scripts/checkpatch.pl: Resync with v5.16

This resyncs us with the version found in v5.16 of the Linux kernel with
the following exceptions:
- Keep our u-boot specific tests / code area.
- Change the location of checkpatch.rst
- Drop the "use strscpy" test as we don't have that, but do have strlcpy
  and want that used now.
- Keep debug/printf in the list for $logFunctions

This also syncs the spdxcheck.py tool and all the associated
documentation.
S
Signed-off-by: Simon Glass <sjg@chromium.org>

1 files changed, 98 insertions, 47 deletions

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index cf59e2b..fe13e26 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -63,6 +63,7 @@ my $min_conf_desc_length = 4;
 my $spelling_file = "$D/spelling.txt";
 my $codespell = 0;
 my $codespellfile = "/usr/share/codespell/dictionary.txt";
+my $user_codespellfile = "";
 my $conststructsfile = "$D/const_structs.checkpatch";
 my $u_boot = 0;
 my $docsfile = "$D/../doc/develop/checkpatch.rst";
@@ -131,7 +132,7 @@ Options:
   --ignore-perl-version      override checking of perl version.  expect
                              runtime errors.
   --codespell                Use the codespell dictionary for spelling/typos
-                             (default:/usr/share/codespell/dictionary.txt)
+                             (default:$codespellfile)
   --codespellfile            Use this codespell dictionary
   --typedefsfile             Read additional types from this file
   --color[=WHEN]             Use colors 'always', 'never', or only when output
@@ -319,7 +320,7 @@ GetOptions(
 	'debug=s'	=> \%debug,
 	'test-only=s'	=> \$tst_only,
 	'codespell!'	=> \$codespell,
-	'codespellfile=s'	=> \$codespellfile,
+	'codespellfile=s'	=> \$user_codespellfile,
 	'typedefsfile=s'	=> \$typedefsfile,
 	'u-boot'	=> \$u_boot,
 	'color=s'	=> \$color,
@@ -328,9 +329,32 @@ GetOptions(
 	'kconfig-prefix=s'	=> \${CONFIG_},
 	'h|help'	=> \$help,
 	'version'	=> \$help
-) or help(1);
+) or $help = 2;
+
+if ($user_codespellfile) {
+	# Use the user provided codespell file unconditionally
+	$codespellfile = $user_codespellfile;
+} elsif (!(-f $codespellfile)) {
+	# If /usr/share/codespell/dictionary.txt is not present, try to find it
+	# under codespell's install directory: <codespell_root>/data/dictionary.txt
+	if (($codespell || $help) && which("codespell") ne "" && which("python") ne "") {
+		my $python_codespell_dict = << "EOF";
+
+import os.path as op
+import codespell_lib
+codespell_dir = op.dirname(codespell_lib.__file__)
+codespell_file = op.join(codespell_dir, 'data', 'dictionary.txt')
+print(codespell_file, end='')
+EOF
+
+		my $codespell_dict = `python -c "$python_codespell_dict" 2> /dev/null`;
+		$codespellfile = $codespell_dict if (-f $codespell_dict);
+	}
+}
 
-help(0) if ($help);
+# $help is 1 if either -h, --help or --version is passed as option - exitcode: 0
+# $help is 2 if invalid option is passed - exitcode: 1
+help($help - 1) if ($help);
 
 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);
@@ -492,7 +516,8 @@ our $Attribute	= qr{
 			____cacheline_aligned|
 			____cacheline_aligned_in_smp|
 			____cacheline_internodealigned_in_smp|
-			__weak
+			__weak|
+			__alloc_size\s*\(\s*\d+\s*(?:,\s*\d+\s*)?\)
 		  }x;
 our $Modifier;
 our $Inline	= qr{inline|__always_inline|noinline|__inline|__inline__};
@@ -504,7 +529,7 @@ our $Binary	= qr{(?i)0b[01]+$Int_type?};
 our $Hex	= qr{(?i)0x[0-9a-f]+$Int_type?};
 our $Int	= qr{[0-9]+$Int_type?};
 our $Octal	= qr{0[0-7]+$Int_type?};
-our $String	= qr{"[X\t]*"};
+our $String	= qr{(?:\b[Lu])?"[X\t]*"};
 our $Float_hex	= qr{(?i)0x[0-9a-f]+p-?[0-9]+[fl]?};
 our $Float_dec	= qr{(?i)(?:[0-9]+\.[0-9]*|[0-9]*\.[0-9]+)(?:e-?[0-9]+)?[fl]?};
 our $Float_int	= qr{(?i)[0-9]+e-?[0-9]+[fl]?};
@@ -1089,10 +1114,10 @@ sub is_maintained_obsolete {
 sub is_SPDX_License_valid {
 	my ($license) = @_;
 
-	return 1 if (!$tree || which("python") eq "" || !(-e "$root/scripts/spdxcheck.py") || !(-e "$gitroot"));
+	return 1 if (!$tree || which("python3") eq "" || !(-x "$root/scripts/spdxcheck.py") || !(-e "$gitroot"));
 
 	my $root_path = abs_path($root);
-	my $status = `cd "$root_path"; echo "$license" | python scripts/spdxcheck.py -`;
+	my $status = `cd "$root_path"; echo "$license" | scripts/spdxcheck.py -`;
 	return 0 if ($status ne "");
 	return 1;
 }
@@ -1186,7 +1211,8 @@ sub git_commit_info {
 #		    git log --format='%H %s' -1 $line |
 #		    echo "commit $(cut -c 1-12,41-)"
 #		done
-	} elsif ($lines[0] =~ /^fatal: ambiguous argument '$commit': unknown revision or path not in the working tree\./) {
+	} elsif ($lines[0] =~ /^fatal: ambiguous argument '$commit': unknown revision or path not in the working tree\./ ||
+		 $lines[0] =~ /^fatal: bad object $commit/) {
 		$id = undef;
 	} else {
 		$id = substr($lines[0], 0, 12);
@@ -2697,6 +2723,8 @@ sub process {
 	my $reported_maintainer_file = 0;
 	my $non_utf8_charset = 0;
 
+	my $last_git_commit_id_linenr = -1;
+
 	my $last_blank_line = 0;
 	my $last_coalesced_string_linenr = -1;
 
@@ -3019,10 +3047,10 @@ sub process {
 					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) {
+					if (lc $email_address eq lc $author_address && $email_name eq $author_name) {
 						$author_sob = $ctx;
 						$authorsignoff = 2;
-					} elsif ($email_address eq $author_address) {
+					} elsif (lc $email_address eq lc $author_address) {
 						$author_sob = $ctx;
 						$authorsignoff = 3;
 					} elsif ($email_name eq $author_name) {
@@ -3280,10 +3308,20 @@ sub process {
 		}
 
 # Check for git id commit length and improperly formed commit descriptions
-		if ($in_commit_log && !$commit_log_possible_stack_dump &&
+# A correctly formed commit description is:
+#    commit <SHA-1 hash length 12+ chars> ("Complete commit subject")
+# with the commit subject '("' prefix and '")' suffix
+# This is a fairly compilicated block as it tests for what appears to be
+# bare SHA-1 hash with  minimum length of 5.  It also avoids several types of
+# possible SHA-1 matches.
+# A commit match can span multiple lines so this block attempts to find a
+# complete typical commit on a maximum of 3 lines
+		if ($perl_version_ok &&
+		    $in_commit_log && !$commit_log_possible_stack_dump &&
 		    $line !~ /^\s*(?:Link|Patchwork|http|https|BugLink|base-commit):/i &&
 		    $line !~ /^This reverts commit [0-9a-f]{7,40}/ &&
-		    ($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i ||
+		    (($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i ||
+		      ($line =~ /\bcommit\s*$/i && defined($rawlines[$linenr]) && $rawlines[$linenr] =~ /^\s*[0-9a-f]{5,}\b/i)) ||
 		     ($line =~ /(?:\s|^)[0-9a-f]{12,40}(?:[\s"'\(\[]|$)/i &&
 		      $line !~ /[\<\[][0-9a-f]{12,40}[\>\]]/i &&
 		      $line !~ /\bfixes:\s*[0-9a-f]{12,40}/i))) {
@@ -3293,49 +3331,56 @@ sub process {
 			my $long = 0;
 			my $case = 1;
 			my $space = 1;
-			my $hasdesc = 0;
-			my $hasparens = 0;
 			my $id = '0123456789ab';
 			my $orig_desc = "commit description";
 			my $description = "";
+			my $herectx = $herecurr;
+			my $has_parens = 0;
+			my $has_quotes = 0;
+
+			my $input = $line;
+			if ($line =~ /(?:\bcommit\s+[0-9a-f]{5,}|\bcommit\s*$)/i) {
+				for (my $n = 0; $n < 2; $n++) {
+					if ($input =~ /\bcommit\s+[0-9a-f]{5,}\s*($balanced_parens)/i) {
+						$orig_desc = $1;
+						$has_parens = 1;
+						# Always strip leading/trailing parens then double quotes if existing
+						$orig_desc = substr($orig_desc, 1, -1);
+						if ($orig_desc =~ /^".*"$/) {
+							$orig_desc = substr($orig_desc, 1, -1);
+							$has_quotes = 1;
+						}
+						last;
+					}
+					last if ($#lines < $linenr + $n);
+					$input .= " " . trim($rawlines[$linenr + $n]);
+					$herectx .= "$rawlines[$linenr + $n]\n";
+				}
+				$herectx = $herecurr if (!$has_parens);
+			}
 
-			if ($line =~ /\b(c)ommit\s+([0-9a-f]{5,})\b/i) {
+			if ($input =~ /\b(c)ommit\s+([0-9a-f]{5,})\b/i) {
 				$init_char = $1;
 				$orig_commit = lc($2);
-			} elsif ($line =~ /\b([0-9a-f]{12,40})\b/i) {
+				$short = 0 if ($input =~ /\bcommit\s+[0-9a-f]{12,40}/i);
+				$long = 1 if ($input =~ /\bcommit\s+[0-9a-f]{41,}/i);
+				$space = 0 if ($input =~ /\bcommit [0-9a-f]/i);
+				$case = 0 if ($input =~ /\b[Cc]ommit\s+[0-9a-f]{5,40}[^A-F]/);
+			} elsif ($input =~ /\b([0-9a-f]{12,40})\b/i) {
 				$orig_commit = lc($1);
 			}
 
-			$short = 0 if ($line =~ /\bcommit\s+[0-9a-f]{12,40}/i);
-			$long = 1 if ($line =~ /\bcommit\s+[0-9a-f]{41,}/i);
-			$space = 0 if ($line =~ /\bcommit [0-9a-f]/i);
-			$case = 0 if ($line =~ /\b[Cc]ommit\s+[0-9a-f]{5,40}[^A-F]/);
-			if ($line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("([^"]+)"\)/i) {
-				$orig_desc = $1;
-				$hasparens = 1;
-			} elsif ($line =~ /\bcommit\s+[0-9a-f]{5,}\s*$/i &&
-				 defined $rawlines[$linenr] &&
-				 $rawlines[$linenr] =~ /^\s*\("([^"]+)"\)/) {
-				$orig_desc = $1;
-				$hasparens = 1;
-			} elsif ($line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("[^"]+$/i &&
-				 defined $rawlines[$linenr] &&
-				 $rawlines[$linenr] =~ /^\s*[^"]+"\)/) {
-				$line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("([^"]+)$/i;
-				$orig_desc = $1;
-				$rawlines[$linenr] =~ /^\s*([^"]+)"\)/;
-				$orig_desc .= " " . $1;
-				$hasparens = 1;
-			}
-
 			($id, $description) = git_commit_info($orig_commit,
 							      $id, $orig_desc);
 
 			if (defined($id) &&
-			   ($short || $long || $space || $case || ($orig_desc ne $description) || !$hasparens)) {
+			    ($short || $long || $space || $case || ($orig_desc ne $description) || !$has_quotes) &&
+			    $last_git_commit_id_linenr != $linenr - 1) {
 				ERROR("GIT_COMMIT_ID",
-				      "Please use git commit description style 'commit <12+ chars of sha1> (\"<title line>\")' - ie: '${init_char}ommit $id (\"$description\")'\n" . $herecurr);
+				      "Please use git commit description style 'commit <12+ chars of sha1> (\"<title line>\")' - ie: '${init_char}ommit $id (\"$description\")'\n" . $herectx);
 			}
+			#don't report the next line if this line ends in commit and the sha1 hash is the next line
+			$last_git_commit_id_linenr = $linenr if ($line =~ /\bcommit\s*$/i);
 		}
 
 # Check for added, moved or deleted files
@@ -4542,6 +4587,7 @@ sub process {
 			#   XXX(foo);
 			#   EXPORT_SYMBOL(something_foo);
 			my $name = $1;
+			$name =~ s/^\s*($Ident).*/$1/;
 			if ($stat =~ /^(?:.\s*}\s*\n)?.([A-Z_]+)\s*\(\s*($Ident)/ &&
 			    $name =~ /^${Ident}_$2/) {
 #print "FOO C name<$name>\n";
@@ -5475,9 +5521,13 @@ sub process {
 			}
 		}
 
-#goto labels aren't indented, allow a single space however
-		if ($line=~/^.\s+[A-Za-z\d_]+:(?![0-9]+)/ and
-		   !($line=~/^. [A-Za-z\d_]+:/) and !($line=~/^.\s+default:/)) {
+# check that goto labels aren't indented (allow a single space indentation)
+# and ignore bitfield definitions like foo:1
+# Strictly, labels can have whitespace after the identifier and before the :
+# but this is not allowed here as many ?: uses would appear to be labels
+		if ($sline =~ /^.\s+[A-Za-z_][A-Za-z\d_]*:(?!\s*\d+)/ &&
+		    $sline !~ /^. [A-Za-z\d_][A-Za-z\d_]*:/ &&
+		    $sline !~ /^.\s+default:/) {
 			if (WARN("INDENTED_LABEL",
 				 "labels should not be indented\n" . $herecurr) &&
 			    $fix) {
@@ -5572,7 +5622,7 @@ sub process {
 # Return of what appears to be an errno should normally be negative
 		if ($sline =~ /\breturn(?:\s*\(+\s*|\s+)(E[A-Z]+)(?:\s*\)+\s*|\s*)[;:,]/) {
 			my $name = $1;
-			if ($name ne 'EOF' && $name ne 'ERROR') {
+			if ($name ne 'EOF' && $name ne 'ERROR' && $name !~ /^EPOLL/) {
 				WARN("USE_NEGATIVE_ERRNO",
 				     "return of an errno should typically be negative (ie: return -$1)\n" . $herecurr);
 			}
@@ -6242,7 +6292,8 @@ sub process {
 		}
 
 # concatenated string without spaces between elements
-		if ($line =~ /$String[A-Za-z0-9_]/ || $line =~ /[A-Za-z0-9_]$String/) {
+		if ($line =~ /$String[A-Z_]/ ||
+		    ($line =~ /([A-Za-z0-9_]+)$String/ && $1 !~ /^[Lu]$/)) {
 			if (CHK("CONCATENATED_STRING",
 				"Concatenated strings should use spaces between elements\n" . $herecurr) &&
 			    $fix) {
@@ -6255,7 +6306,7 @@ sub process {
 		}
 
 # uncoalesced string fragments
-		if ($line =~ /$String\s*"/) {
+		if ($line =~ /$String\s*[Lu]?"/) {
 			if (WARN("STRING_FRAGMENTS",
 				 "Consecutive strings are generally better as a single string\n" . $herecurr) &&
 			    $fix) {