X-Git-Url: http://review.tizen.org/git/?a=blobdiff_plain;f=scripts%2Fcheckpatch.pl;h=62b764f6c3835839f0175be7dcae5318c12b01df;hb=HEAD;hp=9544e57352b325b381a4cc599df09df377e0bf88;hpb=621e09cb3bf7e6d4fce9dd5e6de97e057adebc3a;p=platform%2Fkernel%2Fu-boot.git diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 9544e57..62b764f 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -23,6 +23,9 @@ my $V = '0.32'; use Getopt::Long qw(:config no_auto_abbrev); my $quiet = 0; +my $verbose = 0; +my %verbose_messages = (); +my %verbose_emitted = (); my $tree = 1; my $chk_signoff = 1; my $chk_patch = 1; @@ -43,6 +46,8 @@ my $list_types = 0; my $fix = 0; my $fix_inplace = 0; my $root; +my $gitroot = $ENV{'GIT_DIR'}; +$gitroot = ".git" if !defined($gitroot); my %debug; my %camelcase = (); my %use_type = (); @@ -58,14 +63,17 @@ my $min_conf_desc_length = 4; my $spelling_file = "$D/spelling.txt"; my $codespell = 0; my $codespellfile = "/usr/share/codespell/dictionary.txt"; +my $user_codespellfile = ""; my $conststructsfile = "$D/const_structs.checkpatch"; -my $typedefsfile = ""; my $u_boot = 0; +my $docsfile = "$D/../doc/develop/checkpatch.rst"; +my $typedefsfile; my $color = "auto"; my $allow_c99_comments = 1; # Can be overridden by --ignore C99_COMMENT_TOLERANCE # git output parsing needs US English output, so first set backtick child process LANGUAGE my $git_command ='export LANGUAGE=en_US.UTF-8; git'; my $tabsize = 8; +my ${CONFIG_} = "CONFIG_"; sub help { my ($exitcode) = @_; @@ -76,6 +84,7 @@ Version: $V Options: -q, --quiet quiet + -v, --verbose verbose mode --no-tree run without a kernel tree --no-signoff do not check for 'Signed-off-by' line --patch treat FILE as patchfile (default) @@ -123,12 +132,14 @@ Options: --ignore-perl-version override checking of perl version. expect runtime errors. --codespell Use the codespell dictionary for spelling/typos - (default:/usr/share/codespell/dictionary.txt) + (default:$codespellfile) --codespellfile Use this codespell dictionary --typedefsfile Read additional types from this file --color[=WHEN] Use colors 'always', 'never', or only when output is a terminal ('auto'). Default is 'auto'. --u-boot Run additional checks for U-Boot + --kconfig-prefix=WORD use WORD as a prefix for Kconfig symbols (default + ${CONFIG_}) -h, --help, --version display this help and exit When FILE is - read standard input. @@ -155,15 +166,51 @@ sub list_types { my $text = <$script>; close($script); - my @types = (); + my %types = (); # Also catch when type or level is passed through a variable - for ($text =~ /(?:(?:\bCHK|\bWARN|\bERROR|&\{\$msg_level})\s*\(|\$msg_type\s*=)\s*"([^"]+)"/g) { - push (@types, $_); + while ($text =~ /(?:(\bCHK|\bWARN|\bERROR|&\{\$msg_level})\s*\(|\$msg_type\s*=)\s*"([^"]+)"/g) { + if (defined($1)) { + if (exists($types{$2})) { + $types{$2} .= ",$1" if ($types{$2} ne $1); + } else { + $types{$2} = $1; + } + } else { + $types{$2} = "UNDETERMINED"; + } } - @types = sort(uniq(@types)); + print("#\tMessage type\n\n"); - foreach my $type (@types) { + if ($color) { + print(" ( Color coding: "); + print(RED . "ERROR" . RESET); + print(" | "); + print(YELLOW . "WARNING" . RESET); + print(" | "); + print(GREEN . "CHECK" . RESET); + print(" | "); + print("Multiple levels / Undetermined"); + print(" )\n\n"); + } + + foreach my $type (sort keys %types) { + my $orig_type = $type; + if ($color) { + my $level = $types{$type}; + if ($level eq "ERROR") { + $type = RED . $type . RESET; + } elsif ($level eq "WARN") { + $type = YELLOW . $type . RESET; + } elsif ($level eq "CHK") { + $type = GREEN . $type . RESET; + } + } print(++$count . "\t" . $type . "\n"); + if ($verbose && exists($verbose_messages{$orig_type})) { + my $message = $verbose_messages{$orig_type}; + $message =~ s/\n/\n\t/g; + print("\t" . $message . "\n\n"); + } } exit($exitcode); @@ -195,6 +242,46 @@ if (-f $conf) { unshift(@ARGV, @conf_args) if @conf_args; } +sub load_docs { + open(my $docs, '<', "$docsfile") + or warn "$P: Can't read the documentation file $docsfile $!\n"; + + my $type = ''; + my $desc = ''; + my $in_desc = 0; + + while (<$docs>) { + chomp; + my $line = $_; + $line =~ s/\s+$//; + + if ($line =~ /^\s*\*\*(.+)\*\*$/) { + if ($desc ne '') { + $verbose_messages{$type} = trim($desc); + } + $type = $1; + $desc = ''; + $in_desc = 1; + } elsif ($in_desc) { + if ($line =~ /^(?:\s{4,}|$)/) { + $line =~ s/^\s{4}//; + $desc .= $line; + $desc .= "\n"; + } else { + $verbose_messages{$type} = trim($desc); + $type = ''; + $desc = ''; + $in_desc = 0; + } + } + } + + if ($desc ne '') { + $verbose_messages{$type} = trim($desc); + } + close($docs); +} + # Perl's Getopt::Long allows options to take optional arguments after a space. # Prevent --color by itself from consuming other arguments foreach (@ARGV) { @@ -205,6 +292,7 @@ foreach (@ARGV) { GetOptions( 'q|quiet+' => \$quiet, + 'v|verbose!' => \$verbose, 'tree!' => \$tree, 'signoff!' => \$chk_signoff, 'patch!' => \$chk_patch, @@ -232,18 +320,58 @@ GetOptions( 'debug=s' => \%debug, 'test-only=s' => \$tst_only, 'codespell!' => \$codespell, - 'codespellfile=s' => \$codespellfile, + 'codespellfile=s' => \$user_codespellfile, 'typedefsfile=s' => \$typedefsfile, 'u-boot' => \$u_boot, 'color=s' => \$color, 'no-color' => \$color, #keep old behaviors of -nocolor 'nocolor' => \$color, #keep old behaviors of -nocolor + 'kconfig-prefix=s' => \${CONFIG_}, 'h|help' => \$help, 'version' => \$help -) or help(1); +) or $help = 2; + +if ($user_codespellfile) { + # Use the user provided codespell file unconditionally + $codespellfile = $user_codespellfile; +} elsif (!(-f $codespellfile)) { + # If /usr/share/codespell/dictionary.txt is not present, try to find it + # under codespell's install directory: /data/dictionary.txt + if (($codespell || $help) && which("codespell") ne "" && which("python") ne "") { + my $python_codespell_dict = << "EOF"; + +import os.path as op +import codespell_lib +codespell_dir = op.dirname(codespell_lib.__file__) +codespell_file = op.join(codespell_dir, 'data', 'dictionary.txt') +print(codespell_file, end='') +EOF + + my $codespell_dict = `python -c "$python_codespell_dict" 2> /dev/null`; + $codespellfile = $codespell_dict if (-f $codespell_dict); + } +} + +# $help is 1 if either -h, --help or --version is passed as option - exitcode: 0 +# $help is 2 if invalid option is passed - exitcode: 1 +help($help - 1) if ($help); -help(0) if ($help); +die "$P: --git cannot be used with --file or --fix\n" if ($git && ($file || $fix)); +die "$P: --verbose cannot be used with --terse\n" if ($verbose && $terse); +if ($color =~ /^[01]$/) { + $color = !$color; +} elsif ($color =~ /^always$/i) { + $color = 1; +} elsif ($color =~ /^never$/i) { + $color = 0; +} elsif ($color =~ /^auto$/i) { + $color = (-t STDOUT); +} else { + die "$P: Invalid color mode: $color\n"; +} + +load_docs() if ($verbose); list_types(0) if ($list_types); $fix = 1 if ($fix_inplace); @@ -263,20 +391,8 @@ if ($#ARGV < 0) { push(@ARGV, '-'); } -if ($color =~ /^[01]$/) { - $color = !$color; -} elsif ($color =~ /^always$/i) { - $color = 1; -} elsif ($color =~ /^never$/i) { - $color = 0; -} elsif ($color =~ /^auto$/i) { - $color = (-t STDOUT); -} else { - die "Invalid color mode: $color\n"; -} - # skip TAB size 1 to avoid additional checks on $tabsize - 1 -die "Invalid TAB size: $tabsize\n" if ($tabsize < 2); +die "$P: Invalid TAB size: $tabsize\n" if ($tabsize < 2); sub hash_save_array_words { my ($hashRef, $arrayRef) = @_; @@ -377,6 +493,7 @@ our $InitAttribute = qr{$InitAttributeData|$InitAttributeConst|$InitAttributeIni # We need \b after 'init' otherwise 'initconst' will cause a false positive in a check our $Attribute = qr{ const| + volatile| __percpu| __nocast| __safe| @@ -399,7 +516,8 @@ our $Attribute = qr{ ____cacheline_aligned| ____cacheline_aligned_in_smp| ____cacheline_internodealigned_in_smp| - __weak + __weak| + __alloc_size\s*\(\s*\d+\s*(?:,\s*\d+\s*)?\) }x; our $Modifier; our $Inline = qr{inline|__always_inline|noinline|__inline|__inline__}; @@ -411,7 +529,7 @@ our $Binary = qr{(?i)0b[01]+$Int_type?}; our $Hex = qr{(?i)0x[0-9a-f]+$Int_type?}; our $Int = qr{[0-9]+$Int_type?}; our $Octal = qr{0[0-7]+$Int_type?}; -our $String = qr{"[X\t]*"}; +our $String = qr{(?:\b[Lu])?"[X\t]*"}; our $Float_hex = qr{(?i)0x[0-9a-f]+p-?[0-9]+[fl]?}; our $Float_dec = qr{(?i)(?:[0-9]+\.[0-9]*|[0-9]*\.[0-9]+)(?:e-?[0-9]+)?[fl]?}; our $Float_int = qr{(?i)[0-9]+e-?[0-9]+[fl]?}; @@ -483,7 +601,7 @@ our $logFunctions = qr{(?x: our $allocFunctions = qr{(?x: (?:(?:devm_)? - (?:kv|k|v)[czm]alloc(?:_node|_array)? | + (?:kv|k|v)[czm]alloc(?:_array)?(?:_node)? | kstrdup(?:_const)? | kmemdup(?:_nul)?) | (?:\w+)?alloc_skb(?:_ip_align)? | @@ -503,6 +621,88 @@ our $signature_tags = qr{(?xi: Cc: )}; +our $tracing_logging_tags = qr{(?xi: + [=-]*> | + <[=-]* | + \[ | + \] | + start | + called | + entered | + entry | + enter | + in | + inside | + here | + begin | + exit | + end | + done | + leave | + completed | + out | + return | + [\.\!:\s]* +)}; + +sub edit_distance_min { + my (@arr) = @_; + my $len = scalar @arr; + if ((scalar @arr) < 1) { + # if underflow, return + return; + } + my $min = $arr[0]; + for my $i (0 .. ($len-1)) { + if ($arr[$i] < $min) { + $min = $arr[$i]; + } + } + return $min; +} + +sub get_edit_distance { + my ($str1, $str2) = @_; + $str1 = lc($str1); + $str2 = lc($str2); + $str1 =~ s/-//g; + $str2 =~ s/-//g; + my $len1 = length($str1); + my $len2 = length($str2); + # two dimensional array storing minimum edit distance + my @distance; + for my $i (0 .. $len1) { + for my $j (0 .. $len2) { + if ($i == 0) { + $distance[$i][$j] = $j; + } elsif ($j == 0) { + $distance[$i][$j] = $i; + } elsif (substr($str1, $i-1, 1) eq substr($str2, $j-1, 1)) { + $distance[$i][$j] = $distance[$i - 1][$j - 1]; + } else { + my $dist1 = $distance[$i][$j - 1]; #insert distance + my $dist2 = $distance[$i - 1][$j]; # remove + my $dist3 = $distance[$i - 1][$j - 1]; #replace + $distance[$i][$j] = 1 + edit_distance_min($dist1, $dist2, $dist3); + } + } + } + return $distance[$len1][$len2]; +} + +sub find_standard_signature { + my ($sign_off) = @_; + my @standard_signature_tags = ( + 'Signed-off-by:', 'Co-developed-by:', 'Acked-by:', 'Tested-by:', + 'Reviewed-by:', 'Reported-by:', 'Suggested-by:' + ); + foreach my $signature (@standard_signature_tags) { + return $signature if (get_edit_distance($sign_off, $signature) <= 2); + } + + return ""; +} + our @typeListMisordered = ( qr{char\s+(?:un)?signed}, qr{int\s+(?:(?:un)?signed\s+)?short\s}, @@ -591,6 +791,8 @@ our @mode_permission_funcs = ( ["__ATTR", 2], ); +my $word_pattern = '\b[A-Z]?[a-z]{2,}\b'; + #Create a search pattern for all these functions to speed up a loop below our $mode_perms_search = ""; foreach my $entry (@mode_permission_funcs) { @@ -759,7 +961,7 @@ sub read_words { next; } - $$wordsRef .= '|' if ($$wordsRef ne ""); + $$wordsRef .= '|' if (defined $$wordsRef); $$wordsRef .= $line; } close($file); @@ -769,16 +971,18 @@ sub read_words { return 0; } -my $const_structs = ""; -read_words(\$const_structs, $conststructsfile) - or warn "No structs that should be const will be found - file '$conststructsfile': $!\n"; +my $const_structs; +if (show_type("CONST_STRUCT")) { + read_words(\$const_structs, $conststructsfile) + or warn "No structs that should be const will be found - file '$conststructsfile': $!\n"; +} -my $typeOtherTypedefs = ""; -if (length($typedefsfile)) { +if (defined($typedefsfile)) { + my $typeOtherTypedefs; read_words(\$typeOtherTypedefs, $typedefsfile) or warn "No additional types will be considered - file '$typedefsfile': $!\n"; + $typeTypedefs .= '|' . $typeOtherTypedefs if (defined $typeOtherTypedefs); } -$typeTypedefs .= '|' . $typeOtherTypedefs if ($typeOtherTypedefs ne ""); sub build_types { my $mods = "(?x: \n" . join("|\n ", (@modifierList, @modifierListFile)) . "\n)"; @@ -843,10 +1047,16 @@ our $FuncArg = qr{$Typecast{0,1}($LvalOrFunc|$Constant|$String)}; our $declaration_macros = qr{(?x: (?:$Storage\s+)?(?:[A-Z_][A-Z0-9]*_){0,2}(?:DEFINE|DECLARE)(?:_[A-Z0-9]+){1,6}\s*\(| (?:$Storage\s+)?[HLP]?LIST_HEAD\s*\(| - (?:$Storage\s+)?${Type}\s+uninitialized_var\s*\(| (?:SKCIPHER_REQUEST|SHASH_DESC|AHASH_REQUEST)_ON_STACK\s*\( )}; +our %allow_repeated_words = ( + add => '', + added => '', + bad => '', + be => '', +); + sub deparenthesize { my ($string) = @_; return "" if (!defined($string)); @@ -904,10 +1114,10 @@ sub is_maintained_obsolete { sub is_SPDX_License_valid { my ($license) = @_; - return 1 if (!$tree || which("python") eq "" || !(-e "$root/scripts/spdxcheck.py") || !(-e "$root/.git")); + return 1 if (!$tree || which("python3") eq "" || !(-x "$root/scripts/spdxcheck.py") || !(-e "$gitroot")); my $root_path = abs_path($root); - my $status = `cd "$root_path"; echo "$license" | python scripts/spdxcheck.py -`; + my $status = `cd "$root_path"; echo "$license" | scripts/spdxcheck.py -`; return 0 if ($status ne ""); return 1; } @@ -922,7 +1132,7 @@ sub seed_camelcase_includes { $camelcase_seeded = 1; - if (-e ".git") { + if (-e "$gitroot") { my $git_last_include_commit = `${git_command} log --no-merges --pretty=format:"%h%n" -1 -- include`; chomp $git_last_include_commit; $camelcase_cache = ".checkpatch-camelcase.git.$git_last_include_commit"; @@ -950,7 +1160,7 @@ sub seed_camelcase_includes { return; } - if (-e ".git") { + if (-e "$gitroot") { $files = `${git_command} ls-files "include/*.h"`; @include_files = split('\n', $files); } @@ -970,10 +1180,20 @@ sub seed_camelcase_includes { } } +sub git_is_single_file { + my ($filename) = @_; + + return 0 if ((which("git") eq "") || !(-e "$gitroot")); + + my $output = `${git_command} ls-files -- $filename 2>/dev/null`; + my $count = $output =~ tr/\n//; + return $count eq 1 && $output =~ m{^${filename}$}; +} + sub git_commit_info { my ($commit, $id, $desc) = @_; - return ($id, $desc) if ((which("git") eq "") || !(-e ".git")); + return ($id, $desc) if ((which("git") eq "") || !(-e "$gitroot")); my $output = `${git_command} log --no-color --format='%H %s' -1 $commit 2>&1`; $output =~ s/^\s*//gm; @@ -991,7 +1211,8 @@ sub git_commit_info { # git log --format='%H %s' -1 $line | # echo "commit $(cut -c 1-12,41-)" # done - } elsif ($lines[0] =~ /^fatal: ambiguous argument '$commit': unknown revision or path not in the working tree\./) { + } elsif ($lines[0] =~ /^fatal: ambiguous argument '$commit': unknown revision or path not in the working tree\./ || + $lines[0] =~ /^fatal: bad object $commit/) { $id = undef; } else { $id = substr($lines[0], 0, 12); @@ -1012,7 +1233,7 @@ my $fixlinenr = -1; # If input is git commits, extract all commits from the commit expressions. # For example, HEAD-3 means we need check 'HEAD, HEAD~1, HEAD~2'. -die "$P: No git repository found\n" if ($git && !-e ".git"); +die "$P: No git repository found\n" if ($git && !-e "$gitroot"); if ($git) { my @commits = (); @@ -1043,6 +1264,9 @@ my $vname; $allow_c99_comments = !defined $ignore_type{"C99_COMMENT_TOLERANCE"}; for my $filename (@ARGV) { my $FILE; + my $is_git_file = git_is_single_file($filename); + my $oldfile = $file; + $file = 1 if ($is_git_file); if ($git) { open($FILE, '-|', "git format-patch -M --stdout -1 $filename") || die "$P: $filename: git format-patch failed - $!\n"; @@ -1065,6 +1289,7 @@ for my $filename (@ARGV) { while (<$FILE>) { chomp; push(@rawlines, $_); + $vname = qq("$1") if ($filename eq '-' && $_ =~ m/^Subject:\s+(.+)/i); } close($FILE); @@ -1086,6 +1311,7 @@ for my $filename (@ARGV) { @modifierListFile = (); @typeListFile = (); build_types(); + $file = $oldfile if ($is_git_file); } if (!$quiet) { @@ -1131,6 +1357,7 @@ sub parse_email { my ($formatted_email) = @_; my $name = ""; + my $quoted = ""; my $name_comment = ""; my $address = ""; my $comment = ""; @@ -1162,14 +1389,20 @@ sub parse_email { } } - $name = trim($name); - $name =~ s/^\"|\"$//g; - $name =~ s/(\s*\([^\)]+\))\s*//; - if (defined($1)) { - $name_comment = trim($1); + # Extract comments from names excluding quoted parts + # "John D. (Doe)" - Do not extract + if ($name =~ s/\"(.+)\"//) { + $quoted = $1; } + while ($name =~ s/\s*($balanced_parens)\s*/ /) { + $name_comment .= trim($1); + } + $name =~ s/^[ \"]+|[ \"]+$//g; + $name = trim("$quoted $name"); + $address = trim($address); $address =~ s/^\<|\>$//g; + $comment = trim($comment); if ($name =~ /[^\w \-]/i) { ##has "must quote" chars $name =~ s/(?"; + $formatted_email = "$name$name_comment <$address>"; } - + $formatted_email .= "$comment"; return $formatted_email; } @@ -1206,7 +1444,7 @@ sub reformat_email { my ($email) = @_; my ($email_name, $name_comment, $email_address, $comment) = parse_email($email); - return format_email($email_name, $email_address); + return format_email($email_name, $name_comment, $email_address, $comment); } sub same_email_addresses { @@ -1216,7 +1454,9 @@ sub same_email_addresses { my ($email2_name, $name2_comment, $email2_address, $comment2) = parse_email($email2); return $email1_name eq $email2_name && - $email1_address eq $email2_address; + $email1_address eq $email2_address && + $name1_comment eq $name2_comment && + $comment1 eq $comment2; } sub which { @@ -1681,8 +1921,16 @@ sub ctx_statement_level { sub ctx_locate_comment { my ($first_line, $end_line) = @_; + # If c99 comment on the current line, or the line before or after + my ($current_comment) = ($rawlines[$end_line - 1] =~ m@^\+.*(//.*$)@); + return $current_comment if (defined $current_comment); + ($current_comment) = ($rawlines[$end_line - 2] =~ m@^[\+ ].*(//.*$)@); + return $current_comment if (defined $current_comment); + ($current_comment) = ($rawlines[$end_line] =~ m@^[\+ ].*(//.*$)@); + return $current_comment if (defined $current_comment); + # Catch a comment on the end of the line itself. - my ($current_comment) = ($rawlines[$end_line - 1] =~ m@.*(/\*.*\*/)\s*(?:\\\s*)?$@); + ($current_comment) = ($rawlines[$end_line - 1] =~ m@.*(/\*.*\*/)\s*(?:\\\s*)?$@); return $current_comment if (defined $current_comment); # Look through the context and try and figure out if there is a @@ -2076,7 +2324,16 @@ sub report { splice(@lines, 1, 1); $output = join("\n", @lines); } - $output = (split('\n', $output))[0] . "\n" if ($terse); + + if ($terse) { + $output = (split('\n', $output))[0] . "\n"; + } + + if ($verbose && exists($verbose_messages{$type}) && + !exists($verbose_emitted{$type})) { + $output .= $verbose_messages{$type} . "\n\n"; + $verbose_emitted{$type} = 1; + } push(our @report, $output); @@ -2320,9 +2577,28 @@ sub get_raw_comment { return $comment; } +# Args: +# line: Patch line to check +# auto: Auto variable name, e.g. "per_child_auto" +# suffix: Suffix to expect on member, e.g. "_priv" +# warning: Warning name, e.g. "PRIV_AUTO" +sub u_boot_struct_name { + my ($line, $auto, $suffix, $warning, $herecurr) = @_; + + # Use _priv as a suffix for the device-private data struct + if ($line =~ /^\+\s*\.${auto}\s*=\s*sizeof\(struct\((\w+)\).*/) { + my $struct_name = $1; + if ($struct_name !~ /^\w+${suffix}/) { + WARN($warning, + "struct \'$struct_name\' should have a ${suffix} suffix\n" + . $herecurr); + } + } +} + # Checks specific to U-Boot sub u_boot_line { - my ($realfile, $line, $herecurr) = @_; + my ($realfile, $line, $rawline, $herecurr) = @_; # ask for a test if a new uclass ID is added if ($realfile =~ /uclass-id.h/ && $line =~ /^\+/) { @@ -2343,18 +2619,84 @@ sub u_boot_line { } # use if instead of #if - if ($line =~ /^\+#if.*CONFIG.*/) { + if ($realfile =~ /\.c$/ && $line =~ /^\+#if.*CONFIG.*/) { WARN("PREFER_IF", "Use 'if (IS_ENABLED(CONFIG...))' instead of '#if or #ifdef' where possible\n" . $herecurr); } - # use defconfig to manage CONFIG_CMD options - if ($line =~ /\+\s*#\s*(define|undef)\s+(CONFIG_CMD\w*)\b/) { - ERROR("DEFINE_CONFIG_CMD", - "All commands are managed by Kconfig\n" . $herecurr); + # prefer strl(cpy|cat) over strn(cpy|cat) + if ($line =~ /\bstrn(cpy|cat)\s*\(/) { + WARN("STRL", + "strl$1 is preferred over strn$1 because it always produces a nul-terminated string\n" . $herecurr); + } + + # use Kconfig for all CONFIG symbols + if ($line =~ /\+\s*#\s*(define|undef)\s+(CONFIG_\w*)\b/) { + ERROR("DEFINE_CONFIG_SYM", + "All CONFIG symbols are managed by Kconfig\n" . $herecurr); + } + + # Don't put common.h and dm.h in header files + if ($realfile =~ /\.h$/ && $rawline =~ /^\+#include\s*<(common|dm)\.h>*/) { + ERROR("BARRED_INCLUDE_IN_HDR", + "Avoid including common.h and dm.h in header files\n" . $herecurr); + } + + # Do not disable fdt / initrd relocation + if ($rawline =~ /^\+.*(fdt|initrd)_high=0xffffffff/) { + ERROR("DISABLE_FDT_OR_INITRD_RELOC", + "fdt or initrd relocation disabled at boot time\n" . $herecurr); + } + + # make sure 'skip_board_fixup' is not + if ($rawline =~ /.*skip_board_fixup.*/) { + ERROR("SKIP_BOARD_FIXUP", + "Avoid setting skip_board_fixup env variable\n" . $herecurr); + } + + # Do not use CONFIG_ prefix in CONFIG_IS_ENABLED() calls + if ($line =~ /^\+.*CONFIG_IS_ENABLED\(CONFIG_\w*\).*/) { + ERROR("CONFIG_IS_ENABLED_CONFIG", + "CONFIG_IS_ENABLED() takes values without the CONFIG_ prefix\n" . $herecurr); + } + + # Use _priv as a suffix for the device-private data struct + if ($line =~ /^\+\s*\.priv_auto\s*=\s*sizeof\(struct\((\w+)\).*/) { + my $struct_name = $1; + if ($struct_name !~ /^\w+_priv/) { + WARN("PRIV_AUTO", "struct \'$struct_name\' should have a _priv suffix"); + } + } + + # Check struct names for the 'auto' members of struct driver + u_boot_struct_name($line, "priv_auto", "_priv", "PRIV_AUTO", $herecurr); + u_boot_struct_name($line, "plat_auto", "_plat", "PLAT_AUTO", $herecurr); + u_boot_struct_name($line, "per_child_auto", "_priv", "CHILD_PRIV_AUTO", $herecurr); + u_boot_struct_name($line, "per_child_plat_auto", "_plat", + "CHILD_PLAT_AUTO", $herecurr); + + # Now the ones for struct uclass, skipping those in common with above + u_boot_struct_name($line, "per_device_auto", "_priv", + "DEVICE_PRIV_AUTO", $herecurr); + u_boot_struct_name($line, "per_device_plat_auto", "_plat", + "DEVICE_PLAT_AUTO", $herecurr); + + # Avoid using the pre-schema driver model tags + if ($line =~ /^\+.*u-boot,dm-.*/) { + ERROR("PRE_SCHEMA", + "Driver model schema uses 'bootph-...' tags now\n" . $herecurr); } } +sub exclude_global_initialisers { + my ($realfile) = @_; + + # Do not check for BPF programs (tools/testing/selftests/bpf/progs/*.c, samples/bpf/*_kern.c, *.bpf.c). + return $realfile =~ m@^tools/testing/selftests/bpf/progs/.*\.c$@ || + $realfile =~ m@^samples/bpf/.*_kern\.c$@ || + $realfile =~ m@/bpf/.*\.bpf\.c$@; +} + sub process { my $filename = shift; @@ -2373,6 +2715,7 @@ sub process { my $signoff = 0; my $author = ''; my $authorsignoff = 0; + my $author_sob = ''; my $is_patch = 0; my $is_binding_patch = -1; my $in_header_lines = $file ? 0 : 1; @@ -2386,6 +2729,8 @@ sub process { my $reported_maintainer_file = 0; my $non_utf8_charset = 0; + my $last_git_commit_id_linenr = -1; + my $last_blank_line = 0; my $last_coalesced_string_linenr = -1; @@ -2436,7 +2781,7 @@ sub process { if ($rawline=~/^\+\+\+\s+(\S+)/) { $setup_docs = 0; - if ($1 =~ m@Documentation/admin-guide/kernel-parameters.rst$@) { + if ($1 =~ m@Documentation/admin-guide/kernel-parameters.txt$@) { $setup_docs = 1; } #next; @@ -2636,7 +2981,7 @@ sub process { if (($last_binding_patch != -1) && ($last_binding_patch ^ $is_binding_patch)) { WARN("DT_SPLIT_BINDING_PATCH", - "DT binding docs and includes should be a separate patch. See: Documentation/devicetree/bindings/submitting-patches.txt\n"); + "DT binding docs and includes should be a separate patch. See: Documentation/devicetree/bindings/submitting-patches.rst\n"); } } @@ -2665,8 +3010,8 @@ sub process { # Check if the commit log has what seems like a diff which can confuse patch if ($in_commit_log && !$commit_log_has_diff && - (($line =~ m@^\s+diff\b.*a/[\w/]+@ && - $line =~ m@^\s+diff\b.*a/([\w/]+)\s+b/$1\b@) || + (($line =~ m@^\s+diff\b.*a/([\w/]+)@ && + $line =~ m@^\s+diff\b.*a/[\w/]+\s+b/$1\b@) || $line =~ m@^\s*(?:\-\-\-\s+a/|\+\+\+\s+b/)@ || $line =~ m/^\s*\@\@ \-\d+,\d+ \+\d+,\d+ \@\@/)) { ERROR("DIFF_IN_COMMIT_MSG", @@ -2687,6 +3032,10 @@ sub process { # Check the patch for a From: if (decode("MIME-Header", $line) =~ /^From:\s*(.*)/) { $author = $1; + my $curline = $linenr; + while(defined($rawlines[$curline]) && ($rawlines[$curline++] =~ /^[ \t]\s*(.*)/)) { + $author .= $1; + } $author = encode("utf8", $author) if ($line =~ /=\?utf-8\?/i); $author =~ s/"//g; $author = reformat_email($author); @@ -2696,9 +3045,37 @@ sub process { if ($line =~ /^\s*signed-off-by:\s*(.*)/i) { $signoff++; $in_commit_log = 0; - if ($author ne '') { + if ($author ne '' && $authorsignoff != 1) { if (same_email_addresses($1, $author)) { $authorsignoff = 1; + } else { + my $ctx = $1; + my ($email_name, $email_comment, $email_address, $comment1) = parse_email($ctx); + my ($author_name, $author_comment, $author_address, $comment2) = parse_email($author); + + if (lc $email_address eq lc $author_address && $email_name eq $author_name) { + $author_sob = $ctx; + $authorsignoff = 2; + } elsif (lc $email_address eq lc $author_address) { + $author_sob = $ctx; + $authorsignoff = 3; + } elsif ($email_name eq $author_name) { + $author_sob = $ctx; + $authorsignoff = 4; + + my $address1 = $email_address; + my $address2 = $author_address; + + if ($address1 =~ /(\S+)\+\S+(\@.*)/) { + $address1 = "$1$2"; + } + if ($address2 =~ /(\S+)\+\S+(\@.*)/) { + $address2 = "$1$2"; + } + if ($address1 eq $address2) { + $authorsignoff = 5; + } + } } } } @@ -2725,8 +3102,17 @@ sub process { my $ucfirst_sign_off = ucfirst(lc($sign_off)); if ($sign_off !~ /$signature_tags/) { - WARN("BAD_SIGN_OFF", - "Non-standard signature: $sign_off\n" . $herecurr); + my $suggested_signature = find_standard_signature($sign_off); + if ($suggested_signature eq "") { + WARN("BAD_SIGN_OFF", + "Non-standard signature: $sign_off\n" . $herecurr); + } else { + if (WARN("BAD_SIGN_OFF", + "Non-standard signature: '$sign_off' - perhaps '$suggested_signature'?\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/$sign_off/$suggested_signature/; + } + } } if (defined $space_before && $space_before ne "") { if (WARN("BAD_SIGN_OFF", @@ -2755,7 +3141,7 @@ sub process { } my ($email_name, $name_comment, $email_address, $comment) = parse_email($email); - my $suggested_email = format_email(($email_name, $email_address)); + my $suggested_email = format_email(($email_name, $name_comment, $email_address, $comment)); if ($suggested_email eq "") { ERROR("BAD_SIGN_OFF", "Unrecognized email address: '$email'\n" . $herecurr); @@ -2766,8 +3152,76 @@ sub process { # Don't force email to have quotes # Allow just an angle bracketed address if (!same_email_addresses($email, $suggested_email)) { + if (WARN("BAD_SIGN_OFF", + "email address '$email' might be better as '$suggested_email'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$email\E/$suggested_email/; + } + } + + # Address part shouldn't have comments + my $stripped_address = $email_address; + $stripped_address =~ s/\([^\(\)]*\)//g; + if ($email_address ne $stripped_address) { + if (WARN("BAD_SIGN_OFF", + "address part of email should not have comments: '$email_address'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$email_address\E/$stripped_address/; + } + } + + # Only one name comment should be allowed + my $comment_count = () = $name_comment =~ /\([^\)]+\)/g; + if ($comment_count > 1) { WARN("BAD_SIGN_OFF", - "email address '$email' might be better as '$suggested_email$comment'\n" . $herecurr); + "Use a single name comment in email: '$email'\n" . $herecurr); + } + + + # stable@vger.kernel.org or stable@kernel.org shouldn't + # have an email name. In addition comments should strictly + # begin with a # + if ($email =~ /^.*stable\@(?:vger\.)?kernel\.org/i) { + if (($comment ne "" && $comment !~ /^#.+/) || + ($email_name ne "")) { + my $cur_name = $email_name; + my $new_comment = $comment; + $cur_name =~ s/[a-zA-Z\s\-\"]+//g; + + # Remove brackets enclosing comment text + # and # from start of comments to get comment text + $new_comment =~ s/^\((.*)\)$/$1/; + $new_comment =~ s/^\[(.*)\]$/$1/; + $new_comment =~ s/^[\s\#]+|\s+$//g; + + $new_comment = trim("$new_comment $cur_name") if ($cur_name ne $new_comment); + $new_comment = " # $new_comment" if ($new_comment ne ""); + my $new_email = "$email_address$new_comment"; + + if (WARN("BAD_STABLE_ADDRESS_STYLE", + "Invalid email format for stable: '$email', prefer '$new_email'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$email\E/$new_email/; + } + } + } elsif ($comment ne "" && $comment !~ /^(?:#.+|\(.+\))$/) { + my $new_comment = $comment; + + # Extract comment text from within brackets or + # c89 style /*...*/ comments + $new_comment =~ s/^\[(.*)\]$/$1/; + $new_comment =~ s/^\/\*(.*)\*\/$/$1/; + + $new_comment = trim($new_comment); + $new_comment =~ s/^[^\w]$//; # Single lettered comment with non word character is usually a typo + $new_comment = "($new_comment)" if ($new_comment ne ""); + my $new_email = format_email($email_name, $name_comment, $email_address, $new_comment); + + if (WARN("BAD_SIGN_OFF", + "Unexpected content after email: '$email', should be: '$new_email'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$email\E/$new_email/; + } } } @@ -2790,7 +3244,7 @@ sub process { } if (!defined $lines[$linenr]) { WARN("BAD_SIGN_OFF", - "Co-developed-by: must be immediately followed by Signed-off-by:\n" . "$here\n" . $rawline); + "Co-developed-by: must be immediately followed by Signed-off-by:\n" . "$here\n" . $rawline); } elsif ($rawlines[$linenr] !~ /^\s*signed-off-by:\s*(.*)/i) { WARN("BAD_SIGN_OFF", "Co-developed-by: must be immediately followed by Signed-off-by:\n" . "$here\n" . $rawline . "\n" .$rawlines[$linenr]); @@ -2810,8 +3264,11 @@ sub process { # Check for Gerrit Change-Ids not in any patch context if ($realfile eq '' && !$has_patch_separator && $line =~ /^\s*change-id:/i) { - ERROR("GERRIT_CHANGE_ID", - "Remove Gerrit Change-Id's before submitting upstream\n" . $herecurr); + if (ERROR("GERRIT_CHANGE_ID", + "Remove Gerrit Change-Id's before submitting upstream\n" . $herecurr) && + $fix) { + fix_delete_line($fixlinenr, $rawline); + } } # Check if the commit log is in a possible stack dump @@ -2833,8 +3290,8 @@ sub process { # file delta changes $line =~ /^\s*(?:[\w\.\-]+\/)++[\w\.\-]+:/ || # filename then : - $line =~ /^\s*(?:Fixes:|Link:)/i || - # A Fixes: or Link: line + $line =~ /^\s*(?:Fixes:|Link:|$signature_tags)/i || + # A Fixes: or Link: line or signature tag line $commit_log_possible_stack_dump)) { WARN("COMMIT_LOG_LONG_LINE", "Possible unwrapped commit description (prefer a maximum 75 chars per line)\n" . $herecurr); @@ -2847,11 +3304,30 @@ sub process { $commit_log_possible_stack_dump = 0; } +# Check for lines starting with a # + if ($in_commit_log && $line =~ /^#/) { + if (WARN("COMMIT_COMMENT_SYMBOL", + "Commit log lines starting with '#' are dropped by git as comments\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/^/ /; + } + } + # Check for git id commit length and improperly formed commit descriptions - if ($in_commit_log && !$commit_log_possible_stack_dump && +# A correctly formed commit description is: +# commit ("Complete commit subject") +# with the commit subject '("' prefix and '")' suffix +# This is a fairly compilicated block as it tests for what appears to be +# bare SHA-1 hash with minimum length of 5. It also avoids several types of +# possible SHA-1 matches. +# A commit match can span multiple lines so this block attempts to find a +# complete typical commit on a maximum of 3 lines + if ($perl_version_ok && + $in_commit_log && !$commit_log_possible_stack_dump && $line !~ /^\s*(?:Link|Patchwork|http|https|BugLink|base-commit):/i && $line !~ /^This reverts commit [0-9a-f]{7,40}/ && - ($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i || + (($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i || + ($line =~ /\bcommit\s*$/i && defined($rawlines[$linenr]) && $rawlines[$linenr] =~ /^\s*[0-9a-f]{5,}\b/i)) || ($line =~ /(?:\s|^)[0-9a-f]{12,40}(?:[\s"'\(\[]|$)/i && $line !~ /[\<\[][0-9a-f]{12,40}[\>\]]/i && $line !~ /\bfixes:\s*[0-9a-f]{12,40}/i))) { @@ -2861,49 +3337,56 @@ sub process { my $long = 0; my $case = 1; my $space = 1; - my $hasdesc = 0; - my $hasparens = 0; my $id = '0123456789ab'; my $orig_desc = "commit description"; my $description = ""; + my $herectx = $herecurr; + my $has_parens = 0; + my $has_quotes = 0; + + my $input = $line; + if ($line =~ /(?:\bcommit\s+[0-9a-f]{5,}|\bcommit\s*$)/i) { + for (my $n = 0; $n < 2; $n++) { + if ($input =~ /\bcommit\s+[0-9a-f]{5,}\s*($balanced_parens)/i) { + $orig_desc = $1; + $has_parens = 1; + # Always strip leading/trailing parens then double quotes if existing + $orig_desc = substr($orig_desc, 1, -1); + if ($orig_desc =~ /^".*"$/) { + $orig_desc = substr($orig_desc, 1, -1); + $has_quotes = 1; + } + last; + } + last if ($#lines < $linenr + $n); + $input .= " " . trim($rawlines[$linenr + $n]); + $herectx .= "$rawlines[$linenr + $n]\n"; + } + $herectx = $herecurr if (!$has_parens); + } - if ($line =~ /\b(c)ommit\s+([0-9a-f]{5,})\b/i) { + if ($input =~ /\b(c)ommit\s+([0-9a-f]{5,})\b/i) { $init_char = $1; $orig_commit = lc($2); - } elsif ($line =~ /\b([0-9a-f]{12,40})\b/i) { + $short = 0 if ($input =~ /\bcommit\s+[0-9a-f]{12,40}/i); + $long = 1 if ($input =~ /\bcommit\s+[0-9a-f]{41,}/i); + $space = 0 if ($input =~ /\bcommit [0-9a-f]/i); + $case = 0 if ($input =~ /\b[Cc]ommit\s+[0-9a-f]{5,40}[^A-F]/); + } elsif ($input =~ /\b([0-9a-f]{12,40})\b/i) { $orig_commit = lc($1); } - $short = 0 if ($line =~ /\bcommit\s+[0-9a-f]{12,40}/i); - $long = 1 if ($line =~ /\bcommit\s+[0-9a-f]{41,}/i); - $space = 0 if ($line =~ /\bcommit [0-9a-f]/i); - $case = 0 if ($line =~ /\b[Cc]ommit\s+[0-9a-f]{5,40}[^A-F]/); - if ($line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("([^"]+)"\)/i) { - $orig_desc = $1; - $hasparens = 1; - } elsif ($line =~ /\bcommit\s+[0-9a-f]{5,}\s*$/i && - defined $rawlines[$linenr] && - $rawlines[$linenr] =~ /^\s*\("([^"]+)"\)/) { - $orig_desc = $1; - $hasparens = 1; - } elsif ($line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("[^"]+$/i && - defined $rawlines[$linenr] && - $rawlines[$linenr] =~ /^\s*[^"]+"\)/) { - $line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("([^"]+)$/i; - $orig_desc = $1; - $rawlines[$linenr] =~ /^\s*([^"]+)"\)/; - $orig_desc .= " " . $1; - $hasparens = 1; - } - ($id, $description) = git_commit_info($orig_commit, $id, $orig_desc); if (defined($id) && - ($short || $long || $space || $case || ($orig_desc ne $description) || !$hasparens)) { + ($short || $long || $space || $case || ($orig_desc ne $description) || !$has_quotes) && + $last_git_commit_id_linenr != $linenr - 1) { ERROR("GIT_COMMIT_ID", - "Please use git commit description style 'commit <12+ chars of sha1> (\"\")' - ie: '${init_char}ommit $id (\"$description\")'\n" . $herecurr); + "Please use git commit description style 'commit <12+ chars of sha1> (\"<title line>\")' - ie: '${init_char}ommit $id (\"$description\")'\n" . $herectx); } + #don't report the next line if this line ends in commit and the sha1 hash is the next line + $last_git_commit_id_linenr = $linenr if ($line =~ /\bcommit\s*$/i); } # Check for added, moved or deleted files @@ -2923,7 +3406,7 @@ sub process { ($line =~ /^new file mode\s*\d+\s*$/) && ($realfile =~ m@^Documentation/devicetree/bindings/.*\.txt$@)) { WARN("DT_SCHEMA_BINDING_PATCH", - "DT bindings should be in DT schema format. See: Documentation/devicetree/writing-schema.rst\n"); + "DT bindings should be in DT schema format. See: Documentation/devicetree/bindings/writing-schema.rst\n"); } # Check for wrappage within a valid hunk of the file @@ -2987,15 +3470,18 @@ sub process { # Check for various typo / spelling mistakes if (defined($misspellings) && ($in_commit_log || $line =~ /^(?:\+|Subject:)/i)) { - while ($rawline =~ /(?:^|[^a-z@])($misspellings)(?:\b|$|[^a-z@])/gi) { + while ($rawline =~ /(?:^|[^\w\-'`])($misspellings)(?:[^\w\-'`]|$)/gi) { my $typo = $1; + my $blank = copy_spacing($rawline); + my $ptr = substr($blank, 0, $-[1]) . "^" x length($typo); + my $hereptr = "$hereline$ptr\n"; my $typo_fix = $spelling_fix{lc($typo)}; $typo_fix = ucfirst($typo_fix) if ($typo =~ /^[A-Z]/); $typo_fix = uc($typo_fix) if ($typo =~ /^[A-Z]+$/); my $msg_level = \&WARN; $msg_level = \&CHK if ($file); if (&{$msg_level}("TYPO_SPELLING", - "'$typo' may be misspelled - perhaps '$typo_fix'?\n" . $herecurr) && + "'$typo' may be misspelled - perhaps '$typo_fix'?\n" . $hereptr) && $fix) { $fixed[$fixlinenr] =~ s/(^|[^A-Za-z@])($typo)($|[^A-Za-z@])/$1$typo_fix$3/; } @@ -3013,6 +3499,60 @@ sub process { } } +# check for repeated words separated by a single space +# avoid false positive from list command eg, '-rw-r--r-- 1 root root' + if (($rawline =~ /^\+/ || $in_commit_log) && + $rawline !~ /[bcCdDlMnpPs\?-][rwxsStT-]{9}/) { + pos($rawline) = 1 if (!$in_commit_log); + while ($rawline =~ /\b($word_pattern) (?=($word_pattern))/g) { + + my $first = $1; + my $second = $2; + my $start_pos = $-[1]; + my $end_pos = $+[2]; + if ($first =~ /(?:struct|union|enum)/) { + pos($rawline) += length($first) + length($second) + 1; + next; + } + + next if (lc($first) ne lc($second)); + next if ($first eq 'long'); + + # check for character before and after the word matches + my $start_char = ''; + my $end_char = ''; + $start_char = substr($rawline, $start_pos - 1, 1) if ($start_pos > ($in_commit_log ? 0 : 1)); + $end_char = substr($rawline, $end_pos, 1) if ($end_pos < length($rawline)); + + next if ($start_char =~ /^\S$/); + next if (index(" \t.,;?!", $end_char) == -1); + + # avoid repeating hex occurrences like 'ff ff fe 09 ...' + if ($first =~ /\b[0-9a-f]{2,}\b/i) { + next if (!exists($allow_repeated_words{lc($first)})); + } + + if (WARN("REPEATED_WORD", + "Possible repeated word: '$first'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\b$first $second\b/$first/; + } + } + + # if it's a repeated word on consecutive lines in a comment block + if ($prevline =~ /$;+\s*$/ && + $prevrawline =~ /($word_pattern)\s*$/) { + my $last_word = $1; + if ($rawline =~ /^\+\s*\*\s*$last_word /) { + if (WARN("REPEATED_WORD", + "Possible repeated word: '$last_word'\n" . $hereprev) && + $fix) { + $fixed[$fixlinenr] =~ s/(\+\s*\*\s*)$last_word /$1/; + } + } + } + } + # ignore non-hunk lines and lines being removed next if (!$hunk_line || $line =~ /^-/); @@ -3071,11 +3611,7 @@ sub process { if ($lines[$ln - 1] =~ /^\+\s*(?:bool|tristate|prompt)\s*["']/) { $is_start = 1; - } elsif ($lines[$ln - 1] =~ /^\+\s*(?:help|---help---)\s*$/) { - if ($lines[$ln - 1] =~ "---help---") { - WARN("CONFIG_DESCRIPTION", - "prefer 'help' over '---help---' for new help texts\n" . $herecurr); - } + } elsif ($lines[$ln - 1] =~ /^\+\s*(?:---)?help(?:---)?$/) { $length = -1; } @@ -3102,22 +3638,44 @@ sub process { #print "is_start<$is_start> is_end<$is_end> length<$length>\n"; } -# check for MAINTAINERS entries that don't have the right form - if ($realfile =~ /^MAINTAINERS$/ && - $rawline =~ /^\+[A-Z]:/ && - $rawline !~ /^\+[A-Z]:\t\S/) { - if (WARN("MAINTAINERS_STYLE", - "MAINTAINERS entries use one tab after TYPE:\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/^(\+[A-Z]):\s*/$1:\t/; +# check MAINTAINERS entries + if ($realfile =~ /^MAINTAINERS$/) { +# check MAINTAINERS entries for the right form + if ($rawline =~ /^\+[A-Z]:/ && + $rawline !~ /^\+[A-Z]:\t\S/) { + if (WARN("MAINTAINERS_STYLE", + "MAINTAINERS entries use one tab after TYPE:\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/^(\+[A-Z]):\s*/$1:\t/; + } + } +# check MAINTAINERS entries for the right ordering too + my $preferred_order = 'MRLSWQBCPTFXNK'; + if ($rawline =~ /^\+[A-Z]:/ && + $prevrawline =~ /^[\+ ][A-Z]:/) { + $rawline =~ /^\+([A-Z]):\s*(.*)/; + my $cur = $1; + my $curval = $2; + $prevrawline =~ /^[\+ ]([A-Z]):\s*(.*)/; + my $prev = $1; + my $prevval = $2; + my $curindex = index($preferred_order, $cur); + my $previndex = index($preferred_order, $prev); + if ($curindex < 0) { + WARN("MAINTAINERS_STYLE", + "Unknown MAINTAINERS entry type: '$cur'\n" . $herecurr); + } else { + if ($previndex >= 0 && $curindex < $previndex) { + WARN("MAINTAINERS_STYLE", + "Misordered MAINTAINERS entry - list '$cur:' before '$prev:'\n" . $hereprev); + } elsif ((($prev eq 'F' && $cur eq 'F') || + ($prev eq 'X' && $cur eq 'X')) && + ($prevval cmp $curval) > 0) { + WARN("MAINTAINERS_STYLE", + "Misordered MAINTAINERS entry - list file patterns in alphabetic order\n" . $hereprev); + } + } } - } - -# discourage the use of boolean for type definition attributes of Kconfig options - if ($realfile =~ /Kconfig/ && - $line =~ /^\+\s*\bboolean\b/) { - WARN("CONFIG_TYPE_BOOLEAN", - "Use of boolean is deprecated, please use bool instead.\n" . $herecurr); } if (($realfile =~ /Makefile.*/ || $realfile =~ /Kbuild.*/) && @@ -3214,6 +3772,12 @@ sub process { } } +# check for embedded filenames + if ($rawline =~ /^\+.*\Q$realfile\E/) { + WARN("EMBEDDED_FILENAME", + "It's generally not useful to have the filename in the file\n" . $herecurr); + } + # check we are in a valid source file if not then ignore this hunk next if ($realfile !~ /\.(h|c|s|S|sh|dtsi|dts)$/); @@ -3291,12 +3855,22 @@ sub process { # check for adding lines without a newline. if ($line =~ /^\+/ && defined $lines[$linenr] && $lines[$linenr] =~ /^\\ No newline at end of file/) { - WARN("MISSING_EOF_NEWLINE", - "adding a line without newline at end of file\n" . $herecurr); + if (WARN("MISSING_EOF_NEWLINE", + "adding a line without newline at end of file\n" . $herecurr) && + $fix) { + fix_delete_line($fixlinenr+1, "No newline at end of file"); + } + } + +# check for .L prefix local symbols in .S files + if ($realfile =~ /\.S$/ && + $line =~ /^\+\s*(?:[A-Z]+_)?SYM_[A-Z]+_(?:START|END)(?:_[A-Z_]+)?\s*\(\s*\.L/) { + WARN("AVOID_L_PREFIX", + "Avoid using '.L' prefixed local symbol names for denoting a range of code via 'SYM_*_START/END' annotations; see Documentation/asm-annotations.rst\n" . $herecurr); } if ($u_boot) { - u_boot_line($realfile, $line, $herecurr); + u_boot_line($realfile, $line, $rawline, $herecurr); } # check we are in a valid source file C or perl if not then ignore this hunk @@ -3330,14 +3904,28 @@ sub process { # check for assignments on the start of a line if ($sline =~ /^\+\s+($Assignment)[^=]/) { - CHK("ASSIGNMENT_CONTINUATIONS", - "Assignment operator '$1' should be on the previous line\n" . $hereprev); + my $operator = $1; + if (CHK("ASSIGNMENT_CONTINUATIONS", + "Assignment operator '$1' should be on the previous line\n" . $hereprev) && + $fix && $prevrawline =~ /^\+/) { + # add assignment operator to the previous line, remove from current line + $fixed[$fixlinenr - 1] .= " $operator"; + $fixed[$fixlinenr] =~ s/\Q$operator\E\s*//; + } } # check for && or || at the start of a line if ($rawline =~ /^\+\s*(&&|\|\|)/) { - CHK("LOGICAL_CONTINUATIONS", - "Logical continuations should be on the previous line\n" . $hereprev); + my $operator = $1; + if (CHK("LOGICAL_CONTINUATIONS", + "Logical continuations should be on the previous line\n" . $hereprev) && + $fix && $prevrawline =~ /^\+/) { + # insert logical operator at last non-comment, non-whitepsace char on previous line + $prevline =~ /[\s$;]*$/; + my $line_end = substr($prevrawline, $-[0]); + $fixed[$fixlinenr - 1] =~ s/\Q$line_end\E$/ $operator$line_end/; + $fixed[$fixlinenr] =~ s/\Q$operator\E\s*//; + } } # check indentation starts on a tab stop @@ -3405,7 +3993,7 @@ sub process { if ($realfile =~ m@^(drivers/net/|net/)@ && $prevrawline =~ /^\+[ \t]*\/\*[ \t]*$/ && $rawline =~ /^\+[ \t]*\*/ && - $realline > 2) { + $realline > 3) { # Do not warn about the initial copyright comment block after SPDX-License-Identifier WARN("NETWORKING_BLOCK_COMMENT_STYLE", "networking block comments don't use an empty /* line, use /* Comment...\n" . $hereprev); } @@ -3487,43 +4075,48 @@ sub process { } # check for missing blank lines after declarations - if ($sline =~ /^\+\s+\S/ && #Not at char 1 - # actual declarations - ($prevline =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || +# (declarations must have the same indentation and not be at the start of line) + if (($prevline =~ /\+(\s+)\S/) && $sline =~ /^\+$1\S/) { + # use temporaries + my $sl = $sline; + my $pl = $prevline; + # remove $Attribute/$Sparse uses to simplify comparisons + $sl =~ s/\b(?:$Attribute|$Sparse)\b//g; + $pl =~ s/\b(?:$Attribute|$Sparse)\b//g; + if (($pl =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || # function pointer declarations - $prevline =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || + $pl =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || # foo bar; where foo is some local typedef or #define - $prevline =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || + $pl =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || # known declaration macros - $prevline =~ /^\+\s+$declaration_macros/) && + $pl =~ /^\+\s+$declaration_macros/) && # for "else if" which can look like "$Ident $Ident" - !($prevline =~ /^\+\s+$c90_Keywords\b/ || + !($pl =~ /^\+\s+$c90_Keywords\b/ || # other possible extensions of declaration lines - $prevline =~ /(?:$Compare|$Assignment|$Operators)\s*$/ || + $pl =~ /(?:$Compare|$Assignment|$Operators)\s*$/ || # not starting a section or a macro "\" extended line - $prevline =~ /(?:\{\s*|\\)$/) && + $pl =~ /(?:\{\s*|\\)$/) && # looks like a declaration - !($sline =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || + !($sl =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || # function pointer declarations - $sline =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || + $sl =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || # foo bar; where foo is some local typedef or #define - $sline =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || + $sl =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || # known declaration macros - $sline =~ /^\+\s+$declaration_macros/ || + $sl =~ /^\+\s+$declaration_macros/ || # start of struct or union or enum - $sline =~ /^\+\s+(?:static\s+)?(?:const\s+)?(?:union|struct|enum|typedef)\b/ || + $sl =~ /^\+\s+(?:static\s+)?(?:const\s+)?(?:union|struct|enum|typedef)\b/ || # start or end of block or continuation of declaration - $sline =~ /^\+\s+(?:$|[\{\}\.\#\"\?\:\(\[])/ || + $sl =~ /^\+\s+(?:$|[\{\}\.\#\"\?\:\(\[])/ || # bitfield continuation - $sline =~ /^\+\s+$Ident\s*:\s*\d+\s*[,;]/ || + $sl =~ /^\+\s+$Ident\s*:\s*\d+\s*[,;]/ || # other possible extensions of declaration lines - $sline =~ /^\+\s+\(?\s*(?:$Compare|$Assignment|$Operators)/) && - # indentation of previous and current line are the same - (($prevline =~ /\+(\s+)\S/) && $sline =~ /^\+$1\S/)) { - if (WARN("LINE_SPACING", - "Missing a blank line after declarations\n" . $hereprev) && - $fix) { - fix_insert_line($fixlinenr, "\+"); + $sl =~ /^\+\s+\(?\s*(?:$Compare|$Assignment|$Operators)/)) { + if (WARN("LINE_SPACING", + "Missing a blank line after declarations\n" . $hereprev) && + $fix) { + fix_insert_line($fixlinenr, "\+"); + } } } @@ -3576,12 +4169,16 @@ sub process { } # check indentation of a line with a break; -# if the previous line is a goto or return and is indented the same # of tabs +# if the previous line is a goto, return or break +# and is indented the same # of tabs if ($sline =~ /^\+([\t]+)break\s*;\s*$/) { my $tabs = $1; - if ($prevline =~ /^\+$tabs(?:goto|return)\b/) { - WARN("UNNECESSARY_BREAK", - "break is not useful after a goto or return\n" . $hereprev); + if ($prevline =~ /^\+$tabs(goto|return|break)\b/) { + if (WARN("UNNECESSARY_BREAK", + "break is not useful after a $1\n" . $hereprev) && + $fix) { + fix_delete_line($fixlinenr, $rawline); + } } } @@ -3864,6 +4461,17 @@ sub process { #ignore lines not being added next if ($line =~ /^[^\+]/); +# check for self assignments used to avoid compiler warnings +# e.g.: int foo = foo, *bar = NULL; +# struct foo bar = *(&(bar)); + if ($line =~ /^\+\s*(?:$Declare)?([A-Za-z_][A-Za-z\d_]*)\s*=/) { + my $var = $1; + if ($line =~ /^\+\s*(?:$Declare)?$var\s*=\s*(?:$var|\*\s*\(?\s*&\s*\(?\s*$var\s*\)?\s*\)?)\s*[;,]/) { + WARN("SELF_ASSIGNMENT", + "Do not use self-assignments to avoid compiler warnings\n" . $herecurr); + } + } + # check for dereferences that span multiple lines if ($prevline =~ /^\+.*$Lval\s*(?:\.|->)\s*$/ && $line =~ /^\+\s*(?!\#\s*(?!define\s+|if))\s*$Lval/) { @@ -3979,13 +4587,13 @@ sub process { if (defined $realline_next && exists $lines[$realline_next - 1] && !defined $suppress_export{$realline_next} && - ($lines[$realline_next - 1] =~ /EXPORT_SYMBOL.*\((.*)\)/ || - $lines[$realline_next - 1] =~ /EXPORT_UNUSED_SYMBOL.*\((.*)\)/)) { + ($lines[$realline_next - 1] =~ /EXPORT_SYMBOL.*\((.*)\)/)) { # Handle definitions which produce identifiers with # a prefix: # XXX(foo); # EXPORT_SYMBOL(something_foo); my $name = $1; + $name =~ s/^\s*($Ident).*/$1/; if ($stat =~ /^(?:.\s*}\s*\n)?.([A-Z_]+)\s*\(\s*($Ident)/ && $name =~ /^${Ident}_$2/) { #print "FOO C name<$name>\n"; @@ -4007,8 +4615,7 @@ sub process { } if (!defined $suppress_export{$linenr} && $prevline =~ /^.\s*$/ && - ($line =~ /EXPORT_SYMBOL.*\((.*)\)/ || - $line =~ /EXPORT_UNUSED_SYMBOL.*\((.*)\)/)) { + ($line =~ /EXPORT_SYMBOL.*\((.*)\)/)) { #print "FOO B <$lines[$linenr - 1]>\n"; $suppress_export{$linenr} = 2; } @@ -4019,7 +4626,8 @@ sub process { } # check for global initialisers. - if ($line =~ /^\+$Type\s*$Ident(?:\s+$Modifier)*\s*=\s*($zero_initializer)\s*;/) { + if ($line =~ /^\+$Type\s*$Ident(?:\s+$Modifier)*\s*=\s*($zero_initializer)\s*;/ && + !exclude_global_initialisers($realfile)) { if (ERROR("GLOBAL_INITIALISERS", "do not initialise globals to $1\n" . $herecurr) && $fix) { @@ -4098,12 +4706,24 @@ sub process { } } +# check for const static or static <non ptr type> const declarations +# prefer 'static const <foo>' over 'const static <foo>' and 'static <foo> const' + if ($sline =~ /^\+\s*const\s+static\s+($Type)\b/ || + $sline =~ /^\+\s*static\s+($BasicType)\s+const\b/) { + if (WARN("STATIC_CONST", + "Move const after static - use 'static const $1'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bconst\s+static\b/static const/; + $fixed[$fixlinenr] =~ s/\bstatic\s+($BasicType)\s+const\b/static const $1/; + } + } + # check for non-global char *foo[] = {"bar", ...} declarations. if ($line =~ /^.\s+(?:static\s+|const\s+)?char\s+\*\s*\w+\s*\[\s*\]\s*=\s*\{/) { WARN("STATIC_CONST_CHAR_ARRAY", "char * array declaration might be better as static const\n" . $herecurr); - } + } # check for sizeof(foo)/sizeof(foo[0]) that could be ARRAY_SIZE(foo) if ($line =~ m@\bsizeof\s*\(\s*($Lval)\s*\)@) { @@ -4220,16 +4840,23 @@ sub process { "printk() should include KERN_<LEVEL> facility level\n" . $herecurr); } - if ($line =~ /\bprintk\s*\(\s*KERN_([A-Z]+)/) { - my $orig = $1; +# prefer variants of (subsystem|netdev|dev|pr)_<level> to printk(KERN_<LEVEL> + if ($line =~ /\b(printk(_once|_ratelimited)?)\s*\(\s*KERN_([A-Z]+)/) { + my $printk = $1; + my $modifier = $2; + my $orig = $3; + $modifier = "" if (!defined($modifier)); my $level = lc($orig); $level = "warn" if ($level eq "warning"); my $level2 = $level; $level2 = "dbg" if ($level eq "debug"); + $level .= $modifier; + $level2 .= $modifier; WARN("PREFER_PR_LEVEL", - "Prefer [subsystem eg: netdev]_$level2([subsystem]dev, ... then dev_$level2(dev, ... then pr_$level(... to printk(KERN_$orig ...\n" . $herecurr); + "Prefer [subsystem eg: netdev]_$level2([subsystem]dev, ... then dev_$level2(dev, ... then pr_$level(... to $printk(KERN_$orig ...\n" . $herecurr); } +# prefer dev_<level> to dev_printk(KERN_<LEVEL> if ($line =~ /\bdev_printk\s*\(\s*KERN_([A-Z]+)/) { my $orig = $1; my $level = lc($orig); @@ -4239,6 +4866,12 @@ sub process { "Prefer dev_$level(... to dev_printk(KERN_$orig, ...\n" . $herecurr); } +# trace_printk should not be used in production code. + if ($line =~ /\b(trace_printk|trace_puts|ftrace_vprintk)\s*\(/) { + WARN("TRACE_PRINTK", + "Do not use $1() in production code (this can be ignored if built only with a debug config option)\n" . $herecurr); + } + # ENOSYS means "bad syscall nr" and nothing else. This will have a small # number of false positives, but assembly files are not checked, so at # least the arch entry code will not trigger this warning. @@ -4247,6 +4880,17 @@ sub process { "ENOSYS means 'invalid syscall nr' and nothing else\n" . $herecurr); } +# ENOTSUPP is not a standard error code and should be avoided in new patches. +# Folks usually mean EOPNOTSUPP (also called ENOTSUP), when they type ENOTSUPP. +# Similarly to ENOSYS warning a small number of false positives is expected. + if (!$file && $line =~ /\bENOTSUPP\b/) { + if (WARN("ENOTSUPP", + "ENOTSUPP is not a SUSV4 error code, prefer EOPNOTSUPP\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bENOTSUPP\b/EOPNOTSUPP/; + } + } + # function brace can't be on same line, except for #defines of do while, # or if closed on same line if ($perl_version_ok && @@ -4258,7 +4902,7 @@ sub process { $fix) { fix_delete_line($fixlinenr, $rawline); my $fixed_line = $rawline; - $fixed_line =~ /(^..*$Type\s*$Ident\(.*\)\s*){(.*)$/; + $fixed_line =~ /(^..*$Type\s*$Ident\(.*\)\s*)\{(.*)$/; my $line1 = $1; my $line2 = $2; fix_insert_line($fixlinenr, ltrim($line1)); @@ -4669,7 +5313,7 @@ sub process { # A colon needs no spaces before when it is # terminating a case value or a label. } elsif ($opv eq ':C' || $opv eq ':L') { - if ($ctx =~ /Wx./) { + if ($ctx =~ /Wx./ and $realfile !~ m@.*\.lds\.h$@) { if (ERROR("SPACING", "space prohibited before that '$op' $at\n" . $hereptr)) { $good = rtrim($fix_elements[$n]) . trim($fix_elements[$n + 1]); @@ -4753,7 +5397,7 @@ sub process { ## $line !~ /^.\s*$Type\s+$Ident(?:\s*=[^,{]*)?\s*,\s*$Type\s*$Ident.*/) { ## ## # Remove any bracketed sections to ensure we do not -## # falsly report the parameters of functions. +## # falsely report the parameters of functions. ## my $ln = $line; ## while ($ln =~ s/\([^\(\)]*\)//g) { ## } @@ -4883,9 +5527,13 @@ sub process { } } -#goto labels aren't indented, allow a single space however - if ($line=~/^.\s+[A-Za-z\d_]+:(?![0-9]+)/ and - !($line=~/^. [A-Za-z\d_]+:/) and !($line=~/^.\s+default:/)) { +# check that goto labels aren't indented (allow a single space indentation) +# and ignore bitfield definitions like foo:1 +# Strictly, labels can have whitespace after the identifier and before the : +# but this is not allowed here as many ?: uses would appear to be labels + if ($sline =~ /^.\s+[A-Za-z_][A-Za-z\d_]*:(?!\s*\d+)/ && + $sline !~ /^. [A-Za-z\d_][A-Za-z\d_]*:/ && + $sline !~ /^.\s+default:/) { if (WARN("INDENTED_LABEL", "labels should not be indented\n" . $herecurr) && $fix) { @@ -4894,6 +5542,17 @@ sub process { } } +# check if a statement with a comma should be two statements like: +# foo = bar(), /* comma should be semicolon */ +# bar = baz(); + if (defined($stat) && + $stat =~ /^\+\s*(?:$Lval\s*$Assignment\s*)?$FuncArg\s*,\s*(?:$Lval\s*$Assignment\s*)?$FuncArg\s*;\s*$/) { + my $cnt = statement_rawlines($stat); + my $herectx = get_stat_here($linenr, $cnt, $here); + WARN("SUSPECT_COMMA_SEMICOLON", + "Possible comma where semicolon could be used\n" . $herectx); + } + # return is not a function if (defined($stat) && $stat =~ /^.\s*return(\s*)\(/s) { my $spacing = $1; @@ -4921,7 +5580,7 @@ sub process { $lines[$linenr - 3] !~ /^[ +]\s*$Ident\s*:/) { WARN("RETURN_VOID", "void function return statements are not generally useful\n" . $hereprev); - } + } # if statements using unnecessary parentheses - ie: if ((foo == bar)) if ($perl_version_ok && @@ -4969,7 +5628,7 @@ sub process { # Return of what appears to be an errno should normally be negative if ($sline =~ /\breturn(?:\s*\(+\s*|\s+)(E[A-Z]+)(?:\s*\)+\s*|\s*)[;:,]/) { my $name = $1; - if ($name ne 'EOF' && $name ne 'ERROR') { + if ($name ne 'EOF' && $name ne 'ERROR' && $name !~ /^EPOLL/) { WARN("USE_NEGATIVE_ERRNO", "return of an errno should typically be negative (ie: return -$1)\n" . $herecurr); } @@ -5014,8 +5673,30 @@ sub process { my ($s, $c) = ($stat, $cond); if ($c =~ /\bif\s*\(.*[^<>!=]=[^=].*/s) { - ERROR("ASSIGN_IN_IF", - "do not use assignment in if condition\n" . $herecurr); + if (ERROR("ASSIGN_IN_IF", + "do not use assignment in if condition\n" . $herecurr) && + $fix && $perl_version_ok) { + if ($rawline =~ /^\+(\s+)if\s*\(\s*(\!)?\s*\(\s*(($Lval)\s*=\s*$LvalOrFunc)\s*\)\s*(?:($Compare)\s*($FuncArg))?\s*\)\s*(\{)?\s*$/) { + my $space = $1; + my $not = $2; + my $statement = $3; + my $assigned = $4; + my $test = $8; + my $against = $9; + my $brace = $15; + fix_delete_line($fixlinenr, $rawline); + fix_insert_line($fixlinenr, "$space$statement;"); + my $newline = "${space}if ("; + $newline .= '!' if defined($not); + $newline .= '(' if (defined $not && defined($test) && defined($against)); + $newline .= "$assigned"; + $newline .= " $test $against" if (defined($test) && defined($against)); + $newline .= ')' if (defined $not && defined($test) && defined($against)); + $newline .= ')'; + $newline .= " {" if (defined($brace)); + fix_insert_line($fixlinenr + 1, $newline); + } + } } # Find out what is on the end of the line after the @@ -5136,6 +5817,8 @@ sub process { #CamelCase if ($var !~ /^$Constant$/ && $var =~ /[A-Z][a-z]|[a-z][A-Z]/ && +#Ignore some autogenerated defines and enum values + $var !~ /^(?:[A-Z]+_){1,5}[A-Z]{1,3}[a-z]/ && #Ignore Page<foo> variants $var !~ /^(?:Clear|Set|TestClear|TestSet|)Page[A-Z]/ && #Ignore SI style variants like nS, mV and dB @@ -5231,9 +5914,9 @@ sub process { $dstat =~ s/\s*$//s; # Flatten any parentheses and braces - while ($dstat =~ s/\([^\(\)]*\)/1/ || - $dstat =~ s/\{[^\{\}]*\}/1/ || - $dstat =~ s/.\[[^\[\]]*\]/1/) + while ($dstat =~ s/\([^\(\)]*\)/1u/ || + $dstat =~ s/\{[^\{\}]*\}/1u/ || + $dstat =~ s/.\[[^\[\]]*\]/1u/) { } @@ -5274,6 +5957,7 @@ sub process { $dstat !~ /^\.$Ident\s*=/ && # .foo = $dstat !~ /^(?:\#\s*$Ident|\#\s*$Constant)\s*$/ && # stringification #foo $dstat !~ /^do\s*$Constant\s*while\s*$Constant;?$/ && # do {...} while (...); // do {...} while (...) + $dstat !~ /^while\s*$Constant\s*$Constant\s*$/ && # while (...) {...} $dstat !~ /^for\s*$Constant$/ && # for (...) $dstat !~ /^for\s*$Constant\s+(?:$Ident|-?$Constant)$/ && # for (...) bar() $dstat !~ /^do\s*{/ && # do {... @@ -5315,7 +5999,7 @@ sub process { next if ($arg =~ /\.\.\./); next if ($arg =~ /^type$/i); my $tmp_stmt = $define_stmt; - $tmp_stmt =~ s/\b(sizeof|typeof|__typeof__|__builtin\w+|typecheck\s*\(\s*$Type\s*,|\#+)\s*\(*\s*$arg\s*\)*\b//g; + $tmp_stmt =~ s/\b(__must_be_array|offsetof|sizeof|sizeof_field|__stringify|typeof|__typeof__|__builtin\w+|typecheck\s*\(\s*$Type\s*,|\#+)\s*\(*\s*$arg\s*\)*\b//g; $tmp_stmt =~ s/\#+\s*$arg\b//g; $tmp_stmt =~ s/\b$arg\s*\#\#//g; my $use_cnt = () = $tmp_stmt =~ /\b$arg\b/g; @@ -5592,6 +6276,17 @@ sub process { "Prefer using '\"%s...\", __func__' to using '$context_function', this function's name, in a string\n" . $herecurr); } +# check for unnecessary function tracing like uses +# This does not use $logFunctions because there are many instances like +# 'dprintk(FOO, "%s()\n", __func__);' which do not match $logFunctions + if ($rawline =~ /^\+.*\([^"]*"$tracing_logging_tags{0,3}%s(?:\s*\(\s*\)\s*)?$tracing_logging_tags{0,3}(?:\\n)?"\s*,\s*__func__\s*\)\s*;/) { + if (WARN("TRACING_LOGGING", + "Unnecessary ftrace-like logging - prefer using ftrace\n" . $herecurr) && + $fix) { + fix_delete_line($fixlinenr, $rawline); + } + } + # check for spaces before a quoted newline if ($rawline =~ /^.*\".*\s\\n/) { if (WARN("QUOTED_WHITESPACE_BEFORE_NEWLINE", @@ -5603,7 +6298,8 @@ sub process { } # concatenated string without spaces between elements - if ($line =~ /$String[A-Za-z0-9_]/ || $line =~ /[A-Za-z0-9_]$String/) { + if ($line =~ /$String[A-Z_]/ || + ($line =~ /([A-Za-z0-9_]+)$String/ && $1 !~ /^[Lu]$/)) { if (CHK("CONCATENATED_STRING", "Concatenated strings should use spaces between elements\n" . $herecurr) && $fix) { @@ -5616,7 +6312,7 @@ sub process { } # uncoalesced string fragments - if ($line =~ /$String\s*"/) { + if ($line =~ /$String\s*[Lu]?"/) { if (WARN("STRING_FRAGMENTS", "Consecutive strings are generally better as a single string\n" . $herecurr) && $fix) { @@ -5738,6 +6434,28 @@ sub process { "Avoid logging continuation uses where feasible\n" . $herecurr); } +# check for unnecessary use of %h[xudi] and %hh[xudi] in logging functions + if (defined $stat && + $line =~ /\b$logFunctions\s*\(/ && + index($stat, '"') >= 0) { + my $lc = $stat =~ tr@\n@@; + $lc = $lc + $linenr; + my $stat_real = get_stat_real($linenr, $lc); + pos($stat_real) = index($stat_real, '"'); + while ($stat_real =~ /[^\"%]*(%[\#\d\.\*\-]*(h+)[idux])/g) { + my $pspec = $1; + my $h = $2; + my $lineoff = substr($stat_real, 0, $-[1]) =~ tr@\n@@; + if (WARN("UNNECESSARY_MODIFIER", + "Integer promotion: Using '$h' in '$pspec' is unnecessary\n" . "$here\n$stat_real\n") && + $fix && $fixed[$fixlinenr + $lineoff] =~ /^\+/) { + my $nspec = $pspec; + $nspec =~ s/h//g; + $fixed[$fixlinenr + $lineoff] =~ s/\Q$pspec\E/$nspec/; + } + } + } + # check for mask then right shift without a parentheses if ($perl_version_ok && $line =~ /$LvalOrFunc\s*\&\s*($LvalOrFunc)\s*>>/ && @@ -5896,8 +6614,7 @@ sub process { my $barriers = qr{ mb| rmb| - wmb| - read_barrier_depends + wmb }x; my $barrier_stems = qr{ mb__before_atomic| @@ -5938,10 +6655,12 @@ sub process { } } -# check for smp_read_barrier_depends and read_barrier_depends - if (!$file && $line =~ /\b(smp_|)read_barrier_depends\s*\(/) { - WARN("READ_BARRIER_DEPENDS", - "$1read_barrier_depends should only be used in READ_ONCE or DEC Alpha code\n" . $herecurr); +# check for data_race without a comment. + if ($line =~ /\bdata_race\s*\(/) { + if (!ctx_has_comment($first_line, $linenr)) { + WARN("DATA_RACE", + "data_race without comment\n" . $herecurr); + } } # check of hardware specific defines @@ -5983,50 +6702,68 @@ sub process { } } -# Check for __attribute__ packed, prefer __packed - if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(.*\bpacked\b/) { - WARN("PREFER_PACKED", - "__packed is preferred over __attribute__((packed))\n" . $herecurr); - } - -# Check for __attribute__ aligned, prefer __aligned - if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(.*aligned/) { - WARN("PREFER_ALIGNED", - "__aligned(size) is preferred over __attribute__((aligned(size)))\n" . $herecurr); - } - -# Check for __attribute__ section, prefer __section - if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(.*_*section_*\s*\(\s*("[^"]*")/) { - my $old = substr($rawline, $-[1], $+[1] - $-[1]); - my $new = substr($old, 1, -1); - if (WARN("PREFER_SECTION", - "__section($new) is preferred over __attribute__((section($old)))\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\b__attribute__\s*\(\s*\(\s*_*section_*\s*\(\s*\Q$old\E\s*\)\s*\)\s*\)/__section($new)/; - } - } - -# Check for __attribute__ format(printf, prefer __printf +# Check for compiler attributes if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(\s*format\s*\(\s*printf/) { - if (WARN("PREFER_PRINTF", - "__printf(string-index, first-to-check) is preferred over __attribute__((format(printf, string-index, first-to-check)))\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\b__attribute__\s*\(\s*\(\s*format\s*\(\s*printf\s*,\s*(.*)\)\s*\)\s*\)/"__printf(" . trim($1) . ")"/ex; - + $rawline =~ /\b__attribute__\s*\(\s*($balanced_parens)\s*\)/) { + my $attr = $1; + $attr =~ s/\s*\(\s*(.*)\)\s*/$1/; + + my %attr_list = ( + "alias" => "__alias", + "aligned" => "__aligned", + "always_inline" => "__always_inline", + "assume_aligned" => "__assume_aligned", + "cold" => "__cold", + "const" => "__attribute_const__", + "copy" => "__copy", + "designated_init" => "__designated_init", + "externally_visible" => "__visible", + "format" => "printf|scanf", + "gnu_inline" => "__gnu_inline", + "malloc" => "__malloc", + "mode" => "__mode", + "no_caller_saved_registers" => "__no_caller_saved_registers", + "noclone" => "__noclone", + "noinline" => "noinline", + "nonstring" => "__nonstring", + "noreturn" => "__noreturn", + "packed" => "__packed", + "pure" => "__pure", + "section" => "__section", + "used" => "__used", + "weak" => "__weak" + ); + + while ($attr =~ /\s*(\w+)\s*(${balanced_parens})?/g) { + my $orig_attr = $1; + my $params = ''; + $params = $2 if defined($2); + my $curr_attr = $orig_attr; + $curr_attr =~ s/^[\s_]+|[\s_]+$//g; + if (exists($attr_list{$curr_attr})) { + my $new = $attr_list{$curr_attr}; + if ($curr_attr eq "format" && $params) { + $params =~ /^\s*\(\s*(\w+)\s*,\s*(.*)/; + $new = "__$1\($2"; + } else { + $new = "$new$params"; + } + if (WARN("PREFER_DEFINED_ATTRIBUTE_MACRO", + "Prefer $new over __attribute__(($orig_attr$params))\n" . $herecurr) && + $fix) { + my $remove = "\Q$orig_attr\E" . '\s*' . "\Q$params\E" . '(?:\s*,\s*)?'; + $fixed[$fixlinenr] =~ s/$remove//; + $fixed[$fixlinenr] =~ s/\b__attribute__/$new __attribute__/; + $fixed[$fixlinenr] =~ s/\}\Q$new\E/} $new/; + $fixed[$fixlinenr] =~ s/ __attribute__\s*\(\s*\(\s*\)\s*\)//; + } + } } - } -# Check for __attribute__ format(scanf, prefer __scanf - if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(\s*format\s*\(\s*scanf\b/) { - if (WARN("PREFER_SCANF", - "__scanf(string-index, first-to-check) is preferred over __attribute__((format(scanf, string-index, first-to-check)))\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\b__attribute__\s*\(\s*\(\s*format\s*\(\s*scanf\s*,\s*(.*)\)\s*\)\s*\)/"__scanf(" . trim($1) . ")"/ex; + # Check for __attribute__ unused, prefer __always_unused or __maybe_unused + if ($attr =~ /^_*unused/) { + WARN("PREFER_DEFINED_ATTRIBUTE_MACRO", + "__always_unused or __maybe_unused is preferred over __attribute__((__unused__))\n" . $herecurr); } } @@ -6062,18 +6799,18 @@ sub process { if ($line =~ /(\(\s*$C90_int_types\s*\)\s*)($Constant)\b/) { my $cast = $1; my $const = $2; + my $suffix = ""; + my $newconst = $const; + $newconst =~ s/${Int_type}$//; + $suffix .= 'U' if ($cast =~ /\bunsigned\b/); + if ($cast =~ /\blong\s+long\b/) { + $suffix .= 'LL'; + } elsif ($cast =~ /\blong\b/) { + $suffix .= 'L'; + } if (WARN("TYPECAST_INT_CONSTANT", - "Unnecessary typecast of c90 int constant\n" . $herecurr) && + "Unnecessary typecast of c90 int constant - '$cast$const' could be '$const$suffix'\n" . $herecurr) && $fix) { - my $suffix = ""; - my $newconst = $const; - $newconst =~ s/${Int_type}$//; - $suffix .= 'U' if ($cast =~ /\bunsigned\b/); - if ($cast =~ /\blong\s+long\b/) { - $suffix .= 'LL'; - } elsif ($cast =~ /\blong\b/) { - $suffix .= 'L'; - } $fixed[$fixlinenr] =~ s/\Q$cast\E$const\b/$newconst$suffix/; } } @@ -6133,9 +6870,11 @@ sub process { $specifier = $1; $extension = $2; $qualifier = $3; - if ($extension !~ /[SsBKRraEehMmIiUDdgVCbGNOxtf]/ || + if ($extension !~ /[4SsBKRraEehMmIiUDdgVCbGNOxtf]/ || ($extension eq "f" && - defined $qualifier && $qualifier !~ /^w/)) { + defined $qualifier && $qualifier !~ /^w/) || + ($extension eq "4" && + defined $qualifier && $qualifier !~ /^cc/)) { $bad_specifier = $specifier; last; } @@ -6315,8 +7054,7 @@ sub process { if (defined $cond) { substr($s, 0, length($cond), ''); } - if ($s =~ /^\s*;/ && - $function_name ne 'uninitialized_var') + if ($s =~ /^\s*;/) { WARN("AVOID_EXTERNS", "externs should be avoided in .c files\n" . $herecurr); @@ -6335,17 +7073,13 @@ sub process { } # check for function declarations that have arguments without identifier names -# while avoiding uninitialized_var(x) if (defined $stat && - $stat =~ /^.\s*(?:extern\s+)?$Type\s*(?:($Ident)|\(\s*\*\s*$Ident\s*\))\s*\(\s*([^{]+)\s*\)\s*;/s && - (!defined($1) || - (defined($1) && $1 ne "uninitialized_var")) && - $2 ne "void") { - my $args = trim($2); + $stat =~ /^.\s*(?:extern\s+)?$Type\s*(?:$Ident|\(\s*\*\s*$Ident\s*\))\s*\(\s*([^{]+)\s*\)\s*;/s && + $1 ne "void") { + my $args = trim($1); while ($args =~ m/\s*($Type\s*(?:$Ident|\(\s*\*\s*$Ident?\s*\)\s*$balanced_parens)?)/g) { my $arg = trim($1); - if ($arg =~ /^$Type$/ && - $arg !~ /enum\s+$Ident$/) { + if ($arg =~ /^$Type$/ && $arg !~ /enum\s+$Ident$/) { WARN("FUNCTION_ARGUMENTS", "function definition argument '$arg' should also have an identifier name\n" . $herecurr); } @@ -6381,7 +7115,7 @@ sub process { if (!grep(/$name/, @setup_docs)) { CHK("UNDOCUMENTED_SETUP", - "__setup appears un-documented -- check Documentation/admin-guide/kernel-parameters.rst\n" . $herecurr); + "__setup appears un-documented -- check Documentation/admin-guide/kernel-parameters.txt\n" . $herecurr); } } @@ -6437,7 +7171,7 @@ sub process { } # check for alloc argument mismatch - if ($line =~ /\b(kcalloc|kmalloc_array)\s*\(\s*sizeof\b/) { + if ($line =~ /\b((?:devm_)?(?:kcalloc|kmalloc_array))\s*\(\s*sizeof\b/) { WARN("ALLOC_ARRAY_ARGS", "$1 uses number as first arg, sizeof is generally wrong\n" . $herecurr); } @@ -6463,41 +7197,22 @@ sub process { } } +# check for IS_ENABLED() without CONFIG_<FOO> ($rawline for comments too) + if ($rawline =~ /\bIS_ENABLED\s*\(\s*(\w+)\s*\)/ && $1 !~ /^${CONFIG_}/) { + WARN("IS_ENABLED_CONFIG", + "IS_ENABLED($1) is normally used as IS_ENABLED(${CONFIG_}$1)\n" . $herecurr); + } + # check for #if defined CONFIG_<FOO> || defined CONFIG_<FOO>_MODULE - if ($line =~ /^\+\s*#\s*if\s+defined(?:\s*\(?\s*|\s+)(CONFIG_[A-Z_]+)\s*\)?\s*\|\|\s*defined(?:\s*\(?\s*|\s+)\1_MODULE\s*\)?\s*$/) { + if ($line =~ /^\+\s*#\s*if\s+defined(?:\s*\(?\s*|\s+)(${CONFIG_}[A-Z_]+)\s*\)?\s*\|\|\s*defined(?:\s*\(?\s*|\s+)\1_MODULE\s*\)?\s*$/) { my $config = $1; if (WARN("PREFER_IS_ENABLED", - "Prefer IS_ENABLED(<FOO>) to CONFIG_<FOO> || CONFIG_<FOO>_MODULE\n" . $herecurr) && + "Prefer IS_ENABLED(<FOO>) to ${CONFIG_}<FOO> || ${CONFIG_}<FOO>_MODULE\n" . $herecurr) && $fix) { $fixed[$fixlinenr] = "\+#if IS_ENABLED($config)"; } } -# check for case / default statements not preceded by break/fallthrough/switch - if ($line =~ /^.\s*(?:case\s+(?:$Ident|$Constant)\s*|default):/) { - my $has_break = 0; - my $has_statement = 0; - my $count = 0; - my $prevline = $linenr; - while ($prevline > 1 && ($file || $count < 3) && !$has_break) { - $prevline--; - my $rline = $rawlines[$prevline - 1]; - my $fline = $lines[$prevline - 1]; - last if ($fline =~ /^\@\@/); - next if ($fline =~ /^\-/); - next if ($fline =~ /^.(?:\s*(?:case\s+(?:$Ident|$Constant)[\s$;]*|default):[\s$;]*)*$/); - $has_break = 1 if ($rline =~ /fall[\s_-]*(through|thru)/i); - next if ($fline =~ /^.[\s$;]*$/); - $has_statement = 1; - $count++; - $has_break = 1 if ($fline =~ /\bswitch\b|\b(?:break\s*;[\s$;]*$|exit\s*\(\b|return\b|goto\b|continue\b)/); - } - if (!$has_break && $has_statement) { - WARN("MISSING_BREAK", - "Possible switch case/default not preceded by break or fallthrough comment\n" . $herecurr); - } - } - # check for /* fallthrough */ like comment, prefer fallthrough; my @fallthroughs = ( 'fallthrough', @@ -6613,7 +7328,8 @@ sub process { # check for various structs that are normally const (ops, kgdb, device_tree) # and avoid what seem like struct definitions 'struct foo {' - if ($line !~ /\bconst\b/ && + if (defined($const_structs) && + $line !~ /\bconst\b/ && $line =~ /\bstruct\s+($const_structs)\b(?!\s*\{)/) { WARN("CONST_STRUCT", "struct $1 should normally be const\n" . $herecurr); @@ -6621,12 +7337,14 @@ sub process { # use of NR_CPUS is usually wrong # ignore definitions of NR_CPUS and usage to define arrays as likely right +# ignore designated initializers using NR_CPUS if ($line =~ /\bNR_CPUS\b/ && $line !~ /^.\s*\s*#\s*if\b.*\bNR_CPUS\b/ && $line !~ /^.\s*\s*#\s*define\b.*\bNR_CPUS\b/ && $line !~ /^.\s*$Declare\s.*\[[^\]]*NR_CPUS[^\]]*\]/ && $line !~ /\[[^\]]*\.\.\.[^\]]*NR_CPUS[^\]]*\]/ && - $line !~ /\[[^\]]*NR_CPUS[^\]]*\.\.\.[^\]]*\]/) + $line !~ /\[[^\]]*NR_CPUS[^\]]*\.\.\.[^\]]*\]/ && + $line !~ /^.\s*\.\w+\s*=\s*.*\bNR_CPUS\b/) { WARN("NR_CPUS", "usage of NR_CPUS is often wrong - consider using cpu_possible(), num_possible_cpus(), for_each_possible_cpu(), etc\n" . $herecurr); @@ -6645,6 +7363,17 @@ sub process { "Using $1 should generally have parentheses around the comparison\n" . $herecurr); } +# return sysfs_emit(foo, fmt, ...) fmt without newline + if ($line =~ /\breturn\s+sysfs_emit\s*\(\s*$FuncArg\s*,\s*($String)/ && + substr($rawline, $-[6], $+[6] - $-[6]) !~ /\\n"$/) { + my $offset = $+[6] - 1; + if (WARN("SYSFS_EMIT", + "return sysfs_emit(...) formats should include a terminating newline\n" . $herecurr) && + $fix) { + substr($fixed[$fixlinenr], $offset, 0) = '\\n'; + } + } + # nested likely/unlikely calls if ($line =~ /\b(?:(?:un)?likely)\s*\(\s*!?\s*(IS_ERR(?:_OR_NULL|_VALUE)?|WARN)/) { WARN("LIKELY_MISUSE", @@ -6662,12 +7391,6 @@ sub process { } } -# check for mutex_trylock_recursive usage - if ($line =~ /mutex_trylock_recursive/) { - ERROR("LOCKING", - "recursive locking is bad, do not use this ever.\n" . $herecurr); - } - # check for lockdep_set_novalidate_class if ($line =~ /^.\s*lockdep_set_novalidate_class\s*\(/ || $line =~ /__lockdep_no_validate__\s*\)/ ) { @@ -6830,7 +7553,7 @@ sub process { exit(0); } - # This is not a patch, and we are are in 'no-patch' mode so + # This is not a patch, and we are in 'no-patch' mode so # just keep quiet. if (!$chk_patch && !$is_patch) { exit(0); @@ -6844,9 +7567,33 @@ sub process { if ($signoff == 0) { ERROR("MISSING_SIGN_OFF", "Missing Signed-off-by: line(s)\n"); - } elsif (!$authorsignoff) { - WARN("NO_AUTHOR_SIGN_OFF", - "Missing Signed-off-by: line by nominal patch author '$author'\n"); + } elsif ($authorsignoff != 1) { + # authorsignoff values: + # 0 -> missing sign off + # 1 -> sign off identical + # 2 -> names and addresses match, comments mismatch + # 3 -> addresses match, names different + # 4 -> names match, addresses different + # 5 -> names match, addresses excluding subaddress details (refer RFC 5233) match + + my $sob_msg = "'From: $author' != 'Signed-off-by: $author_sob'"; + + if ($authorsignoff == 0) { + ERROR("NO_AUTHOR_SIGN_OFF", + "Missing Signed-off-by: line by nominal patch author '$author'\n"); + } elsif ($authorsignoff == 2) { + CHK("FROM_SIGN_OFF_MISMATCH", + "From:/Signed-off-by: email comments mismatch: $sob_msg\n"); + } elsif ($authorsignoff == 3) { + WARN("FROM_SIGN_OFF_MISMATCH", + "From:/Signed-off-by: email name mismatch: $sob_msg\n"); + } elsif ($authorsignoff == 4) { + WARN("FROM_SIGN_OFF_MISMATCH", + "From:/Signed-off-by: email address mismatch: $sob_msg\n"); + } elsif ($authorsignoff == 5) { + WARN("FROM_SIGN_OFF_MISMATCH", + "From:/Signed-off-by: email subaddress mismatch: $sob_msg\n"); + } } }