1 files changed, 52 insertions, 4 deletions

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index e73b4efcfb..cb1b652388 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -224,9 +224,8 @@ our $NonptrType;
 our $Type;
 our $Declare;
 
-our $UTF8	= qr {
-	[\x09\x0A\x0D\x20-\x7E]              # ASCII
-	| [\xC2-\xDF][\x80-\xBF]             # non-overlong 2-byte
+our $NON_ASCII_UTF8	= qr{
+	[\xC2-\xDF][\x80-\xBF]               # non-overlong 2-byte
 	|  \xE0[\xA0-\xBF][\x80-\xBF]        # excluding overlongs
 	| [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}  # straight 3-byte
 	|  \xED[\x80-\x9F][\x80-\xBF]        # excluding surrogates
@@ -235,6 +234,11 @@ our $UTF8	= qr {
 	|  \xF4[\x80-\x8F][\x80-\xBF]{2}     # plane 16
 }x;
 
+our $UTF8	= qr{
+	[\x09\x0A\x0D\x20-\x7E]              # ASCII
+	| $NON_ASCII_UTF8
+}x;
+
 # There are still some false positives, but this catches most
 # common cases.
 our $typeTypedefs = qr{(?x:
@@ -1207,6 +1211,11 @@ sub process {
 	my $signoff = 0;
 	my $is_patch = 0;
 
+	my $in_header_lines = $file ? 0 : 1;
+	my $in_commit_log = 0;		#Scanning lines before patch
+	my $reported_maintainer_file = 0;
+	my $non_utf8_charset = 0;
+
 	our @report = ();
 	our $cnt_lines = 0;
 	our $cnt_error = 0;
@@ -1359,7 +1368,6 @@ sub process {
 		if ($line =~ /^diff --git.*?(\S+)$/) {
 			$realfile = $1;
 			$realfile =~ s@^([^/]*)/@@;
-
 		} elsif ($line =~ /^\+\+\+\s+(\S+)/) {
 			$realfile = $1;
 			$realfile =~ s@^([^/]*)/@@;
@@ -1398,6 +1406,8 @@ sub process {
 		if ($line =~ /^\s*signed-off-by:/i) {
 			# This is a signoff, if ugly, so do not double report.
 			$signoff++;
+			$in_commit_log = 0;
+
 			if (!($line =~ /^\s*Signed-off-by:/)) {
 				ERROR("The correct form is \"Signed-off-by\"\n" .
 					$herecurr);
@@ -1408,6 +1418,22 @@ sub process {
 			}
 		}
 
+# Check if MAINTAINERS is being updated.  If so, there's probably no need to
+# emit the "does MAINTAINERS need updating?" message on file add/move/delete
+		if ($line =~ /^\s*MAINTAINERS\s*\|/) {
+			$reported_maintainer_file = 1;
+		}
+
+# Check for added, moved or deleted files
+		if (!$reported_maintainer_file && !$in_commit_log &&
+		    ($line =~ /^(?:new|deleted) file mode\s*\d+\s*$/ ||
+		     $line =~ /^rename (?:from|to) [\w\/\.\-]+\s*$/ ||
+		     ($line =~ /\{\s*([\w\/\.\-]*)\s*\=\>\s*([\w\/\.\-]*)\s*\}/ &&
+		      (defined($1) || defined($2))))) {
+			$reported_maintainer_file = 1;
+			WARN("added, moved or deleted file(s), does MAINTAINERS need updating?\n" . $herecurr);
+		}
+
 # Check for wrappage within a valid hunk of the file
 		if ($realcnt != 0 && $line !~ m{^(?:\+|-| |\\ No newline|$)}) {
 			ERROR("patch seems to be corrupt (line wrapped?)\n" .
@@ -1426,6 +1452,28 @@ sub process {
 			ERROR("Invalid UTF-8, patch and commit message should be encoded in UTF-8\n" . $hereptr);
 		}
 
+# Check if it's the start of a commit log
+# (not a header line and we haven't seen the patch filename)
+		if ($in_header_lines && $realfile =~ /^$/ &&
+		    !($rawline =~ /^\s+\S/ ||
+		      $rawline =~ /^(commit\b|from\b|[\w-]+:).*$/i)) {
+			$in_header_lines = 0;
+			$in_commit_log = 1;
+		}
+
+# Check if there is UTF-8 in a commit log when a mail header has explicitly
+# declined it, i.e defined some charset where it is missing.
+		if ($in_header_lines &&
+		    $rawline =~ /^Content-Type:.+charset="(.+)".*$/ &&
+		    $1 !~ /utf-8/i) {
+			$non_utf8_charset = 1;
+		}
+
+		if ($in_commit_log && $non_utf8_charset && $realfile =~ /^$/ &&
+		    $rawline =~ /$NON_ASCII_UTF8/) {
+			WARN("8-bit UTF-8 used in possible commit log\n" . $herecurr);
+		}
+
 # ignore non-hunk lines and lines being removed
 		next if (!$hunk_line || $line =~ /^-/);