| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20250807211639.47286-5-corbet@lwn.net>
Date: Thu, 7 Aug 2025 15:16:31 -0600
From: Jonathan Corbet <corbet@....net>
To: linux-doc@...r.kernel.org
Cc: linux-kernel@...r.kernel.org,
Mauro Carvalho Chehab <mchehab+huawei@...nel.org>,
Akira Yokosawa <akiyks@...il.com>,
Jonathan Corbet <corbet@....net>
Subject: [PATCH v2 04/12] docs: kdoc: move the prefix transforms out of dump_struct()
dump_struct is one of the longest functions in the kdoc_parser class,
making it hard to read and reason about. Move the definition of the prefix
transformations out of the function, join them with the definition of
"attribute" (which was defined at the top of the file but only used here),
and reformat the code slightly for shorter line widths.
Just code movement in the end.
Reviewed-by: Mauro Carvalho Chehab <mchehab+huawei@...nel.org>
Signed-off-by: Jonathan Corbet <corbet@....net>
---
scripts/lib/kdoc/kdoc_parser.py | 179 +++++++++++++++++---------------
1 file changed, 96 insertions(+), 83 deletions(-)
diff --git a/scripts/lib/kdoc/kdoc_parser.py b/scripts/lib/kdoc/kdoc_parser.py
index 14ded23f11e0..3d007d200da6 100644
--- a/scripts/lib/kdoc/kdoc_parser.py
+++ b/scripts/lib/kdoc/kdoc_parser.py
@@ -54,8 +54,6 @@ doc_inline_start = KernRe(r'^\s*/\*\*\s*$', cache=False)
doc_inline_sect = KernRe(r'\s*\*\s*(@\s*[\w][\w\.]*\s*):(.*)', cache=False)
doc_inline_end = KernRe(r'^\s*\*/\s*$', cache=False)
doc_inline_oneline = KernRe(r'^\s*/\*\*\s*(@[\w\s]+):\s*(.*)\s*\*/\s*$', cache=False)
-attribute = KernRe(r"__attribute__\s*\(\([a-z0-9,_\*\s\(\)]*\)\)",
- flags=re.I | re.S, cache=False)
export_symbol = KernRe(r'^\s*EXPORT_SYMBOL(_GPL)?\s*\(\s*(\w+)\s*\)\s*', cache=False)
export_symbol_ns = KernRe(r'^\s*EXPORT_SYMBOL_NS(_GPL)?\s*\(\s*(\w+)\s*,\s*"\S+"\)\s*', cache=False)
@@ -74,6 +72,97 @@ doc_begin_func = KernRe(str(doc_com) + # initial " * '
r'(?:[-:].*)?$', # description (not captured)
cache = False)
+#
+# Here begins a long set of transformations to turn structure member prefixes
+# and macro invocations into something we can parse and generate kdoc for.
+#
+struct_attribute = KernRe(r"__attribute__\s*\(\([a-z0-9,_\*\s\(\)]*\)\)",
+ flags=re.I | re.S, cache=False)
+struct_args_pattern = r'([^,)]+)'
+
+struct_prefixes = [
+ # Strip attributes
+ (struct_attribute, ' '),
+ (KernRe(r'\s*__aligned\s*\([^;]*\)', re.S), ' '),
+ (KernRe(r'\s*__counted_by\s*\([^;]*\)', re.S), ' '),
+ (KernRe(r'\s*__counted_by_(le|be)\s*\([^;]*\)', re.S), ' '),
+ (KernRe(r'\s*__packed\s*', re.S), ' '),
+ (KernRe(r'\s*CRYPTO_MINALIGN_ATTR', re.S), ' '),
+ (KernRe(r'\s*____cacheline_aligned_in_smp', re.S), ' '),
+ (KernRe(r'\s*____cacheline_aligned', re.S), ' '),
+ #
+ # Unwrap struct_group macros based on this definition:
+ # __struct_group(TAG, NAME, ATTRS, MEMBERS...)
+ # which has variants like: struct_group(NAME, MEMBERS...)
+ # Only MEMBERS arguments require documentation.
+ #
+ # Parsing them happens on two steps:
+ #
+ # 1. drop struct group arguments that aren't at MEMBERS,
+ # storing them as STRUCT_GROUP(MEMBERS)
+ #
+ # 2. remove STRUCT_GROUP() ancillary macro.
+ #
+ # The original logic used to remove STRUCT_GROUP() using an
+ # advanced regex:
+ #
+ # \bSTRUCT_GROUP(\(((?:(?>[^)(]+)|(?1))*)\))[^;]*;
+ #
+ # with two patterns that are incompatible with
+ # Python re module, as it has:
+ #
+ # - a recursive pattern: (?1)
+ # - an atomic grouping: (?>...)
+ #
+ # I tried a simpler version: but it didn't work either:
+ # \bSTRUCT_GROUP\(([^\)]+)\)[^;]*;
+ #
+ # As it doesn't properly match the end parenthesis on some cases.
+ #
+ # So, a better solution was crafted: there's now a NestedMatch
+ # class that ensures that delimiters after a search are properly
+ # matched. So, the implementation to drop STRUCT_GROUP() will be
+ # handled in separate.
+ #
+ (KernRe(r'\bstruct_group\s*\(([^,]*,)', re.S), r'STRUCT_GROUP('),
+ (KernRe(r'\bstruct_group_attr\s*\(([^,]*,){2}', re.S), r'STRUCT_GROUP('),
+ (KernRe(r'\bstruct_group_tagged\s*\(([^,]*),([^,]*),', re.S), r'struct \1 \2; STRUCT_GROUP('),
+ (KernRe(r'\b__struct_group\s*\(([^,]*,){3}', re.S), r'STRUCT_GROUP('),
+ #
+ # Replace macros
+ #
+ # TODO: use NestedMatch for FOO($1, $2, ...) matches
+ #
+ # it is better to also move those to the NestedMatch logic,
+ # to ensure that parenthesis will be properly matched.
+ #
+ (KernRe(r'__ETHTOOL_DECLARE_LINK_MODE_MASK\s*\(([^\)]+)\)', re.S),
+ r'DECLARE_BITMAP(\1, __ETHTOOL_LINK_MODE_MASK_NBITS)'),
+ (KernRe(r'DECLARE_PHY_INTERFACE_MASK\s*\(([^\)]+)\)', re.S),
+ r'DECLARE_BITMAP(\1, PHY_INTERFACE_MODE_MAX)'),
+ (KernRe(r'DECLARE_BITMAP\s*\(' + struct_args_pattern + r',\s*' + struct_args_pattern + r'\)',
+ re.S), r'unsigned long \1[BITS_TO_LONGS(\2)]'),
+ (KernRe(r'DECLARE_HASHTABLE\s*\(' + struct_args_pattern + r',\s*' + struct_args_pattern + r'\)',
+ re.S), r'unsigned long \1[1 << ((\2) - 1)]'),
+ (KernRe(r'DECLARE_KFIFO\s*\(' + struct_args_pattern + r',\s*' + struct_args_pattern +
+ r',\s*' + struct_args_pattern + r'\)', re.S), r'\2 *\1'),
+ (KernRe(r'DECLARE_KFIFO_PTR\s*\(' + struct_args_pattern + r',\s*' +
+ struct_args_pattern + r'\)', re.S), r'\2 *\1'),
+ (KernRe(r'(?:__)?DECLARE_FLEX_ARRAY\s*\(' + struct_args_pattern + r',\s*' +
+ struct_args_pattern + r'\)', re.S), r'\1 \2[]'),
+ (KernRe(r'DEFINE_DMA_UNMAP_ADDR\s*\(' + struct_args_pattern + r'\)', re.S), r'dma_addr_t \1'),
+ (KernRe(r'DEFINE_DMA_UNMAP_LEN\s*\(' + struct_args_pattern + r'\)', re.S), r'__u32 \1'),
+]
+#
+# Regexes here are guaranteed to have the end limiter matching
+# the start delimiter. Yet, right now, only one replace group
+# is allowed.
+#
+struct_nested_prefixes = [
+ (re.compile(r'\bSTRUCT_GROUP\('), r'\1'),
+]
+
+
#
# A little helper to get rid of excess white space
#
@@ -578,91 +667,15 @@ class KernelDoc:
self.emit_msg(ln,
f"expecting prototype for {decl_type} {self.entry.identifier}. Prototype was for {decl_type} {declaration_name} instead\n")
return
-
- args_pattern = r'([^,)]+)'
-
- sub_prefixes = [
- # Strip attributes
- (attribute, ' '),
- (KernRe(r'\s*__aligned\s*\([^;]*\)', re.S), ' '),
- (KernRe(r'\s*__counted_by\s*\([^;]*\)', re.S), ' '),
- (KernRe(r'\s*__counted_by_(le|be)\s*\([^;]*\)', re.S), ' '),
- (KernRe(r'\s*__packed\s*', re.S), ' '),
- (KernRe(r'\s*CRYPTO_MINALIGN_ATTR', re.S), ' '),
- (KernRe(r'\s*____cacheline_aligned_in_smp', re.S), ' '),
- (KernRe(r'\s*____cacheline_aligned', re.S), ' '),
-
- # Unwrap struct_group macros based on this definition:
- # __struct_group(TAG, NAME, ATTRS, MEMBERS...)
- # which has variants like: struct_group(NAME, MEMBERS...)
- # Only MEMBERS arguments require documentation.
- #
- # Parsing them happens on two steps:
- #
- # 1. drop struct group arguments that aren't at MEMBERS,
- # storing them as STRUCT_GROUP(MEMBERS)
- #
- # 2. remove STRUCT_GROUP() ancillary macro.
- #
- # The original logic used to remove STRUCT_GROUP() using an
- # advanced regex:
- #
- # \bSTRUCT_GROUP(\(((?:(?>[^)(]+)|(?1))*)\))[^;]*;
- #
- # with two patterns that are incompatible with
- # Python re module, as it has:
- #
- # - a recursive pattern: (?1)
- # - an atomic grouping: (?>...)
- #
- # I tried a simpler version: but it didn't work either:
- # \bSTRUCT_GROUP\(([^\)]+)\)[^;]*;
- #
- # As it doesn't properly match the end parenthesis on some cases.
- #
- # So, a better solution was crafted: there's now a NestedMatch
- # class that ensures that delimiters after a search are properly
- # matched. So, the implementation to drop STRUCT_GROUP() will be
- # handled in separate.
-
- (KernRe(r'\bstruct_group\s*\(([^,]*,)', re.S), r'STRUCT_GROUP('),
- (KernRe(r'\bstruct_group_attr\s*\(([^,]*,){2}', re.S), r'STRUCT_GROUP('),
- (KernRe(r'\bstruct_group_tagged\s*\(([^,]*),([^,]*),', re.S), r'struct \1 \2; STRUCT_GROUP('),
- (KernRe(r'\b__struct_group\s*\(([^,]*,){3}', re.S), r'STRUCT_GROUP('),
-
- # Replace macros
- #
- # TODO: use NestedMatch for FOO($1, $2, ...) matches
- #
- # it is better to also move those to the NestedMatch logic,
- # to ensure that parenthesis will be properly matched.
-
- (KernRe(r'__ETHTOOL_DECLARE_LINK_MODE_MASK\s*\(([^\)]+)\)', re.S), r'DECLARE_BITMAP(\1, __ETHTOOL_LINK_MODE_MASK_NBITS)'),
- (KernRe(r'DECLARE_PHY_INTERFACE_MASK\s*\(([^\)]+)\)', re.S), r'DECLARE_BITMAP(\1, PHY_INTERFACE_MODE_MAX)'),
- (KernRe(r'DECLARE_BITMAP\s*\(' + args_pattern + r',\s*' + args_pattern + r'\)', re.S), r'unsigned long \1[BITS_TO_LONGS(\2)]'),
- (KernRe(r'DECLARE_HASHTABLE\s*\(' + args_pattern + r',\s*' + args_pattern + r'\)', re.S), r'unsigned long \1[1 << ((\2) - 1)]'),
- (KernRe(r'DECLARE_KFIFO\s*\(' + args_pattern + r',\s*' + args_pattern + r',\s*' + args_pattern + r'\)', re.S), r'\2 *\1'),
- (KernRe(r'DECLARE_KFIFO_PTR\s*\(' + args_pattern + r',\s*' + args_pattern + r'\)', re.S), r'\2 *\1'),
- (KernRe(r'(?:__)?DECLARE_FLEX_ARRAY\s*\(' + args_pattern + r',\s*' + args_pattern + r'\)', re.S), r'\1 \2[]'),
- (KernRe(r'DEFINE_DMA_UNMAP_ADDR\s*\(' + args_pattern + r'\)', re.S), r'dma_addr_t \1'),
- (KernRe(r'DEFINE_DMA_UNMAP_LEN\s*\(' + args_pattern + r'\)', re.S), r'__u32 \1'),
- ]
-
- # Regexes here are guaranteed to have the end limiter matching
- # the start delimiter. Yet, right now, only one replace group
- # is allowed.
-
- sub_nested_prefixes = [
- (re.compile(r'\bSTRUCT_GROUP\('), r'\1'),
- ]
-
+ #
+ # Go through the list of members applying all of our transformations.
+ #
members = trim_private_members(members)
- for search, sub in sub_prefixes:
+ for search, sub in struct_prefixes:
members = search.sub(sub, members)
nested = NestedMatch()
-
- for search, sub in sub_nested_prefixes:
+ for search, sub in struct_nested_prefixes:
members = nested.sub(search, sub, members)
# Keeps the original declaration as-is
--
2.50.1
Powered by blists - more mailing lists