check-sysctl-docs

#!/usr/bin/gawk -f
# SPDX-License-Identifier: GPL-2.0

# Script to check sysctl documentation against source files
#
# Copyright (c) 2020 Stephen Kitt

# Example invocation:
#	scripts/check-sysctl-docs -vtable="kernel" \
#		Documentation/admin-guide/sysctl/kernel.rst \
#		$(git grep -l register_sysctl_)
#
# Specify -vdebug=1 to see debugging information

BEGIN {
    if (!table) {
	print "Please specify the table to look for using the table variable" > "/dev/stderr"
	exit 1
    }
}

# The following globals are used:
# children: maps ctl_table names and procnames to child ctl_table names
# documented: maps documented entries (each key is an entry)
# entries: maps ctl_table names and procnames to counts (so
#          enumerating the subkeys for a given ctl_table lists its
#          procnames)
# files: maps procnames to source file names
# paths: maps ctl_path names to paths
# curpath: the name of the current ctl_path struct
# curtable: the name of the current ctl_table struct
# curentry: the name of the current proc entry (procname when parsing
#           a ctl_table, constructed path when parsing a ctl_path)


# Remove punctuation from the given value
function trimpunct(value) {
    while (value ~ /^["&]/) {
	value = substr(value, 2)
    }
    while (value ~ /[]["&,}]$/) {
	value = substr(value, 1, length(value) - 1)
    }
    return value
}

# Print the information for the given entry
function printentry(entry) {
    seen[entry]++
    printf "* %s from %s", entry, file[entry]
    if (documented[entry]) {
	printf " (documented)"
    }
    print ""
}


# Stage 1: build the list of documented entries
FNR == NR && /^=+$/ {
    if (prevline ~ /Documentation for/) {
	# This is the main title
	next
    }

    # The previous line is a section title, parse it
    $0 = prevline
    if (debug) print "Parsing " $0
    inbrackets = 0
    for (i = 1; i <= NF; i++) {
	if (length($i) == 0) {
	    continue
	}
	if (!inbrackets && substr($i, 1, 1) == "(") {
	    inbrackets = 1
	}
	if (!inbrackets) {
	    token = trimpunct($i)
	    if (length(token) > 0 && token != "and") {
		if (debug) print trimpunct($i)
		documented[trimpunct($i)]++
	    }
	}
	if (inbrackets && substr($i, length($i), 1) == ")") {
	    inbrackets = 0
	}
    }
}

FNR == NR {
    prevline = $0
    next
}


# Stage 2: process each file and find all sysctl tables
BEGINFILE {
    delete children
    delete entries
    delete paths
    curpath = ""
    curtable = ""
    curentry = ""
    if (debug) print "Processing file " FILENAME
}

/^static struct ctl_path/ {
    match($0, /static struct ctl_path ([^][]+)/, tables)
    curpath = tables[1]
    if (debug) print "Processing path " curpath
}

/^static struct ctl_table/ {
    match($0, /static struct ctl_table ([^][]+)/, tables)
    curtable = tables[1]
    if (debug) print "Processing table " curtable
}

/^};$/ {
    curpath = ""
    curtable = ""
    curentry = ""
}

curpath && /\.procname[\t ]*=[\t ]*".+"/ {
    match($0, /.procname[\t ]*=[\t ]*"([^"]+)"/, names)
    if (curentry) {
	curentry = curentry "/" names[1]
    } else {
	curentry = names[1]
    }
    if (debug) print "Setting path " curpath " to " curentry
    paths[curpath] = curentry
}

curtable && /\.procname[\t ]*=[\t ]*".+"/ {
    match($0, /.procname[\t ]*=[\t ]*"([^"]+)"/, names)
    curentry = names[1]
    if (debug) print "Adding entry " curentry " to table " curtable
    entries[curtable][curentry]++
    file[curentry] = FILENAME
}

/\.child[\t ]*=/ {
    child = trimpunct($NF)
    if (debug) print "Linking child " child " to table " curtable " entry " curentry
    children[curtable][curentry] = child
}

/register_sysctl_table\(.*\)/ {
    match($0, /register_sysctl_table\(([^)]+)\)/, tables)
    if (debug) print "Registering table " tables[1]
    if (children[tables[1]][table]) {
	for (entry in entries[children[tables[1]][table]]) {
	    printentry(entry)
	}
    }
}

/register_sysctl_paths\(.*\)/ {
    match($0, /register_sysctl_paths\(([^)]+), ([^)]+)\)/, tables)
    if (debug) print "Attaching table " tables[2] " to path " tables[1]
    if (paths[tables[1]] == table) {
	for (entry in entries[tables[2]]) {
	    printentry(entry)
	}
    }
    split(paths[tables[1]], components, "/")
    if (length(components) > 1 && components[1] == table) {
	# Count the first subdirectory as seen
	seen[components[2]]++
    }
}


END {
    for (entry in documented) {
	if (!seen[entry]) {
	    print "No implementation for " entry
	}
    }
}