From 92215e7a801da7b89037a185c98f5ebb86a415b9 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 29 Dec 2022 18:15:00 +0900 Subject: kbuild: rename cmd_$@ to savedcmd_$@ in *.cmd files The cmd-check macro compares $(cmd_$@) and $(cmd_$1), but a pitfall is that you cannot use cmd_ as the variable name for the command. For example, the following code will not work in the top Makefile or ./Kbuild. quiet_cmd_foo = GEN $@ cmd_foo = touch $@ targets += foo foo: FORCE $(call if_changed,foo) In this case, both $@ and $1 are expanded to 'foo', so $(cmd_check) is always empty. We do not need to use the same prefix for cmd_$@ and cmd_$1. Rename the former to savedcmd_$@. Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier --- scripts/basic/fixdep.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'scripts/basic/fixdep.c') diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c index f932aeaba71a..37782a632494 100644 --- a/scripts/basic/fixdep.c +++ b/scripts/basic/fixdep.c @@ -70,7 +70,7 @@ * * It first generates a line * - * cmd_ = + * savedcmd_ = * * and then basically copies the ..d file to stdout, in the * process filtering out the dependency on autoconf.h and adding @@ -343,7 +343,7 @@ int main(int argc, char *argv[]) target = argv[2]; cmdline = argv[3]; - printf("cmd_%s := %s\n\n", target, cmdline); + printf("savedcmd_%s := %s\n\n", target, cmdline); buf = read_file(depfile); parse_dep_file(buf, target); -- cgit v1.2.3-70-g09d2 From bc6df812a1529ab0cbac7f17ac6c4f4aff2a8bbf Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 7 Jan 2023 18:18:16 +0900 Subject: fixdep: parse Makefile more correctly to handle comments etc. fixdep parses dependency files (*.d) emitted by the compiler. *.d files are Makefiles describing the dependencies of the main source file. fixdep understands minimal Makefile syntax. It works well enough for GCC and Clang, but not for rustc. This commit improves the parser a little more for better processing comments, escape sequences, etc. My main motivation is to drop comments. rustc may output comments (e.g. env-dep). Currentyly, rustc build rules invoke sed to remove comments, but it is more efficient to do it in fixdep. Signed-off-by: Masahiro Yamada Acked-by: Miguel Ojeda Tested-by: Miguel Ojeda --- scripts/basic/fixdep.c | 173 ++++++++++++++++++++++++++++++++++--------------- 1 file changed, 119 insertions(+), 54 deletions(-) (limited to 'scripts/basic/fixdep.c') diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c index 37782a632494..f5a51770eb74 100644 --- a/scripts/basic/fixdep.c +++ b/scripts/basic/fixdep.c @@ -94,6 +94,7 @@ #include #include #include +#include #include #include #include @@ -251,75 +252,139 @@ static int is_ignored_file(const char *s, int len) * assignments are parsed not only by make, but also by the rather simple * parser in scripts/mod/sumversion.c. */ -static void parse_dep_file(char *m, const char *target) +static void parse_dep_file(char *p, const char *target) { - char *p; - int is_last, is_target; - int saw_any_target = 0; - int is_first_dep = 0; - void *buf; - - while (1) { - /* Skip any "white space" */ - while (*m == ' ' || *m == '\\' || *m == '\n') - m++; - - if (!*m) + bool saw_any_target = false; + bool is_target = true; + bool is_source = false; + bool need_parse; + char *q, saved_c; + + while (*p) { + /* handle some special characters first. */ + switch (*p) { + case '#': + /* + * skip comments. + * rustc may emit comments to dep-info. + */ + p++; + while (*p != '\0' && *p != '\n') { + /* + * escaped newlines continue the comment across + * multiple lines. + */ + if (*p == '\\') + p++; + p++; + } + continue; + case ' ': + case '\t': + /* skip whitespaces */ + p++; + continue; + case '\\': + /* + * backslash/newline combinations continue the + * statement. Skip it just like a whitespace. + */ + if (*(p + 1) == '\n') { + p += 2; + continue; + } break; - - /* Find next "white space" */ - p = m; - while (*p && *p != ' ' && *p != '\\' && *p != '\n') + case '\n': + /* + * Makefiles use a line-based syntax, where the newline + * is the end of a statement. After seeing a newline, + * we expect the next token is a target. + */ p++; - is_last = (*p == '\0'); - /* Is the token we found a target name? */ - is_target = (*(p-1) == ':'); - /* Don't write any target names into the dependency file */ - if (is_target) { - /* The /next/ file is the first dependency */ - is_first_dep = 1; - } else if (!is_ignored_file(m, p - m)) { - *p = '\0'; - + is_target = true; + continue; + case ':': /* - * Do not list the source file as dependency, so that - * kbuild is not confused if a .c file is rewritten - * into .S or vice versa. Storing it in source_* is - * needed for modpost to compute srcversions. + * assume the first dependency after a colon as the + * source file. */ - if (is_first_dep) { + p++; + is_target = false; + is_source = true; + continue; + } + + /* find the end of the token */ + q = p; + while (*q != ' ' && *q != '\t' && *q != '\n' && *q != '#' && *q != ':') { + if (*q == '\\') { /* - * If processing the concatenation of multiple - * dependency files, only process the first - * target name, which will be the original - * source name, and ignore any other target - * names, which will be intermediate temporary - * files. + * backslash/newline combinations work like as + * a whitespace, so this is the end of token. */ - if (!saw_any_target) { - saw_any_target = 1; - printf("source_%s := %s\n\n", - target, m); - printf("deps_%s := \\\n", target); + if (*(q + 1) == '\n') + break; + + /* escaped special characters */ + if (*(q + 1) == '#' || *(q + 1) == ':') { + memmove(p + 1, p, q - p); + p++; } - is_first_dep = 0; - } else { - printf(" %s \\\n", m); + + q++; } - buf = read_file(m); - parse_config_file(buf); - free(buf); + if (*q == '\0') + break; + q++; } - if (is_last) - break; + /* Just discard the target */ + if (is_target) { + p = q; + continue; + } + + saved_c = *q; + *q = '\0'; + need_parse = false; /* - * Start searching for next token immediately after the first - * "whitespace" character that follows this token. + * Do not list the source file as dependency, so that kbuild is + * not confused if a .c file is rewritten into .S or vice versa. + * Storing it in source_* is needed for modpost to compute + * srcversions. */ - m = p + 1; + if (is_source) { + /* + * The DT build rule concatenates multiple dep files. + * When processing them, only process the first source + * name, which will be the original one, and ignore any + * other source names, which will be intermediate + * temporary files. + */ + if (!saw_any_target) { + saw_any_target = true; + printf("source_%s := %s\n\n", target, p); + printf("deps_%s := \\\n", target); + need_parse = true; + } + } else if (!is_ignored_file(p, q - p)) { + printf(" %s \\\n", p); + need_parse = true; + } + + if (need_parse) { + void *buf; + + buf = read_file(p); + parse_config_file(buf); + free(buf); + } + + is_source = false; + *q = saved_c; + p = q; } if (!saw_any_target) { -- cgit v1.2.3-70-g09d2 From 871d657385466d380133e457fc86672bedf14cd9 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 7 Jan 2023 18:18:18 +0900 Subject: fixdep: refactor hash table lookup Change the hash table code so it will be easier to add the second table. Signed-off-by: Masahiro Yamada Reviewed-by: Miguel Ojeda Tested-by: Miguel Ojeda --- scripts/basic/fixdep.c | 47 +++++++++++++++++++++++++---------------------- 1 file changed, 25 insertions(+), 22 deletions(-) (limited to 'scripts/basic/fixdep.c') diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c index f5a51770eb74..74f90a0deeb9 100644 --- a/scripts/basic/fixdep.c +++ b/scripts/basic/fixdep.c @@ -113,7 +113,7 @@ struct item { }; #define HASHSZ 256 -static struct item *hashtab[HASHSZ]; +static struct item *config_hashtab[HASHSZ]; static unsigned int strhash(const char *str, unsigned int sz) { @@ -125,25 +125,11 @@ static unsigned int strhash(const char *str, unsigned int sz) return hash; } -/* - * Lookup a value in the configuration string. - */ -static int is_defined_config(const char *name, int len, unsigned int hash) -{ - struct item *aux; - - for (aux = hashtab[hash % HASHSZ]; aux; aux = aux->next) { - if (aux->hash == hash && aux->len == len && - memcmp(aux->name, name, len) == 0) - return 1; - } - return 0; -} - /* * Add a new value to the configuration string. */ -static void define_config(const char *name, int len, unsigned int hash) +static void add_to_hashtable(const char *name, int len, unsigned int hash, + struct item *hashtab[]) { struct item *aux = malloc(sizeof(*aux) + len); @@ -158,17 +144,34 @@ static void define_config(const char *name, int len, unsigned int hash) hashtab[hash % HASHSZ] = aux; } +/* + * Lookup a string in the hash table. If found, just return true. + * If not, add it to the hashtable and return false. + */ +static bool in_hashtable(const char *name, int len, struct item *hashtab[]) +{ + struct item *aux; + unsigned int hash = strhash(name, len); + + for (aux = hashtab[hash % HASHSZ]; aux; aux = aux->next) { + if (aux->hash == hash && aux->len == len && + memcmp(aux->name, name, len) == 0) + return true; + } + + add_to_hashtable(name, len, hash, hashtab); + + return false; +} + /* * Record the use of a CONFIG_* word. */ static void use_config(const char *m, int slen) { - unsigned int hash = strhash(m, slen); - - if (is_defined_config(m, slen, hash)) - return; + if (in_hashtable(m, slen, config_hashtab)) + return; - define_config(m, slen, hash); /* Print out a dependency path from a symbol name. */ printf(" $(wildcard include/config/%.*s) \\\n", slen, m); } -- cgit v1.2.3-70-g09d2 From faa91c472be8ffa3121c9db803d3e529d48e246a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 7 Jan 2023 18:18:19 +0900 Subject: fixdep: avoid parsing the same file over again The dep files (*.d files) emitted by C compilers usually contain the deduplicated list of included files. One exceptional case is when a header is included by the -include command line option, and also by #include directive. For example, the top Makefile adds the command line option, "-include $(srctree)/include/linux/kconfig.h". You do not need to include in every source file. In fact, include/linux/kconfig.h is listed twice in many .*.cmd files due to include/linux/xarray.h having "#include ". I did not fix that since it is a small redundancy. However, this is more annoying for rustc. rustc emits the dependency for each emission type. For example, cmd_rustc_library emits dep-info, obj, and metadata. So, the emitted *.d file contains the dependency for those 3 targets, which makes fixdep parse the same file 3 times. $ grep rust/alloc/raw_vec.rs rust/.alloc.o.cmd rust/alloc/raw_vec.rs \ rust/alloc/raw_vec.rs \ rust/alloc/raw_vec.rs \ To skip the second parsing, this commit adds a hash table for parsed files, just like we did for CONFIG options. Signed-off-by: Masahiro Yamada Acked-by: Miguel Ojeda Tested-by: Miguel Ojeda Reviewed-by: Vincenzo Palazzo --- scripts/basic/fixdep.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'scripts/basic/fixdep.c') diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c index 74f90a0deeb9..e22e689de61e 100644 --- a/scripts/basic/fixdep.c +++ b/scripts/basic/fixdep.c @@ -113,7 +113,7 @@ struct item { }; #define HASHSZ 256 -static struct item *config_hashtab[HASHSZ]; +static struct item *config_hashtab[HASHSZ], *file_hashtab[HASHSZ]; static unsigned int strhash(const char *str, unsigned int sz) { @@ -365,6 +365,10 @@ static void parse_dep_file(char *p, const char *target) * name, which will be the original one, and ignore any * other source names, which will be intermediate * temporary files. + * + * rustc emits the same dependency list for each + * emission type. It is enough to list the source name + * just once. */ if (!saw_any_target) { saw_any_target = true; @@ -372,7 +376,8 @@ static void parse_dep_file(char *p, const char *target) printf("deps_%s := \\\n", target); need_parse = true; } - } else if (!is_ignored_file(p, q - p)) { + } else if (!is_ignored_file(p, q - p) && + !in_hashtable(p, q - p, file_hashtab)) { printf(" %s \\\n", p); need_parse = true; } -- cgit v1.2.3-70-g09d2 From 93c656de8da8b53317bd88ecb7cce592310995d8 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 7 Jan 2023 18:18:20 +0900 Subject: fixdep: do not parse *.rlib, *.rmeta, *.so fixdep is designed only for parsing text files. read_file() appends a terminating null byte ('\0') and parse_config_file() calls strstr() to search for CONFIG options. rustc outputs *.rlib, *.rmeta, *.so to dep-info. fixdep needs them in the dependency, but there is no point in parsing such binary files. Signed-off-by: Masahiro Yamada Reviewed-by: Miguel Ojeda Tested-by: Miguel Ojeda --- scripts/basic/fixdep.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'scripts/basic/fixdep.c') diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c index e22e689de61e..fa562806c2be 100644 --- a/scripts/basic/fixdep.c +++ b/scripts/basic/fixdep.c @@ -250,6 +250,15 @@ static int is_ignored_file(const char *s, int len) str_ends_with(s, len, "include/generated/autoksyms.h"); } +/* Do not parse these files */ +static int is_no_parse_file(const char *s, int len) +{ + /* rustc may list binary files in dep-info */ + return str_ends_with(s, len, ".rlib") || + str_ends_with(s, len, ".rmeta") || + str_ends_with(s, len, ".so"); +} + /* * Important: The below generated source_foo.o and deps_foo.o variable * assignments are parsed not only by make, but also by the rather simple @@ -382,7 +391,7 @@ static void parse_dep_file(char *p, const char *target) need_parse = true; } - if (need_parse) { + if (need_parse && !is_no_parse_file(p, q - p)) { void *buf; buf = read_file(p); -- cgit v1.2.3-70-g09d2