libctf, serialize: preparatory steps

The new serializer is quite a lot more customizable than the old, because it
can write out BTF as well as CTF: you can ask to write out BTF or fail,
write out CTF if required to avoid information loss, otherwise BTF, or
always write out CTF.

Callers often need to find out whether a dict could be written out as BTF
before deciding how to write it out (because a dict can never be written out
as BTF if it is compressed, a caller might well want to ask if there is
anything else that prevents BTF writeout -- say, slices, conflicting types,
or CTF_K_BIG -- before deciding whether to compress it).  GNU ld will do
this whenever it is passed only BTF sections on the input.

Figuring out whether a dict can be written out as BTF is quite expensive: we
have to traverse all the types and check them, including every member of
every struct.  So we'd rather do that work only once.  This means making a
lot of state once private to ctf_preserialize public enough that another
function can initialize it; and since the whole API is available after
calling this function and before serializing, we should probably arrange
that if we do things we know will invalidate the results of all this
checking, we are forced to do it again.

This commit does that, moving all the existing serialization state into a
new ctf_serialize_t and adding to it.  Several functions grow force_ctf
arguments that allow the caller to force CTF emission even if the type
section looks BTFish: the writeout code and archive creation use this to
force CTF emission if we are compressing, and archive creation uses it
to force CTF emission if a CTF multi-member archive is in use, because
BTF doesn't support archives at all so there's no point maintaining
BTF compatibility in that case.  The ctf_write* functions gain support for
writing out BTF headers as well as CTF, depending on whether what was
ultimately written out was actually BTF or not.

Even more than most commits in this series, there is no way this is
going to compile right now: we're in the middle of a major transition,
completed in the next few commits.

diff --git a/libctf/ctf-archive.c b/libctf/ctf-archive.c
index 2924c2b771697580e52a310538687c8476a8d60d..2fcefa88446a95871c7f0120d1abe56d8ddd9ede 100644 (file)
--- a/libctf/ctf-archive.c
+++ b/libctf/ctf-archive.c
@@ -61,7 +61,8 @@ static ctf_dict_t enosym;
    Updates the first dict in the archive with the errno value.  */
 
 static int
-ctf_arc_preserialize (ctf_dict_t **ctf_dicts, ssize_t ctf_dict_cnt)
+ctf_arc_preserialize (ctf_dict_t **ctf_dicts, ssize_t ctf_dict_cnt,
+                     size_t threshold)
 {
   uint64_t old_parent_strlen, all_strlens = 0;
   ssize_t i;
@@ -72,7 +73,8 @@ ctf_arc_preserialize (ctf_dict_t **ctf_dicts, ssize_t ctf_dict_cnt)
   /* Preserialize everything, doing everything but strtab generation and things
      that depend on that.  */
   for (i = 0; i < ctf_dict_cnt; i++)
-    if (ctf_preserialize (ctf_dicts[i]) < 0)
+    if (ctf_preserialize (ctf_dicts[i], threshold != (size_t) -1
+                         || ctf_dict_cnt > 1) < 0)
       goto err;
 
   ctf_dprintf ("Deduplicating strings.\n");
@@ -134,7 +136,7 @@ ctf_arc_write_fd (int fd, ctf_dict_t **ctf_dicts, size_t ctf_dict_cnt,
   /* Prepare by serializing everything.  Done first because it allocates a lot
      of space and thus is more likely to fail.  */
   if (ctf_dict_cnt > 0 &&
-      (err = ctf_arc_preserialize (ctf_dicts, ctf_dict_cnt)) < 0)
+      (err = ctf_arc_preserialize (ctf_dicts, ctf_dict_cnt, threshold)) < 0)
     return err;
 
   ctf_dprintf ("Writing CTF archive with %lu files\n",

diff --git a/libctf/ctf-create.c b/libctf/ctf-create.c
index 60d83f79838f123b443b0f503fd4489724dc19cd..29750007f5f73934151410361c1495e42fa902bf 100644 (file)
--- a/libctf/ctf-create.c
+++ b/libctf/ctf-create.c
@@ -962,6 +962,8 @@ ctf_set_conflicting (ctf_dict_t *fp, ctf_id_t type, const char *cuname)
                                    dtd->dtd_vlen_size < 65536
                                    ? dtd->dtd_vlen_size : 0);
 
+  fp->ctf_serialize.cs_initialized = 0;
+
   return 0;
 }
 
@@ -1843,6 +1845,8 @@ ctf_add_member_bitfield (ctf_dict_t *fp, ctf_id_t souid, const char *name,
 
   dtd->dtd_last_offset += bit_offset;
 
+  fp->ctf_serialize.cs_initialized = 0;
+
   return 0;
 }
 
@@ -2128,6 +2132,8 @@ ctf_add_funcobjt_sym (ctf_dict_t *fp, int is_function, const char *name, ctf_id_
   if (ctf_lookup_by_sym_or_name (fp, 0, name, 0, is_function) != CTF_ERR)
     return (ctf_set_errno (fp, ECTF_DUPLICATE));
 
+  fp->ctf_serialize.cs_initialized = 0;
+
   return ctf_add_funcobjt_sym_forced (fp, is_function, name, id);
 }
 

diff --git a/libctf/ctf-dedup.c b/libctf/ctf-dedup.c
index 7bd401f25302bead41eaf8ab2ea380564575fd77..b23c3df94e12ef43dd3a077a92dd098ffd02687a 100644 (file)
--- a/libctf/ctf-dedup.c
+++ b/libctf/ctf-dedup.c
@@ -3322,6 +3322,9 @@ ctf_dedup_strings (ctf_dict_t *fp)
   ctf_next_t *i = NULL;
   void *dict;
 
+  if (!fp->ctf_serialize.cs_initialized)
+    return ctf_set_errno (fp, ECTF_NOTSERIALIZED);
+
   str_counts = ctf_dynhash_create (ctf_hash_string, ctf_hash_eq_string,
                                   NULL, NULL);
   if (!str_counts)

diff --git a/libctf/ctf-impl.h b/libctf/ctf-impl.h
index f75494ad229aed114f6857802445c6487e1dd356..d1dc56d1d83f480d743831a8355402897f8be2b9 100644 (file)
--- a/libctf/ctf-impl.h
+++ b/libctf/ctf-impl.h
@@ -365,6 +365,19 @@ typedef struct ctf_dedup
   ctf_dict_t *cd_output;
 } ctf_dedup_t;
 
+/* Serializer state.
+
+   This connects the various stages of serialization (ctf_link_output_is_btf,
+   ctf_preserialize, ctf_serialize).  */
+
+typedef struct ctf_serialize
+{
+  int cs_initialized;          /* If 0, needs reinitialization.  */
+  unsigned char *cs_buf;       /* CTF buffer in mid-serialization.  */
+  size_t cs_buf_size;          /* Length of that buffer.  */
+  int cs_is_btf;
+} ctf_serialize_t;
+
 /* The ctf_dict is the structure used to represent a CTF dictionary to library
    clients, who see it only as an opaque pointer.  Modifications can therefore
    be made freely to this structure without regard to client versioning.  The
@@ -411,9 +424,7 @@ struct ctf_dict
   unsigned char *ctf_buf;        /* Uncompressed CTF data buffer, including
                                     CTFv4 header portion.  */
   size_t ctf_size;               /* Size of CTF header + uncompressed data.  */
-  unsigned char *ctf_serializing_buf; /* CTF buffer in mid-serialization.  */
-  size_t ctf_serializing_buf_size; /* Length of that buffer.  */
-  size_t ctf_serializing_nvars;          /* Number of those vars.  */
+  ctf_serialize_t ctf_serialize;  /* State internal to ctf-serialize.c.  */
   uint32_t *ctf_sxlate;                  /* Translation table for unindexed symtypetab
                                     entries.  */
   unsigned long ctf_nsyms;       /* Number of entries in symtab xlate table.  */
@@ -792,7 +803,7 @@ extern void ctf_str_purge_refs (ctf_dict_t *fp);
 extern void ctf_str_rollback (ctf_dict_t *, ctf_snapshot_id_t);
 extern const ctf_strs_writable_t *ctf_str_write_strtab (ctf_dict_t *);
 
-extern int ctf_preserialize (ctf_dict_t *fp);
+extern int ctf_preserialize (ctf_dict_t *fp, int force_ctf);
 extern void ctf_depreserialize (ctf_dict_t *fp);
 
 extern struct ctf_archive_internal *

diff --git a/libctf/ctf-link.c b/libctf/ctf-link.c
index 1a39ae42116c28f491fe7156f11755b7c30caf06..e1c864782af9a26a8bd8a987f7b6e773b050b166 100644 (file)
--- a/libctf/ctf-link.c
+++ b/libctf/ctf-link.c
@@ -1438,6 +1438,8 @@ ctf_link_add_strtab (ctf_dict_t *fp, ctf_link_strtab_string_f *add_string,
        err = iter_arg.err;
     }
 
+  fp->ctf_serialize.cs_initialized = 0;
+
   if (err)
     ctf_set_errno (fp, err);
 
@@ -1601,6 +1603,9 @@ ctf_link_shuffle_syms (ctf_dict_t *fp)
       ctf_err_warn (fp, 0, err, _("error iterating over shuffled symbols"));
       goto err;
     }
+
+  fp->ctf_serialize.cs_initialized = 0;
+
   return 0;
 
  err:

diff --git a/libctf/ctf-open.c b/libctf/ctf-open.c
index 1946b06c8a2041a5c03d1b1e83189fceaa1de736..be3fb66fb98186b9d1de8711a13e826287bb412f 100644 (file)
--- a/libctf/ctf-open.c
+++ b/libctf/ctf-open.c
@@ -2440,7 +2440,7 @@ ctf_dict_close (ctf_dict_t *fp)
   free (fp->ctf_txlate);
   free (fp->ctf_ptrtab);
   free (fp->ctf_pptrtab);
-  free (fp->ctf_serializing_buf);
+  free (fp->ctf_serialize.cs_buf);
 
   free (fp->ctf_header);
   free (fp);

diff --git a/libctf/ctf-serialize.c b/libctf/ctf-serialize.c
index dbae4e26fd0adcac7acb93e47e8bba662df0615c..ae330e63fb71e20d57833803e1b04e31e034d01b 100644 (file)
--- a/libctf/ctf-serialize.c
+++ b/libctf/ctf-serialize.c
@@ -76,7 +76,7 @@ typedef struct emit_symtypetab_state
    updated later on to change the type ID recorded in this location.  The ref
    may not be emitted if the value is already known and cannot change.
 
-   All refs must point within the ctf_serializing_buf.  */
+   All refs must point within the ctf_serialize.cs_buf.  */
 
 static int
 ctf_type_add_ref (ctf_dict_t *fp, uint32_t *ref)
@@ -92,9 +92,9 @@ ctf_type_add_ref (ctf_dict_t *fp, uint32_t *ref)
   if (!ctf_assert (fp, dtd))
     return 0;
 
-  if (!ctf_assert (fp, fp->ctf_serializing_buf != NULL
-                  && (unsigned char *) ref > fp->ctf_serializing_buf
-                  && (unsigned char *) ref < fp->ctf_serializing_buf + fp->ctf_serializing_buf_size))
+  if (!ctf_assert (fp, fp->ctf_serialize.cs_buf != NULL
+                  && (unsigned char *) ref > fp->ctf_serialize.cs_buf
+                  && (unsigned char *) ref < fp->ctf_serialize.cs_buf + fp->ctf_serialize.cs_buf_size))
     return -1;
 
   /* Simple case: final ID different from what is recorded, but already known.
@@ -1023,14 +1023,19 @@ ctf_emit_type_sect (ctf_dict_t *fp, unsigned char **tptr)
 
 /* Overall serialization.  */
 
-/* Do all aspects of serialization up to strtab writeout and variable table
-   sorting, including final type ID assignment.  The resulting dict will have
-   the LCTF_PRESERIALIZED flag on and must not be modified in any way before
-   serialization.  (This is only lightly enforced, as this feature is internal-
-   only, employed by the linker machinery.)  */
 
 int
-ctf_preserialize (ctf_dict_t *fp)
+/* Do all aspects of serialization up to strtab writeout, including final type
+   ID assignment.  The resulting dict will have the LCTF_PRESERIALIZED flag on
+   and must not be modified in any way before serialization.  (This is only
+   lightly enforced, as this feature is internal-only, employed by the linker
+   machinery.)
+
+   If FORCE_CTF is enabled, always emit CTF in LIBCTF_BTM_POSSIBLE mode, and
+   error in LIBCTF_BTM_BTF mode.  */
+
+int
+ctf_preserialize (ctf_dict_t *fp, int force_ctf)
 {
   ctf_header_t hdr, *hdrp;
   ctf_dvdef_t *dvd;
@@ -1188,8 +1193,8 @@ ctf_preserialize (ctf_dict_t *fp)
   if ((buf = malloc (buf_size)) == NULL)
     return (ctf_set_errno (fp, EAGAIN));
 
-  fp->ctf_serializing_buf = buf;
-  fp->ctf_serializing_buf_size = buf_size;
+  fp->ctf_serialize.cs_buf = buf;
+  fp->ctf_serialize.cs_buf_size = buf_size;
 
   memcpy (buf, &hdr, sizeof (ctf_header_t));
   t = (unsigned char *) buf + sizeof (ctf_header_t) + hdr.cth_objtoff;
@@ -1259,8 +1264,9 @@ ctf_preserialize (ctf_dict_t *fp)
   return 0;
 
  err:
-  fp->ctf_serializing_buf = NULL;
-  fp->ctf_serializing_buf_size = 0;
+  fp->ctf_serialize.cs_initialized = 0;
+  fp->ctf_serialize.cs_buf = NULL;
+  fp->ctf_serialize.cs_buf_size = 0;
 
   free (buf);
   ctf_str_purge_refs (fp);
@@ -1276,11 +1282,10 @@ ctf_depreserialize (ctf_dict_t *fp)
   ctf_str_purge_refs (fp);
   ctf_type_purge_refs (fp);
 
-  free (fp->ctf_serializing_buf);
-  fp->ctf_serializing_buf = NULL;
-  fp->ctf_serializing_vars = NULL;
-  fp->ctf_serializing_buf_size = 0;
-  fp->ctf_serializing_nvars = 0;
+  fp->ctf_serialize.cs_initialized = 0;
+  free (fp->ctf_serialize.cs_buf);
+  fp->ctf_serialize.cs_buf = NULL;
+  fp->ctf_serialize.cs_buf_size = 0;
 
   fp->ctf_flags &= ~(LCTF_NO_STR | LCTF_NO_TYPE);
 }
@@ -1295,11 +1300,11 @@ ctf_depreserialize (ctf_dict_t *fp)
    on visible operation).  */
 
 static unsigned char *
-ctf_serialize (ctf_dict_t *fp, size_t *bufsiz)
+ctf_serialize (ctf_dict_t *fp, size_t *bufsiz, int force_ctf)
 {
   const ctf_strs_writable_t *strtab;
   unsigned char *buf, *newbuf;
-  ctf_header_t *hdrp;
+  ctf_btf_header_t *hdrp;
 
   /* Stop unstable file formats (subject to change) getting out into the
      wild.  */
@@ -1314,13 +1319,11 @@ ctf_serialize (ctf_dict_t *fp, size_t *bufsiz)
 
   /* Preserialize, if we need to.  */
 
-  if (!fp->ctf_serializing_buf)
-    if (ctf_preserialize (fp) < 0)
+  if (!fp->ctf_serialize.cs_buf)
+    if (ctf_preserialize (fp, force_ctf) < 0)
       return NULL;                             /* errno is set for us.  */
 
-  /* UPTODO: prevent writing of BTF dicts when upgrading from CTFv3.  */
-
-  /* Allow string lookup again, now we need it to sort the vartab.  */
+  /* Allow string lookup again.  */
   fp->ctf_flags &= ~LCTF_NO_STR;
 
   /* Construct the final string table and fill out all the string refs with the
@@ -1333,33 +1336,38 @@ ctf_serialize (ctf_dict_t *fp, size_t *bufsiz)
   if ((fp->ctf_flags & LCTF_LINKING) && fp->ctf_parent)
     fp->ctf_header->cth_parent_strlen = fp->ctf_parent->ctf_str[CTF_STRTAB_0].cts_len;
 
-  hdrp = (ctf_header_t *) fp->ctf_serializing_buf;
-
   ctf_dprintf ("Writing strtab for %s\n", ctf_cuname (fp));
   strtab = ctf_str_write_strtab (fp);
 
   if (strtab == NULL)
     goto err;
 
-  if ((newbuf = realloc (fp->ctf_serializing_buf, fp->ctf_serializing_buf_size
+  if ((newbuf = realloc (fp->ctf_serialize.cs_buf, fp->ctf_serialize.cs_buf_size
                         + strtab->cts_len)) == NULL)
     goto oom;
 
-  fp->ctf_serializing_buf = newbuf;
-  memcpy (fp->ctf_serializing_buf + fp->ctf_serializing_buf_size, strtab->cts_strs,
+  fp->ctf_serialize.cs_buf = newbuf;
+  memcpy (fp->ctf_serialize.cs_buf + fp->ctf_serialize.cs_buf_size, strtab->cts_strs,
          strtab->cts_len);
-  hdrp = (ctf_header_t *) fp->ctf_serializing_buf;
-  hdrp->cth_strlen = strtab->cts_len;
-  hdrp->cth_parent_strlen = fp->ctf_header->cth_parent_strlen;
-  fp->ctf_serializing_buf_size += hdrp->cth_strlen;
-  *bufsiz = fp->ctf_serializing_buf_size;
-
-  buf = fp->ctf_serializing_buf;
-
-  fp->ctf_serializing_buf = NULL;
-  fp->ctf_serializing_vars = NULL;
-  fp->ctf_serializing_buf_size = 0;
-  fp->ctf_serializing_nvars = 0;
+
+  hdrp = (ctf_btf_header_t *) fp->ctf_serialize.cs_buf;
+  hdrp->bth_str_len = strtab->cts_len;
+  fp->ctf_serialize.cs_buf_size += hdrp->bth_str_len;
+
+  if (!fp->ctf_serialize.cs_is_btf)
+    {
+      ctf_header_t *ctf_hdrp;
+
+      ctf_hdrp = (ctf_header_t *) (void *) hdrp;
+      ctf_hdrp->cth_parent_strlen = fp->ctf_header->cth_parent_strlen;
+    }
+
+  *bufsiz = fp->ctf_serialize.cs_buf_size;
+
+  buf = fp->ctf_serialize.cs_buf;
+
+  fp->ctf_serialize.cs_buf = NULL;
+  fp->ctf_serialize.cs_buf_size = 0;
   fp->ctf_flags &= ~LCTF_NO_TYPE;
 
   return buf;
@@ -1379,7 +1387,7 @@ err:
    the header uncompressed, and the CTF opening functions work on them without
    manual decompression.)
 
-   No support for (testing-only) endian-flipping.  */
+   No support for (testing-only) endian-flipping or pure BTF writing.  */
 int
 ctf_gzwrite (ctf_dict_t *fp, gzFile fd)
 {
@@ -1388,7 +1396,7 @@ ctf_gzwrite (ctf_dict_t *fp, gzFile fd)
   size_t bufsiz;
   size_t len, written = 0;
 
-  if ((buf = ctf_serialize (fp, &bufsiz)) == NULL)
+  if ((buf = ctf_serialize (fp, &bufsiz, 1)) == NULL)
     return -1;                                 /* errno is set for us.  */
 
   p = buf;
@@ -1420,26 +1428,33 @@ ctf_write_mem (ctf_dict_t *fp, size_t *size, size_t threshold)
   unsigned char *src;
   size_t rawbufsiz;
   size_t alloc_len = 0;
+  size_t hdrlen;
   int uncompressed = 0;
   int flip_endian;
   int rc;
 
   flip_endian = getenv ("LIBCTF_WRITE_FOREIGN_ENDIAN") != NULL;
 
-  if ((rawbuf = ctf_serialize (fp, &rawbufsiz)) == NULL)
+  if ((rawbuf = ctf_serialize (fp, &rawbufsiz,
+                              threshold != (size_t) -1)) == NULL)
     return NULL;                               /* errno is set for us.  */
 
-  if (!ctf_assert (fp, rawbufsiz >= sizeof (ctf_header_t)))
+  if (fp->ctf_serialize.cs_is_btf)
+    hdrlen = sizeof (ctf_btf_header_t);
+  else
+    hdrlen = sizeof (ctf_header_t);
+
+  if (!ctf_assert (fp, rawbufsiz >= hdrlen))
     goto err;
 
-  if (rawbufsiz >= threshold)
+  if (rawbufsiz >= threshold && !fp->ctf_serialize.cs_is_btf)
     alloc_len = compressBound (rawbufsiz - sizeof (ctf_header_t))
       + sizeof (ctf_header_t);
 
   /* Trivial operation if the buffer is too small to bother compressing, and
      we're not doing a forced write-time flip.  */
 
-  if (rawbufsiz < threshold)
+  if (rawbufsiz < threshold || fp->ctf_serialize.cs_is_btf)
     {
       alloc_len = rawbufsiz;
       uncompressed = 1;
@@ -1461,28 +1476,31 @@ ctf_write_mem (ctf_dict_t *fp, size_t *size, size_t threshold)
 
   rawhp = (ctf_header_t *) rawbuf;
   hp = (ctf_header_t *) buf;
-  memcpy (hp, rawbuf, sizeof (ctf_header_t));
-  bp = buf + sizeof (ctf_header_t);
-  *size = sizeof (ctf_header_t);
 
-  if (!uncompressed)
+  memcpy (hp, rawbuf, hdrlen);
+  bp = buf + hdrlen;
+  *size = hdrlen;
+
+  if (!uncompressed && !fp->ctf_serialize.cs_is_btf)
     hp->cth_flags |= CTF_F_COMPRESS;
 
-  src = rawbuf + sizeof (ctf_header_t);
+  src = rawbuf + hdrlen;
 
   if (flip_endian)
     {
-      ctf_flip_header (hp);
-      if (ctf_flip (fp, rawhp, src, 1) < 0)
+      if (ctf_flip_header (hp, fp->ctf_serialize.cs_is_btf, 0) < 0)
+       goto err;                               /* errno is set for us.  */
+      if (ctf_flip (fp, rawhp, src, fp->ctf_serialize.cs_is_btf, 1) < 0)
        goto err;                               /* errno is set for us.  */
     }
 
+  /* Must be CTFv4.  */
   if (!uncompressed)
     {
       size_t compress_len = alloc_len - sizeof (ctf_header_t);
 
       if ((rc = compress (bp, (uLongf *) &compress_len,
-                         src, rawbufsiz - sizeof (ctf_header_t))) != Z_OK)
+                         src, rawbufsiz - hdrlen)) != Z_OK)
        {
          ctf_set_errno (fp, ECTF_COMPRESS);
          ctf_err_warn (fp, 0, 0, _("zlib deflate err: %s"), zError (rc));
@@ -1492,8 +1510,8 @@ ctf_write_mem (ctf_dict_t *fp, size_t *size, size_t threshold)
     }
   else
     {
-      memcpy (bp, src, rawbufsiz - sizeof (ctf_header_t));
-      *size += rawbufsiz - sizeof (ctf_header_t);
+      memcpy (bp, src, rawbufsiz - hdrlen);
+      *size += rawbufsiz - hdrlen;
     }
 
   free (rawbuf);