printf "The x86_64 syscalls used by the worker binaries have changed. Please review if this is expected and update polkadot/scripts/list-syscalls/*-worker-syscalls as needed.\n";
+      fi
+  allow_failure: true # TODO: remove this once we have an idea how often the syscall lists will change

polkadot/scripts/list-syscalls/execute-worker-syscalls

@@ -0,0 +1,74 @@
+0 (read)
+1 (write)
+2 (open)
+3 (close)
+4 (stat)
+5 (fstat)
+7 (poll)
+8 (lseek)
+9 (mmap)
+10 (mprotect)
+11 (munmap)
+12 (brk)
+13 (rt_sigaction)
+14 (rt_sigprocmask)
+15 (rt_sigreturn)
+16 (ioctl)
+19 (readv)
+20 (writev)
+24 (sched_yield)
+25 (mremap)
+28 (madvise)
+39 (getpid)
+41 (socket)
+42 (connect)
+45 (recvfrom)
+46 (sendmsg)
+53 (socketpair)
+56 (clone)
+60 (exit)
+61 (wait4)
+62 (kill)
+72 (fcntl)
+79 (getcwd)
+80 (chdir)
+82 (rename)
+83 (mkdir)
+87 (unlink)
+89 (readlink)
+96 (gettimeofday)
+97 (getrlimit)
+99 (sysinfo)
+102 (getuid)
+110 (getppid)
+131 (sigaltstack)
+140 (getpriority)
+141 (setpriority)
+144 (sched_setscheduler)
+157 (prctl)
+158 (arch_prctl)
+165 (mount)
+166 (umount2)
+200 (tkill)
+202 (futex)
+204 (sched_getaffinity)
+213 (epoll_create)
+217 (getdents64)
+218 (set_tid_address)
+228 (clock_gettime)
+230 (clock_nanosleep)
+231 (exit_group)
+232 (epoll_wait)
+233 (epoll_ctl)
+257 (openat)
+262 (newfstatat)
+263 (unlinkat)
+272 (unshare)
+273 (set_robust_list)
+281 (epoll_pwait)
+284 (eventfd)
+290 (eventfd2)
+291 (epoll_create1)
+302 (prlimit64)
+318 (getrandom)
+319 (memfd_create)