diff options
Diffstat (limited to 'scripts/checkpatch.pl')
| -rwxr-xr-x | scripts/checkpatch.pl | 4562 |
1 files changed, 3995 insertions, 567 deletions
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 24793e19d8..e12a244037 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -1,16 +1,23 @@ -#!/usr/bin/env perl +#!/usr/bin/env perl +# SPDX-License-Identifier: GPL-2.0 +# # (c) 2001, Dave Jones. (the file handling bit) # (c) 2005, Joel Schopp <jschopp@austin.ibm.com> (the ugly bit) # (c) 2007,2008, Andy Whitcroft <apw@uk.ibm.com> (new conditions, test suite) # (c) 2008-2010 Andy Whitcroft <apw@canonical.com> # (c) 2013 Vasilis Tsiligiannis <acinonyx@openwrt.gr> (adapt for OpenWrt tree) -# Licensed under the terms of the GNU GPL License version 2 +# (c) 2010-2018 Joe Perches <joe@perches.com> use strict; use warnings; +use POSIX; +use File::Basename; +use Cwd 'abs_path'; +use Term::ANSIColor qw(:constants); +use Encode qw(decode encode); my $P = $0; -$P =~ s@.*/@@g; +my $D = dirname(abs_path($P)); my $V = '0.32-openwrt'; @@ -23,18 +30,42 @@ my $chk_patch = 1; my $tst_only; my $emacs = 0; my $terse = 0; +my $showfile = 0; my $file = 0; +my $git = 0; +my %git_commits = (); my $check = 0; +my $check_orig = 0; my $summary = 1; my $mailback = 0; my $summary_file = 0; my $show_types = 0; +my $list_types = 0; +my $fix = 0; +my $fix_inplace = 0; my $root; my %debug; +my %camelcase = (); +my %use_type = (); +my @use = (); my %ignore_type = (); my @ignore = (); my $help = 0; my $configuration_file = ".checkpatch.conf"; +my $max_line_length = 100; +my $ignore_perl_version = 0; +my $minimum_perl_version = 5.10.0; +my $min_conf_desc_length = 4; +my $spelling_file = "$D/spelling.txt"; +my $codespell = 0; +my $codespellfile = "/usr/share/codespell/dictionary.txt"; +my $conststructsfile = "$D/const_structs.checkpatch"; +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 $tabsize = 8; sub help { my ($exitcode) = @_; @@ -45,16 +76,34 @@ Version: $V Options: -q, --quiet quiet - --no-tree run without a kernel tree + --no-tree run without a OpenWrt tree --no-signoff do not check for 'Signed-off-by' line --patch treat FILE as patchfile (default) --emacs emacs compile window format --terse one line per report + --showfile emit diffed file position, not input file position + -g, --git treat FILE as a single commit or git revision range + single git commit with: + <rev> + <rev>^ + <rev>~n + multiple git commits with: + <rev1>..<rev2> + <rev1>...<rev2> + <rev>-<count> + git merges are ignored -f, --file treat FILE as regular source file --subjective, --strict enable more subjective tests + --list-types list the possible message types + --types TYPE(,TYPE2...) show only these comma separated message types --ignore TYPE(,TYPE2...) ignore various comma separated message types - --show-types show the message "types" in the output - --root=PATH PATH to the kernel tree root + --show-types show the specific message type in the output + --max-line-length=n set the maximum line length, (default $max_line_length) + if exceeded, warn on patches + requires --strict for use with --file + --min-conf-desc-length=n set the min description length, if shorter, warn + --tab-size=n set the number of spaces for tab (default $tabsize) + --root=PATH PATH to the OpenWrt tree root --no-summary suppress the per-file summary --mailback only produce a report in case of warnings/errors --summary-file include the filename in summary @@ -63,6 +112,22 @@ Options: is all off) --test-only=WORD report only warnings/errors containing WORD literally + --fix EXPERIMENTAL - may create horrible results + If correctable single-line errors exist, create + "<inputfile>.EXPERIMENTAL-checkpatch-fixes" + with potential errors corrected to the preferred + checkpatch style + --fix-inplace EXPERIMENTAL - may create horrible results + Is the same as --fix, but overwrites the input + file. It's your fault if there's no backup or git + --ignore-perl-version override checking of perl version. expect + runtime errors. + --codespell Use the codespell dictionary for spelling/typos + (default:/usr/share/codespell/dictionary.txt) + --codespellfile Use this codespell dictionary + --typedefsfile Read additional types from this file + --color[=WHEN] Use colors 'always', 'never', or only when output + is a terminal ('auto'). Default is 'auto'. -h, --help, --version display this help and exit When FILE is - read standard input. @@ -71,6 +136,38 @@ EOM exit($exitcode); } +sub uniq { + my %seen; + return grep { !$seen{$_}++ } @_; +} + +sub list_types { + my ($exitcode) = @_; + + my $count = 0; + + local $/ = undef; + + open(my $script, '<', abs_path($P)) or + die "$P: Can't read '$P' $!\n"; + + my $text = <$script>; + close($script); + + my @types = (); + # Also catch when type or level is passed through a variable + for ($text =~ /(?:(?:\bCHK|\bWARN|\bERROR|&\{\$msg_level})\s*\(|\$msg_type\s*=)\s*"([^"]+)"/g) { + push (@types, $_); + } + @types = sort(uniq(@types)); + print("#\tMessage type\n\n"); + foreach my $type (@types) { + print(++$count . "\t" . $type . "\n"); + } + + exit($exitcode); +} + my $conf = which_conf($configuration_file); if (-f $conf) { my @conf_args; @@ -97,6 +194,14 @@ if (-f $conf) { unshift(@ARGV, @conf_args) if @conf_args; } +# Perl's Getopt::Long allows options to take optional arguments after a space. +# Prevent --color by itself from consuming other arguments +foreach (@ARGV) { + if ($_ eq "--color" || $_ eq "-color") { + $_ = "--color=$color"; + } +} + GetOptions( 'q|quiet+' => \$quiet, 'tree!' => \$tree, @@ -104,44 +209,107 @@ GetOptions( 'patch!' => \$chk_patch, 'emacs!' => \$emacs, 'terse!' => \$terse, + 'showfile!' => \$showfile, 'f|file!' => \$file, + 'g|git!' => \$git, 'subjective!' => \$check, 'strict!' => \$check, 'ignore=s' => \@ignore, + 'types=s' => \@use, 'show-types!' => \$show_types, + 'list-types!' => \$list_types, + 'max-line-length=i' => \$max_line_length, + 'min-conf-desc-length=i' => \$min_conf_desc_length, + 'tab-size=i' => \$tabsize, 'root=s' => \$root, 'summary!' => \$summary, 'mailback!' => \$mailback, 'summary-file!' => \$summary_file, - + 'fix!' => \$fix, + 'fix-inplace!' => \$fix_inplace, + 'ignore-perl-version!' => \$ignore_perl_version, 'debug=s' => \%debug, 'test-only=s' => \$tst_only, + 'codespell!' => \$codespell, + 'codespellfile=s' => \$codespellfile, + 'typedefsfile=s' => \$typedefsfile, + 'color=s' => \$color, + 'no-color' => \$color, #keep old behaviors of -nocolor + 'nocolor' => \$color, #keep old behaviors of -nocolor 'h|help' => \$help, 'version' => \$help ) or help(1); help(0) if ($help); +list_types(0) if ($list_types); + +$fix = 1 if ($fix_inplace); +$check_orig = $check; + +die "$P: --git cannot be used with --file or --fix\n" if ($git && ($file || $fix)); + my $exit = 0; +my $perl_version_ok = 1; +if ($^V && $^V lt $minimum_perl_version) { + $perl_version_ok = 0; + printf "$P: requires at least perl version %vd\n", $minimum_perl_version; + exit(1) if (!$ignore_perl_version); +} + +#if no filenames are given, push '-' to read patch from stdin if ($#ARGV < 0) { - print "$P: no input files\n"; - exit(1); + push(@ARGV, '-'); } -@ignore = split(/,/, join(',',@ignore)); -foreach my $word (@ignore) { - $word =~ s/\s*\n?$//g; - $word =~ s/^\s*//g; - $word =~ s/\s+/ /g; - $word =~ tr/[a-z]/[A-Z]/; +if ($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"; +} + +# skip TAB size 1 to avoid additional checks on $tabsize - 1 +die "$P: Invalid TAB size: $tabsize\n" if ($tabsize < 2); + +sub hash_save_array_words { + my ($hashRef, $arrayRef) = @_; + + my @array = split(/,/, join(',', @$arrayRef)); + foreach my $word (@array) { + $word =~ s/\s*\n?$//g; + $word =~ s/^\s*//g; + $word =~ s/\s+/ /g; + $word =~ tr/[a-z]/[A-Z]/; + + next if ($word =~ m/^\s*#/); + next if ($word =~ m/^\s*$/); + + $hashRef->{$word}++; + } +} - next if ($word =~ m/^\s*#/); - next if ($word =~ m/^\s*$/); +sub hash_show_words { + my ($hashRef, $prefix) = @_; - $ignore_type{$word}++; + if (keys %$hashRef) { + print "\nNOTE: $prefix message types:"; + foreach my $word (sort keys %$hashRef) { + print " $word"; + } + print "\n"; + } } +hash_save_array_words(\%ignore_type, \@ignore); +hash_save_array_words(\%use_type, \@use); + my $dbg_values = 0; my $dbg_possible = 0; my $dbg_type = 0; @@ -192,11 +360,18 @@ our $Sparse = qr{ __force| __iomem| __must_check| - __init_refok| __kprobes| __ref| - __rcu + __refconst| + __refdata| + __rcu| + __private }x; +our $InitAttributePrefix = qr{__(?:mem|cpu|dev|net_|)}; +our $InitAttributeData = qr{$InitAttributePrefix(?:initdata\b)}; +our $InitAttributeConst = qr{$InitAttributePrefix(?:initconst\b)}; +our $InitAttributeInit = qr{$InitAttributePrefix(?:init\b)}; +our $InitAttribute = qr{$InitAttributeData|$InitAttributeConst|$InitAttributeInit}; # Notes to $Attribute: # We need \b after 'init' otherwise 'initconst' will cause a false positive in a check @@ -205,7 +380,7 @@ our $Attribute = qr{ __percpu| __nocast| __safe| - __bitwise__| + __bitwise| __packed__| __packed2__| __naked| @@ -214,33 +389,53 @@ our $Attribute = qr{ __noreturn| __used| __cold| + __pure| __noclone| __deprecated| __read_mostly| + __ro_after_init| __kprobes| - __(?:mem|cpu|dev|)(?:initdata|initconst|init\b)| + $InitAttribute| ____cacheline_aligned| ____cacheline_aligned_in_smp| ____cacheline_internodealigned_in_smp| __weak }x; our $Modifier; -our $Inline = qr{inline|__always_inline|noinline}; +our $Inline = qr{inline|__always_inline|noinline|__inline|__inline__}; our $Member = qr{->$Ident|\.$Ident|\[[^]]*\]}; our $Lval = qr{$Ident(?:$Member)*}; -our $Constant = qr{(?i:(?:[0-9]+|0x[0-9a-f]+)[ul]*)}; -our $Assignment = qr{(?:\*\=|/=|%=|\+=|-=|<<=|>>=|&=|\^=|\|=|=)}; -our $Compare = qr{<=|>=|==|!=|<|>}; +our $Int_type = qr{(?i)llu|ull|ll|lu|ul|l|u}; +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 $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]?}; +our $Float = qr{$Float_hex|$Float_dec|$Float_int}; +our $Constant = qr{$Float|$Binary|$Octal|$Hex|$Int}; +our $Assignment = qr{\*\=|/=|%=|\+=|-=|<<=|>>=|&=|\^=|\|=|=}; +our $Compare = qr{<=|>=|==|!=|<|(?<!-)>}; +our $Arithmetic = qr{\+|-|\*|\/|%}; our $Operators = qr{ <=|>=|==|!=| =>|->|<<|>>|<|>|!|~| - &&|\|\||,|\^|\+\+|--|&|\||\+|-|\*|\/|% + &&|\|\||,|\^|\+\+|--|&|\||$Arithmetic }x; +our $c90_Keywords = qr{do|for|while|if|else|return|goto|continue|switch|default|case|break}x; + +our $BasicType; our $NonptrType; +our $NonptrTypeMisordered; +our $NonptrTypeWithAttr; our $Type; +our $TypeMisordered; our $Declare; +our $DeclareMisordered; our $NON_ASCII_UTF8 = qr{ [\xC2-\xDF][\x80-\xBF] # non-overlong 2-byte @@ -257,39 +452,85 @@ our $UTF8 = qr{ | $NON_ASCII_UTF8 }x; -our $typeTypedefs = qr{(?x: +our $typeC99Typedefs = qr{(?:__)?(?:[us]_?)?int_?(?:8|16|32|64)_t}; +our $typeOtherOSTypedefs = qr{(?x: + u_(?:char|short|int|long) | # bsd + u(?:nchar|short|int|long) # sysv +)}; +our $typeKernelTypedefs = qr{(?x: (?:__)?(?:u|s|be|le)(?:8|16|32|64)| atomic_t )}; +our $typeTypedefs = qr{(?x: + $typeC99Typedefs\b| + $typeOtherOSTypedefs\b| + $typeKernelTypedefs\b +)}; + +our $zero_initializer = qr{(?:(?:0[xX])?0+$Int_type?|NULL|false)\b}; our $logFunctions = qr{(?x: - printk(?:_ratelimited|_once|)| - [a-z0-9]+_(?:printk|emerg|alert|crit|err|warning|warn|notice|info|debug|dbg|vdbg|devel|cont|WARN)(?:_ratelimited|_once|)| + printk(?:_ratelimited|_once|_deferred_once|_deferred|)| + (?:[a-z0-9]+_){1,2}(?:printk|emerg|alert|crit|err|warning|warn|notice|info|debug|dbg|vdbg|devel|cont|WARN)(?:_ratelimited|_once|)| + TP_printk| WARN(?:_RATELIMIT|_ONCE|)| panic| - MODULE_[A-Z_]+ + MODULE_[A-Z_]+| + seq_vprintf|seq_printf|seq_puts +)}; + +our $allocFunctions = qr{(?x: + (?:(?:devm_)? + (?:kv|k|v)[czm]alloc(?:_node|_array)? | + kstrdup(?:_const)? | + kmemdup(?:_nul)?) | + (?:\w+)?alloc_skb(?:_ip_align)? | + # dev_alloc_skb/netdev_alloc_skb, et al + dma_alloc_coherent )}; our $signature_tags = qr{(?xi: Signed-off-by:| + Co-developed-by:| Acked-by:| Tested-by:| Reviewed-by:| Reported-by:| + Suggested-by:| To:| Cc: )}; +our @typeListMisordered = ( + qr{char\s+(?:un)?signed}, + qr{int\s+(?:(?:un)?signed\s+)?short\s}, + qr{int\s+short(?:\s+(?:un)?signed)}, + qr{short\s+int(?:\s+(?:un)?signed)}, + qr{(?:un)?signed\s+int\s+short}, + qr{short\s+(?:un)?signed}, + qr{long\s+int\s+(?:un)?signed}, + qr{int\s+long\s+(?:un)?signed}, + qr{long\s+(?:un)?signed\s+int}, + qr{int\s+(?:un)?signed\s+long}, + qr{int\s+(?:un)?signed}, + qr{int\s+long\s+long\s+(?:un)?signed}, + qr{long\s+long\s+int\s+(?:un)?signed}, + qr{long\s+long\s+(?:un)?signed\s+int}, + qr{long\s+long\s+(?:un)?signed}, + qr{long\s+(?:un)?signed}, +); + our @typeList = ( qr{void}, - qr{(?:unsigned\s+)?char}, - qr{(?:unsigned\s+)?short}, - qr{(?:unsigned\s+)?int}, - qr{(?:unsigned\s+)?long}, - qr{(?:unsigned\s+)?long\s+int}, - qr{(?:unsigned\s+)?long\s+long}, - qr{(?:unsigned\s+)?long\s+long\s+int}, - qr{unsigned}, + qr{(?:(?:un)?signed\s+)?char}, + qr{(?:(?:un)?signed\s+)?short\s+int}, + qr{(?:(?:un)?signed\s+)?short}, + qr{(?:(?:un)?signed\s+)?int}, + qr{(?:(?:un)?signed\s+)?long\s+int}, + qr{(?:(?:un)?signed\s+)?long\s+long\s+int}, + qr{(?:(?:un)?signed\s+)?long\s+long}, + qr{(?:(?:un)?signed\s+)?long}, + qr{(?:un)?signed}, qr{float}, qr{double}, qr{bool}, @@ -299,21 +540,254 @@ our @typeList = ( qr{${Ident}_t}, qr{${Ident}_handler}, qr{${Ident}_handler_fn}, + @typeListMisordered, +); + +our $C90_int_types = qr{(?x: + long\s+long\s+int\s+(?:un)?signed| + long\s+long\s+(?:un)?signed\s+int| + long\s+long\s+(?:un)?signed| + (?:(?:un)?signed\s+)?long\s+long\s+int| + (?:(?:un)?signed\s+)?long\s+long| + int\s+long\s+long\s+(?:un)?signed| + int\s+(?:(?:un)?signed\s+)?long\s+long| + + long\s+int\s+(?:un)?signed| + long\s+(?:un)?signed\s+int| + long\s+(?:un)?signed| + (?:(?:un)?signed\s+)?long\s+int| + (?:(?:un)?signed\s+)?long| + int\s+long\s+(?:un)?signed| + int\s+(?:(?:un)?signed\s+)?long| + + int\s+(?:un)?signed| + (?:(?:un)?signed\s+)?int +)}; + +our @typeListFile = (); +our @typeListWithAttr = ( + @typeList, + qr{struct\s+$InitAttribute\s+$Ident}, + qr{union\s+$InitAttribute\s+$Ident}, ); + our @modifierList = ( qr{fastcall}, ); +our @modifierListFile = (); + +our @mode_permission_funcs = ( + ["module_param", 3], + ["module_param_(?:array|named|string)", 4], + ["module_param_array_named", 5], + ["debugfs_create_(?:file|u8|u16|u32|u64|x8|x16|x32|x64|size_t|atomic_t|bool|blob|regset32|u32_array)", 2], + ["proc_create(?:_data|)", 2], + ["(?:CLASS|DEVICE|SENSOR|SENSOR_DEVICE|IIO_DEVICE)_ATTR", 2], + ["IIO_DEV_ATTR_[A-Z_]+", 1], + ["SENSOR_(?:DEVICE_|)ATTR_2", 2], + ["SENSOR_TEMPLATE(?:_2|)", 3], + ["__ATTR", 2], +); + +#Create a search pattern for all these functions to speed up a loop below +our $mode_perms_search = ""; +foreach my $entry (@mode_permission_funcs) { + $mode_perms_search .= '|' if ($mode_perms_search ne ""); + $mode_perms_search .= $entry->[0]; +} +$mode_perms_search = "(?:${mode_perms_search})"; + +our %deprecated_apis = ( + "synchronize_rcu_bh" => "synchronize_rcu", + "synchronize_rcu_bh_expedited" => "synchronize_rcu_expedited", + "call_rcu_bh" => "call_rcu", + "rcu_barrier_bh" => "rcu_barrier", + "synchronize_sched" => "synchronize_rcu", + "synchronize_sched_expedited" => "synchronize_rcu_expedited", + "call_rcu_sched" => "call_rcu", + "rcu_barrier_sched" => "rcu_barrier", + "get_state_synchronize_sched" => "get_state_synchronize_rcu", + "cond_synchronize_sched" => "cond_synchronize_rcu", +); + +#Create a search pattern for all these strings to speed up a loop below +our $deprecated_apis_search = ""; +foreach my $entry (keys %deprecated_apis) { + $deprecated_apis_search .= '|' if ($deprecated_apis_search ne ""); + $deprecated_apis_search .= $entry; +} +$deprecated_apis_search = "(?:${deprecated_apis_search})"; + +our $mode_perms_world_writable = qr{ + S_IWUGO | + S_IWOTH | + S_IRWXUGO | + S_IALLUGO | + 0[0-7][0-7][2367] +}x; + +our %mode_permission_string_types = ( + "S_IRWXU" => 0700, + "S_IRUSR" => 0400, + "S_IWUSR" => 0200, + "S_IXUSR" => 0100, + "S_IRWXG" => 0070, + "S_IRGRP" => 0040, + "S_IWGRP" => 0020, + "S_IXGRP" => 0010, + "S_IRWXO" => 0007, + "S_IROTH" => 0004, + "S_IWOTH" => 0002, + "S_IXOTH" => 0001, + "S_IRWXUGO" => 0777, + "S_IRUGO" => 0444, + "S_IWUGO" => 0222, + "S_IXUGO" => 0111, +); + +#Create a search pattern for all these strings to speed up a loop below +our $mode_perms_string_search = ""; +foreach my $entry (keys %mode_permission_string_types) { + $mode_perms_string_search .= '|' if ($mode_perms_string_search ne ""); + $mode_perms_string_search .= $entry; +} +our $single_mode_perms_string_search = "(?:${mode_perms_string_search})"; +our $multi_mode_perms_string_search = qr{ + ${single_mode_perms_string_search} + (?:\s*\|\s*${single_mode_perms_string_search})* +}x; + +sub perms_to_octal { + my ($string) = @_; + + return trim($string) if ($string =~ /^\s*0[0-7]{3,3}\s*$/); + + my $val = ""; + my $oval = ""; + my $to = 0; + my $curpos = 0; + my $lastpos = 0; + while ($string =~ /\b(($single_mode_perms_string_search)\b(?:\s*\|\s*)?\s*)/g) { + $curpos = pos($string); + my $match = $2; + my $omatch = $1; + last if ($lastpos > 0 && ($curpos - length($omatch) != $lastpos)); + $lastpos = $curpos; + $to |= $mode_permission_string_types{$match}; + $val .= '\s*\|\s*' if ($val ne ""); + $val .= $match; + $oval .= $omatch; + } + $oval =~ s/^\s*\|\s*//; + $oval =~ s/\s*\|\s*$//; + return sprintf("%04o", $to); +} our $allowed_asm_includes = qr{(?x: irq| - memory + memory| + time| + reboot )}; # memory.h: ARM has a custom one +# Load common spelling mistakes and build regular expression list. +my $misspellings; +my %spelling_fix; + +if (open(my $spelling, '<', $spelling_file)) { + while (<$spelling>) { + my $line = $_; + + $line =~ s/\s*\n?$//g; + $line =~ s/^\s*//g; + + next if ($line =~ m/^\s*#/); + next if ($line =~ m/^\s*$/); + + my ($suspect, $fix) = split(/\|\|/, $line); + + $spelling_fix{$suspect} = $fix; + } + close($spelling); +} else { + warn "No typos will be found - file '$spelling_file': $!\n"; +} + +if ($codespell) { + if (open(my $spelling, '<', $codespellfile)) { + while (<$spelling>) { + my $line = $_; + + $line =~ s/\s*\n?$//g; + $line =~ s/^\s*//g; + + next if ($line =~ m/^\s*#/); + next if ($line =~ m/^\s*$/); + next if ($line =~ m/, disabled/i); + + $line =~ s/,.*$//; + + my ($suspect, $fix) = split(/->/, $line); + + $spelling_fix{$suspect} = $fix; + } + close($spelling); + } else { + warn "No codespell typos will be found - file '$codespellfile': $!\n"; + } +} + +$misspellings = join("|", sort keys %spelling_fix) if keys %spelling_fix; + +sub read_words { + my ($wordsRef, $file) = @_; + + if (open(my $words, '<', $file)) { + while (<$words>) { + my $line = $_; + + $line =~ s/\s*\n?$//g; + $line =~ s/^\s*//g; + + next if ($line =~ m/^\s*#/); + next if ($line =~ m/^\s*$/); + if ($line =~ /\s/) { + print("$file: '$line' invalid - ignored\n"); + next; + } + + $$wordsRef .= '|' if ($$wordsRef ne ""); + $$wordsRef .= $line; + } + close($file); + return 1; + } + + 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 $typeOtherTypedefs = ""; +if (length($typedefsfile)) { + read_words(\$typeOtherTypedefs, $typedefsfile) + or warn "No additional types will be considered - file '$typedefsfile': $!\n"; +} +$typeTypedefs .= '|' . $typeOtherTypedefs if ($typeOtherTypedefs ne ""); + sub build_types { - my $mods = "(?x: \n" . join("|\n ", @modifierList) . "\n)"; - my $all = "(?x: \n" . join("|\n ", @typeList) . "\n)"; + my $mods = "(?x: \n" . join("|\n ", (@modifierList, @modifierListFile)) . "\n)"; + my $all = "(?x: \n" . join("|\n ", (@typeList, @typeListFile)) . "\n)"; + my $Misordered = "(?x: \n" . join("|\n ", @typeListMisordered) . "\n)"; + my $allWithAttr = "(?x: \n" . join("|\n ", @typeListWithAttr) . "\n)"; $Modifier = qr{(?:$Attribute|$Sparse|$mods)}; + $BasicType = qr{ + (?:$typeTypedefs\b)| + (?:${all}\b) + }x; $NonptrType = qr{ (?:$Modifier\s+|const\s+)* (?: @@ -323,16 +797,37 @@ sub build_types { ) (?:\s+$Modifier|\s+const)* }x; + $NonptrTypeMisordered = qr{ + (?:$Modifier\s+|const\s+)* + (?: + (?:${Misordered}\b) + ) + (?:\s+$Modifier|\s+const)* + }x; + $NonptrTypeWithAttr = qr{ + (?:$Modifier\s+|const\s+)* + (?: + (?:typeof|__typeof__)\s*\([^\)]*\)| + (?:$typeTypedefs\b)| + (?:${allWithAttr}\b) + ) + (?:\s+$Modifier|\s+const)* + }x; $Type = qr{ $NonptrType - (?:(?:\s|\*|\[\])+\s*const|(?:\s|\*|\[\])+|(?:\s*\[\s*\])+)? + (?:(?:\s|\*|\[\])+\s*const|(?:\s|\*\s*(?:const\s*)?|\[\])+|(?:\s*\[\s*\])+){0,4} (?:\s+$Inline|\s+$Modifier)* }x; - $Declare = qr{(?:$Storage\s+)?$Type}; + $TypeMisordered = qr{ + $NonptrTypeMisordered + (?:(?:\s|\*|\[\])+\s*const|(?:\s|\*\s*(?:const\s*)?|\[\])+|(?:\s*\[\s*\])+){0,4} + (?:\s+$Inline|\s+$Modifier)* + }x; + $Declare = qr{(?:$Storage\s+(?:$Inline\s+)?)?$Type}; + $DeclareMisordered = qr{(?:$Storage\s+(?:$Inline\s+)?)?$TypeMisordered}; } build_types(); - our $Typecast = qr{\s*(\(\s*$NonptrType\s*\)){0,1}\s*}; # Using $balanced_parens, $LvalOrFunc, or $FuncArg @@ -340,26 +835,216 @@ our $Typecast = qr{\s*(\(\s*$NonptrType\s*\)){0,1}\s*}; # Any use must be runtime checked with $^V our $balanced_parens = qr/(\((?:[^\(\)]++|(?-1))*\))/; -our $LvalOrFunc = qr{($Lval)\s*($balanced_parens{0,1})\s*}; -our $FuncArg = qr{$Typecast{0,1}($LvalOrFunc|$Constant)}; +our $LvalOrFunc = qr{((?:[\&\*]\s*)?$Lval)\s*($balanced_parens{0,1})\s*}; +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*\( +)}; sub deparenthesize { my ($string) = @_; return "" if (!defined($string)); - $string =~ s@^\s*\(\s*@@g; - $string =~ s@\s*\)\s*$@@g; + + while ($string =~ /^\s*\(.*\)\s*$/) { + $string =~ s@^\s*\(\s*@@; + $string =~ s@\s*\)\s*$@@; + } + $string =~ s@\s+@ @g; + return $string; } +sub seed_camelcase_file { + my ($file) = @_; + + return if (!(-f $file)); + + local $/; + + open(my $include_file, '<', "$file") + or warn "$P: Can't read '$file' $!\n"; + my $text = <$include_file>; + close($include_file); + + my @lines = split('\n', $text); + + foreach my $line (@lines) { + next if ($line !~ /(?:[A-Z][a-z]|[a-z][A-Z])/); + if ($line =~ /^[ \t]*(?:#[ \t]*define|typedef\s+$Type)\s+(\w*(?:[A-Z][a-z]|[a-z][A-Z])\w*)/) { + $camelcase{$1} = 1; + } elsif ($line =~ /^\s*$Declare\s+(\w*(?:[A-Z][a-z]|[a-z][A-Z])\w*)\s*[\(\[,;]/) { + $camelcase{$1} = 1; + } elsif ($line =~ /^\s*(?:union|struct|enum)\s+(\w*(?:[A-Z][a-z]|[a-z][A-Z])\w*)\s*[;\{]/) { + $camelcase{$1} = 1; + } + } +} + +our %maintained_status = (); + +sub is_maintained_obsolete { + my ($filename) = @_; + + return 0 if (!$tree || !(-e "$root/scripts/get_maintainer.pl")); + + if (!exists($maintained_status{$filename})) { + $maintained_status{$filename} = `perl $root/scripts/get_maintainer.pl --status --nom --nol --nogit --nogit-fallback -f $filename 2>&1`; + } + + return $maintained_status{$filename} =~ /obsolete/i; +} + +sub is_SPDX_License_valid { + my ($license) = @_; + + return 1 if (!$tree || which("python") eq "" || !(-e "$root/scripts/spdxcheck.py") || !(-e "$root/.git")); + + my $root_path = abs_path($root); + my $status = `cd "$root_path"; echo "$license" | python scripts/spdxcheck.py -`; + return 0 if ($status ne ""); + return 1; +} + +my $camelcase_seeded = 0; +sub seed_camelcase_includes { + return if ($camelcase_seeded); + + my $files; + my $camelcase_cache = ""; + my @include_files = (); + + $camelcase_seeded = 1; + + if (-e ".git") { + 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"; + } else { + my $last_mod_date = 0; + $files = `find $root/include -name "*.h"`; + @include_files = split('\n', $files); + foreach my $file (@include_files) { + my $date = POSIX::strftime("%Y%m%d%H%M", + localtime((stat $file)[9])); + $last_mod_date = $date if ($last_mod_date < $date); + } + $camelcase_cache = ".checkpatch-camelcase.date.$last_mod_date"; + } + + if ($camelcase_cache ne "" && -f $camelcase_cache) { + open(my $camelcase_file, '<', "$camelcase_cache") + or warn "$P: Can't read '$camelcase_cache' $!\n"; + while (<$camelcase_file>) { + chomp; + $camelcase{$_} = 1; + } + close($camelcase_file); + + return; + } + + if (-e ".git") { + $files = `${git_command} ls-files "include/*.h"`; + @include_files = split('\n', $files); + } + + foreach my $file (@include_files) { + seed_camelcase_file($file); + } + + if ($camelcase_cache ne "") { + unlink glob ".checkpatch-camelcase.*"; + open(my $camelcase_file, '>', "$camelcase_cache") + or warn "$P: Can't write '$camelcase_cache' $!\n"; + foreach (sort { lc($a) cmp lc($b) } keys(%camelcase)) { + print $camelcase_file ("$_\n"); + } + close($camelcase_file); + } +} + +sub git_commit_info { + my ($commit, $id, $desc) = @_; + + return ($id, $desc) if ((which("git") eq "") || !(-e ".git")); + + my $output = `${git_command} log --no-color --format='%H %s' -1 $commit 2>&1`; + $output =~ s/^\s*//gm; + my @lines = split("\n", $output); + + return ($id, $desc) if ($#lines < 0); + + if ($lines[0] =~ /^error: short SHA1 $commit is ambiguous/) { +# Maybe one day convert this block of bash into something that returns +# all matching commit ids, but it's very slow... +# +# echo "checking commits $1..." +# git rev-list --remotes | grep -i "^$1" | +# while read line ; do +# 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\./) { + $id = undef; + } else { + $id = substr($lines[0], 0, 12); + $desc = substr($lines[0], 41); + } + + return ($id, $desc); +} + $chk_signoff = 0 if ($file); my @rawlines = (); my @lines = (); +my @fixed = (); +my @fixed_inserted = (); +my @fixed_deleted = (); +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 ($git && !-e ".git"); + +if ($git) { + my @commits = (); + foreach my $commit_expr (@ARGV) { + my $git_range; + if ($commit_expr =~ m/^(.*)-(\d+)$/) { + $git_range = "-$2 $1"; + } elsif ($commit_expr =~ m/\.\./) { + $git_range = "$commit_expr"; + } else { + $git_range = "-1 $commit_expr"; + } + my $lines = `${git_command} log --no-color --no-merges --pretty=format:'%H %s' $git_range`; + foreach my $line (split(/\n/, $lines)) { + $line =~ /^([0-9a-fA-F]{40,40}) (.*)$/; + next if (!defined($1) || !defined($2)); + my $sha1 = $1; + my $subject = $2; + unshift(@commits, $sha1); + $git_commits{$sha1} = $subject; + } + } + die "$P: no git commits after extraction!\n" if (@commits == 0); + @ARGV = @commits; +} + my $vname; +$allow_c99_comments = !defined $ignore_type{"C99_COMMENT_TOLERANCE"}; for my $filename (@ARGV) { my $FILE; - if ($file) { + if ($git) { + open($FILE, '-|', "git format-patch -M --stdout -1 $filename") || + die "$P: $filename: git format-patch failed - $!\n"; + } elsif ($file) { open($FILE, '-|', "diff -u /dev/null $filename") || die "$P: $filename: diff failed - $!\n"; } elsif ($filename eq '-') { @@ -370,19 +1055,56 @@ for my $filename (@ARGV) { } if ($filename eq '-') { $vname = 'Your patch'; + } elsif ($git) { + $vname = "Commit " . substr($filename, 0, 12) . ' ("' . $git_commits{$filename} . '")'; } else { $vname = $filename; } while (<$FILE>) { chomp; push(@rawlines, $_); + $vname = qq("$1") if ($filename eq '-' && $_ =~ m/^Subject:\s+(.+)/i); } close($FILE); + + if ($#ARGV > 0 && $quiet == 0) { + print '-' x length($vname) . "\n"; + print "$vname\n"; + print '-' x length($vname) . "\n"; + } + if (!process($filename)) { $exit = 1; } @rawlines = (); @lines = (); + @fixed = (); + @fixed_inserted = (); + @fixed_deleted = (); + $fixlinenr = -1; + @modifierListFile = (); + @typeListFile = (); + build_types(); +} + +if (!$quiet) { + hash_show_words(\%use_type, "Used"); + hash_show_words(\%ignore_type, "Ignored"); + + if (!$perl_version_ok) { + print << "EOM" + +NOTE: perl $^V is not modern enough to detect all possible issues. + An upgrade to at least perl $minimum_perl_version is suggested. +EOM + } + if ($exit) { + print << "EOM" + +NOTE: If any of the errors are false positives, please report + them to the maintainer, see CHECKPATCH in MAINTAINERS. +EOM + } } exit($exit); @@ -402,12 +1124,13 @@ sub top_of_openwrt_tree { } } return 1; - } +} sub parse_email { my ($formatted_email) = @_; my $name = ""; + my $name_comment = ""; my $address = ""; my $comment = ""; @@ -421,9 +1144,9 @@ sub parse_email { } elsif ($formatted_email =~ /(\S+\@\S+)(.*)$/) { $address = $1; $comment = $2 if defined $2; - $formatted_email =~ s/$address.*$//; + $formatted_email =~ s/\Q$address\E.*$//; $name = $formatted_email; - $name =~ s/^\s+|\s+$//g; + $name = trim($name); $name =~ s/^\"|\"$//g; # If there's a name left after stripping spaces and # leading quotes, and the address doesn't have both @@ -438,9 +1161,13 @@ sub parse_email { } } - $name =~ s/^\s+|\s+$//g; + $name = trim($name); $name =~ s/^\"|\"$//g; - $address =~ s/^\s+|\s+$//g; + $name =~ s/(\s*\([^\)]+\))\s*//; + if (defined($1)) { + $name_comment = trim($1); + } + $address = trim($address); $address =~ s/^\<|\>$//g; if ($name =~ /[^\w \-]/i) { ##has "must quote" chars @@ -448,7 +1175,7 @@ sub parse_email { $name = "\"$name\""; } - return ($name, $address, $comment); + return ($name, $name_comment, $address, $comment); } sub format_email { @@ -456,9 +1183,9 @@ sub format_email { my $formatted_email; - $name =~ s/^\s+|\s+$//g; + $name = trim($name); $name =~ s/^\"|\"$//g; - $address =~ s/^\s+|\s+$//g; + $address = trim($address); if ($name =~ /[^\w \-]/i) { ##has "must quote" chars $name =~ s/(?<!\\)"/\\"/g; ##escape quotes @@ -474,6 +1201,35 @@ sub format_email { return $formatted_email; } +sub reformat_email { + my ($email) = @_; + + my ($email_name, $name_comment, $email_address, $comment) = parse_email($email); + return format_email($email_name, $email_address); +} + +sub same_email_addresses { + my ($email1, $email2) = @_; + + my ($email1_name, $name1_comment, $email1_address, $comment1) = parse_email($email1); + my ($email2_name, $name2_comment, $email2_address, $comment2) = parse_email($email2); + + return $email1_name eq $email2_name && + $email1_address eq $email2_address; +} + +sub which { + my ($bin) = @_; + + foreach my $path (split(/:/, $ENV{PATH})) { + if (-e "$path/$bin") { + return "$path/$bin"; + } + } + + return ""; +} + sub which_conf { my ($conf) = @_; @@ -495,7 +1251,7 @@ sub expand_tabs { if ($c eq "\t") { $res .= ' '; $n++; - for (; ($n % 8) != 0; $n++) { + for (; ($n % $tabsize) != 0; $n++) { $res .= ' '; } next; @@ -551,7 +1307,7 @@ sub sanitise_line { for ($off = 1; $off < length($line); $off++) { $c = substr($line, $off, 1); - # Comments we are wacking completly including the begin + # Comments we are whacking completely including the begin # and end, all to $;. if ($sanitise_quote eq '' && substr($line, $off, 2) eq '/*') { $sanitise_quote = '*/'; @@ -620,9 +1376,22 @@ sub sanitise_line { $res =~ s@(\#\s*(?:error|warning)\s+).*@$1$clean@; } + if ($allow_c99_comments && $res =~ m@(//.*$)@) { + my $match = $1; + $res =~ s/\Q$match\E/"$;" x length($match)/e; + } + return $res; } +sub get_quoted_string { + my ($line, $rawline) = @_; + + return "" if (!defined($line) || !defined($rawline)); + return "" if ($line !~ m/($String)/g); + return substr($rawline, $-[0], $+[0] - $-[0]); +} + sub ctx_statement_block { my ($linenr, $remain, $off) = @_; my $line = $linenr - 1; @@ -911,8 +1680,16 @@ sub ctx_statement_level { sub ctx_locate_comment { my ($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 @@ -966,6 +1743,28 @@ sub raw_line { return $line; } +sub get_stat_real { + my ($linenr, $lc) = @_; + + my $stat_real = raw_line($linenr, 0); + for (my $count = $linenr + 1; $count <= $lc; $count++) { + $stat_real = $stat_real . "\n" . raw_line($count, 0); + } + + return $stat_real; +} + +sub get_stat_here { + my ($linenr, $cnt, $here) = @_; + + my $herectx = $here . "\n"; + for (my $n = 0; $n < $cnt; $n++) { + $herectx .= raw_line($linenr, $n) . "\n"; + } + + return $herectx; +} + sub cat_vet { my ($vet) = @_; my ($res, $coded); @@ -1228,13 +2027,13 @@ sub possible { for my $modifier (split(' ', $possible)) { if ($modifier !~ $notPermitted) { warn "MODIFIER: $modifier ($possible) ($line)\n" if ($dbg_possible); - push(@modifierList, $modifier); + push(@modifierListFile, $modifier); } } } else { warn "POSSIBLE: $possible ($line)\n" if ($dbg_possible); - push(@typeList, $possible); + push(@typeListFile, $possible); } build_types(); } else { @@ -1245,47 +2044,169 @@ sub possible { my $prefix = ''; sub show_type { - return !defined $ignore_type{$_[0]}; + my ($type) = @_; + + $type =~ tr/[a-z]/[A-Z]/; + + return defined $use_type{$type} if (scalar keys %use_type > 0); + + return !defined $ignore_type{$type}; } sub report { - if (!show_type($_[1]) || - (defined $tst_only && $_[2] !~ /\Q$tst_only\E/)) { + my ($level, $type, $msg) = @_; + + if (!show_type($type) || + (defined $tst_only && $msg !~ /\Q$tst_only\E/)) { return 0; } - my $line; + my $output = ''; + if ($color) { + if ($level eq 'ERROR') { + $output .= RED; + } elsif ($level eq 'WARNING') { + $output .= YELLOW; + } else { + $output .= GREEN; + } + } + $output .= $prefix . $level . ':'; if ($show_types) { - $line = "$prefix$_[0]:$_[1]: $_[2]\n"; - } else { - $line = "$prefix$_[0]: $_[2]\n"; + $output .= BLUE if ($color); + $output .= "$type:"; } - $line = (split('\n', $line))[0] . "\n" if ($terse); + $output .= RESET if ($color); + $output .= ' ' . $msg . "\n"; - push(our @report, $line); + if ($showfile) { + my @lines = split("\n", $output, -1); + splice(@lines, 1, 1); + $output = join("\n", @lines); + } + $output = (split('\n', $output))[0] . "\n" if ($terse); + + push(our @report, $output); return 1; } + sub report_dump { our @report; } +sub fixup_current_range { + my ($lineRef, $offset, $length) = @_; + + if ($$lineRef =~ /^\@\@ -\d+,\d+ \+(\d+),(\d+) \@\@/) { + my $o = $1; + my $l = $2; + my $no = $o + $offset; + my $nl = $l + $length; + $$lineRef =~ s/\+$o,$l \@\@/\+$no,$nl \@\@/; + } +} + +sub fix_inserted_deleted_lines { + my ($linesRef, $insertedRef, $deletedRef) = @_; + + my $range_last_linenr = 0; + my $delta_offset = 0; + + my $old_linenr = 0; + my $new_linenr = 0; + + my $next_insert = 0; + my $next_delete = 0; + + my @lines = (); + + my $inserted = @{$insertedRef}[$next_insert++]; + my $deleted = @{$deletedRef}[$next_delete++]; + + foreach my $old_line (@{$linesRef}) { + my $save_line = 1; + my $line = $old_line; #don't modify the array + if ($line =~ /^(?:\+\+\+|\-\-\-)\s+\S+/) { #new filename + $delta_offset = 0; + } elsif ($line =~ /^\@\@ -\d+,\d+ \+\d+,\d+ \@\@/) { #new hunk + $range_last_linenr = $new_linenr; + fixup_current_range(\$line, $delta_offset, 0); + } + + while (defined($deleted) && ${$deleted}{'LINENR'} == $old_linenr) { + $deleted = @{$deletedRef}[$next_delete++]; + $save_line = 0; + fixup_current_range(\$lines[$range_last_linenr], $delta_offset--, -1); + } + + while (defined($inserted) && ${$inserted}{'LINENR'} == $old_linenr) { + push(@lines, ${$inserted}{'LINE'}); + $inserted = @{$insertedRef}[$next_insert++]; + $new_linenr++; + fixup_current_range(\$lines[$range_last_linenr], $delta_offset++, 1); + } + + if ($save_line) { + push(@lines, $line); + $new_linenr++; + } + + $old_linenr++; + } + + return @lines; +} + +sub fix_insert_line { + my ($linenr, $line) = @_; + + my $inserted = { + LINENR => $linenr, + LINE => $line, + }; + push(@fixed_inserted, $inserted); +} + +sub fix_delete_line { + my ($linenr, $line) = @_; + + my $deleted = { + LINENR => $linenr, + LINE => $line, + }; + + push(@fixed_deleted, $deleted); +} + sub ERROR { - if (report("ERROR", $_[0], $_[1])) { + my ($type, $msg) = @_; + + if (report("ERROR", $type, $msg)) { our $clean = 0; our $cnt_error++; + return 1; } + return 0; } sub WARN { - if (report("WARNING", $_[0], $_[1])) { + my ($type, $msg) = @_; + + if (report("WARNING", $type, $msg)) { our $clean = 0; our $cnt_warn++; + return 1; } + return 0; } sub CHK { - if ($check && report("CHECK", $_[0], $_[1])) { + my ($type, $msg) = @_; + + if ($check && report("CHECK", $type, $msg)) { our $clean = 0; our $cnt_chk++; + return 1; } + return 0; } sub check_absolute_file { @@ -1316,6 +2237,53 @@ sub check_absolute_file { } } +sub trim { + my ($string) = @_; + + $string =~ s/^\s+|\s+$//g; + + return $string; +} + +sub ltrim { + my ($string) = @_; + + $string =~ s/^\s+//; + + return $string; +} + +sub rtrim { + my ($string) = @_; + + $string =~ s/\s+$//; + + return $string; +} + +sub string_find_replace { + my ($string, $find, $replace) = @_; + + $string =~ s/$find/$replace/g; + + return $string; +} + +sub tabify { + my ($leading) = @_; + + my $source_indent = $tabsize; + my $max_spaces_before_tab = $source_indent - 1; + my $spaces_to_tab = " " x $source_indent; + + #convert leading spaces to tabs + 1 while $leading =~ s@^([\t]*)$spaces_to_tab@$1\t@g; + #Remove spaces before a tab + 1 while $leading =~ s@^([\t]*)( {1,$max_spaces_before_tab})\t@$1\t@g; + + return "$leading"; +} + sub pos_last_openparen { my ($line) = @_; @@ -1343,7 +2311,20 @@ sub pos_last_openparen { } } - return $last_openparen + 1; + return length(expand_tabs(substr($line, 0, $last_openparen))) + 1; +} + +sub get_raw_comment { + my ($line, $rawline) = @_; + my $comment = ''; + + for my $i (0 .. (length($line) - 1)) { + if (substr($line, $i, 1) eq "$;") { + $comment .= substr($rawline, $i, 1); + } + } + + return $comment; } sub process { @@ -1362,10 +2343,23 @@ sub process { our $clean = 1; my $signoff = 0; + my $author = ''; + my $authorsignoff = 0; my $is_patch = 0; - - my $in_header_lines = 1; + my $is_binding_patch = -1; + my $in_header_lines = $file ? 0 : 1; my $in_commit_log = 0; #Scanning lines before patch + my $has_patch_separator = 0; #Found a --- line + my $has_commit_log = 0; #Encountered lines before patch + my $commit_log_lines = 0; #Number of commit log lines + my $commit_log_possible_stack_dump = 0; + my $commit_log_long_line = 0; + my $commit_log_has_diff = 0; + my $reported_maintainer_file = 0; + my $non_utf8_charset = 0; + + my $last_blank_line = 0; + my $last_coalesced_string_linenr = -1; our @report = (); our $cnt_lines = 0; @@ -1378,6 +2372,7 @@ sub process { my $realline = 0; my $realcnt = 0; my $here = ''; + my $context_function; #undef'd unless there's a known function my $in_comment = 0; my $comment_edge = 0; my $first_line = 0; @@ -1391,14 +2386,21 @@ sub process { my %suppress_export; my $suppress_statement = 0; - # Pre-scan the patch sanitizing the lines. + my %signatures = (); + + my $camelcase_file_seeded = 0; + + my $checklicenseline = 1; + sanitise_line_reset(); my $line; foreach my $rawline (@rawlines) { $linenr++; $line = $rawline; - if ($rawline=~/^\@\@ -\d+(?:,\d+)? \+(\d+)(,(\d+))? \@\@/) { + push(@fixed, $rawline) if ($fix); + + if ($rawline =~ /^\@\@ -\d+(?:,\d+)? \+(\d+)(,(\d+))? \@\@/) { $realline=$1-1; if (defined $2) { $realcnt=$3+1; @@ -1462,13 +2464,28 @@ sub process { $realcnt = 0; $linenr = 0; + $fixlinenr = -1; foreach my $line (@lines) { $linenr++; + $fixlinenr++; + my $sline = $line; #copy of $line + $sline =~ s/$;/ /g; #with comments as spaces my $rawline = $rawlines[$linenr - 1]; + my $raw_comment = get_raw_comment($line, $rawline); + +# check if it's a mode change, rename or start of a patch + if (!$in_commit_log && + ($line =~ /^ mode change [0-7]+ => [0-7]+ \S+\s*$/ || + ($line =~ /^rename (?:from|to) \S+\s*$/ || + $line =~ /^diff --git a\/[\w\/\.\_\-]+ b\/\S+\s*$/))) { + $is_patch = 1; + } #extract the line range in the file after the patch is applied - if ($line=~/^\@\@ -\d+(?:,\d+)? \+(\d+)(,(\d+))? \@\@/) { + if (!$in_commit_log && + $line =~ /^\@\@ -\d+(?:,\d+)? \+(\d+)(,(\d+))? \@\@(.*)/) { + my $context = $4; $is_patch = 1; $first_line = $linenr + 1; $realline=$1-1; @@ -1484,6 +2501,11 @@ sub process { %suppress_whiletrailers = (); %suppress_export = (); $suppress_statement = 0; + if ($context =~ /\b(\w+)\s*\(/) { + $context_function = $1; + } else { + undef $context_function; + } next; # track the line number as we move through the hunk, note that @@ -1509,21 +2531,19 @@ sub process { my $hunk_line = ($realcnt != 0); -#make up the handle for any error we report on this line - $prefix = "$filename:$realline: " if ($emacs && $file); - $prefix = "$filename:$linenr: " if ($emacs && !$file); - $here = "#$linenr: " if (!$file); $here = "#$realline: " if ($file); + my $found_file = 0; # extract the filename as it passes if ($line =~ /^diff --git.*?(\S+)$/) { $realfile = $1; - $realfile =~ s@^([^/]*)/@@; + $realfile =~ s@^([^/]*)/@@ if (!$file); $in_commit_log = 0; + $found_file = 1; } elsif ($line =~ /^\+\+\+\s+(\S+)/) { $realfile = $1; - $realfile =~ s@^([^/]*)/@@; + $realfile =~ s@^([^/]*)/@@ if (!$file); $in_commit_log = 0; $p1_prefix = $1; @@ -1537,6 +2557,44 @@ sub process { ERROR("MODIFIED_INCLUDE_ASM", "do not modify files in include/asm, change architecture specific files in include/asm-<architecture>\n" . "$here$rawline\n"); } + $found_file = 1; + } + +#make up the handle for any error we report on this line + if ($showfile) { + $prefix = "$realfile:$realline: " + } elsif ($emacs) { + if ($file) { + $prefix = "$filename:$realline: "; + } else { + $prefix = "$filename:$linenr: "; + } + } + + if ($found_file) { + if (is_maintained_obsolete($realfile)) { + WARN("OBSOLETE", + "$realfile is marked as 'obsolete' in the MAINTAINERS hierarchy. No unnecessary modifications please.\n"); + } + if ($realfile =~ m@^(?:drivers/net/|net/|drivers/staging/)@) { + $check = 1; + } else { + $check = $check_orig; + } + $checklicenseline = 1; + + if ($realfile !~ /^MAINTAINERS/) { + my $last_binding_patch = $is_binding_patch; + + $is_binding_patch = () = $realfile =~ m@^(?:Documentation/devicetree/|include/dt-bindings/)@; + + if (($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.rst\n"); + } + } + next; } @@ -1548,44 +2606,110 @@ sub process { $cnt_lines++ if ($realcnt != 0); +# Verify the existence of a commit log if appropriate +# 2 is used because a $signature is counted in $commit_log_lines + if ($in_commit_log) { + if ($line !~ /^\s*$/) { + $commit_log_lines++; #could be a $signature + } + } elsif ($has_commit_log && $commit_log_lines < 2) { + WARN("COMMIT_MESSAGE", + "Missing commit description - Add an appropriate one\n"); + $commit_log_lines = 2; #warn only once + } + +# Check if the commit log has what seems like a diff which can confuse patch + if ($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*(?:\-\-\-\s+a/|\+\+\+\s+b/)@ || + $line =~ m/^\s*\@\@ \-\d+,\d+ \+\d+,\d+ \@\@/)) { + ERROR("DIFF_IN_COMMIT_MSG", + "Avoid using diff content in the commit message - patch(1) might not work\n" . $herecurr); + $commit_log_has_diff = 1; + } + # Check for incorrect file permissions if ($line =~ /^new (file )?mode.*[7531]\d{0,2}$/) { my $permhere = $here . "FILE: $realfile\n"; - if ($realfile =~ /(Makefile|Kconfig|\.c|\.h|\.S|\.tmpl)$/) { + if ($realfile !~ m@scripts/@ && + $realfile !~ /\.(py|pl|awk|sh)$/) { ERROR("EXECUTE_PERMISSIONS", "do not set execute permissions for source files\n" . $permhere); } } +# Check the patch for a From: + if (decode("MIME-Header", $line) =~ /^From:\s*(.*)/) { + $author = $1; + $author = encode("utf8", $author) if ($line =~ /=\?utf-8\?/i); + $author =~ s/"//g; + $author = reformat_email($author); + } + # Check the patch for a signoff: - if ($line =~ /^\s*signed-off-by:/i) { + if ($line =~ /^\s*signed-off-by:\s*(.*)/i) { $signoff++; $in_commit_log = 0; + if ($author ne '') { + if (same_email_addresses($1, $author)) { + $authorsignoff = 1; + } + } + } + +# Check for patch separator + if ($line =~ /^---$/) { + $has_patch_separator = 1; + $in_commit_log = 0; + } + +# Check if MAINTAINERS is being updated. If so, there's probably no need to +# emit the "does MAINTAINERS need updating?" message on file add/move/delete + if ($line =~ /^\s*MAINTAINERS\s*\|/) { + $reported_maintainer_file = 1; } # Check signature styles if (!$in_header_lines && - $line =~ /^(\s*)($signature_tags)(\s*)(.*)/) { + $line =~ /^(\s*)([a-z0-9_-]+by:|$signature_tags)(\s*)(.*)/i) { my $space_before = $1; my $sign_off = $2; my $space_after = $3; my $email = $4; my $ucfirst_sign_off = ucfirst(lc($sign_off)); - if (defined $space_before && $space_before ne "") { + if ($sign_off !~ /$signature_tags/) { WARN("BAD_SIGN_OFF", - "Do not use whitespace before $ucfirst_sign_off\n" . $herecurr); + "Non-standard signature: $sign_off\n" . $herecurr); + } + if (defined $space_before && $space_before ne "") { + if (WARN("BAD_SIGN_OFF", + "Do not use whitespace before $ucfirst_sign_off\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] = + "$ucfirst_sign_off $email"; + } } if ($sign_off =~ /-by:$/i && $sign_off ne $ucfirst_sign_off) { - WARN("BAD_SIGN_OFF", - "'$ucfirst_sign_off' is the preferred signature form\n" . $herecurr); + if (WARN("BAD_SIGN_OFF", + "'$ucfirst_sign_off' is the preferred signature form\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] = + "$ucfirst_sign_off $email"; + } + } if (!defined $space_after || $space_after ne " ") { - WARN("BAD_SIGN_OFF", - "Use a single space after $ucfirst_sign_off\n" . $herecurr); + if (WARN("BAD_SIGN_OFF", + "Use a single space after $ucfirst_sign_off\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] = + "$ucfirst_sign_off $email"; + } } - my ($email_name, $email_address, $comment) = parse_email($email); + my ($email_name, $name_comment, $email_address, $comment) = parse_email($email); my $suggested_email = format_email(($email_name, $email_address)); if ($suggested_email eq "") { ERROR("BAD_SIGN_OFF", @@ -1596,13 +2720,165 @@ sub process { $dequoted =~ s/" </ </; # Don't force email to have quotes # Allow just an angle bracketed address - if ("$dequoted$comment" ne $email && - "<$email_address>$comment" ne $email && - "$suggested_email$comment" ne $email) { + if (!same_email_addresses($email, $suggested_email)) { WARN("BAD_SIGN_OFF", "email address '$email' might be better as '$suggested_email$comment'\n" . $herecurr); } } + +# Check for duplicate signatures + my $sig_nospace = $line; + $sig_nospace =~ s/\s//g; + $sig_nospace = lc($sig_nospace); + if (defined $signatures{$sig_nospace}) { + WARN("BAD_SIGN_OFF", + "Duplicate signature\n" . $herecurr); + } else { + $signatures{$sig_nospace} = 1; + } + +# Check Co-developed-by: immediately followed by Signed-off-by: with same name and email + if ($sign_off =~ /^co-developed-by:$/i) { + if ($email eq $author) { + WARN("BAD_SIGN_OFF", + "Co-developed-by: should not be used to attribute nominal patch author '$author'\n" . "$here\n" . $rawline); + } + if (!defined $lines[$linenr]) { + WARN("BAD_SIGN_OFF", + "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]); + } elsif ($1 ne $email) { + WARN("BAD_SIGN_OFF", + "Co-developed-by and Signed-off-by: name/email do not match \n" . "$here\n" . $rawline . "\n" .$rawlines[$linenr]); + } + } + } + +# Check email subject for common tools that don't need to be mentioned + if ($in_header_lines && + $line =~ /^Subject:.*\b(?:checkpatch|sparse|smatch)\b[^:]/i) { + WARN("EMAIL_SUBJECT", + "A patch subject line should describe the change not the tool that found it\n" . $herecurr); + } + +# Check for Gerrit Change-Ids not in any patch context + if ($realfile eq '' && !$has_patch_separator && $line =~ /^\s*change-id:/i) { + ERROR("GERRIT_CHANGE_ID", + "Remove Gerrit Change-Id's before submitting upstream\n" . $herecurr); + } + +# Check if the commit log is in a possible stack dump + if ($in_commit_log && !$commit_log_possible_stack_dump && + ($line =~ /^\s*(?:WARNING:|BUG:)/ || + $line =~ /^\s*\[\s*\d+\.\d{6,6}\s*\]/ || + # timestamp + $line =~ /^\s*\[\<[0-9a-fA-F]{8,}\>\]/) || + $line =~ /^(?:\s+\w+:\s+[0-9a-fA-F]+){3,3}/ || + $line =~ /^\s*\#\d+\s*\[[0-9a-fA-F]+\]\s*\w+ at [0-9a-fA-F]+/) { + # stack dump address styles + $commit_log_possible_stack_dump = 1; + } + +# Check for line lengths > 75 in commit log, warn once + if ($in_commit_log && !$commit_log_long_line && + length($line) > 75 && + !($line =~ /^\s*[a-zA-Z0-9_\/\.]+\s+\|\s+\d+/ || + # file delta changes + $line =~ /^\s*(?:[\w\.\-]+\/)++[\w\.\-]+:/ || + # filename then : + $line =~ /^\s*(?:Fixes:|Link:)/i || + # A Fixes: or Link: line + $commit_log_possible_stack_dump)) { + WARN("COMMIT_LOG_LONG_LINE", + "Possible unwrapped commit description (prefer a maximum 75 chars per line)\n" . $herecurr); + $commit_log_long_line = 1; + } + +# Reset possible stack dump if a blank line is found + if ($in_commit_log && $commit_log_possible_stack_dump && + $line =~ /^\s*$/) { + $commit_log_possible_stack_dump = 0; + } + +# Check for git id commit length and improperly formed commit descriptions + if ($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 =~ /(?:\s|^)[0-9a-f]{12,40}(?:[\s"'\(\[]|$)/i && + $line !~ /[\<\[][0-9a-f]{12,40}[\>\]]/i && + $line !~ /\bfixes:\s*[0-9a-f]{12,40}/i))) { + my $init_char = "c"; + my $orig_commit = ""; + my $short = 1; + my $long = 0; + my $case = 1; + my $space = 1; + my $hasdesc = 0; + my $hasparens = 0; + my $id = '0123456789ab'; + my $orig_desc = "commit description"; + my $description = ""; + + if ($line =~ /\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) { + $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)) { + ERROR("GIT_COMMIT_ID", + "Please use git commit description style 'commit <12+ chars of sha1> (\"<title line>\")' - ie: '${init_char}ommit $id (\"$description\")'\n" . $herecurr); + } + } + +# Check for added, moved or deleted files + if (!$reported_maintainer_file && !$in_commit_log && + ($line =~ /^(?:new|deleted) file mode\s*\d+\s*$/ || + $line =~ /^rename (?:from|to) [\w\/\.\-]+\s*$/ || + ($line =~ /\{\s*([\w\/\.\-]*)\s*\=\>\s*([\w\/\.\-]*)\s*\}/ && + (defined($1) || defined($2))))) { + $is_patch = 1; + $reported_maintainer_file = 1; + WARN("FILE_PATH_CHANGES", + "added, moved or deleted file(s), does MAINTAINERS need updating?\n" . $herecurr); + } + +# Check for adding new DT bindings not in schema format + if (!$in_commit_log && + ($line =~ /^new file mode\s*\d+\s*$/) && + ($realfile =~ m@^Documentation/devicetree/bindings/.*\.txt$@)) { + WARN("DT_SCHEMA_BINDING_PATCH", + "DT bindings should be in DT schema format. See: Documentation/devicetree/writing-schema.rst\n"); } # Check for wrappage within a valid hunk of the file @@ -1612,20 +2888,6 @@ sub process { $herecurr) if (!$emitted_corrupt++); } -# Check for absolute kernel paths. - if ($tree) { - while ($line =~ m{(?:^|\s)(/\S*)}g) { - my $file = $1; - - if ($file =~ m{^(.*?)(?::\d+)+:?$} && - check_absolute_file($1, $herecurr)) { - # - } else { - check_absolute_file($file, $herecurr); - } - } - } - # UTF-8 regex found at http://www.w3.org/International/questions/qa-forms-utf-8.en.php if (($realfile =~ /^$/ || $line =~ /^\+/) && $rawline !~ m/^$UTF8*$/) { @@ -1642,39 +2904,112 @@ sub process { # Check if it's the start of a commit log # (not a header line and we haven't seen the patch filename) if ($in_header_lines && $realfile =~ /^$/ && - $rawline !~ /^(commit\b|from\b|[\w-]+:).+$/i) { + !($rawline =~ /^\s+(?:\S|$)/ || + $rawline =~ /^(?:commit\b|from\b|[\w-]+:)/i)) { $in_header_lines = 0; $in_commit_log = 1; + $has_commit_log = 1; } -# Still not yet in a patch, check for any UTF-8 - if ($in_commit_log && $realfile =~ /^$/ && +# Check if there is UTF-8 in a commit log when a mail header has explicitly +# declined it, i.e defined some charset where it is missing. + if ($in_header_lines && + $rawline =~ /^Content-Type:.+charset="(.+)".*$/ && + $1 !~ /utf-8/i) { + $non_utf8_charset = 1; + } + + if ($in_commit_log && $non_utf8_charset && $realfile =~ /^$/ && $rawline =~ /$NON_ASCII_UTF8/) { - CHK("UTF8_BEFORE_PATCH", + WARN("UTF8_BEFORE_PATCH", "8-bit UTF-8 used in possible commit log\n" . $herecurr); } +# Check for absolute kernel paths in commit message + if ($tree && $in_commit_log) { + while ($line =~ m{(?:^|\s)(/\S*)}g) { + my $file = $1; + + if ($file =~ m{^(.*?)(?::\d+)+:?$} && + check_absolute_file($1, $herecurr)) { + # + } else { + check_absolute_file($file, $herecurr); + } + } + } + +# Check for various typo / spelling mistakes + if (defined($misspellings) && + ($in_commit_log || $line =~ /^(?:\+|Subject:)/i)) { + while ($rawline =~ /(?:^|[^a-z@])($misspellings)(?:\b|$|[^a-z@])/gi) { + my $typo = $1; + 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) && + $fix) { + $fixed[$fixlinenr] =~ s/(^|[^A-Za-z@])($typo)($|[^A-Za-z@])/$1$typo_fix$3/; + } + } + } + +# check for invalid commit id + if ($in_commit_log && $line =~ /(^fixes:|\bcommit)\s+([0-9a-f]{6,40})\b/i) { + my $id; + my $description; + ($id, $description) = git_commit_info($2, undef, undef); + if (!defined($id)) { + WARN("UNKNOWN_COMMIT_ID", + "Unknown commit id '$2', maybe rebased or not pulled?\n" . $herecurr); + } + } + # ignore non-hunk lines and lines being removed next if (!$hunk_line || $line =~ /^-/); #trailing whitespace if ($line =~ /^\+.*\015/) { my $herevet = "$here\n" . cat_vet($rawline) . "\n"; - ERROR("DOS_LINE_ENDINGS", - "DOS line endings\n" . $herevet); - + if (ERROR("DOS_LINE_ENDINGS", + "DOS line endings\n" . $herevet) && + $fix) { + $fixed[$fixlinenr] =~ s/[\s\015]+$//; + } } elsif ($rawline =~ /^\+.*\S\s+$/ || $rawline =~ /^\+\s+$/) { my $herevet = "$here\n" . cat_vet($rawline) . "\n"; - ERROR("TRAILING_WHITESPACE", - "trailing whitespace\n" . $herevet); + if (ERROR("TRAILING_WHITESPACE", + "trailing whitespace\n" . $herevet) && + $fix) { + $fixed[$fixlinenr] =~ s/\s+$//; + } + $rpt_cleaners = 1; } +# Check for FSF mailing addresses. + if ($rawline =~ /\bwrite to the Free/i || + $rawline =~ /\b675\s+Mass\s+Ave/i || + $rawline =~ /\b59\s+Temple\s+Pl/i || + $rawline =~ /\b51\s+Franklin\s+St/i) { + my $herevet = "$here\n" . cat_vet($rawline) . "\n"; + my $msg_level = \&ERROR; + $msg_level = \&CHK if ($file); + &{$msg_level}("FSF_MAILING_ADDRESS", + "Do not include the paragraph about writing to the Free Software Foundation's mailing address from the sample GPL notice. The FSF has changed addresses in the past, and may do so again. Linux already includes a copy of the GPL.\n" . $herevet) + } + # check for Kconfig help text having a real description # Only applies when adding the entry originally, after that we do not have # sufficient context to determine whether it is indeed long enough. if ($realfile =~ /Kconfig/ && - $line =~ /.\s*config\s+/) { + # 'choice' is usually the last thing on the line (though + # Kconfig supports named choices), so use a word boundary + # (\b) rather than a whitespace character (\s) + $line =~ /^\+\s*(?:config|menuconfig|choice)\b/) { my $length = 0; my $cnt = $realcnt; my $ln = $linenr + 1; @@ -1687,10 +3022,15 @@ sub process { $is_end = $lines[$ln - 1] =~ /^\+/; next if ($f =~ /^-/); + last if (!$file && $f =~ /^\@\@/); - if ($lines[$ln - 1] =~ /.\s*(?:bool|tristate)\s*\"/) { + if ($lines[$ln - 1] =~ /^\+\s*(?:bool|tristate|prompt)\s*["']/) { $is_start = 1; - } elsif ($lines[$ln - 1] =~ /.\s*(?:---)?help(?:---)?$/) { + } 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); + } $length = -1; } @@ -1698,17 +3038,72 @@ sub process { $f =~ s/#.*//; $f =~ s/^\s+//; next if ($f =~ /^$/); - if ($f =~ /^\s*config\s/) { + + # This only checks context lines in the patch + # and so hopefully shouldn't trigger false + # positives, even though some of these are + # common words in help texts + if ($f =~ /^\s*(?:config|menuconfig|choice|endchoice| + if|endif|menu|endmenu|source)\b/x) { $is_end = 1; last; } $length++; } - WARN("CONFIG_DESCRIPTION", - "please write a paragraph that describes the config symbol fully\n" . $herecurr) if ($is_start && $is_end && $length < 4); + if ($is_start && $is_end && $length < $min_conf_desc_length) { + WARN("CONFIG_DESCRIPTION", + "please write a paragraph that describes the config symbol fully\n" . $herecurr); + } #print "is_start<$is_start> is_end<$is_end> length<$length>\n"; } +# 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.*/ || $realfile =~ /Kbuild.*/) && ($line =~ /\+(EXTRA_[A-Z]+FLAGS).*/)) { my $flag = $1; @@ -1723,39 +3118,159 @@ sub process { "Use of $flag is deprecated, please use \`$replacement->{$flag} instead.\n" . $herecurr) if ($replacement->{$flag}); } -# check we are in a valid source file if not then ignore this hunk - next if ($realfile !~ /\.(h|c|s|S|pl|sh)$/); - -#80 column limit - if ($line =~ /^\+/ && $prevrawline !~ /\/\*\*/ && - $rawline !~ /^.\s*\*\s*\@$Ident\s/ && - !($line =~ /^\+\s*$logFunctions\s*\(\s*(?:(KERN_\S+\s*|[^"]*))?"[X\t]*"\s*(?:|,|\)\s*;)\s*$/ || - $line =~ /^\+\s*"[^"]*"\s*(?:\s*|,|\)\s*;)\s*$/) && - $length > 80) - { - WARN("LONG_LINE", - "line over 80 characters\n" . $herecurr); +# check for DT compatible documentation + if (defined $root && + (($realfile =~ /\.dtsi?$/ && $line =~ /^\+\s*compatible\s*=\s*\"/) || + ($realfile =~ /\.[ch]$/ && $line =~ /^\+.*\.compatible\s*=\s*\"/))) { + + my @compats = $rawline =~ /\"([a-zA-Z0-9\-\,\.\+_]+)\"/g; + + my $dt_path = $root . "/Documentation/devicetree/bindings/"; + my $vp_file = $dt_path . "vendor-prefixes.yaml"; + + foreach my $compat (@compats) { + my $compat2 = $compat; + $compat2 =~ s/\,[a-zA-Z0-9]*\-/\,<\.\*>\-/; + my $compat3 = $compat; + $compat3 =~ s/\,([a-z]*)[0-9]*\-/\,$1<\.\*>\-/; + `grep -Erq "$compat|$compat2|$compat3" $dt_path`; + if ( $? >> 8 ) { + WARN("UNDOCUMENTED_DT_STRING", + "DT compatible string \"$compat\" appears un-documented -- check $dt_path\n" . $herecurr); + } + + next if $compat !~ /^([a-zA-Z0-9\-]+)\,/; + my $vendor = $1; + `grep -Eq "\\"\\^\Q$vendor\E,\\.\\*\\":" $vp_file`; + if ( $? >> 8 ) { + WARN("UNDOCUMENTED_DT_STRING", + "DT compatible string vendor \"$vendor\" appears un-documented -- check $vp_file\n" . $herecurr); + } + } } -# Check for user-visible strings broken across lines, which breaks the ability -# to grep for the string. Limited to strings used as parameters (those -# following an open parenthesis), which almost completely eliminates false -# positives, as well as warning only once per parameter rather than once per -# line of the string. Make an exception when the previous string ends in a -# newline (multiple lines in one string constant) or \n\t (common in inline -# assembly to indent the instruction on the following line). - if ($line =~ /^\+\s*"/ && - $prevline =~ /"\s*$/ && - $prevline =~ /\(/ && - $prevrawline !~ /\\n(?:\\t)*"\s*$/) { - WARN("SPLIT_STRING", - "quoted string split across lines\n" . $hereprev); +# check for using SPDX license tag at beginning of files + if ($realline == $checklicenseline) { + if ($rawline =~ /^[ \+]\s*\#\!\s*\//) { + $checklicenseline = 2; + } elsif ($rawline =~ /^\+/) { + my $comment = ""; + if ($realfile =~ /\.(h|s|S)$/) { + $comment = '/*'; + } elsif ($realfile =~ /\.(c|dts|dtsi)$/) { + $comment = '//'; + } elsif (($checklicenseline == 2) || $realfile =~ /\.(sh|pl|py|awk|tc|yaml)$/) { + $comment = '#'; + } elsif ($realfile =~ /\.rst$/) { + $comment = '..'; + } + +# check SPDX comment style for .[chsS] files + if ($realfile =~ /\.[chsS]$/ && + $rawline =~ /SPDX-License-Identifier:/ && + $rawline !~ m@^\+\s*\Q$comment\E\s*@) { + WARN("SPDX_LICENSE_TAG", + "Improper SPDX comment style for '$realfile', please use '$comment' instead\n" . $herecurr); + } + + if ($comment !~ /^$/ && + $rawline !~ m@^\+\Q$comment\E SPDX-License-Identifier: @) { + WARN("SPDX_LICENSE_TAG", + "Missing or malformed SPDX-License-Identifier tag in line $checklicenseline\n" . $herecurr); + } elsif ($rawline =~ /(SPDX-License-Identifier: .*)/) { + my $spdx_license = $1; + if (!is_SPDX_License_valid($spdx_license)) { + WARN("SPDX_LICENSE_TAG", + "'$spdx_license' is not supported in LICENSES/...\n" . $herecurr); + } + if ($realfile =~ m@^Documentation/devicetree/bindings/@ && + not $spdx_license =~ /GPL-2\.0.*BSD-2-Clause/) { + my $msg_level = \&WARN; + $msg_level = \&CHK if ($file); + if (&{$msg_level}("SPDX_LICENSE_TAG", + + "DT binding documents should be licensed (GPL-2.0-only OR BSD-2-Clause)\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/SPDX-License-Identifier: .*/SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)/; + } + } + } + } } -# check for spaces before a quoted newline - if ($rawline =~ /^.*\".*\s\\n/) { - WARN("QUOTED_WHITESPACE_BEFORE_NEWLINE", - "unnecessary whitespace before a quoted newline\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)$/); + +# check for using SPDX-License-Identifier on the wrong line number + if ($realline != $checklicenseline && + $rawline =~ /\bSPDX-License-Identifier:/ && + substr($line, @-, @+ - @-) eq "$;" x (@+ - @-)) { + WARN("SPDX_LICENSE_TAG", + "Misplaced SPDX-License-Identifier tag - use line $checklicenseline instead\n" . $herecurr); + } + +# line length limit (with some exclusions) +# +# There are a few types of lines that may extend beyond $max_line_length: +# logging functions like pr_info that end in a string +# lines with a single string +# #defines that are a single string +# lines with an RFC3986 like URL +# +# There are 3 different line length message types: +# LONG_LINE_COMMENT a comment starts before but extends beyond $max_line_length +# LONG_LINE_STRING a string starts before but extends beyond $max_line_length +# LONG_LINE all other lines longer than $max_line_length +# +# if LONG_LINE is ignored, the other 2 types are also ignored +# + + if ($line =~ /^\+/ && $length > $max_line_length) { + my $msg_type = "LONG_LINE"; + + # Check the allowed long line types first + + # logging functions that end in a string that starts + # before $max_line_length + if ($line =~ /^\+\s*$logFunctions\s*\(\s*(?:(?:KERN_\S+\s*|[^"]*))?($String\s*(?:|,|\)\s*;)\s*)$/ && + length(expand_tabs(substr($line, 1, length($line) - length($1) - 1))) <= $max_line_length) { + $msg_type = ""; + + # lines with only strings (w/ possible termination) + # #defines with only strings + } elsif ($line =~ /^\+\s*$String\s*(?:\s*|,|\)\s*;)\s*$/ || + $line =~ /^\+\s*#\s*define\s+\w+\s+$String$/) { + $msg_type = ""; + + # More special cases + } elsif ($line =~ /^\+.*\bEFI_GUID\s*\(/ || + $line =~ /^\+\s*(?:\w+)?\s*DEFINE_PER_CPU/) { + $msg_type = ""; + + # URL ($rawline is used in case the URL is in a comment) + } elsif ($rawline =~ /^\+.*\b[a-z][\w\.\+\-]*:\/\/\S+/i) { + $msg_type = ""; + + # Otherwise set the alternate message types + + # a comment starts before $max_line_length + } elsif ($line =~ /($;[\s$;]*)$/ && + length(expand_tabs(substr($line, 1, length($line) - length($1) - 1))) <= $max_line_length) { + $msg_type = "LONG_LINE_COMMENT" + + # a quoted string starts before $max_line_length + } elsif ($sline =~ /\s*($String(?:\s*(?:\\|,\s*|\)\s*;\s*))?)$/ && + length(expand_tabs(substr($line, 1, length($line) - length($1) - 1))) <= $max_line_length) { + $msg_type = "LONG_LINE_STRING" + } + + if ($msg_type ne "" && + (show_type("LONG_LINE") || show_type($msg_type))) { + my $msg_level = \&WARN; + $msg_level = \&CHK if ($file); + &{$msg_level}($msg_type, + "line length of $length exceeds $max_line_length columns\n" . $herecurr); + } } # check for adding lines without a newline. @@ -1764,38 +3279,39 @@ sub process { "adding a line without newline at end of file\n" . $herecurr); } -# Blackfin: use hi/lo macros - if ($realfile =~ m@arch/blackfin/.*\.S$@) { - if ($line =~ /\.[lL][[:space:]]*=.*&[[:space:]]*0x[fF][fF][fF][fF]/) { - my $herevet = "$here\n" . cat_vet($line) . "\n"; - ERROR("LO_MACRO", - "use the LO() macro, not (... & 0xFFFF)\n" . $herevet); - } - if ($line =~ /\.[hH][[:space:]]*=.*>>[[:space:]]*16/) { - my $herevet = "$here\n" . cat_vet($line) . "\n"; - ERROR("HI_MACRO", - "use the HI() macro, not (... >> 16)\n" . $herevet); - } - } - # check we are in a valid source file C or perl if not then ignore this hunk - next if ($realfile !~ /\.(h|c|pl)$/); + next if ($realfile !~ /\.(h|c|pl|dtsi|dts)$/); # at the beginning of a line any tabs must come first and anything -# more than 8 must use tabs. +# more than $tabsize must use tabs. if ($rawline =~ /^\+\s* \t\s*\S/ || $rawline =~ /^\+\s* \s*/) { my $herevet = "$here\n" . cat_vet($rawline) . "\n"; - ERROR("CODE_INDENT", - "code indent should use tabs where possible\n" . $herevet); $rpt_cleaners = 1; + if (ERROR("CODE_INDENT", + "code indent should use tabs where possible\n" . $herevet) && + $fix) { + $fixed[$fixlinenr] =~ s/^\+([ \t]+)/"\+" . tabify($1)/e; + } } # check for space before tabs. if ($rawline =~ /^\+/ && $rawline =~ / \t/) { my $herevet = "$here\n" . cat_vet($rawline) . "\n"; - WARN("SPACE_BEFORE_TAB", - "please, no space before tabs\n" . $herevet); + if (WARN("SPACE_BEFORE_TAB", + "please, no space before tabs\n" . $herevet) && + $fix) { + while ($fixed[$fixlinenr] =~ + s/(^\+.*) {$tabsize,$tabsize}\t/$1\t\t/) {} + while ($fixed[$fixlinenr] =~ + s/(^\+.*) +\t/$1\t/) {} + } + } + +# check for assignments on the start of a line + if ($sline =~ /^\+\s+($Assignment)[^=]/) { + CHK("ASSIGNMENT_CONTINUATIONS", + "Assignment operator '$1' should be on the previous line\n" . $hereprev); } # check for && or || at the start of a line @@ -1804,40 +3320,191 @@ sub process { "Logical continuations should be on the previous line\n" . $hereprev); } +# check indentation starts on a tab stop + if ($perl_version_ok && + $sline =~ /^\+\t+( +)(?:$c90_Keywords\b|\{\s*$|\}\s*(?:else\b|while\b|\s*$)|$Declare\s*$Ident\s*[;=])/) { + my $indent = length($1); + if ($indent % $tabsize) { + if (WARN("TABSTOP", + "Statements should start on a tabstop\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s@(^\+\t+) +@$1 . "\t" x ($indent/$tabsize)@e; + } + } + } + # check multi-line statement indentation matches previous line - if ($^V && $^V ge 5.10.0 && - $prevline =~ /^\+(\t*)(if \(|$Ident\().*(\&\&|\|\||,)\s*$/) { + if ($perl_version_ok && + $prevline =~ /^\+([ \t]*)((?:$c90_Keywords(?:\s+if)\s*)|(?:$Declare\s*)?(?:$Ident|\(\s*\*\s*$Ident\s*\))\s*|(?:\*\s*)*$Lval\s*=\s*$Ident\s*)\(.*(\&\&|\|\||,)\s*$/) { $prevline =~ /^\+(\t*)(.*)$/; my $oldindent = $1; my $rest = $2; my $pos = pos_last_openparen($rest); if ($pos >= 0) { - $line =~ /^\+([ \t]*)/; - my $newindent = $1; + $line =~ /^(\+| )([ \t]*)/; + my $newindent = $2; my $goodtabindent = $oldindent . - "\t" x ($pos / 8) . - " " x ($pos % 8); + "\t" x ($pos / $tabsize) . + " " x ($pos % $tabsize); my $goodspaceindent = $oldindent . " " x $pos; if ($newindent ne $goodtabindent && $newindent ne $goodspaceindent) { - CHK("PARENTHESIS_ALIGNMENT", - "Alignment should match open parenthesis\n" . $hereprev); + + if (CHK("PARENTHESIS_ALIGNMENT", + "Alignment should match open parenthesis\n" . $hereprev) && + $fix && $line =~ /^\+/) { + $fixed[$fixlinenr] =~ + s/^\+[ \t]*/\+$goodtabindent/; + } } } } - if ($line =~ /^\+.*\*[ \t]*\)[ \t]+/) { - CHK("SPACING", - "No space is necessary after a cast\n" . $hereprev); +# check for space after cast like "(int) foo" or "(struct foo) bar" +# avoid checking a few false positives: +# "sizeof(<type>)" or "__alignof__(<type>)" +# function pointer declarations like "(*foo)(int) = bar;" +# structure definitions like "(struct foo) { 0 };" +# multiline macros that define functions +# known attributes or the __attribute__ keyword + if ($line =~ /^\+(.*)\(\s*$Type\s*\)([ \t]++)((?![={]|\\$|$Attribute|__attribute__))/ && + (!defined($1) || $1 !~ /\b(?:sizeof|__alignof__)\s*$/)) { + if (CHK("SPACING", + "No space is necessary after a cast\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ + s/(\(\s*$Type\s*\))[ \t]+/$1/; + } + } + +# Block comment styles +# Networking with an initial /* + if ($realfile =~ m@^(drivers/net/|net/)@ && + $prevrawline =~ /^\+[ \t]*\/\*[ \t]*$/ && + $rawline =~ /^\+[ \t]*\*/ && + $realline > 2) { + WARN("NETWORKING_BLOCK_COMMENT_STYLE", + "networking block comments don't use an empty /* line, use /* Comment...\n" . $hereprev); + } + +# Block comments use * on subsequent lines + if ($prevline =~ /$;[ \t]*$/ && #ends in comment + $prevrawline =~ /^\+.*?\/\*/ && #starting /* + $prevrawline !~ /\*\/[ \t]*$/ && #no trailing */ + $rawline =~ /^\+/ && #line is new + $rawline !~ /^\+[ \t]*\*/) { #no leading * + WARN("BLOCK_COMMENT_STYLE", + "Block comments use * on subsequent lines\n" . $hereprev); + } + +# Block comments use */ on trailing lines + if ($rawline !~ m@^\+[ \t]*\*/[ \t]*$@ && #trailing */ + $rawline !~ m@^\+.*/\*.*\*/[ \t]*$@ && #inline /*...*/ + $rawline !~ m@^\+.*\*{2,}/[ \t]*$@ && #trailing **/ + $rawline =~ m@^\+[ \t]*.+\*\/[ \t]*$@) { #non blank */ + WARN("BLOCK_COMMENT_STYLE", + "Block comments use a trailing */ on a separate line\n" . $herecurr); + } + +# Block comment * alignment + if ($prevline =~ /$;[ \t]*$/ && #ends in comment + $line =~ /^\+[ \t]*$;/ && #leading comment + $rawline =~ /^\+[ \t]*\*/ && #leading * + (($prevrawline =~ /^\+.*?\/\*/ && #leading /* + $prevrawline !~ /\*\/[ \t]*$/) || #no trailing */ + $prevrawline =~ /^\+[ \t]*\*/)) { #leading * + my $oldindent; + $prevrawline =~ m@^\+([ \t]*/?)\*@; + if (defined($1)) { + $oldindent = expand_tabs($1); + } else { + $prevrawline =~ m@^\+(.*/?)\*@; + $oldindent = expand_tabs($1); + } + $rawline =~ m@^\+([ \t]*)\*@; + my $newindent = $1; + $newindent = expand_tabs($newindent); + if (length($oldindent) ne length($newindent)) { + WARN("BLOCK_COMMENT_STYLE", + "Block comments should align the * on each line\n" . $hereprev); + } } - if ($rawline =~ /^\+[ \t]*\/\*[ \t]*$/ && - $prevrawline =~ /^\+[ \t]*$/) { - CHK("BLOCK_COMMENT_STYLE", - "Don't begin block comments with only a /* line, use /* comment...\n" . $hereprev); +# check for missing blank lines after struct/union declarations +# with exceptions for various attributes and macros + if ($prevline =~ /^[\+ ]};?\s*$/ && + $line =~ /^\+/ && + !($line =~ /^\+\s*$/ || + $line =~ /^\+\s*EXPORT_SYMBOL/ || + $line =~ /^\+\s*MODULE_/i || + $line =~ /^\+\s*\#\s*(?:end|elif|else)/ || + $line =~ /^\+[a-z_]*init/ || + $line =~ /^\+\s*(?:static\s+)?[A-Z_]*ATTR/ || + $line =~ /^\+\s*DECLARE/ || + $line =~ /^\+\s*builtin_[\w_]*driver/ || + $line =~ /^\+\s*__setup/)) { + if (CHK("LINE_SPACING", + "Please use a blank line after function/struct/union/enum declarations\n" . $hereprev) && + $fix) { + fix_insert_line($fixlinenr, "\+"); + } + } + +# check for multiple consecutive blank lines + if ($prevline =~ /^[\+ ]\s*$/ && + $line =~ /^\+\s*$/ && + $last_blank_line != ($linenr - 1)) { + if (CHK("LINE_SPACING", + "Please don't use multiple blank lines\n" . $hereprev) && + $fix) { + fix_delete_line($fixlinenr, $rawline); + } + + $last_blank_line = $linenr; + } + +# check for missing blank lines after declarations + if ($sline =~ /^\+\s+\S/ && #Not at char 1 + # actual declarations + ($prevline =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || + # function pointer declarations + $prevline =~ /^\+\s+$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*[=,;\[]/ || + # known declaration macros + $prevline =~ /^\+\s+$declaration_macros/) && + # for "else if" which can look like "$Ident $Ident" + !($prevline =~ /^\+\s+$c90_Keywords\b/ || + # other possible extensions of declaration lines + $prevline =~ /(?:$Compare|$Assignment|$Operators)\s*$/ || + # not starting a section or a macro "\" extended line + $prevline =~ /(?:\{\s*|\\)$/) && + # looks like a declaration + !($sline =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || + # function pointer declarations + $sline =~ /^\+\s+$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*[=,;\[]/ || + # known declaration macros + $sline =~ /^\+\s+$declaration_macros/ || + # start of struct or union or enum + $sline =~ /^\+\s+(?:static\s+)?(?:const\s+)?(?:union|struct|enum|typedef)\b/ || + # start or end of block or continuation of declaration + $sline =~ /^\+\s+(?:$|[\{\}\.\#\"\?\:\(\[])/ || + # bitfield continuation + $sline =~ /^\+\s+$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, "\+"); + } } # check for spaces at the beginning of a line. @@ -1845,39 +3512,77 @@ sub process { # 1) within comments # 2) indented preprocessor commands # 3) hanging labels - if ($rawline =~ /^\+ / && $line !~ /\+ *(?:$;|#|$Ident:)/) { + if ($rawline =~ /^\+ / && $line !~ /^\+ *(?:$;|#|$Ident:)/) { my $herevet = "$here\n" . cat_vet($rawline) . "\n"; - WARN("LEADING_SPACE", - "please, no spaces at the start of a line\n" . $herevet); + if (WARN("LEADING_SPACE", + "please, no spaces at the start of a line\n" . $herevet) && + $fix) { + $fixed[$fixlinenr] =~ s/^\+([ \t]+)/"\+" . tabify($1)/e; + } } # check we are in a valid C source file if not then ignore this hunk next if ($realfile !~ /\.(h|c)$/); +# check for unusual line ending [ or ( + if ($line =~ /^\+.*([\[\(])\s*$/) { + CHK("OPEN_ENDED_LINE", + "Lines should not end with a '$1'\n" . $herecurr); + } + +# check if this appears to be the start function declaration, save the name + if ($sline =~ /^\+\{\s*$/ && + $prevline =~ /^\+(?:(?:(?:$Storage|$Inline)\s*)*\s*$Type\s*)?($Ident)\(/) { + $context_function = $1; + } + +# check if this appears to be the end of function declaration + if ($sline =~ /^\+\}\s*$/) { + undef $context_function; + } + +# check indentation of any line with a bare else +# (but not if it is a multiple line "if (foo) return bar; else return baz;") +# if the previous line is a break or return and is indented 1 tab more... + if ($sline =~ /^\+([\t]+)(?:}[ \t]*)?else(?:[ \t]*{)?\s*$/) { + my $tabs = length($1) + 1; + if ($prevline =~ /^\+\t{$tabs,$tabs}break\b/ || + ($prevline =~ /^\+\t{$tabs,$tabs}return\b/ && + defined $lines[$linenr] && + $lines[$linenr] !~ /^[ \+]\t{$tabs,$tabs}return/)) { + WARN("UNNECESSARY_ELSE", + "else is not generally useful after a break or return\n" . $hereprev); + } + } + +# check indentation of a line with a break; +# if the previous line is a goto or return and is indented the same # of tabs + if ($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" . $hereprev); + } + } + # check for RCS/CVS revision markers if ($rawline =~ /^\+.*\$(Revision|Log|Id)(?:\$|)/) { WARN("CVS_KEYWORD", "CVS style keyword markers, these will _not_ be updated\n". $herecurr); } -# Blackfin: don't use __builtin_bfin_[cs]sync - if ($line =~ /__builtin_bfin_csync/) { - my $herevet = "$here\n" . cat_vet($line) . "\n"; - ERROR("CSYNC", - "use the CSYNC() macro in asm/blackfin.h\n" . $herevet); - } - if ($line =~ /__builtin_bfin_ssync/) { - my $herevet = "$here\n" . cat_vet($line) . "\n"; - ERROR("SSYNC", - "use the SSYNC() macro in asm/blackfin.h\n" . $herevet); +# check for old HOTPLUG __dev<foo> section markings + if ($line =~ /\b(__dev(init|exit)(data|const|))\b/) { + WARN("HOTPLUG_SECTION", + "Using $1 is unnecessary\n" . $herecurr); } # Check for potential 'bare' types my ($stat, $cond, $line_nr_next, $remain_next, $off_next, $realline_next); #print "LINE<$line>\n"; - if ($linenr >= $suppress_statement && - $realcnt && $line =~ /.\s*\S/) { + if ($linenr > $suppress_statement && + $realcnt && $sline =~ /.\s*\S/) { ($stat, $cond, $line_nr_next, $remain_next, $off_next) = ctx_statement_block($linenr, $realcnt, 0); $stat =~ s/\n./\n /g; @@ -1977,7 +3682,7 @@ sub process { # if/while/etc brace do not go on next line, unless defining a do while loop, # or if that brace on the next line is for something else - if ($line =~ /(.*)\b((?:if|while|for|switch)\s*\(|do\b|else\b)/ && $line !~ /^.\s*\#/) { + if ($line =~ /(.*)\b((?:if|while|for|switch|(?:[a-z_]+|)for_each[a-z_]+)\s*\(|do\b|else\b)/ && $line !~ /^.\s*\#/) { my $pre_ctx = "$1$2"; my ($level, @ctx) = ctx_statement_level($linenr, $realcnt, 0); @@ -2004,7 +3709,7 @@ sub process { #print "realcnt<$realcnt> ctx_cnt<$ctx_cnt>\n"; #print "pre<$pre_ctx>\nline<$line>\nctx<$ctx>\nnext<$lines[$ctx_ln - 1]>\n"; - if ($ctx !~ /{\s*/ && defined($lines[$ctx_ln -1]) && $lines[$ctx_ln - 1] =~ /^\+\s*{/) { + if ($ctx !~ /{\s*/ && defined($lines[$ctx_ln - 1]) && $lines[$ctx_ln - 1] =~ /^\+\s*{/) { ERROR("OPEN_BRACE", "that open brace { should be on the previous line\n" . "$here\n$ctx\n$rawlines[$ctx_ln - 1]\n"); @@ -2023,7 +3728,7 @@ sub process { } # Check relative indent for conditionals and blocks. - if ($line =~ /\b(?:(?:if|while|for)\s*\(|do\b)/ && $line !~ /^.\s*#/ && $line !~ /\}\s*while\s*/) { + if ($line =~ /\b(?:(?:if|while|for|(?:[a-z_]+|)for_each[a-z_]+)\s*\(|(?:do|else)\b)/ && $line !~ /^.\s*#/ && $line !~ /\}\s*while\s*/) { ($stat, $cond, $line_nr_next, $remain_next, $off_next) = ctx_statement_block($linenr, $realcnt, 0) if (!defined $stat); @@ -2031,15 +3736,22 @@ sub process { substr($s, 0, length($c), ''); - # Make sure we remove the line prefixes as we have - # none on the first line, and are going to readd them - # where necessary. - $s =~ s/\n./\n/gs; + # remove inline comments + $s =~ s/$;/ /g; + $c =~ s/$;/ /g; # Find out how long the conditional actually is. my @newlines = ($c =~ /\n/gs); my $cond_lines = 1 + $#newlines; + # Make sure we remove the line prefixes as we have + # none on the first line, and are going to readd them + # where necessary. + $s =~ s/\n./\n/gs; + while ($s =~ /\n\s+\\\n/) { + $cond_lines += $s =~ s/\n\s+\\\n/\n/g; + } + # We want to check the first line inside the block # starting at the end of the conditional, so remove: # 1) any blank line termination @@ -2105,8 +3817,12 @@ sub process { #print "line<$line> prevline<$prevline> indent<$indent> sindent<$sindent> check<$check> continuation<$continuation> s<$s> cond_lines<$cond_lines> stat_real<$stat_real> stat<$stat>\n"; - if ($check && (($sindent % 8) != 0 || - ($sindent <= $indent && $s ne ''))) { + if ($check && $s ne '' && + (($sindent % $tabsize) != 0 || + ($sindent < $indent) || + ($sindent == $indent && + ($s !~ /^\s*(?:\}|\{|else\b)/)) || + ($sindent > $indent + $tabsize))) { WARN("SUSPECT_CODE_INDENT", "suspect code indent for conditional statements ($indent, $sindent)\n" . $herecurr . "$stat_real\n"); } @@ -2126,7 +3842,43 @@ sub process { $prev_values = substr($curr_values, -1); #ignore lines not being added - if ($line=~/^[^\+]/) {next;} + next if ($line =~ /^[^\+]/); + +# check for dereferences that span multiple lines + if ($prevline =~ /^\+.*$Lval\s*(?:\.|->)\s*$/ && + $line =~ /^\+\s*(?!\#\s*(?!define\s+|if))\s*$Lval/) { + $prevline =~ /($Lval\s*(?:\.|->))\s*$/; + my $ref = $1; + $line =~ /^.\s*($Lval)/; + $ref .= $1; + $ref =~ s/\s//g; + WARN("MULTILINE_DEREFERENCE", + "Avoid multiple line dereference - prefer '$ref'\n" . $hereprev); + } + +# check for declarations of signed or unsigned without int + while ($line =~ m{\b($Declare)\s*(?!char\b|short\b|int\b|long\b)\s*($Ident)?\s*[=,;\[\)\(]}g) { + my $type = $1; + my $var = $2; + $var = "" if (!defined $var); + if ($type =~ /^(?:(?:$Storage|$Inline|$Attribute)\s+)*((?:un)?signed)((?:\s*\*)*)\s*$/) { + my $sign = $1; + my $pointer = $2; + + $pointer = "" if (!defined $pointer); + + if (WARN("UNSPECIFIED_INT", + "Prefer '" . trim($sign) . " int" . rtrim($pointer) . "' to bare use of '$sign" . rtrim($pointer) . "'\n" . $herecurr) && + $fix) { + my $decl = trim($sign) . " int "; + my $comp_pointer = $pointer; + $comp_pointer =~ s/\s//g; + $decl .= $comp_pointer; + $decl = rtrim($decl) if ($var eq ""); + $fixed[$fixlinenr] =~ s@\b$sign\s*\Q$pointer\E\s*$var\b@$decl$var@; + } + } + } # TEST: allow direct testing of the type matcher. if ($dbg_type) { @@ -2154,8 +3906,18 @@ sub process { # check for initialisation to aggregates open brace on the next line if ($line =~ /^.\s*{/ && $prevline =~ /(?:^|[^=])=\s*$/) { - ERROR("OPEN_BRACE", - "that open brace { should be on the previous line\n" . $hereprev); + if (ERROR("OPEN_BRACE", + "that open brace { should be on the previous line\n" . $hereprev) && + $fix && $prevline =~ /^\+/ && $line =~ /^\+/) { + fix_delete_line($fixlinenr - 1, $prevrawline); + fix_delete_line($fixlinenr, $rawline); + my $fixedline = $prevrawline; + $fixedline =~ s/\s*=\s*$/ = {/; + fix_insert_line($fixlinenr, $fixedline); + $fixedline = $line; + $fixedline =~ s/^(.\s*)\{\s*/$1/; + fix_insert_line($fixlinenr, $fixedline); + } } # @@ -2167,15 +3929,25 @@ sub process { my $path = $1; if ($path =~ m{//}) { ERROR("MALFORMED_INCLUDE", - "malformed #include filename\n" . - $herecurr); + "malformed #include filename\n" . $herecurr); + } + if ($path =~ "^uapi/" && $realfile =~ m@\binclude/uapi/@) { + ERROR("UAPI_INCLUDE", + "No #include in ...include/uapi/... should use a uapi/ path prefix\n" . $herecurr); } } # no C99 // comments if ($line =~ m{//}) { - ERROR("C99_COMMENTS", - "do not use C99 // comments\n" . $herecurr); + if (ERROR("C99_COMMENTS", + "do not use C99 // comments\n" . $herecurr) && + $fix) { + my $line = $fixed[$fixlinenr]; + if ($line =~ /\/\/(.*)$/) { + my $comment = trim($1); + $fixed[$fixlinenr] =~ s@\/\/(.*)$@/\* $comment \*/@; + } + } } # Remove C99 comments. $line =~ s@//.*@@; @@ -2227,16 +3999,48 @@ sub process { } # check for global initialisers. - if ($line =~ /^.$Type\s*$Ident\s*(?:\s+$Modifier)*\s*=\s*(0|NULL|false)\s*;/) { - ERROR("GLOBAL_INITIALISERS", - "do not initialise globals to 0 or NULL\n" . - $herecurr); + if ($line =~ /^\+$Type\s*$Ident(?:\s+$Modifier)*\s*=\s*($zero_initializer)\s*;/) { + if (ERROR("GLOBAL_INITIALISERS", + "do not initialise globals to $1\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/(^.$Type\s*$Ident(?:\s+$Modifier)*)\s*=\s*$zero_initializer\s*;/$1;/; + } } # check for static initialisers. - if ($line =~ /\bstatic\s.*=\s*(0|NULL|false)\s*;/) { - ERROR("INITIALISED_STATIC", - "do not initialise statics to 0 or NULL\n" . - $herecurr); + if ($line =~ /^\+.*\bstatic\s.*=\s*($zero_initializer)\s*;/) { + if (ERROR("INITIALISED_STATIC", + "do not initialise statics to $1\n" . + $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/(\bstatic\s.*?)\s*=\s*$zero_initializer\s*;/$1;/; + } + } + +# check for misordered declarations of char/short/int/long with signed/unsigned + while ($sline =~ m{(\b$TypeMisordered\b)}g) { + my $tmp = trim($1); + WARN("MISORDERED_TYPE", + "type '$tmp' should be specified in [[un]signed] [short|int|long|long long] order\n" . $herecurr); + } + +# check for unnecessary <signed> int declarations of short/long/long long + while ($sline =~ m{\b($TypeMisordered(\s*\*)*|$C90_int_types)\b}g) { + my $type = trim($1); + next if ($type !~ /\bint\b/); + next if ($type !~ /\b(?:short|long\s+long|long)\b/); + my $new_type = $type; + $new_type =~ s/\b\s*int\s*\b/ /; + $new_type =~ s/\b\s*(?:un)?signed\b\s*/ /; + $new_type =~ s/^const\s+//; + $new_type = "unsigned $new_type" if ($type =~ /\bunsigned\b/); + $new_type = "const $new_type" if ($type =~ /^const\b/); + $new_type =~ s/\s+/ /g; + $new_type = trim($new_type); + if (WARN("UNNECESSARY_INT", + "Prefer '$new_type' over '$type' as the int is unnecessary\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\b\Q$type\E\b/$new_type/; + } } # check for static const char * arrays. @@ -2244,19 +4048,63 @@ sub process { WARN("STATIC_CONST_CHAR_ARRAY", "static const char * array should probably be static const char * const\n" . $herecurr); - } + } + +# check for initialized const char arrays that should be static const + if ($line =~ /^\+\s*const\s+(char|unsigned\s+char|_*u8|(?:[us]_)?int8_t)\s+\w+\s*\[\s*(?:\w+\s*)?\]\s*=\s*"/) { + if (WARN("STATIC_CONST_CHAR_ARRAY", + "const array should probably be static const\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/(^.\s*)const\b/${1}static const/; + } + } # check for static char foo[] = "bar" declarations. if ($line =~ /\bstatic\s+char\s+(\w+)\s*\[\s*\]\s*=\s*"/) { WARN("STATIC_CONST_CHAR_ARRAY", "static char array declaration should probably be static const char\n" . $herecurr); + } + +# check for const <foo> const where <foo> is not a pointer or array type + if ($sline =~ /\bconst\s+($BasicType)\s+const\b/) { + my $found = $1; + if ($sline =~ /\bconst\s+\Q$found\E\s+const\b\s*\*/) { + WARN("CONST_CONST", + "'const $found const *' should probably be 'const $found * const'\n" . $herecurr); + } elsif ($sline !~ /\bconst\s+\Q$found\E\s+const\s+\w+\s*\[/) { + WARN("CONST_CONST", + "'const $found const' should probably be 'const $found'\n" . $herecurr); + } + } + +# check for non-global char *foo[] = {"bar", ...} declarations. + if ($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" . + $herecurr); } -# check for declarations of struct pci_device_id - if ($line =~ /\bstruct\s+pci_device_id\s+\w+\s*\[\s*\]\s*\=\s*\{/) { - WARN("DEFINE_PCI_DEVICE_TABLE", - "Use DEFINE_PCI_DEVICE_TABLE for struct pci_device_id\n" . $herecurr); +# check for sizeof(foo)/sizeof(foo[0]) that could be ARRAY_SIZE(foo) + if ($line =~ m@\bsizeof\s*\(\s*($Lval)\s*\)@) { + my $array = $1; + if ($line =~ m@\b(sizeof\s*\(\s*\Q$array\E\s*\)\s*/\s*sizeof\s*\(\s*\Q$array\E\s*\[\s*0\s*\]\s*\))@) { + my $array_div = $1; + if (WARN("ARRAY_SIZE", + "Prefer ARRAY_SIZE($array)\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$array_div\E/ARRAY_SIZE($array)/; + } + } + } + +# check for function declarations without arguments like "int foo()" + if ($line =~ /(\b$Type\s*$Ident)\s*\(\s*\)/) { + if (ERROR("FUNCTION_WITHOUT_ARGS", + "Bad function definition - $1() should probably be $1(void)\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/(\b($Type)\s+($Ident))\s*\(\s*\)/$2 $3(void)/; + } } # check for new typedefs, only function parameters and sparse annotations @@ -2265,7 +4113,7 @@ sub process { $line !~ /\btypedef\s+$Type\s*\(\s*\*?$Ident\s*\)\s*\(/ && $line !~ /\btypedef\s+$Type\s+$Ident\s*\(/ && $line !~ /\b$typeTypedefs\b/ && - $line !~ /\b__bitwise(?:__|)\b/) { + $line !~ /\b__bitwise\b/) { WARN("NEW_TYPEDEFS", "do not add new typedefs\n" . $herecurr); } @@ -2274,7 +4122,7 @@ sub process { # (char*[ const]) while ($line =~ m{(\($NonptrType(\s*(?:$Modifier\b\s*|\*\s*)+)\))}g) { #print "AA<$1>\n"; - my ($from, $to) = ($2, $2); + my ($ident, $from, $to) = ($1, $2, $2); # Should start with a space. $to =~ s/^(\S)/ $1/; @@ -2284,15 +4132,22 @@ sub process { while ($to =~ s/\*\s+\*/\*\*/) { } - #print "from<$from> to<$to>\n"; +## print "1: from<$from> to<$to> ident<$ident>\n"; if ($from ne $to) { - ERROR("POINTER_LOCATION", - "\"(foo$from)\" should be \"(foo$to)\"\n" . $herecurr); + if (ERROR("POINTER_LOCATION", + "\"(foo$from)\" should be \"(foo$to)\"\n" . $herecurr) && + $fix) { + my $sub_from = $ident; + my $sub_to = $ident; + $sub_to =~ s/\Q$from\E/$to/; + $fixed[$fixlinenr] =~ + s@\Q$sub_from\E@$sub_to@; + } } } while ($line =~ m{(\b$NonptrType(\s*(?:$Modifier\b\s*|\*\s*)+)($Ident))}g) { #print "BB<$1>\n"; - my ($from, $to, $ident) = ($2, $2, $3); + my ($match, $from, $to, $ident) = ($1, $2, $2, $3); # Should start with a space. $to =~ s/^(\S)/ $1/; @@ -2304,20 +4159,30 @@ sub process { # Modifiers should have spaces. $to =~ s/(\b$Modifier$)/$1 /; - #print "from<$from> to<$to> ident<$ident>\n"; +## print "2: from<$from> to<$to> ident<$ident>\n"; if ($from ne $to && $ident !~ /^$Modifier$/) { - ERROR("POINTER_LOCATION", - "\"foo${from}bar\" should be \"foo${to}bar\"\n" . $herecurr); + if (ERROR("POINTER_LOCATION", + "\"foo${from}bar\" should be \"foo${to}bar\"\n" . $herecurr) && + $fix) { + + my $sub_from = $match; + my $sub_to = $match; + $sub_to =~ s/\Q$from\E/$to/; + $fixed[$fixlinenr] =~ + s@\Q$sub_from\E@$sub_to@; + } } } -# # no BUG() or BUG_ON() -# if ($line =~ /\b(BUG|BUG_ON)\b/) { -# print "Try to use WARN_ON & Recovery code rather than BUG() or BUG_ON()\n"; -# print "$herecurr"; -# $clean = 0; -# } +# avoid BUG() or BUG_ON() + if ($line =~ /\b(?:BUG|BUG_ON)\b/) { + my $msg_level = \&WARN; + $msg_level = \&CHK if ($file); + &{$msg_level}("AVOID_BUG", + "Avoid crashing the kernel - try using WARN_ON & recovery code rather than BUG() or BUG_ON()\n" . $herecurr); + } +# avoid LINUX_VERSION_CODE if ($line =~ /\bLINUX_VERSION_CODE\b/) { WARN("LINUX_VERSION_CODE", "LINUX_VERSION_CODE should be avoided, code should be for the version to which it is merged\n" . $herecurr); @@ -2326,52 +4191,171 @@ sub process { # check for uses of printk_ratelimit if ($line =~ /\bprintk_ratelimit\s*\(/) { WARN("PRINTK_RATELIMITED", -"Prefer printk_ratelimited or pr_<level>_ratelimited to printk_ratelimit\n" . $herecurr); - } - -# printk should use KERN_* levels. Note that follow on printk's on the -# same line do not need a level, so we use the current block context -# to try and find and validate the current printk. In summary the current -# printk includes all preceding printk's which have no newline on the end. -# we assume the first bad printk is the one to report. - if ($line =~ /\bprintk\((?!KERN_)\s*"/) { - my $ok = 0; - for (my $ln = $linenr - 1; $ln >= $first_line; $ln--) { - #print "CHECK<$lines[$ln - 1]\n"; - # we have a preceding printk if it ends - # with "\n" ignore it, else it is to blame - if ($lines[$ln - 1] =~ m{\bprintk\(}) { - if ($rawlines[$ln - 1] !~ m{\\n"}) { - $ok = 1; - } - last; - } - } - if ($ok == 0) { - WARN("PRINTK_WITHOUT_KERN_LEVEL", - "printk() should include KERN_ facility level\n" . $herecurr); + "Prefer printk_ratelimited or pr_<level>_ratelimited to printk_ratelimit\n" . $herecurr); + } + +# printk should use KERN_* levels + if ($line =~ /\bprintk\s*\(\s*(?!KERN_[A-Z]+\b)/) { + WARN("PRINTK_WITHOUT_KERN_LEVEL", + "printk() should include KERN_<LEVEL> facility level\n" . $herecurr); + } + + if ($line =~ /\bprintk\s*\(\s*KERN_([A-Z]+)/) { + my $orig = $1; + my $level = lc($orig); + $level = "warn" if ($level eq "warning"); + my $level2 = $level; + $level2 = "dbg" if ($level eq "debug"); + WARN("PREFER_PR_LEVEL", + "Prefer [subsystem eg: netdev]_$level2([subsystem]dev, ... then dev_$level2(dev, ... then pr_$level(... to printk(KERN_$orig ...\n" . $herecurr); + } + + if ($line =~ /\bdev_printk\s*\(\s*KERN_([A-Z]+)/) { + my $orig = $1; + my $level = lc($orig); + $level = "warn" if ($level eq "warning"); + $level = "dbg" if ($level eq "debug"); + WARN("PREFER_DEV_LEVEL", + "Prefer dev_$level(... to dev_printk(KERN_$orig, ...\n" . $herecurr); + } + +# ENOSYS means "bad syscall nr" and nothing else. This will have a small +# number of false positives, but assembly files are not checked, so at +# least the arch entry code will not trigger this warning. + if ($line =~ /\bENOSYS\b/) { + WARN("ENOSYS", + "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 (($line=~/$Type\s*$Ident\(.*\).*\s\{/) and - !($line=~/\#\s*define.*do\s\{/) and !($line=~/}/)) { - ERROR("OPEN_BRACE", - "open brace '{' following function declarations go on the next line\n" . $herecurr); + if ($perl_version_ok && + $sline =~ /$Type\s*$Ident\s*$balanced_parens\s*\{/ && + $sline !~ /\#\s*define\b.*do\s*\{/ && + $sline !~ /}/) { + if (ERROR("OPEN_BRACE", + "open brace '{' following function definitions go on the next line\n" . $herecurr) && + $fix) { + fix_delete_line($fixlinenr, $rawline); + my $fixed_line = $rawline; + $fixed_line =~ /(^..*$Type\s*$Ident\(.*\)\s*){(.*)$/; + my $line1 = $1; + my $line2 = $2; + fix_insert_line($fixlinenr, ltrim($line1)); + fix_insert_line($fixlinenr, "\+{"); + if ($line2 !~ /^\s*$/) { + fix_insert_line($fixlinenr, "\+\t" . trim($line2)); + } + } } # open braces for enum, union and struct go on the same line. if ($line =~ /^.\s*{/ && $prevline =~ /^.\s*(?:typedef\s+)?(enum|union|struct)(?:\s+$Ident)?\s*$/) { - ERROR("OPEN_BRACE", - "open brace '{' following $1 go on the same line\n" . $hereprev); + if (ERROR("OPEN_BRACE", + "open brace '{' following $1 go on the same line\n" . $hereprev) && + $fix && $prevline =~ /^\+/ && $line =~ /^\+/) { + fix_delete_line($fixlinenr - 1, $prevrawline); + fix_delete_line($fixlinenr, $rawline); + my $fixedline = rtrim($prevrawline) . " {"; + fix_insert_line($fixlinenr, $fixedline); + $fixedline = $rawline; + $fixedline =~ s/^(.\s*)\{\s*/$1\t/; + if ($fixedline !~ /^\+\s*$/) { + fix_insert_line($fixlinenr, $fixedline); + } + } } # missing space after union, struct or enum definition - if ($line =~ /^.\s*(?:typedef\s+)?(enum|union|struct)(?:\s+$Ident)?(?:\s+$Ident)?[=\{]/) { - WARN("SPACING", - "missing space after $1 definition\n" . $herecurr); + if ($line =~ /^.\s*(?:typedef\s+)?(enum|union|struct)(?:\s+$Ident){1,2}[=\{]/) { + if (WARN("SPACING", + "missing space after $1 definition\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ + s/^(.\s*(?:typedef\s+)?(?:enum|union|struct)(?:\s+$Ident){1,2})([=\{])/$1 $2/; + } + } + +# Function pointer declarations +# check spacing between type, funcptr, and args +# canonical declaration is "type (*funcptr)(args...)" + if ($line =~ /^.\s*($Declare)\((\s*)\*(\s*)($Ident)(\s*)\)(\s*)\(/) { + my $declare = $1; + my $pre_pointer_space = $2; + my $post_pointer_space = $3; + my $funcname = $4; + my $post_funcname_space = $5; + my $pre_args_space = $6; + +# the $Declare variable will capture all spaces after the type +# so check it for a missing trailing missing space but pointer return types +# don't need a space so don't warn for those. + my $post_declare_space = ""; + if ($declare =~ /(\s+)$/) { + $post_declare_space = $1; + $declare = rtrim($declare); + } + if ($declare !~ /\*$/ && $post_declare_space =~ /^$/) { + WARN("SPACING", + "missing space after return type\n" . $herecurr); + $post_declare_space = " "; + } + +# unnecessary space "type (*funcptr)(args...)" +# This test is not currently implemented because these declarations are +# equivalent to +# int foo(int bar, ...) +# and this is form shouldn't/doesn't generate a checkpatch warning. +# +# elsif ($declare =~ /\s{2,}$/) { +# WARN("SPACING", +# "Multiple spaces after return type\n" . $herecurr); +# } + +# unnecessary space "type ( *funcptr)(args...)" + if (defined $pre_pointer_space && + $pre_pointer_space =~ /^\s/) { + WARN("SPACING", + "Unnecessary space after function pointer open parenthesis\n" . $herecurr); + } + +# unnecessary space "type (* funcptr)(args...)" + if (defined $post_pointer_space && + $post_pointer_space =~ /^\s/) { + WARN("SPACING", + "Unnecessary space before function pointer name\n" . $herecurr); + } + +# unnecessary space "type (*funcptr )(args...)" + if (defined $post_funcname_space && + $post_funcname_space =~ /^\s/) { + WARN("SPACING", + "Unnecessary space after function pointer name\n" . $herecurr); + } + +# unnecessary space "type (*funcptr) (args...)" + if (defined $pre_args_space && + $pre_args_space =~ /^\s/) { + WARN("SPACING", + "Unnecessary space before function pointer arguments\n" . $herecurr); + } + + if (show_type("SPACING") && $fix) { + $fixed[$fixlinenr] =~ + s/^(.\s*)$Declare\s*\(\s*\*\s*$Ident\s*\)\s*\(/$1 . $declare . $post_declare_space . '(*' . $funcname . ')('/ex; + } } # check for spacing round square brackets; allowed: @@ -2382,9 +4366,13 @@ sub process { my ($where, $prefix) = ($-[1], $1); if ($prefix !~ /$Type\s+$/ && ($where != 0 || $prefix !~ /^.\s+$/) && - $prefix !~ /[{,]\s+$/) { - ERROR("BRACKET_SPACE", - "space prohibited before open square bracket '['\n" . $herecurr); + $prefix !~ /[{,:]\s+$/) { + if (ERROR("BRACKET_SPACE", + "space prohibited before open square bracket '['\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ + s/^(\+.*?)\s+\[/$1\[/; + } } } @@ -2401,7 +4389,6 @@ sub process { __attribute__|format|__extension__| asm|__asm__)$/x) { - # cpp #define statements have non-optional spaces, ie # if there is a space between the name and the open # parenthesis it is simply not a parameter group. @@ -2415,25 +4402,53 @@ sub process { } elsif ($ctx =~ /$Type$/) { } else { - WARN("SPACING", - "space prohibited between function name and open parenthesis '('\n" . $herecurr); + if (WARN("SPACING", + "space prohibited between function name and open parenthesis '('\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ + s/\b$name\s+\(/$name\(/; + } } } + # Check operator spacing. if (!($line=~/\#\s*include/)) { + my $fixed_line = ""; + my $line_fixed = 0; + my $ops = qr{ <<=|>>=|<=|>=|==|!=| \+=|-=|\*=|\/=|%=|\^=|\|=|&=| =>|->|<<|>>|<|>|=|!|~| &&|\|\||,|\^|\+\+|--|&|\||\+|-|\*|\/|%| - \?|: + \?:|\?|: }x; my @elements = split(/($ops|;)/, $opline); + +## print("element count: <" . $#elements . ">\n"); +## foreach my $el (@elements) { +## print("el: <$el>\n"); +## } + + my @fix_elements = (); my $off = 0; + foreach my $el (@elements) { + push(@fix_elements, substr($rawline, $off, length($el))); + $off += length($el); + } + + $off = 0; + my $blank = copy_spacing($opline); + my $last_after = -1; for (my $n = 0; $n < $#elements; $n += 2) { + + my $good = $fix_elements[$n] . $fix_elements[$n + 1]; + +## print("n: <$n> good: <$good>\n"); + $off += length($elements[$n]); # Pick up the preceding and succeeding characters. @@ -2481,7 +4496,7 @@ sub process { # Ignore operators passed as parameters. if ($op_type ne 'V' && - $ca =~ /\s$/ && $cc =~ /^\s*,/) { + $ca =~ /\s$/ && $cc =~ /^\s*[,\)]/) { # # Ignore comments # } elsif ($op =~ /^$;+$/) { @@ -2490,27 +4505,62 @@ sub process { } elsif ($op eq ';') { if ($ctx !~ /.x[WEBC]/ && $cc !~ /^\\/ && $cc !~ /^;/) { - ERROR("SPACING", - "space required after that '$op' $at\n" . $hereptr); + if (ERROR("SPACING", + "space required after that '$op' $at\n" . $hereptr)) { + $good = $fix_elements[$n] . trim($fix_elements[$n + 1]) . " "; + $line_fixed = 1; + } } # // is a comment } elsif ($op eq '//') { + # : when part of a bitfield + } elsif ($opv eq ':B') { + # skip the bitfield test for now + # No spaces for: # -> - # : when part of a bitfield - } elsif ($op eq '->' || $opv eq ':B') { + } elsif ($op eq '->') { if ($ctx =~ /Wx.|.xW/) { - ERROR("SPACING", - "spaces prohibited around that '$op' $at\n" . $hereptr); + if (ERROR("SPACING", + "spaces prohibited around that '$op' $at\n" . $hereptr)) { + $good = rtrim($fix_elements[$n]) . trim($fix_elements[$n + 1]); + if (defined $fix_elements[$n + 2]) { + $fix_elements[$n + 2] =~ s/^\s+//; + } + $line_fixed = 1; + } } - # , must have a space on the right. + # , must not have a space before and must have a space on the right. } elsif ($op eq ',') { + my $rtrim_before = 0; + my $space_after = 0; + if ($ctx =~ /Wx./) { + if (ERROR("SPACING", + "space prohibited before that '$op' $at\n" . $hereptr)) { + $line_fixed = 1; + $rtrim_before = 1; + } + } if ($ctx !~ /.x[WEC]/ && $cc !~ /^}/) { - ERROR("SPACING", - "space required after that '$op' $at\n" . $hereptr); + if (ERROR("SPACING", + "space required after that '$op' $at\n" . $hereptr)) { + $line_fixed = 1; + $last_after = $n; + $space_after = 1; + } + } + if ($rtrim_before || $space_after) { + if ($rtrim_before) { + $good = rtrim($fix_elements[$n]) . trim($fix_elements[$n + 1]); + } else { + $good = $fix_elements[$n] . trim($fix_elements[$n + 1]); + } + if ($space_after) { + $good .= " "; + } } # '*' as part of a type definition -- reported already. @@ -2524,34 +4574,56 @@ sub process { $opv eq '*U' || $opv eq '-U' || $opv eq '&U' || $opv eq '&&U') { if ($ctx !~ /[WEBC]x./ && $ca !~ /(?:\)|!|~|\*|-|\&|\||\+\+|\-\-|\{)$/) { - ERROR("SPACING", - "space required before that '$op' $at\n" . $hereptr); + if (ERROR("SPACING", + "space required before that '$op' $at\n" . $hereptr)) { + if ($n != $last_after + 2) { + $good = $fix_elements[$n] . " " . ltrim($fix_elements[$n + 1]); + $line_fixed = 1; + } + } } if ($op eq '*' && $cc =~/\s*$Modifier\b/) { # A unary '*' may be const } elsif ($ctx =~ /.xW/) { - ERROR("SPACING", - "space prohibited after that '$op' $at\n" . $hereptr); + if (ERROR("SPACING", + "space prohibited after that '$op' $at\n" . $hereptr)) { + $good = $fix_elements[$n] . rtrim($fix_elements[$n + 1]); + if (defined $fix_elements[$n + 2]) { + $fix_elements[$n + 2] =~ s/^\s+//; + } + $line_fixed = 1; + } } # unary ++ and unary -- are allowed no space on one side. } elsif ($op eq '++' or $op eq '--') { if ($ctx !~ /[WEOBC]x[^W]/ && $ctx !~ /[^W]x[WOBEC]/) { - ERROR("SPACING", - "space required one side of that '$op' $at\n" . $hereptr); + if (ERROR("SPACING", + "space required one side of that '$op' $at\n" . $hereptr)) { + $good = $fix_elements[$n] . trim($fix_elements[$n + 1]) . " "; + $line_fixed = 1; + } } if ($ctx =~ /Wx[BE]/ || ($ctx =~ /Wx./ && $cc =~ /^;/)) { - ERROR("SPACING", - "space prohibited before that '$op' $at\n" . $hereptr); + if (ERROR("SPACING", + "space prohibited before that '$op' $at\n" . $hereptr)) { + $good = rtrim($fix_elements[$n]) . trim($fix_elements[$n + 1]); + $line_fixed = 1; + } } if ($ctx =~ /ExW/) { - ERROR("SPACING", - "space prohibited after that '$op' $at\n" . $hereptr); + if (ERROR("SPACING", + "space prohibited after that '$op' $at\n" . $hereptr)) { + $good = $fix_elements[$n] . trim($fix_elements[$n + 1]); + if (defined $fix_elements[$n + 2]) { + $fix_elements[$n + 2] =~ s/^\s+//; + } + $line_fixed = 1; + } } - # << and >> may either have or not have spaces both sides } elsif ($op eq '<<' or $op eq '>>' or $op eq '&' or $op eq '^' or $op eq '|' or @@ -2559,18 +4631,41 @@ sub process { $op eq '*' or $op eq '/' or $op eq '%') { - if ($ctx =~ /Wx[^WCE]|[^WCE]xW/) { - ERROR("SPACING", - "need consistent spacing around '$op' $at\n" . - $hereptr); + if ($check) { + if (defined $fix_elements[$n + 2] && $ctx !~ /[EW]x[EW]/) { + if (CHK("SPACING", + "spaces preferred around that '$op' $at\n" . $hereptr)) { + $good = rtrim($fix_elements[$n]) . " " . trim($fix_elements[$n + 1]) . " "; + $fix_elements[$n + 2] =~ s/^\s+//; + $line_fixed = 1; + } + } elsif (!defined $fix_elements[$n + 2] && $ctx !~ /Wx[OE]/) { + if (CHK("SPACING", + "space preferred before that '$op' $at\n" . $hereptr)) { + $good = rtrim($fix_elements[$n]) . " " . trim($fix_elements[$n + 1]); + $line_fixed = 1; + } + } + } elsif ($ctx =~ /Wx[^WCE]|[^WCE]xW/) { + if (ERROR("SPACING", + "need consistent spacing around '$op' $at\n" . $hereptr)) { + $good = rtrim($fix_elements[$n]) . " " . trim($fix_elements[$n + 1]) . " "; + if (defined $fix_elements[$n + 2]) { + $fix_elements[$n + 2] =~ s/^\s+//; + } + $line_fixed = 1; + } } # A colon needs no spaces before when it is # terminating a case value or a label. } elsif ($opv eq ':C' || $opv eq ':L') { if ($ctx =~ /Wx./) { - ERROR("SPACING", - "space prohibited before that '$op' $at\n" . $hereptr); + if (ERROR("SPACING", + "space prohibited before that '$op' $at\n" . $hereptr)) { + $good = rtrim($fix_elements[$n]) . trim($fix_elements[$n + 1]); + $line_fixed = 1; + } } # All the others need spaces both sides. @@ -2586,18 +4681,54 @@ sub process { $ok = 1; } - # Ignore ?: - if (($opv eq ':O' && $ca =~ /\?$/) || - ($op eq '?' && $cc =~ /^:/)) { + # for asm volatile statements + # ignore a colon with another + # colon immediately before or after + if (($op eq ':') && + ($ca =~ /:$/ || $cc =~ /^:/)) { $ok = 1; } + # messages are ERROR, but ?: are CHK if ($ok == 0) { - ERROR("SPACING", - "spaces required around that '$op' $at\n" . $hereptr); + my $msg_level = \&ERROR; + $msg_level = \&CHK if (($op eq '?:' || $op eq '?' || $op eq ':') && $ctx =~ /VxV/); + + if (&{$msg_level}("SPACING", + "spaces required around that '$op' $at\n" . $hereptr)) { + $good = rtrim($fix_elements[$n]) . " " . trim($fix_elements[$n + 1]) . " "; + if (defined $fix_elements[$n + 2]) { + $fix_elements[$n + 2] =~ s/^\s+//; + } + $line_fixed = 1; + } } } $off += length($elements[$n + 1]); + +## print("n: <$n> GOOD: <$good>\n"); + + $fixed_line = $fixed_line . $good; + } + + if (($#elements % 2) == 0) { + $fixed_line = $fixed_line . $fix_elements[$#elements]; + } + + if ($fix && $line_fixed && $fixed_line ne $fixed[$fixlinenr]) { + $fixed[$fixlinenr] = $fixed_line; + } + + + } + +# check for whitespace before a non-naked semicolon + if ($line =~ /^\+.*\S\s+;\s*$/) { + if (WARN("SPACING", + "space prohibited before semicolon\n" . $herecurr) && + $fix) { + 1 while $fixed[$fixlinenr] =~ + s/^(\+.*\S)\s+;/$1;/; } } @@ -2609,100 +4740,240 @@ sub process { ## # check for multiple declarations, allowing for a function declaration ## # continuation. -## if ($line =~ /^.\s*$Type\s+$Ident(?:\s*=[^,{]*)?\s*,\s*$Ident.*/ && -## $line !~ /^.\s*$Type\s+$Ident(?:\s*=[^,{]*)?\s*,\s*$Type\s*$Ident.*/) { +## if ($line =~ /^.\s*$Type\s+$Ident(?:\s*=[^,{]*)?\s*,\s*$Ident.*/ && +## $line !~ /^.\s*$Type\s+$Ident(?:\s*=[^,{]*)?\s*,\s*$Type\s*$Ident.*/) { ## -## # Remove any bracketed sections to ensure we do not -## # falsly report the parameters of functions. -## my $ln = $line; -## while ($ln =~ s/\([^\(\)]*\)//g) { -## } -## if ($ln =~ /,/) { -## WARN("MULTIPLE_DECLARATION", +## # Remove any bracketed sections to ensure we do not +## # falsly report the parameters of functions. +## my $ln = $line; +## while ($ln =~ s/\([^\(\)]*\)//g) { +## } +## if ($ln =~ /,/) { +## WARN("MULTIPLE_DECLARATION", ## "declaring multiple variables together should be avoided\n" . $herecurr); -## } -## } +## } +## } #need space before brace following if, while, etc if (($line =~ /\(.*\)\{/ && $line !~ /\($Type\)\{/) || - $line =~ /do\{/) { - ERROR("SPACING", - "space required before the open brace '{'\n" . $herecurr); + $line =~ /\b(?:else|do)\{/) { + if (ERROR("SPACING", + "space required before the open brace '{'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/^(\+.*(?:do|else|\)))\{/$1 {/; + } } +## # check for blank lines before declarations +## if ($line =~ /^.\t+$Type\s+$Ident(?:\s*=.*)?;/ && +## $prevrawline =~ /^.\s*$/) { +## WARN("SPACING", +## "No blank lines before declarations\n" . $hereprev); +## } +## + # closing brace should have a space following it when it has anything # on the line - if ($line =~ /}(?!(?:,|;|\)))\S/) { - ERROR("SPACING", - "space required after that close brace '}'\n" . $herecurr); + if ($line =~ /}(?!(?:,|;|\)|\}))\S/) { + if (ERROR("SPACING", + "space required after that close brace '}'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ + s/}((?!(?:,|;|\)))\S)/} $1/; + } } # check spacing on square brackets if ($line =~ /\[\s/ && $line !~ /\[\s*$/) { - ERROR("SPACING", - "space prohibited after that open square bracket '['\n" . $herecurr); + if (ERROR("SPACING", + "space prohibited after that open square bracket '['\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ + s/\[\s+/\[/; + } } if ($line =~ /\s\]/) { - ERROR("SPACING", - "space prohibited before that close square bracket ']'\n" . $herecurr); + if (ERROR("SPACING", + "space prohibited before that close square bracket ']'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ + s/\s+\]/\]/; + } } # check spacing on parentheses if ($line =~ /\(\s/ && $line !~ /\(\s*(?:\\)?$/ && $line !~ /for\s*\(\s+;/) { - ERROR("SPACING", - "space prohibited after that open parenthesis '('\n" . $herecurr); + if (ERROR("SPACING", + "space prohibited after that open parenthesis '('\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ + s/\(\s+/\(/; + } } if ($line =~ /(\s+)\)/ && $line !~ /^.\s*\)/ && $line !~ /for\s*\(.*;\s+\)/ && $line !~ /:\s+\)/) { - ERROR("SPACING", - "space prohibited before that close parenthesis ')'\n" . $herecurr); + if (ERROR("SPACING", + "space prohibited before that close parenthesis ')'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ + s/\s+\)/\)/; + } + } + +# check unnecessary parentheses around addressof/dereference single $Lvals +# ie: &(foo->bar) should be &foo->bar and *(foo->bar) should be *foo->bar + + while ($line =~ /(?:[^&]&\s*|\*)\(\s*($Ident\s*(?:$Member\s*)+)\s*\)/g) { + my $var = $1; + if (CHK("UNNECESSARY_PARENTHESES", + "Unnecessary parentheses around $var\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\(\s*\Q$var\E\s*\)/$var/; + } + } + +# check for unnecessary parentheses around function pointer uses +# ie: (foo->bar)(); should be foo->bar(); +# but not "if (foo->bar) (" to avoid some false positives + if ($line =~ /(\bif\s*|)(\(\s*$Ident\s*(?:$Member\s*)+\))[ \t]*\(/ && $1 !~ /^if/) { + my $var = $2; + if (CHK("UNNECESSARY_PARENTHESES", + "Unnecessary parentheses around function pointer $var\n" . $herecurr) && + $fix) { + my $var2 = deparenthesize($var); + $var2 =~ s/\s//g; + $fixed[$fixlinenr] =~ s/\Q$var\E/$var2/; + } + } + +# check for unnecessary parentheses around comparisons in if uses +# when !drivers/staging or command-line uses --strict + if (($realfile !~ m@^(?:drivers/staging/)@ || $check_orig) && + $perl_version_ok && defined($stat) && + $stat =~ /(^.\s*if\s*($balanced_parens))/) { + my $if_stat = $1; + my $test = substr($2, 1, -1); + my $herectx; + while ($test =~ /(?:^|[^\w\&\!\~])+\s*\(\s*([\&\!\~]?\s*$Lval\s*(?:$Compare\s*$FuncArg)?)\s*\)/g) { + my $match = $1; + # avoid parentheses around potential macro args + next if ($match =~ /^\s*\w+\s*$/); + if (!defined($herectx)) { + $herectx = $here . "\n"; + my $cnt = statement_rawlines($if_stat); + for (my $n = 0; $n < $cnt; $n++) { + my $rl = raw_line($linenr, $n); + $herectx .= $rl . "\n"; + last if $rl =~ /^[ \+].*\{/; + } + } + CHK("UNNECESSARY_PARENTHESES", + "Unnecessary parentheses around '$match'\n" . $herectx); + } } #goto labels aren't indented, allow a single space however if ($line=~/^.\s+[A-Za-z\d_]+:(?![0-9]+)/ and !($line=~/^. [A-Za-z\d_]+:/) and !($line=~/^.\s+default:/)) { - WARN("INDENTED_LABEL", - "labels should not be indented\n" . $herecurr); + if (WARN("INDENTED_LABEL", + "labels should not be indented\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ + s/^(.)\s+/$1/; + } } -# Return is not a function. - if (defined($stat) && $stat =~ /^.\s*return(\s*)(\(.*);/s) { +# return is not a function + if (defined($stat) && $stat =~ /^.\s*return(\s*)\(/s) { my $spacing = $1; - my $value = $2; - - # Flatten any parentheses - $value =~ s/\(/ \(/g; - $value =~ s/\)/\) /g; - while ($value =~ s/\[[^\[\]]*\]/1/ || - $value !~ /(?:$Ident|-?$Constant)\s* - $Compare\s* - (?:$Ident|-?$Constant)/x && - $value =~ s/\([^\(\)]*\)/1/) { - } -#print "value<$value>\n"; - if ($value =~ /^\s*(?:$Ident|-?$Constant)\s*$/) { - ERROR("RETURN_PARENTHESES", - "return is not a function, parentheses are not required\n" . $herecurr); - + if ($perl_version_ok && + $stat =~ /^.\s*return\s*($balanced_parens)\s*;\s*$/) { + my $value = $1; + $value = deparenthesize($value); + if ($value =~ m/^\s*$FuncArg\s*(?:\?|$)/) { + ERROR("RETURN_PARENTHESES", + "return is not a function, parentheses are not required\n" . $herecurr); + } } elsif ($spacing !~ /\s+/) { ERROR("SPACING", "space required before the open parenthesis '('\n" . $herecurr); } } -# Return of what appears to be an errno should normally be -'ve - if ($line =~ /^.\s*return\s*(E[A-Z]*)\s*;/) { + +# unnecessary return in a void function +# at end-of-function, with the previous line a single leading tab, then return; +# and the line before that not a goto label target like "out:" + if ($sline =~ /^[ \+]}\s*$/ && + $prevline =~ /^\+\treturn\s*;\s*$/ && + $linenr >= 3 && + $lines[$linenr - 3] =~ /^[ +]/ && + $lines[$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 && + $line =~ /\bif\s*((?:\(\s*){2,})/) { + my $openparens = $1; + my $count = $openparens =~ tr@\(@\(@; + my $msg = ""; + if ($line =~ /\bif\s*(?:\(\s*){$count,$count}$LvalOrFunc\s*($Compare)\s*$LvalOrFunc(?:\s*\)){$count,$count}/) { + my $comp = $4; #Not $1 because of $LvalOrFunc + $msg = " - maybe == should be = ?" if ($comp eq "=="); + WARN("UNNECESSARY_PARENTHESES", + "Unnecessary parentheses$msg\n" . $herecurr); + } + } + +# comparisons with a constant or upper case identifier on the left +# avoid cases like "foo + BAR < baz" +# only fix matches surrounded by parentheses to avoid incorrect +# conversions like "FOO < baz() + 5" being "misfixed" to "baz() > FOO + 5" + if ($perl_version_ok && + $line =~ /^\+(.*)\b($Constant|[A-Z_][A-Z0-9_]*)\s*($Compare)\s*($LvalOrFunc)/) { + my $lead = $1; + my $const = $2; + my $comp = $3; + my $to = $4; + my $newcomp = $comp; + if ($lead !~ /(?:$Operators|\.)\s*$/ && + $to !~ /^(?:Constant|[A-Z_][A-Z0-9_]*)$/ && + WARN("CONSTANT_COMPARISON", + "Comparisons should place the constant on the right side of the test\n" . $herecurr) && + $fix) { + if ($comp eq "<") { + $newcomp = ">"; + } elsif ($comp eq "<=") { + $newcomp = ">="; + } elsif ($comp eq ">") { + $newcomp = "<"; + } elsif ($comp eq ">=") { + $newcomp = "<="; + } + $fixed[$fixlinenr] =~ s/\(\s*\Q$const\E\s*$Compare\s*\Q$to\E\s*\)/($to $newcomp $const)/; + } + } + +# Return of what appears to be an errno should normally be negative + if ($sline =~ /\breturn(?:\s*\(+\s*|\s+)(E[A-Z]+)(?:\s*\)+\s*|\s*)[;:,]/) { my $name = $1; if ($name ne 'EOF' && $name ne 'ERROR') { WARN("USE_NEGATIVE_ERRNO", - "return of an errno should typically be -ve (return -$1)\n" . $herecurr); + "return of an errno should typically be negative (ie: return -$1)\n" . $herecurr); } } # Need a space before open parenthesis after if, while etc - if ($line=~/\b(if|while|for|switch)\(/) { - ERROR("SPACING", "space required before the open parenthesis '('\n" . $herecurr); + if ($line =~ /\b(if|while|for|switch)\(/) { + if (ERROR("SPACING", + "space required before the open parenthesis '('\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ + s/\b(if|while|for|switch)\(/$1 \(/; + } } # Check for illegal assignment in if conditional -- and check for trailing @@ -2729,6 +5000,7 @@ sub process { } } if (!defined $suppress_whiletrailers{$linenr} && + defined($stat) && defined($cond) && $line =~ /\b(?:if|while|for)\s*\(/ && $line !~ /^.\s*#/) { my ($s, $c) = ($stat, $cond); @@ -2789,7 +5061,7 @@ sub process { # if should not continue a brace if ($line =~ /}\s*if\b/) { ERROR("TRAILING_STATEMENTS", - "trailing statements should be on next line\n" . + "trailing statements should be on next line (or did you mean 'else if'?)\n" . $herecurr); } # case and default should not have general statements after them @@ -2805,14 +5077,26 @@ sub process { # Check for }<nl>else {, these must be at the same # indent level to be relevant to each other. - if ($prevline=~/}\s*$/ and $line=~/^.\s*else\s*/ and - $previndent == $indent) { - ERROR("ELSE_AFTER_BRACE", - "else should follow close brace '}'\n" . $hereprev); + if ($prevline=~/}\s*$/ and $line=~/^.\s*else\s*/ && + $previndent == $indent) { + if (ERROR("ELSE_AFTER_BRACE", + "else should follow close brace '}'\n" . $hereprev) && + $fix && $prevline =~ /^\+/ && $line =~ /^\+/) { + fix_delete_line($fixlinenr - 1, $prevrawline); + fix_delete_line($fixlinenr, $rawline); + my $fixedline = $prevrawline; + $fixedline =~ s/}\s*$//; + if ($fixedline !~ /^\+\s*$/) { + fix_insert_line($fixlinenr, $fixedline); + } + $fixedline = $rawline; + $fixedline =~ s/^(.\s*)else/$1} else/; + fix_insert_line($fixlinenr, $fixedline); + } } - if ($prevline=~/}\s*$/ and $line=~/^.\s*while\s*/ and - $previndent == $indent) { + if ($prevline=~/}\s*$/ and $line=~/^.\s*while\s*/ && + $previndent == $indent) { my ($s, $c) = ctx_statement_block($linenr, $realcnt, 0); # Find out what is on the end of the line after the @@ -2821,25 +5105,65 @@ sub process { $s =~ s/\n.*//g; if ($s =~ /^\s*;/) { - ERROR("WHILE_AFTER_BRACE", - "while should follow close brace '}'\n" . $hereprev); + if (ERROR("WHILE_AFTER_BRACE", + "while should follow close brace '}'\n" . $hereprev) && + $fix && $prevline =~ /^\+/ && $line =~ /^\+/) { + fix_delete_line($fixlinenr - 1, $prevrawline); + fix_delete_line($fixlinenr, $rawline); + my $fixedline = $prevrawline; + my $trailing = $rawline; + $trailing =~ s/^\+//; + $trailing = trim($trailing); + $fixedline =~ s/}\s*$/} $trailing/; + fix_insert_line($fixlinenr, $fixedline); + } } } -#studly caps, commented out until figure out how to distinguish between use of existing and adding new -# if (($line=~/[\w_][a-z\d]+[A-Z]/) and !($line=~/print/)) { -# print "No studly caps, use _\n"; -# print "$herecurr"; -# $clean = 0; -# } +#Specific variable tests + while ($line =~ m{($Constant|$Lval)}g) { + my $var = $1; + +#CamelCase + if ($var !~ /^$Constant$/ && + $var =~ /[A-Z][a-z]|[a-z][A-Z]/ && +#Ignore Page<foo> variants + $var !~ /^(?:Clear|Set|TestClear|TestSet|)Page[A-Z]/ && +#Ignore SI style variants like nS, mV and dB +#(ie: max_uV, regulator_min_uA_show, RANGE_mA_VALUE) + $var !~ /^(?:[a-z0-9_]*|[A-Z0-9_]*)?_?[a-z][A-Z](?:_[a-z0-9_]+|_[A-Z0-9_]+)?$/ && +#Ignore some three character SI units explicitly, like MiB and KHz + $var !~ /^(?:[a-z_]*?)_?(?:[KMGT]iB|[KMGT]?Hz)(?:_[a-z_]+)?$/) { + while ($var =~ m{($Ident)}g) { + my $word = $1; + next if ($word !~ /[A-Z][a-z]|[a-z][A-Z]/); + if ($check) { + seed_camelcase_includes(); + if (!$file && !$camelcase_file_seeded) { + seed_camelcase_file($realfile); + $camelcase_file_seeded = 1; + } + } + if (!defined $camelcase{$word}) { + $camelcase{$word} = 1; + CHK("CAMELCASE", + "Avoid CamelCase: <$word>\n" . $herecurr); + } + } + } + } #no spaces allowed after \ in define - if ($line=~/\#\s*define.*\\\s$/) { - WARN("WHITESPACE_AFTER_LINE_CONTINUATION", - "Whitepspace after \\ makes next lines useless\n" . $herecurr); + if ($line =~ /\#\s*define.*\\\s+$/) { + if (WARN("WHITESPACE_AFTER_LINE_CONTINUATION", + "Whitespace after \\ makes next lines useless\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\s+$//; + } } -#warn if <asm/foo.h> is #included and <linux/foo.h> is available (uses RAW line) +# warn if <asm/foo.h> is #included and <linux/foo.h> is available and includes +# itself <asm/foo.h> (uses RAW line) if ($tree && $rawline =~ m{^.\s*\#\s*include\s*\<asm\/(.*)\.h\>}) { my $file = "$1.h"; my $checkfile = "include/linux/$file"; @@ -2847,12 +5171,15 @@ sub process { $realfile ne $checkfile && $1 !~ /$allowed_asm_includes/) { - if ($realfile =~ m{^arch/}) { - CHK("ARCH_INCLUDE_LINUX", - "Consider using #include <linux/$file> instead of <asm/$file>\n" . $herecurr); - } else { - WARN("INCLUDE_LINUX", - "Use #include <linux/$file> instead of <asm/$file>\n" . $herecurr); + my $asminclude = `grep -Ec "#include\\s+<asm/$file>" $root/$checkfile`; + if ($asminclude > 0) { + if ($realfile =~ m{^arch/}) { + CHK("ARCH_INCLUDE_LINUX", + "Consider using #include <linux/$file> instead of <asm/$file>\n" . $herecurr); + } else { + WARN("INCLUDE_LINUX", + "Use #include <linux/$file> instead of <asm/$file>\n" . $herecurr); + } } } } @@ -2866,13 +5193,29 @@ sub process { my $cnt = $realcnt; my ($off, $dstat, $dcond, $rest); my $ctx = ''; + my $has_flow_statement = 0; + my $has_arg_concat = 0; ($dstat, $dcond, $ln, $cnt, $off) = ctx_statement_block($linenr, $realcnt, 0); $ctx = $dstat; #print "dstat<$dstat> dcond<$dcond> cnt<$cnt> off<$off>\n"; #print "LINE<$lines[$ln-1]> len<" . length($lines[$ln-1]) . "\n"; - $dstat =~ s/^.\s*\#\s*define\s+$Ident(?:\([^\)]*\))?\s*//; + $has_flow_statement = 1 if ($ctx =~ /\b(goto|return)\b/); + $has_arg_concat = 1 if ($ctx =~ /\#\#/ && $ctx !~ /\#\#\s*(?:__VA_ARGS__|args)\b/); + + $dstat =~ s/^.\s*\#\s*define\s+$Ident(\([^\)]*\))?\s*//; + my $define_args = $1; + my $define_stmt = $dstat; + my @def_args = (); + + if (defined $define_args && $define_args ne "") { + $define_args = substr($define_args, 1, length($define_args) - 2); + $define_args =~ s/\s*//g; + $define_args =~ s/\\\+?//g; + @def_args = split(",", $define_args); + } + $dstat =~ s/$;//g; $dstat =~ s/\\\n.//g; $dstat =~ s/^\s*//s; @@ -2881,68 +5224,169 @@ sub process { # Flatten any parentheses and braces while ($dstat =~ s/\([^\(\)]*\)/1/ || $dstat =~ s/\{[^\{\}]*\}/1/ || - $dstat =~ s/\[[^\[\]]*\]/1/) + $dstat =~ s/.\[[^\[\]]*\]/1/) { } - # Flatten any obvious string concatentation. - while ($dstat =~ s/("X*")\s*$Ident/$1/ || - $dstat =~ s/$Ident\s*("X*")/$1/) + # Flatten any obvious string concatenation. + while ($dstat =~ s/($String)\s*$Ident/$1/ || + $dstat =~ s/$Ident\s*($String)/$1/) { } + # Make asm volatile uses seem like a generic function + $dstat =~ s/\b_*asm_*\s+_*volatile_*\b/asm_volatile/g; + my $exceptions = qr{ $Declare| module_param_named| - MODULE_PARAM_DESC| + MODULE_PARM_DESC| DECLARE_PER_CPU| DEFINE_PER_CPU| __typeof__\(| union| struct| \.$Ident\s*=\s*| - ^\"|\"$ + ^\"|\"$| + ^\[ }x; #print "REST<$rest> dstat<$dstat> ctx<$ctx>\n"; + + $ctx =~ s/\n*$//; + my $stmt_cnt = statement_rawlines($ctx); + my $herectx = get_stat_here($linenr, $stmt_cnt, $here); + if ($dstat ne '' && $dstat !~ /^(?:$Ident|-?$Constant),$/ && # 10, // foo(), $dstat !~ /^(?:$Ident|-?$Constant);$/ && # foo(); - $dstat !~ /^[!~-]?(?:$Ident|$Constant)$/ && # 10 // foo() // !foo // ~foo // -foo - $dstat !~ /^'X'$/ && # character constants + $dstat !~ /^[!~-]?(?:$Lval|$Constant)$/ && # 10 // foo() // !foo // ~foo // -foo // foo->bar // foo.bar->baz + $dstat !~ /^'X'$/ && $dstat !~ /^'XX'$/ && # character constants $dstat !~ /$exceptions/ && $dstat !~ /^\.$Ident\s*=/ && # .foo = + $dstat !~ /^(?:\#\s*$Ident|\#\s*$Constant)\s*$/ && # stringification #foo $dstat !~ /^do\s*$Constant\s*while\s*$Constant;?$/ && # do {...} while (...); // do {...} while (...) $dstat !~ /^for\s*$Constant$/ && # for (...) $dstat !~ /^for\s*$Constant\s+(?:$Ident|-?$Constant)$/ && # for (...) bar() $dstat !~ /^do\s*{/ && # do {... - $dstat !~ /^\(\{/) # ({... + $dstat !~ /^\(\{/ && # ({... + $ctx !~ /^.\s*#\s*define\s+TRACE_(?:SYSTEM|INCLUDE_FILE|INCLUDE_PATH)\b/) { - $ctx =~ s/\n*$//; - my $herectx = $here . "\n"; - my $cnt = statement_rawlines($ctx); - - for (my $n = 0; $n < $cnt; $n++) { - $herectx .= raw_line($linenr, $n) . "\n"; - } - - if ($dstat =~ /;/) { + if ($dstat =~ /^\s*if\b/) { + ERROR("MULTISTATEMENT_MACRO_USE_DO_WHILE", + "Macros starting with if should be enclosed by a do - while loop to avoid possible if/else logic defects\n" . "$herectx"); + } elsif ($dstat =~ /;/) { ERROR("MULTISTATEMENT_MACRO_USE_DO_WHILE", "Macros with multiple statements should be enclosed in a do - while loop\n" . "$herectx"); } else { ERROR("COMPLEX_MACRO", - "Macros with complex values should be enclosed in parenthesis\n" . "$herectx"); + "Macros with complex values should be enclosed in parentheses\n" . "$herectx"); } + + } + + # Make $define_stmt single line, comment-free, etc + my @stmt_array = split('\n', $define_stmt); + my $first = 1; + $define_stmt = ""; + foreach my $l (@stmt_array) { + $l =~ s/\\$//; + if ($first) { + $define_stmt = $l; + $first = 0; + } elsif ($l =~ /^[\+ ]/) { + $define_stmt .= substr($l, 1); + } + } + $define_stmt =~ s/$;//g; + $define_stmt =~ s/\s+/ /g; + $define_stmt = trim($define_stmt); + +# check if any macro arguments are reused (ignore '...' and 'type') + foreach my $arg (@def_args) { + next if ($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; + $tmp_stmt =~ s/\#+\s*$arg\b//g; + $tmp_stmt =~ s/\b$arg\s*\#\#//g; + my $use_cnt = () = $tmp_stmt =~ /\b$arg\b/g; + if ($use_cnt > 1) { + CHK("MACRO_ARG_REUSE", + "Macro argument reuse '$arg' - possible side-effects?\n" . "$herectx"); + } +# check if any macro arguments may have other precedence issues + if ($tmp_stmt =~ m/($Operators)?\s*\b$arg\b\s*($Operators)?/m && + ((defined($1) && $1 ne ',') || + (defined($2) && $2 ne ','))) { + CHK("MACRO_ARG_PRECEDENCE", + "Macro argument '$arg' may be better as '($arg)' to avoid precedence issues\n" . "$herectx"); + } + } + +# check for macros with flow control, but without ## concatenation +# ## concatenation is commonly a macro that defines a function so ignore those + if ($has_flow_statement && !$has_arg_concat) { + my $cnt = statement_rawlines($ctx); + my $herectx = get_stat_here($linenr, $cnt, $here); + + WARN("MACRO_WITH_FLOW_CONTROL", + "Macros with flow control statements should be avoided\n" . "$herectx"); + } + +# check for line continuations outside of #defines, preprocessor #, and asm + + } else { + if ($prevline !~ /^..*\\$/ && + $line !~ /^\+\s*\#.*\\$/ && # preprocessor + $line !~ /^\+.*\b(__asm__|asm)\b.*\\$/ && # asm + $line =~ /^\+.*\\$/) { + WARN("LINE_CONTINUATIONS", + "Avoid unnecessary line continuations\n" . $herecurr); } } -# make sure symbols are always wrapped with VMLINUX_SYMBOL() ... -# all assignments may have only one of the following with an assignment: -# . -# ALIGN(...) -# VMLINUX_SYMBOL(...) - if ($realfile eq 'vmlinux.lds.h' && $line =~ /(?:(?:^|\s)$Ident\s*=|=\s*$Ident(?:\s|$))/) { - WARN("MISSING_VMLINUX_SYMBOL", - "vmlinux.lds.h needs VMLINUX_SYMBOL() around C-visible symbols\n" . $herecurr); +# do {} while (0) macro tests: +# single-statement macros do not need to be enclosed in do while (0) loop, +# macro should not end with a semicolon + if ($perl_version_ok && + $realfile !~ m@/vmlinux.lds.h$@ && + $line =~ /^.\s*\#\s*define\s+$Ident(\()?/) { + my $ln = $linenr; + my $cnt = $realcnt; + my ($off, $dstat, $dcond, $rest); + my $ctx = ''; + ($dstat, $dcond, $ln, $cnt, $off) = + ctx_statement_block($linenr, $realcnt, 0); + $ctx = $dstat; + + $dstat =~ s/\\\n.//g; + $dstat =~ s/$;/ /g; + + if ($dstat =~ /^\+\s*#\s*define\s+$Ident\s*${balanced_parens}\s*do\s*{(.*)\s*}\s*while\s*\(\s*0\s*\)\s*([;\s]*)\s*$/) { + my $stmts = $2; + my $semis = $3; + + $ctx =~ s/\n*$//; + my $cnt = statement_rawlines($ctx); + my $herectx = get_stat_here($linenr, $cnt, $here); + + if (($stmts =~ tr/;/;/) == 1 && + $stmts !~ /^\s*(if|while|for|switch)\b/) { + WARN("SINGLE_STATEMENT_DO_WHILE_MACRO", + "Single statement macros should not use a do {} while (0) loop\n" . "$herectx"); + } + if (defined $semis && $semis ne "") { + WARN("DO_WHILE_MACRO_WITH_TRAILING_SEMICOLON", + "do {} while (0) macros should not be semicolon terminated\n" . "$herectx"); + } + } elsif ($dstat =~ /^\+\s*#\s*define\s+$Ident.*;\s*$/) { + $ctx =~ s/\n*$//; + my $cnt = statement_rawlines($ctx); + my $herectx = get_stat_here($linenr, $cnt, $here); + + WARN("TRAILING_SEMICOLON", + "macros should not use a trailing semicolon\n" . "$herectx"); + } } # check for redundant bracing round if etc @@ -3051,55 +5495,343 @@ sub process { } } if ($level == 0 && $block =~ /^\s*\{/ && !$allowed) { - my $herectx = $here . "\n"; my $cnt = statement_rawlines($block); - - for (my $n = 0; $n < $cnt; $n++) { - $herectx .= raw_line($linenr, $n) . "\n"; - } + my $herectx = get_stat_here($linenr, $cnt, $here); WARN("BRACES", "braces {} are not necessary for single statement blocks\n" . $herectx); } } +# check for single line unbalanced braces + if ($sline =~ /^.\s*\}\s*else\s*$/ || + $sline =~ /^.\s*else\s*\{\s*$/) { + CHK("BRACES", "Unbalanced braces around else statement\n" . $herecurr); + } + +# check for unnecessary blank lines around braces + if (($line =~ /^.\s*}\s*$/ && $prevrawline =~ /^.\s*$/)) { + if (CHK("BRACES", + "Blank lines aren't necessary before a close brace '}'\n" . $hereprev) && + $fix && $prevrawline =~ /^\+/) { + fix_delete_line($fixlinenr - 1, $prevrawline); + } + } + if (($rawline =~ /^.\s*$/ && $prevline =~ /^..*{\s*$/)) { + if (CHK("BRACES", + "Blank lines aren't necessary after an open brace '{'\n" . $hereprev) && + $fix) { + fix_delete_line($fixlinenr, $rawline); + } + } + # no volatiles please my $asm_volatile = qr{\b(__asm__|asm)\s+(__volatile__|volatile)\b}; if ($line =~ /\bvolatile\b/ && $line !~ /$asm_volatile/) { WARN("VOLATILE", - "Use of volatile is usually wrong: see Documentation/volatile-considered-harmful.txt\n" . $herecurr); + "Use of volatile is usually wrong: see Documentation/process/volatile-considered-harmful.rst\n" . $herecurr); + } + +# Check for user-visible strings broken across lines, which breaks the ability +# to grep for the string. Make exceptions when the previous string ends in a +# newline (multiple lines in one string constant) or '\t', '\r', ';', or '{' +# (common in inline assembly) or is a octal \123 or hexadecimal \xaf value + if ($line =~ /^\+\s*$String/ && + $prevline =~ /"\s*$/ && + $prevrawline !~ /(?:\\(?:[ntr]|[0-7]{1,3}|x[0-9a-fA-F]{1,2})|;\s*|\{\s*)"\s*$/) { + if (WARN("SPLIT_STRING", + "quoted string split across lines\n" . $hereprev) && + $fix && + $prevrawline =~ /^\+.*"\s*$/ && + $last_coalesced_string_linenr != $linenr - 1) { + my $extracted_string = get_quoted_string($line, $rawline); + my $comma_close = ""; + if ($rawline =~ /\Q$extracted_string\E(\s*\)\s*;\s*$|\s*,\s*)/) { + $comma_close = $1; + } + + fix_delete_line($fixlinenr - 1, $prevrawline); + fix_delete_line($fixlinenr, $rawline); + my $fixedline = $prevrawline; + $fixedline =~ s/"\s*$//; + $fixedline .= substr($extracted_string, 1) . trim($comma_close); + fix_insert_line($fixlinenr - 1, $fixedline); + $fixedline = $rawline; + $fixedline =~ s/\Q$extracted_string\E\Q$comma_close\E//; + if ($fixedline !~ /\+\s*$/) { + fix_insert_line($fixlinenr, $fixedline); + } + $last_coalesced_string_linenr = $linenr; + } + } + +# check for missing a space in a string concatenation + if ($prevrawline =~ /[^\\]\w"$/ && $rawline =~ /^\+[\t ]+"\w/) { + WARN('MISSING_SPACE', + "break quoted strings at a space character\n" . $hereprev); + } + +# check for an embedded function name in a string when the function is known +# This does not work very well for -f --file checking as it depends on patch +# context providing the function name or a single line form for in-file +# function declarations + if ($line =~ /^\+.*$String/ && + defined($context_function) && + get_quoted_string($line, $rawline) =~ /\b$context_function\b/ && + length(get_quoted_string($line, $rawline)) != (length($context_function) + 2)) { + WARN("EMBEDDED_FUNCTION_NAME", + "Prefer using '\"%s...\", __func__' to using '$context_function', this function's name, in a string\n" . $herecurr); + } + +# check for spaces before a quoted newline + if ($rawline =~ /^.*\".*\s\\n/) { + if (WARN("QUOTED_WHITESPACE_BEFORE_NEWLINE", + "unnecessary whitespace before a quoted newline\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/^(\+.*\".*)\s+\\n/$1\\n/; + } + + } + +# concatenated string without spaces between elements + if ($line =~ /$String[A-Za-z0-9_]/ || $line =~ /[A-Za-z0-9_]$String/) { + if (CHK("CONCATENATED_STRING", + "Concatenated strings should use spaces between elements\n" . $herecurr) && + $fix) { + while ($line =~ /($String)/g) { + my $extracted_string = substr($rawline, $-[0], $+[0] - $-[0]); + $fixed[$fixlinenr] =~ s/\Q$extracted_string\E([A-Za-z0-9_])/$extracted_string $1/; + $fixed[$fixlinenr] =~ s/([A-Za-z0-9_])\Q$extracted_string\E/$1 $extracted_string/; + } + } + } + +# uncoalesced string fragments + if ($line =~ /$String\s*"/) { + if (WARN("STRING_FRAGMENTS", + "Consecutive strings are generally better as a single string\n" . $herecurr) && + $fix) { + while ($line =~ /($String)(?=\s*")/g) { + my $extracted_string = substr($rawline, $-[0], $+[0] - $-[0]); + $fixed[$fixlinenr] =~ s/\Q$extracted_string\E\s*"/substr($extracted_string, 0, -1)/e; + } + } + } + +# check for non-standard and hex prefixed decimal printf formats + my $show_L = 1; #don't show the same defect twice + my $show_Z = 1; + while ($line =~ /(?:^|")([X\t]*)(?:"|$)/g) { + my $string = substr($rawline, $-[1], $+[1] - $-[1]); + $string =~ s/%%/__/g; + # check for %L + if ($show_L && $string =~ /%[\*\d\.\$]*L([diouxX])/) { + WARN("PRINTF_L", + "\%L$1 is non-standard C, use %ll$1\n" . $herecurr); + $show_L = 0; + } + # check for %Z + if ($show_Z && $string =~ /%[\*\d\.\$]*Z([diouxX])/) { + WARN("PRINTF_Z", + "%Z$1 is non-standard C, use %z$1\n" . $herecurr); + $show_Z = 0; + } + # check for 0x<decimal> + if ($string =~ /0x%[\*\d\.\$\Llzth]*[diou]/) { + ERROR("PRINTF_0XDECIMAL", + "Prefixing 0x with decimal output is defective\n" . $herecurr); + } + } + +# check for line continuations in quoted strings with odd counts of " + if ($rawline =~ /\\$/ && $sline =~ tr/"/"/ % 2) { + WARN("LINE_CONTINUATIONS", + "Avoid line continuations in quoted strings\n" . $herecurr); } # warn about #if 0 if ($line =~ /^.\s*\#\s*if\s+0\b/) { - CHK("REDUNDANT_CODE", - "if this code is redundant consider removing it\n" . - $herecurr); + WARN("IF_0", + "Consider removing the code enclosed by this #if 0 and its #endif\n" . $herecurr); + } + +# warn about #if 1 + if ($line =~ /^.\s*\#\s*if\s+1\b/) { + WARN("IF_1", + "Consider removing the #if 1 and its #endif\n" . $herecurr); + } + +# check for needless "if (<foo>) fn(<foo>)" uses + if ($prevline =~ /\bif\s*\(\s*($Lval)\s*\)/) { + my $tested = quotemeta($1); + my $expr = '\s*\(\s*' . $tested . '\s*\)\s*;'; + if ($line =~ /\b(kfree|usb_free_urb|debugfs_remove(?:_recursive)?|(?:kmem_cache|mempool|dma_pool)_destroy)$expr/) { + my $func = $1; + if (WARN('NEEDLESS_IF', + "$func(NULL) is safe and this check is probably not required\n" . $hereprev) && + $fix) { + my $do_fix = 1; + my $leading_tabs = ""; + my $new_leading_tabs = ""; + if ($lines[$linenr - 2] =~ /^\+(\t*)if\s*\(\s*$tested\s*\)\s*$/) { + $leading_tabs = $1; + } else { + $do_fix = 0; + } + if ($lines[$linenr - 1] =~ /^\+(\t+)$func\s*\(\s*$tested\s*\)\s*;\s*$/) { + $new_leading_tabs = $1; + if (length($leading_tabs) + 1 ne length($new_leading_tabs)) { + $do_fix = 0; + } + } else { + $do_fix = 0; + } + if ($do_fix) { + fix_delete_line($fixlinenr - 1, $prevrawline); + $fixed[$fixlinenr] =~ s/^\+$new_leading_tabs/\+$leading_tabs/; + } + } + } + } + +# check for unnecessary "Out of Memory" messages + if ($line =~ /^\+.*\b$logFunctions\s*\(/ && + $prevline =~ /^[ \+]\s*if\s*\(\s*(\!\s*|NULL\s*==\s*)?($Lval)(\s*==\s*NULL\s*)?\s*\)/ && + (defined $1 || defined $3) && + $linenr > 3) { + my $testval = $2; + my $testline = $lines[$linenr - 3]; + + my ($s, $c) = ctx_statement_block($linenr - 3, $realcnt, 0); +# print("line: <$line>\nprevline: <$prevline>\ns: <$s>\nc: <$c>\n\n\n"); + + if ($s =~ /(?:^|\n)[ \+]\s*(?:$Type\s*)?\Q$testval\E\s*=\s*(?:\([^\)]*\)\s*)?\s*$allocFunctions\s*\(/ && + $s !~ /\b__GFP_NOWARN\b/ ) { + WARN("OOM_MESSAGE", + "Possible unnecessary 'out of memory' message\n" . $hereprev); + } + } + +# check for logging functions with KERN_<LEVEL> + if ($line !~ /printk(?:_ratelimited|_once)?\s*\(/ && + $line =~ /\b$logFunctions\s*\(.*\b(KERN_[A-Z]+)\b/) { + my $level = $1; + if (WARN("UNNECESSARY_KERN_LEVEL", + "Possible unnecessary $level\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\s*$level\s*//; + } } -# check for needless kfree() checks - if ($prevline =~ /\bif\s*\(([^\)]*)\)/) { - my $expr = $1; - if ($line =~ /\bkfree\(\Q$expr\E\);/) { - WARN("NEEDLESS_KFREE", - "kfree(NULL) is safe this check is probably not required\n" . $hereprev); +# check for logging continuations + if ($line =~ /\bprintk\s*\(\s*KERN_CONT\b|\bpr_cont\s*\(/) { + WARN("LOGGING_CONTINUATION", + "Avoid logging continuation uses where feasible\n" . $herecurr); + } + +# check for mask then right shift without a parentheses + if ($perl_version_ok && + $line =~ /$LvalOrFunc\s*\&\s*($LvalOrFunc)\s*>>/ && + $4 !~ /^\&/) { # $LvalOrFunc may be &foo, ignore if so + WARN("MASK_THEN_SHIFT", + "Possible precedence defect with mask then right shift - may need parentheses\n" . $herecurr); + } + +# check for pointer comparisons to NULL + if ($perl_version_ok) { + while ($line =~ /\b$LvalOrFunc\s*(==|\!=)\s*NULL\b/g) { + my $val = $1; + my $equal = "!"; + $equal = "" if ($4 eq "!="); + if (CHK("COMPARISON_TO_NULL", + "Comparison to NULL could be written \"${equal}${val}\"\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\b\Q$val\E\s*(?:==|\!=)\s*NULL\b/$equal$val/; + } + } + } + +# check for bad placement of section $InitAttribute (e.g.: __initdata) + if ($line =~ /(\b$InitAttribute\b)/) { + my $attr = $1; + if ($line =~ /^\+\s*static\s+(?:const\s+)?(?:$attr\s+)?($NonptrTypeWithAttr)\s+(?:$attr\s+)?($Ident(?:\[[^]]*\])?)\s*[=;]/) { + my $ptr = $1; + my $var = $2; + if ((($ptr =~ /\b(union|struct)\s+$attr\b/ && + ERROR("MISPLACED_INIT", + "$attr should be placed after $var\n" . $herecurr)) || + ($ptr !~ /\b(union|struct)\s+$attr\b/ && + WARN("MISPLACED_INIT", + "$attr should be placed after $var\n" . $herecurr))) && + $fix) { + $fixed[$fixlinenr] =~ s/(\bstatic\s+(?:const\s+)?)(?:$attr\s+)?($NonptrTypeWithAttr)\s+(?:$attr\s+)?($Ident(?:\[[^]]*\])?)\s*([=;])\s*/"$1" . trim(string_find_replace($2, "\\s*$attr\\s*", " ")) . " " . trim(string_find_replace($3, "\\s*$attr\\s*", "")) . " $attr" . ("$4" eq ";" ? ";" : " = ")/e; + } + } + } + +# check for $InitAttributeData (ie: __initdata) with const + if ($line =~ /\bconst\b/ && $line =~ /($InitAttributeData)/) { + my $attr = $1; + $attr =~ /($InitAttributePrefix)(.*)/; + my $attr_prefix = $1; + my $attr_type = $2; + if (ERROR("INIT_ATTRIBUTE", + "Use of const init definition must use ${attr_prefix}initconst\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ + s/$InitAttributeData/${attr_prefix}initconst/; + } + } + +# check for $InitAttributeConst (ie: __initconst) without const + if ($line !~ /\bconst\b/ && $line =~ /($InitAttributeConst)/) { + my $attr = $1; + if (ERROR("INIT_ATTRIBUTE", + "Use of $attr requires a separate use of const\n" . $herecurr) && + $fix) { + my $lead = $fixed[$fixlinenr] =~ + /(^\+\s*(?:static\s+))/; + $lead = rtrim($1); + $lead = "$lead " if ($lead !~ /^\+$/); + $lead = "${lead}const "; + $fixed[$fixlinenr] =~ s/(^\+\s*(?:static\s+))/$lead/; + } + } + +# check for __read_mostly with const non-pointer (should just be const) + if ($line =~ /\b__read_mostly\b/ && + $line =~ /($Type)\s*$Ident/ && $1 !~ /\*\s*$/ && $1 =~ /\bconst\b/) { + if (ERROR("CONST_READ_MOSTLY", + "Invalid use of __read_mostly with const type\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\s+__read_mostly\b//; } } -# check for needless usb_free_urb() checks - if ($prevline =~ /\bif\s*\(([^\)]*)\)/) { - my $expr = $1; - if ($line =~ /\busb_free_urb\(\Q$expr\E\);/) { - WARN("NEEDLESS_USB_FREE_URB", - "usb_free_urb(NULL) is safe this check is probably not required\n" . $hereprev); + +# don't use __constant_<foo> functions outside of include/uapi/ + if ($realfile !~ m@^include/uapi/@ && + $line =~ /(__constant_(?:htons|ntohs|[bl]e(?:16|32|64)_to_cpu|cpu_to_[bl]e(?:16|32|64)))\s*\(/) { + my $constant_func = $1; + my $func = $constant_func; + $func =~ s/^__constant_//; + if (WARN("CONSTANT_CONVERSION", + "$constant_func should be $func\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\b$constant_func\b/$func/g; } } # prefer usleep_range over udelay - if ($line =~ /\budelay\s*\(\s*(\w+)\s*\)/) { + if ($line =~ /\budelay\s*\(\s*(\d+)\s*\)/) { + my $delay = $1; # ignore udelay's < 10, however - if (! (($1 =~ /(\d+)/) && ($1 < 10)) ) { + if (! ($delay < 10) ) { CHK("USLEEP_RANGE", - "usleep_range is preferred over udelay; see Documentation/timers/timers-howto.txt\n" . $line); + "usleep_range is preferred over udelay; see Documentation/timers/timers-howto.rst\n" . $herecurr); + } + if ($delay > 2000) { + WARN("LONG_UDELAY", + "long udelay - prefer mdelay; see arch/arm/include/asm/delay.h\n" . $herecurr); } } @@ -3107,10 +5839,22 @@ sub process { if ($line =~ /\bmsleep\s*\((\d+)\);/) { if ($1 < 20) { WARN("MSLEEP", - "msleep < 20ms can sleep for up to 20ms; see Documentation/timers/timers-howto.txt\n" . $line); + "msleep < 20ms can sleep for up to 20ms; see Documentation/timers/timers-howto.rst\n" . $herecurr); } } +# check for comparisons of jiffies + if ($line =~ /\bjiffies\s*$Compare|$Compare\s*jiffies\b/) { + WARN("JIFFIES_COMPARISON", + "Comparing jiffies is almost always wrong; prefer time_after, time_before and friends\n" . $herecurr); + } + +# check for comparisons of get_jiffies_64() + if ($line =~ /\bget_jiffies_64\s*\(\s*\)\s*$Compare|$Compare\s*get_jiffies_64\s*\(\s*\)/) { + WARN("JIFFIES_COMPARISON", + "Comparing get_jiffies_64() is almost always wrong; prefer time_after64, time_before64 and friends\n" . $herecurr); + } + # warn about #ifdefs in C files # if ($line =~ /^.\s*\#\s*if(|n)def/ && ($realfile =~ /\.c$/)) { # print "#ifdef in C files should be avoided\n"; @@ -3120,8 +5864,13 @@ sub process { # warn about spacing in #ifdefs if ($line =~ /^.\s*\#\s*(ifdef|ifndef|elif)\s\s+/) { - ERROR("SPACING", - "exactly one space required after that #$1\n" . $herecurr); + if (ERROR("SPACING", + "exactly one space required after that #$1\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ + s/^(.\s*\#\s*(ifdef|ifndef|elif))\s{2,}/$1 /; + } + } # check for spinlock_t definitions without a comment. @@ -3134,22 +5883,84 @@ sub process { } } # check for memory barriers without a comment. - if ($line =~ /\b(mb|rmb|wmb|read_barrier_depends|smp_mb|smp_rmb|smp_wmb|smp_read_barrier_depends)\(/) { + + my $barriers = qr{ + mb| + rmb| + wmb| + read_barrier_depends + }x; + my $barrier_stems = qr{ + mb__before_atomic| + mb__after_atomic| + store_release| + load_acquire| + store_mb| + (?:$barriers) + }x; + my $all_barriers = qr{ + (?:$barriers)| + smp_(?:$barrier_stems)| + virt_(?:$barrier_stems) + }x; + + if ($line =~ /\b(?:$all_barriers)\s*\(/) { if (!ctx_has_comment($first_line, $linenr)) { - CHK("MEMORY_BARRIER", - "memory barrier without comment\n" . $herecurr); + WARN("MEMORY_BARRIER", + "memory barrier without comment\n" . $herecurr); } } + + my $underscore_smp_barriers = qr{__smp_(?:$barrier_stems)}x; + + if ($realfile !~ m@^include/asm-generic/@ && + $realfile !~ m@/barrier\.h$@ && + $line =~ m/\b(?:$underscore_smp_barriers)\s*\(/ && + $line !~ m/^.\s*\#\s*define\s+(?:$underscore_smp_barriers)\s*\(/) { + WARN("MEMORY_BARRIER", + "__smp memory barriers shouldn't be used outside barrier.h and asm-generic\n" . $herecurr); + } + +# check for waitqueue_active without a comment. + if ($line =~ /\bwaitqueue_active\s*\(/) { + if (!ctx_has_comment($first_line, $linenr)) { + WARN("WAITQUEUE_ACTIVE", + "waitqueue_active without comment\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" . $herecurr); + } + } + +# check for smp_read_barrier_depends and read_barrier_depends + if (!$file && $line =~ /\b(smp_|)read_barrier_depends\s*\(/) { + WARN("READ_BARRIER_DEPENDS", + "$1read_barrier_depends should only be used in READ_ONCE or DEC Alpha code\n" . $herecurr); + } + # check of hardware specific defines if ($line =~ m@^.\s*\#\s*if.*\b(__i386__|__powerpc64__|__sun__|__s390x__)\b@ && $realfile !~ m@include/asm-@) { CHK("ARCH_DEFINES", "architecture specific defines should be avoided\n" . $herecurr); } +# check that the storage class is not after a type + if ($line =~ /\b($Type)\s+($Storage)\b/) { + WARN("STORAGE_CLASS", + "storage class '$2' should be located before type '$1'\n" . $herecurr); + } # Check that the storage class is at the beginning of a declaration - if ($line =~ /\b$Storage\b/ && $line !~ /^.\s*$Storage\b/) { + if ($line =~ /\b$Storage\b/ && + $line !~ /^.\s*$Storage/ && + $line =~ /^.\s*(.+?)\$Storage\s/ && + $1 !~ /[\,\)]\s*$/) { WARN("STORAGE_CLASS", - "storage class should be at the beginning of the declaration\n" . $herecurr) + "storage class should be at the beginning of the declaration\n" . $herecurr); } # check the location of the inline attribute, that it is between @@ -3161,33 +5972,109 @@ sub process { } # Check for __inline__ and __inline, prefer inline - if ($line =~ /\b(__inline__|__inline)\b/) { - WARN("INLINE", - "plain inline is preferred over $1\n" . $herecurr); + if ($realfile !~ m@\binclude/uapi/@ && + $line =~ /\b(__inline__|__inline)\b/) { + if (WARN("INLINE", + "plain inline is preferred over $1\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\b(__inline__|__inline)\b/inline/; + + } } # Check for __attribute__ packed, prefer __packed - if ($line =~ /\b__attribute__\s*\(\s*\(.*\bpacked\b/) { + if ($realfile !~ m@\binclude/uapi/@ && + $line =~ /\b__attribute__\s*\(\s*\(.*\bpacked\b/) { WARN("PREFER_PACKED", "__packed is preferred over __attribute__((packed))\n" . $herecurr); } # Check for __attribute__ aligned, prefer __aligned - if ($line =~ /\b__attribute__\s*\(\s*\(.*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($new)/; + } + } + # Check for __attribute__ format(printf, prefer __printf - if ($line =~ /\b__attribute__\s*\(\s*\(\s*format\s*\(\s*printf/) { - WARN("PREFER_PRINTF", - "__printf(string-index, first-to-check) is preferred over __attribute__((format(printf, string-index, first-to-check)))\n" . $herecurr); + if ($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($1) . ")"/ex; + + } } # Check for __attribute__ format(scanf, prefer __scanf - if ($line =~ /\b__attribute__\s*\(\s*\(\s*format\s*\(\s*scanf\b/) { - WARN("PREFER_SCANF", - "__scanf(string-index, first-to-check) is preferred over __attribute__((format(scanf, string-index, first-to-check)))\n" . $herecurr); + if ($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($1) . ")"/ex; + } + } + +# Check for __attribute__ weak, or __weak declarations (may have link issues) + if ($perl_version_ok && + $line =~ /(?:$Declare|$DeclareMisordered)\s*$Ident\s*$balanced_parens\s*(?:$Attribute)?\s*;/ && + ($line =~ /\b__attribute__\s*\(\s*\(.*\bweak\b/ || + $line =~ /\b__weak\b/)) { + ERROR("WEAK_DECLARATION", + "Using weak declarations can have unintended link defects\n" . $herecurr); + } + +# check for c99 types like uint8_t used outside of uapi/ and tools/ + if ($realfile !~ m@\binclude/uapi/@ && + $realfile !~ m@\btools/@ && + $line =~ /\b($Declare)\s*$Ident\s*[=;,\[]/) { + my $type = $1; + if ($type =~ /\b($typeC99Typedefs)\b/) { + $type = $1; + my $kernel_type = 'u'; + $kernel_type = 's' if ($type =~ /^_*[si]/); + $type =~ /(\d+)/; + $kernel_type .= $1; + if (CHK("PREFER_KERNEL_TYPES", + "Prefer kernel type '$kernel_type' over '$type'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\b$type\b/$kernel_type/; + } + } + } + +# check for cast of C90 native int or longer types constants + if ($line =~ /(\(\s*$C90_int_types\s*\)\s*)($Constant)\b/) { + my $cast = $1; + my $const = $2; + if (WARN("TYPECAST_INT_CONSTANT", + "Unnecessary typecast of c90 int constant\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/; + } } # check for sizeof(&) @@ -3196,16 +6083,88 @@ sub process { "sizeof(& should be avoided\n" . $herecurr); } -# check for line continuations in quoted strings with odd counts of " - if ($rawline =~ /\\$/ && $rawline =~ tr/"/"/ % 2) { - WARN("LINE_CONTINUATIONS", - "Avoid line continuations in quoted strings\n" . $herecurr); +# check for sizeof without parenthesis + if ($line =~ /\bsizeof\s+((?:\*\s*|)$Lval|$Type(?:\s+$Lval|))/) { + if (WARN("SIZEOF_PARENTHESIS", + "sizeof $1 should be sizeof($1)\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bsizeof\s+((?:\*\s*|)$Lval|$Type(?:\s+$Lval|))/"sizeof(" . trim($1) . ")"/ex; + } + } + +# check for struct spinlock declarations + if ($line =~ /^.\s*\bstruct\s+spinlock\s+\w+\s*;/) { + WARN("USE_SPINLOCK_T", + "struct spinlock should be spinlock_t\n" . $herecurr); + } + +# check for seq_printf uses that could be seq_puts + if ($sline =~ /\bseq_printf\s*\(.*"\s*\)\s*;\s*$/) { + my $fmt = get_quoted_string($line, $rawline); + $fmt =~ s/%%//g; + if ($fmt !~ /%/) { + if (WARN("PREFER_SEQ_PUTS", + "Prefer seq_puts to seq_printf\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bseq_printf\b/seq_puts/; + } + } + } + +# check for vsprintf extension %p<foo> misuses + if ($perl_version_ok && + defined $stat && + $stat =~ /^\+(?![^\{]*\{\s*).*\b(\w+)\s*\(.*$String\s*,/s && + $1 !~ /^_*volatile_*$/) { + my $stat_real; + + my $lc = $stat =~ tr@\n@@; + $lc = $lc + $linenr; + for (my $count = $linenr; $count <= $lc; $count++) { + my $specifier; + my $extension; + my $qualifier; + my $bad_specifier = ""; + my $fmt = get_quoted_string($lines[$count - 1], raw_line($count, 0)); + $fmt =~ s/%%//g; + + while ($fmt =~ /(\%[\*\d\.]*p(\w)(\w*))/g) { + $specifier = $1; + $extension = $2; + $qualifier = $3; + if ($extension !~ /[SsBKRraEehMmIiUDdgVCbGNOxtf]/ || + ($extension eq "f" && + defined $qualifier && $qualifier !~ /^w/)) { + $bad_specifier = $specifier; + last; + } + if ($extension eq "x" && !defined($stat_real)) { + if (!defined($stat_real)) { + $stat_real = get_stat_real($linenr, $lc); + } + WARN("VSPRINTF_SPECIFIER_PX", + "Using vsprintf specifier '\%px' potentially exposes the kernel memory layout, if you don't really need the address please consider using '\%p'.\n" . "$here\n$stat_real\n"); + } + } + if ($bad_specifier ne "") { + my $stat_real = get_stat_real($linenr, $lc); + my $ext_type = "Invalid"; + my $use = ""; + if ($bad_specifier =~ /p[Ff]/) { + $use = " - use %pS instead"; + $use =~ s/pS/ps/ if ($bad_specifier =~ /pf/); + } + + WARN("VSPRINTF_POINTER_EXTENSION", + "$ext_type vsprintf pointer extension '$bad_specifier'$use\n" . "$here\n$stat_real\n"); + } + } } # Check for misused memsets - if ($^V && $^V ge 5.10.0 && + if ($perl_version_ok && defined $stat && - $stat =~ /^\+(?:.*?)\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*$FuncArg\s*\)/s) { + $stat =~ /^\+(?:.*?)\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*$FuncArg\s*\)/) { my $ms_addr = $2; my $ms_val = $7; @@ -3220,8 +6179,50 @@ sub process { } } +# Check for memcpy(foo, bar, ETH_ALEN) that could be ether_addr_copy(foo, bar) +# if ($perl_version_ok && +# defined $stat && +# $stat =~ /^\+(?:.*?)\bmemcpy\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/) { +# if (WARN("PREFER_ETHER_ADDR_COPY", +# "Prefer ether_addr_copy() over memcpy() if the Ethernet addresses are __aligned(2)\n" . "$here\n$stat\n") && +# $fix) { +# $fixed[$fixlinenr] =~ s/\bmemcpy\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/ether_addr_copy($2, $7)/; +# } +# } + +# Check for memcmp(foo, bar, ETH_ALEN) that could be ether_addr_equal*(foo, bar) +# if ($perl_version_ok && +# defined $stat && +# $stat =~ /^\+(?:.*?)\bmemcmp\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/) { +# WARN("PREFER_ETHER_ADDR_EQUAL", +# "Prefer ether_addr_equal() or ether_addr_equal_unaligned() over memcmp()\n" . "$here\n$stat\n") +# } + +# check for memset(foo, 0x0, ETH_ALEN) that could be eth_zero_addr +# check for memset(foo, 0xFF, ETH_ALEN) that could be eth_broadcast_addr +# if ($perl_version_ok && +# defined $stat && +# $stat =~ /^\+(?:.*?)\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/) { +# +# my $ms_val = $7; +# +# if ($ms_val =~ /^(?:0x|)0+$/i) { +# if (WARN("PREFER_ETH_ZERO_ADDR", +# "Prefer eth_zero_addr over memset()\n" . "$here\n$stat\n") && +# $fix) { +# $fixed[$fixlinenr] =~ s/\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*,\s*ETH_ALEN\s*\)/eth_zero_addr($2)/; +# } +# } elsif ($ms_val =~ /^(?:0xff|255)$/i) { +# if (WARN("PREFER_ETH_BROADCAST_ADDR", +# "Prefer eth_broadcast_addr() over memset()\n" . "$here\n$stat\n") && +# $fix) { +# $fixed[$fixlinenr] =~ s/\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*,\s*ETH_ALEN\s*\)/eth_broadcast_addr($2)/; +# } +# } +# } + # typecasts on min/max could be min_t/max_t - if ($^V && $^V ge 5.10.0 && + if ($perl_version_ok && defined $stat && $stat =~ /^\+(?:.*?)\b(min|max)\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\)/) { if (defined $2 || defined $7) { @@ -3244,6 +6245,64 @@ sub process { } } +# check usleep_range arguments + if ($perl_version_ok && + defined $stat && + $stat =~ /^\+(?:.*?)\busleep_range\s*\(\s*($FuncArg)\s*,\s*($FuncArg)\s*\)/) { + my $min = $1; + my $max = $7; + if ($min eq $max) { + WARN("USLEEP_RANGE", + "usleep_range should not use min == max args; see Documentation/timers/timers-howto.rst\n" . "$here\n$stat\n"); + } elsif ($min =~ /^\d+$/ && $max =~ /^\d+$/ && + $min > $max) { + WARN("USLEEP_RANGE", + "usleep_range args reversed, use min then max; see Documentation/timers/timers-howto.rst\n" . "$here\n$stat\n"); + } + } + +# check for naked sscanf + if ($perl_version_ok && + defined $stat && + $line =~ /\bsscanf\b/ && + ($stat !~ /$Ident\s*=\s*sscanf\s*$balanced_parens/ && + $stat !~ /\bsscanf\s*$balanced_parens\s*(?:$Compare)/ && + $stat !~ /(?:$Compare)\s*\bsscanf\s*$balanced_parens/)) { + my $lc = $stat =~ tr@\n@@; + $lc = $lc + $linenr; + my $stat_real = get_stat_real($linenr, $lc); + WARN("NAKED_SSCANF", + "unchecked sscanf return value\n" . "$here\n$stat_real\n"); + } + +# check for simple sscanf that should be kstrto<foo> + if ($perl_version_ok && + defined $stat && + $line =~ /\bsscanf\b/) { + my $lc = $stat =~ tr@\n@@; + $lc = $lc + $linenr; + my $stat_real = get_stat_real($linenr, $lc); + if ($stat_real =~ /\bsscanf\b\s*\(\s*$FuncArg\s*,\s*("[^"]+")/) { + my $format = $6; + my $count = $format =~ tr@%@%@; + if ($count == 1 && + $format =~ /^"\%(?i:ll[udxi]|[udxi]ll|ll|[hl]h?[udxi]|[udxi][hl]h?|[hl]h?|[udxi])"$/) { + WARN("SSCANF_TO_KSTRTO", + "Prefer kstrto<type> to single variable sscanf\n" . "$here\n$stat_real\n"); + } + } + } + +# check for new externs in .h files. + if ($realfile =~ /\.h$/ && + $line =~ /^\+\s*(extern\s+)$Type\s*$Ident\s*\(/s) { + if (CHK("AVOID_EXTERNS", + "extern prototypes should be avoided in .h files\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/(.*)\bextern\b\s*(.*)/$1$2/; + } + } + # check for new externs in .c files. if ($realfile =~ /\.c$/ && defined $stat && $stat =~ /^.\s*(?:extern\s+)?$Type\s+($Ident)(\s*)\(/s) @@ -3274,22 +6333,206 @@ sub process { "externs should be avoided in .c files\n" . $herecurr); } -# check for pointless casting of kmalloc return - if ($line =~ /\*\s*\)\s*[kv][czm]alloc(_node){0,1}\b/) { +# 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($2); + while ($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$/) { + WARN("FUNCTION_ARGUMENTS", + "function definition argument '$arg' should also have an identifier name\n" . $herecurr); + } + } + } + +# check for function definitions + if ($perl_version_ok && + defined $stat && + $stat =~ /^.\s*(?:$Storage\s+)?$Type\s*($Ident)\s*$balanced_parens\s*{/s) { + $context_function = $1; + +# check for multiline function definition with misplaced open brace + my $ok = 0; + my $cnt = statement_rawlines($stat); + my $herectx = $here . "\n"; + for (my $n = 0; $n < $cnt; $n++) { + my $rl = raw_line($linenr, $n); + $herectx .= $rl . "\n"; + $ok = 1 if ($rl =~ /^[ \+]\{/); + $ok = 1 if ($rl =~ /\{/ && $n == 0); + last if $rl =~ /^[ \+].*\{/; + } + if (!$ok) { + ERROR("OPEN_BRACE", + "open brace '{' following function definitions go on the next line\n" . $herectx); + } + } + +# check for pointless casting of alloc functions + if ($line =~ /\*\s*\)\s*$allocFunctions\b/) { WARN("UNNECESSARY_CASTS", "unnecessary cast may hide bugs, see http://c-faq.com/malloc/mallocnocast.html\n" . $herecurr); } +# alloc style +# p = alloc(sizeof(struct foo), ...) should be p = alloc(sizeof(*p), ...) + if ($perl_version_ok && + $line =~ /\b($Lval)\s*\=\s*(?:$balanced_parens)?\s*((?:kv|k|v)[mz]alloc(?:_node)?)\s*\(\s*(sizeof\s*\(\s*struct\s+$Lval\s*\))/) { + CHK("ALLOC_SIZEOF_STRUCT", + "Prefer $3(sizeof(*$1)...) over $3($4...)\n" . $herecurr); + } + +# check for k[mz]alloc with multiplies that could be kmalloc_array/kcalloc + if ($perl_version_ok && + defined $stat && + $stat =~ /^\+\s*($Lval)\s*\=\s*(?:$balanced_parens)?\s*(k[mz]alloc)\s*\(\s*($FuncArg)\s*\*\s*($FuncArg)\s*,/) { + my $oldfunc = $3; + my $a1 = $4; + my $a2 = $10; + my $newfunc = "kmalloc_array"; + $newfunc = "kcalloc" if ($oldfunc eq "kzalloc"); + my $r1 = $a1; + my $r2 = $a2; + if ($a1 =~ /^sizeof\s*\S/) { + $r1 = $a2; + $r2 = $a1; + } + if ($r1 !~ /^sizeof\b/ && $r2 =~ /^sizeof\s*\S/ && + !($r1 =~ /^$Constant$/ || $r1 =~ /^[A-Z_][A-Z0-9_]*$/)) { + my $cnt = statement_rawlines($stat); + my $herectx = get_stat_here($linenr, $cnt, $here); + + if (WARN("ALLOC_WITH_MULTIPLY", + "Prefer $newfunc over $oldfunc with multiply\n" . $herectx) && + $cnt == 1 && + $fix) { + $fixed[$fixlinenr] =~ s/\b($Lval)\s*\=\s*(?:$balanced_parens)?\s*(k[mz]alloc)\s*\(\s*($FuncArg)\s*\*\s*($FuncArg)/$1 . ' = ' . "$newfunc(" . trim($r1) . ', ' . trim($r2)/e; + } + } + } + +# check for krealloc arg reuse + if ($perl_version_ok && + $line =~ /\b($Lval)\s*\=\s*(?:$balanced_parens)?\s*krealloc\s*\(\s*($Lval)\s*,/ && + $1 eq $3) { + WARN("KREALLOC_ARG_REUSE", + "Reusing the krealloc arg is almost always a bug\n" . $herecurr); + } + +# check for alloc argument mismatch + if ($line =~ /\b(kcalloc|kmalloc_array)\s*\(\s*sizeof\b/) { + WARN("ALLOC_ARRAY_ARGS", + "$1 uses number as first arg, sizeof is generally wrong\n" . $herecurr); + } + # check for multiple semicolons if ($line =~ /;\s*;\s*$/) { - WARN("ONE_SEMICOLON", - "Statements terminations use 1 semicolon\n" . $herecurr); + if (WARN("ONE_SEMICOLON", + "Statements terminations use 1 semicolon\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/(\s*;\s*){2,}$/;/g; + } + } + +# check for #defines like: 1 << <digit> that could be BIT(digit), it is not exported to uapi + if ($realfile !~ m@^include/uapi/@ && + $line =~ /#\s*define\s+\w+\s+\(?\s*1\s*([ulUL]*)\s*\<\<\s*(?:\d+|$Ident)\s*\)?/) { + my $ull = ""; + $ull = "_ULL" if (defined($1) && $1 =~ /ll/i); + if (CHK("BIT_MACRO", + "Prefer using the BIT$ull macro\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\(?\s*1\s*[ulUL]*\s*<<\s*(\d+|$Ident)\s*\)?/BIT${ull}($1)/; + } + } + +# check for #if defined CONFIG_<FOO> || defined CONFIG_<FOO>_MODULE + if ($line =~ /^\+\s*#\s*if\s+defined(?:\s*\(?\s*|\s+)(CONFIG_[A-Z_]+)\s*\)?\s*\|\|\s*defined(?:\s*\(?\s*|\s+)\1_MODULE\s*\)?\s*$/) { + my $config = $1; + if (WARN("PREFER_IS_ENABLED", + "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', + '@fallthrough@', + 'lint -fallthrough[ \t]*', + 'intentional(?:ly)?[ \t]*fall(?:(?:s | |-)[Tt]|t)hr(?:ough|u|ew)', + '(?:else,?\s*)?FALL(?:S | |-)?THR(?:OUGH|U|EW)[ \t.!]*(?:-[^\n\r]*)?', + 'Fall(?:(?:s | |-)[Tt]|t)hr(?:ough|u|ew)[ \t.!]*(?:-[^\n\r]*)?', + 'fall(?:s | |-)?thr(?:ough|u|ew)[ \t.!]*(?:-[^\n\r]*)?', + ); + if ($raw_comment ne '') { + foreach my $ft (@fallthroughs) { + if ($raw_comment =~ /$ft/) { + my $msg_level = \&WARN; + $msg_level = \&CHK if ($file); + &{$msg_level}("PREFER_FALLTHROUGH", + "Prefer 'fallthrough;' over fallthrough comment\n" . $herecurr); + last; + } + } + } + +# check for switch/default statements without a break; + if ($perl_version_ok && + defined $stat && + $stat =~ /^\+[$;\s]*(?:case[$;\s]+\w+[$;\s]*:[$;\s]*|)*[$;\s]*\bdefault[$;\s]*:[$;\s]*;/g) { + my $cnt = statement_rawlines($stat); + my $herectx = get_stat_here($linenr, $cnt, $here); + + WARN("DEFAULT_NO_BREAK", + "switch default: should use break\n" . $herectx); } # check for gcc specific __FUNCTION__ - if ($line =~ /__FUNCTION__/) { - WARN("USE_FUNC", - "__func__ should be used instead of gcc specific __FUNCTION__\n" . $herecurr); + if ($line =~ /\b__FUNCTION__\b/) { + if (WARN("USE_FUNC", + "__func__ should be used instead of gcc specific __FUNCTION__\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\b__FUNCTION__\b/__func__/g; + } + } + +# check for uses of __DATE__, __TIME__, __TIMESTAMP__ + while ($line =~ /\b(__(?:DATE|TIME|TIMESTAMP)__)\b/g) { + ERROR("DATE_TIME", + "Use of the '$1' macro makes the build non-deterministic\n" . $herecurr); } # check for use of yield() @@ -3298,6 +6541,33 @@ sub process { "Using yield() is generally wrong. See yield() kernel-doc (sched/core.c)\n" . $herecurr); } +# check for comparisons against true and false + if ($line =~ /\+\s*(.*?)\b(true|false|$Lval)\s*(==|\!=)\s*(true|false|$Lval)\b(.*)$/i) { + my $lead = $1; + my $arg = $2; + my $test = $3; + my $otype = $4; + my $trail = $5; + my $op = "!"; + + ($arg, $otype) = ($otype, $arg) if ($arg =~ /^(?:true|false)$/i); + + my $type = lc($otype); + if ($type =~ /^(?:true|false)$/) { + if (("$test" eq "==" && "$type" eq "true") || + ("$test" eq "!=" && "$type" eq "false")) { + $op = ""; + } + + CHK("BOOL_COMPARISON", + "Using comparison to $otype is error prone\n" . $herecurr); + +## maybe suggesting a correct construct would better +## "Using comparison to $otype is error prone. Perhaps use '${lead}${op}${arg}${trail}'\n" . $herecurr); + + } + } + # check for semaphores initialized locked if ($line =~ /^.\s*sema_init.+,\W?0\W?\)/) { WARN("CONSIDER_COMPLETION", @@ -3310,55 +6580,32 @@ sub process { "$1 is obsolete, use k$3 instead\n" . $herecurr); } -# check for __initcall(), use device_initcall() explicitly please +# check for __initcall(), use device_initcall() explicitly or more appropriate function please if ($line =~ /^.\s*__initcall\s*\(/) { WARN("USE_DEVICE_INITCALL", - "please use device_initcall() instead of __initcall()\n" . $herecurr); - } - -# check for various ops structs, ensure they are const. - my $struct_ops = qr{acpi_dock_ops| - address_space_operations| - backlight_ops| - block_device_operations| - dentry_operations| - dev_pm_ops| - dma_map_ops| - extent_io_ops| - file_lock_operations| - file_operations| - hv_ops| - ide_dma_ops| - intel_dvo_dev_ops| - item_operations| - iwl_ops| - kgdb_arch| - kgdb_io| - kset_uevent_ops| - lock_manager_operations| - microcode_ops| - mtrr_ops| - neigh_ops| - nlmsvc_binding| - pci_raw_ops| - pipe_buf_operations| - platform_hibernation_ops| - platform_suspend_ops| - proto_ops| - rpc_pipe_ops| - seq_operations| - snd_ac97_build_ops| - soc_pcmcia_socket_ops| - stacktrace_ops| - sysfs_ops| - tty_operations| - usb_mon_operations| - wd_ops}x; + "please use device_initcall() or more appropriate function instead of __initcall() (see include/linux/init.h)\n" . $herecurr); + } + +# check for spin_is_locked(), suggest lockdep instead + if ($line =~ /\bspin_is_locked\(/) { + WARN("USE_LOCKDEP", + "Where possible, use lockdep_assert_held instead of assertions based on spin_is_locked\n" . $herecurr); + } + +# check for deprecated apis + if ($line =~ /\b($deprecated_apis_search)\b\s*\(/) { + my $deprecated_api = $1; + my $new_api = $deprecated_apis{$deprecated_api}; + WARN("DEPRECATED_API", + "Deprecated use of '$deprecated_api', prefer '$new_api' instead\n" . $herecurr); + } + +# check for various structs that are normally const (ops, kgdb, device_tree) +# and avoid what seem like struct definitions 'struct foo {' if ($line !~ /\bconst\b/ && - $line =~ /\bstruct\s+($struct_ops)\b/) { + $line =~ /\bstruct\s+($const_structs)\b(?!\s*\{)/) { WARN("CONST_STRUCT", - "struct $1 should normally be const\n" . - $herecurr); + "struct $1 should normally be const\n" . $herecurr); } # use of NR_CPUS is usually wrong @@ -3374,16 +6621,23 @@ sub process { "usage of NR_CPUS is often wrong - consider using cpu_possible(), num_possible_cpus(), for_each_possible_cpu(), etc\n" . $herecurr); } -# check for %L{u,d,i} in strings - my $string; - while ($line =~ /(?:^|")([X\t]*)(?:"|$)/g) { - $string = substr($rawline, $-[1], $+[1] - $-[1]); - $string =~ s/%%/__/g; - if ($string =~ /(?<!%)%L[udi]/) { - WARN("PRINTF_L", - "\%Ld/%Lu are not-standard C, use %lld/%llu\n" . $herecurr); - last; - } +# Use of __ARCH_HAS_<FOO> or ARCH_HAVE_<BAR> is wrong. + if ($line =~ /\+\s*#\s*define\s+((?:__)?ARCH_(?:HAS|HAVE)\w*)\b/) { + ERROR("DEFINE_ARCH_HAS", + "#define of '$1' is wrong - use Kconfig variables or standard guards instead\n" . $herecurr); + } + +# likely/unlikely comparisons similar to "(likely(foo) > 0)" + if ($perl_version_ok && + $line =~ /\b((?:un)?likely)\s*\(\s*$FuncArg\s*\)\s*$Compare/) { + WARN("LIKELY_MISUSE", + "Using $1 should generally have parentheses around the comparison\n" . $herecurr); + } + +# nested likely/unlikely calls + if ($line =~ /\b(?:(?:un)?likely)\s*\(\s*!?\s*(IS_ERR(?:_OR_NULL|_VALUE)?|WARN)/) { + WARN("LIKELY_MISUSE", + "nested (un)?likely() calls, $1 already uses unlikely() internally\n" . $herecurr); } # whine mightly about in_atomic @@ -3397,6 +6651,12 @@ sub process { } } +# check for mutex_trylock_recursive usage + if ($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*\(/ || $line =~ /__lockdep_no_validate__\s*\)/ ) { @@ -3408,11 +6668,143 @@ sub process { } } - if ($line =~ /debugfs_create_file.*S_IWUGO/ || - $line =~ /DEVICE_ATTR.*S_IWUGO/ ) { + if ($line =~ /debugfs_create_\w+.*\b$mode_perms_world_writable\b/ || + $line =~ /DEVICE_ATTR.*\b$mode_perms_world_writable\b/) { WARN("EXPORTED_WORLD_WRITABLE", "Exporting world writable files is usually an error. Consider more restrictive permissions.\n" . $herecurr); } + +# check for DEVICE_ATTR uses that could be DEVICE_ATTR_<FOO> +# and whether or not function naming is typical and if +# DEVICE_ATTR permissions uses are unusual too + if ($perl_version_ok && + defined $stat && + $stat =~ /\bDEVICE_ATTR\s*\(\s*(\w+)\s*,\s*\(?\s*(\s*(?:${multi_mode_perms_string_search}|0[0-7]{3,3})\s*)\s*\)?\s*,\s*(\w+)\s*,\s*(\w+)\s*\)/) { + my $var = $1; + my $perms = $2; + my $show = $3; + my $store = $4; + my $octal_perms = perms_to_octal($perms); + if ($show =~ /^${var}_show$/ && + $store =~ /^${var}_store$/ && + $octal_perms eq "0644") { + if (WARN("DEVICE_ATTR_RW", + "Use DEVICE_ATTR_RW\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bDEVICE_ATTR\s*\(\s*$var\s*,\s*\Q$perms\E\s*,\s*$show\s*,\s*$store\s*\)/DEVICE_ATTR_RW(${var})/; + } + } elsif ($show =~ /^${var}_show$/ && + $store =~ /^NULL$/ && + $octal_perms eq "0444") { + if (WARN("DEVICE_ATTR_RO", + "Use DEVICE_ATTR_RO\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bDEVICE_ATTR\s*\(\s*$var\s*,\s*\Q$perms\E\s*,\s*$show\s*,\s*NULL\s*\)/DEVICE_ATTR_RO(${var})/; + } + } elsif ($show =~ /^NULL$/ && + $store =~ /^${var}_store$/ && + $octal_perms eq "0200") { + if (WARN("DEVICE_ATTR_WO", + "Use DEVICE_ATTR_WO\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bDEVICE_ATTR\s*\(\s*$var\s*,\s*\Q$perms\E\s*,\s*NULL\s*,\s*$store\s*\)/DEVICE_ATTR_WO(${var})/; + } + } elsif ($octal_perms eq "0644" || + $octal_perms eq "0444" || + $octal_perms eq "0200") { + my $newshow = "$show"; + $newshow = "${var}_show" if ($show ne "NULL" && $show ne "${var}_show"); + my $newstore = $store; + $newstore = "${var}_store" if ($store ne "NULL" && $store ne "${var}_store"); + my $rename = ""; + if ($show ne $newshow) { + $rename .= " '$show' to '$newshow'"; + } + if ($store ne $newstore) { + $rename .= " '$store' to '$newstore'"; + } + WARN("DEVICE_ATTR_FUNCTIONS", + "Consider renaming function(s)$rename\n" . $herecurr); + } else { + WARN("DEVICE_ATTR_PERMS", + "DEVICE_ATTR unusual permissions '$perms' used\n" . $herecurr); + } + } + +# Mode permission misuses where it seems decimal should be octal +# This uses a shortcut match to avoid unnecessary uses of a slow foreach loop +# o Ignore module_param*(...) uses with a decimal 0 permission as that has a +# specific definition of not visible in sysfs. +# o Ignore proc_create*(...) uses with a decimal 0 permission as that means +# use the default permissions + if ($perl_version_ok && + defined $stat && + $line =~ /$mode_perms_search/) { + foreach my $entry (@mode_permission_funcs) { + my $func = $entry->[0]; + my $arg_pos = $entry->[1]; + + my $lc = $stat =~ tr@\n@@; + $lc = $lc + $linenr; + my $stat_real = get_stat_real($linenr, $lc); + + my $skip_args = ""; + if ($arg_pos > 1) { + $arg_pos--; + $skip_args = "(?:\\s*$FuncArg\\s*,\\s*){$arg_pos,$arg_pos}"; + } + my $test = "\\b$func\\s*\\(${skip_args}($FuncArg(?:\\|\\s*$FuncArg)*)\\s*[,\\)]"; + if ($stat =~ /$test/) { + my $val = $1; + $val = $6 if ($skip_args ne ""); + if (!($func =~ /^(?:module_param|proc_create)/ && $val eq "0") && + (($val =~ /^$Int$/ && $val !~ /^$Octal$/) || + ($val =~ /^$Octal$/ && length($val) ne 4))) { + ERROR("NON_OCTAL_PERMISSIONS", + "Use 4 digit octal (0777) not decimal permissions\n" . "$here\n" . $stat_real); + } + if ($val =~ /^$Octal$/ && (oct($val) & 02)) { + ERROR("EXPORTED_WORLD_WRITABLE", + "Exporting writable files is usually an error. Consider more restrictive permissions.\n" . "$here\n" . $stat_real); + } + } + } + } + +# check for uses of S_<PERMS> that could be octal for readability + while ($line =~ m{\b($multi_mode_perms_string_search)\b}g) { + my $oval = $1; + my $octal = perms_to_octal($oval); + if (WARN("SYMBOLIC_PERMS", + "Symbolic permissions '$oval' are not preferred. Consider using octal permissions '$octal'.\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$oval\E/$octal/; + } + } + +# validate content of MODULE_LICENSE against list from include/linux/module.h + if ($line =~ /\bMODULE_LICENSE\s*\(\s*($String)\s*\)/) { + my $extracted_string = get_quoted_string($line, $rawline); + my $valid_licenses = qr{ + GPL| + GPL\ v2| + GPL\ and\ additional\ rights| + Dual\ BSD/GPL| + Dual\ MIT/GPL| + Dual\ MPL/GPL| + Proprietary + }x; + if ($extracted_string !~ /^"(?:$valid_licenses)"$/x) { + WARN("MODULE_LICENSE", + "unknown module license " . $extracted_string . "\n" . $herecurr); + } + } + +# check for sysctl duplicate constants + if ($line =~ /\.extra[12]\s*=\s*&(zero|one|int_max)\b/) { + WARN("DUPLICATED_SYSCTL_CONST", + "duplicated sysctl range checking value '$1', consider using the shared one in include/linux/sysctl.h\n" . $herecurr); + } } # If we have no input at all, then there is nothing to report on @@ -3433,13 +6825,18 @@ sub process { exit(0); } - if (!$is_patch) { + if (!$is_patch && $filename !~ /cover-letter\.patch$/) { ERROR("NOT_UNIFIED_DIFF", "Does not appear to be a unified-diff format patch\n"); } - if ($is_patch && $chk_signoff && $signoff == 0) { - ERROR("MISSING_SIGN_OFF", - "Missing Signed-off-by: line(s)\n"); + if ($is_patch && $has_commit_log && $chk_signoff) { + if ($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"); + } } print report_dump(); @@ -3448,44 +6845,75 @@ sub process { print "total: $cnt_error errors, $cnt_warn warnings, " . (($check)? "$cnt_chk checks, " : "") . "$cnt_lines lines checked\n"; - print "\n" if ($quiet == 0); } if ($quiet == 0) { + # If there were any defects found and not already fixing them + if (!$clean and !$fix) { + print << "EOM" - if ($^V lt 5.10.0) { - print("NOTE: perl $^V is not modern enough to detect all possible issues.\n"); - print("An upgrade to at least perl v5.10.0 is suggested.\n\n"); +NOTE: For some of the reported defects, checkpatch may be able to + mechanically convert to the typical style using --fix or --fix-inplace. +EOM } - # If there were whitespace errors which cleanpatch can fix # then suggest that. if ($rpt_cleaners) { - print "NOTE: whitespace errors detected, you may wish to use scripts/cleanpatch or\n"; - print " scripts/cleanfile\n\n"; $rpt_cleaners = 0; + print << "EOM" + +NOTE: Whitespace errors detected. + You may wish to use scripts/cleanpatch or scripts/cleanfile +EOM } } - if ($quiet == 0 && keys %ignore_type) { - print "NOTE: Ignored message types:"; - foreach my $ignore (sort keys %ignore_type) { - print " $ignore"; - } - print "\n\n"; - } + if ($clean == 0 && $fix && + ("@rawlines" ne "@fixed" || + $#fixed_inserted >= 0 || $#fixed_deleted >= 0)) { + my $newfile = $filename; + $newfile .= ".EXPERIMENTAL-checkpatch-fixes" if (!$fix_inplace); + my $linecount = 0; + my $f; + + @fixed = fix_inserted_deleted_lines(\@fixed, \@fixed_inserted, \@fixed_deleted); + + open($f, '>', $newfile) + or die "$P: Can't open $newfile for write\n"; + foreach my $fixed_line (@fixed) { + $linecount++; + if ($file) { + if ($linecount > 3) { + $fixed_line =~ s/^\+//; + print $f $fixed_line . "\n"; + } + } else { + print $f $fixed_line . "\n"; + } + } + close($f); - if ($clean == 1 && $quiet == 0) { - print "$vname has no obvious style problems and is ready for submission.\n" - } - if ($clean == 0 && $quiet == 0) { - print << "EOM"; -$vname has style problems, please review. + if (!$quiet) { + print << "EOM"; -If any of these errors are false positives, please report -them to the maintainer, see CHECKPATCH in MAINTAINERS. +Wrote EXPERIMENTAL --fix correction(s) to '$newfile' + +Do _NOT_ trust the results written to this file. +Do _NOT_ submit these changes without inspecting them for correctness. + +This EXPERIMENTAL file is simply a convenience to help rewrite patches. +No warranties, expressed or implied... EOM + } } + if ($quiet == 0) { + print "\n"; + if ($clean == 1) { + print "$vname has no obvious style problems and is ready for submission.\n"; + } else { + print "$vname has style problems, please review.\n"; + } + } return $clean; } |