mirror/binutils-gdb
2
0
Fork 0
mirror of https://sourceware.org/git/binutils-gdb.git synced 2024-12-27 04:52:05 +08:00
Code Issues Packages Projects Releases Wiki Activity
43a61d7d3e
binutils-gdb/libctf/ctf-lookup.c
Nick Alcock 688d28f621 libctf, next: introduce new class of easier-to-use iterators 
The libctf machinery currently only provides one way to iterate over its
data structures: ctf_*_iter functions that take a callback and an arg
and repeatedly call it.

This *works*, but if you are doing a lot of iteration it is really quite
inconvenient: you have to package up your local variables into
structures over and over again and spawn lots of little functions even
if it would be clearer in a single run of code.  Look at ctf-string.c
for an extreme example of how unreadable this can get, with
three-line-long functions proliferating wildly.

The deduplicator takes this to the Nth level. It iterates over a whole
bunch of things: if we'd had to use _iter-class iterators for all of
them there would be twenty additional functions in the deduplicator
alone, for no other reason than that the iterator API requires it.

Let's do something better. strtok_r gives us half the design: generators
in a number of other languages give us the other half.

The *_next API allows you to iterate over CTF-like entities in a single
function using a normal while loop. e.g. here we are iterating over all
the types in a dict:

ctf_next_t *i = NULL;
int *hidden;
ctf_id_t id;

while ((id = ctf_type_next (fp, &i, &hidden, 1)) != CTF_ERR)
  {
    /* do something with 'hidden' and 'id' */
  }
if (ctf_errno (fp) != ECTF_NEXT_END)
    /* iteration error */

Here we are walking through the members of a struct with CTF ID
'struct_type':

ctf_next_t *i = NULL;
ssize_t offset;
const char *name;
ctf_id_t membtype;

while ((offset = ctf_member_next (fp, struct_type, &i, &name,
                                  &membtype)) >= 0
  {
    /* do something with offset, name, and membtype */
  }
if (ctf_errno (fp) != ECTF_NEXT_END)
    /* iteration error */

Like every other while loop, this means you have access to all the local
variables outside the loop while inside it, with no need to tiresomely
package things up in structures, move the body of the loop into a
separate function, etc, as you would with an iterator taking a callback.

ctf_*_next allocates 'i' for you on first entry (when it must be NULL),
and frees and NULLs it and returns a _next-dependent flag value when the
iteration is over: the fp errno is set to ECTF_NEXT_END when the
iteartion ends normally.  If you want to exit early, call
ctf_next_destroy on the iterator.  You can copy iterators using
ctf_next_copy, which copies their current iteration position so you can
remember loop positions and go back to them later (or ctf_next_destroy
them if you don't need them after all).

Each _next function returns an always-likely-to-be-useful property of
the thing being iterated over, and takes pointers to parameters for the
others: with very few exceptions all those parameters can be NULLs if
you're not interested in them, so e.g. you can iterate over only the
offsets of members of a structure this way:

while ((offset = ctf_member_next (fp, struct_id, &i, NULL, NULL)) >= 0)

If you pass an iterator in use by one iteration function to another one,
you get the new error ECTF_NEXT_WRONGFUN back; if you try to change
ctf_file_t in mid-iteration, you get ECTF_NEXT_WRONGFP back.

Internally the ctf_next_t remembers the iteration function in use,
various sizes and increments useful for almost all iterations, then
uses unions to overlap the actual entities being iterated over to keep
ctf_next_t size down.

Iterators available in the public API so far (all tested in actual use
in the deduplicator):

/* Iterate over the members of a STRUCT or UNION, returning each member's
   offset and optionally name and member type in turn.  On end-of-iteration,
   returns -1.  */
ssize_t
ctf_member_next (ctf_file_t *fp, ctf_id_t type, ctf_next_t **it,
                 const char **name, ctf_id_t *membtype);

/* Iterate over the members of an enum TYPE, returning each enumerand's
   NAME or NULL at end of iteration or error, and optionally passing
   back the enumerand's integer VALue.  */
const char *
ctf_enum_next (ctf_file_t *fp, ctf_id_t type, ctf_next_t **it,
              int *val);

/* Iterate over every type in the given CTF container (not including
   parents), optionally including non-user-visible types, returning
   each type ID and optionally the hidden flag in turn. Returns CTF_ERR
   on end of iteration or error.  */
ctf_id_t
ctf_type_next (ctf_file_t *fp, ctf_next_t **it, int *flag,
               int want_hidden);

/* Iterate over every variable in the given CTF container, in arbitrary
   order, returning the name and type of each variable in turn.  The
   NAME argument is not optional.  Returns CTF_ERR on end of iteration
   or error.  */
ctf_id_t
ctf_variable_next (ctf_file_t *fp, ctf_next_t **it, const char **name);

/* Iterate over all CTF files in an archive, returning each dict in turn as a
   ctf_file_t, and NULL on error or end of iteration.  It is the caller's
   responsibility to close it.  Parent dicts may be skipped.  Regardless of
   whether they are skipped or not, the caller must ctf_import the parent if
   need be.  */
ctf_file_t *
ctf_archive_next (const ctf_archive_t *wrapper, ctf_next_t **it,
                  const char **name, int skip_parent, int *errp);

ctf_label_next is prototyped but not implemented yet.

include/
	* ctf-api.h (ECTF_NEXT_END): New error.
	(ECTF_NEXT_WRONGFUN): Likewise.
	(ECTF_NEXT_WRONGFP): Likewise.
	(ECTF_NERR): Adjust.
	(ctf_next_t): New.
	(ctf_next_create): New prototype.
	(ctf_next_destroy): Likewise.
	(ctf_next_copy): Likewise.
	(ctf_member_next): Likewise.
	(ctf_enum_next): Likewise.
	(ctf_type_next): Likewise.
	(ctf_label_next): Likewise.
	(ctf_variable_next): Likewise.

libctf/
	* ctf-impl.h (ctf_next): New.
	(ctf_get_dict): New prototype.
	* ctf-lookup.c (ctf_get_dict): New, split out of...
	(ctf_lookup_by_id): ... here.
	* ctf-util.c (ctf_next_create): New.
	(ctf_next_destroy): New.
	(ctf_next_copy): New.
	* ctf-types.c (includes): Add <assert.h>.
	(ctf_member_next): New.
	(ctf_enum_next): New.
	(ctf_type_iter): Document the lack of iteration over parent
	types.
	(ctf_type_next): New.
	(ctf_variable_next): New.
	* ctf-archive.c (ctf_archive_next): New.
	* libctf.ver: Add new public functions.
2020-07-22 17:57:50 +01:00

444 lines
12 KiB
C
Raw Blame History

/* Symbol, variable and name lookup.
Copyright (C) 2019-2020 Free Software Foundation, Inc.
This file is part of libctf.
libctf is free software; you can redistribute it and/or modify it under
the terms of the GNU General Public License as published by the Free
Software Foundation; either version 3, or (at your option) any later
version.
This program is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
See the GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; see the file COPYING. If not see
<http://www.gnu.org/licenses/>. */
#include <ctf-impl.h>
#include <elf.h>
#include <string.h>
/* Compare the given input string and length against a table of known C storage
qualifier keywords. We just ignore these in ctf_lookup_by_name, below. To
do this quickly, we use a pre-computed Perfect Hash Function similar to the
technique originally described in the classic paper:
R.J. Cichelli, "Minimal Perfect Hash Functions Made Simple",
Communications of the ACM, Volume 23, Issue 1, January 1980, pp. 17-19.
For an input string S of length N, we use hash H = S[N - 1] + N - 105, which
for the current set of qualifiers yields a unique H in the range [0 .. 20].
The hash can be modified when the keyword set changes as necessary. We also
store the length of each keyword and check it prior to the final strcmp().
TODO: just use gperf. */
static int
isqualifier (const char *s, size_t len)
{
static const struct qual
{
const char *q_name;
size_t q_len;
} qhash[] = {
{"static", 6}, {"", 0}, {"", 0}, {"", 0},
{"volatile", 8}, {"", 0}, {"", 0}, {"", 0}, {"", 0},
{"", 0}, {"auto", 4}, {"extern", 6}, {"", 0}, {"", 0},
{"", 0}, {"", 0}, {"const", 5}, {"register", 8},
{"", 0}, {"restrict", 8}, {"_Restrict", 9}
};
int h = s[len - 1] + (int) len - 105;
const struct qual *qp = &qhash[h];
return (h >= 0 && (size_t) h < sizeof (qhash) / sizeof (qhash[0])
&& (size_t) len == qp->q_len &&
strncmp (qp->q_name, s, qp->q_len) == 0);
}
/* Attempt to convert the given C type name into the corresponding CTF type ID.
It is not possible to do complete and proper conversion of type names
without implementing a more full-fledged parser, which is necessary to
handle things like types that are function pointers to functions that
have arguments that are function pointers, and fun stuff like that.
Instead, this function implements a very simple conversion algorithm that
finds the things that we actually care about: structs, unions, enums,
integers, floats, typedefs, and pointers to any of these named types. */
ctf_id_t
ctf_lookup_by_name (ctf_file_t *fp, const char *name)
{
static const char delimiters[] = " \t\n\r\v\f*";
const ctf_lookup_t *lp;
const char *p, *q, *end;
ctf_id_t type = 0;
ctf_id_t ntype, ptype;
if (name == NULL)
return (ctf_set_errno (fp, EINVAL));
for (p = name, end = name + strlen (name); *p != '\0'; p = q)
{
while (isspace (*p))
p++; /* Skip leading whitespace. */
if (p == end)
break;
if ((q = strpbrk (p + 1, delimiters)) == NULL)
q = end; /* Compare until end. */
if (*p == '*')
{
/* Find a pointer to type by looking in fp->ctf_ptrtab.
If we can't find a pointer to the given type, see if
we can compute a pointer to the type resulting from
resolving the type down to its base type and use
that instead. This helps with cases where the CTF
data includes "struct foo *" but not "foo_t *" and
the user tries to access "foo_t *" in the debugger.
TODO need to handle parent containers too. */
ntype = fp->ctf_ptrtab[LCTF_TYPE_TO_INDEX (fp, type)];
if (ntype == 0)
{
ntype = ctf_type_resolve_unsliced (fp, type);
if (ntype == CTF_ERR
|| (ntype =
fp->ctf_ptrtab[LCTF_TYPE_TO_INDEX (fp, ntype)]) == 0)
{
(void) ctf_set_errno (fp, ECTF_NOTYPE);
goto err;
}
}
type = LCTF_INDEX_TO_TYPE (fp, ntype, (fp->ctf_flags & LCTF_CHILD));
q = p + 1;
continue;
}
if (isqualifier (p, (size_t) (q - p)))
continue; /* Skip qualifier keyword. */
for (lp = fp->ctf_lookups; lp->ctl_prefix != NULL; lp++)
{
/* TODO: This is not MT-safe. */
if ((lp->ctl_prefix[0] == '\0' ||
strncmp (p, lp->ctl_prefix, (size_t) (q - p)) == 0) &&
(size_t) (q - p) >= lp->ctl_len)
{
for (p += lp->ctl_len; isspace (*p); p++)
continue; /* Skip prefix and next whitespace. */
if ((q = strchr (p, '*')) == NULL)
q = end; /* Compare until end. */
while (isspace (q[-1]))
q--; /* Exclude trailing whitespace. */
/* Expand and/or allocate storage for a slice of the name, then
copy it in. */
if (fp->ctf_tmp_typeslicelen >= (size_t) (q - p) + 1)
{
memcpy (fp->ctf_tmp_typeslice, p, (size_t) (q - p));
fp->ctf_tmp_typeslice[(size_t) (q - p)] = '\0';
}
else
{
free (fp->ctf_tmp_typeslice);
fp->ctf_tmp_typeslice = xstrndup (p, (size_t) (q - p));
if (fp->ctf_tmp_typeslice == NULL)
{
(void) ctf_set_errno (fp, ENOMEM);
return CTF_ERR;
}
}
if ((type = ctf_lookup_by_rawhash (fp, lp->ctl_hash,
fp->ctf_tmp_typeslice)) == 0)
{
(void) ctf_set_errno (fp, ECTF_NOTYPE);
goto err;
}
break;
}
}
if (lp->ctl_prefix == NULL)
{
(void) ctf_set_errno (fp, ECTF_NOTYPE);
goto err;
}
}
if (*p != '\0' || type == 0)
return (ctf_set_errno (fp, ECTF_SYNTAX));
return type;
err:
if (fp->ctf_parent != NULL
&& (ptype = ctf_lookup_by_name (fp->ctf_parent, name)) != CTF_ERR)
return ptype;
return CTF_ERR;
}
typedef struct ctf_lookup_var_key
{
ctf_file_t *clvk_fp;
const char *clvk_name;
} ctf_lookup_var_key_t;
/* A bsearch function for variable names. */
static int
ctf_lookup_var (const void *key_, const void *memb_)
{
const ctf_lookup_var_key_t *key = key_;
const ctf_varent_t *memb = memb_;
return (strcmp (key->clvk_name, ctf_strptr (key->clvk_fp, memb->ctv_name)));
}
/* Given a variable name, return the type of the variable with that name. */
ctf_id_t
ctf_lookup_variable (ctf_file_t *fp, const char *name)
{
ctf_varent_t *ent;
ctf_lookup_var_key_t key = { fp, name };
/* This array is sorted, so we can bsearch for it. */
ent = bsearch (&key, fp->ctf_vars, fp->ctf_nvars, sizeof (ctf_varent_t),
ctf_lookup_var);
if (ent == NULL)
{
if (fp->ctf_parent != NULL)
return ctf_lookup_variable (fp->ctf_parent, name);
return (ctf_set_errno (fp, ECTF_NOTYPEDAT));
}
return ent->ctv_type;
}
/* Given a symbol table index, return the name of that symbol from the secondary
string table, or the null string (never NULL). */
const char *
ctf_lookup_symbol_name (ctf_file_t *fp, unsigned long symidx)
{
const ctf_sect_t *sp = &fp->ctf_symtab;
Elf64_Sym sym, *gsp;
if (sp->cts_data == NULL)
{
ctf_set_errno (fp, ECTF_NOSYMTAB);
return _CTF_NULLSTR;
}
if (symidx >= fp->ctf_nsyms)
{
ctf_set_errno (fp, EINVAL);
return _CTF_NULLSTR;
}
if (sp->cts_entsize == sizeof (Elf32_Sym))
{
const Elf32_Sym *symp = (Elf32_Sym *) sp->cts_data + symidx;
gsp = ctf_sym_to_elf64 (symp, &sym);
}
else
gsp = (Elf64_Sym *) sp->cts_data + symidx;
if (gsp->st_name < fp->ctf_str[CTF_STRTAB_1].cts_len)
return (const char *) fp->ctf_str[CTF_STRTAB_1].cts_strs + gsp->st_name;
return _CTF_NULLSTR;
}
/* Given a symbol table index, return the type of the data object described
by the corresponding entry in the symbol table. */
ctf_id_t
ctf_lookup_by_symbol (ctf_file_t *fp, unsigned long symidx)
{
const ctf_sect_t *sp = &fp->ctf_symtab;
ctf_id_t type;
if (sp->cts_data == NULL)
return (ctf_set_errno (fp, ECTF_NOSYMTAB));
if (symidx >= fp->ctf_nsyms)
return (ctf_set_errno (fp, EINVAL));
if (sp->cts_entsize == sizeof (Elf32_Sym))
{
const Elf32_Sym *symp = (Elf32_Sym *) sp->cts_data + symidx;
if (ELF32_ST_TYPE (symp->st_info) != STT_OBJECT)
return (ctf_set_errno (fp, ECTF_NOTDATA));
}
else
{
const Elf64_Sym *symp = (Elf64_Sym *) sp->cts_data + symidx;
if (ELF64_ST_TYPE (symp->st_info) != STT_OBJECT)
return (ctf_set_errno (fp, ECTF_NOTDATA));
}
if (fp->ctf_sxlate[symidx] == -1u)
return (ctf_set_errno (fp, ECTF_NOTYPEDAT));
type = *(uint32_t *) ((uintptr_t) fp->ctf_buf + fp->ctf_sxlate[symidx]);
if (type == 0)
return (ctf_set_errno (fp, ECTF_NOTYPEDAT));
return type;
}
/* Return the native dict of a given type: if called on a child and the
type is in the parent, return the parent. Needed if you plan to access
the type directly, without using the API. */
ctf_file_t *
ctf_get_dict (ctf_file_t *fp, ctf_id_t type)
{
if ((fp->ctf_flags & LCTF_CHILD) && LCTF_TYPE_ISPARENT (fp, type))
return fp->ctf_parent;
return fp;
}
/* Return the pointer to the internal CTF type data corresponding to the
given type ID. If the ID is invalid, the function returns NULL.
This function is not exported outside of the library. */
const ctf_type_t *
ctf_lookup_by_id (ctf_file_t **fpp, ctf_id_t type)
{
ctf_file_t *fp = *fpp; /* Caller passes in starting CTF dict. */
ctf_id_t idx;
if ((fp = ctf_get_dict (fp, type)) == NULL)
{
(void) ctf_set_errno (*fpp, ECTF_NOPARENT);
return NULL;
}
/* If this dict is writable, check for a dynamic type. */
if (fp->ctf_flags & LCTF_RDWR)
{
ctf_dtdef_t *dtd;
if ((dtd = ctf_dynamic_type (fp, type)) != NULL)
{
*fpp = fp;
return &dtd->dtd_data;
}
(void) ctf_set_errno (*fpp, ECTF_BADID);
return NULL;
}
/* Check for a type in the static portion. */
idx = LCTF_TYPE_TO_INDEX (fp, type);
if (idx > 0 && (unsigned long) idx <= fp->ctf_typemax)
{
*fpp = fp; /* Function returns ending CTF container. */
return (LCTF_INDEX_TO_TYPEPTR (fp, idx));
}
(void) ctf_set_errno (*fpp, ECTF_BADID);
return NULL;
}
/* Given a symbol table index, return the info for the function described
by the corresponding entry in the symbol table. */
int
ctf_func_info (ctf_file_t *fp, unsigned long symidx, ctf_funcinfo_t *fip)
{
const ctf_sect_t *sp = &fp->ctf_symtab;
const uint32_t *dp;
uint32_t info, kind, n;
if (sp->cts_data == NULL)
return (ctf_set_errno (fp, ECTF_NOSYMTAB));
if (symidx >= fp->ctf_nsyms)
return (ctf_set_errno (fp, EINVAL));
if (sp->cts_entsize == sizeof (Elf32_Sym))
{
const Elf32_Sym *symp = (Elf32_Sym *) sp->cts_data + symidx;
if (ELF32_ST_TYPE (symp->st_info) != STT_FUNC)
return (ctf_set_errno (fp, ECTF_NOTFUNC));
}
else
{
const Elf64_Sym *symp = (Elf64_Sym *) sp->cts_data + symidx;
if (ELF64_ST_TYPE (symp->st_info) != STT_FUNC)
return (ctf_set_errno (fp, ECTF_NOTFUNC));
}
if (fp->ctf_sxlate[symidx] == -1u)
return (ctf_set_errno (fp, ECTF_NOFUNCDAT));
dp = (uint32_t *) ((uintptr_t) fp->ctf_buf + fp->ctf_sxlate[symidx]);
info = *dp++;
kind = LCTF_INFO_KIND (fp, info);
n = LCTF_INFO_VLEN (fp, info);
if (kind == CTF_K_UNKNOWN && n == 0)
return (ctf_set_errno (fp, ECTF_NOFUNCDAT));
if (kind != CTF_K_FUNCTION)
return (ctf_set_errno (fp, ECTF_CORRUPT));
fip->ctc_return = *dp++;
fip->ctc_argc = n;
fip->ctc_flags = 0;
if (n != 0 && dp[n - 1] == 0)
{
fip->ctc_flags |= CTF_FUNC_VARARG;
fip->ctc_argc--;
}
return 0;
}
/* Given a symbol table index, return the arguments for the function described
by the corresponding entry in the symbol table. */
int
ctf_func_args (ctf_file_t * fp, unsigned long symidx, uint32_t argc,
ctf_id_t * argv)
{
const uint32_t *dp;
ctf_funcinfo_t f;
if (ctf_func_info (fp, symidx, &f) < 0)
return -1; /* errno is set for us. */
/* The argument data is two uint32_t's past the translation table
offset: one for the function info, and one for the return type. */
dp = (uint32_t *) ((uintptr_t) fp->ctf_buf + fp->ctf_sxlate[symidx]) + 2;
for (argc = MIN (argc, f.ctc_argc); argc != 0; argc--)
*argv++ = *dp++;
return 0;
}
Reference in New Issue View Git Blame Copy Permalink