Get the syscall lists for workers

Adds --only-list-syscalls option to list-syscalls.rb to produce these lists
paritytech · Sep 21, 2023 · 9d6d172 · 9d6d172
1 parent f635302
commit 9d6d172
Show file tree

Hide file tree

Showing 3 changed files with 182 additions and 19 deletions.
diff --git a/polkadot/scripts/list-syscalls/execute-worker-syscalls b/polkadot/scripts/list-syscalls/execute-worker-syscalls
@@ -0,0 +1,71 @@
+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)
+55 (getsockopt)
+56 (clone)
+60 (exit)
+61 (wait4)
+62 (kill)
+72 (fcntl)
+79 (getcwd)
+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)
+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)
+273 (set_robust_list)
+281 (epoll_pwait)
+284 (eventfd)
+290 (eventfd2)
+291 (epoll_create1)
+302 (prlimit64)
+318 (getrandom)
+319 (memfd_create)
diff --git a/polkadot/scripts/list-syscalls.rb → ...ot/scripts/list-syscalls/list-syscalls.rb b/polkadot/scripts/list-syscalls.rb → ...ot/scripts/list-syscalls/list-syscalls.rb
@@ -4,11 +4,14 @@
 #
 # Syntax: list-syscalls.rb <binary> [--only-used-syscalls]
 #
-# From: https://gist.github.com/koute/166f82bfee5e27324077891008fca6eb
+# Author: @koute
+# Source: https://gist.github.com/koute/166f82bfee5e27324077891008fca6eb
 
 require 'shellwords'
 require 'set'
 
+SYNTAX_STRING = 'Syntax: list-syscalls.rb <binary> [--only-used-syscalls]'.freeze
+
 # Generated from `libc` using the following regex:
 #   'pub const SYS_([a-z0-9_]+): ::c_long = (\d+);'
 #   '    \2 => "\1",'
@@ -455,18 +458,29 @@
 REG_MAP = (REGS_R64.map { |r| [r, r] } + REGS_R32.zip(REGS_R64) + REGS_R16.zip(REGS_R64) + REGS_R8.zip(REGS_R64)).to_h
 REGS_R = (REGS_R64 + REGS_R32 + REGS_R16 + REGS_R8).join('|')
 
-if ARGV.length != 1
-  warn 'Syntax: list-syscalls.rb <binary> [--only-used-syscalls]'
+if ARGV.empty?
+  warn SYNTAX_STRING
   exit 1
 end
 
-raise "no such file: #{ARGV[0]}" unless File.exist? ARGV[0]
+file_path = ARGV[0]
+raise "no such file: #{file_path}" unless File.exist? file_path
 
-puts 'Running objdump...'
-dump = `objdump -wd -j .text -M intel #{ARGV[0].shellescape}`
+only_used_syscalls = false
+ARGV[1..].each do |arg|
+  if arg == '--only-used-syscalls'
+    only_used_syscalls = true
+  else
+    warn "invalid argument '#{arg}':\n#{SYNTAX_STRING}"
+    exit 1
+  end
+end
+
+puts 'Running objdump...' unless only_used_syscalls
+dump = `objdump -wd -j .text -M intel #{file_path.shellescape}`
 raise 'objdump failed' unless $?.exitstatus == 0
 
-puts 'Parsing objdump output...'
+puts 'Parsing objdump output...' unless only_used_syscalls
 current_fn = nil
 code_for_fn = {}
 fns_with_syscall = Set.new
@@ -490,8 +504,10 @@
   fns_with_indirect_syscall.add(current_fn) if code =~ /<(syscall|__syscall_cp)>/
 end
 
-puts "Found #{fns_with_syscall.length} functions doing direct syscalls"
-puts "Found #{fns_with_indirect_syscall.length} functions doing indirect syscalls"
+unless only_used_syscalls
+  puts "Found #{fns_with_syscall.length} functions doing direct syscalls"
+  puts "Found #{fns_with_indirect_syscall.length} functions doing indirect syscalls"
+end
 
 syscalls_for_fn = {}
 not_found_count = 0
@@ -570,16 +586,20 @@
   end
 end
 
-puts 'Functions per syscall:'
-fns_for_syscall.sort_by { |sc, _| sc }.each do |syscall, fn_names|
-  fn_names = fn_names.sort.uniq
+if only_used_syscalls
+  puts syscalls_for_fn.values.flatten.sort.uniq.map { |sc| SYSCALLS[sc] || sc }.join("\n")
+else
+  puts 'Functions per syscall:'
+  fns_for_syscall.sort_by { |sc, _| sc }.each do |syscall, fn_names|
+    fn_names = fn_names.sort.uniq
 
-  puts "    #{SYSCALLS[syscall] || syscall} [#{fn_names.length} functions]"
-  fn_names.each do |fn_name|
-    puts "        #{fn_name}"
+    puts "    #{SYSCALLS[syscall] || syscall} [#{fn_names.length} functions]"
+    fn_names.each do |fn_name|
+      puts "        #{fn_name}"
+    end
   end
-end
 
-puts
-puts 'Used syscalls:'
-puts '    ' + syscalls_for_fn.values.flatten.sort.uniq.map { |sc| SYSCALLS[sc] || sc }.join("\n    ")
+  puts
+  puts 'Used syscalls:'
+  puts '    ' + syscalls_for_fn.values.flatten.sort.uniq.map { |sc| SYSCALLS[sc] || sc }.join("\n    ")
+end
diff --git a/polkadot/scripts/list-syscalls/prepare-worker-syscalls b/polkadot/scripts/list-syscalls/prepare-worker-syscalls
@@ -0,0 +1,72 @@
+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)
+55 (getsockopt)
+56 (clone)
+60 (exit)
+61 (wait4)
+62 (kill)
+72 (fcntl)
+79 (getcwd)
+82 (rename)
+83 (mkdir)
+87 (unlink)
+89 (readlink)
+96 (gettimeofday)
+97 (getrlimit)
+98 (getrusage)
+99 (sysinfo)
+102 (getuid)
+110 (getppid)
+131 (sigaltstack)
+140 (getpriority)
+141 (setpriority)
+144 (sched_setscheduler)
+157 (prctl)
+158 (arch_prctl)
+200 (tkill)
+202 (futex)
+203 (sched_setaffinity)
+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)
+273 (set_robust_list)
+281 (epoll_pwait)
+284 (eventfd)
+290 (eventfd2)
+291 (epoll_create1)
+302 (prlimit64)
+309 (getcpu)
+318 (getrandom)