diff options
-rw-r--r-- | doc/develop/checkpatch.rst | 755 | ||||
-rw-r--r-- | doc/develop/index.rst | 1 | ||||
-rwxr-xr-x | scripts/checkpatch.pl | 1114 | ||||
-rwxr-xr-x | scripts/spdxcheck.py | 296 |
4 files changed, 1919 insertions, 247 deletions
diff --git a/doc/develop/checkpatch.rst b/doc/develop/checkpatch.rst new file mode 100644 index 0000000000..51fed1bd72 --- /dev/null +++ b/doc/develop/checkpatch.rst @@ -0,0 +1,755 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +========== +Checkpatch +========== + +Checkpatch (scripts/checkpatch.pl) is a perl script which checks for trivial +style violations in patches and optionally corrects them. Checkpatch can +also be run on file contexts and without the kernel tree. + +Checkpatch is not always right. Your judgement takes precedence over checkpatch +messages. If your code looks better with the violations, then its probably +best left alone. + + +Options +======= + +This section will describe the options checkpatch can be run with. + +Usage:: + + ./scripts/checkpatch.pl [OPTION]... [FILE]... + +Available options: + + - -q, --quiet + + Enable quiet mode. + + - -v, --verbose + Enable verbose mode. Additional verbose test descriptions are output + so as to provide information on why that particular message is shown. + + - --no-tree + + Run checkpatch without the kernel tree. + + - --no-signoff + + Disable the 'Signed-off-by' line check. The sign-off is a simple line at + the end of the explanation for the patch, which certifies that you wrote it + or otherwise have the right to pass it on as an open-source patch. + + Example:: + + Signed-off-by: Random J Developer <random@developer.example.org> + + Setting this flag effectively stops a message for a missing signed-off-by + line in a patch context. + + - --patch + + Treat FILE as a patch. This is the default option and need not be + explicitly specified. + + - --emacs + + Set output to emacs compile window format. This allows emacs users to jump + from the error in the compile window directly to the offending line in the + patch. + + - --terse + + Output only one line per report. + + - --showfile + + Show the diffed file position instead of the input file position. + + - -g, --git + + Treat FILE as a single commit or a git revision range. + + Single commit with: + + - <rev> + - <rev>^ + - <rev>~n + + Multiple commits with: + + - <rev1>..<rev2> + - <rev1>...<rev2> + - <rev>-<count> + + - -f, --file + + Treat FILE as a regular source file. This option must be used when running + checkpatch on source files in the kernel. + + - --subjective, --strict + + Enable stricter tests in checkpatch. By default the tests emitted as CHECK + do not activate by default. Use this flag to activate the CHECK tests. + + - --list-types + + Every message emitted by checkpatch has an associated TYPE. Add this flag + to display all the types in checkpatch. + + Note that when this flag is active, checkpatch does not read the input FILE, + and no message is emitted. Only a list of types in checkpatch is output. + + - --types TYPE(,TYPE2...) + + Only display messages with the given types. + + Example:: + + ./scripts/checkpatch.pl mypatch.patch --types EMAIL_SUBJECT,BRACES + + - --ignore TYPE(,TYPE2...) + + Checkpatch will not emit messages for the specified types. + + Example:: + + ./scripts/checkpatch.pl mypatch.patch --ignore EMAIL_SUBJECT,BRACES + + - --show-types + + By default checkpatch doesn't display the type associated with the messages. + Set this flag to show the message type in the output. + + - --max-line-length=n + + Set the max line length (default 100). If a line exceeds the specified + length, a LONG_LINE message is emitted. + + + The message level is different for patch and file contexts. For patches, + a WARNING is emitted. While a milder CHECK is emitted for files. So for + file contexts, the --strict flag must also be enabled. + + - --min-conf-desc-length=n + + Set the Kconfig entry minimum description length, if shorter, warn. + + - --tab-size=n + + Set the number of spaces for tab (default 8). + + - --root=PATH + + PATH to the kernel tree root. + + This option must be specified when invoking checkpatch from outside + the kernel root. + + - --no-summary + + Suppress the per file summary. + + - --mailback + + Only produce a report in case of Warnings or Errors. Milder Checks are + excluded from this. + + - --summary-file + + Include the filename in summary. + + - --debug KEY=[0|1] + + Turn on/off debugging of KEY, where KEY is one of 'values', 'possible', + 'type', and 'attr' (default is all off). + + - --fix + + This is an EXPERIMENTAL feature. If correctable errors exists, a file + <inputfile>.EXPERIMENTAL-checkpatch-fixes is created which has the + automatically fixable errors corrected. + + - --fix-inplace + + EXPERIMENTAL - Similar to --fix but input file is overwritten with fixes. + + DO NOT USE this flag unless you are absolutely sure and you have a backup + in place. + + - --ignore-perl-version + + Override checking of perl version. Runtime errors maybe encountered after + enabling this flag if the perl version does not meet the minimum specified. + + - --codespell + + Use the codespell dictionary for checking spelling errors. + + - --codespellfile + + Use the specified codespell file. + Default is '/usr/share/codespell/dictionary.txt'. + + - --typedefsfile + + Read additional types from this file. + + - --color[=WHEN] + + Use colors 'always', 'never', or only when output is a terminal ('auto'). + Default is 'auto'. + + - --kconfig-prefix=WORD + + Use WORD as a prefix for Kconfig symbols (default is `CONFIG_`). + + - -h, --help, --version + + Display the help text. + +Message Levels +============== + +Messages in checkpatch are divided into three levels. The levels of messages +in checkpatch denote the severity of the error. They are: + + - ERROR + + This is the most strict level. Messages of type ERROR must be taken + seriously as they denote things that are very likely to be wrong. + + - WARNING + + This is the next stricter level. Messages of type WARNING requires a + more careful review. But it is milder than an ERROR. + + - CHECK + + This is the mildest level. These are things which may require some thought. + +Type Descriptions +================= + +This section contains a description of all the message types in checkpatch. + +.. Types in this section are also parsed by checkpatch. +.. The types are grouped into subsections based on use. + + +Allocation style +---------------- + + **ALLOC_ARRAY_ARGS** + The first argument for kcalloc or kmalloc_array should be the + number of elements. sizeof() as the first argument is generally + wrong. + See: https://www.kernel.org/doc/html/latest/core-api/memory-allocation.html + + **ALLOC_SIZEOF_STRUCT** + The allocation style is bad. In general for family of + allocation functions using sizeof() to get memory size, + constructs like:: + + p = alloc(sizeof(struct foo), ...) + + should be:: + + p = alloc(sizeof(*p), ...) + + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#allocating-memory + + **ALLOC_WITH_MULTIPLY** + Prefer kmalloc_array/kcalloc over kmalloc/kzalloc with a + sizeof multiply. + See: https://www.kernel.org/doc/html/latest/core-api/memory-allocation.html + + +API usage +--------- + + **ARCH_DEFINES** + Architecture specific defines should be avoided wherever + possible. + + **ARCH_INCLUDE_LINUX** + Whenever asm/file.h is included and linux/file.h exists, a + conversion can be made when linux/file.h includes asm/file.h. + However this is not always the case (See signal.h). + This message type is emitted only for includes from arch/. + + **AVOID_BUG** + BUG() or BUG_ON() should be avoided totally. + Use WARN() and WARN_ON() instead, and handle the "impossible" + error condition as gracefully as possible. + See: https://www.kernel.org/doc/html/latest/process/deprecated.html#bug-and-bug-on + + **CONSIDER_KSTRTO** + The simple_strtol(), simple_strtoll(), simple_strtoul(), and + simple_strtoull() functions explicitly ignore overflows, which + may lead to unexpected results in callers. The respective kstrtol(), + kstrtoll(), kstrtoul(), and kstrtoull() functions tend to be the + correct replacements. + See: https://www.kernel.org/doc/html/latest/process/deprecated.html#simple-strtol-simple-strtoll-simple-strtoul-simple-strtoull + + **LOCKDEP** + The lockdep_no_validate class was added as a temporary measure to + prevent warnings on conversion of device->sem to device->mutex. + It should not be used for any other purpose. + See: https://lore.kernel.org/lkml/1268959062.9440.467.camel@laptop/ + + **MALFORMED_INCLUDE** + The #include statement has a malformed path. This has happened + because the author has included a double slash "//" in the pathname + accidentally. + + **USE_LOCKDEP** + lockdep_assert_held() annotations should be preferred over + assertions based on spin_is_locked() + See: https://www.kernel.org/doc/html/latest/locking/lockdep-design.html#annotations + + **UAPI_INCLUDE** + No #include statements in include/uapi should use a uapi/ path. + + +Comment style +------------- + + **BLOCK_COMMENT_STYLE** + The comment style is incorrect. The preferred style for multi- + line comments is:: + + /* + * This is the preferred style + * for multi line comments. + */ + + The networking comment style is a bit different, with the first line + not empty like the former:: + + /* This is the preferred comment style + * for files in net/ and drivers/net/ + */ + + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#commenting + + **C99_COMMENTS** + C99 style single line comments (//) should not be used. + Prefer the block comment style instead. + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#commenting + + +Commit message +-------------- + + **BAD_SIGN_OFF** + The signed-off-by line does not fall in line with the standards + specified by the community. + See: https://www.kernel.org/doc/html/latest/process/submitting-patches.html#developer-s-certificate-of-origin-1-1 + + **BAD_STABLE_ADDRESS_STYLE** + The email format for stable is incorrect. + Some valid options for stable address are:: + + 1. stable@vger.kernel.org + 2. stable@kernel.org + + For adding version info, the following comment style should be used:: + + stable@vger.kernel.org # version info + + **COMMIT_COMMENT_SYMBOL** + Commit log lines starting with a '#' are ignored by git as + comments. To solve this problem addition of a single space + infront of the log line is enough. + + **COMMIT_MESSAGE** + The patch is missing a commit description. A brief + description of the changes made by the patch should be added. + See: https://www.kernel.org/doc/html/latest/process/submitting-patches.html#describe-your-changes + + **MISSING_SIGN_OFF** + The patch is missing a Signed-off-by line. A signed-off-by + line should be added according to Developer's certificate of + Origin. + See: https://www.kernel.org/doc/html/latest/process/submitting-patches.html#sign-your-work-the-developer-s-certificate-of-origin + + **NO_AUTHOR_SIGN_OFF** + The author of the patch has not signed off the patch. It is + required that a simple sign off line should be present at the + end of explanation of the patch to denote that the author has + written it or otherwise has the rights to pass it on as an open + source patch. + See: https://www.kernel.org/doc/html/latest/process/submitting-patches.html#sign-your-work-the-developer-s-certificate-of-origin + + **DIFF_IN_COMMIT_MSG** + Avoid having diff content in commit message. + This causes problems when one tries to apply a file containing both + the changelog and the diff because patch(1) tries to apply the diff + which it found in the changelog. + See: https://lore.kernel.org/lkml/20150611134006.9df79a893e3636019ad2759e@linux-foundation.org/ + + **GERRIT_CHANGE_ID** + To be picked up by gerrit, the footer of the commit message might + have a Change-Id like:: + + Change-Id: Ic8aaa0728a43936cd4c6e1ed590e01ba8f0fbf5b + Signed-off-by: A. U. Thor <author@example.com> + + The Change-Id line must be removed before submitting. + + **GIT_COMMIT_ID** + The proper way to reference a commit id is: + commit <12+ chars of sha1> ("<title line>") + + An example may be:: + + Commit e21d2170f36602ae2708 ("video: remove unnecessary + platform_set_drvdata()") removed the unnecessary + platform_set_drvdata(), but left the variable "dev" unused, + delete it. + + See: https://www.kernel.org/doc/html/latest/process/submitting-patches.html#describe-your-changes + + +Comparison style +---------------- + + **ASSIGN_IN_IF** + Do not use assignments in if condition. + Example:: + + if ((foo = bar(...)) < BAZ) { + + should be written as:: + + foo = bar(...); + if (foo < BAZ) { + + **BOOL_COMPARISON** + Comparisons of A to true and false are better written + as A and !A. + See: https://lore.kernel.org/lkml/1365563834.27174.12.camel@joe-AO722/ + + **COMPARISON_TO_NULL** + Comparisons to NULL in the form (foo == NULL) or (foo != NULL) + are better written as (!foo) and (foo). + + **CONSTANT_COMPARISON** + Comparisons with a constant or upper case identifier on the left + side of the test should be avoided. + + +Macros, Attributes and Symbols +------------------------------ + + **ARRAY_SIZE** + The ARRAY_SIZE(foo) macro should be preferred over + sizeof(foo)/sizeof(foo[0]) for finding number of elements in an + array. + + The macro is defined in include/linux/kernel.h:: + + #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + + **AVOID_EXTERNS** + Function prototypes don't need to be declared extern in .h + files. It's assumed by the compiler and is unnecessary. + + **AVOID_L_PREFIX** + Local symbol names that are prefixed with `.L` should be avoided, + as this has special meaning for the assembler; a symbol entry will + not be emitted into the symbol table. This can prevent `objtool` + from generating correct unwind info. + + Symbols with STB_LOCAL binding may still be used, and `.L` prefixed + local symbol names are still generally usable within a function, + but `.L` prefixed local symbol names should not be used to denote + the beginning or end of code regions via + `SYM_CODE_START_LOCAL`/`SYM_CODE_END` + + **BIT_MACRO** + Defines like: 1 << <digit> could be BIT(digit). + The BIT() macro is defined in include/linux/bitops.h:: + + #define BIT(nr) (1UL << (nr)) + + **CONST_READ_MOSTLY** + When a variable is tagged with the __read_mostly annotation, it is a + signal to the compiler that accesses to the variable will be mostly + reads and rarely(but NOT never) a write. + + const __read_mostly does not make any sense as const data is already + read-only. The __read_mostly annotation thus should be removed. + + **DATE_TIME** + It is generally desirable that building the same source code with + the same set of tools is reproducible, i.e. the output is always + exactly the same. + + The kernel does *not* use the ``__DATE__`` and ``__TIME__`` macros, + and enables warnings if they are used as they can lead to + non-deterministic builds. + See: https://www.kernel.org/doc/html/latest/kbuild/reproducible-builds.html#timestamps + + **DEFINE_ARCH_HAS** + The ARCH_HAS_xyz and ARCH_HAVE_xyz patterns are wrong. + + For big conceptual features use Kconfig symbols instead. And for + smaller things where we have compatibility fallback functions but + want architectures able to override them with optimized ones, we + should either use weak functions (appropriate for some cases), or + the symbol that protects them should be the same symbol we use. + See: https://lore.kernel.org/lkml/CA+55aFycQ9XJvEOsiM3txHL5bjUc8CeKWJNR_H+MiicaddB42Q@mail.gmail.com/ + + **INIT_ATTRIBUTE** + Const init definitions should use __initconst instead of + __initdata. + + Similarly init definitions without const require a separate + use of const. + + **INLINE_LOCATION** + The inline keyword should sit between storage class and type. + + For example, the following segment:: + + inline static int example_function(void) + { + ... + } + + should be:: + + static inline int example_function(void) + { + ... + } + + **MULTISTATEMENT_MACRO_USE_DO_WHILE** + Macros with multiple statements should be enclosed in a + do - while block. Same should also be the case for macros + starting with `if` to avoid logic defects:: + + #define macrofun(a, b, c) \ + do { \ + if (a == 5) \ + do_this(b, c); \ + } while (0) + + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#macros-enums-and-rtl + + **WEAK_DECLARATION** + Using weak declarations like __attribute__((weak)) or __weak + can have unintended link defects. Avoid using them. + + +Functions and Variables +----------------------- + + **CAMELCASE** + Avoid CamelCase Identifiers. + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#naming + + **FUNCTION_WITHOUT_ARGS** + Function declarations without arguments like:: + + int foo() + + should be:: + + int foo(void) + + **GLOBAL_INITIALISERS** + Global variables should not be initialized explicitly to + 0 (or NULL, false, etc.). Your compiler (or rather your + loader, which is responsible for zeroing out the relevant + sections) automatically does it for you. + + **INITIALISED_STATIC** + Static variables should not be initialized explicitly to zero. + Your compiler (or rather your loader) automatically does + it for you. + + **RETURN_PARENTHESES** + return is not a function and as such doesn't need parentheses:: + + return (bar); + + can simply be:: + + return bar; + + +Spacing and Brackets +-------------------- + + **ASSIGNMENT_CONTINUATIONS** + Assignment operators should not be written at the start of a + line but should follow the operand at the previous line. + + **BRACES** + The placement of braces is stylistically incorrect. + The preferred way is to put the opening brace last on the line, + and put the closing brace first:: + + if (x is true) { + we do y + } + + This applies for all non-functional blocks. + However, there is one special case, namely functions: they have the + opening brace at the beginning of the next line, thus:: + + int function(int x) + { + body of function + } + + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#placing-braces-and-spaces + + **BRACKET_SPACE** + Whitespace before opening bracket '[' is prohibited. + There are some exceptions: + + 1. With a type on the left:: + + ;int [] a; + + 2. At the beginning of a line for slice initialisers:: + + [0...10] = 5, + + 3. Inside a curly brace:: + + = { [0...10] = 5 } + + **CODE_INDENT** + Code indent should use tabs instead of spaces. + Outside of comments, documentation and Kconfig, + spaces are never used for indentation. + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#indentation + + **CONCATENATED_STRING** + Concatenated elements should have a space in between. + Example:: + + printk(KERN_INFO"bar"); + + should be:: + + printk(KERN_INFO "bar"); + + **ELSE_AFTER_BRACE** + `else {` should follow the closing block `}` on the same line. + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#placing-braces-and-spaces + + **LINE_SPACING** + Vertical space is wasted given the limited number of lines an + editor window can display when multiple blank lines are used. + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#spaces + + **OPEN_BRACE** + The opening brace should be following the function definitions on the + next line. For any non-functional block it should be on the same line + as the last construct. + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#placing-braces-and-spaces + + **POINTER_LOCATION** + When using pointer data or a function that returns a pointer type, + the preferred use of * is adjacent to the data name or function name + and not adjacent to the type name. + Examples:: + + char *linux_banner; + unsigned long long memparse(char *ptr, char **retptr); + char *match_strdup(substring_t *s); + + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#spaces + + **SPACING** + Whitespace style used in the kernel sources is described in kernel docs. + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#spaces + + **SWITCH_CASE_INDENT_LEVEL** + switch should be at the same indent as case. + Example:: + + switch (suffix) { + case 'G': + case 'g': + mem <<= 30; + break; + case 'M': + case 'm': + mem <<= 20; + break; + case 'K': + case 'k': + mem <<= 10; + /* fall through */ + default: + break; + } + + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#indentation + + **TRAILING_WHITESPACE** + Trailing whitespace should always be removed. + Some editors highlight the trailing whitespace and cause visual + distractions when editing files. + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#spaces + + **WHILE_AFTER_BRACE** + while should follow the closing bracket on the same line:: + + do { + ... + } while(something); + + See: https://www.kernel.org/doc/html/latest/process/coding-style.html#placing-braces-and-spaces + + +Others +------ + + **CONFIG_DESCRIPTION** + Kconfig symbols should have a help text which fully describes + it. + + **CORRUPTED_PATCH** + The patch seems to be corrupted or lines are wrapped. + Please regenerate the patch file before sending it to the maintainer. + + **DOS_LINE_ENDINGS** + For DOS-formatted patches, there are extra ^M symbols at the end of + the line. These should be removed. + + **EXECUTE_PERMISSIONS** + There is no reason for source files to be executable. The executable + bit can be removed safely. + + **NON_OCTAL_PERMISSIONS** + Permission bits should use 4 digit octal permissions (like 0700 or 0444). + Avoid using any other base like decimal. + + **NOT_UNIFIED_DIFF** + The patch file does not appear to be in unified-diff format. Please + regenerate the patch file before sending it to the maintainer. + + **PRINTF_0XDECIMAL** + Prefixing 0x with decimal output is defective and should be corrected. + + **TRAILING_STATEMENTS** + Trailing statements (for example after any conditional) should be + on the next line. + Like:: + + if (x == y) break; + + should be:: + + if (x == y) + break; diff --git a/doc/develop/index.rst b/doc/develop/index.rst index 83c929babd..a7e625562c 100644 --- a/doc/develop/index.rst +++ b/doc/develop/index.rst @@ -54,5 +54,6 @@ Refactoring .. toctree:: :maxdepth: 1 + checkpatch coccinelle moveconfig diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 08a827535a..5696d3a5f3 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -23,6 +23,9 @@ my $V = '0.32'; use Getopt::Long qw(:config no_auto_abbrev); my $quiet = 0; +my $verbose = 0; +my %verbose_messages = (); +my %verbose_emitted = (); my $tree = 1; my $chk_signoff = 1; my $chk_patch = 1; @@ -43,6 +46,8 @@ my $list_types = 0; my $fix = 0; my $fix_inplace = 0; my $root; +my $gitroot = $ENV{'GIT_DIR'}; +$gitroot = ".git" if !defined($gitroot); my %debug; my %camelcase = (); my %use_type = (); @@ -59,13 +64,15 @@ 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 $u_boot = 0; +my $docsfile = "$D/../doc/develop/checkpatch.rst"; +my $typedefsfile; my $color = "auto"; my $allow_c99_comments = 1; # Can be overridden by --ignore C99_COMMENT_TOLERANCE # git output parsing needs US English output, so first set backtick child process LANGUAGE my $git_command ='export LANGUAGE=en_US.UTF-8; git'; my $tabsize = 8; +my ${CONFIG_} = "CONFIG_"; sub help { my ($exitcode) = @_; @@ -76,6 +83,7 @@ Version: $V Options: -q, --quiet quiet + -v, --verbose verbose mode --no-tree run without a kernel tree --no-signoff do not check for 'Signed-off-by' line --patch treat FILE as patchfile (default) @@ -129,6 +137,8 @@ Options: --color[=WHEN] Use colors 'always', 'never', or only when output is a terminal ('auto'). Default is 'auto'. --u-boot Run additional checks for U-Boot + --kconfig-prefix=WORD use WORD as a prefix for Kconfig symbols (default + ${CONFIG_}) -h, --help, --version display this help and exit When FILE is - read standard input. @@ -155,15 +165,51 @@ sub list_types { my $text = <$script>; close($script); - my @types = (); + my %types = (); # Also catch when type or level is passed through a variable - for ($text =~ /(?:(?:\bCHK|\bWARN|\bERROR|&\{\$msg_level})\s*\(|\$msg_type\s*=)\s*"([^"]+)"/g) { - push (@types, $_); + while ($text =~ /(?:(\bCHK|\bWARN|\bERROR|&\{\$msg_level})\s*\(|\$msg_type\s*=)\s*"([^"]+)"/g) { + if (defined($1)) { + if (exists($types{$2})) { + $types{$2} .= ",$1" if ($types{$2} ne $1); + } else { + $types{$2} = $1; + } + } else { + $types{$2} = "UNDETERMINED"; + } } - @types = sort(uniq(@types)); + print("#\tMessage type\n\n"); - foreach my $type (@types) { + if ($color) { + print(" ( Color coding: "); + print(RED . "ERROR" . RESET); + print(" | "); + print(YELLOW . "WARNING" . RESET); + print(" | "); + print(GREEN . "CHECK" . RESET); + print(" | "); + print("Multiple levels / Undetermined"); + print(" )\n\n"); + } + + foreach my $type (sort keys %types) { + my $orig_type = $type; + if ($color) { + my $level = $types{$type}; + if ($level eq "ERROR") { + $type = RED . $type . RESET; + } elsif ($level eq "WARN") { + $type = YELLOW . $type . RESET; + } elsif ($level eq "CHK") { + $type = GREEN . $type . RESET; + } + } print(++$count . "\t" . $type . "\n"); + if ($verbose && exists($verbose_messages{$orig_type})) { + my $message = $verbose_messages{$orig_type}; + $message =~ s/\n/\n\t/g; + print("\t" . $message . "\n\n"); + } } exit($exitcode); @@ -195,6 +241,46 @@ if (-f $conf) { unshift(@ARGV, @conf_args) if @conf_args; } +sub load_docs { + open(my $docs, '<', "$docsfile") + or warn "$P: Can't read the documentation file $docsfile $!\n"; + + my $type = ''; + my $desc = ''; + my $in_desc = 0; + + while (<$docs>) { + chomp; + my $line = $_; + $line =~ s/\s+$//; + + if ($line =~ /^\s*\*\*(.+)\*\*$/) { + if ($desc ne '') { + $verbose_messages{$type} = trim($desc); + } + $type = $1; + $desc = ''; + $in_desc = 1; + } elsif ($in_desc) { + if ($line =~ /^(?:\s{4,}|$)/) { + $line =~ s/^\s{4}//; + $desc .= $line; + $desc .= "\n"; + } else { + $verbose_messages{$type} = trim($desc); + $type = ''; + $desc = ''; + $in_desc = 0; + } + } + } + + if ($desc ne '') { + $verbose_messages{$type} = trim($desc); + } + close($docs); +} + # Perl's Getopt::Long allows options to take optional arguments after a space. # Prevent --color by itself from consuming other arguments foreach (@ARGV) { @@ -205,6 +291,7 @@ foreach (@ARGV) { GetOptions( 'q|quiet+' => \$quiet, + 'v|verbose!' => \$verbose, 'tree!' => \$tree, 'signoff!' => \$chk_signoff, 'patch!' => \$chk_patch, @@ -238,12 +325,29 @@ GetOptions( 'color=s' => \$color, 'no-color' => \$color, #keep old behaviors of -nocolor 'nocolor' => \$color, #keep old behaviors of -nocolor + 'kconfig-prefix=s' => \${CONFIG_}, 'h|help' => \$help, 'version' => \$help ) or help(1); help(0) if ($help); +die "$P: --git cannot be used with --file or --fix\n" if ($git && ($file || $fix)); +die "$P: --verbose cannot be used with --terse\n" if ($verbose && $terse); + +if ($color =~ /^[01]$/) { + $color = !$color; +} elsif ($color =~ /^always$/i) { + $color = 1; +} elsif ($color =~ /^never$/i) { + $color = 0; +} elsif ($color =~ /^auto$/i) { + $color = (-t STDOUT); +} else { + die "$P: Invalid color mode: $color\n"; +} + +load_docs() if ($verbose); list_types(0) if ($list_types); $fix = 1 if ($fix_inplace); @@ -263,20 +367,8 @@ if ($#ARGV < 0) { push(@ARGV, '-'); } -if ($color =~ /^[01]$/) { - $color = !$color; -} elsif ($color =~ /^always$/i) { - $color = 1; -} elsif ($color =~ /^never$/i) { - $color = 0; -} elsif ($color =~ /^auto$/i) { - $color = (-t STDOUT); -} else { - die "Invalid color mode: $color\n"; -} - # skip TAB size 1 to avoid additional checks on $tabsize - 1 -die "Invalid TAB size: $tabsize\n" if ($tabsize < 2); +die "$P: Invalid TAB size: $tabsize\n" if ($tabsize < 2); sub hash_save_array_words { my ($hashRef, $arrayRef) = @_; @@ -377,6 +469,7 @@ our $InitAttribute = qr{$InitAttributeData|$InitAttributeConst|$InitAttributeIni # We need \b after 'init' otherwise 'initconst' will cause a false positive in a check our $Attribute = qr{ const| + volatile| __percpu| __nocast| __safe| @@ -483,7 +576,7 @@ our $logFunctions = qr{(?x: our $allocFunctions = qr{(?x: (?:(?:devm_)? - (?:kv|k|v)[czm]alloc(?:_node|_array)? | + (?:kv|k|v)[czm]alloc(?:_array)?(?:_node)? | kstrdup(?:_const)? | kmemdup(?:_nul)?) | (?:\w+)?alloc_skb(?:_ip_align)? | @@ -503,6 +596,88 @@ our $signature_tags = qr{(?xi: Cc: )}; +our $tracing_logging_tags = qr{(?xi: + [=-]*> | + <[=-]* | + \[ | + \] | + start | + called | + entered | + entry | + enter | + in | + inside | + here | + begin | + exit | + end | + done | + leave | + completed | + out | + return | + [\.\!:\s]* +)}; + +sub edit_distance_min { + my (@arr) = @_; + my $len = scalar @arr; + if ((scalar @arr) < 1) { + # if underflow, return + return; + } + my $min = $arr[0]; + for my $i (0 .. ($len-1)) { + if ($arr[$i] < $min) { + $min = $arr[$i]; + } + } + return $min; +} + +sub get_edit_distance { + my ($str1, $str2) = @_; + $str1 = lc($str1); + $str2 = lc($str2); + $str1 =~ s/-//g; + $str2 =~ s/-//g; + my $len1 = length($str1); + my $len2 = length($str2); + # two dimensional array storing minimum edit distance + my @distance; + for my $i (0 .. $len1) { + for my $j (0 .. $len2) { + if ($i == 0) { + $distance[$i][$j] = $j; + } elsif ($j == 0) { + $distance[$i][$j] = $i; + } elsif (substr($str1, $i-1, 1) eq substr($str2, $j-1, 1)) { + $distance[$i][$j] = $distance[$i - 1][$j - 1]; + } else { + my $dist1 = $distance[$i][$j - 1]; #insert distance + my $dist2 = $distance[$i - 1][$j]; # remove + my $dist3 = $distance[$i - 1][$j - 1]; #replace + $distance[$i][$j] = 1 + edit_distance_min($dist1, $dist2, $dist3); + } + } + } + return $distance[$len1][$len2]; +} + +sub find_standard_signature { + my ($sign_off) = @_; + my @standard_signature_tags = ( + 'Signed-off-by:', 'Co-developed-by:', 'Acked-by:', 'Tested-by:', + 'Reviewed-by:', 'Reported-by:', 'Suggested-by:' + ); + foreach my $signature (@standard_signature_tags) { + return $signature if (get_edit_distance($sign_off, $signature) <= 2); + } + + return ""; +} + our @typeListMisordered = ( qr{char\s+(?:un)?signed}, qr{int\s+(?:(?:un)?signed\s+)?short\s}, @@ -591,6 +766,8 @@ our @mode_permission_funcs = ( ["__ATTR", 2], ); +my $word_pattern = '\b[A-Z]?[a-z]{2,}\b'; + #Create a search pattern for all these functions to speed up a loop below our $mode_perms_search = ""; foreach my $entry (@mode_permission_funcs) { @@ -759,7 +936,7 @@ sub read_words { next; } - $$wordsRef .= '|' if ($$wordsRef ne ""); + $$wordsRef .= '|' if (defined $$wordsRef); $$wordsRef .= $line; } close($file); @@ -769,16 +946,18 @@ sub read_words { return 0; } -my $const_structs = ""; -read_words(\$const_structs, $conststructsfile) - or warn "No structs that should be const will be found - file '$conststructsfile': $!\n"; +my $const_structs; +if (show_type("CONST_STRUCT")) { + read_words(\$const_structs, $conststructsfile) + or warn "No structs that should be const will be found - file '$conststructsfile': $!\n"; +} -my $typeOtherTypedefs = ""; -if (length($typedefsfile)) { +if (defined($typedefsfile)) { + my $typeOtherTypedefs; read_words(\$typeOtherTypedefs, $typedefsfile) or warn "No additional types will be considered - file '$typedefsfile': $!\n"; + $typeTypedefs .= '|' . $typeOtherTypedefs if (defined $typeOtherTypedefs); } -$typeTypedefs .= '|' . $typeOtherTypedefs if ($typeOtherTypedefs ne ""); sub build_types { my $mods = "(?x: \n" . join("|\n ", (@modifierList, @modifierListFile)) . "\n)"; @@ -843,10 +1022,16 @@ our $FuncArg = qr{$Typecast{0,1}($LvalOrFunc|$Constant|$String)}; our $declaration_macros = qr{(?x: (?:$Storage\s+)?(?:[A-Z_][A-Z0-9]*_){0,2}(?:DEFINE|DECLARE)(?:_[A-Z0-9]+){1,6}\s*\(| (?:$Storage\s+)?[HLP]?LIST_HEAD\s*\(| - (?:$Storage\s+)?${Type}\s+uninitialized_var\s*\(| (?:SKCIPHER_REQUEST|SHASH_DESC|AHASH_REQUEST)_ON_STACK\s*\( )}; +our %allow_repeated_words = ( + add => '', + added => '', + bad => '', + be => '', +); + sub deparenthesize { my ($string) = @_; return "" if (!defined($string)); @@ -904,7 +1089,7 @@ sub is_maintained_obsolete { sub is_SPDX_License_valid { my ($license) = @_; - return 1 if (!$tree || which("python") eq "" || !(-e "$root/scripts/spdxcheck.py") || !(-e "$root/.git")); + return 1 if (!$tree || which("python") eq "" || !(-e "$root/scripts/spdxcheck.py") || !(-e "$gitroot")); my $root_path = abs_path($root); my $status = `cd "$root_path"; echo "$license" | python scripts/spdxcheck.py -`; @@ -922,7 +1107,7 @@ sub seed_camelcase_includes { $camelcase_seeded = 1; - if (-e ".git") { + if (-e "$gitroot") { my $git_last_include_commit = `${git_command} log --no-merges --pretty=format:"%h%n" -1 -- include`; chomp $git_last_include_commit; $camelcase_cache = ".checkpatch-camelcase.git.$git_last_include_commit"; @@ -950,7 +1135,7 @@ sub seed_camelcase_includes { return; } - if (-e ".git") { + if (-e "$gitroot") { $files = `${git_command} ls-files "include/*.h"`; @include_files = split('\n', $files); } @@ -970,10 +1155,20 @@ sub seed_camelcase_includes { } } +sub git_is_single_file { + my ($filename) = @_; + + return 0 if ((which("git") eq "") || !(-e "$gitroot")); + + my $output = `${git_command} ls-files -- $filename 2>/dev/null`; + my $count = $output =~ tr/\n//; + return $count eq 1 && $output =~ m{^${filename}$}; +} + sub git_commit_info { my ($commit, $id, $desc) = @_; - return ($id, $desc) if ((which("git") eq "") || !(-e ".git")); + return ($id, $desc) if ((which("git") eq "") || !(-e "$gitroot")); my $output = `${git_command} log --no-color --format='%H %s' -1 $commit 2>&1`; $output =~ s/^\s*//gm; @@ -1012,7 +1207,7 @@ my $fixlinenr = -1; # If input is git commits, extract all commits from the commit expressions. # For example, HEAD-3 means we need check 'HEAD, HEAD~1, HEAD~2'. -die "$P: No git repository found\n" if ($git && !-e ".git"); +die "$P: No git repository found\n" if ($git && !-e "$gitroot"); if ($git) { my @commits = (); @@ -1043,6 +1238,9 @@ my $vname; $allow_c99_comments = !defined $ignore_type{"C99_COMMENT_TOLERANCE"}; for my $filename (@ARGV) { my $FILE; + my $is_git_file = git_is_single_file($filename); + my $oldfile = $file; + $file = 1 if ($is_git_file); if ($git) { open($FILE, '-|', "git format-patch -M --stdout -1 $filename") || die "$P: $filename: git format-patch failed - $!\n"; @@ -1065,6 +1263,7 @@ for my $filename (@ARGV) { while (<$FILE>) { chomp; push(@rawlines, $_); + $vname = qq("$1") if ($filename eq '-' && $_ =~ m/^Subject:\s+(.+)/i); } close($FILE); @@ -1086,6 +1285,7 @@ for my $filename (@ARGV) { @modifierListFile = (); @typeListFile = (); build_types(); + $file = $oldfile if ($is_git_file); } if (!$quiet) { @@ -1131,6 +1331,7 @@ sub parse_email { my ($formatted_email) = @_; my $name = ""; + my $quoted = ""; my $name_comment = ""; my $address = ""; my $comment = ""; @@ -1162,14 +1363,20 @@ sub parse_email { } } - $name = trim($name); - $name =~ s/^\"|\"$//g; - $name =~ s/(\s*\([^\)]+\))\s*//; - if (defined($1)) { - $name_comment = trim($1); + # Extract comments from names excluding quoted parts + # "John D. (Doe)" - Do not extract + if ($name =~ s/\"(.+)\"//) { + $quoted = $1; + } + while ($name =~ s/\s*($balanced_parens)\s*/ /) { + $name_comment .= trim($1); } + $name =~ s/^[ \"]+|[ \"]+$//g; + $name = trim("$quoted $name"); + $address = trim($address); $address =~ s/^\<|\>$//g; + $comment = trim($comment); if ($name =~ /[^\w \-]/i) { ##has "must quote" chars $name =~ s/(?<!\\)"/\\"/g; ##escape quotes @@ -1180,25 +1387,30 @@ sub parse_email { } sub format_email { - my ($name, $address) = @_; + my ($name, $name_comment, $address, $comment) = @_; my $formatted_email; - $name = trim($name); - $name =~ s/^\"|\"$//g; + $name =~ s/^[ \"]+|[ \"]+$//g; $address = trim($address); + $address =~ s/(?:\.|\,|\")+$//; ##trailing commas, dots or quotes if ($name =~ /[^\w \-]/i) { ##has "must quote" chars $name =~ s/(?<!\\)"/\\"/g; ##escape quotes $name = "\"$name\""; } + $name_comment = trim($name_comment); + $name_comment = " $name_comment" if ($name_comment ne ""); + $comment = trim($comment); + $comment = " $comment" if ($comment ne ""); + if ("$name" eq "") { $formatted_email = "$address"; } else { - $formatted_email = "$name <$address>"; + $formatted_email = "$name$name_comment <$address>"; } - + $formatted_email .= "$comment"; return $formatted_email; } @@ -1206,7 +1418,7 @@ sub reformat_email { my ($email) = @_; my ($email_name, $name_comment, $email_address, $comment) = parse_email($email); - return format_email($email_name, $email_address); + return format_email($email_name, $name_comment, $email_address, $comment); } sub same_email_addresses { @@ -1216,7 +1428,9 @@ sub same_email_addresses { my ($email2_name, $name2_comment, $email2_address, $comment2) = parse_email($email2); return $email1_name eq $email2_name && - $email1_address eq $email2_address; + $email1_address eq $email2_address && + $name1_comment eq $name2_comment && + $comment1 eq $comment2; } sub which { @@ -1681,8 +1895,16 @@ sub ctx_statement_level { sub ctx_locate_comment { my ($first_line, $end_line) = @_; + # If c99 comment on the current line, or the line before or after + my ($current_comment) = ($rawlines[$end_line - 1] =~ m@^\+.*(//.*$)@); + return $current_comment if (defined $current_comment); + ($current_comment) = ($rawlines[$end_line - 2] =~ m@^[\+ ].*(//.*$)@); + return $current_comment if (defined $current_comment); + ($current_comment) = ($rawlines[$end_line] =~ m@^[\+ ].*(//.*$)@); + return $current_comment if (defined $current_comment); + # Catch a comment on the end of the line itself. - my ($current_comment) = ($rawlines[$end_line - 1] =~ m@.*(/\*.*\*/)\s*(?:\\\s*)?$@); + ($current_comment) = ($rawlines[$end_line - 1] =~ m@.*(/\*.*\*/)\s*(?:\\\s*)?$@); return $current_comment if (defined $current_comment); # Look through the context and try and figure out if there is a @@ -2076,7 +2298,16 @@ sub report { splice(@lines, 1, 1); $output = join("\n", @lines); } - $output = (split('\n', $output))[0] . "\n" if ($terse); + + if ($terse) { + $output = (split('\n', $output))[0] . "\n"; + } + + if ($verbose && exists($verbose_messages{$type}) && + !exists($verbose_emitted{$type})) { + $output .= $verbose_messages{$type} . "\n\n"; + $verbose_emitted{$type} = 1; + } push(our @report, $output); @@ -2425,6 +2656,15 @@ sub u_boot_line { "DEVICE_PLAT_AUTO", $herecurr); } +sub exclude_global_initialisers { + my ($realfile) = @_; + + # Do not check for BPF programs (tools/testing/selftests/bpf/progs/*.c, samples/bpf/*_kern.c, *.bpf.c). + return $realfile =~ m@^tools/testing/selftests/bpf/progs/.*\.c$@ || + $realfile =~ m@^samples/bpf/.*_kern\.c$@ || + $realfile =~ m@/bpf/.*\.bpf\.c$@; +} + sub process { my $filename = shift; @@ -2443,6 +2683,7 @@ sub process { my $signoff = 0; my $author = ''; my $authorsignoff = 0; + my $author_sob = ''; my $is_patch = 0; my $is_binding_patch = -1; my $in_header_lines = $file ? 0 : 1; @@ -2506,7 +2747,7 @@ sub process { if ($rawline=~/^\+\+\+\s+(\S+)/) { $setup_docs = 0; - if ($1 =~ m@Documentation/admin-guide/kernel-parameters.rst$@) { + if ($1 =~ m@Documentation/admin-guide/kernel-parameters.txt$@) { $setup_docs = 1; } #next; @@ -2706,7 +2947,7 @@ sub process { if (($last_binding_patch != -1) && ($last_binding_patch ^ $is_binding_patch)) { WARN("DT_SPLIT_BINDING_PATCH", - "DT binding docs and includes should be a separate patch. See: Documentation/devicetree/bindings/submitting-patches.txt\n"); + "DT binding docs and includes should be a separate patch. See: Documentation/devicetree/bindings/submitting-patches.rst\n"); } } @@ -2735,8 +2976,8 @@ sub process { # Check if the commit log has what seems like a diff which can confuse patch if ($in_commit_log && !$commit_log_has_diff && - (($line =~ m@^\s+diff\b.*a/[\w/]+@ && - $line =~ m@^\s+diff\b.*a/([\w/]+)\s+b/$1\b@) || + (($line =~ m@^\s+diff\b.*a/([\w/]+)@ && + $line =~ m@^\s+diff\b.*a/[\w/]+\s+b/$1\b@) || $line =~ m@^\s*(?:\-\-\-\s+a/|\+\+\+\s+b/)@ || $line =~ m/^\s*\@\@ \-\d+,\d+ \+\d+,\d+ \@\@/)) { ERROR("DIFF_IN_COMMIT_MSG", @@ -2757,6 +2998,10 @@ sub process { # Check the patch for a From: if (decode("MIME-Header", $line) =~ /^From:\s*(.*)/) { $author = $1; + my $curline = $linenr; + while(defined($rawlines[$curline]) && ($rawlines[$curline++] =~ /^[ \t]\s*(.*)/)) { + $author .= $1; + } $author = encode("utf8", $author) if ($line =~ /=\?utf-8\?/i); $author =~ s/"//g; $author = reformat_email($author); @@ -2766,9 +3011,37 @@ sub process { if ($line =~ /^\s*signed-off-by:\s*(.*)/i) { $signoff++; $in_commit_log = 0; - if ($author ne '') { + if ($author ne '' && $authorsignoff != 1) { if (same_email_addresses($1, $author)) { $authorsignoff = 1; + } else { + my $ctx = $1; + my ($email_name, $email_comment, $email_address, $comment1) = parse_email($ctx); + my ($author_name, $author_comment, $author_address, $comment2) = parse_email($author); + + if ($email_address eq $author_address && $email_name eq $author_name) { + $author_sob = $ctx; + $authorsignoff = 2; + } elsif ($email_address eq $author_address) { + $author_sob = $ctx; + $authorsignoff = 3; + } elsif ($email_name eq $author_name) { + $author_sob = $ctx; + $authorsignoff = 4; + + my $address1 = $email_address; + my $address2 = $author_address; + + if ($address1 =~ /(\S+)\+\S+(\@.*)/) { + $address1 = "$1$2"; + } + if ($address2 =~ /(\S+)\+\S+(\@.*)/) { + $address2 = "$1$2"; + } + if ($address1 eq $address2) { + $authorsignoff = 5; + } + } } } } @@ -2795,8 +3068,17 @@ sub process { my $ucfirst_sign_off = ucfirst(lc($sign_off)); if ($sign_off !~ /$signature_tags/) { - WARN("BAD_SIGN_OFF", - "Non-standard signature: $sign_off\n" . $herecurr); + my $suggested_signature = find_standard_signature($sign_off); + if ($suggested_signature eq "") { + WARN("BAD_SIGN_OFF", + "Non-standard signature: $sign_off\n" . $herecurr); + } else { + if (WARN("BAD_SIGN_OFF", + "Non-standard signature: '$sign_off' - perhaps '$suggested_signature'?\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/$sign_off/$suggested_signature/; + } + } } if (defined $space_before && $space_before ne "") { if (WARN("BAD_SIGN_OFF", @@ -2825,7 +3107,7 @@ sub process { } my ($email_name, $name_comment, $email_address, $comment) = parse_email($email); - my $suggested_email = format_email(($email_name, $email_address)); + my $suggested_email = format_email(($email_name, $name_comment, $email_address, $comment)); if ($suggested_email eq "") { ERROR("BAD_SIGN_OFF", "Unrecognized email address: '$email'\n" . $herecurr); @@ -2836,8 +3118,76 @@ sub process { # Don't force email to have quotes # Allow just an angle bracketed address if (!same_email_addresses($email, $suggested_email)) { + if (WARN("BAD_SIGN_OFF", + "email address '$email' might be better as '$suggested_email'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$email\E/$suggested_email/; + } + } + + # Address part shouldn't have comments + my $stripped_address = $email_address; + $stripped_address =~ s/\([^\(\)]*\)//g; + if ($email_address ne $stripped_address) { + if (WARN("BAD_SIGN_OFF", + "address part of email should not have comments: '$email_address'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$email_address\E/$stripped_address/; + } + } + + # Only one name comment should be allowed + my $comment_count = () = $name_comment =~ /\([^\)]+\)/g; + if ($comment_count > 1) { WARN("BAD_SIGN_OFF", - "email address '$email' might be better as '$suggested_email$comment'\n" . $herecurr); + "Use a single name comment in email: '$email'\n" . $herecurr); + } + + + # stable@vger.kernel.org or stable@kernel.org shouldn't + # have an email name. In addition comments should strictly + # begin with a # + if ($email =~ /^.*stable\@(?:vger\.)?kernel\.org/i) { + if (($comment ne "" && $comment !~ /^#.+/) || + ($email_name ne "")) { + my $cur_name = $email_name; + my $new_comment = $comment; + $cur_name =~ s/[a-zA-Z\s\-\"]+//g; + + # Remove brackets enclosing comment text + # and # from start of comments to get comment text + $new_comment =~ s/^\((.*)\)$/$1/; + $new_comment =~ s/^\[(.*)\]$/$1/; + $new_comment =~ s/^[\s\#]+|\s+$//g; + + $new_comment = trim("$new_comment $cur_name") if ($cur_name ne $new_comment); + $new_comment = " # $new_comment" if ($new_comment ne ""); + my $new_email = "$email_address$new_comment"; + + if (WARN("BAD_STABLE_ADDRESS_STYLE", + "Invalid email format for stable: '$email', prefer '$new_email'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$email\E/$new_email/; + } + } + } elsif ($comment ne "" && $comment !~ /^(?:#.+|\(.+\))$/) { + my $new_comment = $comment; + + # Extract comment text from within brackets or + # c89 style /*...*/ comments + $new_comment =~ s/^\[(.*)\]$/$1/; + $new_comment =~ s/^\/\*(.*)\*\/$/$1/; + + $new_comment = trim($new_comment); + $new_comment =~ s/^[^\w]$//; # Single lettered comment with non word character is usually a typo + $new_comment = "($new_comment)" if ($new_comment ne ""); + my $new_email = format_email($email_name, $name_comment, $email_address, $new_comment); + + if (WARN("BAD_SIGN_OFF", + "Unexpected content after email: '$email', should be: '$new_email'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$email\E/$new_email/; + } } } @@ -2860,7 +3210,7 @@ sub process { } if (!defined $lines[$linenr]) { WARN("BAD_SIGN_OFF", - "Co-developed-by: must be immediately followed by Signed-off-by:\n" . "$here\n" . $rawline); + "Co-developed-by: must be immediately followed by Signed-off-by:\n" . "$here\n" . $rawline); } elsif ($rawlines[$linenr] !~ /^\s*signed-off-by:\s*(.*)/i) { WARN("BAD_SIGN_OFF", "Co-developed-by: must be immediately followed by Signed-off-by:\n" . "$here\n" . $rawline . "\n" .$rawlines[$linenr]); @@ -2880,8 +3230,11 @@ sub process { # Check for Gerrit Change-Ids not in any patch context if ($realfile eq '' && !$has_patch_separator && $line =~ /^\s*change-id:/i) { - ERROR("GERRIT_CHANGE_ID", - "Remove Gerrit Change-Id's before submitting upstream\n" . $herecurr); + if (ERROR("GERRIT_CHANGE_ID", + "Remove Gerrit Change-Id's before submitting upstream\n" . $herecurr) && + $fix) { + fix_delete_line($fixlinenr, $rawline); + } } # Check if the commit log is in a possible stack dump @@ -2903,8 +3256,8 @@ sub process { # file delta changes $line =~ /^\s*(?:[\w\.\-]+\/)++[\w\.\-]+:/ || # filename then : - $line =~ /^\s*(?:Fixes:|Link:)/i || - # A Fixes: or Link: line + $line =~ /^\s*(?:Fixes:|Link:|$signature_tags)/i || + # A Fixes: or Link: line or signature tag line $commit_log_possible_stack_dump)) { WARN("COMMIT_LOG_LONG_LINE", "Possible unwrapped commit description (prefer a maximum 75 chars per line)\n" . $herecurr); @@ -2917,6 +3270,15 @@ sub process { $commit_log_possible_stack_dump = 0; } +# Check for lines starting with a # + if ($in_commit_log && $line =~ /^#/) { + if (WARN("COMMIT_COMMENT_SYMBOL", + "Commit log lines starting with '#' are dropped by git as comments\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/^/ /; + } + } + # Check for git id commit length and improperly formed commit descriptions if ($in_commit_log && !$commit_log_possible_stack_dump && $line !~ /^\s*(?:Link|Patchwork|http|https|BugLink|base-commit):/i && @@ -2993,7 +3355,7 @@ sub process { ($line =~ /^new file mode\s*\d+\s*$/) && ($realfile =~ m@^Documentation/devicetree/bindings/.*\.txt$@)) { WARN("DT_SCHEMA_BINDING_PATCH", - "DT bindings should be in DT schema format. See: Documentation/devicetree/writing-schema.rst\n"); + "DT bindings should be in DT schema format. See: Documentation/devicetree/bindings/writing-schema.rst\n"); } # Check for wrappage within a valid hunk of the file @@ -3057,15 +3419,18 @@ sub process { # Check for various typo / spelling mistakes if (defined($misspellings) && ($in_commit_log || $line =~ /^(?:\+|Subject:)/i)) { - while ($rawline =~ /(?:^|[^a-z@])($misspellings)(?:\b|$|[^a-z@])/gi) { + while ($rawline =~ /(?:^|[^\w\-'`])($misspellings)(?:[^\w\-'`]|$)/gi) { my $typo = $1; + my $blank = copy_spacing($rawline); + my $ptr = substr($blank, 0, $-[1]) . "^" x length($typo); + my $hereptr = "$hereline$ptr\n"; my $typo_fix = $spelling_fix{lc($typo)}; $typo_fix = ucfirst($typo_fix) if ($typo =~ /^[A-Z]/); $typo_fix = uc($typo_fix) if ($typo =~ /^[A-Z]+$/); my $msg_level = \&WARN; $msg_level = \&CHK if ($file); if (&{$msg_level}("TYPO_SPELLING", - "'$typo' may be misspelled - perhaps '$typo_fix'?\n" . $herecurr) && + "'$typo' may be misspelled - perhaps '$typo_fix'?\n" . $hereptr) && $fix) { $fixed[$fixlinenr] =~ s/(^|[^A-Za-z@])($typo)($|[^A-Za-z@])/$1$typo_fix$3/; } @@ -3083,6 +3448,60 @@ sub process { } } +# check for repeated words separated by a single space +# avoid false positive from list command eg, '-rw-r--r-- 1 root root' + if (($rawline =~ /^\+/ || $in_commit_log) && + $rawline !~ /[bcCdDlMnpPs\?-][rwxsStT-]{9}/) { + pos($rawline) = 1 if (!$in_commit_log); + while ($rawline =~ /\b($word_pattern) (?=($word_pattern))/g) { + + my $first = $1; + my $second = $2; + my $start_pos = $-[1]; + my $end_pos = $+[2]; + if ($first =~ /(?:struct|union|enum)/) { + pos($rawline) += length($first) + length($second) + 1; + next; + } + + next if (lc($first) ne lc($second)); + next if ($first eq 'long'); + + # check for character before and after the word matches + my $start_char = ''; + my $end_char = ''; + $start_char = substr($rawline, $start_pos - 1, 1) if ($start_pos > ($in_commit_log ? 0 : 1)); + $end_char = substr($rawline, $end_pos, 1) if ($end_pos < length($rawline)); + + next if ($start_char =~ /^\S$/); + next if (index(" \t.,;?!", $end_char) == -1); + + # avoid repeating hex occurrences like 'ff ff fe 09 ...' + if ($first =~ /\b[0-9a-f]{2,}\b/i) { + next if (!exists($allow_repeated_words{lc($first)})); + } + + if (WARN("REPEATED_WORD", + "Possible repeated word: '$first'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\b$first $second\b/$first/; + } + } + + # if it's a repeated word on consecutive lines in a comment block + if ($prevline =~ /$;+\s*$/ && + $prevrawline =~ /($word_pattern)\s*$/) { + my $last_word = $1; + if ($rawline =~ /^\+\s*\*\s*$last_word /) { + if (WARN("REPEATED_WORD", + "Possible repeated word: '$last_word'\n" . $hereprev) && + $fix) { + $fixed[$fixlinenr] =~ s/(\+\s*\*\s*)$last_word /$1/; + } + } + } + } + # ignore non-hunk lines and lines being removed next if (!$hunk_line || $line =~ /^-/); @@ -3141,11 +3560,7 @@ sub process { if ($lines[$ln - 1] =~ /^\+\s*(?:bool|tristate|prompt)\s*["']/) { $is_start = 1; - } elsif ($lines[$ln - 1] =~ /^\+\s*(?:help|---help---)\s*$/) { - if ($lines[$ln - 1] =~ "---help---") { - WARN("CONFIG_DESCRIPTION", - "prefer 'help' over '---help---' for new help texts\n" . $herecurr); - } + } elsif ($lines[$ln - 1] =~ /^\+\s*(?:---)?help(?:---)?$/) { $length = -1; } @@ -3172,22 +3587,44 @@ sub process { #print "is_start<$is_start> is_end<$is_end> length<$length>\n"; } -# check for MAINTAINERS entries that don't have the right form - if ($realfile =~ /^MAINTAINERS$/ && - $rawline =~ /^\+[A-Z]:/ && - $rawline !~ /^\+[A-Z]:\t\S/) { - if (WARN("MAINTAINERS_STYLE", - "MAINTAINERS entries use one tab after TYPE:\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/^(\+[A-Z]):\s*/$1:\t/; +# check MAINTAINERS entries + if ($realfile =~ /^MAINTAINERS$/) { +# check MAINTAINERS entries for the right form + if ($rawline =~ /^\+[A-Z]:/ && + $rawline !~ /^\+[A-Z]:\t\S/) { + if (WARN("MAINTAINERS_STYLE", + "MAINTAINERS entries use one tab after TYPE:\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/^(\+[A-Z]):\s*/$1:\t/; + } + } +# check MAINTAINERS entries for the right ordering too + my $preferred_order = 'MRLSWQBCPTFXNK'; + if ($rawline =~ /^\+[A-Z]:/ && + $prevrawline =~ /^[\+ ][A-Z]:/) { + $rawline =~ /^\+([A-Z]):\s*(.*)/; + my $cur = $1; + my $curval = $2; + $prevrawline =~ /^[\+ ]([A-Z]):\s*(.*)/; + my $prev = $1; + my $prevval = $2; + my $curindex = index($preferred_order, $cur); + my $previndex = index($preferred_order, $prev); + if ($curindex < 0) { + WARN("MAINTAINERS_STYLE", + "Unknown MAINTAINERS entry type: '$cur'\n" . $herecurr); + } else { + if ($previndex >= 0 && $curindex < $previndex) { + WARN("MAINTAINERS_STYLE", + "Misordered MAINTAINERS entry - list '$cur:' before '$prev:'\n" . $hereprev); + } elsif ((($prev eq 'F' && $cur eq 'F') || + ($prev eq 'X' && $cur eq 'X')) && + ($prevval cmp $curval) > 0) { + WARN("MAINTAINERS_STYLE", + "Misordered MAINTAINERS entry - list file patterns in alphabetic order\n" . $hereprev); + } + } } - } - -# discourage the use of boolean for type definition attributes of Kconfig options - if ($realfile =~ /Kconfig/ && - $line =~ /^\+\s*\bboolean\b/) { - WARN("CONFIG_TYPE_BOOLEAN", - "Use of boolean is deprecated, please use bool instead.\n" . $herecurr); } if (($realfile =~ /Makefile.*/ || $realfile =~ /Kbuild.*/) && @@ -3284,6 +3721,12 @@ sub process { } } +# check for embedded filenames + if ($rawline =~ /^\+.*\Q$realfile\E/) { + WARN("EMBEDDED_FILENAME", + "It's generally not useful to have the filename in the file\n" . $herecurr); + } + # check we are in a valid source file if not then ignore this hunk next if ($realfile !~ /\.(h|c|s|S|sh|dtsi|dts)$/); @@ -3361,8 +3804,18 @@ sub process { # check for adding lines without a newline. if ($line =~ /^\+/ && defined $lines[$linenr] && $lines[$linenr] =~ /^\\ No newline at end of file/) { - WARN("MISSING_EOF_NEWLINE", - "adding a line without newline at end of file\n" . $herecurr); + if (WARN("MISSING_EOF_NEWLINE", + "adding a line without newline at end of file\n" . $herecurr) && + $fix) { + fix_delete_line($fixlinenr+1, "No newline at end of file"); + } + } + +# check for .L prefix local symbols in .S files + if ($realfile =~ /\.S$/ && + $line =~ /^\+\s*(?:[A-Z]+_)?SYM_[A-Z]+_(?:START|END)(?:_[A-Z_]+)?\s*\(\s*\.L/) { + WARN("AVOID_L_PREFIX", + "Avoid using '.L' prefixed local symbol names for denoting a range of code via 'SYM_*_START/END' annotations; see Documentation/asm-annotations.rst\n" . $herecurr); } if ($u_boot) { @@ -3400,14 +3853,28 @@ sub process { # check for assignments on the start of a line if ($sline =~ /^\+\s+($Assignment)[^=]/) { - CHK("ASSIGNMENT_CONTINUATIONS", - "Assignment operator '$1' should be on the previous line\n" . $hereprev); + my $operator = $1; + if (CHK("ASSIGNMENT_CONTINUATIONS", + "Assignment operator '$1' should be on the previous line\n" . $hereprev) && + $fix && $prevrawline =~ /^\+/) { + # add assignment operator to the previous line, remove from current line + $fixed[$fixlinenr - 1] .= " $operator"; + $fixed[$fixlinenr] =~ s/\Q$operator\E\s*//; + } } # check for && or || at the start of a line if ($rawline =~ /^\+\s*(&&|\|\|)/) { - CHK("LOGICAL_CONTINUATIONS", - "Logical continuations should be on the previous line\n" . $hereprev); + my $operator = $1; + if (CHK("LOGICAL_CONTINUATIONS", + "Logical continuations should be on the previous line\n" . $hereprev) && + $fix && $prevrawline =~ /^\+/) { + # insert logical operator at last non-comment, non-whitepsace char on previous line + $prevline =~ /[\s$;]*$/; + my $line_end = substr($prevrawline, $-[0]); + $fixed[$fixlinenr - 1] =~ s/\Q$line_end\E$/ $operator$line_end/; + $fixed[$fixlinenr] =~ s/\Q$operator\E\s*//; + } } # check indentation starts on a tab stop @@ -3475,7 +3942,7 @@ sub process { if ($realfile =~ m@^(drivers/net/|net/)@ && $prevrawline =~ /^\+[ \t]*\/\*[ \t]*$/ && $rawline =~ /^\+[ \t]*\*/ && - $realline > 2) { + $realline > 3) { # Do not warn about the initial copyright comment block after SPDX-License-Identifier WARN("NETWORKING_BLOCK_COMMENT_STYLE", "networking block comments don't use an empty /* line, use /* Comment...\n" . $hereprev); } @@ -3557,43 +4024,48 @@ sub process { } # check for missing blank lines after declarations - if ($sline =~ /^\+\s+\S/ && #Not at char 1 - # actual declarations - ($prevline =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || +# (declarations must have the same indentation and not be at the start of line) + if (($prevline =~ /\+(\s+)\S/) && $sline =~ /^\+$1\S/) { + # use temporaries + my $sl = $sline; + my $pl = $prevline; + # remove $Attribute/$Sparse uses to simplify comparisons + $sl =~ s/\b(?:$Attribute|$Sparse)\b//g; + $pl =~ s/\b(?:$Attribute|$Sparse)\b//g; + if (($pl =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || # function pointer declarations - $prevline =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || + $pl =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || # foo bar; where foo is some local typedef or #define - $prevline =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || + $pl =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || # known declaration macros - $prevline =~ /^\+\s+$declaration_macros/) && + $pl =~ /^\+\s+$declaration_macros/) && # for "else if" which can look like "$Ident $Ident" - !($prevline =~ /^\+\s+$c90_Keywords\b/ || + !($pl =~ /^\+\s+$c90_Keywords\b/ || # other possible extensions of declaration lines - $prevline =~ /(?:$Compare|$Assignment|$Operators)\s*$/ || + $pl =~ /(?:$Compare|$Assignment|$Operators)\s*$/ || # not starting a section or a macro "\" extended line - $prevline =~ /(?:\{\s*|\\)$/) && + $pl =~ /(?:\{\s*|\\)$/) && # looks like a declaration - !($sline =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || + !($sl =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || # function pointer declarations - $sline =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || + $sl =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || # foo bar; where foo is some local typedef or #define - $sline =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || + $sl =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || # known declaration macros - $sline =~ /^\+\s+$declaration_macros/ || + $sl =~ /^\+\s+$declaration_macros/ || # start of struct or union or enum - $sline =~ /^\+\s+(?:static\s+)?(?:const\s+)?(?:union|struct|enum|typedef)\b/ || + $sl =~ /^\+\s+(?:static\s+)?(?:const\s+)?(?:union|struct|enum|typedef)\b/ || # start or end of block or continuation of declaration - $sline =~ /^\+\s+(?:$|[\{\}\.\#\"\?\:\(\[])/ || + $sl =~ /^\+\s+(?:$|[\{\}\.\#\"\?\:\(\[])/ || # bitfield continuation - $sline =~ /^\+\s+$Ident\s*:\s*\d+\s*[,;]/ || + $sl =~ /^\+\s+$Ident\s*:\s*\d+\s*[,;]/ || # other possible extensions of declaration lines - $sline =~ /^\+\s+\(?\s*(?:$Compare|$Assignment|$Operators)/) && - # indentation of previous and current line are the same - (($prevline =~ /\+(\s+)\S/) && $sline =~ /^\+$1\S/)) { - if (WARN("LINE_SPACING", - "Missing a blank line after declarations\n" . $hereprev) && - $fix) { - fix_insert_line($fixlinenr, "\+"); + $sl =~ /^\+\s+\(?\s*(?:$Compare|$Assignment|$Operators)/)) { + if (WARN("LINE_SPACING", + "Missing a blank line after declarations\n" . $hereprev) && + $fix) { + fix_insert_line($fixlinenr, "\+"); + } } } @@ -3646,12 +4118,16 @@ sub process { } # check indentation of a line with a break; -# if the previous line is a goto or return and is indented the same # of tabs +# if the previous line is a goto, return or break +# and is indented the same # of tabs if ($sline =~ /^\+([\t]+)break\s*;\s*$/) { my $tabs = $1; - if ($prevline =~ /^\+$tabs(?:goto|return)\b/) { - WARN("UNNECESSARY_BREAK", - "break is not useful after a goto or return\n" . $hereprev); + if ($prevline =~ /^\+$tabs(goto|return|break)\b/) { + if (WARN("UNNECESSARY_BREAK", + "break is not useful after a $1\n" . $hereprev) && + $fix) { + fix_delete_line($fixlinenr, $rawline); + } } } @@ -3934,6 +4410,17 @@ sub process { #ignore lines not being added next if ($line =~ /^[^\+]/); +# check for self assignments used to avoid compiler warnings +# e.g.: int foo = foo, *bar = NULL; +# struct foo bar = *(&(bar)); + if ($line =~ /^\+\s*(?:$Declare)?([A-Za-z_][A-Za-z\d_]*)\s*=/) { + my $var = $1; + if ($line =~ /^\+\s*(?:$Declare)?$var\s*=\s*(?:$var|\*\s*\(?\s*&\s*\(?\s*$var\s*\)?\s*\)?)\s*[;,]/) { + WARN("SELF_ASSIGNMENT", + "Do not use self-assignments to avoid compiler warnings\n" . $herecurr); + } + } + # check for dereferences that span multiple lines if ($prevline =~ /^\+.*$Lval\s*(?:\.|->)\s*$/ && $line =~ /^\+\s*(?!\#\s*(?!define\s+|if))\s*$Lval/) { @@ -4049,8 +4536,7 @@ sub process { if (defined $realline_next && exists $lines[$realline_next - 1] && !defined $suppress_export{$realline_next} && - ($lines[$realline_next - 1] =~ /EXPORT_SYMBOL.*\((.*)\)/ || - $lines[$realline_next - 1] =~ /EXPORT_UNUSED_SYMBOL.*\((.*)\)/)) { + ($lines[$realline_next - 1] =~ /EXPORT_SYMBOL.*\((.*)\)/)) { # Handle definitions which produce identifiers with # a prefix: # XXX(foo); @@ -4077,8 +4563,7 @@ sub process { } if (!defined $suppress_export{$linenr} && $prevline =~ /^.\s*$/ && - ($line =~ /EXPORT_SYMBOL.*\((.*)\)/ || - $line =~ /EXPORT_UNUSED_SYMBOL.*\((.*)\)/)) { + ($line =~ /EXPORT_SYMBOL.*\((.*)\)/)) { #print "FOO B <$lines[$linenr - 1]>\n"; $suppress_export{$linenr} = 2; } @@ -4089,7 +4574,8 @@ sub process { } # check for global initialisers. - if ($line =~ /^\+$Type\s*$Ident(?:\s+$Modifier)*\s*=\s*($zero_initializer)\s*;/) { + if ($line =~ /^\+$Type\s*$Ident(?:\s+$Modifier)*\s*=\s*($zero_initializer)\s*;/ && + !exclude_global_initialisers($realfile)) { if (ERROR("GLOBAL_INITIALISERS", "do not initialise globals to $1\n" . $herecurr) && $fix) { @@ -4168,12 +4654,24 @@ sub process { } } +# check for const static or static <non ptr type> const declarations +# prefer 'static const <foo>' over 'const static <foo>' and 'static <foo> const' + if ($sline =~ /^\+\s*const\s+static\s+($Type)\b/ || + $sline =~ /^\+\s*static\s+($BasicType)\s+const\b/) { + if (WARN("STATIC_CONST", + "Move const after static - use 'static const $1'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bconst\s+static\b/static const/; + $fixed[$fixlinenr] =~ s/\bstatic\s+($BasicType)\s+const\b/static const $1/; + } + } + # check for non-global char *foo[] = {"bar", ...} declarations. if ($line =~ /^.\s+(?:static\s+|const\s+)?char\s+\*\s*\w+\s*\[\s*\]\s*=\s*\{/) { WARN("STATIC_CONST_CHAR_ARRAY", "char * array declaration might be better as static const\n" . $herecurr); - } + } # check for sizeof(foo)/sizeof(foo[0]) that could be ARRAY_SIZE(foo) if ($line =~ m@\bsizeof\s*\(\s*($Lval)\s*\)@) { @@ -4290,16 +4788,23 @@ sub process { "printk() should include KERN_<LEVEL> facility level\n" . $herecurr); } - if ($line =~ /\bprintk\s*\(\s*KERN_([A-Z]+)/) { - my $orig = $1; +# prefer variants of (subsystem|netdev|dev|pr)_<level> to printk(KERN_<LEVEL> + if ($line =~ /\b(printk(_once|_ratelimited)?)\s*\(\s*KERN_([A-Z]+)/) { + my $printk = $1; + my $modifier = $2; + my $orig = $3; + $modifier = "" if (!defined($modifier)); my $level = lc($orig); $level = "warn" if ($level eq "warning"); my $level2 = $level; $level2 = "dbg" if ($level eq "debug"); + $level .= $modifier; + $level2 .= $modifier; WARN("PREFER_PR_LEVEL", - "Prefer [subsystem eg: netdev]_$level2([subsystem]dev, ... then dev_$level2(dev, ... then pr_$level(... to printk(KERN_$orig ...\n" . $herecurr); + "Prefer [subsystem eg: netdev]_$level2([subsystem]dev, ... then dev_$level2(dev, ... then pr_$level(... to $printk(KERN_$orig ...\n" . $herecurr); } +# prefer dev_<level> to dev_printk(KERN_<LEVEL> if ($line =~ /\bdev_printk\s*\(\s*KERN_([A-Z]+)/) { my $orig = $1; my $level = lc($orig); @@ -4309,6 +4814,12 @@ sub process { "Prefer dev_$level(... to dev_printk(KERN_$orig, ...\n" . $herecurr); } +# trace_printk should not be used in production code. + if ($line =~ /\b(trace_printk|trace_puts|ftrace_vprintk)\s*\(/) { + WARN("TRACE_PRINTK", + "Do not use $1() in production code (this can be ignored if built only with a debug config option)\n" . $herecurr); + } + # ENOSYS means "bad syscall nr" and nothing else. This will have a small # number of false positives, but assembly files are not checked, so at # least the arch entry code will not trigger this warning. @@ -4317,6 +4828,17 @@ sub process { "ENOSYS means 'invalid syscall nr' and nothing else\n" . $herecurr); } +# ENOTSUPP is not a standard error code and should be avoided in new patches. +# Folks usually mean EOPNOTSUPP (also called ENOTSUP), when they type ENOTSUPP. +# Similarly to ENOSYS warning a small number of false positives is expected. + if (!$file && $line =~ /\bENOTSUPP\b/) { + if (WARN("ENOTSUPP", + "ENOTSUPP is not a SUSV4 error code, prefer EOPNOTSUPP\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bENOTSUPP\b/EOPNOTSUPP/; + } + } + # function brace can't be on same line, except for #defines of do while, # or if closed on same line if ($perl_version_ok && @@ -4328,7 +4850,7 @@ sub process { $fix) { fix_delete_line($fixlinenr, $rawline); my $fixed_line = $rawline; - $fixed_line =~ /(^..*$Type\s*$Ident\(.*\)\s*){(.*)$/; + $fixed_line =~ /(^..*$Type\s*$Ident\(.*\)\s*)\{(.*)$/; my $line1 = $1; my $line2 = $2; fix_insert_line($fixlinenr, ltrim($line1)); @@ -4739,7 +5261,7 @@ sub process { # A colon needs no spaces before when it is # terminating a case value or a label. } elsif ($opv eq ':C' || $opv eq ':L') { - if ($ctx =~ /Wx./) { + if ($ctx =~ /Wx./ and $realfile !~ m@.*\.lds\.h$@) { if (ERROR("SPACING", "space prohibited before that '$op' $at\n" . $hereptr)) { $good = rtrim($fix_elements[$n]) . trim($fix_elements[$n + 1]); @@ -4823,7 +5345,7 @@ sub process { ## $line !~ /^.\s*$Type\s+$Ident(?:\s*=[^,{]*)?\s*,\s*$Type\s*$Ident.*/) { ## ## # Remove any bracketed sections to ensure we do not -## # falsly report the parameters of functions. +## # falsely report the parameters of functions. ## my $ln = $line; ## while ($ln =~ s/\([^\(\)]*\)//g) { ## } @@ -4964,6 +5486,17 @@ sub process { } } +# check if a statement with a comma should be two statements like: +# foo = bar(), /* comma should be semicolon */ +# bar = baz(); + if (defined($stat) && + $stat =~ /^\+\s*(?:$Lval\s*$Assignment\s*)?$FuncArg\s*,\s*(?:$Lval\s*$Assignment\s*)?$FuncArg\s*;\s*$/) { + my $cnt = statement_rawlines($stat); + my $herectx = get_stat_here($linenr, $cnt, $here); + WARN("SUSPECT_COMMA_SEMICOLON", + "Possible comma where semicolon could be used\n" . $herectx); + } + # return is not a function if (defined($stat) && $stat =~ /^.\s*return(\s*)\(/s) { my $spacing = $1; @@ -4991,7 +5524,7 @@ sub process { $lines[$linenr - 3] !~ /^[ +]\s*$Ident\s*:/) { WARN("RETURN_VOID", "void function return statements are not generally useful\n" . $hereprev); - } + } # if statements using unnecessary parentheses - ie: if ((foo == bar)) if ($perl_version_ok && @@ -5084,8 +5617,30 @@ sub process { my ($s, $c) = ($stat, $cond); if ($c =~ /\bif\s*\(.*[^<>!=]=[^=].*/s) { - ERROR("ASSIGN_IN_IF", - "do not use assignment in if condition\n" . $herecurr); + if (ERROR("ASSIGN_IN_IF", + "do not use assignment in if condition\n" . $herecurr) && + $fix && $perl_version_ok) { + if ($rawline =~ /^\+(\s+)if\s*\(\s*(\!)?\s*\(\s*(($Lval)\s*=\s*$LvalOrFunc)\s*\)\s*(?:($Compare)\s*($FuncArg))?\s*\)\s*(\{)?\s*$/) { + my $space = $1; + my $not = $2; + my $statement = $3; + my $assigned = $4; + my $test = $8; + my $against = $9; + my $brace = $15; + fix_delete_line($fixlinenr, $rawline); + fix_insert_line($fixlinenr, "$space$statement;"); + my $newline = "${space}if ("; + $newline .= '!' if defined($not); + $newline .= '(' if (defined $not && defined($test) && defined($against)); + $newline .= "$assigned"; + $newline .= " $test $against" if (defined($test) && defined($against)); + $newline .= ')' if (defined $not && defined($test) && defined($against)); + $newline .= ')'; + $newline .= " {" if (defined($brace)); + fix_insert_line($fixlinenr + 1, $newline); + } + } } # Find out what is on the end of the line after the @@ -5206,6 +5761,8 @@ sub process { #CamelCase if ($var !~ /^$Constant$/ && $var =~ /[A-Z][a-z]|[a-z][A-Z]/ && +#Ignore some autogenerated defines and enum values + $var !~ /^(?:[A-Z]+_){1,5}[A-Z]{1,3}[a-z]/ && #Ignore Page<foo> variants $var !~ /^(?:Clear|Set|TestClear|TestSet|)Page[A-Z]/ && #Ignore SI style variants like nS, mV and dB @@ -5301,9 +5858,9 @@ sub process { $dstat =~ s/\s*$//s; # Flatten any parentheses and braces - while ($dstat =~ s/\([^\(\)]*\)/1/ || - $dstat =~ s/\{[^\{\}]*\}/1/ || - $dstat =~ s/.\[[^\[\]]*\]/1/) + while ($dstat =~ s/\([^\(\)]*\)/1u/ || + $dstat =~ s/\{[^\{\}]*\}/1u/ || + $dstat =~ s/.\[[^\[\]]*\]/1u/) { } @@ -5344,6 +5901,7 @@ sub process { $dstat !~ /^\.$Ident\s*=/ && # .foo = $dstat !~ /^(?:\#\s*$Ident|\#\s*$Constant)\s*$/ && # stringification #foo $dstat !~ /^do\s*$Constant\s*while\s*$Constant;?$/ && # do {...} while (...); // do {...} while (...) + $dstat !~ /^while\s*$Constant\s*$Constant\s*$/ && # while (...) {...} $dstat !~ /^for\s*$Constant$/ && # for (...) $dstat !~ /^for\s*$Constant\s+(?:$Ident|-?$Constant)$/ && # for (...) bar() $dstat !~ /^do\s*{/ && # do {... @@ -5385,7 +5943,7 @@ sub process { next if ($arg =~ /\.\.\./); next if ($arg =~ /^type$/i); my $tmp_stmt = $define_stmt; - $tmp_stmt =~ s/\b(sizeof|typeof|__typeof__|__builtin\w+|typecheck\s*\(\s*$Type\s*,|\#+)\s*\(*\s*$arg\s*\)*\b//g; + $tmp_stmt =~ s/\b(__must_be_array|offsetof|sizeof|sizeof_field|__stringify|typeof|__typeof__|__builtin\w+|typecheck\s*\(\s*$Type\s*,|\#+)\s*\(*\s*$arg\s*\)*\b//g; $tmp_stmt =~ s/\#+\s*$arg\b//g; $tmp_stmt =~ s/\b$arg\s*\#\#//g; my $use_cnt = () = $tmp_stmt =~ /\b$arg\b/g; @@ -5662,6 +6220,17 @@ sub process { "Prefer using '\"%s...\", __func__' to using '$context_function', this function's name, in a string\n" . $herecurr); } +# check for unnecessary function tracing like uses +# This does not use $logFunctions because there are many instances like +# 'dprintk(FOO, "%s()\n", __func__);' which do not match $logFunctions + if ($rawline =~ /^\+.*\([^"]*"$tracing_logging_tags{0,3}%s(?:\s*\(\s*\)\s*)?$tracing_logging_tags{0,3}(?:\\n)?"\s*,\s*__func__\s*\)\s*;/) { + if (WARN("TRACING_LOGGING", + "Unnecessary ftrace-like logging - prefer using ftrace\n" . $herecurr) && + $fix) { + fix_delete_line($fixlinenr, $rawline); + } + } + # check for spaces before a quoted newline if ($rawline =~ /^.*\".*\s\\n/) { if (WARN("QUOTED_WHITESPACE_BEFORE_NEWLINE", @@ -5808,6 +6377,28 @@ sub process { "Avoid logging continuation uses where feasible\n" . $herecurr); } +# check for unnecessary use of %h[xudi] and %hh[xudi] in logging functions + if (defined $stat && + $line =~ /\b$logFunctions\s*\(/ && + index($stat, '"') >= 0) { + my $lc = $stat =~ tr@\n@@; + $lc = $lc + $linenr; + my $stat_real = get_stat_real($linenr, $lc); + pos($stat_real) = index($stat_real, '"'); + while ($stat_real =~ /[^\"%]*(%[\#\d\.\*\-]*(h+)[idux])/g) { + my $pspec = $1; + my $h = $2; + my $lineoff = substr($stat_real, 0, $-[1]) =~ tr@\n@@; + if (WARN("UNNECESSARY_MODIFIER", + "Integer promotion: Using '$h' in '$pspec' is unnecessary\n" . "$here\n$stat_real\n") && + $fix && $fixed[$fixlinenr + $lineoff] =~ /^\+/) { + my $nspec = $pspec; + $nspec =~ s/h//g; + $fixed[$fixlinenr + $lineoff] =~ s/\Q$pspec\E/$nspec/; + } + } + } + # check for mask then right shift without a parentheses if ($perl_version_ok && $line =~ /$LvalOrFunc\s*\&\s*($LvalOrFunc)\s*>>/ && @@ -5966,8 +6557,7 @@ sub process { my $barriers = qr{ mb| rmb| - wmb| - read_barrier_depends + wmb }x; my $barrier_stems = qr{ mb__before_atomic| @@ -6008,10 +6598,12 @@ sub process { } } -# check for smp_read_barrier_depends and read_barrier_depends - if (!$file && $line =~ /\b(smp_|)read_barrier_depends\s*\(/) { - WARN("READ_BARRIER_DEPENDS", - "$1read_barrier_depends should only be used in READ_ONCE or DEC Alpha code\n" . $herecurr); +# check for data_race without a comment. + if ($line =~ /\bdata_race\s*\(/) { + if (!ctx_has_comment($first_line, $linenr)) { + WARN("DATA_RACE", + "data_race without comment\n" . $herecurr); + } } # check of hardware specific defines @@ -6053,50 +6645,68 @@ sub process { } } -# Check for __attribute__ packed, prefer __packed - if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(.*\bpacked\b/) { - WARN("PREFER_PACKED", - "__packed is preferred over __attribute__((packed))\n" . $herecurr); - } - -# Check for __attribute__ aligned, prefer __aligned - if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(.*aligned/) { - WARN("PREFER_ALIGNED", - "__aligned(size) is preferred over __attribute__((aligned(size)))\n" . $herecurr); - } - -# Check for __attribute__ section, prefer __section - if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(.*_*section_*\s*\(\s*("[^"]*")/) { - my $old = substr($rawline, $-[1], $+[1] - $-[1]); - my $new = substr($old, 1, -1); - if (WARN("PREFER_SECTION", - "__section(\"$new\") is preferred over __attribute__((section($old)))\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\b__attribute__\s*\(\s*\(\s*_*section_*\s*\(\s*\Q$old\E\s*\)\s*\)\s*\)/__section($new)/; - } - } - -# Check for __attribute__ format(printf, prefer __printf +# Check for compiler attributes if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(\s*format\s*\(\s*printf/) { - if (WARN("PREFER_PRINTF", - "__printf(string-index, first-to-check) is preferred over __attribute__((format(printf, string-index, first-to-check)))\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\b__attribute__\s*\(\s*\(\s*format\s*\(\s*printf\s*,\s*(.*)\)\s*\)\s*\)/"__printf(" . trim($1) . ")"/ex; - + $rawline =~ /\b__attribute__\s*\(\s*($balanced_parens)\s*\)/) { + my $attr = $1; + $attr =~ s/\s*\(\s*(.*)\)\s*/$1/; + + my %attr_list = ( + "alias" => "__alias", + "aligned" => "__aligned", + "always_inline" => "__always_inline", + "assume_aligned" => "__assume_aligned", + "cold" => "__cold", + "const" => "__attribute_const__", + "copy" => "__copy", + "designated_init" => "__designated_init", + "externally_visible" => "__visible", + "format" => "printf|scanf", + "gnu_inline" => "__gnu_inline", + "malloc" => "__malloc", + "mode" => "__mode", + "no_caller_saved_registers" => "__no_caller_saved_registers", + "noclone" => "__noclone", + "noinline" => "noinline", + "nonstring" => "__nonstring", + "noreturn" => "__noreturn", + "packed" => "__packed", + "pure" => "__pure", + "section" => "__section", + "used" => "__used", + "weak" => "__weak" + ); + + while ($attr =~ /\s*(\w+)\s*(${balanced_parens})?/g) { + my $orig_attr = $1; + my $params = ''; + $params = $2 if defined($2); + my $curr_attr = $orig_attr; + $curr_attr =~ s/^[\s_]+|[\s_]+$//g; + if (exists($attr_list{$curr_attr})) { + my $new = $attr_list{$curr_attr}; + if ($curr_attr eq "format" && $params) { + $params =~ /^\s*\(\s*(\w+)\s*,\s*(.*)/; + $new = "__$1\($2"; + } else { + $new = "$new$params"; + } + if (WARN("PREFER_DEFINED_ATTRIBUTE_MACRO", + "Prefer $new over __attribute__(($orig_attr$params))\n" . $herecurr) && + $fix) { + my $remove = "\Q$orig_attr\E" . '\s*' . "\Q$params\E" . '(?:\s*,\s*)?'; + $fixed[$fixlinenr] =~ s/$remove//; + $fixed[$fixlinenr] =~ s/\b__attribute__/$new __attribute__/; + $fixed[$fixlinenr] =~ s/\}\Q$new\E/} $new/; + $fixed[$fixlinenr] =~ s/ __attribute__\s*\(\s*\(\s*\)\s*\)//; + } + } } - } -# Check for __attribute__ format(scanf, prefer __scanf - if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(\s*format\s*\(\s*scanf\b/) { - if (WARN("PREFER_SCANF", - "__scanf(string-index, first-to-check) is preferred over __attribute__((format(scanf, string-index, first-to-check)))\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\b__attribute__\s*\(\s*\(\s*format\s*\(\s*scanf\s*,\s*(.*)\)\s*\)\s*\)/"__scanf(" . trim($1) . ")"/ex; + # Check for __attribute__ unused, prefer __always_unused or __maybe_unused + if ($attr =~ /^_*unused/) { + WARN("PREFER_DEFINED_ATTRIBUTE_MACRO", + "__always_unused or __maybe_unused is preferred over __attribute__((__unused__))\n" . $herecurr); } } @@ -6132,18 +6742,18 @@ sub process { if ($line =~ /(\(\s*$C90_int_types\s*\)\s*)($Constant)\b/) { my $cast = $1; my $const = $2; + my $suffix = ""; + my $newconst = $const; + $newconst =~ s/${Int_type}$//; + $suffix .= 'U' if ($cast =~ /\bunsigned\b/); + if ($cast =~ /\blong\s+long\b/) { + $suffix .= 'LL'; + } elsif ($cast =~ /\blong\b/) { + $suffix .= 'L'; + } if (WARN("TYPECAST_INT_CONSTANT", - "Unnecessary typecast of c90 int constant\n" . $herecurr) && + "Unnecessary typecast of c90 int constant - '$cast$const' could be '$const$suffix'\n" . $herecurr) && $fix) { - my $suffix = ""; - my $newconst = $const; - $newconst =~ s/${Int_type}$//; - $suffix .= 'U' if ($cast =~ /\bunsigned\b/); - if ($cast =~ /\blong\s+long\b/) { - $suffix .= 'LL'; - } elsif ($cast =~ /\blong\b/) { - $suffix .= 'L'; - } $fixed[$fixlinenr] =~ s/\Q$cast\E$const\b/$newconst$suffix/; } } @@ -6203,9 +6813,11 @@ sub process { $specifier = $1; $extension = $2; $qualifier = $3; - if ($extension !~ /[SsBKRraEehMmIiUDdgVCbGNOxtf]/ || + if ($extension !~ /[4SsBKRraEehMmIiUDdgVCbGNOxtf]/ || ($extension eq "f" && - defined $qualifier && $qualifier !~ /^w/)) { + defined $qualifier && $qualifier !~ /^w/) || + ($extension eq "4" && + defined $qualifier && $qualifier !~ /^cc/)) { $bad_specifier = $specifier; last; } @@ -6385,8 +6997,7 @@ sub process { if (defined $cond) { substr($s, 0, length($cond), ''); } - if ($s =~ /^\s*;/ && - $function_name ne 'uninitialized_var') + if ($s =~ /^\s*;/) { WARN("AVOID_EXTERNS", "externs should be avoided in .c files\n" . $herecurr); @@ -6405,17 +7016,13 @@ sub process { } # check for function declarations that have arguments without identifier names -# while avoiding uninitialized_var(x) if (defined $stat && - $stat =~ /^.\s*(?:extern\s+)?$Type\s*(?:($Ident)|\(\s*\*\s*$Ident\s*\))\s*\(\s*([^{]+)\s*\)\s*;/s && - (!defined($1) || - (defined($1) && $1 ne "uninitialized_var")) && - $2 ne "void") { - my $args = trim($2); + $stat =~ /^.\s*(?:extern\s+)?$Type\s*(?:$Ident|\(\s*\*\s*$Ident\s*\))\s*\(\s*([^{]+)\s*\)\s*;/s && + $1 ne "void") { + my $args = trim($1); while ($args =~ m/\s*($Type\s*(?:$Ident|\(\s*\*\s*$Ident?\s*\)\s*$balanced_parens)?)/g) { my $arg = trim($1); - if ($arg =~ /^$Type$/ && - $arg !~ /enum\s+$Ident$/) { + if ($arg =~ /^$Type$/ && $arg !~ /enum\s+$Ident$/) { WARN("FUNCTION_ARGUMENTS", "function definition argument '$arg' should also have an identifier name\n" . $herecurr); } @@ -6451,7 +7058,7 @@ sub process { if (!grep(/$name/, @setup_docs)) { CHK("UNDOCUMENTED_SETUP", - "__setup appears un-documented -- check Documentation/admin-guide/kernel-parameters.rst\n" . $herecurr); + "__setup appears un-documented -- check Documentation/admin-guide/kernel-parameters.txt\n" . $herecurr); } } @@ -6507,7 +7114,7 @@ sub process { } # check for alloc argument mismatch - if ($line =~ /\b(kcalloc|kmalloc_array)\s*\(\s*sizeof\b/) { + if ($line =~ /\b((?:devm_)?(?:kcalloc|kmalloc_array))\s*\(\s*sizeof\b/) { WARN("ALLOC_ARRAY_ARGS", "$1 uses number as first arg, sizeof is generally wrong\n" . $herecurr); } @@ -6533,41 +7140,22 @@ sub process { } } +# check for IS_ENABLED() without CONFIG_<FOO> ($rawline for comments too) + if ($rawline =~ /\bIS_ENABLED\s*\(\s*(\w+)\s*\)/ && $1 !~ /^${CONFIG_}/) { + WARN("IS_ENABLED_CONFIG", + "IS_ENABLED($1) is normally used as IS_ENABLED(${CONFIG_}$1)\n" . $herecurr); + } + # check for #if defined CONFIG_<FOO> || defined CONFIG_<FOO>_MODULE - if ($line =~ /^\+\s*#\s*if\s+defined(?:\s*\(?\s*|\s+)(CONFIG_[A-Z_]+)\s*\)?\s*\|\|\s*defined(?:\s*\(?\s*|\s+)\1_MODULE\s*\)?\s*$/) { + if ($line =~ /^\+\s*#\s*if\s+defined(?:\s*\(?\s*|\s+)(${CONFIG_}[A-Z_]+)\s*\)?\s*\|\|\s*defined(?:\s*\(?\s*|\s+)\1_MODULE\s*\)?\s*$/) { my $config = $1; if (WARN("PREFER_IS_ENABLED", - "Prefer IS_ENABLED(<FOO>) to CONFIG_<FOO> || CONFIG_<FOO>_MODULE\n" . $herecurr) && + "Prefer IS_ENABLED(<FOO>) to ${CONFIG_}<FOO> || ${CONFIG_}<FOO>_MODULE\n" . $herecurr) && $fix) { $fixed[$fixlinenr] = "\+#if IS_ENABLED($config)"; } } -# check for case / default statements not preceded by break/fallthrough/switch - if ($line =~ /^.\s*(?:case\s+(?:$Ident|$Constant)\s*|default):/) { - my $has_break = 0; - my $has_statement = 0; - my $count = 0; - my $prevline = $linenr; - while ($prevline > 1 && ($file || $count < 3) && !$has_break) { - $prevline--; - my $rline = $rawlines[$prevline - 1]; - my $fline = $lines[$prevline - 1]; - last if ($fline =~ /^\@\@/); - next if ($fline =~ /^\-/); - next if ($fline =~ /^.(?:\s*(?:case\s+(?:$Ident|$Constant)[\s$;]*|default):[\s$;]*)*$/); - $has_break = 1 if ($rline =~ /fall[\s_-]*(through|thru)/i); - next if ($fline =~ /^.[\s$;]*$/); - $has_statement = 1; - $count++; - $has_break = 1 if ($fline =~ /\bswitch\b|\b(?:break\s*;[\s$;]*$|exit\s*\(\b|return\b|goto\b|continue\b)/); - } - if (!$has_break && $has_statement) { - WARN("MISSING_BREAK", - "Possible switch case/default not preceded by break or fallthrough comment\n" . $herecurr); - } - } - # check for /* fallthrough */ like comment, prefer fallthrough; my @fallthroughs = ( 'fallthrough', @@ -6683,7 +7271,8 @@ sub process { # check for various structs that are normally const (ops, kgdb, device_tree) # and avoid what seem like struct definitions 'struct foo {' - if ($line !~ /\bconst\b/ && + if (defined($const_structs) && + $line !~ /\bconst\b/ && $line =~ /\bstruct\s+($const_structs)\b(?!\s*\{)/) { WARN("CONST_STRUCT", "struct $1 should normally be const\n" . $herecurr); @@ -6691,12 +7280,14 @@ sub process { # use of NR_CPUS is usually wrong # ignore definitions of NR_CPUS and usage to define arrays as likely right +# ignore designated initializers using NR_CPUS if ($line =~ /\bNR_CPUS\b/ && $line !~ /^.\s*\s*#\s*if\b.*\bNR_CPUS\b/ && $line !~ /^.\s*\s*#\s*define\b.*\bNR_CPUS\b/ && $line !~ /^.\s*$Declare\s.*\[[^\]]*NR_CPUS[^\]]*\]/ && $line !~ /\[[^\]]*\.\.\.[^\]]*NR_CPUS[^\]]*\]/ && - $line !~ /\[[^\]]*NR_CPUS[^\]]*\.\.\.[^\]]*\]/) + $line !~ /\[[^\]]*NR_CPUS[^\]]*\.\.\.[^\]]*\]/ && + $line !~ /^.\s*\.\w+\s*=\s*.*\bNR_CPUS\b/) { WARN("NR_CPUS", "usage of NR_CPUS is often wrong - consider using cpu_possible(), num_possible_cpus(), for_each_possible_cpu(), etc\n" . $herecurr); @@ -6715,6 +7306,17 @@ sub process { "Using $1 should generally have parentheses around the comparison\n" . $herecurr); } +# return sysfs_emit(foo, fmt, ...) fmt without newline + if ($line =~ /\breturn\s+sysfs_emit\s*\(\s*$FuncArg\s*,\s*($String)/ && + substr($rawline, $-[6], $+[6] - $-[6]) !~ /\\n"$/) { + my $offset = $+[6] - 1; + if (WARN("SYSFS_EMIT", + "return sysfs_emit(...) formats should include a terminating newline\n" . $herecurr) && + $fix) { + substr($fixed[$fixlinenr], $offset, 0) = '\\n'; + } + } + # nested likely/unlikely calls if ($line =~ /\b(?:(?:un)?likely)\s*\(\s*!?\s*(IS_ERR(?:_OR_NULL|_VALUE)?|WARN)/) { WARN("LIKELY_MISUSE", @@ -6732,12 +7334,6 @@ sub process { } } -# check for mutex_trylock_recursive usage - if ($line =~ /mutex_trylock_recursive/) { - ERROR("LOCKING", - "recursive locking is bad, do not use this ever.\n" . $herecurr); - } - # check for lockdep_set_novalidate_class if ($line =~ /^.\s*lockdep_set_novalidate_class\s*\(/ || $line =~ /__lockdep_no_validate__\s*\)/ ) { @@ -6900,7 +7496,7 @@ sub process { exit(0); } - # This is not a patch, and we are are in 'no-patch' mode so + # This is not a patch, and we are in 'no-patch' mode so # just keep quiet. if (!$chk_patch && !$is_patch) { exit(0); @@ -6914,9 +7510,33 @@ sub process { if ($signoff == 0) { ERROR("MISSING_SIGN_OFF", "Missing Signed-off-by: line(s)\n"); - } elsif (!$authorsignoff) { - WARN("NO_AUTHOR_SIGN_OFF", - "Missing Signed-off-by: line by nominal patch author '$author'\n"); + } elsif ($authorsignoff != 1) { + # authorsignoff values: + # 0 -> missing sign off + # 1 -> sign off identical + # 2 -> names and addresses match, comments mismatch + # 3 -> addresses match, names different + # 4 -> names match, addresses different + # 5 -> names match, addresses excluding subaddress details (refer RFC 5233) match + + my $sob_msg = "'From: $author' != 'Signed-off-by: $author_sob'"; + + if ($authorsignoff == 0) { + ERROR("NO_AUTHOR_SIGN_OFF", + "Missing Signed-off-by: line by nominal patch author '$author'\n"); + } elsif ($authorsignoff == 2) { + CHK("FROM_SIGN_OFF_MISMATCH", + "From:/Signed-off-by: email comments mismatch: $sob_msg\n"); + } elsif ($authorsignoff == 3) { + WARN("FROM_SIGN_OFF_MISMATCH", + "From:/Signed-off-by: email name mismatch: $sob_msg\n"); + } elsif ($authorsignoff == 4) { + WARN("FROM_SIGN_OFF_MISMATCH", + "From:/Signed-off-by: email address mismatch: $sob_msg\n"); + } elsif ($authorsignoff == 5) { + WARN("FROM_SIGN_OFF_MISMATCH", + "From:/Signed-off-by: email subaddress mismatch: $sob_msg\n"); + } } } diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py new file mode 100755 index 0000000000..3e784cf9f4 --- /dev/null +++ b/scripts/spdxcheck.py @@ -0,0 +1,296 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# Copyright Thomas Gleixner <tglx@linutronix.de> + +from argparse import ArgumentParser +from ply import lex, yacc +import locale +import traceback +import sys +import git +import re +import os + +class ParserException(Exception): + def __init__(self, tok, txt): + self.tok = tok + self.txt = txt + +class SPDXException(Exception): + def __init__(self, el, txt): + self.el = el + self.txt = txt + +class SPDXdata(object): + def __init__(self): + self.license_files = 0 + self.exception_files = 0 + self.licenses = [ ] + self.exceptions = { } + +# Read the spdx data from the LICENSES directory +def read_spdxdata(repo): + + # The subdirectories of LICENSES in the kernel source + # Note: exceptions needs to be parsed as last directory. + license_dirs = [ "preferred", "dual", "deprecated", "exceptions" ] + lictree = repo.head.commit.tree['LICENSES'] + + spdx = SPDXdata() + + for d in license_dirs: + for el in lictree[d].traverse(): + if not os.path.isfile(el.path): + continue + + exception = None + for l in open(el.path).readlines(): + if l.startswith('Valid-License-Identifier:'): + lid = l.split(':')[1].strip().upper() + if lid in spdx.licenses: + raise SPDXException(el, 'Duplicate License Identifier: %s' %lid) + else: + spdx.licenses.append(lid) + + elif l.startswith('SPDX-Exception-Identifier:'): + exception = l.split(':')[1].strip().upper() + spdx.exceptions[exception] = [] + + elif l.startswith('SPDX-Licenses:'): + for lic in l.split(':')[1].upper().strip().replace(' ', '').replace('\t', '').split(','): + if not lic in spdx.licenses: + raise SPDXException(None, 'Exception %s missing license %s' %(exception, lic)) + spdx.exceptions[exception].append(lic) + + elif l.startswith("License-Text:"): + if exception: + if not len(spdx.exceptions[exception]): + raise SPDXException(el, 'Exception %s is missing SPDX-Licenses' %exception) + spdx.exception_files += 1 + else: + spdx.license_files += 1 + break + return spdx + +class id_parser(object): + + reserved = [ 'AND', 'OR', 'WITH' ] + tokens = [ 'LPAR', 'RPAR', 'ID', 'EXC' ] + reserved + + precedence = ( ('nonassoc', 'AND', 'OR'), ) + + t_ignore = ' \t' + + def __init__(self, spdx): + self.spdx = spdx + self.lasttok = None + self.lastid = None + self.lexer = lex.lex(module = self, reflags = re.UNICODE) + # Initialize the parser. No debug file and no parser rules stored on disk + # The rules are small enough to be generated on the fly + self.parser = yacc.yacc(module = self, write_tables = False, debug = False) + self.lines_checked = 0 + self.checked = 0 + self.spdx_valid = 0 + self.spdx_errors = 0 + self.curline = 0 + self.deepest = 0 + + # Validate License and Exception IDs + def validate(self, tok): + id = tok.value.upper() + if tok.type == 'ID': + if not id in self.spdx.licenses: + raise ParserException(tok, 'Invalid License ID') + self.lastid = id + elif tok.type == 'EXC': + if id not in self.spdx.exceptions: + raise ParserException(tok, 'Invalid Exception ID') + if self.lastid not in self.spdx.exceptions[id]: + raise ParserException(tok, 'Exception not valid for license %s' %self.lastid) + self.lastid = None + elif tok.type != 'WITH': + self.lastid = None + + # Lexer functions + def t_RPAR(self, tok): + r'\)' + self.lasttok = tok.type + return tok + + def t_LPAR(self, tok): + r'\(' + self.lasttok = tok.type + return tok + + def t_ID(self, tok): + r'[A-Za-z.0-9\-+]+' + + if self.lasttok == 'EXC': + print(tok) + raise ParserException(tok, 'Missing parentheses') + + tok.value = tok.value.strip() + val = tok.value.upper() + + if val in self.reserved: + tok.type = val + elif self.lasttok == 'WITH': + tok.type = 'EXC' + + self.lasttok = tok.type + self.validate(tok) + return tok + + def t_error(self, tok): + raise ParserException(tok, 'Invalid token') + + def p_expr(self, p): + '''expr : ID + | ID WITH EXC + | expr AND expr + | expr OR expr + | LPAR expr RPAR''' + pass + + def p_error(self, p): + if not p: + raise ParserException(None, 'Unfinished license expression') + else: + raise ParserException(p, 'Syntax error') + + def parse(self, expr): + self.lasttok = None + self.lastid = None + self.parser.parse(expr, lexer = self.lexer) + + def parse_lines(self, fd, maxlines, fname): + self.checked += 1 + self.curline = 0 + try: + for line in fd: + line = line.decode(locale.getpreferredencoding(False), errors='ignore') + self.curline += 1 + if self.curline > maxlines: + break + self.lines_checked += 1 + if line.find("SPDX-License-Identifier:") < 0: + continue + expr = line.split(':')[1].strip() + # Remove trailing comment closure + if line.strip().endswith('*/'): + expr = expr.rstrip('*/').strip() + # Remove trailing xml comment closure + if line.strip().endswith('-->'): + expr = expr.rstrip('-->').strip() + # Special case for SH magic boot code files + if line.startswith('LIST \"'): + expr = expr.rstrip('\"').strip() + self.parse(expr) + self.spdx_valid += 1 + # + # Should we check for more SPDX ids in the same file and + # complain if there are any? + # + break + + except ParserException as pe: + if pe.tok: + col = line.find(expr) + pe.tok.lexpos + tok = pe.tok.value + sys.stdout.write('%s: %d:%d %s: %s\n' %(fname, self.curline, col, pe.txt, tok)) + else: + sys.stdout.write('%s: %d:0 %s\n' %(fname, self.curline, col, pe.txt)) + self.spdx_errors += 1 + +def scan_git_tree(tree): + for el in tree.traverse(): + # Exclude stuff which would make pointless noise + # FIXME: Put this somewhere more sensible + if el.path.startswith("LICENSES"): + continue + if el.path.find("license-rules.rst") >= 0: + continue + if not os.path.isfile(el.path): + continue + with open(el.path, 'rb') as fd: + parser.parse_lines(fd, args.maxlines, el.path) + +def scan_git_subtree(tree, path): + for p in path.strip('/').split('/'): + tree = tree[p] + scan_git_tree(tree) + +if __name__ == '__main__': + + ap = ArgumentParser(description='SPDX expression checker') + ap.add_argument('path', nargs='*', help='Check path or file. If not given full git tree scan. For stdin use "-"') + ap.add_argument('-m', '--maxlines', type=int, default=15, + help='Maximum number of lines to scan in a file. Default 15') + ap.add_argument('-v', '--verbose', action='store_true', help='Verbose statistics output') + args = ap.parse_args() + + # Sanity check path arguments + if '-' in args.path and len(args.path) > 1: + sys.stderr.write('stdin input "-" must be the only path argument\n') + sys.exit(1) + + try: + # Use git to get the valid license expressions + repo = git.Repo(os.getcwd()) + assert not repo.bare + + # Initialize SPDX data + spdx = read_spdxdata(repo) + + # Initialize the parser + parser = id_parser(spdx) + + except SPDXException as se: + if se.el: + sys.stderr.write('%s: %s\n' %(se.el.path, se.txt)) + else: + sys.stderr.write('%s\n' %se.txt) + sys.exit(1) + + except Exception as ex: + sys.stderr.write('FAIL: %s\n' %ex) + sys.stderr.write('%s\n' %traceback.format_exc()) + sys.exit(1) + + try: + if len(args.path) and args.path[0] == '-': + stdin = os.fdopen(sys.stdin.fileno(), 'rb') + parser.parse_lines(stdin, args.maxlines, '-') + else: + if args.path: + for p in args.path: + if os.path.isfile(p): + parser.parse_lines(open(p, 'rb'), args.maxlines, p) + elif os.path.isdir(p): + scan_git_subtree(repo.head.reference.commit.tree, p) + else: + sys.stderr.write('path %s does not exist\n' %p) + sys.exit(1) + else: + # Full git tree scan + scan_git_tree(repo.head.commit.tree) + + if args.verbose: + sys.stderr.write('\n') + sys.stderr.write('License files: %12d\n' %spdx.license_files) + sys.stderr.write('Exception files: %12d\n' %spdx.exception_files) + sys.stderr.write('License IDs %12d\n' %len(spdx.licenses)) + sys.stderr.write('Exception IDs %12d\n' %len(spdx.exceptions)) + sys.stderr.write('\n') + sys.stderr.write('Files checked: %12d\n' %parser.checked) + sys.stderr.write('Lines checked: %12d\n' %parser.lines_checked) + sys.stderr.write('Files with SPDX: %12d\n' %parser.spdx_valid) + sys.stderr.write('Files with errors: %12d\n' %parser.spdx_errors) + + sys.exit(0) + + except Exception as ex: + sys.stderr.write('FAIL: %s\n' %ex) + sys.stderr.write('%s\n' %traceback.format_exc()) + sys.exit(1) |