Merge tag 'docs-4.18' of git://git.lwn.net/linux

Pull documentation updates from Jonathan Corbet:
 "There's been a fair amount of work in the docs tree this time around,
  including:

   - Extensive RST conversions and organizational work in the
     memory-management docs thanks to Mike Rapoport.

   - An update of Documentation/features from Andrea Parri and a script
     to keep it updated.

   - Various LICENSES updates from Thomas, along with a script to check
     SPDX tags.

   - Work to fix dangling references to documentation files; this
     involved a fair number of one-liner comment changes outside of
     Documentation/

  ... and the usual list of documentation improvements, typo fixes, etc"

* tag 'docs-4.18' of git://git.lwn.net/linux: (103 commits)
  Documentation: document hung_task_panic kernel parameter
  docs/admin-guide/mm: add high level concepts overview
  docs/vm: move ksm and transhuge from "user" to "internals" section.
  docs: Use the kerneldoc comments for memalloc_no*()
  doc: document scope NOFS, NOIO APIs
  docs: update kernel versions and dates in tables
  docs/vm: transhuge: split userspace bits to admin-guide/mm/transhuge
  docs/vm: transhuge: minor updates
  docs/vm: transhuge: change sections order
  Documentation: arm: clean up Marvell Berlin family info
  Documentation: gpio: driver: Fix a typo and some odd grammar
  docs: ranoops.rst: fix location of ramoops.txt
  scripts/documentation-file-ref-check: rewrite it in perl with auto-fix mode
  docs: uio-howto.rst: use a code block to solve a warning
  mm, THP, doc: Add document for thp_swpout/thp_swpout_fallback
  w1: w1_io.c: fix a kernel-doc warning
  Documentation/process/posting: wrap text at 80 cols
  docs: admin-guide: add cgroup-v2 documentation
  Revert "Documentation/features/vm: Remove arch support status file for 'pte_special'"
  Documentation: refcount-vs-atomic: Update reference to LKMM doc.
  ...

1 files changed, 113 insertions, 12 deletions

diff --git a/scripts/documentation-file-ref-check b/scripts/documentation-file-ref-check
index bc1659900e89..2520bc14ffac 100755
--- a/scripts/documentation-file-ref-check
+++ b/scripts/documentation-file-ref-check
@@ -1,15 +1,116 @@
-#!/bin/sh
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+#
 # Treewide grep for references to files under Documentation, and report
 # non-existing files in stderr.
 
-for f in $(git ls-files); do
-	for ref in $(grep -ho "Documentation/[A-Za-z0-9_.,~/*+-]*" "$f"); do
-		# presume trailing . and , are not part of the name
-		ref=${ref%%[.,]}
-
-		# use ls to handle wildcards
-		if ! ls $ref >/dev/null 2>&1; then
-			echo "$f: $ref" >&2
-		fi
-	done
-done
+use warnings;
+use strict;
+use Getopt::Long qw(:config no_auto_abbrev);
+
+my $scriptname = $0;
+$scriptname =~ s,.*/([^/]+/),$1,;
+
+# Parse arguments
+my $help = 0;
+my $fix = 0;
+
+GetOptions(
+	'fix' => \$fix,
+	'h|help|usage' => \$help,
+);
+
+if ($help != 0) {
+    print "$scriptname [--help] [--fix-rst]\n";
+    exit -1;
+}
+
+# Step 1: find broken references
+print "Finding broken references. This may take a while...  " if ($fix);
+
+my %broken_ref;
+
+open IN, "git grep 'Documentation/'|"
+     or die "Failed to run git grep";
+while (<IN>) {
+	next if (!m/^([^:]+):(.*)/);
+
+	my $f = $1;
+	my $ln = $2;
+
+	# Makefiles contain nasty expressions to parse docs
+	next if ($f =~ m/Makefile/);
+	# Skip this script
+	next if ($f eq $scriptname);
+
+	if ($ln =~ m,\b(\S*)(Documentation/[A-Za-z0-9\_\.\,\~/\*+-]*),) {
+		my $prefix = $1;
+		my $ref = $2;
+		my $base = $2;
+
+		$ref =~ s/[\,\.]+$//;
+
+		my $fulref = "$prefix$ref";
+
+		$fulref =~ s/^(\<file|ref)://;
+		$fulref =~ s/^[\'\`]+//;
+		$fulref =~ s,^\$\(.*\)/,,;
+		$base =~ s,.*/,,;
+
+		# Remove URL false-positives
+		next if ($fulref =~ m/^http/);
+
+		# Check if exists, evaluating wildcards
+		next if (grep -e, glob("$ref $fulref"));
+
+		if ($fix) {
+			if (!($ref =~ m/(devicetree|scripts|Kconfig|Kbuild)/)) {
+				$broken_ref{$ref}++;
+			}
+		} else {
+			print STDERR "$f: $fulref\n";
+		}
+	}
+}
+
+exit 0 if (!$fix);
+
+# Step 2: Seek for file name alternatives
+print "Auto-fixing broken references. Please double-check the results\n";
+
+foreach my $ref (keys %broken_ref) {
+	my $new =$ref;
+
+	# get just the basename
+	$new =~ s,.*/,,;
+
+	# Seek for the same name on another place, as it may have been moved
+	my $f="";
+
+	$f = qx(find . -iname $new) if ($new);
+
+	# usual reason for breakage: file renamed to .rst
+	if (!$f) {
+		$new =~ s/\.txt$/.rst/;
+		$f=qx(find . -iname $new) if ($new);
+	}
+
+	my @find = split /\s+/, $f;
+
+	if (!$f) {
+		print STDERR "ERROR: Didn't find a replacement for $ref\n";
+	} elsif (scalar(@find) > 1) {
+		print STDERR "WARNING: Won't auto-replace, as found multiple files close to $ref:\n";
+		foreach my $j (@find) {
+			$j =~ s,^./,,;
+			print STDERR "    $j\n";
+		}
+	} else {
+		$f = $find[0];
+		$f =~ s,^./,,;
+		print "INFO: Replacing $ref to $f\n";
+		foreach my $j (qx(git grep -l $ref)) {
+			qx(sed "s\@$ref\@$f\@g" -i $j);
+		}
+	}
+}