filter: basic write hooking infrastructure

Filters can now call hook_write and unhook_write if they want to
redirect writing to stdout to a different function. This saves us from
potential file descriptor pipes and other less efficient mechanisms.

We do this instead of replacing the call in html_raw because some places
stdlib's printf functions are used (ui-patch or within git itself),
which has its own internal buffering, which makes it difficult to
interlace our function calls. So, we dlsym libc's write and then
override it in the link stage.

While we're at it, we move considerations of argument count into the
generic new filter handler.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

4 files changed, 67 insertions, 23 deletions

diff --git a/cgit.c b/cgit.c
index 4f31e58..725fd65 100644
--- a/cgit.c
+++ b/cgit.c
@@ -904,6 +904,8 @@ int main(int argc, const char **argv)
         const char *path;
         int err, ttl;
 
+        cgit_init_filters();
+
         prepare_context(&ctx);
         cgit_repolist.length = 0;
         cgit_repolist.count = 0;
diff --git a/cgit.h b/cgit.h
index 893c38f..519d2af 100644
--- a/cgit.h
+++ b/cgit.h
@@ -61,13 +61,13 @@ struct cgit_filter {
         int (*close)(struct cgit_filter *);
         void (*fprintf)(struct cgit_filter *, FILE *, const char *prefix);
         void (*cleanup)(struct cgit_filter *);
+        int argument_count;
 };
 
 struct cgit_exec_filter {
         struct cgit_filter base;
         char *cmd;
         char **argv;
-        int extra_args;
         int old_stdout;
         int pipe_fh[2];
         int pid;
@@ -357,6 +357,7 @@ extern void cgit_fprintf_filter(struct cgit_filter *filter, FILE *f, const char
 extern void cgit_exec_filter_init(struct cgit_exec_filter *filter, char *cmd, char **argv);
 extern struct cgit_filter *cgit_new_filter(const char *cmd, filter_type filtertype);
 extern void cgit_cleanup_filters(void);
+extern void cgit_init_filters(void);
 
 extern void cgit_prepare_repo_env(struct cgit_repo * repo);
 
diff --git a/cgit.mk b/cgit.mk
index 19a76e7..9d6dea8 100644
--- a/cgit.mk
+++ b/cgit.mk
@@ -61,6 +61,8 @@ $(CGIT_VERSION_OBJS): $(CGIT_PREFIX)VERSION
 $(CGIT_VERSION_OBJS): EXTRA_CPPFLAGS = \
         -DCGIT_VERSION='"$(CGIT_VERSION)"'
 
+CGIT_LIBS += -ldl
+
 
 # Git handles dependencies using ":=" so dependencies in CGIT_OBJ are not
 # handled by that and we must handle them ourselves.
@@ -88,4 +90,4 @@ $(CGIT_OBJS): %.o: %.c GIT-CFLAGS $(CGIT_PREFIX)CGIT-CFLAGS $(missing_dep_dirs)
         $(QUIET_CC)$(CC) -o $*.o -c $(dep_args) $(ALL_CFLAGS) $(EXTRA_CPPFLAGS) $(CGIT_CFLAGS) $<
 
 $(CGIT_PREFIX)cgit: $(CGIT_OBJS) GIT-LDFLAGS $(GITLIBS)
-        $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
+        $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) $(CGIT_LIBS)
diff --git a/filter.c b/filter.c
index 30bc74b..f5a5992 100644
--- a/filter.c
+++ b/filter.c
@@ -12,6 +12,11 @@
 #include <unistd.h>
 #include <string.h>
 #include <stdlib.h>
+#include <dlfcn.h>
+
+static ssize_t (*libc_write)(int fd, const void *buf, size_t count);
+static ssize_t (*filter_write)(struct cgit_filter *base, const void *buf, size_t count) = NULL;
+static struct cgit_filter *current_write_filter = NULL;
 
 static inline void reap_filter(struct cgit_filter *filter)
 {
@@ -32,12 +37,43 @@ void cgit_cleanup_filters(void)
         }
 }
 
+void cgit_init_filters(void)
+{
+        libc_write = dlsym(RTLD_NEXT, "write");
+        if (!libc_write)
+                die("Could not locate libc's write function");
+}
+
+ssize_t write(int fd, const void *buf, size_t count)
+{
+        if (fd != STDOUT_FILENO || !filter_write)
+                return libc_write(fd, buf, count);
+        return filter_write(current_write_filter, buf, count);
+}
+
+static inline void hook_write(struct cgit_filter *filter, ssize_t (*new_write)(struct cgit_filter *base, const void *buf, size_t count))
+{
+        /* We want to avoid buggy nested patterns. */
+        assert(filter_write == NULL);
+        assert(current_write_filter == NULL);
+        current_write_filter = filter;
+        filter_write = new_write;
+}
+
+static inline void unhook_write()
+{
+        assert(filter_write != NULL);
+        assert(current_write_filter != NULL);
+        filter_write = NULL;
+        current_write_filter = NULL;
+}
+
 static int open_exec_filter(struct cgit_filter *base, va_list ap)
 {
         struct cgit_exec_filter *filter = (struct cgit_exec_filter *) base;
         int i;
 
-        for (i = 0; i < filter->extra_args; i++)
+        for (i = 0; i < filter->base.argument_count; i++)
                 filter->argv[i+1] = va_arg(ap, char *);
 
         filter->old_stdout = chk_positive(dup(STDOUT_FILENO),
@@ -74,7 +110,7 @@ static int close_exec_filter(struct cgit_filter *base)
         die("Subprocess %s exited abnormally", filter->cmd);
 
 done:
-        for (i = 0; i < filter->extra_args; i++)
+        for (i = 0; i < filter->base.argument_count; i++)
                 filter->argv[i+1] = NULL;
         return 0;
 
@@ -99,7 +135,7 @@ static void cleanup_exec_filter(struct cgit_filter *base)
         }
 }
 
-static struct cgit_filter *new_exec_filter(const char *cmd, filter_type filtertype)
+static struct cgit_filter *new_exec_filter(const char *cmd, int argument_count)
 {
         struct cgit_exec_filter *f;
         int args_size = 0;
@@ -107,20 +143,8 @@ static struct cgit_filter *new_exec_filter(const char *cmd, filter_type filterty
         f = xmalloc(sizeof(*f));
         /* We leave argv for now and assign it below. */
         cgit_exec_filter_init(f, xstrdup(cmd), NULL);
-
-        switch (filtertype) {
-                case SOURCE:
-                case ABOUT:
-                        f->extra_args = 1;
-                        break;
-
-                case COMMIT:
-                default:
-                        f->extra_args = 0;
-                        break;
-        }
-
-        args_size = (2 + f->extra_args) * sizeof(char *);
+        f->base.argument_count = argument_count;
+        args_size = (2 + argument_count) * sizeof(char *);
         f->argv = xmalloc(args_size);
         memset(f->argv, 0, args_size);
         f->argv[0] = f->cmd;
@@ -136,6 +160,8 @@ void cgit_exec_filter_init(struct cgit_exec_filter *filter, char *cmd, char **ar
         filter->base.cleanup = cleanup_exec_filter;
         filter->cmd = cmd;
         filter->argv = argv;
+        /* The argument count for open_filter is zero by default, unless called from new_filter, above. */
+        filter->base.argument_count = 0;
 }
 
 int cgit_open_filter(struct cgit_filter *filter, ...)
@@ -162,7 +188,7 @@ void cgit_fprintf_filter(struct cgit_filter *filter, FILE *f, const char *prefix
 
 static const struct {
         const char *prefix;
-        struct cgit_filter *(*ctor)(const char *cmd, filter_type filtertype);
+        struct cgit_filter *(*ctor)(const char *cmd, int argument_count);
 } filter_specs[] = {
         { "exec", new_exec_filter },
 };
@@ -172,6 +198,8 @@ struct cgit_filter *cgit_new_filter(const char *cmd, filter_type filtertype)
         char *colon;
         int i;
         size_t len;
+        int argument_count;
+
         if (!cmd || !cmd[0])
                 return NULL;
 
@@ -184,16 +212,27 @@ struct cgit_filter *cgit_new_filter(const char *cmd, filter_type filtertype)
         if (len == 1)
                 colon = NULL;
 
+        switch (filtertype) {
+                case SOURCE:
+                case ABOUT:
+                        argument_count = 1;
+                        break;
+
+                case COMMIT:
+                default:
+                        argument_count = 0;
+                        break;
+        }
+
         /* If no prefix is given, exec filter is the default. */
         if (!colon)
-                return new_exec_filter(cmd, filtertype);
+                return new_exec_filter(cmd, argument_count);
 
         for (i = 0; i < ARRAY_SIZE(filter_specs); i++) {
                 if (len == strlen(filter_specs[i].prefix) &&
                     !strncmp(filter_specs[i].prefix, cmd, len))
-                        return filter_specs[i].ctor(colon + 1, filtertype);
+                        return filter_specs[i].ctor(colon + 1, argument_count);
         }
 
         die("Invalid filter type: %.*s", (int) len, cmd);
 }
-